From 5ed5b72f109742660413781c9c4b20650263b0c5 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Sat, 18 Apr 2026 22:14:09 +0300 Subject: [PATCH 01/95] docs: consolidate refactor follow-ups into a single REFACTOR.md MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Single forward-looking reference that replaces the two untracked planning docs (REFACTOR_PLAN.md + REFACTOR_EXECUTION.md) which had become a mix of historical PR timeline and still-relevant decisions. Keeps only what's actionable going forward: - Module tiers, the four registries, and the module distribution model (architecture summary). - Remaining work: Phase 5 (v2 → main) and the modules-branch decision. - Operational patterns worth preserving (standing checks, TDZ rule, branch-sync file-presence diff procedure, prettier drift pattern). - 17 curated open questions across design, distribution, core slotting, and documentation. Canonical references (docs/module-contract.md, docs/architecture.md, etc.) are linked but not duplicated. This doc is transient — retire when the refactor is fully behind us. Co-Authored-By: Claude Opus 4.7 (1M context) --- REFACTOR.md | 175 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 175 insertions(+) create mode 100644 REFACTOR.md diff --git a/REFACTOR.md b/REFACTOR.md new file mode 100644 index 000000000..2ae7f81ec --- /dev/null +++ b/REFACTOR.md @@ -0,0 +1,175 @@ +# NanoClaw Refactor — Forward-Looking Reference + +Consolidates what's still relevant from `REFACTOR_PLAN.md` and `REFACTOR_EXECUTION.md`: open decisions, remaining work, operational patterns worth keeping. Historical PR timeline and phase framing have been dropped — the work is in the commit history. + +--- + +## Architecture (still authoritative) + +### Module tiers + +Three categories, distinguished by shipping model and dependency direction: + +| Tier | Where it lives | Loaded by default? | Removal cost | +|------|----------------|--------------------|--------------| +| **Core** | `src/**` (outside `src/modules/`, `src/channels/`, `src/providers/`) | always | N/A — can't remove | +| **Default modules** | `src/modules//` on main | yes — imported by `src/modules/index.ts` | edit core imports (intentional friction) | +| **Optional modules** | `src/modules//` on main (for now — see open q #7) | yes, via barrel import | delete files + barrel line + revert `MODULE-HOOK` edits | +| **Channel adapters** | `src/channels/.ts` on `channels` branch | no — cherry-pick via `/add-` | delete files + barrel line | +| **Providers** | on `providers` branch | no — cherry-pick via `/add-` | delete files + barrel line | + +Default modules today: `typing`, `mount-security`, `approvals`, `cli`. +Optional modules: `interactive`, `scheduling`, `permissions`, `agent-to-agent`, `self-mod`. + +Dependency rule: **core ← default modules ← optional modules**. Optional modules must not depend on each other. Known transitional violation (flagged): `src/db/messaging-groups.ts` auto-wires `agent_destinations` when agent-to-agent is installed. + +### The four registries + +Full contract in [`docs/module-contract.md`](docs/module-contract.md). Summary: + +1. **Delivery action handlers** — `delivery.ts`; modules call `registerDeliveryAction(name, fn)`. +2. **Router inbound gate** — `router.ts`; single setter (`setSenderResolver` + `setAccessGate`). Default: allow-all. +3. **Response dispatcher** — `response-registry.ts`; modules call `registerResponseHandler(fn)`. First to return `true` claims. +4. **Container MCP tool self-registration** — `container/agent-runner/src/mcp-tools/server.ts`; modules call `registerTools([...])` at import. + +Anything else single-consumer uses either a `sqlite_master`-guarded inline read or a `MODULE-HOOK::start/end` skill edit. + +### Module distribution (pending) + +- **`main`** — core + default modules + default channel (`cli`). Ships clean. +- **`channels`** — fully loaded runnable branch with all channel adapters; skills cherry-pick from it. +- **`providers`** — same pattern for agent providers (OpenCode). +- **`modules` branch** — proposed but NOT created yet. See "Remaining work" below. + +--- + +## Remaining work + +### Phase 5: merge `v2` → `main` + +Cut-over the refactor. Pre-reqs (already met): green build, green tests, green service boot, clean `channels` / `providers` syncs. + +Open logistics: +- Release versioning: bump to `1.3.0` at merge time or cut a `v2-rc` tag first for internal testing? Non-blocking — decide at merge. +- Coordinate with anyone still running the old `main` (v1.2.53) — breaking change for them. +- Announce the new layout + the one shell command that changed (`pnpm run chat` is new default). + +### `modules` branch — create, skip, or defer? + +The original plan (PR #10) was to fork a `modules` branch and populate it with the 5 optional modules, so future `/add-` skills pull via `git show origin/modules:path`. Three paths: + +- **(a) Create it now.** Matches the `channels`/`providers` pattern for consistency. Extra surface to maintain: every core change must be merged into `modules` at phase boundaries (same cadence as channels/providers). Pays off if we ever want to make a module *truly* optional (not shipped on main). +- **(b) Skip it.** Leave all 5 optional modules shipped on main. No `modules` branch, no install skills, no cherry-picking. Simpler but loses the "opt-in" property for users who want a leaner install. +- **(c) Defer.** Ship main without the modules branch; create it later if someone actually wants to slim their install. No-cost option for now. + +Recommendation leans toward (c) — we've already paid the architectural cost (tier boundary, dependency rule, registries) without needing the branch today. + +### Per-module follow-ups (tracked as open questions below) + +Each has a specific landing zone when we get to it: +- #11–13 (admin mechanism, providers registry, container-runner audit) — scope a focused cleanup pass. +- #14 (CLAUDE.md review) — single dedicated PR touching every module. +- #15 (A2A / destinations rethink) — requires design, not just cleanup. +- #17–18 (self-mod rethink, per-group source) — requires design. +- #19 (system vs user CLAUDE.md) — requires install-skill tooling. + +--- + +## Operational patterns (keep using these) + +### Standing checks for every PR + +Non-negotiable; a unit test suite alone doesn't catch circular-import TDZ bugs: + +1. `pnpm run build` clean. +2. `pnpm test` + `bun test` (in `container/agent-runner/`) all green. +3. **Service actually starts.** `gtimeout 5 node dist/index.js` (or `launchctl kickstart`) must reach `NanoClaw running`. Unit tests import individual files; only `main()` exercises the module-init order. +4. Expected boot log lines present (at least: `Central DB ready`, `Delivery polls started`, `Host sweep started`, `NanoClaw running`, plus any module lifecycle line like `OneCLI approval handler started` or `CLI channel listening`). + +### Module architecture rule (TDZ bug, PR #3) + +Any registry state a module writes to at import time must live in a file with **no back-edge to `src/index.ts`** — transitively. `src/index.ts` imports `src/modules/index.js` for side effects; if a module calls `registerX()` at top level and `X` lives in `src/index.ts`, the ES module loader hits a TDZ reference on the const declaration. Fix: registry state lives in its own dependency-free file (e.g. `src/response-registry.ts`). Any new registry follows the same pattern. + +### Branch sync procedure + +After every `v2` (or future `main`) sync into `channels` / `providers` / future `modules`: + +1. **File-presence diff.** Enumerate files that existed pre-sync but are missing post-sync: + ``` + git ls-tree -r | awk '{print $4}' | sort > /tmp/pre.txt + git ls-tree -r | awk '{print $4}' | sort > /tmp/post.txt + comm -23 /tmp/pre.txt /tmp/post.txt + ``` + Classify each missing file: + - **Intentional** (core deleted it) → leave deleted. + - **Branch-owned** (channels branch still needs it) → restore from pre-sync HEAD. + + This has caught real losses on both `channels` (17 adapter files plus 3 setup scripts after PR #2's channel move) and `providers` (opencode files after PR #2). + +2. **Cross-file consistency.** When restoring a file, check whether something *else* that also changed references it (e.g. `setup/index.ts`'s `STEPS` map). + +3. **Run the standing checks** against the synced branch (not just v2). + +### Prettier drift pattern + +The `format:fix` pre-commit hook sometimes reformats peer files *after* the commit completes, leaving cosmetic-only diffs in the working tree. Discard with `git checkout -- `. Do not re-commit the drift — it's trivial whitespace and noise. + +--- + +## Open questions (curated) + +### Design / architecture + +1. **`NANOCLAW_ADMIN_USER_IDS` as the admin mechanism.** Host queries `user_roles` at container wake, collapses into env var, container compares sender IDs. Conflates identity-at-send with privilege-at-wake and forces the container to care about namespaced user IDs. Revisit during a container-runner audit. + +2. **Host-side `src/providers/` registry.** One real consumer (OpenCode). A registry is probably overkill — the install skill could just edit `container-runner.ts` via `MODULE-HOOK`. Fold into the container-runner audit. + +3. **Container-runner audit.** `src/container-runner.ts` has accreted wake/spawn/kill, mount assembly, OneCLI credential application, admin-ID env var, idle timers, image rebuild. Some pieces should pull apart or move into modules. Not blocking. Related to #1 and #2. + +4. **Revisit destinations + A2A capability holistically.** The destination projection invariant, dual-purpose routing+ACL table, channel vs agent destination shapes, `createMessagingGroupAgent` auto-wire coupling — more machinery than the feature warrants. Phase 3 moved it out of core intact; a redesign is warranted but scoped post-refactor. + +5. **Self-mod approach rethink.** Three separate MCP tools + three delivery actions + three approval handlers for what's essentially "mutate container.config.json and rebuild." Also: post-rebuild latency (host sweep waits up to 60s), and agents sometimes send redundant `add_mcp_server` + `request_rebuild` pairs. Consider collapsing into a single "apply this container-config diff" approval primitive. + +6. **Per-agent-group source / per-group base image.** Self-mod today layers packages/MCP on a shared base. As groups diverge (different base images, provider configs, runtime toolchains), the shared-base assumption won't scale. Scope post-refactor. + +### Distribution / operational + +7. **Providers on a consolidated `modules` branch?** Staying separate for now. Revisit if a second optional provider appears. + +8. **Per-group module enablement.** Modules are currently project-wide. If one agent group wants approvals and another doesn't, we'd need per-group feature flags. Flag if asked. + +9. **Module removal UX.** We do not drop tables on uninstall. Is that the right default? (Alternative: `/remove-` optionally runs a down migration. YAGNI until requested.) + +10. **Cross-module ordering for the response dispatcher.** Registration order determines who claims a given `questionId`. IDs are disjoint in practice (`q-…` vs `appr-…`), so first-match-wins is safe. If a third response-consuming module arrives, we may need keyed dispatch. + +11. **Versioned module migrations.** Reinstalls are idempotent (migrator skips anything already in `schema_version`). If a module ships a *new* migration in a later version, the install skill must append the new file + barrel entry without touching prior ones. Simplest rule: install skills are additive; content changes to an already-applied migration are a hard error. + +12. **Telegram pairing imports from permissions (channels branch).** `src/channels/telegram.ts` reaches into `src/modules/permissions/db/*` for `grantRole`/`hasAnyOwner`/`upsertUser` in the pairing-bootstrap branch. Cross-branch tier violation. Fix: extract those writes into a pairing helper (e.g. `src/channels/telegram-pairing-accept.ts` or `setup/pair-telegram.ts`). Non-blocking. + +### Core slotting (files not explicitly discussed) + +13. **`state-sqlite.ts`, `webhook-server.ts`, `timezone.ts`.** state-sqlite is likely core (host tracker). Webhook-server likely core (channel infra). Timezone likely core utility. Confirm if any of them prove to be module-shaped during future audits. + +14. **Chat SDK bridge location.** `src/channels/chat-sdk-bridge.ts` is channel infra that bridges adapters on the `channels` branch. Stays in `src/channels/` for now. + +15. **OneCLI credential injection.** Lives in `container-runner.ts`. Every agent call uses it, no clean optional boundary. Stays core. Related: `onecli-approvals.ts` is bundled inside the `approvals` default module on the assumption OneCLI stays in core. If OneCLI later moves to its own module, `onecli-approvals` follows. + +### Documentation + +16. **CLAUDE.md content per module.** Every module ships with project.md + agent.md. Need a dedicated review pass: (a) write the missing agent-to-agent snippets, (b) audit other modules for accuracy/tone, (c) confirm `agent.md` files are actually tailored for the agent vs. copy-pastes of `project.md`. + +17. **Split system CLAUDE.md from user CLAUDE.md.** Project `CLAUDE.md` and `groups/global/CLAUDE.md` mix system-authored content (module contracts, install-skill appends) with user customizations. Updates currently risk clobbering user intent. Look at a system-owned region (or separate file) that skills rewrite freely plus a user-owned one that's never touched. Related to #16. + +--- + +## Where the canonical references live + +- **Module contract** — [`docs/module-contract.md`](docs/module-contract.md) +- **Architecture overview** — [`docs/architecture.md`](docs/architecture.md) +- **DB layout** — [`docs/db.md`](docs/db.md), [`docs/db-central.md`](docs/db-central.md), [`docs/db-session.md`](docs/db-session.md) +- **Agent-runner internals** — [`docs/agent-runner-details.md`](docs/agent-runner-details.md) +- **Channel isolation model** — [`docs/isolation-model.md`](docs/isolation-model.md) +- **Build + runtime split** — [`docs/build-and-runtime.md`](docs/build-and-runtime.md) +- **Top-level** — [`CLAUDE.md`](CLAUDE.md) + +This doc (`REFACTOR.md`) is transient — prune when open questions close; retire entirely once the refactor is fully behind us and the operational patterns have been absorbed into `CLAUDE.md` or `docs/`. From 47e320380971fb173470ef1ceab34e7c4d5e6e79 Mon Sep 17 00:00:00 2001 From: Bryan Lozano Date: Sun, 19 Apr 2026 01:11:46 -0700 Subject: [PATCH 02/95] feat: add /add-ollama-provider skill and docs/ollama.md MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adds a new operational skill that routes any agent group to a local Ollama instance instead of the Anthropic API. Ollama speaks the Anthropic /v1/messages endpoint natively, so no new provider code is needed — just env var overrides and a model setting in the shared settings file. The skill also documents and applies two prerequisite source changes: - ContainerConfig gains env and blockedHosts fields (container-config.ts) - container-runner wires those fields as -e and --add-host Docker flags - Dockerfile home dir set to chmod 777 so containers running as the host uid can write ~/.claude config (discovered during implementation) docs/ollama.md covers the architecture, OneCLI proxy bypass rationale, network isolation via blockedHosts, model selection tradeoffs for Apple Silicon, and revert instructions. Co-Authored-By: Claude Sonnet 4.6 --- .claude/skills/add-ollama-provider/SKILL.md | 179 ++++++++++++++++++++ docs/ollama.md | 88 ++++++++++ 2 files changed, 267 insertions(+) create mode 100644 .claude/skills/add-ollama-provider/SKILL.md create mode 100644 docs/ollama.md diff --git a/.claude/skills/add-ollama-provider/SKILL.md b/.claude/skills/add-ollama-provider/SKILL.md new file mode 100644 index 000000000..83f7e5ae6 --- /dev/null +++ b/.claude/skills/add-ollama-provider/SKILL.md @@ -0,0 +1,179 @@ +--- +name: add-ollama-provider +description: Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run their agent locally, cut API costs, or experiment with open-weight models. See docs/ollama.md for background. +--- + +# Add Ollama Provider + +Routes an agent group to a local Ollama instance instead of the Anthropic API. +See `docs/ollama.md` for how this works and the tradeoffs involved. + +## Prerequisites + +1. **Ollama is installed and running** on the host — verify: `curl -s http://localhost:11434/api/tags` +2. **A model is pulled** — e.g. `ollama pull gemma4` or `ollama pull qwen3-coder` +3. **The agent group already exists** — run `/init-first-agent` first if needed + +## 1. Check source support + +The feature requires two fields in `ContainerConfig` (`env` and `blockedHosts`) and their +corresponding wiring in `container-runner.ts`. Check if already present: + +```bash +grep -c 'blockedHosts' src/container-config.ts src/container-runner.ts +``` + +If either count is 0, apply the changes in steps 1a and 1b. Otherwise skip to step 2. + +### 1a. Extend ContainerConfig + +In `src/container-config.ts`, add to the `ContainerConfig` interface: + +```typescript +env?: Record; +blockedHosts?: string[]; +``` + +And in `readContainerConfig`, add inside the returned object: + +```typescript +env: raw.env, +blockedHosts: raw.blockedHosts, +``` + +### 1b. Wire into container-runner + +In `src/container-runner.ts`, after the `NANOCLAW_MCP_SERVERS` block, add: + +```typescript +// Per-agent-group env overrides — applied last to win over OneCLI values. +if (containerConfig.env) { + for (const [key, value] of Object.entries(containerConfig.env)) { + args.push('-e', `${key}=${value}`); + } +} + +// Blocked hosts: resolve to 0.0.0.0 so they are unreachable inside the container. +if (containerConfig.blockedHosts) { + for (const host of containerConfig.blockedHosts) { + args.push('--add-host', `${host}:0.0.0.0`); + } +} +``` + +### 1c. Fix home directory permissions (if not already done) + +The container may run as your host uid (not uid 1000). Check the Dockerfile: + +```bash +grep 'chmod.*home/node' container/Dockerfile +``` + +If it shows `chmod 755`, change it to `chmod 777` so any uid can write there. +Then rebuild the container image: `./container/build.sh` + +## 2. Identify the setup + +Ask the user (plain text, not AskUserQuestion): + +1. **Which agent group?** List available groups: `sqlite3 data/v2.db "SELECT folder, name FROM agent_groups;"` +2. **Which Ollama model?** List available: `curl -s http://localhost:11434/api/tags | grep '"name"'` +3. **Block Anthropic API?** Recommended yes — prevents accidental spend if config drifts. + +Record as `FOLDER`, `MODEL`, and `BLOCK_ANTHROPIC`. + +## 3. Configure container.json + +Read `groups//container.json`. Add (or merge into) an `env` block and optionally `blockedHosts`: + +```json +{ + "env": { + "ANTHROPIC_BASE_URL": "http://host.docker.internal:11434", + "ANTHROPIC_API_KEY": "ollama", + "NO_PROXY": "host.docker.internal", + "no_proxy": "host.docker.internal" + }, + "blockedHosts": ["api.anthropic.com"] +} +``` + +Omit `blockedHosts` if the user declined step 2. + +**Why these vars:** `ANTHROPIC_BASE_URL` redirects the Anthropic SDK to Ollama. +`ANTHROPIC_API_KEY=ollama` satisfies the SDK's key requirement (Ollama ignores it). +`NO_PROXY` bypasses the OneCLI HTTPS proxy for requests to `host.docker.internal` +so they reach Ollama directly instead of going through the credential gateway. + +## 4. Set the model + +Read the agent group's shared Claude settings: + +```bash +# Find the agent group ID +AG_ID=$(sqlite3 data/v2.db "SELECT id FROM agent_groups WHERE folder='';") +SETTINGS=data/v2-sessions/$AG_ID/.claude-shared/settings.json +``` + +Add `"model": ""` to that settings file. Create the file if it doesn't exist: + +```json +{ + "model": "gemma4:latest" +} +``` + +If the file already has content, merge the `model` key in — don't overwrite existing keys. + +**Why here and not container.json:** Claude Code reads its model from its own settings +file, not from env vars. This file is bind-mounted into the container as `~/.claude/settings.json`. + +## 5. Build and restart + +```bash +export PATH="/opt/homebrew/bin:$PATH" +pnpm run build +launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist +launchctl load ~/Library/LaunchAgents/com.nanoclaw.plist +# Linux: systemctl --user restart nanoclaw +``` + +## 6. Verify + +Send a message to the agent. Then confirm: + +```bash +# Ollama shows the model as active +curl -s http://localhost:11434/api/ps | grep '"name"' + +# Container has the right env vars +CTR=$(docker ps --filter "name=nanoclaw-v2-" --format "{{.Names}}" | head -1) +docker inspect "$CTR" --format '{{json .HostConfig.ExtraHosts}}' +docker exec "$CTR" env | grep ANTHROPIC +``` + +Expected: `api.anthropic.com:0.0.0.0` in ExtraHosts, `ANTHROPIC_BASE_URL=http://host.docker.internal:11434`. + +## Reverting to Claude + +To switch back to the Anthropic API: + +1. Remove the `env` and `blockedHosts` keys from `groups//container.json` +2. Remove `"model"` from the shared settings file +3. Restart the service + +No rebuild needed — both files are read at container spawn time. + +## Troubleshooting + +**Agent hangs, no response:** Ollama may be loading the model cold (large models take 10–30s). +Watch `curl -s http://localhost:11434/api/ps` — the model appears once loaded. + +**"model not found" error in container logs:** The model name in settings.json doesn't match +what Ollama has. Run `ollama list` on the host and use the exact name shown. + +**Responses claim to be Claude:** The model was trained on data that includes Claude conversations. +Add a line to `groups//CLAUDE.md` telling it what model it runs on. + +**Agent responds but Ollama shows no activity:** `NO_PROXY` may not have taken effect for +`http_proxy` (lowercase). Add both `NO_PROXY` and `no_proxy` to the env block. diff --git a/docs/ollama.md b/docs/ollama.md new file mode 100644 index 000000000..0ea025393 --- /dev/null +++ b/docs/ollama.md @@ -0,0 +1,88 @@ +# Running Agents on Local Ollama + +NanoClaw agents can be routed to a local [Ollama](https://ollama.com) instance instead of the Anthropic API. This cuts API costs to zero and keeps all inference on your hardware. + +## How It Works + +Ollama exposes an Anthropic-compatible `/v1/messages` endpoint. The Claude Code CLI (which runs inside agent containers) uses the Anthropic SDK, which reads `ANTHROPIC_BASE_URL` to find the API host. Pointing that variable at Ollama is all that's needed — no new provider code, no changes to the agent runtime. + +``` +┌─────────────────────────────┐ +│ Agent container │ +│ │ +│ Claude Code CLI │ +│ ↓ ANTHROPIC_BASE_URL │ +│ http://host.docker. │ ┌──────────────────┐ +│ internal:11434 ───────┼─────▶│ Ollama :11434 │ +│ │ │ gemma4:latest │ +└─────────────────────────────┘ └──────────────────┘ +``` + +`host.docker.internal` is Docker's magic hostname that resolves to the host machine from inside a container — so Ollama running on your Mac or Linux box is reachable at that address. + +## The OneCLI Complication + +NanoClaw normally runs API calls through an OneCLI HTTPS proxy that injects real credentials in place of a placeholder key. When redirecting to Ollama you need to bypass that proxy so requests go direct. Two env vars handle this: + +- `NO_PROXY=host.docker.internal` — tells the Anthropic SDK's HTTP client to skip the proxy for that hostname +- `no_proxy=host.docker.internal` — lowercase variant for tools that check the lowercase form + +Both are set in the agent group's `container.json` alongside `ANTHROPIC_BASE_URL`. + +## Network Isolation + +Setting `ANTHROPIC_BASE_URL` redirects requests but doesn't prevent a misconfigured agent from accidentally reaching `api.anthropic.com` directly. The `blockedHosts` field in `container.json` adds a Docker `--add-host` flag that resolves the domain to `0.0.0.0`, making it physically unreachable from inside the container: + +```json +"blockedHosts": ["api.anthropic.com"] +``` + +With this in place, even if the model setting drifts back to a Claude model name, the API call will fail immediately rather than silently billing your account. + +## Model Selection + +The Claude Code CLI reads its model from `~/.claude/settings.json` inside the container, which NanoClaw bind-mounts from `data/v2-sessions//.claude-shared/settings.json`. Set `"model": "gemma4:latest"` (or whatever Ollama model you've pulled) there. Use the exact name from `ollama list`. + +Model selection considerations for Apple Silicon: + +| Model | Size | Quality | Speed (M4 Pro) | +|-------|------|---------|----------------| +| `gemma4:latest` | 12B | Good general-purpose | Fast | +| `qwen3-coder:latest` | 32B | Excellent for coding tasks | Moderate | +| `llama3.2:latest` | 3B | Basic | Very fast | + +The agent uses tool calls extensively (read/write files, shell commands). Models that support tool use reliably work best. Gemma 4 and Qwen 3 Coder both handle structured tool calls well. + +## What Changes at the Code Level + +Three files need to support this feature. See `/add-ollama-provider` for the exact changes. + +**`src/container-config.ts`** — `ContainerConfig` interface needs `env` and `blockedHosts` fields so the per-group JSON can carry them. + +**`src/container-runner.ts`** — At container spawn time, `env` entries become `-e KEY=VAL` Docker flags (applied after OneCLI's injected vars so they win), and `blockedHosts` entries become `--add-host HOST:0.0.0.0` flags. + +**`container/Dockerfile`** — The container runs as the host user's uid (e.g. 501 on macOS), not as the `node` user (uid 1000). The home directory must be `chmod 777` so any uid can write `~/.claude.json` and `~/.claude/settings.json`. + +## Tradeoffs + +| | Ollama (local) | Anthropic API | +|---|---|---| +| Cost | Free | Pay-per-token | +| Privacy | Fully local | Data sent to Anthropic | +| Model quality | Good (open-weight) | Excellent (Claude) | +| Cold start | 5–30s (model load) | ~1s | +| Context window | Varies by model | 200k tokens (Sonnet) | +| Tool use reliability | Good (large models) | Excellent | +| Hardware req. | 16GB+ RAM | None | + +For personal automation on capable hardware, the tradeoff favors local. For complex multi-step tasks requiring large context or high reliability, Claude is still ahead. + +## Reverting to Claude + +Remove the `env` and `blockedHosts` keys from `groups//container.json`, remove `"model"` from the shared settings file, and restart the service. No rebuild needed. + +## See Also + +- `/add-ollama-provider` — step-by-step skill to configure any agent group for Ollama +- [Ollama Anthropic compatibility docs](https://ollama.com/blog/openai-compatibility) — upstream docs on the API bridge +- `docs/architecture.md` — how the container spawn and env injection pipeline works From 01389ff8fc9eb9d41d8a230d890d1940416ea477 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Sun, 19 Apr 2026 10:43:35 +0000 Subject: [PATCH 03/95] feat(new-setup): add onecli, auth, and cli-agent dispatcher steps Aggregates the loose OneCLI install, secret registration, and first-agent wiring commands from /setup into three new dispatcher steps. Adds --cli-only mode to init-first-agent so /new-setup can reach a working 2-way CLI chat with the bare minimum. - setup/onecli.ts: idempotent install + PATH + api-host + .env, polls /health - setup/auth.ts: --check verifies secret; --create --value registers it - setup/cli-agent.ts: wraps init-first-agent --cli-only - scripts/init-first-agent.ts: --cli-only mode; DM mode unchanged Co-Authored-By: Claude Opus 4.7 (1M context) --- scripts/init-first-agent.ts | 231 +++++++++++++++++++++++------------- setup/auth.ts | 186 +++++++++++++++++++++++++++++ setup/cli-agent.ts | 100 ++++++++++++++++ setup/index.ts | 3 + setup/onecli.ts | 194 ++++++++++++++++++++++++++++++ 5 files changed, 631 insertions(+), 83 deletions(-) create mode 100644 setup/auth.ts create mode 100644 setup/cli-agent.ts create mode 100644 setup/onecli.ts diff --git a/scripts/init-first-agent.ts b/scripts/init-first-agent.ts index efb3b6bdb..c40f07f93 100644 --- a/scripts/init-first-agent.ts +++ b/scripts/init-first-agent.ts @@ -1,15 +1,26 @@ /** - * Init the first (or Nth) NanoClaw v2 agent for a DM channel. + * Init the first (or Nth) NanoClaw v2 agent. + * + * Two modes: + * + * 1. **DM channel mode** (default): wires a real DM channel (discord, telegram, + * etc.) + the CLI channel to the same agent, stages a welcome into the DM + * session so the agent greets the operator over that channel. + * + * 2. **CLI-only mode** (`--cli-only`): wires only the CLI channel. Used by + * `/new-setup` to get to a working 2-way CLI chat with the bare minimum. + * Owner grant uses a synthetic `cli:local` user so admin-gated flows work. * * Creates/reuses: user, owner grant (if none), agent group + filesystem, - * DM messaging group, wiring, session. Stages a system welcome message so - * the host sweep wakes the container and the agent DMs the operator via + * messaging group(s), wiring, session. Stages a system welcome message so + * the host sweep wakes the container and the agent sends the greeting via * the normal delivery path. * * Runs alongside the service (WAL-mode sqlite) — does NOT initialize * channel adapters, so there's no Gateway conflict. * * Usage: + * # DM mode * pnpm exec tsx scripts/init-first-agent.ts \ * --channel discord \ * --user-id discord:1470183333427675709 \ @@ -18,6 +29,12 @@ * [--agent-name "Andy"] \ * [--welcome "System instruction: ..."] * + * # CLI-only mode + * pnpm exec tsx scripts/init-first-agent.ts --cli-only \ + * --display-name "Gavriel" \ + * [--agent-name "Andy"] \ + * [--welcome "System instruction: ..."] + * * For direct-addressable channels (telegram, whatsapp, etc.), --platform-id * is typically the same as the handle in --user-id, with the channel prefix. */ @@ -38,9 +55,10 @@ import { grantRole, hasAnyOwner } from '../src/modules/permissions/db/user-roles import { upsertUser } from '../src/modules/permissions/db/users.js'; import { initGroupFilesystem } from '../src/group-init.js'; import { resolveSession, writeSessionMessage } from '../src/session-manager.js'; -import type { AgentGroup } from '../src/types.js'; +import type { AgentGroup, MessagingGroup } from '../src/types.js'; interface Args { + cliOnly: boolean; channel: string; userId: string; platformId: string; @@ -52,12 +70,19 @@ interface Args { const DEFAULT_WELCOME = 'System instruction: run /welcome to introduce yourself to the user on this new channel.'; +const CLI_CHANNEL = 'cli'; +const CLI_PLATFORM_ID = 'local'; +const CLI_SYNTHETIC_USER_ID = `${CLI_CHANNEL}:${CLI_PLATFORM_ID}`; + function parseArgs(argv: string[]): Args { - const out: Partial = {}; + const out: Partial = { cliOnly: false }; for (let i = 0; i < argv.length; i++) { const key = argv[i]; const val = argv[i + 1]; switch (key) { + case '--cli-only': + out.cliOnly = true; + break; case '--channel': out.channel = (val ?? '').toLowerCase(); i++; @@ -85,7 +110,26 @@ function parseArgs(argv: string[]): Args { } } - const required: (keyof Args)[] = ['channel', 'userId', 'platformId', 'displayName']; + if (!out.displayName) { + console.error('Missing required arg: --display-name'); + console.error('See scripts/init-first-agent.ts header for usage.'); + process.exit(2); + } + + if (out.cliOnly) { + // CLI-only: channel/user/platform default to the synthetic local CLI identity. + return { + cliOnly: true, + channel: CLI_CHANNEL, + userId: CLI_SYNTHETIC_USER_ID, + platformId: CLI_PLATFORM_ID, + displayName: out.displayName, + agentName: out.agentName?.trim() || out.displayName, + welcome: out.welcome?.trim() || DEFAULT_WELCOME, + }; + } + + const required: (keyof Args)[] = ['channel', 'userId', 'platformId']; const missing = required.filter((k) => !out[k]); if (missing.length) { console.error(`Missing required args: ${missing.map((k) => `--${k.replace(/([A-Z])/g, '-$1').toLowerCase()}`).join(', ')}`); @@ -94,11 +138,12 @@ function parseArgs(argv: string[]): Args { } return { + cliOnly: false, channel: out.channel!, userId: out.userId!, platformId: out.platformId!, - displayName: out.displayName!, - agentName: out.agentName?.trim() || out.displayName!, + displayName: out.displayName, + agentName: out.agentName?.trim() || out.displayName, welcome: out.welcome?.trim() || DEFAULT_WELCOME, }; } @@ -115,6 +160,48 @@ function generateId(prefix: string): string { return `${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; } +function ensureCliMessagingGroup(now: string): MessagingGroup { + let cliMg = getMessagingGroupByPlatform(CLI_CHANNEL, CLI_PLATFORM_ID); + if (cliMg) return cliMg; + + cliMg = { + id: generateId('mg'), + channel_type: CLI_CHANNEL, + platform_id: CLI_PLATFORM_ID, + name: 'Local CLI', + is_group: 0, + unknown_sender_policy: 'public', + created_at: now, + }; + createMessagingGroup(cliMg); + console.log(`Created CLI messaging group: ${cliMg.id}`); + return cliMg; +} + +function wireIfMissing( + mg: MessagingGroup, + ag: AgentGroup, + now: string, + label: string, +): void { + const existing = getMessagingGroupAgentByPair(mg.id, ag.id); + if (existing) { + console.log(`Wiring already exists: ${existing.id} (${label})`); + return; + } + createMessagingGroupAgent({ + id: generateId('mga'), + messaging_group_id: mg.id, + agent_group_id: ag.id, + trigger_rules: null, + response_scope: 'all', + session_mode: 'shared', + priority: 0, + created_at: now, + }); + console.log(`Wired ${label}: ${mg.id} -> ${ag.id}`); +} + async function main(): Promise { const args = parseArgs(process.argv.slice(2)); @@ -123,7 +210,8 @@ async function main(): Promise { const now = new Date().toISOString(); - // 1. User + (conditional) owner grant + // 1. User + (conditional) owner grant. + // In cli-only mode, the synthetic `cli:local` user becomes the first owner. const userId = namespacedUserId(args.channel, args.userId); upsertUser({ id: userId, @@ -145,7 +233,9 @@ async function main(): Promise { } // 2. Agent group + filesystem - const folder = `dm-with-${normalizeName(args.displayName)}`; + const folder = args.cliOnly + ? `cli-with-${normalizeName(args.displayName)}` + : `dm-with-${normalizeName(args.displayName)}`; let ag: AgentGroup | undefined = getAgentGroupByFolder(folder); if (!ag) { const agId = generateId('ag'); @@ -168,54 +258,54 @@ async function main(): Promise { 'When you receive a system welcome prompt, introduce yourself briefly and invite them to chat. Keep replies concise.', }); - // 3. DM messaging group - const platformId = namespacedPlatformId(args.channel, args.platformId); - let mg = getMessagingGroupByPlatform(args.channel, platformId); - if (!mg) { - const mgId = generateId('mg'); - createMessagingGroup({ - id: mgId, - channel_type: args.channel, - platform_id: platformId, - name: args.displayName, - is_group: 0, - unknown_sender_policy: 'strict', - created_at: now, - }); - mg = getMessagingGroupByPlatform(args.channel, platformId)!; - console.log(`Created messaging group: ${mg.id} (${platformId})`); + // 3. Primary messaging group + wiring + welcome session. + // In DM mode: the DM messaging group is primary, CLI is wired as a bonus. + // In cli-only mode: the CLI messaging group is primary; no DM group. + const cliMg = ensureCliMessagingGroup(now); + + let primaryMg: MessagingGroup; + if (args.cliOnly) { + primaryMg = cliMg; } else { - console.log(`Reusing messaging group: ${mg.id} (${platformId})`); + const platformId = namespacedPlatformId(args.channel, args.platformId); + let dmMg = getMessagingGroupByPlatform(args.channel, platformId); + if (!dmMg) { + const mgId = generateId('mg'); + createMessagingGroup({ + id: mgId, + channel_type: args.channel, + platform_id: platformId, + name: args.displayName, + is_group: 0, + unknown_sender_policy: 'strict', + created_at: now, + }); + dmMg = getMessagingGroupByPlatform(args.channel, platformId)!; + console.log(`Created messaging group: ${dmMg.id} (${platformId})`); + } else { + console.log(`Reusing messaging group: ${dmMg.id} (${platformId})`); + } + primaryMg = dmMg; } - // 4. Wire (auto-creates the companion agent_destinations row) - const existingMga = getMessagingGroupAgentByPair(mg.id, ag.id); - if (!existingMga) { - createMessagingGroupAgent({ - id: generateId('mga'), - messaging_group_id: mg.id, - agent_group_id: ag.id, - trigger_rules: null, - response_scope: 'all', - session_mode: 'shared', - priority: 0, - created_at: now, - }); - console.log(`Wired ${mg.id} -> ${ag.id}`); - } else { - console.log(`Wiring already exists: ${existingMga.id}`); + // Wire primary (DM or CLI), auto-creates companion agent_destinations row. + wireIfMissing(primaryMg, ag, now, args.cliOnly ? 'cli' : 'dm'); + + // In DM mode also wire CLI so `pnpm run chat` works immediately. + if (!args.cliOnly) { + wireIfMissing(cliMg, ag, now, 'cli-bonus'); } - // 5. Session + staged welcome message - const { session, created } = resolveSession(ag.id, mg.id, null, 'shared'); + // 4. Session + staged welcome (on the primary messaging group) + const { session, created } = resolveSession(ag.id, primaryMg.id, null, 'shared'); console.log(`${created ? 'Created' : 'Reusing'} session: ${session.id}`); writeSessionMessage(ag.id, session.id, { id: generateId('sys-welcome'), kind: 'chat', timestamp: now, - platformId: mg.platform_id, - channelType: args.channel, + platformId: primaryMg.platform_id, + channelType: primaryMg.channel_type, threadId: null, content: JSON.stringify({ text: args.welcome, @@ -224,48 +314,23 @@ async function main(): Promise { }), }); - // 6. Wire the CLI channel to the same agent so the user can `pnpm run chat` - // immediately. CLI ships with main and is always available — separate - // messaging_group from the DM channel, so the two don't share a session. - const CLI_PLATFORM_ID = 'local'; - let cliMg = getMessagingGroupByPlatform('cli', CLI_PLATFORM_ID); - if (!cliMg) { - cliMg = { - id: generateId('mg'), - channel_type: 'cli', - platform_id: CLI_PLATFORM_ID, - name: 'Local CLI', - is_group: 0, - unknown_sender_policy: 'public', - created_at: now, - }; - createMessagingGroup(cliMg); - console.log(`Created CLI messaging group: ${cliMg.id}`); - } - const existingCliMga = getMessagingGroupAgentByPair(cliMg.id, ag.id); - if (!existingCliMga) { - createMessagingGroupAgent({ - id: generateId('mga'), - messaging_group_id: cliMg.id, - agent_group_id: ag.id, - trigger_rules: null, - response_scope: 'all', - session_mode: 'shared', - priority: 0, - created_at: now, - }); - console.log(`Wired cli/${CLI_PLATFORM_ID} -> ${ag.id}`); - } - console.log(''); console.log('Init complete.'); console.log(` owner: ${userId}${promotedToOwner ? ' (promoted on first owner)' : ''}`); console.log(` agent: ${ag.name} [${ag.id}] @ groups/${folder}`); - console.log(` channel: ${args.channel} ${platformId}`); + if (args.cliOnly) { + console.log(` channel: cli/${CLI_PLATFORM_ID}`); + } else { + console.log(` channel: ${args.channel} ${primaryMg.platform_id}`); + console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``); + } console.log(` session: ${session.id}`); - console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``); console.log(''); - console.log('Host sweep (<=60s) will wake the container and the agent will send the welcome DM.'); + console.log( + args.cliOnly + ? 'Host sweep (<=60s) will wake the container. Try `pnpm run chat hi`.' + : 'Host sweep (<=60s) will wake the container and the agent will send the welcome DM.', + ); } main().catch((err) => { diff --git a/setup/auth.ts b/setup/auth.ts new file mode 100644 index 000000000..14e27b042 --- /dev/null +++ b/setup/auth.ts @@ -0,0 +1,186 @@ +/** + * Step: auth — Verify or register an Anthropic credential in OneCLI. + * + * Modes: + * --check (default) Verify an Anthropic secret exists. + * --create --value Create an Anthropic secret. Errors if one + * already exists unless --force is passed. + * + * The actual user-facing prompt (subscription vs API key, paste the token) + * stays in the /new-setup SKILL.md. This step is just the machine side: + * it calls `onecli secrets list` / `onecli secrets create` and emits a + * structured status block. The token value is never logged. + */ +import { execFileSync } from 'child_process'; +import os from 'os'; +import path from 'path'; + +import { log } from '../src/log.js'; +import { emitStatus } from './status.js'; + +const LOCAL_BIN = path.join(os.homedir(), '.local', 'bin'); + +interface Args { + mode: 'check' | 'create'; + value?: string; + force: boolean; +} + +function childEnv(): NodeJS.ProcessEnv { + const parts = [LOCAL_BIN]; + if (process.env.PATH) parts.push(process.env.PATH); + return { ...process.env, PATH: parts.join(path.delimiter) }; +} + +function parseArgs(args: string[]): Args { + let mode: 'check' | 'create' = 'check'; + let value: string | undefined; + let force = false; + + for (let i = 0; i < args.length; i++) { + const key = args[i]; + const val = args[i + 1]; + switch (key) { + case '--check': + mode = 'check'; + break; + case '--create': + mode = 'create'; + break; + case '--value': + value = val; + i++; + break; + case '--force': + force = true; + break; + } + } + + if (mode === 'create' && !value) { + emitStatus('AUTH', { + STATUS: 'failed', + ERROR: 'missing_value_for_create', + LOG: 'logs/setup.log', + }); + process.exit(2); + } + + return { mode, value, force }; +} + +interface OnecliSecret { + id: string; + name: string; + type: string; + hostPattern: string | null; +} + +function listSecrets(): OnecliSecret[] { + const out = execFileSync('onecli', ['secrets', 'list'], { + encoding: 'utf-8', + env: childEnv(), + stdio: ['ignore', 'pipe', 'ignore'], + }); + const parsed = JSON.parse(out) as { data?: unknown }; + return Array.isArray(parsed.data) ? (parsed.data as OnecliSecret[]) : []; +} + +function findAnthropicSecret(secrets: OnecliSecret[]): OnecliSecret | undefined { + return secrets.find((s) => s.type === 'anthropic'); +} + +function createAnthropicSecret(value: string): void { + // `value` is a credential — do not log it, do not echo, do not pass through a shell. + execFileSync( + 'onecli', + [ + 'secrets', + 'create', + '--name', + 'Anthropic', + '--type', + 'anthropic', + '--value', + value, + '--host-pattern', + 'api.anthropic.com', + ], + { + env: childEnv(), + stdio: ['ignore', 'ignore', 'pipe'], + }, + ); +} + +export async function run(args: string[]): Promise { + const { mode, value, force } = parseArgs(args); + + let secrets: OnecliSecret[]; + try { + secrets = listSecrets(); + } catch (err) { + log.error('onecli secrets list failed', { err }); + emitStatus('AUTH', { + STATUS: 'failed', + ERROR: 'onecli_list_failed', + HINT: 'Is OneCLI running? Run `/new-setup` from the onecli step.', + LOG: 'logs/setup.log', + }); + process.exit(1); + } + + const existing = findAnthropicSecret(secrets); + + if (mode === 'check') { + emitStatus('AUTH', { + SECRET_PRESENT: !!existing, + ANTHROPIC_OK: !!existing, + STATUS: existing ? 'success' : 'missing', + ...(existing ? { SECRET_NAME: existing.name, SECRET_ID: existing.id } : {}), + LOG: 'logs/setup.log', + }); + return; + } + + // mode === 'create' + if (existing && !force) { + emitStatus('AUTH', { + SECRET_PRESENT: true, + STATUS: 'skipped', + REASON: 'anthropic_secret_already_exists', + SECRET_NAME: existing.name, + SECRET_ID: existing.id, + HINT: 'Re-run with --force to replace, or delete the existing secret first.', + LOG: 'logs/setup.log', + }); + return; + } + + try { + createAnthropicSecret(value!); + } catch (err) { + const e = err as { stderr?: string | Buffer; status?: number }; + const stderr = typeof e.stderr === 'string' ? e.stderr : e.stderr?.toString('utf-8') ?? ''; + log.error('onecli secrets create failed', { status: e.status, stderr }); + emitStatus('AUTH', { + STATUS: 'failed', + ERROR: 'onecli_create_failed', + EXIT_CODE: e.status ?? -1, + LOG: 'logs/setup.log', + }); + process.exit(1); + } + + // Re-verify + const updated = findAnthropicSecret(listSecrets()); + + emitStatus('AUTH', { + SECRET_PRESENT: !!updated, + ANTHROPIC_OK: !!updated, + CREATED: true, + STATUS: updated ? 'success' : 'failed', + ...(updated ? { SECRET_NAME: updated.name, SECRET_ID: updated.id } : {}), + LOG: 'logs/setup.log', + }); +} diff --git a/setup/cli-agent.ts b/setup/cli-agent.ts new file mode 100644 index 000000000..e5a901dda --- /dev/null +++ b/setup/cli-agent.ts @@ -0,0 +1,100 @@ +/** + * Step: cli-agent — Create the first agent wired to the CLI channel. + * + * Thin wrapper around `scripts/init-first-agent.ts --cli-only`. Emits a + * status block so /new-setup SKILL.md can parse the result without having + * to read the script's plain stdout. + * + * Args: + * --display-name (required) operator's display name + * --agent-name (optional) agent persona name, defaults to display-name + * --welcome (optional) system welcome instruction + */ +import { execFileSync } from 'child_process'; +import path from 'path'; + +import { log } from '../src/log.js'; +import { emitStatus } from './status.js'; + +function parseArgs(args: string[]): { + displayName: string; + agentName?: string; + welcome?: string; +} { + let displayName: string | undefined; + let agentName: string | undefined; + let welcome: string | undefined; + + for (let i = 0; i < args.length; i++) { + const key = args[i]; + const val = args[i + 1]; + switch (key) { + case '--display-name': + displayName = val; + i++; + break; + case '--agent-name': + agentName = val; + i++; + break; + case '--welcome': + welcome = val; + i++; + break; + } + } + + if (!displayName) { + emitStatus('CLI_AGENT', { + STATUS: 'failed', + ERROR: 'missing_display_name', + LOG: 'logs/setup.log', + }); + process.exit(2); + } + + return { displayName, agentName, welcome }; +} + +export async function run(args: string[]): Promise { + const { displayName, agentName, welcome } = parseArgs(args); + + const projectRoot = process.cwd(); + const script = path.join(projectRoot, 'scripts', 'init-first-agent.ts'); + + const scriptArgs = ['exec', 'tsx', script, '--cli-only', '--display-name', displayName]; + if (agentName) scriptArgs.push('--agent-name', agentName); + if (welcome) scriptArgs.push('--welcome', welcome); + + log.info('Invoking init-first-agent in cli-only mode', { displayName, agentName }); + + try { + execFileSync('pnpm', scriptArgs, { + cwd: projectRoot, + stdio: ['ignore', 'pipe', 'pipe'], + encoding: 'utf-8', + }); + } catch (err) { + const e = err as { stdout?: string; stderr?: string; status?: number }; + log.error('init-first-agent failed', { + status: e.status, + stdout: e.stdout, + stderr: e.stderr, + }); + emitStatus('CLI_AGENT', { + STATUS: 'failed', + ERROR: 'init_script_failed', + EXIT_CODE: e.status ?? -1, + LOG: 'logs/setup.log', + }); + process.exit(1); + } + + emitStatus('CLI_AGENT', { + DISPLAY_NAME: displayName, + AGENT_NAME: agentName || displayName, + CHANNEL: 'cli/local', + STATUS: 'success', + LOG: 'logs/setup.log', + }); +} diff --git a/setup/index.ts b/setup/index.ts index e3b9dd7bb..526ea7d63 100644 --- a/setup/index.ts +++ b/setup/index.ts @@ -16,6 +16,9 @@ const STEPS: Record< mounts: () => import('./mounts.js'), service: () => import('./service.js'), verify: () => import('./verify.js'), + onecli: () => import('./onecli.js'), + auth: () => import('./auth.js'), + 'cli-agent': () => import('./cli-agent.js'), }; async function main(): Promise { diff --git a/setup/onecli.ts b/setup/onecli.ts new file mode 100644 index 000000000..710737151 --- /dev/null +++ b/setup/onecli.ts @@ -0,0 +1,194 @@ +/** + * Step: onecli — Install + configure the OneCLI gateway and CLI. + * + * Aggregates what the old /setup + /init-onecli skills ran as loose shell + * commands. Idempotent: skips install if `onecli` already works, and safely + * re-applies PATH, api-host, and .env updates. + * + * Emits ONECLI_URL so /new-setup SKILL.md can forward it downstream (e.g. as + * ${ONECLI_URL} in status messages). Polls /health to give downstream steps + * (auth, service) a ready gateway. + */ +import { execFileSync, execSync } from 'child_process'; +import fs from 'fs'; +import os from 'os'; +import path from 'path'; + +import { log } from '../src/log.js'; +import { emitStatus } from './status.js'; + +const LOCAL_BIN = path.join(os.homedir(), '.local', 'bin'); + +function childEnv(): NodeJS.ProcessEnv { + const parts = [LOCAL_BIN]; + if (process.env.PATH) parts.push(process.env.PATH); + return { ...process.env, PATH: parts.join(path.delimiter) }; +} + +function onecliVersion(): string | null { + try { + return execFileSync('onecli', ['version'], { + encoding: 'utf-8', + env: childEnv(), + stdio: ['ignore', 'pipe', 'ignore'], + }).trim(); + } catch { + return null; + } +} + +function getApiHost(): string | null { + try { + const out = execFileSync('onecli', ['config', 'get', 'api-host'], { + encoding: 'utf-8', + env: childEnv(), + stdio: ['ignore', 'pipe', 'ignore'], + }).trim(); + const parsed = JSON.parse(out) as { value?: unknown }; + return typeof parsed.value === 'string' && parsed.value ? parsed.value : null; + } catch { + return null; + } +} + +function extractUrlFromOutput(output: string): string | null { + const match = output.match(/https?:\/\/[\w.\-]+(?::\d+)?/); + return match ? match[0] : null; +} + +function ensureShellProfilePath(): void { + const home = os.homedir(); + const line = 'export PATH="$HOME/.local/bin:$PATH"'; + for (const profile of [path.join(home, '.bashrc'), path.join(home, '.zshrc')]) { + try { + const content = fs.existsSync(profile) ? fs.readFileSync(profile, 'utf-8') : ''; + if (!content.includes('.local/bin')) { + fs.appendFileSync(profile, `\n${line}\n`); + log.info('Added ~/.local/bin to PATH in shell profile', { profile }); + } + } catch (err) { + log.warn('Could not update shell profile', { profile, err }); + } + } +} + +function writeEnvOnecliUrl(url: string): void { + const envFile = path.join(process.cwd(), '.env'); + let content = fs.existsSync(envFile) ? fs.readFileSync(envFile, 'utf-8') : ''; + if (/^ONECLI_URL=/m.test(content)) { + content = content.replace(/^ONECLI_URL=.*$/m, `ONECLI_URL=${url}`); + } else { + content = content.trimEnd() + (content ? '\n' : '') + `ONECLI_URL=${url}\n`; + } + fs.writeFileSync(envFile, content); +} + +function installOnecli(): { stdout: string; ok: boolean } { + // OneCLI's own install script handles gateway + CLI + PATH. + // We run the two canonical installers in sequence and capture stdout so + // we can extract the printed URL as a fallback to `onecli config get`. + let stdout = ''; + try { + stdout += execSync('curl -fsSL onecli.sh/install | sh', { + encoding: 'utf-8', + stdio: ['ignore', 'pipe', 'pipe'], + }); + stdout += execSync('curl -fsSL onecli.sh/cli/install | sh', { + encoding: 'utf-8', + stdio: ['ignore', 'pipe', 'pipe'], + }); + return { stdout, ok: true }; + } catch (err) { + const e = err as { stdout?: string; stderr?: string }; + log.error('OneCLI install failed', { stderr: e.stderr }); + return { stdout: stdout + (e.stdout ?? '') + (e.stderr ?? ''), ok: false }; + } +} + +async function pollHealth(url: string, timeoutMs: number): Promise { + const deadline = Date.now() + timeoutMs; + while (Date.now() < deadline) { + try { + const res = await fetch(`${url}/health`); + if (res.ok) return true; + } catch { + // not ready yet + } + await new Promise((resolve) => setTimeout(resolve, 1000)); + } + return false; +} + +export async function run(_args: string[]): Promise { + ensureShellProfilePath(); + + let installOutput = ''; + let present = !!onecliVersion(); + if (!present) { + log.info('Installing OneCLI gateway and CLI'); + const res = installOnecli(); + installOutput = res.stdout; + if (!res.ok) { + emitStatus('ONECLI', { + INSTALLED: false, + STATUS: 'failed', + ERROR: 'install_failed', + LOG: 'logs/setup.log', + }); + process.exit(1); + } + present = !!onecliVersion(); + if (!present) { + emitStatus('ONECLI', { + INSTALLED: false, + STATUS: 'failed', + ERROR: 'onecli_not_on_path_after_install', + HINT: 'Open a new shell or run `export PATH="$HOME/.local/bin:$PATH"` and retry.', + LOG: 'logs/setup.log', + }); + process.exit(1); + } + } + + let url = getApiHost(); + if (!url && installOutput) { + url = extractUrlFromOutput(installOutput); + if (url) { + try { + execFileSync('onecli', ['config', 'set', 'api-host', url], { + stdio: 'ignore', + env: childEnv(), + }); + } catch (err) { + log.warn('onecli config set api-host failed', { err }); + } + } + } + + if (!url) { + emitStatus('ONECLI', { + INSTALLED: true, + STATUS: 'failed', + ERROR: 'could_not_resolve_api_host', + HINT: 'Run `onecli config get api-host` to inspect the gateway URL.', + LOG: 'logs/setup.log', + }); + process.exit(1); + } + + writeEnvOnecliUrl(url); + log.info('Wrote ONECLI_URL to .env', { url }); + + const healthy = await pollHealth(url, 15000); + + emitStatus('ONECLI', { + INSTALLED: true, + ONECLI_URL: url, + HEALTHY: healthy, + STATUS: healthy ? 'success' : 'degraded', + ...(healthy + ? {} + : { HINT: 'Gateway did not respond to /health within 15s. Try `onecli start`.' }), + LOG: 'logs/setup.log', + }); +} From 6db81554bf7d3b42df3ddd3d533385fd24b02151 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Sun, 19 Apr 2026 10:43:38 +0000 Subject: [PATCH 04/95] feat(new-setup): add probe step for dynamic context injection MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Single upfront parallel scan the SKILL.md renders via `!`...`` so Claude sees system state before generating its first response. Each field maps to a routing decision (skip/run/ask) for a downstream step. Reports: OS, SHELL, DOCKER + IMAGE_PRESENT, ONECLI_STATUS + ONECLI_URL, ANTHROPIC_SECRET, SERVICE_STATUS, CLI_AGENT_WIRED, INFERRED_DISPLAY_NAME, TZ_STATUS + TZ_ENV + TZ_SYSTEM. Runs in ~200ms on a fully-set-up host. Not a replacement for per-step idempotency — each step keeps its own checks since probe is a snapshot and can go stale by execution time. Uses /api/health (OneCLI's actual endpoint). Anthropic secret check uses the CLI client so it works whenever onecli is installed, even if the direct HTTP health probe fails (different network paths). Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/index.ts | 1 + setup/probe.ts | 308 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 309 insertions(+) create mode 100644 setup/probe.ts diff --git a/setup/index.ts b/setup/index.ts index 526ea7d63..baa97e332 100644 --- a/setup/index.ts +++ b/setup/index.ts @@ -19,6 +19,7 @@ const STEPS: Record< onecli: () => import('./onecli.js'), auth: () => import('./auth.js'), 'cli-agent': () => import('./cli-agent.js'), + probe: () => import('./probe.js'), }; async function main(): Promise { diff --git a/setup/probe.ts b/setup/probe.ts new file mode 100644 index 000000000..14d08296d --- /dev/null +++ b/setup/probe.ts @@ -0,0 +1,308 @@ +/** + * Step: probe — Single upfront parallel scan for /new-setup's dynamic context + * injection. Rendered into the SKILL.md prompt via `!`pnpm exec tsx ... probe`` + * so Claude sees the current system state before generating its first response. + * + * This is a routing aid, NOT a replacement for per-step idempotency checks. + * Each existing step keeps its own checks; probe just tells the skill which + * steps to bother calling. + * + * Keep this step fast (<2s total). All probes swallow their own errors and + * report a neutral state rather than failing the whole scan. + */ +import { execFileSync, execSync } from 'child_process'; +import fs from 'fs'; +import os from 'os'; +import path from 'path'; + +import Database from 'better-sqlite3'; + +import { DATA_DIR } from '../src/config.js'; +import { log } from '../src/log.js'; +import { isValidTimezone } from '../src/timezone.js'; +import { commandExists, getPlatform, isWSL } from './platform.js'; +import { emitStatus } from './status.js'; + +const LOCAL_BIN = path.join(os.homedir(), '.local', 'bin'); +const PROBE_TIMEOUT_MS = 2000; +const HEALTH_TIMEOUT_MS = 2000; +const AGENT_IMAGE = 'nanoclaw-agent:latest'; + +function childEnv(): NodeJS.ProcessEnv { + const parts = [LOCAL_BIN]; + if (process.env.PATH) parts.push(process.env.PATH); + return { ...process.env, PATH: parts.join(path.delimiter) }; +} + +function readEnvVar(name: string): string | null { + const envFile = path.join(process.cwd(), '.env'); + if (!fs.existsSync(envFile)) return null; + const content = fs.readFileSync(envFile, 'utf-8'); + const m = content.match(new RegExp(`^${name}=(.+)$`, 'm')); + if (!m) return null; + return m[1].trim().replace(/^["']|["']$/g, ''); +} + +function probeDocker(): { + status: 'running' | 'installed_not_running' | 'not_found'; + imagePresent: boolean; +} { + if (!commandExists('docker')) return { status: 'not_found', imagePresent: false }; + try { + execSync('docker info', { stdio: 'ignore', timeout: PROBE_TIMEOUT_MS }); + } catch { + return { status: 'installed_not_running', imagePresent: false }; + } + let imagePresent = false; + try { + execSync(`docker image inspect ${AGENT_IMAGE}`, { + stdio: 'ignore', + timeout: PROBE_TIMEOUT_MS, + }); + imagePresent = true; + } catch { + // image not built yet + } + return { status: 'running', imagePresent }; +} + +function probeOnecliUrl(): string | null { + const fromEnv = readEnvVar('ONECLI_URL'); + if (fromEnv) return fromEnv; + try { + const out = execFileSync('onecli', ['config', 'get', 'api-host'], { + encoding: 'utf-8', + env: childEnv(), + stdio: ['ignore', 'pipe', 'ignore'], + timeout: PROBE_TIMEOUT_MS, + }).trim(); + const parsed = JSON.parse(out) as { value?: unknown }; + if (typeof parsed.value === 'string' && parsed.value) return parsed.value; + } catch { + // onecli not installed or config not set + } + return null; +} + +async function probeOnecliStatus( + url: string | null, +): Promise<'healthy' | 'installed_not_healthy' | 'not_found'> { + const installed = + commandExists('onecli') || fs.existsSync(path.join(LOCAL_BIN, 'onecli')); + if (!installed) return 'not_found'; + if (!url) return 'installed_not_healthy'; + try { + const controller = new AbortController(); + const timer = setTimeout(() => controller.abort(), HEALTH_TIMEOUT_MS); + const res = await fetch(`${url}/api/health`, { signal: controller.signal }); + clearTimeout(timer); + return res.ok ? 'healthy' : 'installed_not_healthy'; + } catch { + return 'installed_not_healthy'; + } +} + +function probeAnthropicSecret(): boolean { + try { + const out = execFileSync('onecli', ['secrets', 'list'], { + encoding: 'utf-8', + env: childEnv(), + stdio: ['ignore', 'pipe', 'ignore'], + timeout: PROBE_TIMEOUT_MS, + }); + const parsed = JSON.parse(out) as { data?: Array<{ type: string }> }; + return !!parsed.data?.some((s) => s.type === 'anthropic'); + } catch { + return false; + } +} + +function probeServiceStatus(): 'running' | 'stopped' | 'not_configured' { + const platform = getPlatform(); + if (platform === 'macos') { + try { + const out = execSync('launchctl list', { + encoding: 'utf-8', + timeout: PROBE_TIMEOUT_MS, + }); + const line = out.split('\n').find((l) => l.includes('com.nanoclaw')); + if (!line) return 'not_configured'; + // Format: "PID STATUS LABEL" — PID is "-" when loaded but not running + const pid = line.trim().split(/\s+/)[0]; + return pid && pid !== '-' ? 'running' : 'stopped'; + } catch { + return 'not_configured'; + } + } + if (platform === 'linux') { + try { + execSync('systemctl --user is-active nanoclaw', { + stdio: 'ignore', + timeout: PROBE_TIMEOUT_MS, + }); + return 'running'; + } catch { + // Either stopped, not-configured, or is-active returned non-zero. + // Distinguish by checking if the unit file exists at all. + try { + execSync('systemctl --user cat nanoclaw', { + stdio: 'ignore', + timeout: PROBE_TIMEOUT_MS, + }); + return 'stopped'; + } catch { + return 'not_configured'; + } + } + } + return 'not_configured'; +} + +function probeCliAgentWired(): boolean { + const dbPath = path.join(DATA_DIR, 'v2.db'); + if (!fs.existsSync(dbPath)) return false; + let db: Database.Database | null = null; + try { + db = new Database(dbPath, { readonly: true }); + const row = db + .prepare( + `SELECT 1 FROM messaging_group_agents mga + JOIN messaging_groups mg ON mg.id = mga.messaging_group_id + WHERE mg.channel_type = 'cli' LIMIT 1`, + ) + .get(); + return !!row; + } catch { + // Tables may not exist yet + return false; + } finally { + db?.close(); + } +} + +function probeInferredDisplayName(): string { + const reject = (s: string | null | undefined): boolean => + !s || !s.trim() || s.trim().toLowerCase() === 'root'; + + // 1. git global user name + try { + const name = execFileSync('git', ['config', '--global', 'user.name'], { + encoding: 'utf-8', + timeout: 1000, + stdio: ['ignore', 'pipe', 'ignore'], + }).trim(); + if (!reject(name)) return name; + } catch { + // git missing or no config set + } + + const user = process.env.USER || os.userInfo().username; + const platform = getPlatform(); + + // 2. Platform full-name from directory services + if (platform === 'macos') { + try { + const fullName = execFileSync('id', ['-F', user], { + encoding: 'utf-8', + timeout: 1000, + stdio: ['ignore', 'pipe', 'ignore'], + }).trim(); + if (!reject(fullName)) return fullName; + } catch { + // id -F not supported + } + } else if (platform === 'linux') { + try { + const entry = execFileSync('getent', ['passwd', user], { + encoding: 'utf-8', + timeout: 1000, + stdio: ['ignore', 'pipe', 'ignore'], + }).trim(); + const gecos = entry.split(':')[4]; + if (gecos) { + const fullName = gecos.split(',')[0].trim(); + if (!reject(fullName)) return fullName; + } + } catch { + // getent missing + } + } + + // 3. $USER / whoami fallback + if (!reject(user)) return user; + return 'User'; +} + +function probeTimezone(): { + status: 'configured' | 'autodetected' | 'utc_suspicious' | 'needs_input'; + envTz: string; + systemTz: string; +} { + const envTz = readEnvVar('TZ'); + const systemTz = Intl.DateTimeFormat().resolvedOptions().timeZone || ''; + + let status: 'configured' | 'autodetected' | 'utc_suspicious' | 'needs_input'; + if (envTz && isValidTimezone(envTz)) { + status = 'configured'; + } else if (systemTz === 'UTC' || systemTz === 'Etc/UTC') { + status = 'utc_suspicious'; + } else if (systemTz && isValidTimezone(systemTz)) { + status = 'autodetected'; + } else { + status = 'needs_input'; + } + + return { + status, + envTz: envTz || 'none', + systemTz: systemTz || 'unknown', + }; +} + +export async function run(_args: string[]): Promise { + const started = Date.now(); + + // Resolve OS (with WSL distinguished) + const platform = getPlatform(); + const wsl = isWSL(); + const osLabel: 'macos' | 'linux' | 'wsl' | 'unknown' = + wsl ? 'wsl' : platform === 'macos' ? 'macos' : platform === 'linux' ? 'linux' : 'unknown'; + const shell = process.env.SHELL || 'unknown'; + + // Sync probes (child_process is blocking; parallelizing provides little gain + // and complicates error handling). + const docker = probeDocker(); + const oneCliUrl = probeOnecliUrl(); + const serviceStatus = probeServiceStatus(); + const cliAgentWired = probeCliAgentWired(); + const displayName = probeInferredDisplayName(); + const tz = probeTimezone(); + + // Async: health check is the only non-blocking probe. + const onecliStatus = await probeOnecliStatus(oneCliUrl); + + // Secret check uses the CLI client and works whenever onecli is installed, + // even if our direct HTTP health probe failed (different network paths). + const anthropicSecret = onecliStatus !== 'not_found' ? probeAnthropicSecret() : false; + + const elapsedMs = Date.now() - started; + log.info('probe complete', { elapsedMs }); + + emitStatus('PROBE', { + OS: osLabel, + SHELL: shell, + DOCKER: docker.status, + IMAGE_PRESENT: docker.imagePresent, + ONECLI_STATUS: onecliStatus, + ONECLI_URL: oneCliUrl || 'none', + ANTHROPIC_SECRET: anthropicSecret, + SERVICE_STATUS: serviceStatus, + CLI_AGENT_WIRED: cliAgentWired, + INFERRED_DISPLAY_NAME: displayName, + TZ_STATUS: tz.status, + TZ_ENV: tz.envTz, + TZ_SYSTEM: tz.systemTz, + ELAPSED_MS: elapsedMs, + STATUS: 'success', + }); +} From f6ddd20636a395c1947ab9d6bc3d76b3bef44119 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Sun, 19 Apr 2026 10:43:41 +0000 Subject: [PATCH 05/95] feat(new-setup): add skill definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Shortest path from zero to a working two-way agent chat via the CLI channel. Renders `!`pnpm exec tsx setup/index.ts --step probe`` at the top for dynamic context injection — Claude sees current system state before generating its first response and routes each subsequent step (skip/ask/run) off the probe snapshot. Pre-approves the Bash patterns it needs via `allowed-tools` so setup runs without per-step prompts. Lives alongside /setup for now; will replace it once proven. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup/SKILL.md | 116 ++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 .claude/skills/new-setup/SKILL.md diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md new file mode 100644 index 000000000..4ea6ece63 --- /dev/null +++ b/.claude/skills/new-setup/SKILL.md @@ -0,0 +1,116 @@ +--- +name: new-setup +description: Shortest path from zero to a working two-way agent chat, for any user regardless of technical background — ends at a running NanoClaw instance with at least one CLI-reachable agent. +allowed-tools: Bash(bash setup.sh) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm run chat *) Bash(brew install *) Bash(curl -fsSL https://get.docker.com | sh) Bash(sudo usermod -aG docker *) Bash(open -a Docker) Bash(sudo systemctl start docker) +--- + +# NanoClaw bare-minimum setup + +Purpose of this skill is to take any user — technical or not — from zero to a two-way chat with an agent in the fewest steps possible. Done means a running NanoClaw instance with at least one agent reachable via the CLI channel. + +Only run the steps strictly required for the NanoClaw process to start and respond to the user end-to-end. Everything else is deferred to post-setup skills. + +For each step, print a one-liner to the user explaining what it does and why it's needed. Keep the tone friendly and lightly informative — context, not jargon. + +Each step is invoked as `pnpm exec tsx setup/index.ts --step ` and emits a structured status block Claude parses to decide what to do next. + +Start with a probe: a single parallel scan that snapshots every prerequisite and dependency. The rest of the flow reads this snapshot to decide what to run, skip, or ask about — no per-step re-checking. + +## Current state + +!`pnpm exec tsx setup/index.ts --step probe` + +## Flow + +Parse the probe block above. For each step below, consult the named probe fields and skip, ask, or run accordingly. Before running any step, say the quoted one-liner to the user. + +### 1. Node bootstrap + +Always runs — probe can't report on this since it lives below the Node layer. + +> *"Now I'm installing Node and your project's dependencies, so the rest of setup has what it needs to run."* + +Run `bash setup.sh`. Parse the status block. + +- `NODE_OK=false` → Offer to install Node 22 (macOS: `brew install node@22`; Linux: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs`). Re-run. +- `DEPS_OK=false` or `NATIVE_OK=false` → Read `logs/setup.log`, fix, re-run. + +> **Loose command:** `bash setup.sh`. Justification: pre-Node bootstrap. Can't call the Node-based dispatcher before Node and `pnpm install` are in place. + +### 2. Docker + +Check probe results and skip if `DOCKER=running` AND `IMAGE_PRESENT=true`. + +**Runtime:** +- `DOCKER=not_found` → + > *"Now I'm installing Docker so your agents can work safely in a contained environment."* + - macOS: `brew install --cask docker && open -a Docker` + - Linux: `curl -fsSL https://get.docker.com | sh && sudo usermod -aG docker $USER` (tell user they may need to log out/in for group membership) +- `DOCKER=installed_not_running` → + > *"Starting Docker up so the agent containers can come online."* + - macOS: `open -a Docker` + - Linux: `sudo systemctl start docker` + +Wait ~15s after either, then proceed. + +> **Loose commands:** Docker install/start. Justification: platform-specific package-manager invocations. Wrapping them in a `--step` would just move the same branching into TypeScript with no added value. + +**Image (run if `IMAGE_PRESENT=false`):** + +> *"Next I'm building the agent container image — takes a few minutes the first time, but it's a one-off."* + +`pnpm exec tsx setup/index.ts --step container -- --runtime docker` + +### 3. OneCLI + +Check probe results and skip if `ONECLI_STATUS=healthy`. + +> *"Now I'm installing OneCLI — a local vault that keeps your API keys safe and hands them to your agents only when they need them."* + +`pnpm exec tsx setup/index.ts --step onecli` + +### 4. Anthropic credential + +Check probe results and skip if `ANTHROPIC_SECRET=true`. + +> *"Your agent needs an Anthropic credential to talk to Claude. Let's get that set up."* + +Use `AskUserQuestion`: +1. **Claude subscription (Pro/Max)** — "Run `claude setup-token` in another terminal. It prints a token; paste it back here when ready." +2. **Anthropic API key** — "Get one from https://console.anthropic.com/settings/keys." + +Wait for the token. When received, run: + +`pnpm exec tsx setup/index.ts --step auth -- --create --value ` + +### 5. Service + +Check probe results and skip if `SERVICE_STATUS=running`. + +> *"Starting the NanoClaw background service so it can relay messages between you and your agent."* + +`pnpm exec tsx setup/index.ts --step service` + +### 6. First CLI agent + +Check probe results and skip if `CLI_AGENT_WIRED=true`. + +> *"Now I'm creating your first agent and hooking it up to the terminal so you can start chatting."* + +Ask: *"What should I call you?"* Default: the value of `INFERRED_DISPLAY_NAME` from probe. + +`pnpm exec tsx setup/index.ts --step cli-agent -- --display-name ""` + +### 7. First chat + +> *"You're all set — send your first message to your agent:"* + +`pnpm run chat hi` + +The agent should reply within ~60s (first container spin-up is slowest). If no reply, tail `logs/nanoclaw.log`. + +> **Loose command:** `pnpm run chat hi`. Justification: this is the command the user will keep using after setup. Hiding it behind a `--step` would force them to memorize a second way to do the same thing. + +## If anything fails + +Any step that reports `STATUS: failed` in its status block: read `logs/setup.log`, diagnose, fix the underlying cause, re-run the same `--step`. Don't bypass errors to keep moving. From b3e8b2e047c96a36b8436e64894259d979aff9cd Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Sun, 19 Apr 2026 11:03:49 +0000 Subject: [PATCH 06/95] fix(new-setup): run probe before pnpm is installed Port probe to zero-dep plain ESM (setup/probe.mjs) so /new-setup can inject dynamic context on a fresh machine where pnpm/node_modules don't yet exist. Skill falls back to a STATUS: unavailable block if Node itself isn't on PATH, and the flow treats that as "run every step from 1" (each step is idempotent). Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup/SKILL.md | 8 +- setup/index.ts | 1 - setup/{probe.ts => probe.mjs} | 193 ++++++++++++++++++------------ 3 files changed, 122 insertions(+), 80 deletions(-) rename setup/{probe.ts => probe.mjs} (62%) diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index 4ea6ece63..3643b92b8 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -1,7 +1,7 @@ --- name: new-setup description: Shortest path from zero to a working two-way agent chat, for any user regardless of technical background — ends at a running NanoClaw instance with at least one CLI-reachable agent. -allowed-tools: Bash(bash setup.sh) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm run chat *) Bash(brew install *) Bash(curl -fsSL https://get.docker.com | sh) Bash(sudo usermod -aG docker *) Bash(open -a Docker) Bash(sudo systemctl start docker) +allowed-tools: Bash(bash setup.sh) Bash(node setup/probe.mjs) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm run chat *) Bash(brew install *) Bash(curl -fsSL https://get.docker.com | sh) Bash(sudo usermod -aG docker *) Bash(open -a Docker) Bash(sudo systemctl start docker) --- # NanoClaw bare-minimum setup @@ -14,16 +14,18 @@ For each step, print a one-liner to the user explaining what it does and why it' Each step is invoked as `pnpm exec tsx setup/index.ts --step ` and emits a structured status block Claude parses to decide what to do next. -Start with a probe: a single parallel scan that snapshots every prerequisite and dependency. The rest of the flow reads this snapshot to decide what to run, skip, or ask about — no per-step re-checking. +Start with a probe: a single parallel scan that snapshots every prerequisite and dependency. The rest of the flow reads this snapshot to decide what to run, skip, or ask about — no per-step re-checking. The probe is plain ESM JS (`setup/probe.mjs`) with no external deps so it can run before step 1 has installed `pnpm`/`node_modules`. ## Current state -!`pnpm exec tsx setup/index.ts --step probe` +!`command -v node >/dev/null 2>&1 && node setup/probe.mjs || printf '=== NANOCLAW SETUP: PROBE ===\nSTATUS: unavailable\nREASON: node_not_installed\n=== END ===\n'` ## Flow Parse the probe block above. For each step below, consult the named probe fields and skip, ask, or run accordingly. Before running any step, say the quoted one-liner to the user. +If the probe reports `STATUS: unavailable` (Node isn't installed yet), ignore all `skip if …` probe conditions and run every step from 1 onward — each step has its own idempotency check, so re-running is safe. + ### 1. Node bootstrap Always runs — probe can't report on this since it lives below the Node layer. diff --git a/setup/index.ts b/setup/index.ts index baa97e332..526ea7d63 100644 --- a/setup/index.ts +++ b/setup/index.ts @@ -19,7 +19,6 @@ const STEPS: Record< onecli: () => import('./onecli.js'), auth: () => import('./auth.js'), 'cli-agent': () => import('./cli-agent.js'), - probe: () => import('./probe.js'), }; async function main(): Promise { diff --git a/setup/probe.ts b/setup/probe.mjs similarity index 62% rename from setup/probe.ts rename to setup/probe.mjs index 14d08296d..a28f75971 100644 --- a/setup/probe.ts +++ b/setup/probe.mjs @@ -1,40 +1,82 @@ +#!/usr/bin/env node /** - * Step: probe — Single upfront parallel scan for /new-setup's dynamic context - * injection. Rendered into the SKILL.md prompt via `!`pnpm exec tsx ... probe`` - * so Claude sees the current system state before generating its first response. + * Setup step: probe — Single upfront parallel scan for /new-setup's dynamic + * context injection. Rendered into the SKILL.md prompt via + * `!node setup/probe.mjs` so Claude sees the current system state before + * generating its first response. * * This is a routing aid, NOT a replacement for per-step idempotency checks. - * Each existing step keeps its own checks; probe just tells the skill which - * steps to bother calling. + * Each step keeps its own checks; probe tells the skill which steps to skip. * - * Keep this step fast (<2s total). All probes swallow their own errors and - * report a neutral state rather than failing the whole scan. + * Plain ESM JS (zero deps) by design: this runs BEFORE setup.sh has installed + * pnpm and node_modules, so it can only use Node built-ins. `better-sqlite3` + * is dynamic-imported so the probe degrades gracefully on fresh installs. + * + * Keep fast (<2s total). All probes swallow their own errors and report a + * neutral state rather than failing the whole scan. */ -import { execFileSync, execSync } from 'child_process'; -import fs from 'fs'; -import os from 'os'; -import path from 'path'; - -import Database from 'better-sqlite3'; - -import { DATA_DIR } from '../src/config.js'; -import { log } from '../src/log.js'; -import { isValidTimezone } from '../src/timezone.js'; -import { commandExists, getPlatform, isWSL } from './platform.js'; -import { emitStatus } from './status.js'; +import { execFileSync, execSync } from 'node:child_process'; +import fs from 'node:fs'; +import os from 'node:os'; +import path from 'node:path'; const LOCAL_BIN = path.join(os.homedir(), '.local', 'bin'); const PROBE_TIMEOUT_MS = 2000; const HEALTH_TIMEOUT_MS = 2000; const AGENT_IMAGE = 'nanoclaw-agent:latest'; +const DATA_DIR = path.resolve(process.cwd(), 'data'); -function childEnv(): NodeJS.ProcessEnv { +function childEnv() { const parts = [LOCAL_BIN]; if (process.env.PATH) parts.push(process.env.PATH); return { ...process.env, PATH: parts.join(path.delimiter) }; } -function readEnvVar(name: string): string | null { +function getPlatform() { + const p = os.platform(); + if (p === 'darwin') return 'macos'; + if (p === 'linux') return 'linux'; + return 'unknown'; +} + +function isWSL() { + if (os.platform() !== 'linux') return false; + try { + const release = fs.readFileSync('/proc/version', 'utf-8').toLowerCase(); + return release.includes('microsoft') || release.includes('wsl'); + } catch { + return false; + } +} + +function commandExists(name) { + try { + execSync(`command -v ${name}`, { stdio: 'ignore' }); + return true; + } catch { + return false; + } +} + +function isValidTimezone(tz) { + try { + new Intl.DateTimeFormat(undefined, { timeZone: tz }); + return true; + } catch { + return false; + } +} + +function emitStatus(step, fields) { + const lines = [`=== NANOCLAW SETUP: ${step} ===`]; + for (const [k, v] of Object.entries(fields)) { + lines.push(`${k}: ${v}`); + } + lines.push('=== END ==='); + console.log(lines.join('\n')); +} + +function readEnvVar(name) { const envFile = path.join(process.cwd(), '.env'); if (!fs.existsSync(envFile)) return null; const content = fs.readFileSync(envFile, 'utf-8'); @@ -43,10 +85,7 @@ function readEnvVar(name: string): string | null { return m[1].trim().replace(/^["']|["']$/g, ''); } -function probeDocker(): { - status: 'running' | 'installed_not_running' | 'not_found'; - imagePresent: boolean; -} { +function probeDocker() { if (!commandExists('docker')) return { status: 'not_found', imagePresent: false }; try { execSync('docker info', { stdio: 'ignore', timeout: PROBE_TIMEOUT_MS }); @@ -66,7 +105,7 @@ function probeDocker(): { return { status: 'running', imagePresent }; } -function probeOnecliUrl(): string | null { +function probeOnecliUrl() { const fromEnv = readEnvVar('ONECLI_URL'); if (fromEnv) return fromEnv; try { @@ -76,7 +115,7 @@ function probeOnecliUrl(): string | null { stdio: ['ignore', 'pipe', 'ignore'], timeout: PROBE_TIMEOUT_MS, }).trim(); - const parsed = JSON.parse(out) as { value?: unknown }; + const parsed = JSON.parse(out); if (typeof parsed.value === 'string' && parsed.value) return parsed.value; } catch { // onecli not installed or config not set @@ -84,9 +123,7 @@ function probeOnecliUrl(): string | null { return null; } -async function probeOnecliStatus( - url: string | null, -): Promise<'healthy' | 'installed_not_healthy' | 'not_found'> { +async function probeOnecliStatus(url) { const installed = commandExists('onecli') || fs.existsSync(path.join(LOCAL_BIN, 'onecli')); if (!installed) return 'not_found'; @@ -102,7 +139,7 @@ async function probeOnecliStatus( } } -function probeAnthropicSecret(): boolean { +function probeAnthropicSecret() { try { const out = execFileSync('onecli', ['secrets', 'list'], { encoding: 'utf-8', @@ -110,14 +147,14 @@ function probeAnthropicSecret(): boolean { stdio: ['ignore', 'pipe', 'ignore'], timeout: PROBE_TIMEOUT_MS, }); - const parsed = JSON.parse(out) as { data?: Array<{ type: string }> }; - return !!parsed.data?.some((s) => s.type === 'anthropic'); + const parsed = JSON.parse(out); + return !!(parsed.data && parsed.data.some((s) => s.type === 'anthropic')); } catch { return false; } } -function probeServiceStatus(): 'running' | 'stopped' | 'not_configured' { +function probeServiceStatus() { const platform = getPlatform(); if (platform === 'macos') { try { @@ -127,7 +164,6 @@ function probeServiceStatus(): 'running' | 'stopped' | 'not_configured' { }); const line = out.split('\n').find((l) => l.includes('com.nanoclaw')); if (!line) return 'not_configured'; - // Format: "PID STATUS LABEL" — PID is "-" when loaded but not running const pid = line.trim().split(/\s+/)[0]; return pid && pid !== '-' ? 'running' : 'stopped'; } catch { @@ -142,8 +178,6 @@ function probeServiceStatus(): 'running' | 'stopped' | 'not_configured' { }); return 'running'; } catch { - // Either stopped, not-configured, or is-active returned non-zero. - // Distinguish by checking if the unit file exists at all. try { execSync('systemctl --user cat nanoclaw', { stdio: 'ignore', @@ -158,33 +192,36 @@ function probeServiceStatus(): 'running' | 'stopped' | 'not_configured' { return 'not_configured'; } -function probeCliAgentWired(): boolean { +async function probeCliAgentWired() { const dbPath = path.join(DATA_DIR, 'v2.db'); if (!fs.existsSync(dbPath)) return false; - let db: Database.Database | null = null; + // Dynamic-import so probe still runs before `pnpm install` has built the + // native module. On truly fresh installs `data/v2.db` can't exist anyway, + // so the short-circuit above handles that path. try { - db = new Database(dbPath, { readonly: true }); - const row = db - .prepare( - `SELECT 1 FROM messaging_group_agents mga - JOIN messaging_groups mg ON mg.id = mga.messaging_group_id - WHERE mg.channel_type = 'cli' LIMIT 1`, - ) - .get(); - return !!row; + const mod = await import('better-sqlite3'); + const Database = mod.default ?? mod; + const db = new Database(dbPath, { readonly: true }); + try { + const row = db + .prepare( + `SELECT 1 FROM messaging_group_agents mga + JOIN messaging_groups mg ON mg.id = mga.messaging_group_id + WHERE mg.channel_type = 'cli' LIMIT 1`, + ) + .get(); + return !!row; + } finally { + db.close(); + } } catch { - // Tables may not exist yet return false; - } finally { - db?.close(); } } -function probeInferredDisplayName(): string { - const reject = (s: string | null | undefined): boolean => - !s || !s.trim() || s.trim().toLowerCase() === 'root'; +function probeInferredDisplayName() { + const reject = (s) => !s || !s.trim() || s.trim().toLowerCase() === 'root'; - // 1. git global user name try { const name = execFileSync('git', ['config', '--global', 'user.name'], { encoding: 'utf-8', @@ -199,7 +236,6 @@ function probeInferredDisplayName(): string { const user = process.env.USER || os.userInfo().username; const platform = getPlatform(); - // 2. Platform full-name from directory services if (platform === 'macos') { try { const fullName = execFileSync('id', ['-F', user], { @@ -228,20 +264,15 @@ function probeInferredDisplayName(): string { } } - // 3. $USER / whoami fallback if (!reject(user)) return user; return 'User'; } -function probeTimezone(): { - status: 'configured' | 'autodetected' | 'utc_suspicious' | 'needs_input'; - envTz: string; - systemTz: string; -} { +function probeTimezone() { const envTz = readEnvVar('TZ'); const systemTz = Intl.DateTimeFormat().resolvedOptions().timeZone || ''; - let status: 'configured' | 'autodetected' | 'utc_suspicious' | 'needs_input'; + let status; if (envTz && isValidTimezone(envTz)) { status = 'configured'; } else if (systemTz === 'UTC' || systemTz === 'Etc/UTC') { @@ -259,34 +290,35 @@ function probeTimezone(): { }; } -export async function run(_args: string[]): Promise { +export async function run() { const started = Date.now(); - // Resolve OS (with WSL distinguished) const platform = getPlatform(); const wsl = isWSL(); - const osLabel: 'macos' | 'linux' | 'wsl' | 'unknown' = - wsl ? 'wsl' : platform === 'macos' ? 'macos' : platform === 'linux' ? 'linux' : 'unknown'; + const osLabel = wsl + ? 'wsl' + : platform === 'macos' + ? 'macos' + : platform === 'linux' + ? 'linux' + : 'unknown'; const shell = process.env.SHELL || 'unknown'; - // Sync probes (child_process is blocking; parallelizing provides little gain - // and complicates error handling). const docker = probeDocker(); const oneCliUrl = probeOnecliUrl(); const serviceStatus = probeServiceStatus(); - const cliAgentWired = probeCliAgentWired(); const displayName = probeInferredDisplayName(); const tz = probeTimezone(); - // Async: health check is the only non-blocking probe. - const onecliStatus = await probeOnecliStatus(oneCliUrl); + const [onecliStatus, cliAgentWired] = await Promise.all([ + probeOnecliStatus(oneCliUrl), + probeCliAgentWired(), + ]); - // Secret check uses the CLI client and works whenever onecli is installed, - // even if our direct HTTP health probe failed (different network paths). - const anthropicSecret = onecliStatus !== 'not_found' ? probeAnthropicSecret() : false; + const anthropicSecret = + onecliStatus !== 'not_found' ? probeAnthropicSecret() : false; const elapsedMs = Date.now() - started; - log.info('probe complete', { elapsedMs }); emitStatus('PROBE', { OS: osLabel, @@ -306,3 +338,12 @@ export async function run(_args: string[]): Promise { STATUS: 'success', }); } + +const invokedDirectly = + import.meta.url === `file://${path.resolve(process.argv[1] ?? '')}`; +if (invokedDirectly) { + run().catch((err) => { + console.error(err); + process.exit(1); + }); +} From 77624d785453e38ea4b4baab61691041d2b1f402 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Sun, 19 Apr 2026 11:05:54 +0000 Subject: [PATCH 07/95] fix(new-setup): wrap probe in shell script for single-command permission check The chained `&& / ||` inline command tripped Claude Code's per-operation permission check. Move the Node-missing fallback into setup/probe.sh so the skill's `!` block is a single `bash setup/probe.sh` call. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup/SKILL.md | 4 ++-- setup/probe.sh | 19 +++++++++++++++++++ 2 files changed, 21 insertions(+), 2 deletions(-) create mode 100755 setup/probe.sh diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index 3643b92b8..4c2a1fea3 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -1,7 +1,7 @@ --- name: new-setup description: Shortest path from zero to a working two-way agent chat, for any user regardless of technical background — ends at a running NanoClaw instance with at least one CLI-reachable agent. -allowed-tools: Bash(bash setup.sh) Bash(node setup/probe.mjs) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm run chat *) Bash(brew install *) Bash(curl -fsSL https://get.docker.com | sh) Bash(sudo usermod -aG docker *) Bash(open -a Docker) Bash(sudo systemctl start docker) +allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm run chat *) Bash(brew install *) Bash(curl -fsSL https://get.docker.com | sh) Bash(sudo usermod -aG docker *) Bash(open -a Docker) Bash(sudo systemctl start docker) --- # NanoClaw bare-minimum setup @@ -18,7 +18,7 @@ Start with a probe: a single parallel scan that snapshots every prerequisite and ## Current state -!`command -v node >/dev/null 2>&1 && node setup/probe.mjs || printf '=== NANOCLAW SETUP: PROBE ===\nSTATUS: unavailable\nREASON: node_not_installed\n=== END ===\n'` +!`bash setup/probe.sh` ## Flow diff --git a/setup/probe.sh b/setup/probe.sh new file mode 100755 index 000000000..8be294835 --- /dev/null +++ b/setup/probe.sh @@ -0,0 +1,19 @@ +#!/bin/bash +# Wrapper for setup/probe.mjs so /new-setup's inline `!` block is a single +# shell command (permission-check friendly). When Node isn't installed yet, +# emit an "unavailable" status block so the skill's flow knows to skip the +# probe's skip-if conditions and run every step from 1. +set -u + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" + +if command -v node >/dev/null 2>&1; then + exec node "$PROJECT_ROOT/setup/probe.mjs" "$@" +fi + +cat <<'EOF' +=== NANOCLAW SETUP: PROBE === +STATUS: unavailable +REASON: node_not_installed +=== END === +EOF From 77fec6c7c33cf69adbdac6b1081e625e2901657e Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Sun, 19 Apr 2026 11:37:03 +0000 Subject: [PATCH 08/95] fix(new-setup): avoid double-bootstrap and corepack EACCES on system Node MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Two fixes to the fresh-install path: 1. setup.sh: when `corepack enable` runs as a non-root user against a system-wide Node install (apt-installed to /usr/bin), it fails EACCES trying to symlink /usr/bin/pnpm, leaving pnpm off PATH. Retry with sudo when pnpm is still missing — gated to Linux/WSL so macOS Homebrew prefixes aren't polluted with root-owned shims. 2. SKILL.md step 1: if the probe reports STATUS: unavailable (Node not installed), install Node BEFORE invoking `bash setup.sh`. The old flow ran setup.sh first as a diagnostic, which always failed fast, installed Node, then re-ran — two bootstraps for no reason. Combined: fresh Linux box now goes Node install -> single setup.sh run. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup/SKILL.md | 13 +++++++++---- setup.sh | 13 ++++++++++++- 2 files changed, 21 insertions(+), 5 deletions(-) diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index 4c2a1fea3..2a92b58bc 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -28,13 +28,18 @@ If the probe reports `STATUS: unavailable` (Node isn't installed yet), ignore al ### 1. Node bootstrap -Always runs — probe can't report on this since it lives below the Node layer. - > *"Now I'm installing Node and your project's dependencies, so the rest of setup has what it needs to run."* -Run `bash setup.sh`. Parse the status block. +If the probe reported `STATUS: unavailable` (Node isn't installed yet), install Node 22 **before** running `bash setup.sh` — otherwise the first bootstrap run is guaranteed to fail and you'll pay for it twice: -- `NODE_OK=false` → Offer to install Node 22 (macOS: `brew install node@22`; Linux: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs`). Re-run. +- macOS: `brew install node@22` +- Linux / WSL: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs` + +Then run `bash setup.sh`. If the probe reported any other status, run `bash setup.sh` directly — it's idempotent and verifies host deps + native modules. + +Parse the status block: + +- `NODE_OK=false` → Node install didn't take effect (PATH issue, keg-only formula, etc.). Investigate `logs/setup.log`, resolve, re-run. - `DEPS_OK=false` or `NATIVE_OK=false` → Read `logs/setup.log`, fix, re-run. > **Loose command:** `bash setup.sh`. Justification: pre-Node bootstrap. Can't call the Node-based dispatcher before Node and `pnpm install` are in place. diff --git a/setup.sh b/setup.sh index fb69d0a62..af2c5e55b 100755 --- a/setup.sh +++ b/setup.sh @@ -72,10 +72,21 @@ install_deps() { cd "$PROJECT_ROOT" - # Enable corepack for pnpm + # Enable corepack so `pnpm` shim lands on PATH. log "Enabling corepack" corepack enable >> "$LOG_FILE" 2>&1 || true + # On Linux/WSL with system-wide Node (e.g. apt-installed to /usr/bin), + # corepack needs root to symlink /usr/bin/pnpm. Retry with sudo when pnpm + # isn't on PATH. macOS Homebrew installs land in a user-writable prefix, + # and a sudo retry there would create root-owned shims inside /opt/homebrew + # that later break brew — so the retry is Linux-only. + if ! command -v pnpm >/dev/null 2>&1 && [ "$PLATFORM" = "linux" ] \ + && command -v sudo >/dev/null 2>&1; then + log "pnpm not on PATH after corepack enable — retrying with sudo" + sudo corepack enable >> "$LOG_FILE" 2>&1 || true + fi + log "Running pnpm install --frozen-lockfile" if pnpm install --frozen-lockfile >> "$LOG_FILE" 2>&1; then DEPS_OK="true" From f553c8126cd296bf1e83420318f2d780040bb464 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Sun, 19 Apr 2026 11:50:00 +0000 Subject: [PATCH 09/95] refactor(new-setup): add step-4 join barrier and drop scripted one-liners MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Two flow fixes: 1. Add "Ordering and parallelism" section making explicit that step 4 (auth) must block until step 3 (OneCLI) is complete — auth writes the secret into the vault, so firing an AskUserQuestion while OneCLI is still installing asks the user for a credential the system can't store. Step 2 (container build) is safe to run past step 4, joined before step 6 (first CLI agent). 2. Drop the per-step quoted one-liners. They duplicated Claude's own natural narration ("While those build, let's get your credential set up." → immediately echoed by the scripted "Your agent needs an Anthropic credential..."). Each step now has a short description instead; Claude narrates in its own voice. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup/SKILL.md | 38 +++++++++++++++++-------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index 2a92b58bc..ba62242bf 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -10,7 +10,7 @@ Purpose of this skill is to take any user — technical or not — from zero to Only run the steps strictly required for the NanoClaw process to start and respond to the user end-to-end. Everything else is deferred to post-setup skills. -For each step, print a one-liner to the user explaining what it does and why it's needed. Keep the tone friendly and lightly informative — context, not jargon. +Before each step, narrate to the user in your own words what's about to happen — one short, friendly sentence, no jargon. Don't read a scripted line; use the step context below to speak naturally. Each step is invoked as `pnpm exec tsx setup/index.ts --step ` and emits a structured status block Claude parses to decide what to do next. @@ -22,13 +22,21 @@ Start with a probe: a single parallel scan that snapshots every prerequisite and ## Flow -Parse the probe block above. For each step below, consult the named probe fields and skip, ask, or run accordingly. Before running any step, say the quoted one-liner to the user. +Parse the probe block above. For each step below, consult the named probe fields and skip, ask, or run accordingly. If the probe reports `STATUS: unavailable` (Node isn't installed yet), ignore all `skip if …` probe conditions and run every step from 1 onward — each step has its own idempotency check, so re-running is safe. -### 1. Node bootstrap +## Ordering and parallelism -> *"Now I'm installing Node and your project's dependencies, so the rest of setup has what it needs to run."* +Run steps sequentially by default: invoke the step, wait for its status block, act on the result, move to the next. + +One permitted parallelism: + +- **Step 2 (container image build) and step 3 (OneCLI install)** are independent — they may start together in the background. +- **Step 4 (auth) must NOT start until step 3 has completed.** Auth writes the secret into the OneCLI vault; if OneCLI isn't installed and healthy yet, the user gets asked for a credential the system can't store. Do not open an `AskUserQuestion` for step 4 while OneCLI is still installing. +- Step 2's image build may continue running past step 4 — the image isn't consumed until step 6 (first CLI agent). Join before step 6. + +### 1. Node bootstrap If the probe reported `STATUS: unavailable` (Node isn't installed yet), install Node 22 **before** running `bash setup.sh` — otherwise the first bootstrap run is guaranteed to fail and you'll pay for it twice: @@ -49,12 +57,10 @@ Parse the status block: Check probe results and skip if `DOCKER=running` AND `IMAGE_PRESENT=true`. **Runtime:** -- `DOCKER=not_found` → - > *"Now I'm installing Docker so your agents can work safely in a contained environment."* +- `DOCKER=not_found` → Docker itself is missing — install it so agent containers have an isolated place to run. - macOS: `brew install --cask docker && open -a Docker` - Linux: `curl -fsSL https://get.docker.com | sh && sudo usermod -aG docker $USER` (tell user they may need to log out/in for group membership) -- `DOCKER=installed_not_running` → - > *"Starting Docker up so the agent containers can come online."* +- `DOCKER=installed_not_running` → Docker is installed but the daemon is down — start it. - macOS: `open -a Docker` - Linux: `sudo systemctl start docker` @@ -62,9 +68,7 @@ Wait ~15s after either, then proceed. > **Loose commands:** Docker install/start. Justification: platform-specific package-manager invocations. Wrapping them in a `--step` would just move the same branching into TypeScript with no added value. -**Image (run if `IMAGE_PRESENT=false`):** - -> *"Next I'm building the agent container image — takes a few minutes the first time, but it's a one-off."* +**Image (run if `IMAGE_PRESENT=false`):** build the agent container image — takes a few minutes the first time, one-off cost. `pnpm exec tsx setup/index.ts --step container -- --runtime docker` @@ -72,7 +76,7 @@ Wait ~15s after either, then proceed. Check probe results and skip if `ONECLI_STATUS=healthy`. -> *"Now I'm installing OneCLI — a local vault that keeps your API keys safe and hands them to your agents only when they need them."* +OneCLI is the local vault that holds API keys and only releases them to agents when they need them. `pnpm exec tsx setup/index.ts --step onecli` @@ -80,7 +84,7 @@ Check probe results and skip if `ONECLI_STATUS=healthy`. Check probe results and skip if `ANTHROPIC_SECRET=true`. -> *"Your agent needs an Anthropic credential to talk to Claude. Let's get that set up."* +The agent needs an Anthropic credential to talk to Claude. Two sources: Use `AskUserQuestion`: 1. **Claude subscription (Pro/Max)** — "Run `claude setup-token` in another terminal. It prints a token; paste it back here when ready." @@ -94,7 +98,7 @@ Wait for the token. When received, run: Check probe results and skip if `SERVICE_STATUS=running`. -> *"Starting the NanoClaw background service so it can relay messages between you and your agent."* +Start the NanoClaw background service — it relays messages between the user and the agent. `pnpm exec tsx setup/index.ts --step service` @@ -102,15 +106,15 @@ Check probe results and skip if `SERVICE_STATUS=running`. Check probe results and skip if `CLI_AGENT_WIRED=true`. -> *"Now I'm creating your first agent and hooking it up to the terminal so you can start chatting."* +If step 2's container build is still running in the background, join it here before proceeding — the agent needs the image. -Ask: *"What should I call you?"* Default: the value of `INFERRED_DISPLAY_NAME` from probe. +Create the first agent and wire it to the CLI channel. Ask the user "What should I call you?" first — default the offered value to `INFERRED_DISPLAY_NAME` from the probe. `pnpm exec tsx setup/index.ts --step cli-agent -- --display-name ""` ### 7. First chat -> *"You're all set — send your first message to your agent:"* +Everything's ready — send the first message to the agent. `pnpm run chat hi` From 0992979c5a02089a64b2a31098153f40b3c16ab8 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Sun, 19 Apr 2026 12:01:05 +0000 Subject: [PATCH 10/95] feat(new-setup): probe host-deps and skip bootstrap when already installed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Probe now emits HOST_DEPS (ok|missing) based on whether node_modules/better-sqlite3/build/Release/better_sqlite3.node exists — the canonical proof that `pnpm install` ran and the native build step succeeded. Step 1 (Node bootstrap) skips when HOST_DEPS=ok instead of always re-running setup.sh. Probe now genuinely routes step 1 the same way it routes every other step. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup/SKILL.md | 6 ++++-- setup/probe.mjs | 18 ++++++++++++++++++ 2 files changed, 22 insertions(+), 2 deletions(-) diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index ba62242bf..f08fd16a8 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -38,12 +38,14 @@ One permitted parallelism: ### 1. Node bootstrap -If the probe reported `STATUS: unavailable` (Node isn't installed yet), install Node 22 **before** running `bash setup.sh` — otherwise the first bootstrap run is guaranteed to fail and you'll pay for it twice: +Check probe results and skip if `HOST_DEPS=ok` — Node, pnpm, `node_modules`, and `better-sqlite3`'s native binding are already in place. + +If the probe reported `STATUS: unavailable` (Node isn't installed yet — probe itself couldn't run), install Node 22 **before** running `bash setup.sh`, otherwise the first bootstrap run is guaranteed to fail: - macOS: `brew install node@22` - Linux / WSL: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs` -Then run `bash setup.sh`. If the probe reported any other status, run `bash setup.sh` directly — it's idempotent and verifies host deps + native modules. +Then run `bash setup.sh`. If the probe succeeded but `HOST_DEPS=missing`, run `bash setup.sh` directly — Node is there, deps aren't. Parse the status block: diff --git a/setup/probe.mjs b/setup/probe.mjs index a28f75971..5aea0d4e5 100644 --- a/setup/probe.mjs +++ b/setup/probe.mjs @@ -268,6 +268,22 @@ function probeInferredDisplayName() { return 'User'; } +function probeHostDeps() { + const nodeModules = path.resolve(process.cwd(), 'node_modules'); + if (!fs.existsSync(nodeModules)) return 'missing'; + // better-sqlite3's compiled native binding is the canonical proof that + // `pnpm install` ran AND the native build step succeeded. Cheaper than + // actually loading the module, and unambiguous on success. + const nativeBinding = path.join( + nodeModules, + 'better-sqlite3', + 'build', + 'Release', + 'better_sqlite3.node', + ); + return fs.existsSync(nativeBinding) ? 'ok' : 'missing'; +} + function probeTimezone() { const envTz = readEnvVar('TZ'); const systemTz = Intl.DateTimeFormat().resolvedOptions().timeZone || ''; @@ -309,6 +325,7 @@ export async function run() { const serviceStatus = probeServiceStatus(); const displayName = probeInferredDisplayName(); const tz = probeTimezone(); + const hostDeps = probeHostDeps(); const [onecliStatus, cliAgentWired] = await Promise.all([ probeOnecliStatus(oneCliUrl), @@ -323,6 +340,7 @@ export async function run() { emitStatus('PROBE', { OS: osLabel, SHELL: shell, + HOST_DEPS: hostDeps, DOCKER: docker.status, IMAGE_PRESENT: docker.imagePresent, ONECLI_STATUS: onecliStatus, From 5542107b9e9496a189ffd0ce2530d3b615b7e27f Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Sun, 19 Apr 2026 12:10:21 +0000 Subject: [PATCH 11/95] fix(new-setup): align onecli health path and rework auth flow MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit onecli step: - Poll /api/health (was /health) so the step's health check matches the probe's. On hosted OneCLI (app.onecli.sh) the old path returned non-ok, flagging the gateway as "degraded" even though install succeeded. - Drop the "try `onecli start`" hint — no such subcommand exists and it sent the skill off chasing fabricated commands. A failed health poll is demoted to a soft warning; the auth step surfaces a real outage via `onecli secrets list`. SKILL.md step 4: rewrite to match the /setup skill's pattern — the user generates the token themselves, picks dashboard or CLI to register it with OneCLI, and the skill verifies via `auth --check`. Tokens no longer travel through chat. Co-Authored-By: Koshkoshinsk Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup/SKILL.md | 24 ++++++++++++++++++------ setup/onecli.ts | 14 +++++++++++--- 2 files changed, 29 insertions(+), 9 deletions(-) diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index f08fd16a8..a671fb038 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -86,15 +86,27 @@ OneCLI is the local vault that holds API keys and only releases them to agents w Check probe results and skip if `ANTHROPIC_SECRET=true`. -The agent needs an Anthropic credential to talk to Claude. Two sources: +The credential never travels through chat — the user generates it, registers it with OneCLI themselves, and the skill verifies. -Use `AskUserQuestion`: -1. **Claude subscription (Pro/Max)** — "Run `claude setup-token` in another terminal. It prints a token; paste it back here when ready." -2. **Anthropic API key** — "Get one from https://console.anthropic.com/settings/keys." +**4a. Pick the source.** `AskUserQuestion`: -Wait for the token. When received, run: +1. **Claude subscription (Pro/Max)** — "Generate a token via `claude setup-token` in another terminal." +2. **Anthropic API key** — "Use a pay-per-use key from console.anthropic.com/settings/keys." -`pnpm exec tsx setup/index.ts --step auth -- --create --value ` +**4b. Wait for the user to obtain the credential.** For subscription, have them run `claude setup-token` in another terminal. For API key, point them to the console URL above. Either way, they keep the token — just confirm when they have it. + +**4c. Pick the registration path.** `AskUserQuestion` — substitute `${ONECLI_URL}` from the probe (or `.env`): + +1. **Dashboard** — "Open ${ONECLI_URL} in a browser; add a secret of type `anthropic`, value = the token, host-pattern `api.anthropic.com`." +2. **CLI** — "Run in another terminal: `onecli secrets create --name Anthropic --type anthropic --value YOUR_TOKEN --host-pattern api.anthropic.com`" + +Wait for the user's confirmation. If their reply happens to include a token (starts with `sk-ant-`), register it for them: `pnpm exec tsx setup/index.ts --step auth -- --create --value `. + +**4d. Verify.** + +`pnpm exec tsx setup/index.ts --step auth -- --check` + +If `ANTHROPIC_OK=false`, the secret isn't there yet — ask them to retry, then re-check. ### 5. Service diff --git a/setup/onecli.ts b/setup/onecli.ts index 710737151..ddb68c6eb 100644 --- a/setup/onecli.ts +++ b/setup/onecli.ts @@ -106,10 +106,11 @@ function installOnecli(): { stdout: string; ok: boolean } { } async function pollHealth(url: string, timeoutMs: number): Promise { + // `/api/health` matches the path probe.mjs uses — keep them aligned. const deadline = Date.now() + timeoutMs; while (Date.now() < deadline) { try { - const res = await fetch(`${url}/health`); + const res = await fetch(`${url}/api/health`); if (res.ok) return true; } catch { // not ready yet @@ -185,10 +186,17 @@ export async function run(_args: string[]): Promise { INSTALLED: true, ONECLI_URL: url, HEALTHY: healthy, - STATUS: healthy ? 'success' : 'degraded', + // Install succeeded regardless — a failed health poll often just means + // the endpoint is auth-gated or the gateway hasn't finished warming up. + // The next step (auth) will surface a genuinely broken gateway via + // `onecli secrets list`, so don't trigger rescue attempts from here. + STATUS: 'success', ...(healthy ? {} - : { HINT: 'Gateway did not respond to /health within 15s. Try `onecli start`.' }), + : { + HEALTH_HINT: + 'Health poll returned non-ok within 15s — likely auth-gated. Proceed to the auth step; it will surface a real outage.', + }), LOG: 'logs/setup.log', }); } From 96d765611230e7f4026126c0a92fa3dd4090fa16 Mon Sep 17 00:00:00 2001 From: "exe.dev user" Date: Sun, 19 Apr 2026 12:40:53 +0000 Subject: [PATCH 12/95] refactor(new-setup): rewrite probe in pure bash, drop unavailable fallback The probe now returns a real snapshot from second zero, so every step consults real probe fields instead of falling back to "run every step blindly" when Node isn't installed. Also drops the redundant CLI_AGENT_WIRED field (it gated the last step on its own end-state) and scopes timezone out of the probe (timezone is not part of /new-setup). Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup/SKILL.md | 12 +- setup/onecli.ts | 2 +- setup/probe.mjs | 367 ------------------------------ setup/probe.sh | 247 +++++++++++++++++++- 4 files changed, 243 insertions(+), 385 deletions(-) delete mode 100644 setup/probe.mjs diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index a671fb038..6b956957f 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -14,7 +14,7 @@ Before each step, narrate to the user in your own words what's about to happen Each step is invoked as `pnpm exec tsx setup/index.ts --step ` and emits a structured status block Claude parses to decide what to do next. -Start with a probe: a single parallel scan that snapshots every prerequisite and dependency. The rest of the flow reads this snapshot to decide what to run, skip, or ask about — no per-step re-checking. The probe is plain ESM JS (`setup/probe.mjs`) with no external deps so it can run before step 1 has installed `pnpm`/`node_modules`. +Start with a probe: a single upfront scan that snapshots every prerequisite and dependency. The rest of the flow reads this snapshot to decide what to run, skip, or ask about — no per-step re-checking. The probe is pure bash (`setup/probe.sh`) with no external deps so it runs correctly before Node has been installed. ## Current state @@ -22,9 +22,7 @@ Start with a probe: a single parallel scan that snapshots every prerequisite and ## Flow -Parse the probe block above. For each step below, consult the named probe fields and skip, ask, or run accordingly. - -If the probe reports `STATUS: unavailable` (Node isn't installed yet), ignore all `skip if …` probe conditions and run every step from 1 onward — each step has its own idempotency check, so re-running is safe. +Parse the probe block above. For each step below, consult the named probe fields and skip, ask, or run accordingly. The probe always returns a real snapshot — there is no "node not installed" fallback; `HOST_DEPS=missing` is how you know Node/pnpm haven't been bootstrapped yet. ## Ordering and parallelism @@ -40,12 +38,12 @@ One permitted parallelism: Check probe results and skip if `HOST_DEPS=ok` — Node, pnpm, `node_modules`, and `better-sqlite3`'s native binding are already in place. -If the probe reported `STATUS: unavailable` (Node isn't installed yet — probe itself couldn't run), install Node 22 **before** running `bash setup.sh`, otherwise the first bootstrap run is guaranteed to fail: +If `HOST_DEPS=missing` and `node --version` fails (Node isn't installed at all), install Node 22 **before** running `bash setup.sh`, otherwise the first bootstrap run is guaranteed to fail: - macOS: `brew install node@22` - Linux / WSL: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs` -Then run `bash setup.sh`. If the probe succeeded but `HOST_DEPS=missing`, run `bash setup.sh` directly — Node is there, deps aren't. +Then run `bash setup.sh`. If Node is already present and only `HOST_DEPS=missing`, run `bash setup.sh` directly — deps just haven't been installed yet. Parse the status block: @@ -118,8 +116,6 @@ Start the NanoClaw background service — it relays messages between the user an ### 6. First CLI agent -Check probe results and skip if `CLI_AGENT_WIRED=true`. - If step 2's container build is still running in the background, join it here before proceeding — the agent needs the image. Create the first agent and wire it to the CLI channel. Ask the user "What should I call you?" first — default the offered value to `INFERRED_DISPLAY_NAME` from the probe. diff --git a/setup/onecli.ts b/setup/onecli.ts index ddb68c6eb..226d30271 100644 --- a/setup/onecli.ts +++ b/setup/onecli.ts @@ -106,7 +106,7 @@ function installOnecli(): { stdout: string; ok: boolean } { } async function pollHealth(url: string, timeoutMs: number): Promise { - // `/api/health` matches the path probe.mjs uses — keep them aligned. + // `/api/health` matches the path probe.sh uses — keep them aligned. const deadline = Date.now() + timeoutMs; while (Date.now() < deadline) { try { diff --git a/setup/probe.mjs b/setup/probe.mjs deleted file mode 100644 index 5aea0d4e5..000000000 --- a/setup/probe.mjs +++ /dev/null @@ -1,367 +0,0 @@ -#!/usr/bin/env node -/** - * Setup step: probe — Single upfront parallel scan for /new-setup's dynamic - * context injection. Rendered into the SKILL.md prompt via - * `!node setup/probe.mjs` so Claude sees the current system state before - * generating its first response. - * - * This is a routing aid, NOT a replacement for per-step idempotency checks. - * Each step keeps its own checks; probe tells the skill which steps to skip. - * - * Plain ESM JS (zero deps) by design: this runs BEFORE setup.sh has installed - * pnpm and node_modules, so it can only use Node built-ins. `better-sqlite3` - * is dynamic-imported so the probe degrades gracefully on fresh installs. - * - * Keep fast (<2s total). All probes swallow their own errors and report a - * neutral state rather than failing the whole scan. - */ -import { execFileSync, execSync } from 'node:child_process'; -import fs from 'node:fs'; -import os from 'node:os'; -import path from 'node:path'; - -const LOCAL_BIN = path.join(os.homedir(), '.local', 'bin'); -const PROBE_TIMEOUT_MS = 2000; -const HEALTH_TIMEOUT_MS = 2000; -const AGENT_IMAGE = 'nanoclaw-agent:latest'; -const DATA_DIR = path.resolve(process.cwd(), 'data'); - -function childEnv() { - const parts = [LOCAL_BIN]; - if (process.env.PATH) parts.push(process.env.PATH); - return { ...process.env, PATH: parts.join(path.delimiter) }; -} - -function getPlatform() { - const p = os.platform(); - if (p === 'darwin') return 'macos'; - if (p === 'linux') return 'linux'; - return 'unknown'; -} - -function isWSL() { - if (os.platform() !== 'linux') return false; - try { - const release = fs.readFileSync('/proc/version', 'utf-8').toLowerCase(); - return release.includes('microsoft') || release.includes('wsl'); - } catch { - return false; - } -} - -function commandExists(name) { - try { - execSync(`command -v ${name}`, { stdio: 'ignore' }); - return true; - } catch { - return false; - } -} - -function isValidTimezone(tz) { - try { - new Intl.DateTimeFormat(undefined, { timeZone: tz }); - return true; - } catch { - return false; - } -} - -function emitStatus(step, fields) { - const lines = [`=== NANOCLAW SETUP: ${step} ===`]; - for (const [k, v] of Object.entries(fields)) { - lines.push(`${k}: ${v}`); - } - lines.push('=== END ==='); - console.log(lines.join('\n')); -} - -function readEnvVar(name) { - const envFile = path.join(process.cwd(), '.env'); - if (!fs.existsSync(envFile)) return null; - const content = fs.readFileSync(envFile, 'utf-8'); - const m = content.match(new RegExp(`^${name}=(.+)$`, 'm')); - if (!m) return null; - return m[1].trim().replace(/^["']|["']$/g, ''); -} - -function probeDocker() { - if (!commandExists('docker')) return { status: 'not_found', imagePresent: false }; - try { - execSync('docker info', { stdio: 'ignore', timeout: PROBE_TIMEOUT_MS }); - } catch { - return { status: 'installed_not_running', imagePresent: false }; - } - let imagePresent = false; - try { - execSync(`docker image inspect ${AGENT_IMAGE}`, { - stdio: 'ignore', - timeout: PROBE_TIMEOUT_MS, - }); - imagePresent = true; - } catch { - // image not built yet - } - return { status: 'running', imagePresent }; -} - -function probeOnecliUrl() { - const fromEnv = readEnvVar('ONECLI_URL'); - if (fromEnv) return fromEnv; - try { - const out = execFileSync('onecli', ['config', 'get', 'api-host'], { - encoding: 'utf-8', - env: childEnv(), - stdio: ['ignore', 'pipe', 'ignore'], - timeout: PROBE_TIMEOUT_MS, - }).trim(); - const parsed = JSON.parse(out); - if (typeof parsed.value === 'string' && parsed.value) return parsed.value; - } catch { - // onecli not installed or config not set - } - return null; -} - -async function probeOnecliStatus(url) { - const installed = - commandExists('onecli') || fs.existsSync(path.join(LOCAL_BIN, 'onecli')); - if (!installed) return 'not_found'; - if (!url) return 'installed_not_healthy'; - try { - const controller = new AbortController(); - const timer = setTimeout(() => controller.abort(), HEALTH_TIMEOUT_MS); - const res = await fetch(`${url}/api/health`, { signal: controller.signal }); - clearTimeout(timer); - return res.ok ? 'healthy' : 'installed_not_healthy'; - } catch { - return 'installed_not_healthy'; - } -} - -function probeAnthropicSecret() { - try { - const out = execFileSync('onecli', ['secrets', 'list'], { - encoding: 'utf-8', - env: childEnv(), - stdio: ['ignore', 'pipe', 'ignore'], - timeout: PROBE_TIMEOUT_MS, - }); - const parsed = JSON.parse(out); - return !!(parsed.data && parsed.data.some((s) => s.type === 'anthropic')); - } catch { - return false; - } -} - -function probeServiceStatus() { - const platform = getPlatform(); - if (platform === 'macos') { - try { - const out = execSync('launchctl list', { - encoding: 'utf-8', - timeout: PROBE_TIMEOUT_MS, - }); - const line = out.split('\n').find((l) => l.includes('com.nanoclaw')); - if (!line) return 'not_configured'; - const pid = line.trim().split(/\s+/)[0]; - return pid && pid !== '-' ? 'running' : 'stopped'; - } catch { - return 'not_configured'; - } - } - if (platform === 'linux') { - try { - execSync('systemctl --user is-active nanoclaw', { - stdio: 'ignore', - timeout: PROBE_TIMEOUT_MS, - }); - return 'running'; - } catch { - try { - execSync('systemctl --user cat nanoclaw', { - stdio: 'ignore', - timeout: PROBE_TIMEOUT_MS, - }); - return 'stopped'; - } catch { - return 'not_configured'; - } - } - } - return 'not_configured'; -} - -async function probeCliAgentWired() { - const dbPath = path.join(DATA_DIR, 'v2.db'); - if (!fs.existsSync(dbPath)) return false; - // Dynamic-import so probe still runs before `pnpm install` has built the - // native module. On truly fresh installs `data/v2.db` can't exist anyway, - // so the short-circuit above handles that path. - try { - const mod = await import('better-sqlite3'); - const Database = mod.default ?? mod; - const db = new Database(dbPath, { readonly: true }); - try { - const row = db - .prepare( - `SELECT 1 FROM messaging_group_agents mga - JOIN messaging_groups mg ON mg.id = mga.messaging_group_id - WHERE mg.channel_type = 'cli' LIMIT 1`, - ) - .get(); - return !!row; - } finally { - db.close(); - } - } catch { - return false; - } -} - -function probeInferredDisplayName() { - const reject = (s) => !s || !s.trim() || s.trim().toLowerCase() === 'root'; - - try { - const name = execFileSync('git', ['config', '--global', 'user.name'], { - encoding: 'utf-8', - timeout: 1000, - stdio: ['ignore', 'pipe', 'ignore'], - }).trim(); - if (!reject(name)) return name; - } catch { - // git missing or no config set - } - - const user = process.env.USER || os.userInfo().username; - const platform = getPlatform(); - - if (platform === 'macos') { - try { - const fullName = execFileSync('id', ['-F', user], { - encoding: 'utf-8', - timeout: 1000, - stdio: ['ignore', 'pipe', 'ignore'], - }).trim(); - if (!reject(fullName)) return fullName; - } catch { - // id -F not supported - } - } else if (platform === 'linux') { - try { - const entry = execFileSync('getent', ['passwd', user], { - encoding: 'utf-8', - timeout: 1000, - stdio: ['ignore', 'pipe', 'ignore'], - }).trim(); - const gecos = entry.split(':')[4]; - if (gecos) { - const fullName = gecos.split(',')[0].trim(); - if (!reject(fullName)) return fullName; - } - } catch { - // getent missing - } - } - - if (!reject(user)) return user; - return 'User'; -} - -function probeHostDeps() { - const nodeModules = path.resolve(process.cwd(), 'node_modules'); - if (!fs.existsSync(nodeModules)) return 'missing'; - // better-sqlite3's compiled native binding is the canonical proof that - // `pnpm install` ran AND the native build step succeeded. Cheaper than - // actually loading the module, and unambiguous on success. - const nativeBinding = path.join( - nodeModules, - 'better-sqlite3', - 'build', - 'Release', - 'better_sqlite3.node', - ); - return fs.existsSync(nativeBinding) ? 'ok' : 'missing'; -} - -function probeTimezone() { - const envTz = readEnvVar('TZ'); - const systemTz = Intl.DateTimeFormat().resolvedOptions().timeZone || ''; - - let status; - if (envTz && isValidTimezone(envTz)) { - status = 'configured'; - } else if (systemTz === 'UTC' || systemTz === 'Etc/UTC') { - status = 'utc_suspicious'; - } else if (systemTz && isValidTimezone(systemTz)) { - status = 'autodetected'; - } else { - status = 'needs_input'; - } - - return { - status, - envTz: envTz || 'none', - systemTz: systemTz || 'unknown', - }; -} - -export async function run() { - const started = Date.now(); - - const platform = getPlatform(); - const wsl = isWSL(); - const osLabel = wsl - ? 'wsl' - : platform === 'macos' - ? 'macos' - : platform === 'linux' - ? 'linux' - : 'unknown'; - const shell = process.env.SHELL || 'unknown'; - - const docker = probeDocker(); - const oneCliUrl = probeOnecliUrl(); - const serviceStatus = probeServiceStatus(); - const displayName = probeInferredDisplayName(); - const tz = probeTimezone(); - const hostDeps = probeHostDeps(); - - const [onecliStatus, cliAgentWired] = await Promise.all([ - probeOnecliStatus(oneCliUrl), - probeCliAgentWired(), - ]); - - const anthropicSecret = - onecliStatus !== 'not_found' ? probeAnthropicSecret() : false; - - const elapsedMs = Date.now() - started; - - emitStatus('PROBE', { - OS: osLabel, - SHELL: shell, - HOST_DEPS: hostDeps, - DOCKER: docker.status, - IMAGE_PRESENT: docker.imagePresent, - ONECLI_STATUS: onecliStatus, - ONECLI_URL: oneCliUrl || 'none', - ANTHROPIC_SECRET: anthropicSecret, - SERVICE_STATUS: serviceStatus, - CLI_AGENT_WIRED: cliAgentWired, - INFERRED_DISPLAY_NAME: displayName, - TZ_STATUS: tz.status, - TZ_ENV: tz.envTz, - TZ_SYSTEM: tz.systemTz, - ELAPSED_MS: elapsedMs, - STATUS: 'success', - }); -} - -const invokedDirectly = - import.meta.url === `file://${path.resolve(process.argv[1] ?? '')}`; -if (invokedDirectly) { - run().catch((err) => { - console.error(err); - process.exit(1); - }); -} diff --git a/setup/probe.sh b/setup/probe.sh index 8be294835..6f40fff55 100755 --- a/setup/probe.sh +++ b/setup/probe.sh @@ -1,19 +1,248 @@ #!/bin/bash -# Wrapper for setup/probe.mjs so /new-setup's inline `!` block is a single -# shell command (permission-check friendly). When Node isn't installed yet, -# emit an "unavailable" status block so the skill's flow knows to skip the -# probe's skip-if conditions and run every step from 1. +# Setup step: probe — single upfront parallel-ish scan that snapshots every +# prerequisite and dependency for /new-setup's dynamic context injection. +# Rendered into the SKILL.md prompt via `!bash setup/probe.sh` so Claude sees +# the current system state before generating its first response. +# +# Pure bash by design: this runs BEFORE setup.sh has installed Node, pnpm, and +# node_modules, so it cannot rely on any Node-based tooling. Every field below +# is computed from POSIX utilities + grep/awk/curl. +# +# This is a routing aid, NOT a replacement for per-step idempotency checks. +# Each step keeps its own checks; probe tells the skill which steps to skip. +# +# Keep fast (<2s total). All probes swallow their own errors and report a +# neutral state rather than failing the whole scan. set -u +START_S=$(date +%s) + PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +LOCAL_BIN="$HOME/.local/bin" +AGENT_IMAGE="nanoclaw-agent:latest" -if command -v node >/dev/null 2>&1; then - exec node "$PROJECT_ROOT/setup/probe.mjs" "$@" +export PATH="$LOCAL_BIN:$PATH" + +command_exists() { command -v "$1" >/dev/null 2>&1; } + +# Best-effort 2s timeout; falls back to no timeout on macOS if `timeout` isn't +# installed (the probed commands are all expected to return fast anyway). +with_timeout() { + if command_exists timeout; then timeout 2 "$@" + elif command_exists gtimeout; then gtimeout 2 "$@" + else "$@" + fi +} + +trim() { + local s="$1" + s="${s#"${s%%[![:space:]]*}"}" + s="${s%"${s##*[![:space:]]}"}" + printf '%s' "$s" +} + +read_env_var() { + local name="$1" + local envfile="$PROJECT_ROOT/.env" + [[ -f "$envfile" ]] || return 0 + local line + line=$(grep -E "^${name}=" "$envfile" 2>/dev/null | head -n1) || return 0 + [[ -z "$line" ]] && return 0 + local val="${line#*=}" + val="${val%\"}"; val="${val#\"}" + val="${val%\'}"; val="${val#\'}" + trim "$val" +} + +probe_os() { + case "$(uname -s 2>/dev/null)" in + Darwin) echo "macos" ;; + Linux) + if [[ -r /proc/version ]] && grep -qEi "microsoft|wsl" /proc/version; then + echo "wsl" + else + echo "linux" + fi + ;; + *) echo "unknown" ;; + esac +} + +probe_host_deps() { + local node_modules="$PROJECT_ROOT/node_modules" + local native="$node_modules/better-sqlite3/build/Release/better_sqlite3.node" + # `better-sqlite3`'s compiled native binding is the canonical proof that + # `pnpm install` ran AND the native build step succeeded. + if [[ -d "$node_modules" && -f "$native" ]]; then + echo "ok" + else + echo "missing" + fi +} + +# Sets DOCKER_STATUS and IMAGE_PRESENT as globals. +probe_docker() { + DOCKER_STATUS="not_found" + IMAGE_PRESENT="false" + command_exists docker || return 0 + if ! with_timeout docker info >/dev/null 2>&1; then + DOCKER_STATUS="installed_not_running" + return 0 + fi + DOCKER_STATUS="running" + if with_timeout docker image inspect "$AGENT_IMAGE" >/dev/null 2>&1; then + IMAGE_PRESENT="true" + fi +} + +probe_onecli_url() { + local url + url=$(read_env_var ONECLI_URL) + if [[ -n "$url" ]]; then + printf '%s' "$url" + return + fi + command_exists onecli || return 0 + local out + out=$(with_timeout onecli config get api-host 2>/dev/null) || return 0 + # Minimal JSON extract: {"value":"http..."} — avoid hard dep on jq + if [[ "$out" =~ \"value\"[[:space:]]*:[[:space:]]*\"([^\"]+)\" ]]; then + printf '%s' "${BASH_REMATCH[1]}" + fi +} + +probe_onecli_status() { + local url="$1" + if ! command_exists onecli && [[ ! -x "$LOCAL_BIN/onecli" ]]; then + echo "not_found"; return + fi + if [[ -z "$url" ]]; then + echo "installed_not_healthy"; return + fi + if command_exists curl \ + && curl -fsS --max-time 2 "${url}/api/health" >/dev/null 2>&1; then + echo "healthy" + else + echo "installed_not_healthy" + fi +} + +probe_anthropic_secret() { + command_exists onecli || { echo "false"; return; } + local out + out=$(with_timeout onecli secrets list 2>/dev/null) || { echo "false"; return; } + if echo "$out" | grep -Eq '"type"[[:space:]]*:[[:space:]]*"anthropic"'; then + echo "true" + else + echo "false" + fi +} + +probe_service_status() { + local platform="$1" + case "$platform" in + macos) + command_exists launchctl || { echo "not_configured"; return; } + local line + line=$(with_timeout launchctl list 2>/dev/null | grep "com.nanoclaw") || { + echo "not_configured"; return; } + local pid + pid=$(echo "$line" | awk '{print $1}') + if [[ -n "$pid" && "$pid" != "-" ]]; then + echo "running" + else + echo "stopped" + fi + ;; + linux|wsl) + command_exists systemctl || { echo "not_configured"; return; } + if with_timeout systemctl --user is-active nanoclaw >/dev/null 2>&1; then + echo "running" + elif with_timeout systemctl --user cat nanoclaw >/dev/null 2>&1; then + echo "stopped" + else + echo "not_configured" + fi + ;; + *) + echo "not_configured" + ;; + esac +} + +probe_display_name() { + local platform="$1" + local reject_re='^(|root)$' + local name + + if command_exists git; then + name=$(trim "$(git config --global user.name 2>/dev/null)") + if [[ -n "$name" && ! "$name" =~ $reject_re ]]; then + printf '%s' "$name"; return + fi + fi + + local user="${USER:-$(id -un 2>/dev/null)}" + + case "$platform" in + macos) + if command_exists id; then + name=$(trim "$(id -F "$user" 2>/dev/null)") + if [[ -n "$name" && ! "$name" =~ $reject_re ]]; then + printf '%s' "$name"; return + fi + fi + ;; + linux|wsl) + if command_exists getent; then + local entry gecos + entry=$(getent passwd "$user" 2>/dev/null) + gecos=$(echo "$entry" | awk -F: '{print $5}') + name=$(trim "$(echo "$gecos" | awk -F, '{print $1}')") + if [[ -n "$name" && ! "$name" =~ $reject_re ]]; then + printf '%s' "$name"; return + fi + fi + ;; + esac + + if [[ -n "$user" && ! "$user" =~ $reject_re ]]; then + printf '%s' "$user" + else + printf 'User' + fi +} + +OS=$(probe_os) +SHELL_NAME="${SHELL:-unknown}" +HOST_DEPS=$(probe_host_deps) +probe_docker +ONECLI_URL_VAL=$(probe_onecli_url) +ONECLI_STATUS=$(probe_onecli_status "$ONECLI_URL_VAL") +if [[ "$ONECLI_STATUS" == "not_found" ]]; then + ANTHROPIC_SECRET="false" +else + ANTHROPIC_SECRET=$(probe_anthropic_secret) fi +SERVICE_STATUS=$(probe_service_status "$OS") +DISPLAY_NAME=$(probe_display_name "$OS") -cat <<'EOF' +END_S=$(date +%s) +ELAPSED_MS=$(( (END_S - START_S) * 1000 )) + +cat < Date: Sun, 19 Apr 2026 12:46:34 +0000 Subject: [PATCH 13/95] docs(add-github): document bot account, userName, sender policy, and wiring Update SKILL.md with tested setup: dedicated bot account prerequisite, GITHUB_BOT_USERNAME env var for @-mention detection, private vs public repo sender policy guidance, member registration for strict mode, per-thread session mode, and wiring example. Co-Authored-By: Claude Opus 4.6 (1M context) --- .claude/skills/add-github/SKILL.md | 86 ++++++++++++++++++++++++------ 1 file changed, 70 insertions(+), 16 deletions(-) diff --git a/.claude/skills/add-github/SKILL.md b/.claude/skills/add-github/SKILL.md index e60e562e2..78366f3c9 100644 --- a/.claude/skills/add-github/SKILL.md +++ b/.claude/skills/add-github/SKILL.md @@ -7,6 +7,10 @@ description: Add GitHub channel integration via Chat SDK. PR and issue comment t Adds GitHub support via the Chat SDK bridge. The agent participates in PR and issue comment threads. +## Prerequisites + +You need a **dedicated GitHub bot account** (not your personal account). The adapter uses this account to post replies and filters out its own messages to avoid loops. Create a free GitHub account for your bot (e.g. `my-org-bot`), then invite it as a collaborator with write access to the repos you want monitored. + ## Install NanoClaw doesn't ship channels in trunk. This skill copies the GitHub adapter in from the `channels` branch. @@ -55,40 +59,90 @@ pnpm run build ## Credentials -> 1. Go to [GitHub Settings > Developer Settings > Personal Access Tokens](https://github.com/settings/tokens) -> 2. Create a **Fine-grained token** with: -> - Repository access: select the repos you want the bot to monitor -> - Permissions: **Pull requests** (Read & Write), **Issues** (Read & Write) -> 3. Copy the token -> 4. Set up a webhook on your repo(s): -> - Go to **Settings** > **Webhooks** > **Add webhook** -> - Payload URL: `https://your-domain/webhook/github` -> - Content type: `application/json` -> - Secret: generate a random string -> - Events: select **Issue comments**, **Pull request review comments** +### 1. Create a Personal Access Token for the bot account -### Configure environment +Log in as your **bot account**, then: + +1. Go to [Settings > Developer Settings > Personal Access Tokens](https://github.com/settings/tokens) +2. Create a **Fine-grained token** with: + - Repository access: select the repos you want the bot to monitor + - Permissions: **Pull requests** (Read & Write), **Issues** (Read & Write) +3. Copy the token + +### 2. Set up a webhook on each repo + +On each repo (logged in as the repo owner/admin): + +1. Go to **Settings** > **Webhooks** > **Add webhook** +2. Payload URL: `https://your-domain/webhook/github` (the shared webhook server, default port 3000) +3. Content type: `application/json` +4. Secret: generate a random string (e.g. `openssl rand -hex 20`) +5. Events: select **Issue comments** and **Pull request review comments** + +### 3. Configure environment Add to `.env`: ```bash GITHUB_TOKEN=github_pat_... GITHUB_WEBHOOK_SECRET=your-webhook-secret +GITHUB_BOT_USERNAME=your-bot-username ``` +`GITHUB_BOT_USERNAME` must match the bot account's GitHub username exactly. This is used for @-mention detection — the agent responds when someone writes `@your-bot-username` in a PR or issue comment. + Sync to container: `mkdir -p data/env && cp .env data/env/env` +## Wiring + +Ask the user: **Is this a private or public repo?** + +- **Private repo** — use `unknown_sender_policy: 'public'`. Only collaborators can comment anyway, so it's safe to let all comments through. +- **Public repo** — use `unknown_sender_policy: 'strict'`. Only registered members can trigger the agent, preventing strangers from consuming agent resources. Add trusted collaborators as members (see below). + +Run `/manage-channels` to wire the GitHub channel to an agent group, or insert manually: + +```sql +-- Create messaging group (one per repo) +INSERT INTO messaging_groups (id, channel_type, platform_id, name, is_group, unknown_sender_policy, created_at) +VALUES ('mg-github-myrepo', 'github', 'github:owner/repo', 'owner/repo', 1, '', datetime('now')); + +-- Wire to agent group +INSERT INTO messaging_group_agents (id, messaging_group_id, agent_group_id, trigger_rules, response_scope, session_mode, priority, created_at) +VALUES ('mga-github-myrepo', 'mg-github-myrepo', '', '', 'all', 'per-thread', 10, datetime('now')); +``` + +Replace `` with `public` or `strict` based on the user's choice above. + +### Adding members (for strict mode) + +When using `strict`, add each GitHub user who should be able to trigger the agent: + +```sql +-- Add user (kind = 'github', id = 'github:') +INSERT OR IGNORE INTO users (id, kind, display_name, created_at) +VALUES ('github:', 'github', '', datetime('now')); + +-- Grant membership to the agent group +INSERT OR IGNORE INTO agent_group_members (user_id, agent_group_id) +VALUES ('github:', ''); +``` + +To find a GitHub user's numeric ID: `gh api users/ --jq .id` + +Use `per-thread` session mode so each PR/issue gets its own agent session. + ## Next Steps If you're in the middle of `/setup`, return to the setup flow now. -Otherwise, run `/manage-channels` to wire this channel to an agent group. +Otherwise, restart the service (`systemctl --user restart nanoclaw` or `launchctl kickstart -k gui/$(id -u)/com.nanoclaw`) to pick up the new channel. ## Channel Info - **type**: `github` - **terminology**: GitHub has "repositories" containing "pull requests" and "issues." Each PR or issue comment thread is a separate conversation. -- **how-to-find-id**: The platform ID is `owner/repo` (e.g. `acme/backend`). Each PR/issue becomes its own thread automatically. +- **how-to-find-id**: The platform ID is `github:owner/repo` (e.g. `github:acme/backend`). Each PR/issue becomes its own thread automatically. - **supports-threads**: yes (PR and issue comment threads are native conversations) -- **typical-use**: Webhook/notification — the agent receives PR and issue events and responds in comment threads -- **default-isolation**: Typically shares a session with a chat channel (e.g. Slack) so the agent can summarize PRs and respond to reviews in the same context. Use a separate agent group if the repo contains sensitive code that other channels shouldn't access. +- **typical-use**: Webhook-driven — the agent receives PR and issue comment events and responds in comment threads when @-mentioned. After the first mention, the thread is subscribed and the agent responds to all follow-up comments. +- **default-isolation**: Use `per-thread` session mode. Each PR or issue gets its own isolated agent session. Typically wire to a dedicated agent group if the repo contains sensitive code. From 0d09c6ea212be54886cb97cd8d2c76ea311a8a28 Mon Sep 17 00:00:00 2001 From: Gabi Simons Date: Sun, 19 Apr 2026 15:45:02 +0000 Subject: [PATCH 14/95] docs(add-linear): OAuth app auth, bridge patch, team routing, wiring Rewrite SKILL.md with tested setup: OAuth app with client credentials (recommended), bridge catchAll patch for platforms without @-mention, LINEAR_TEAM_KEY for team-based routing, webhook setup with delay note, private vs public sender policy, and wiring example. Co-Authored-By: Claude Opus 4.6 (1M context) --- .claude/skills/add-linear/SKILL.md | 115 ++++++++++++++++++++++++----- 1 file changed, 96 insertions(+), 19 deletions(-) diff --git a/.claude/skills/add-linear/SKILL.md b/.claude/skills/add-linear/SKILL.md index f3650b61d..dc657af9f 100644 --- a/.claude/skills/add-linear/SKILL.md +++ b/.claude/skills/add-linear/SKILL.md @@ -5,11 +5,24 @@ description: Add Linear channel integration via Chat SDK. Issue comment threads # Add Linear Channel -Adds Linear support via the Chat SDK bridge. The agent participates in issue comment threads. +Adds Linear support via the Chat SDK bridge. The agent participates in issue comment threads. Every comment on a Linear issue triggers the agent — no @-mention needed. + +## Prerequisites + +**Recommended:** Create a Linear **OAuth application** so the agent posts as an app identity, not as you. This prevents the adapter from filtering your own comments as self-messages. + +1. Go to [Linear Settings > API > OAuth Applications](https://linear.app/settings/api/applications/new) +2. Create an app (e.g. "NanoClaw Bot") + - Developer URL: your repo URL (e.g. `https://github.com/your-org/nanoclaw`) + - Callback URL: `http://localhost` +3. After creating, click the app and enable **Client credentials** under grant types +4. Copy the **Client ID** and **Client Secret** + +**Alternative:** Use a Personal API Key (`LINEAR_API_KEY`) for simpler setup. The agent will post as you, and your own comments will be filtered (other team members' comments still work). ## Install -NanoClaw doesn't ship channels in trunk. This skill copies the Linear adapter in from the `channels` branch. +NanoClaw doesn't ship channels in trunk. This skill copies the Linear adapter in from the `channels` branch and patches the Chat SDK bridge to support catch-all message forwarding (Linear OAuth apps can't be @-mentioned). ### Pre-flight (idempotent) @@ -18,6 +31,7 @@ Skip to **Credentials** if all of these are already in place: - `src/channels/linear.ts` exists - `src/channels/index.ts` contains `import './linear.js';` - `@chat-adapter/linear` is listed in `package.json` dependencies +- `src/channels/chat-sdk-bridge.ts` contains `catchAll` Otherwise continue. Every step below is safe to re-run. @@ -41,13 +55,42 @@ Append to `src/channels/index.ts` (skip if the line is already present): import './linear.js'; ``` -### 4. Install the adapter package (pinned) +### 4. Patch the Chat SDK bridge for catch-all message forwarding + +Linear OAuth apps can't be @-mentioned, so the bridge's `onNewMention` handler never fires. Add `catchAll` support to `src/channels/chat-sdk-bridge.ts`: + +**4a.** Add `catchAll?: boolean` to the `ChatSdkBridgeConfig` interface: + +```typescript + /** + * Forward ALL messages in unsubscribed threads, not just @-mentions. + * Use for platforms where the bot identity can't be @-mentioned (e.g. + * Linear OAuth apps). The thread is auto-subscribed on first message. + */ + catchAll?: boolean; +``` + +**4b.** Add this handler block right after the `chat.onNewMention(...)` block (before the DMs block): + +```typescript + // Catch-all for platforms where @-mention isn't possible (e.g. Linear + // OAuth apps). Forward every unsubscribed message and auto-subscribe. + if (config.catchAll) { + chat.onNewMessage(/.*/, async (thread, message) => { + const channelId = adapter.channelIdFromThreadId(thread.id); + await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); + await thread.subscribe(); + }); + } +``` + +### 5. Install the adapter package (pinned) ```bash pnpm install @chat-adapter/linear@4.26.0 ``` -### 5. Build +### 6. Build ```bash pnpm run build @@ -55,37 +98,71 @@ pnpm run build ## Credentials -> 1. Go to [Linear Settings > API Keys](https://linear.app/settings/account/security/api-keys/new) -> 2. Create a **Personal API Key** (or use an OAuth application for team-wide access) -> 3. Copy the API key -> 4. Set up a webhook: -> - Go to **Settings** > **API** > **Webhooks** > **New webhook** -> - URL: `https://your-domain/webhook/linear` -> - Select events: **Comment** (created, updated) -> - Copy the signing secret +### 1. Set up a webhook -### Configure environment +1. Go to **Linear Settings** > **API** > **Webhooks** > **New webhook** +2. Label: `NanoClaw` +3. URL: `https://your-domain/webhook/linear` (the shared webhook server, default port 3000) +4. Team: select the team you want to monitor +5. Events: check **Comment** +6. Save — copy the **signing secret** + +Note: Linear webhook delivery may be delayed 1-5 minutes for new webhooks. This is normal. + +### 2. Configure environment Add to `.env`: ```bash -LINEAR_API_KEY=lin_api_... -LINEAR_WEBHOOK_SECRET=your-webhook-secret +# OAuth app (recommended) +LINEAR_CLIENT_ID=your-client-id +LINEAR_CLIENT_SECRET=your-client-secret + +# OR Personal API key (simpler, but agent posts as you) +# LINEAR_API_KEY=lin_api_... + +LINEAR_WEBHOOK_SECRET=your-webhook-signing-secret +LINEAR_BOT_USERNAME=NanoClaw Bot +LINEAR_TEAM_KEY=ENG ``` +- `LINEAR_BOT_USERNAME`: display name for the bot (used for self-message detection when using a Personal API Key) +- `LINEAR_TEAM_KEY`: the Linear team key (e.g. `ENG`, `NAN`). Find it in Linear under Settings > Teams. All issues in this team route to one messaging group. + Sync to container: `mkdir -p data/env && cp .env data/env/env` +## Wiring + +Ask the user: **Is this a private or public Linear workspace?** + +- **Private workspace** — use `unknown_sender_policy: 'public'`. Only workspace members can comment. +- **Public workspace** — use `unknown_sender_policy: 'strict'` and add trusted members (see GitHub skill for member registration example). + +Run `/manage-channels` to wire the Linear channel to an agent group, or insert manually: + +```sql +-- Create messaging group (one per team) +INSERT INTO messaging_groups (id, channel_type, platform_id, name, is_group, unknown_sender_policy, created_at) +VALUES ('mg-linear-eng', 'linear', 'linear:ENG', 'Engineering', 1, 'public', datetime('now')); + +-- Wire to agent group +INSERT INTO messaging_group_agents (id, messaging_group_id, agent_group_id, trigger_rules, response_scope, session_mode, priority, created_at) +VALUES ('mga-linear-eng', 'mg-linear-eng', '', '', 'all', 'per-thread', 10, datetime('now')); +``` + +The `platform_id` must be `linear:` matching the `LINEAR_TEAM_KEY` env var. Use `per-thread` session mode so each issue comment thread gets its own agent session. + ## Next Steps If you're in the middle of `/setup`, return to the setup flow now. -Otherwise, run `/manage-channels` to wire this channel to an agent group. +Otherwise, restart the service (`systemctl --user restart nanoclaw` or `launchctl kickstart -k gui/$(id -u)/com.nanoclaw`) to pick up the new channel. ## Channel Info - **type**: `linear` - **terminology**: Linear has "teams" containing "issues." Each issue's comment thread is a separate conversation. -- **how-to-find-id**: The platform ID is your team key (e.g. `ENG`). Find it in Linear under Settings > Teams. Each issue becomes its own thread automatically. +- **how-to-find-id**: The platform ID is `linear:` (e.g. `linear:ENG`). Find your team key in Linear under Settings > Teams. Each issue becomes its own thread automatically. - **supports-threads**: yes (issue comment threads are native conversations) -- **typical-use**: Webhook/notification — the agent receives issue comment events and responds in threads -- **default-isolation**: Typically shares a session with a chat channel (e.g. Slack) so the agent can discuss issues in the same context as team chat. Use a separate agent group if the Linear team tracks sensitive work. +- **typical-use**: Webhook-driven — the agent receives all issue comment events and responds automatically. No @-mention needed (Linear OAuth apps can't be @-mentioned). +- **default-isolation**: Use `per-thread` session mode. Each issue comment thread gets its own isolated agent session. From 0dae3498c3595649c1f72d54aa850a8747133b03 Mon Sep 17 00:00:00 2001 From: Tal Moskovich Date: Sun, 19 Apr 2026 23:06:11 +0300 Subject: [PATCH 15/95] docs(add-opencode): pin SDK/CLI to 1.4.17, document overlay propagation and env vars - Pin @opencode-ai/sdk and opencode-ai CLI both to 1.4.17; warn against latest (1.14.x has a breaking session API rewrite incompatible with the current provider code) - Add step 7: propagate provider files into existing per-group overlays (data/v2-sessions/*/agent-runner-src/providers/) which override the image at runtime and are never auto-updated by rebuilds - Add build cache gotcha: prune builder if "Unknown provider" after rebuild - Document ANTHROPIC_BASE_URL as required for non-anthropic providers, with correct base URL per provider (DeepSeek, OpenRouter examples) - Add OPENCODE_SMALL_MODEL to all examples - Document OneCLI credential grant (set-secrets replaces, not appends) Co-Authored-By: Claude Sonnet 4.6 --- .claude/skills/add-opencode/SKILL.md | 90 ++++++++++++++++++++-------- 1 file changed, 66 insertions(+), 24 deletions(-) diff --git a/.claude/skills/add-opencode/SKILL.md b/.claude/skills/add-opencode/SKILL.md index 1dd31df9f..08a558f23 100644 --- a/.claude/skills/add-opencode/SKILL.md +++ b/.claude/skills/add-opencode/SKILL.md @@ -60,10 +60,10 @@ import './opencode.js'; ### 4. Add the agent-runner dependency -Pinned. Bump deliberately, not with `bun update`. +Pinned. Bump deliberately, not with `bun update`. Use `1.4.17` — must match the `opencode-ai` CLI version pinned in step 5. The 1.14.x SDK has a completely different API and is **incompatible** with the current provider code. ```bash -cd container/agent-runner && bun add @opencode-ai/sdk@1.4.3 && cd - +cd container/agent-runner && bun add @opencode-ai/sdk@1.4.17 && cd - ``` ### 5. Add `opencode-ai` to the container Dockerfile @@ -73,9 +73,11 @@ Two edits to `container/Dockerfile`, both idempotent (skip if already present): **(a)** In the "Pin CLI versions" ARG block (around line 18), add after `ARG VERCEL_VERSION=latest`: ```dockerfile -ARG OPENCODE_VERSION=latest +ARG OPENCODE_VERSION=1.4.17 ``` +> **Do not use `latest`** — the CLI and SDK must be the same version. `latest` silently upgrades the CLI to 1.14.x which has a breaking session API change (UUID session IDs → `ses_` prefix) incompatible with SDK 1.4.x. + **(b)** In the `pnpm install -g` block (around line 80), append `"opencode-ai@${OPENCODE_VERSION}"` to the list: ```dockerfile @@ -94,6 +96,25 @@ pnpm exec tsc -p container/agent-runner/tsconfig.json --noEmit # container typ ./container/build.sh # agent image ``` +> **Build cache gotcha:** The container buildkit caches COPY steps aggressively. If provider files were already present in the build context before, the new files may not be picked up. If you see "Unknown provider: opencode" after the build, prune the builder and rebuild: +> ```bash +> docker builder prune -f && ./container/build.sh +> ``` + +### 7. Propagate to existing per-group overlays + +Each agent group has a live source overlay at `data/v2-sessions//agent-runner-src/providers/` that **overrides the image at runtime**. This overlay is created when the group is first wired and never auto-updated by image rebuilds. Any group that already existed before this skill ran needs the new files copied in manually. + +```bash +for overlay in data/v2-sessions/*/agent-runner-src/providers/; do + [ -d "$overlay" ] || continue + cp container/agent-runner/src/providers/opencode.ts "$overlay" + cp container/agent-runner/src/providers/mcp-to-opencode.ts "$overlay" + cp container/agent-runner/src/providers/index.ts "$overlay" + echo "Updated: $overlay" +done +``` + ## Configuration ### Host `.env` (typical) @@ -102,35 +123,62 @@ Set model/provider strings in the form OpenCode expects (often `provider/model-i These variables are read **on the host** and passed into the container only when the effective provider is `opencode`. They do not switch the provider by themselves; the DB still needs `agent_provider` set (below). -- `OPENCODE_PROVIDER` — OpenCode provider id, e.g. `openrouter`, `anthropic` (if unset, the runner defaults to `anthropic`). -- `OPENCODE_MODEL` — full model id, e.g. `openrouter/anthropic/claude-sonnet-4`. -- `OPENCODE_SMALL_MODEL` — optional second model for "small" tasks. +- `OPENCODE_PROVIDER` — OpenCode provider id, e.g. `openrouter`, `anthropic`, `deepseek`. +- `OPENCODE_MODEL` — full model id in `provider/model` form, e.g. `deepseek/deepseek-chat`. +- `OPENCODE_SMALL_MODEL` — optional second model for lighter tasks; defaults to `OPENCODE_MODEL` if unset. +- `ANTHROPIC_BASE_URL` — **required for non-`anthropic` providers.** The opencode container provider passes this as the `baseURL` for the upstream provider config so requests route through OneCLI's credential proxy or directly to the provider's API. Set it to the provider's API base URL (e.g. `https://api.deepseek.com/v1`, `https://openrouter.ai/api/v1`). -Credentials: OneCLI / credential proxy patterns are unchanged. For non-`anthropic` OpenCode providers, the runner registers a placeholder API key and **`ANTHROPIC_BASE_URL`** (the credential proxy) as `baseURL` so the real key never lives in the container. +Credentials: register provider API keys in OneCLI with the matching `--host-pattern` (e.g. `api.deepseek.com`, `openrouter.ai`). OneCLI injects them via `HTTPS_PROXY` in the container — the key never lives in `.env` or the container environment. + +After adding a secret, **grant the agent access** — agents in `selective` mode only receive secrets they've been explicitly assigned: + +```bash +# Find the agent id and secret id, then: +onecli agents set-secrets --id --secret-ids , +``` + +Always include existing secret IDs in the list — `set-secrets` replaces, not appends. + +#### Example: DeepSeek + +```env +OPENCODE_PROVIDER=deepseek +OPENCODE_MODEL=deepseek/deepseek-chat +OPENCODE_SMALL_MODEL=deepseek/deepseek-chat +ANTHROPIC_BASE_URL=https://api.deepseek.com/v1 +``` + +Register the key: +```bash +onecli secrets create --name "DeepSeek" --type generic \ + --value YOUR_KEY --host-pattern "api.deepseek.com" \ + --header-name "Authorization" --value-format "Bearer {value}" +``` #### Example: OpenRouter ```env -# OpenCode — host passes these into the container when agent_provider is opencode OPENCODE_PROVIDER=openrouter OPENCODE_MODEL=openrouter/anthropic/claude-sonnet-4 OPENCODE_SMALL_MODEL=openrouter/anthropic/claude-haiku-4.5 +ANTHROPIC_BASE_URL=https://openrouter.ai/api/v1 ``` -#### Example: Anthropic via existing proxy env +Register the key: +```bash +onecli secrets create --name "OpenRouter" --type generic \ + --value YOUR_KEY --host-pattern "openrouter.ai" \ + --header-name "Authorization" --value-format "Bearer {value}" +``` -When `OPENCODE_PROVIDER` is `anthropic`, OpenCode uses normal Anthropic env inside the container (proxy + placeholder key pattern unchanged). +#### Example: Anthropic (no ANTHROPIC_BASE_URL needed) + +When `OPENCODE_PROVIDER` is `anthropic`, OpenCode uses normal Anthropic env inside the container — the proxy + placeholder key pattern is unchanged and `ANTHROPIC_BASE_URL` is not required. ```env OPENCODE_PROVIDER=anthropic OPENCODE_MODEL=anthropic/claude-sonnet-4-20250514 -``` - -#### Example: only a main model - -```env -OPENCODE_PROVIDER=openrouter -OPENCODE_MODEL=openrouter/google/gemini-2.5-pro-preview +OPENCODE_SMALL_MODEL=anthropic/claude-haiku-4-5-20251001 ``` #### OpenCode Zen (`x-api-key`, not Bearer) @@ -142,13 +190,9 @@ Zen's HTTP API (e.g. `POST …/zen/v1/messages`) expects the key in the **`x-api **Host `.env` (typical Zen shape):** ```env -# NanoClaw still resolves AGENT_PROVIDER from agent_groups / sessions; set agent_provider to opencode there. -# OpenCode SDK: Zen as the upstream provider + models under opencode/… OPENCODE_PROVIDER=opencode OPENCODE_MODEL=opencode/big-pickle OPENCODE_SMALL_MODEL=opencode/big-pickle - -# Point the credential proxy at Zen's Anthropic-compatible base URL (host + OneCLI must forward this host). ANTHROPIC_BASE_URL=https://opencode.ai/zen/v1 ``` @@ -162,8 +206,6 @@ onecli secrets create --name "OpenCode Zen" --type generic \ --header-name "x-api-key" --value-format "{value}" ``` -For comparison, OpenRouter uses `Authorization` + `Bearer {value}`. Zen is different by design. - ### Per group / per session Schema: **`agent_groups.agent_provider`** and **`sessions.agent_provider`**. Set to `opencode` for groups or sessions that should use OpenCode. The container receives `AGENT_PROVIDER` from the resolved value (session overrides group). @@ -173,7 +215,7 @@ Extra MCP servers still come from **`NANOCLAW_MCP_SERVERS`** / `container_config ## Operational notes - OpenCode keeps a local **`opencode serve`** process and SSE subscription; the provider tears down with **`stream.return`** and **SIGKILL** on the server process on **`abort()`** / shared runtime reset to avoid MCP/zombie hangs. -- Session continuation is opaque (`ses_*` ids); stale sessions are cleared using **`isSessionInvalid`** on OpenCode-specific errors (timeouts, connection resets, not-found patterns) in addition to the poll-loop's existing recovery. +- Session continuation uses UUID format (SDK 1.4.x / CLI 1.4.x). Stale sessions are cleared by `isSessionInvalid` on OpenCode-specific error patterns. If you see UUID-related errors after an accidental CLI upgrade, clear `session_state` in `outbound.db` and wipe the `opencode-xdg` directory under the session folder. - **`NO_PROXY`** for localhost matters when the OpenCode client talks to `127.0.0.1` inside the container while HTTP(S)_PROXY is set (e.g. OneCLI). ## Verify From 47950671fafcf0da34f4459d783be322f827f270 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 01:00:04 +0300 Subject: [PATCH 16/95] =?UTF-8?q?docs:=20add=20v1=E2=86=92v2=20action-item?= =?UTF-8?q?s=20analysis=20+=20SDK=20signal=20probe=20tool?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - docs/v1-vs-v2/: full v1→v2 regression analysis (SUMMARY + 21 per-module docs + ACTION-ITEMS rollup with decisions + timezone recreation spec). - container/agent-runner/scripts/sdk-signal-probe.ts: empirical harness used to characterise Claude Agent SDK event/hook/stderr timing for the stuck-detection design in item 9. - src/channels/chat-sdk-bridge.ts: document the conversations Map staleness in a code comment; fix deferred to when dynamic group registration lands (ACTION-ITEMS item 17). No runtime behavior change. Co-Authored-By: Claude Opus 4.7 (1M context) --- .../agent-runner/scripts/sdk-signal-probe.ts | 169 ++++++ docs/v1-vs-v2/ACTION-ITEMS.md | 530 ++++++++++++++++ docs/v1-vs-v2/SUMMARY.md | 146 +++++ docs/v1-vs-v2/channels.md | 305 ++++++++++ docs/v1-vs-v2/config.md | 99 +++ docs/v1-vs-v2/container-index.md | 72 +++ docs/v1-vs-v2/container-mcp-tools.md | 59 ++ docs/v1-vs-v2/container-runner.md | 51 ++ docs/v1-vs-v2/container-runtime.md | 46 ++ docs/v1-vs-v2/db.md | 542 +++++++++++++++++ docs/v1-vs-v2/env.md | 38 ++ docs/v1-vs-v2/formatting-test.md | 154 +++++ docs/v1-vs-v2/group-folder.md | 38 ++ docs/v1-vs-v2/group-queue.md | 48 ++ docs/v1-vs-v2/index-host.md | 70 +++ docs/v1-vs-v2/ipc.md | 240 ++++++++ docs/v1-vs-v2/logger.md | 38 ++ docs/v1-vs-v2/remote-control.md | 90 +++ docs/v1-vs-v2/router.md | 67 ++ docs/v1-vs-v2/sender-allowlist.md | 46 ++ docs/v1-vs-v2/session-cleanup.md | 44 ++ docs/v1-vs-v2/task-scheduler.md | 100 +++ .../timezone-formatting-v1-recreation.md | 570 ++++++++++++++++++ docs/v1-vs-v2/timezone.md | 27 + docs/v1-vs-v2/types.md | 58 ++ src/channels/chat-sdk-bridge.ts | 6 + 26 files changed, 3653 insertions(+) create mode 100644 container/agent-runner/scripts/sdk-signal-probe.ts create mode 100644 docs/v1-vs-v2/ACTION-ITEMS.md create mode 100644 docs/v1-vs-v2/SUMMARY.md create mode 100644 docs/v1-vs-v2/channels.md create mode 100644 docs/v1-vs-v2/config.md create mode 100644 docs/v1-vs-v2/container-index.md create mode 100644 docs/v1-vs-v2/container-mcp-tools.md create mode 100644 docs/v1-vs-v2/container-runner.md create mode 100644 docs/v1-vs-v2/container-runtime.md create mode 100644 docs/v1-vs-v2/db.md create mode 100644 docs/v1-vs-v2/env.md create mode 100644 docs/v1-vs-v2/formatting-test.md create mode 100644 docs/v1-vs-v2/group-folder.md create mode 100644 docs/v1-vs-v2/group-queue.md create mode 100644 docs/v1-vs-v2/index-host.md create mode 100644 docs/v1-vs-v2/ipc.md create mode 100644 docs/v1-vs-v2/logger.md create mode 100644 docs/v1-vs-v2/remote-control.md create mode 100644 docs/v1-vs-v2/router.md create mode 100644 docs/v1-vs-v2/sender-allowlist.md create mode 100644 docs/v1-vs-v2/session-cleanup.md create mode 100644 docs/v1-vs-v2/task-scheduler.md create mode 100644 docs/v1-vs-v2/timezone-formatting-v1-recreation.md create mode 100644 docs/v1-vs-v2/timezone.md create mode 100644 docs/v1-vs-v2/types.md diff --git a/container/agent-runner/scripts/sdk-signal-probe.ts b/container/agent-runner/scripts/sdk-signal-probe.ts new file mode 100644 index 000000000..a4a3c98fe --- /dev/null +++ b/container/agent-runner/scripts/sdk-signal-probe.ts @@ -0,0 +1,169 @@ +#!/usr/bin/env bun +/** + * SDK signal probe: run a prompt, log every signal the Agent SDK emits — + * async-iterator events + hook callbacks + CLI stderr — with absolute + * and relative timing. + * + * Usage: + * bun run scripts/sdk-signal-probe.ts "" # simple string mode + * bun run scripts/sdk-signal-probe.ts --stream "" # streaming-input mode + * bun run scripts/sdk-signal-probe.ts --stream "

" \ + * --push "5000:" --push "15000:" --timeout 60000 # multi-push + * + * Streaming mode (`--stream`) passes an AsyncIterable prompt to `query()`, + * which keeps the CLI subprocess alive past the first result (per SDK + * deep dive). Required for post-result pushes, agent teams, background + * task notifications. + */ +import { query } from '@anthropic-ai/claude-agent-sdk'; + +const args = process.argv.slice(2); +const prompts: string[] = []; +const pushes: Array<{ atMs: number; text: string }> = []; +let streamMode = false; +let timeoutMs: number | undefined; + +for (let i = 0; i < args.length; i++) { + const a = args[i]; + if (a === '--stream') streamMode = true; + else if (a === '--push') { + const val = args[++i] ?? ''; + const ix = val.indexOf(':'); + if (ix === -1) throw new Error(`bad --push (want MS:text): ${val}`); + pushes.push({ atMs: parseInt(val.slice(0, ix), 10), text: val.slice(ix + 1) }); + } else if (a === '--timeout') timeoutMs = parseInt(args[++i] ?? '0', 10); + else if (a === '--prompt') prompts.push(args[++i] ?? ''); + else prompts.push(a); +} + +const prompt = prompts.join(' '); +if (!prompt) { + console.error('usage: sdk-signal-probe.ts [--stream] "" [--push MS:]... [--timeout MS]'); + process.exit(1); +} + +const T0 = Date.now(); +let LAST = T0; + +function log(source: string, type: string, payload: unknown = {}): void { + const now = Date.now(); + const entry = { t_ms: now - T0, d_ms: now - LAST, source, type, payload }; + LAST = now; + console.log(JSON.stringify(entry)); +} + +function hookLogger(eventName: string) { + return async (input: unknown, toolUseID: string | undefined): Promise => { + log('hook', eventName, { toolUseID, input }); + // Stuck-tool simulation: if env flag is set and this is a PreToolUse for Bash, + // never resolve — simulates a tool that hangs forever. + if (process.env.PROBE_HANG === 'true' && eventName === 'PreToolUse') { + const toolName = (input as any)?.tool_name ?? (input as any)?.name; + if (toolName === 'Bash') { + log('meta', 'pre_tool_use_hanging', { toolUseID, toolName }); + await new Promise(() => { + /* never resolves */ + }); + } + } + return { continue: true }; + }; +} + +const HOOK_EVENTS = [ + 'PreToolUse', + 'PostToolUse', + 'PostToolUseFailure', + 'Notification', + 'UserPromptSubmit', + 'SessionStart', + 'SessionEnd', + 'Stop', + 'SubagentStart', + 'SubagentStop', + 'PreCompact', + 'PermissionRequest', +] as const; + +const hooks: Record = {}; +for (const ev of HOOK_EVENTS) hooks[ev] = [{ hooks: [hookLogger(ev)] }]; + +// Build prompt — string (single-turn) or AsyncIterable (streaming-input) +let promptInput: any; + +if (streamMode) { + const sessionId = `probe-${Date.now()}`; + async function* streamPrompt() { + // Initial user message + yield { + type: 'user' as const, + message: { role: 'user' as const, content: prompt }, + parent_tool_use_id: null, + session_id: sessionId, + }; + // Schedule subsequent pushes + const startT = Date.now(); + const sorted = [...pushes].sort((a, b) => a.atMs - b.atMs); + for (const p of sorted) { + const waitMs = Math.max(0, p.atMs - (Date.now() - startT)); + if (waitMs > 0) await new Promise((r) => setTimeout(r, waitMs)); + log('meta', 'push_message', { atMs: p.atMs, text: p.text }); + yield { + type: 'user' as const, + message: { role: 'user' as const, content: p.text }, + parent_tool_use_id: null, + session_id: sessionId, + }; + } + // Keep stream open for tail events; iterator ends when we return + // (no more work expected). For post-result-idle scenarios, wait here. + await new Promise((r) => setTimeout(r, 5000)); + } + promptInput = streamPrompt(); +} else { + promptInput = prompt; +} + +log('meta', 'probe_start', { prompt, streamMode, pushes, timeoutMs }); + +const q = query({ + prompt: promptInput, + options: { + includePartialMessages: true, + hooks: hooks as any, + stderr: (data: string) => log('stderr', 'chunk', { data }), + settingSources: [], + permissionMode: 'bypassPermissions', + allowDangerouslySkipPermissions: true, + }, +}); + +// Absolute time cap — exit cleanly so the log flushes +if (timeoutMs) { + setTimeout(() => { + log('meta', 'timeout_hit', { timeoutMs }); + setTimeout(() => process.exit(0), 250); + }, timeoutMs); +} + +try { + for await (const event of q) { + const snapshot: any = { ...event }; + try { + const raw = JSON.stringify(snapshot); + if (raw.length > 2000) { + snapshot._truncated_bytes = raw.length; + if (snapshot.message?.content) { + const c = JSON.stringify(snapshot.message.content); + snapshot.message = { ...snapshot.message, content: c.slice(0, 500) + `…<+${c.length - 500}b>` }; + } + } + } catch { + /* best-effort */ + } + log('event', snapshot.type ?? 'unknown', { subtype: snapshot.subtype, event: snapshot }); + } + log('meta', 'iterator_done'); +} catch (err: any) { + log('meta', 'iterator_error', { message: err?.message, stack: err?.stack?.split('\n').slice(0, 5) }); +} diff --git a/docs/v1-vs-v2/ACTION-ITEMS.md b/docs/v1-vs-v2/ACTION-ITEMS.md new file mode 100644 index 000000000..806bff467 --- /dev/null +++ b/docs/v1-vs-v2/ACTION-ITEMS.md @@ -0,0 +1,530 @@ +# v1 → v2 Action Items + +Working doc for each finding from [SUMMARY.md](SUMMARY.md). Decisions were made one-by-one; this rollup summarizes the outcome. + +**Status legend**: `pending` · `discussing` · `decided` · `deferred` · `dropped` · `done` + +--- + +## Rollup + +### To implement (~800 LOC total, roughly) + +| # | Topic | LOC | Notes | +|---|---|---|---| +| 1 | Engage modes + sender scope + accumulate/drop + fan-out + tool blocklist | ~315 | DB migration drops `trigger_rules`/`response_scope`, adds `engage_mode`/`engage_pattern`/`sender_scope`/`ignored_message_policy` + `trigger` column on `messages_in`; router `pickAgents` fan-out; adapter-level gating via new hooks | +| 5 | `request_approval` flow for unknown senders (default policy flips from `strict` to `request_approval`) | ~175 | New `pending_sender_approvals` table; reuses existing `pickApprover` + card infra | +| 9 | Stuck detection (60s claim-age rule), heartbeat-based lifecycle, `max(30m, bash_timeout)` absolute ceiling, SDK tool blocklist (`AskUserQuestion`, `EnterPlanMode`, `ExitPlanMode`, `EnterWorktree`, `ExitWorktree`), remove `IDLE_TIMEOUT` setTimeout + `IDLE_END_MS` machinery | ~115 | Container state row for Bash timeout tracking | +| 15 | Delete three dead config constants from `src/config.ts` | 3 | `POLL_INTERVAL`, `SCHEDULER_POLL_INTERVAL`, `IPC_POLL_INTERVAL` | +| 18 | Timezone + formatting recreation — port v1 bit-for-bit (`formatLocalTime`, `` header, `reply_to` + `` XML, `stripInternalTags`) + scheduling tool TZ normalization + cron TZ parsing | ~195 (75 prod + 120 tests) | Full spec in [timezone-formatting-v1-recreation.md](timezone-formatting-v1-recreation.md) | + +### Deferred (wait for trigger) + +| # | Topic | Trigger | +|---|---|---| +| 2 | `nonMainReadOnly` mount isolation | If multi-tenant / untrusted-group use ever surfaces. In the meantime, mount-declaration skill must explicitly prompt RO/RW when added | +| 3a | End-to-end recovery test | When next touching `host-sweep.ts` / `index.ts` startup | +| 14 | Remote control subsystem | When someone needs it. Opt-in skill, provider-specific (Claude SDK only) | +| 17 | Dynamic group-add (bridge conversations cache refresh) | When implementing dynamic group registration feature. Code comment added at `chat-sdk-bridge.ts:73` | + +### Dropped (won't implement / not-a-regression) + +| # | Topic | Why | +|---|---|---| +| 3 | Explicit pending-message recovery | Working as designed via sweep's immediate first tick + `cleanupOrphans` | +| 4 | `response_scope` enforcement | Folded into item 1 migration (column deleted, values backfilled) | +| 6 | Per-group container timeout | Not a regression — v1's hard-kill was worse than v2's keep-alive-after-idle | +| 7 | Container streaming output markers | Replaced by `send_message` MCP tool; latency ~1s is fine for chat UX | +| 8 | Per-exit container log files | Underlying info still recoverable (session DBs, heartbeat mtime, exit code) | +| 10 | Host-level retry on agent error | Folded into item 9's kill + sweep-reset loop | +| 11 | Process ID in logger output | Single host process; container stderr already tagged with `agentGroup.folder` | +| 12 | Task dedup via unique series_id index | Recurrence logic is structurally dedup-safe; not a real issue | +| 13 | Silent-drop sender mode | Admin can use `unknown_sender_policy='strict'` or remove from members instead | +| 16 | Configurable retention thresholds | Personal-assistant scale; source constants are fine | + +### Extras recorded during discussion +- **1a**: Implementation-ordering plan for item 1 +- **6a**: Remove `IDLE_END_MS` from `poll-loop.ts` (folded into item 9) +- **3a**: E2E recovery test (deferred) + +--- + +## HIGH + +### 1. Trigger-rule matching in `pickAgent` +**Finding**: `src/router.ts:246` TODO. Confirmed trigger filtering is non-functional end-to-end: `trigger_rules` JSON is parsed into `ConversationConfig` and passed to adapters, but the Chat SDK bridge never reads it, and router's `pickAgent` picks by priority only. `response_scope` on `messaging_group_agents` is stored but never enforced. Chat SDK bridge hard-subscribes on every mention (bridge:173) and every DM (bridge:189). + +**Status**: decided — design locked; implementation pending + +**Decision**: replace `trigger_rules` JSON + `response_scope` with four explicit orthogonal columns on `messaging_group_agents`. Fan out inbound messages to all matching agents (N containers for N agents). Adapter-level gating in the bridge. `sender_scope` enforcement moves to the permissions module. + +**Schema** (`messaging_group_agents`): +``` +engage_mode TEXT NOT NULL DEFAULT 'mention' + -- 'pattern' | 'mention' | 'mention-sticky' +engage_pattern TEXT -- required when mode='pattern'; '.' = always +sender_scope TEXT NOT NULL DEFAULT 'all' -- 'all' | 'known' +ignored_message_policy TEXT NOT NULL DEFAULT 'drop' -- 'drop' | 'accumulate' +``` +Drop `trigger_rules` + `response_scope`. **No per-wiring accumulate cap** — storage is unbounded. + +**Global wake cap** (not a column): reuse `MAX_MESSAGES_PER_PROMPT` in `src/config.ts` (already defined, default 10, currently dead code from v1). Pass to container via `NANOCLAW_MAX_MESSAGES_PER_PROMPT`. Container applies `ORDER BY seq DESC LIMIT $N` when pulling pending messages on wake. + +**Session DB** (`messages_in`): +``` +trigger INTEGER NOT NULL DEFAULT 1 -- 0 = context-only, 1 = wake agent +``` +Host's `countDueMessages` / wake logic gates on `trigger=1`. Container reads all messages for context regardless. + +**Decisions locked**: +- `always` collapses into `pattern` with `engage_pattern='.'` (three modes total) +- `mention` and `mention-sticky` are separate modes (stickiness is user-visible) +- `pattern` is a JS regex string — applied as `new RegExp(pattern).test(text)` +- Accumulate cap = last N messages, default 10 +- Fan-out: each matching agent gets its own session + container +- Per-channel defaults live in the setup/register flow, not in the schema: + - DM → `pattern` with `.` + - Threaded group → `mention-sticky` + - Non-threaded group → `mention` + +**Routing flow** (future): +1. Inbound → resolve messaging_group → group-level `unknown_sender_policy` gate +2. `pickAgents()` returns all wired agents (not just priority 0) +3. For each agent: + a. `sender_scope` check (permissions module) + b. `engage_mode` check (regex / mention / mention-sticky) + c. Matched → write with `trigger=1`, wake container + d. Not matched + `accumulate` → write with `trigger=0`, don't wake (no cap — stored forever) + e. Not matched + `drop` → skip + +On wake, container pulls pending messages with `ORDER BY seq DESC LIMIT MAX_MESSAGES_PER_PROMPT` so only the most recent N reach the prompt regardless of accumulation depth. + +**Adapter bridge**: +- Read `conversations.get(channelId)` before `setupConfig.onInbound(...)` +- For `pattern` mode: test regex +- For `mention` / `mention-sticky`: require bot to be mentioned +- Only `thread.subscribe()` when mode is `mention-sticky` (today it subscribes unconditionally) + +**LOC estimate**: ~315 (~255 prod + ~60 test) +- schema migration + backfill: 40 +- session DB `trigger` column: 25 +- types + adapter contract: 20 +- DB helpers (CRUD): 20 +- host→adapter plumbing (including `NANOCLAW_MAX_MESSAGES_PER_PROMPT` env): 10 +- router fan-out + gating: 70 +- sender-scope in permissions module: 15 +- Chat SDK bridge gating + subscribe control: 40 +- container-side `LIMIT N` on pending-message pull: 5 +- smart defaults in setup/register flow: 15 +- tests: 60 + +(Note: earlier plan's "accumulate prune-to-N in router" is dropped — host doesn't prune. Cap is container-side only.) + +**Core vs module split**: +- Core (`src/`): schema, engage_mode enforcement, pickAgents fan-out, bridge gating, `trigger` column, accumulate/drop +- Permissions module: `sender_scope` enforcement (extends existing access gate). Default `sender_scope='all'` → no-op when permissions module absent + +**Next step**: new action item for implementation — see item 1a. + +--- + +### 1a. Implementation plan for engage/sender/ignored columns +**Status**: pending — ready to implement +**Order**: (a) migration + backfill, (b) types + DB helpers, (c) router fan-out + gating, (d) bridge gating, (e) permissions sender_scope, (f) setup-flow defaults, (g) tests +**Next step**: draft the migration + write up the PR plan when ready + +### 2. `nonMainReadOnly` mount isolation +**Finding**: `mount-security.ts` moved to `src/modules/mount-security/index.ts` during the refactor. `validateMount(mount)` no longer takes an `isMain` param; `MountAllowlist` has no `nonMainReadOnly` field. Regression is real. But v1's "main vs non-main" concept doesn't map cleanly to v2 — `agent_groups` has no `is_main` flag. + +**Status**: deferred + +**Decision**: do not restore the v1 flag. Trust admin-declared `readonly` values in `container.json`. The allowlist's per-root `allowReadWrite` + path gating is sufficient for the current threat model (personal-assistant use, single admin). If multi-tenant / untrusted auxiliary groups become a real use case, prefer framing B (add `agent_groups.mount_access: 'rw' | 'ro'` column) over resurrecting `isMain`. + +**Rationale**: v2 deliberately dropped the "main" concept. Reintroducing `isMain` to restore a defense-in-depth check that was designed for a different entity model is the wrong trade. Admin already has to opt-in twice (allowlist `allowReadWrite: true` + container.json `readonly: false`) to get RW — that's two deliberate keys. The v1 flag was a triple-check for a rare class of admin mistakes in a shared-infra setup. + +**Follow-up (required)**: when building the skill / guide / setup flow that lets admins declare additional mounts (e.g. self-customize, manage-mounts, or a new `/add-mount` skill), the flow **must clearly surface the RO vs RW distinction** to the admin — explicit choice, explicit warning when RW is selected, and default to RO. This replaces v1's automatic enforcement with informed consent. + +**Next step**: when the mount-declaration skill/flow is next touched, add explicit RO/RW prompting. Track as a sub-item if a skill exists yet. + +### 3. Explicit pending-message recovery on startup +**Finding**: v1 had a named `recoverPendingMessages()` function at startup. v2 relies on the host sweep. Verified: the recovery path exists and is correct — just renamed/relocated. + +**Status**: decided — working as designed, no code change + +**Current mechanism** (verified against tree): +1. `cleanupOrphans()` at startup kills any leftover container from the previous run (`src/index.ts:69`) +2. `startHostSweep()` runs its first sweep **immediately** — no 60s delay (`src/host-sweep.ts:38`) +3. Sweep per session: `syncProcessingAcks` → `countDueMessages` → `wakeContainer` if work pending and no container → `detectStaleContainers` resets stuck `processing` rows with backoff + +**Scenarios covered**: +- Host crashed while container idle with pending messages → orphan cleanup + first sweep re-wakes +- Host crashed mid-processing → stale detection resets `processing → pending`, next sweep wakes +- Container crashed with host alive → heartbeat mtime catches it inside 10 min `STALE_THRESHOLD_MS` + +**Rationale**: the function got renamed (recovery → sweep) but the behavior is equivalent or better. Sweep is continuous; recovery used to be one-shot. + +**Next step**: see item 3a. + +--- + +### 3a. End-to-end recovery test +**Finding**: no test confirms the host-crash-restart scenario produces timely re-delivery. + +**Status**: pending — nice-to-have + +**Decision**: add an integration test: (1) write a pending message to inbound.db, (2) kill the host simulating crash, (3) start host, (4) assert container is woken and message processed within a bounded time (≤5s? ≤ one sweep interval). + +**Rationale**: the sweep logic is correct as written, but a regression here would be silent (messages just sit). Worth a safety net. + +**Next step**: draft test when touching `host-sweep.ts` or `index.ts` startup flow next. + +--- + +## MEDIUM + +### 4. `response_scope` enforcement +**Finding**: `messaging_group_agents.response_scope` stores `'all' | 'triggered' | 'allowlisted'` but nothing reads it. + +**Status**: decided — folded into item 1 + +**Decision**: delete the `response_scope` column as part of the item-1 migration. Values backfill into the new explicit columns: + +| Old `response_scope` | New columns | +|---|---| +| `all` | `engage_mode='pattern'`, `engage_pattern='.'`, `sender_scope='all'` | +| `triggered` | `engage_mode='mention'` (or `'pattern'` if legacy row has a pattern), `sender_scope='all'` | +| `allowlisted` | `engage_mode` derived from `trigger_rules`, `sender_scope='known'` | + +**Rationale**: `response_scope` conflated two orthogonal axes (engage + sender). Splitting them is the whole point of item 1. + +**Next step**: ensure the item-1 migration includes the `response_scope` backfill in its UP step. + +### 5. `request_approval` flow for unknown senders +**Finding**: `unknown_sender_policy='request_approval'` is scaffolded in `src/modules/permissions/index.ts:100-108` but falls through to log-and-drop (explicit TODO comment). Current default is `'strict'`, which silently drops — user has no signal that their agent isn't responding. + +**Status**: decided — implement, keep simple + +**Decision**: implement full approval flow **and** flip the schema default from `'strict'` to `'request_approval'`. UX rationale: users wire their DM during setup; silent drops create a mystery when the agent doesn't respond. Public is unsafe. Approval default → admin sees a card and explicitly decides. + +**Flow**: +1. Unknown sender writes to wired messaging group with policy `'request_approval'` +2. If pending approval for `(messaging_group, sender)` already exists → drop this message silently (in-flight dedup; not persistence) +3. Otherwise: insert into `pending_sender_approvals` with original message + timestamp +4. `pickApprover(agent_group_id)` + `pickApprovalDelivery(approverUserId)` — existing machinery in `src/access.ts` +5. Deliver a card via adapter's `deliver()` with `Card`/`Actions`/`Button` primitives (already in chat-sdk-bridge) +6. Card action id prefix `nsa::` (parallels existing `ncq:` prefix for `ask_user_question`) +7. On `allow`: upsert `users` row, insert into `agent_group_members`, deliver stored message through normal routing (original timestamp preserved), cleanup pending row +8. On `deny`: cleanup pending row, drop the message. No denial persistence — next attempt from same sender triggers a fresh card. + +**No denial persistence** explicit rationale: personal-assistant scale, admin can switch policy to `'strict'` per messaging group if a hostile sender starts spamming. Avoids a new table column and a TTL config. + +**New table**: +``` +pending_sender_approvals ( + id TEXT PRIMARY KEY, + messaging_group_id TEXT NOT NULL, + agent_group_id TEXT NOT NULL, + sender_identity TEXT NOT NULL, -- channel_type:handle + sender_name TEXT, + original_message TEXT NOT NULL, -- JSON of the InboundEvent + approver_user_id TEXT NOT NULL, + created_at TEXT NOT NULL, + UNIQUE(messaging_group_id, sender_identity) -- enforces in-flight dedup +) +``` +Dedicated (not reusing `pending_approvals` which is OneCLI-specific). + +**Reuse**: +- `pickApprover` / `pickApprovalDelivery` in `src/access.ts` +- Card rendering primitives already in `src/channels/chat-sdk-bridge.ts` +- `onAction` dispatch — add the `nsa:` prefix handler alongside existing `ncq:` + +**LOC estimate**: ~175 +- Migration + CRUD for `pending_sender_approvals`: 55 +- `handleUnknownSender` request_approval branch + in-flight dedup: 25 +- Host-side card dispatcher (pick approver + deliver card): 25 +- `onAction` handler for `nsa:` prefix (allow/deny): 30 +- Schema default flip + router auto-create update: 5 +- Tests: 35 + +**Module location**: all in `src/modules/permissions/`. Module stays optional; default-allow fallback behavior when not loaded is preserved. + +**Open gotchas noted**: +- The router's auto-create at `router.ts:123` currently hardcodes `'strict'` — change to omit the field so schema default applies +- `pickApprover` may return null if no admin/owner exists (e.g. fresh install before first user registered). In that case: log + drop silently, treat as effectively `'strict'` for safety. Don't block message forever. + +**Next step**: implement alongside item 1 or as a follow-up. Same migration window is fine (one migration for engage columns + request_approval default change + new table). + +### 6. Per-group container timeout +**Finding**: v1's `containerConfig.timeout` override is gone. All groups share `IDLE_TIMEOUT`. Original framing (slow-but-healthy agents getting killed) was wrong — v1's `timeout` was a hard wall-clock kill on the whole spawn, totally different from v2's `IDLE_TIMEOUT` (keep-alive after last activity). V2's behavior is strictly better for long-running agents. + +**Status**: dropped — not a regression + +**Decision**: don't restore per-group timeout override. `IDLE_TIMEOUT=30min` global is the right model. If per-group idle tuning ever becomes useful it's ~15 LOC (new column, env injection at spawn) — small feature add, not a regression to repair. + +**Rationale**: v2 lets long-running agents finish; v1 would have hard-killed them at 30min. Current behavior is an improvement. + +**Next step**: see 6a. + +--- + +### 6a. Remove IDLE_END_MS (container-side query idle termination) +**Finding**: `container/agent-runner/src/poll-loop.ts:11` defines `IDLE_END_MS = 20_000`. Inside `processQuery`, a concurrent interval ends the active Agent SDK `query()` stream after 20s of SDK silence. Any SDK event (tool use, tool result, streamed text, new pushed message) resets the timer. + +This is a general "SDK silence detector," not specifically post-result. It fires any time: +- Mid-work: slow tool call with no intermediate SDK events (`npm install`, `pytest`, long `WebFetch`, etc.) +- Post-result: agent finished, stream waiting for potential follow-up +- Any other pause in the SDK stream + +**Status**: decided — remove, pending SDK verification + +**Decision**: delete `IDLE_END_MS` and its setInterval check. Let the `query()` stream stay open as long as the container is active. Container's 30-min `IDLE_TIMEOUT` (host-side in `container-runner.ts`) is the single source of truth for "when to let go." + +**Rationale**: +- When new messages arrive mid-stream, they push in via `query.push()` with no reconnect — stream-open is cheaper per-message than close-and-reopen +- Closing early forces a reconnect + cold prompt cache for the next message +- Container stays alive anyway; ending the stream doesn't save resources at the container level +- `CLAUDE_CODE_AUTO_COMPACT_WINDOW=165000` already handles context window growth within a long-lived query +- Anthropic API's own stream timeout will fire if needed; SDK should handle it transparently +- Avoids the false-positive kill during legitimate slow tool calls (common case: agent running `npm install` gets cut off at 20s) + +**Caveat (must verify before removal)**: confirm Claude Agent SDK doesn't require explicit `query.end()` for prompt-cache commit or session-state persistence. Expected to be fine (SDK checkpoints per turn) but double-check docs / run a quick test where container idles with stream open, then processes a follow-up. + +**LOC estimate**: ~−15 (net deletion — remove constant, setInterval idle check, the `done` flag plumbing may also simplify) + +**Next step**: when implementing item 1's changes (or standalone), verify SDK behavior with stream-open-indefinite, then delete IDLE_END_MS block. Watch for any test assertions on it. + +### 7. Container streaming output (marker-based pre-delivery) +**Finding**: v1's `---NANOCLAW_OUTPUT_START/END---` markers enabled pre-completion delivery. v2's two paths (final-result `dispatchResultText` + mid-turn `send_message` MCP tool) both write to outbound.db; host polls every `ACTIVE_POLL_MS = 1000ms`. + +**Status**: dropped — not a regression + +**Decision**: v2's `send_message` MCP tool is the correct replacement for v1's marker-based streaming. Latency is ≤1s (poll interval), which is fine for chat UX. + +**Rationale**: v1's marker model required the agent and host to share a fragile state machine over stdout. v2 uses explicit tool calls and a DB surface — cleaner architecture, comparable latency, and control stays with the agent. If perceived latency ever becomes a real complaint, tune `ACTIVE_POLL_MS` down (500ms / 250ms) — low-cost knob. + +**Next step**: none. + +### 8. Per-exit container log files +**Finding**: v1 wrote timestamped per-exit logs with full I/O + mounts + stderr. v2: stderr → `log.debug` (invisible at default `LOG_LEVEL=info`), container close → `log.info` with exit code, session DBs preserved on disk. Real gap: stderr on abnormal exit isn't auto-surfaced. + +**Status**: dropped + +**Decision**: skip — no per-exit file restoration, no stderr-on-crash buffer. + +**Rationale**: underlying forensic info is still recoverable (session DBs on disk, heartbeat mtime, exit code in log). `LOG_LEVEL=debug` surfaces stderr when needed. The cost of adding buffered crash-log promotion (~15 LOC) isn't justified by the frequency of post-mortem cases. + +**Next step**: none. + +### 9. Stuck detection + heartbeat-based container lifecycle +**Finding**: v2's sweep detects stale heartbeats (10 min) and resets messages with backoff, but doesn't kill the container. Idle timeout is delivery-count-based (30 min since last messages_out). Together these produce a gap where a stuck container holds resources + blocks new wakes for up to 30 min. + +**Empirical findings from SDK probe** (`container/agent-runner/scripts/sdk-signal-probe.ts`, runs logged in `/tmp/probe-*.jsonl`): +- Silent Bash tools (e.g. `sleep 30`) produce 30+ seconds of zero SDK events — heartbeat goes stale during legitimate work +- Natural intra-stream silences up to ~12s observed mid-tool-use JSON streaming +- `PreToolUse` / `PostToolUse` hook pair is reliable; `PostToolUseFailure` fires on blocked requests +- `SubagentStart`/`SubagentStop` and `system/task_started`/`system/task_notification` pairs also reliable +- **Pushing a new message mid-active-turn does NOT fire `UserPromptSubmit`** (fires only at start of a new turn, after `result`) +- SDK's built-in `AskUserQuestion` doesn't actually block; returns placeholder +- Bash tool's declared `timeout` param is visible in `tool_use` input — we can read it container-side +- Stuck tools (hook that never resolves) produce indefinite silence — no SDK-side timeout + +**Status**: decided + +**Decision**: replace existing IDLE_TIMEOUT setTimeout + STALE_THRESHOLD=10min combo with message-scoped stuck detection + absolute 30-min ceiling. Reset messages inline when we kill. Blocklist SDK tools that don't fit our async model. + +**Sweep logic** (per active session): + +If container isn't running → reset any `'processing'` rows in processing_ack to `'pending'` + tries++ + backoff. Done. + +If container IS running, apply in order: + +1. **Absolute ceiling**: if `heartbeat_mtime` older than `max(30 min, current_bash_timeout)` → kill + reset any processing to pending + retry++. + Rationale: 30 min idle ceiling, extended only if agent is currently inside a Bash tool with longer declared timeout. Agents needing >30 min should use `run_in_background`. + +2. **Message-scoped stuck**: for each `processing_ack` row with status=`'processing'`: + - `claim_age = now - status_changed` + - `tolerance = max(60s, current_bash_timeout)` if Bash in flight, else `60s` + - If `claim_age > tolerance` AND `heartbeat_mtime <= status_changed` → kill + reset this message + retry++ + + Semantics: "container claimed a message and went silent for >tolerance since claim." + +No separate idle rule — rule 1 covers it. An idle container hits 30-min stale with no processing rows; kill has nothing to reset. + +**Container state surface** (for Bash timeout tracking): +New table in outbound.db (or session_state row): +``` +container_state ( + session_id TEXT PRIMARY KEY, + current_tool TEXT, -- null when no tool in flight + tool_declared_timeout_ms INTEGER, + tool_started_at TEXT +) +``` +Container writes on `PreToolUse` (reads Bash `timeout` from tool input), clears on `PostToolUse` / `PostToolUseFailure`. Host reads in sweep decision. + +**Tool blocklist** (initial): +- `AskUserQuestion` — SDK built-in; we have our own DB-backed MCP version +- `EnterPlanMode` / `ExitPlanMode` — Claude Code UI only +- `EnterWorktree` / `ExitWorktree` — Claude Code UI only + +Enforcement: +- Pass `disallowedTools: [...]` to `query()` options — agent never sees them in its tool list +- `PreToolUse` hook guard (defense-in-depth): if a blocklisted tool name somehow fires, immediately reset the current message + kill (treat as stuck) + +**Kill old machinery**: +- Remove `setTimeout` + `resetIdle` plumbing in `container-runner.ts:128-140` +- Remove `resetContainerIdleTimer` export + its caller in `delivery.ts:26` +- Remove `IDLE_END_MS = 20_000` in `poll-loop.ts:11` (item 6a decision) — stream stays open as long as container alive +- Existing `detectStaleContainers` logic merges into the new sweep rules; the heartbeat-stale-10-min path disappears + +**LOC estimate**: ~115 +- New sweep decision logic replacing existing detectStaleContainers + IDLE_TIMEOUT path: 50 +- Container state table + PreToolUse/PostToolUse write, host read: 25 +- Tool blocklist (disallowedTools + hook guard): 15 +- Deletions (IDLE_TIMEOUT setTimeout, IDLE_END_MS): −25 +- Tests (kill paths, Bash-timeout grace, blocklist hit): 50 + +**Why this converged here** (rationale summary): +- Empirical data showed we can't reliably tell stuck from legitimate-silent-work without state. Bash-declared-timeout is the cleanest per-tool signal available. +- 60s-since-claim is tight enough for normal work (WebSearch/WebFetch finish in ~8s) but generous enough for reasonable delays. Exception for Bash covers agents running scripts with user-declared timeouts. +- 30-min absolute ceiling prevents infinitely-stuck containers; agents needing longer have `run_in_background`. +- Pushing messages can't serve as a liveness probe (they're silent mid-turn), so detection is state-driven, not push-driven. +- Blocklist prevents a whole class of "SDK tool designed for interactive UI" footguns that would appear stuck in our async model. + +**Next step**: implement as a focused PR. Order: (a) tool blocklist — safe to ship alone, (b) container state table + PreToolUse writes, (c) sweep rewrite + message reset, (d) delete old IDLE_TIMEOUT + IDLE_END_MS machinery, (e) tests. + +### 10. Host-level retry with backoff on agent error +**Finding**: v1 had MAX_RETRIES=5 + exp. backoff on `processGroupMessages` failure. v2's equivalent is now covered by item 9's sweep logic — any time the container isn't running with `'processing'` rows present, they get reset to pending with backoff + retry++. + +**Status**: folded into item 9 + +**Decision**: no separate action. Agent-error retry happens via container-exit → sweep reset. Container errors also surface via provider-side session invalidation check (`poll-loop.ts:200-211` — `provider.isSessionInvalid(err)` → clears stored session id → fresh retry). Both paths preserved. + +**Next step**: none. + +--- + +### 11. Process ID in logger output +**Finding**: v1 emitted `(${process.pid})` after the level tag. v2 dropped it. + +**Status**: dropped + +**Decision**: don't restore. Host is single-process (PID is constant). Container stderr already gets tagged with `{ container: agentGroup.folder }` at `container-runner.ts:121`, which is more informative than a PID. + +**Next step**: none. + +--- + +## LOW + +### 11. Process ID in logger output +**Finding**: v1 emitted `(${process.pid})` after the level tag. v2 dropped it. +**Status**: pending +**Decision**: +**Rationale**: +**Next step**: + +### 12. Task dedup via unique `(kind, series_id)` index +**Finding**: verified — `messages_in.series_id` column exists with a non-unique index. Concern was theoretical: two pending rows with same series could coexist. + +**Status**: dropped + +**Decision**: not a real issue. Recurrence logic at `src/modules/scheduling/recurrence.ts` is structurally dedup-safe: only `completed` rows with `recurrence` get cloned, and after cloning `recurrence` is cleared on the original so it can't re-clone. Plus container's atomic `markProcessing` prevents double-execution at claim time. + +**Next step**: none. + +### 13. Silent-drop mode for noisy senders +**Finding**: v1's `mode:'drop'` let you ignore specific users without logging. v2 only has binary allow/deny via access gate. + +**Status**: dropped — won't implement + +**Decision**: not worth the table + gate complexity for a personal-assistant scale. If a specific sender becomes a problem, admin can switch the messaging_group's `unknown_sender_policy` to `'strict'` or remove the sender from `agent_group_members`. + +**Next step**: none. + +### 14. Remote control subsystem +**Finding**: v1's `/remote-control` command spawned `claude remote-control` CLI detached, polled stdout for session URL, persisted PID/URL state. Entirely gone in v2. + +**Status**: deferred — opt-in skill when needed + +**Decision**: reintroduce as an opt-in install skill (e.g. `/add-remote-control`), not on trunk. Provider-specific: only works with `claude` provider (Claude Agent SDK); not supported by OpenCode or other providers. Skill should check `agent_group.provider` at install time and bail gracefully with an error message if not `'claude'`. + +**Rationale**: niche feature valuable only for direct agent SDK attachment during dev/debugging. Keeping it off trunk matches v2's "infra-only trunk, features-via-skills" philosophy. Also avoids carrying code for a feature that simply doesn't exist in non-Claude providers. + +**Next step**: none until someone needs it. When implementing, likely lives on the `providers` branch (since it's provider-specific) or its own branch, installed via skill that copies files + checks provider. + +### 15. Dead config constants +**Finding**: verified — `POLL_INTERVAL` (line 13), `SCHEDULER_POLL_INTERVAL` (line 14), and `IPC_POLL_INTERVAL` (line 32) in `src/config.ts` have zero imports elsewhere in v2. Container's `POLL_INTERVAL_MS` in `poll-loop.ts` is a distinct local constant, unrelated. + +**Status**: decided — delete + +**Decision**: remove the three constants from `src/config.ts`. Trivial 3-line deletion. + +**Next step**: do as part of any sweep-touching PR, or standalone. + +### 16. Configurable retention thresholds +**Finding**: `STALE_THRESHOLD_MS` (10 min) and `MAX_TRIES` (5) in `host-sweep.ts` are hardcoded. Item 9's redesign replaces `STALE_THRESHOLD_MS` with new constants (60s claim-age, 30 min ceiling). + +**Status**: dropped — keep as constants + +**Decision**: leave the new item-9 thresholds + `MAX_TRIES` as source constants. Adding config surface for them isn't worth it at personal-assistant scale. If operational tuning ever becomes a real need, revisit — they're small centralized constants, one-line change each. + +**Next step**: none. + +### 17. Dynamic group-add (IPC watcher equivalent) +**Finding**: not actually a restart requirement — investigation showed: +- Router reads `messaging_groups` + `messaging_group_agents` fresh per inbound (dynamic by design) +- Chat SDK bridge has a `conversations: Map` populated at setup + `updateConversations()` method +- **Nothing in the bridge currently reads the map**, and no code calls `updateConversations()` after startup +- Today: stale map has no observable effect (dead state) +- After item 1 ships (adapter-level gating): stale map would matter; new wirings wouldn't apply in the adapter gate until restart + +**Status**: deferred — comment added now, implement alongside dynamic group registration feature + +**Decision**: don't refactor the adapter interface now. Added a NOTE comment at `src/channels/chat-sdk-bridge.ts:73` flagging the staleness issue so the next person touching the bridge or adding dynamic-registration sees it. When dynamic group registration is implemented (admin adds a new messaging_group_agents row while host is running), handle cache refresh then — most likely by calling `adapter.updateConversations(freshConfigs)` after the mutation, keyed off the adapter's `channelType`. + +**Rationale**: item 1's initial landing can keep the adapter gating responsibilities small or skip adapter-side gating entirely. Refactoring ConversationConfig now would add scope; better to ship item 1 first, see if over-subscription bites, address if it does. + +**Next step**: when building the admin-skill path for adding messaging_group ↔ agent_group wirings, include a `refreshAdapterConversations(channelType)` call after the INSERT. ~10 LOC when needed. + +--- + +## Test regressions (v1 `formatting.test.ts` assertions) + +### 18+19+20+21. Timezone + formatting recreation (merged) +**Finding**: v1 had a full timezone-aware formatting pipeline. v2 lost most of it, producing real bugs where the agent misinterprets user intent (scheduling for wrong times, suggesting time-inappropriate things). + +**Scope** — recreate v1 behavior faithfully wherever times touch the agent: +- Timestamp formatting on inbound messages: `formatLocalTime(utcIso, TIMEZONE)` producing "Jan 1, 2024, 1:30 PM" format via `Intl.DateTimeFormat('en-US', {...})` (v1 `timezone.ts`) +- `` header prepended to message block (v1 `router.ts:20-22`) +- Reply-to with message ID: `......` (v1 `router.ts:10-18`) +- `stripInternalTags()`: regex `/[\s\S]*?<\/internal>/g` applied to outbound text, then `.trim()` (v1 `router.ts:25-27`) +- Cron expressions parsed with explicit user TZ: `CronExpressionParser.parse(expr, { tz: TIMEZONE })` (v1 `task-scheduler.ts:20-49`) +- User-specified times normalized via the user's TZ: in v1 this was the host-side task scheduler; in v2 it's the new-in-v2 scheduling MCP tool (`mcp-tools/scheduling.ts`). Same principle — accept user-local times, normalize to UTC for storage, interpret cron in user's TZ. + +**Status**: decided — recreate with tests + +**Decision**: port v1's formatter + timezone behavior faithfully. Full recreation spec at [`timezone-formatting-v1-recreation.md`](timezone-formatting-v1-recreation.md) — includes exact v1 code, line numbers at commit `27c5220`, complete test inventory from `src/v1/formatting.test.ts` and `src/v1/task-scheduler.test.ts`. + +**Core principle** (per Gavriel): the agent operates in the user's timezone. Every timestamp the agent sees is user-local. Every time the agent outputs is interpreted as user-local. This is load-bearing for correctness, not a nice-to-have. + +**Porting plan** (from recreation spec): +1. `container/agent-runner/src/formatter.ts` — replace `formatTime` with `formatLocalTime(ts, TIMEZONE)` call; add reply_to attribute + `` element exactly as v1 +2. Prepend `\n` to the messages block at formatter entry +3. Extract `stripInternalTags` as a named function; apply in outbound dispatch path (`poll-loop.ts:389` currently uses inline regex) +4. `container/agent-runner/src/mcp-tools/scheduling.ts` — clarify `processAfter` description, normalize to UTC ISO in handler +5. `src/modules/scheduling/recurrence.ts` — pass `{ tz: TIMEZONE }` to `CronExpressionParser.parse()` explicitly +6. Port all test cases from v1's `formatting.test.ts` and `task-scheduler.test.ts` to v2's test tree + +**LOC estimate**: ~75 prod + ~120 tests (reproducing v1's 40+ test cases) + +**Next step**: implement as a focused PR. Order: (a) formatter changes + tests, (b) context header + tests, (c) reply_to + tests, (d) stripInternalTags extraction + tests, (e) scheduling tool + cron TZ + tests. + +### 19, 20, 21 — merged into 18 above +See item 18 for the full recreation plan and spec reference. + +--- + +## Notes +- `src/v1/` was deleted upstream (commit 86becf8) after this analysis was written. v2 tree has since had a major module extraction (approvals, interactive, scheduling, permissions, agent-to-agent, self-mod) and a new CLI channel. **Verify each item against the current tree before deciding** — some may already be addressed. diff --git a/docs/v1-vs-v2/SUMMARY.md b/docs/v1-vs-v2/SUMMARY.md new file mode 100644 index 000000000..30e7d388c --- /dev/null +++ b/docs/v1-vs-v2/SUMMARY.md @@ -0,0 +1,146 @@ +# v1 → v2 Deep Dive: Aggregate Summary + +Per-file deep-dives were produced for every file in `src/v1/` and `container/agent-runner/src/v1/`. This document aggregates findings across all 21 modules. + +## Per-file docs + +| Topic | File | v1 source(s) | +|---|---|---| +| Configuration | [config.md](config.md) | `src/v1/config.ts` | +| Environment helpers | [env.md](env.md) | `src/v1/env.ts` | +| Types | [types.md](types.md) | `src/v1/types.ts` | +| Logger | [logger.md](logger.md) | `src/v1/logger.ts` | +| Timezone | [timezone.md](timezone.md) | `src/v1/timezone.ts` | +| Database layer | [db.md](db.md) | `src/v1/db.ts` | +| Container runner | [container-runner.md](container-runner.md) | `src/v1/container-runner.ts` | +| Container runtime + mounts | [container-runtime.md](container-runtime.md) | `src/v1/container-runtime.ts`, `mount-security.ts` | +| Group folder | [group-folder.md](group-folder.md) | `src/v1/group-folder.ts` | +| Group queue | [group-queue.md](group-queue.md) | `src/v1/group-queue.ts` | +| Host index | [index-host.md](index-host.md) | `src/v1/index.ts` | +| IPC (host + container) | [ipc.md](ipc.md) | `src/v1/ipc.ts`, `container/.../v1/ipc-mcp-stdio.ts` | +| Remote control | [remote-control.md](remote-control.md) | `src/v1/remote-control.ts` | +| Router | [router.md](router.md) | `src/v1/router.ts` + `index.ts` routing | +| Sender allowlist | [sender-allowlist.md](sender-allowlist.md) | `src/v1/sender-allowlist.ts` | +| Session cleanup | [session-cleanup.md](session-cleanup.md) | `src/v1/session-cleanup.ts` | +| Task scheduler | [task-scheduler.md](task-scheduler.md) | `src/v1/task-scheduler.ts` | +| Channels | [channels.md](channels.md) | `src/v1/channels/*` | +| Agent-runner entry | [container-index.md](container-index.md) | `container/.../v1/index.ts` | +| Agent-runner MCP tools | [container-mcp-tools.md](container-mcp-tools.md) | `container/.../v1/mcp-tools.ts` | +| Formatting test (orphan) | [formatting-test.md](formatting-test.md) | `src/v1/formatting.test.ts` | + +## The big shift + +v2 rewrote the fundamental transport between host and container. The one-line version: + +> **v1 = IPC files + stdin/stdout + in-memory GroupQueue + polling message loop. +> v2 = two SQLite DBs per session + event-driven routing + 60s host sweep.** + +Everything else flows from that. Removing IPC forced a rewrite of the router, the container-runner, the agent-runner entry, and the MCP-tool bridge. The 60s sweep absorbed the task scheduler, session cleanup, and pending-message recovery. The entity model (users/roles/messaging_groups) replaced the flat sender allowlist and chat-level config. Provider abstraction + Chat SDK bridge replaced hardcoded Claude SDK + per-channel adapters. + +Net LOC: v1 (~7.4k host + monolithic container-runner) → v2 (~5.5k host, split modules). Fewer lines, cleaner boundaries, more coverage. + +## What's kept (identical or near-identical) +- `timezone.ts` — byte-identical +- `group-folder.ts` — byte-identical validation; v2 adds `group-init.ts` for filesystem scaffold +- `container-runtime.ts` — nearly identical (only logger import swapped) +- `mount-security.ts` — same structure, one field removed (see regressions) +- `config.ts` / `env.ts` — same structure, same `.env` surface; several constants now dead code +- `logger.ts` — same levels/colors/routing, but API shape changed (message-first instead of data-first) +- MCP `send_message` tool — kept + enhanced with named destinations + +## What's new in v2 +- **Two-DB session model** (`inbound.db` + `outbound.db`) with even/odd seq parity, journal_mode=DELETE for cross-mount visibility +- **Entity model** — `users`, `user_roles` (owner/admin/scoped), `agent_group_members`, `messaging_groups`, `messaging_group_agents`, `user_dms` (cold-DM cache) +- **Host sweep** (60s) — absorbs scheduler, cleanup, pending-message recovery, recurrence firing, stale detection, orphan cleanup +- **Chat SDK bridge** — unifies Discord/Slack/Teams/other adapters through `@anthropic-ai/chat` +- **Provider abstraction** — default Claude + opt-in OpenCode etc. via `providers` branch +- **OneCLI integration** — credential gateway + approval flow (`src/onecli-approvals.ts`) +- **16 new MCP tools** — scheduling (6), interactive (2), self-mod (3), agent mgmt (1), message manipulation (3), plus enhanced `send_message` +- **Heartbeat file mtime** — replaces IPC liveness +- **Session persistence** — session ID survives container restarts +- **Dual-rate polling** — 1000ms idle / 500ms active inside container +- **Idle stream termination** — 20s timeout prevents zombie queries +- **Processing ACK** — reverse channel (outbound → inbound) for idempotence +- **Migration system** — 9 numbered migrations vs v1's ad-hoc ALTERs +- **Webhook server** (new for HTTP-based channels) +- **Container typing indicator refresh** via delivery + +## What's removed (deliberately) +- **IPC transport** (files, stdin/stdout JSON, MCP-over-stdio bridge) — replaced by DB polling +- **`GroupQueue`** in-memory state machine — serialization via `messages_in.status` +- **Output markers** (`---NANOCLAW_OUTPUT_START/END---`) — results land in `messages_out` +- **State persistence** (`router_state`, `lastAgentTimestamp` map) — each message is independent +- **Per-exit container log files** — only logger.debug to host log +- **Flat sender allowlist** (JSON config) — replaced by role-based access + `unknown_sender_policy` +- **Remote control subsystem** (`/remote-control` command → spawned CLI) +- **IPC watcher** (dynamic group-add while running) +- **`task_runs` audit table** — no task execution log +- **Cron/interval task types** as first-class entities — tasks are `messages_in` rows with `kind='task'` + `recurrence` +- **Stdin protocol** for agent input — container reads from inbound.db + +## Regressions worth fixing (ranked) + +### HIGH priority +1. **Trigger-rule matching in `pickAgent`** (`src/router.ts:198` TODO). + Without this, a messaging group wired to multiple agents fires ALL of them on every message. Schema (`messaging_group_agents.trigger_rules`) is ready; the check is ~10 lines. **Likely broken-by-default for multi-agent setups.** + +2. **`nonMainReadOnly` mount isolation removed** (`src/mount-security.ts`). + Non-main/shared agent groups can now mount read-write on any path the allowlist permits. v1 enforced read-only-for-non-main regardless of allowlist. **Security regression** for multi-tenant setups. Restore: add field + restore `isMain` param flow. + +3. **Pending-message recovery on startup** (`src/v1/index.ts:465-473`). + v1 explicitly scanned for unprocessed messages on restart. v2 relies on the sweep to notice. Likely works in practice, but worth a test: kill container mid-message, restart host, verify redelivery within ≤5s. + +### MEDIUM priority +4. **`response_scope` enforcement** (`messaging_group_agents.response_scope` stored but unused). + Values `'all' | 'triggered' | 'allowlisted'` are saved but nothing reads them. + +5. **`request_approval` flow for unknown senders** (`src/router.ts:295` TODO). + `unknown_sender_policy='request_approval'` is scaffolded but doesn't actually produce an approval card. + +6. **Per-group container timeout**. + v1's `containerConfig.timeout` override is gone; all groups share `IDLE_TIMEOUT`. Slow-but-healthy agents get killed with fast agents' timeout. + +7. **Container streaming output**. + v1's marker-based pre-completion delivery is gone. v2 must wait for outbound.db poll. Latency-sensitive UX regresses. + +8. **Per-exit container logs**. + v1 wrote timestamped per-exit log files with full I/O + mounts + stderr. v2 only has logger.debug. Zero-cost on success, high-value on crash. Restore at least for non-zero exit. + +9. **Explicit container kill on stale detection**. + v2's sweep marks messages for retry but doesn't stop the stale container. Only `cleanupOrphans()` at startup removes them. Add `stopContainer()` when heartbeat stale AND processing stuck. + +10. **Host-level retry with backoff on agent error**. + v1 had MAX_RETRIES=5 + exp. backoff on `processGroupMessages` failure. v2 only retries on stale-heartbeat. Explicit agent-error retry could close the gap. + +### LOW priority +11. **Process ID in logger output** — lost multi-process debugging info +12. **Task dedup via unique `(kind, series_id)` index** — v2 can have two pending rows with same series; best-effort via atomic status update +13. **Silent-drop mode for noisy senders** — v1's `mode:'drop'` had a use case; orthogonal to privilege +14. **Remote control** — decide: restore as opt-in skill or document as removed +15. **Dead config constants** (`POLL_INTERVAL`, `SCHEDULER_POLL_INTERVAL`, `IPC_POLL_INTERVAL`) — delete from `src/config.ts` +16. **Configurable retention thresholds** (`STALE_THRESHOLD_MS`, `MAX_TRIES`) — move from constants to `config.ts` +17. **Dynamic group-add** (IPC watcher equivalent) — probably not worth; document that restart is required + +## Things kept as test-only regression risk +The orphan `src/v1/formatting.test.ts` asserted behaviors that aren't fully exercised in v2: +- **Timezone-aware formatted timestamps** — v1 emitted locale strings ("Jan 1, 2024, 1:30 PM"); v2 emits UTC HH:MM +- **`` header** — gone +- **`reply_to=""` attribute** — v2 only stores sender name + truncated preview +- **Trigger-pattern unit tests** — no direct equivalent (logic moved to DB but isn't tested at the router level) +- **Internal tag stripping** tests — no isolated tests in agent-runner + +These are specs worth porting to v2 tests once trigger matching is implemented. + +## Files entirely gone in v2 +- `src/v1/ipc.ts` + `src/v1/ipc-auth.test.ts` — IPC is dead +- `container/.../v1/ipc-mcp-stdio.ts` — MCP-over-stdio bridge dead +- `src/v1/group-queue.ts` — serialization via DB +- `src/v1/session-cleanup.ts` — merged into `host-sweep.ts` +- `src/v1/task-scheduler.ts` — merged into `host-sweep.ts` + system actions in `delivery.ts` +- `src/v1/remote-control.ts` — feature removed +- `src/v1/sender-allowlist.ts` — entity model supersedes + +## Net architectural assessment +v2 is strictly simpler, more consistent, and more robust in its happy path. The remaining TODOs (trigger matching, response_scope, request_approval) reflect scaffolding that was checked in ahead of the feature — none are deep design issues. The one actual regression is `nonMainReadOnly` mount isolation; it was a defense-in-depth feature and deserves to come back. The removal of per-exit container logs and streaming output markers are judgment calls that traded observability for simplicity — both can be restored cheaply if needed. + +No file in v1 contains a behavior that v2 is architecturally unable to express. The outstanding work is feature-completion, not architecture. diff --git a/docs/v1-vs-v2/channels.md b/docs/v1-vs-v2/channels.md new file mode 100644 index 000000000..bd4dda4c2 --- /dev/null +++ b/docs/v1-vs-v2/channels.md @@ -0,0 +1,305 @@ +# channels: v1 vs v2 + +## Scope + +### v1 +- **Paths**: `src/v1/channels/index.ts`, `src/v1/channels/registry.ts`, `src/v1/channels/registry.test.ts` +- **LOC**: 62 total (1 + 23 + 38) +- **Purpose**: Registry and interface stubs for external channel adapters (real adapters live on `channels` branch) + +### v2 counterparts +- **Paths**: `src/channels/adapter.ts`, `src/channels/channel-registry.ts`, `src/channels/chat-sdk-bridge.ts`, `src/channels/index.ts`, `src/channels/ask-question.ts`, and tests +- **LOC**: 1,055 total (excluding tests: ~757) +- **Purpose**: Full adapter interface, registry with lifecycle, Chat SDK bridge (new in v2), ask_question normalization, plus integration tests + +--- + +## Adapter Interface Diff + +### v1: `Channel` (from src/v1/types.ts:87–98) + +```typescript +export interface Channel { + name: string; + connect(): Promise; + sendMessage(jid: string, text: string): Promise; + isConnected(): boolean; + ownsJid(jid: string): boolean; + disconnect(): Promise; + setTyping?(jid: string, isTyping: boolean): Promise; // Optional + syncGroups?(force: boolean): Promise; // Optional +} +``` + +**Callbacks** (src/v1/types.ts:101–112): +- `OnInboundMessage(chatJid: string, message: NewMessage): void` +- `OnChatMetadata(chatJid: string, timestamp: string, name?: string, channel?: string, isGroup?: boolean): void` + +**Factory & Registration** (src/v1/channels/registry.ts:3–23): +```typescript +export interface ChannelOpts { + onMessage: OnInboundMessage; + onChatMetadata: OnChatMetadata; + registeredGroups: () => Record; +} +export type ChannelFactory = (opts: ChannelOpts) => Channel | null; +registerChannel(name: string, factory: ChannelFactory): void; +getChannelFactory(name: string): ChannelFactory | undefined; +getRegisteredChannelNames(): string[]; +``` + +--- + +### v2: `ChannelAdapter` (from src/channels/adapter.ts:61–106) + +```typescript +export interface ChannelAdapter { + name: string; + channelType: string; + supportsThreads: boolean; // NEW: declares thread model + + // Lifecycle (was: connect/disconnect) + setup(config: ChannelSetup): Promise; + teardown(): Promise; + isConnected(): boolean; + + // Message delivery (was: sendMessage, now structured) + deliver(platformId: string, threadId: string | null, message: OutboundMessage): Promise; + + // Optional + setTyping?(platformId: string, threadId: string | null): Promise; + syncConversations?(): Promise; + updateConversations?(conversations: ConversationConfig[]): void; + openDM?(userHandle: string): Promise; // NEW: cold-DM initiation +} +``` + +**Callbacks** (src/channels/adapter.ts:18–30): +```typescript +export interface ChannelSetup { + conversations: ConversationConfig[]; + onInbound(platformId: string, threadId: string | null, message: InboundMessage): void | Promise; + onMetadata(platformId: string, name?: string, isGroup?: boolean): void; + onAction(questionId: string, selectedOption: string, userId: string): void; // NEW +} +``` + +**Factory & Registration** (src/channels/channel-registry.ts:25–47): +```typescript +export type ChannelAdapterFactory = () => ChannelAdapter | Promise | null; +export interface ChannelRegistration { + factory: ChannelAdapterFactory; + containerConfig?: { mounts?: [...]; env?: Record; }; +} +registerChannelAdapter(name: string, registration: ChannelRegistration): void; +getChannelAdapter(channelType: string): ChannelAdapter | undefined; // RENAMED +getActiveAdapters(): ChannelAdapter[]; // NEW +getRegisteredChannelNames(): string[]; +getChannelContainerConfig(name: string): ChannelRegistration['containerConfig']; // NEW +``` + +--- + +## Capability Map + +| v1 Behavior | v2 Location | Status | Notes | +|---|---|---|---| +| **Interface & Lifecycle** | | | | +| `connect()` → `disconnect()` | `setup()` / `teardown()` | Renamed + consolidated | v2 groups init work; adds promise-based retry on NetworkError (src/channels/channel-registry.ts:73) | +| `Channel.name: string` | `ChannelAdapter.name` + `ChannelAdapter.channelType` | Split | `name` is identity; `channelType` is the key for active lookup | +| `ownsJid(jid)` | Implicit in platformId model | Removed | v2 uses structured platformId + threadId; ownership logic pushed to router | +| **Message Flow** | | | | +| `sendMessage(jid, text)` | `deliver(platformId, threadId, message)` | Refactored | v2 passes structured `OutboundMessage` with `kind` field; returns platform messageId; supports edit/reaction ops (src/channels/chat-sdk-bridge.ts:279–289) | +| Callbacks: `onMessage` | `onInbound(platformId, threadId, message)` | Refactored | v2 passes message object with `kind` enum ('chat' \| 'chat-sdk'); can be async | +| Callbacks: `onChatMetadata` | `onMetadata(platformId, name?, isGroup?)` | Simplified | Signature matches v1; removed `channel` param; timestamp now in inbound message itself | +| | `onAction(questionId, option, userId)` | **NEW** | Handles ask_question card button clicks via Chat SDK bridge (src/channels/chat-sdk-bridge.ts:193–218) | +| **Typing Indicator** | | | | +| `setTyping(jid, bool)` | `setTyping(platformId, threadId)` | Refactored | v2 omits boolean flag (always true, no off-toggle); threaded parameter | +| **Group/Conversation Sync** | | | | +| `syncGroups(force?)` | `syncConversations()?: Promise` | Renamed | Now returns structured list; decoupled from periodic init (optional hook) | +| | `updateConversations(configs)`: void | **NEW** | Push notifications of conversation changes from host to adapter (e.g., new wiring) | +| **Thread Model** | | | | +| Implicit (adapter-specific) | `supportsThreads: boolean` | **NEW** | v2 explicitly declares it; router uses this to collapse/expand thread context (src/channels/adapter.ts:73–75) | +| **DM Initiation** | | | | +| Not exposed | `openDM(userHandle)?: Promise` | **NEW** | For cold-DM reaching (approvals, onboarding, alerts) on platforms that distinguish user-id from DM-channel-id. Optional; fallback in user-dm.ts if absent (src/channels/adapter.ts:94–105) | +| **Inbound Message Structure** | | | | +| v1 `NewMessage` object | v2 `InboundMessage` (generic JSON) | Generalized | v1 had flat fields (sender, content, timestamp, thread_id, reply_to_*); v2 wraps serialized Chat SDK Message or native JSON in `content` field; Chat SDK bridge enriches (adds senderId, senderName) before sending (src/channels/chat-sdk-bridge.ts:124–141) | +| **Outbound Message Structure** | | | | +| Plain text + typing flag | v2 `OutboundMessage` (typed `kind` + flexible `content`) | Generalized | Supports 'chat', 'chat-sdk', edit ops, reactions, ask_question cards (src/channels/adapter.ts:46–51, src/channels/chat-sdk-bridge.ts:279–317) | +| **Factory Pattern** | | | | +| `ChannelFactory(opts) → Channel \| null` | `ChannelAdapterFactory() → ChannelAdapter \| Promise<...> \| null` | Async + cred check | v2 supports async factory (for loading credentials); promise-based retry on NetworkError (src/channels/channel-registry.ts:68–87) | +| **Container Config** | | | | +| Not exposed | `ChannelRegistration.containerConfig` | **NEW** | Adapters can declare mounts + env vars for their container (used by container-runner); see src/channels/channel-registry.ts:45–47 | + +--- + +## Message Conversion & Error Handling + +### v1 Flow +- Adapter calls `onMessage(chatJid, NewMessage)` synchronously +- Router extracts fields, upserts user, creates/finds session, writes to `inbound.db` +- No built-in error handling; adapters catch and log themselves + +### v2 Flow (src/channels/chat-sdk-bridge.ts:85–141) +1. **Inbound**: Chat SDK `Message` → `InboundMessage` (kind='chat-sdk', content=serialized JSON) +2. **Attachment handling**: Downloads attachments, converts to base64 (src/channels/chat-sdk-bridge.ts:90–111) +3. **Reply context extraction**: Platform-specific hook (src/channels/chat-sdk-bridge.ts:115–120) +4. **User field normalization**: Maps Chat SDK author → senderId, sender, senderName (src/channels/chat-sdk-bridge.ts:124–131) +5. **Raw data drop**: Removes `raw` to save DB space (src/channels/chat-sdk-bridge.ts:134) +6. **Call onInbound**: Async-capable (can await router writes) + +**Outbound** (src/channels/chat-sdk-bridge.ts:273–344): +- Supports multiple operation types via `content.operation`: + - `'edit'` + `messageId` → `adapter.editMessage()` + - `'reaction'` + `emoji` → `adapter.addReaction()` + - `type: 'ask_question'` → render Card with buttons + - Normal text/markdown → `adapter.postMessage()` with optional files + +**Error Propagation**: +- Network errors on setup get retry (src/channels/channel-registry.ts:73; duck-type check for Error.name==='NetworkError') +- Delivery errors logged but don't block (src/channels/chat-sdk-bridge.ts:213–214, 484–486) + +--- + +## New: Chat SDK Bridge + +The v2 `Chat` abstraction (from `@anthropic-ai/chat`) wraps platform-specific adapters (Discord.js, Slack SDK, etc.) into a unified API. The NanoClaw `createChatSdkBridge()` (src/channels/chat-sdk-bridge.ts:68–384) adapts that `Chat` instance to the `ChannelAdapter` interface. + +**Key methods**: +- `setup(hostConfig)`: Initialize Chat, set up event handlers (subscribed messages, DMs, mentions, actions), start Gateway listener or register webhook (src/channels/chat-sdk-bridge.ts:149–271) +- `deliver()`: Route outbound payloads (text, edit, reaction, ask_question card) to Chat SDK (src/channels/chat-sdk-bridge.ts:273–344) +- `setTyping()`: Delegate to `adapter.startTyping()` (src/channels/chat-sdk-bridge.ts:346–349) +- `teardown()`: Abort Gateway, shutdown Chat (src/channels/chat-sdk-bridge.ts:351–355) +- `updateConversations()`: Rebuild conversation map on changes (src/channels/chat-sdk-bridge.ts:361–363) +- `openDM()`: Conditional; only if underlying adapter supports it (src/channels/chat-sdk-bridge.ts:366–381) + +**Event routing** (src/channels/chat-sdk-bridge.ts:163–191): +- `chat.onSubscribedMessage()` → `onInbound()` for all known threads +- `chat.onNewMention()` → `onInbound()` + auto-subscribe +- `chat.onDirectMessage()` → `onInbound()` for DMs +- `chat.onAction()` → `onAction()` for ask_question button clicks (src/channels/chat-sdk-bridge.ts:193–218) + +**Gateway listener** (src/channels/chat-sdk-bridge.ts:222–268): +- Adapters like Discord that support websocket connection declare `startGatewayListener()`. +- NanoClaw runs it, forwards interactions (button clicks) to a local HTTP webhook server (src/channels/chat-sdk-bridge.ts:392–506). +- Non-Gateway adapters (Slack, Teams) register on the shared webhook-server instead (src/channels/chat-sdk-bridge.ts:266–268). + +--- + +## Test Fixtures + +### v1 (src/v1/channels/registry.test.ts:10–38) +- Simple lambda factories: `() => null` +- No mock adapters (tests only verify registry API mechanics) +- Test count: 4 (unknown-channel, round-trip, listing, overwrite) + +### v2 (src/channels/channel-registry.test.ts + src/channels/chat-sdk-bridge.test.ts) + +**Mock Adapter** (src/channels/channel-registry.test.ts:31–71): +```typescript +createMockAdapter(channelType): ChannelAdapter & { delivered, inbound, setupConfig } + - Properties: name, channelType, supportsThreads, delivered[], inbound[], setupConfig + - Methods: setup(config), teardown(), isConnected(), deliver(), setTyping(), updateConversations() +``` + +**Registry Tests** (src/channels/channel-registry.test.ts:84–119): +- Adapter registration with container config (src/channels/channel-registry.test.ts:88–98) +- Credential-missing adapters skipped (src/channels/channel-registry.test.ts:101–119) + +**Integration Tests** (src/channels/channel-registry.test.ts:122–234): +- Router receives inbound from adapter, writes to inbound.db (src/channels/channel-registry.test.ts:166–197) +- Delivery adapter bridge calls adapter.deliver() (src/channels/channel-registry.test.ts:199–233) + +**Chat SDK Bridge Tests** (src/channels/chat-sdk-bridge.test.ts:11–38): +- Conditional openDM exposure (src/channels/chat-sdk-bridge.test.ts:12–18) +- openDM delegation to underlying adapter (src/channels/chat-sdk-bridge.test.ts:20–37) + +--- + +## Missing from v2 + +### 1. `ownsJid(jid: string): boolean` +- **v1 use**: Adapters declared ownership of a JID (e.g., "does this Telegram numeric ID belong to me?") +- **v2 model**: JIDs → platformId + threadId; ownership is implicit in `platformId` format (e.g., `"telegram:6037840640"` vs `"discord:guildId:channelId"`). Router uses this to route inbound to the right adapter. +- **Impact**: Adapters no longer need explicit ownership checks; the structured ID handles it. + +### 2. `syncGroups(force?: boolean): Promise` +- **v1 use**: Periodic or on-demand sync of all groups/channels from the platform. +- **v2 model**: Optional `syncConversations()` returns metadata instead of mutating internal state; host calls it when needed (not baked into adapter init). Conversations are tracked in central DB `messaging_groups` table. +- **Impact**: Host has more control; adapters don't side-effect their own state. + +### 3. `registeredGroups` callback in `ChannelOpts` +- **v1 use**: Passed at init time; adapters could query which groups were registered. +- **v2 model**: Conversations provided upfront in `ChannelSetup.conversations`; can be updated via `updateConversations()`. +- **Impact**: Cleaner dependency injection; avoids callback nesting. + +### 4. `channel` parameter in `OnChatMetadata` +- **v1 use**: Metadata callback could optionally return which channel type made the discovery. +- **v2 model**: Not needed; `platformId` in `onMetadata(platformId, name, isGroup)` encodes the channel type. + +--- + +## Behavioral Discrepancies + +### 1. Thread-ID Handling +- **v1**: Some adapters (Telegram, WhatsApp) don't use threads; JIDs are the same as channel IDs. Others (Discord, Slack) embed thread IDs in reply_to logic. +- **v2**: Explicit `supportsThreads` flag; adapters that don't support threads pass `threadId: null` to `onInbound()`. Router uses this to decide session granularity (file:src/channels/adapter.ts:73–75). + +### 2. Outbound Message Structure +- **v1**: Plain text + optional typing flag. +- **v2**: Structured `{ kind, content, files? }` with operation support (edit, reaction, ask_question cards). Allows multi-op delivery without repeated deliver() calls. + +### 3. Inbound Serialization +- **v1**: Adapters directly passed `NewMessage` interface objects. +- **v2**: Adapters pass `InboundMessage` with generic `content` field (JSON-serializable JS object). Chat SDK bridge converts Chat SDK Message → JSON, then stringifies for DB (file:src/channels/chat-sdk-bridge.ts:136–140). + +### 4. Ask-Question Handling +- **v1**: No native support; would be custom per-adapter. +- **v2**: Unified via `ask_question` payload type. Chat SDK bridge renders as Card + Buttons; handles button clicks via `onAction()` callback and updates card to show selection (file:src/channels/chat-sdk-bridge.ts:292–317, 459–486). + +### 5. Cold-DM Initiation +- **v1**: Not exposed. +- **v2**: `openDM(userHandle): Promise` allows host to initiate DMs to users without prior message. Adapters that need it (Discord, Slack, Teams) implement; others omit and fall back to direct handle as platformId (file:src/user-dm.ts fallback). + +### 6. Async Factory +- **v1**: `ChannelFactory` returns `Channel | null` synchronously. +- **v2**: `ChannelAdapterFactory` returns `ChannelAdapter | Promise | null`, supporting async credential loading. Registry retries on `NetworkError` (file:src/channels/channel-registry.ts:68–87). + +### 7. Lifecycle Promises +- **v1**: `connect()` / `disconnect()` are separate. +- **v2**: `setup()` / `teardown()` grouped; no intermediate "starting/stopping" state. Gateway listeners and webhook servers are started inside `setup()`, torn down inside `teardown()` (file:src/channels/chat-sdk-bridge.ts:149–271, 351–355). + +--- + +## Worth Preserving? + +**All v1 patterns are preserved in v2, just restructured:** + +1. **Adapter interface model**: v1's optional hooks (`setTyping?`, `syncGroups?`) become v2's optional methods (`setTyping?`, `syncConversations?`, `openDM?`). Structural compatibility for native adapters. + +2. **Registry pattern**: v1's `registerChannel(name, factory)` → v2's `registerChannelAdapter(name, registration)`. Same self-registration barrel; v2 adds container config metadata. + +3. **Callback-driven message flow**: v1's `onMessage` and `onChatMetadata` callbacks live on as `onInbound` and `onMetadata`. v2 adds `onAction` for interactive features (ask_question buttons). + +4. **No built-in state mutation**: v1 adapters own their group state; v2 adapters are stateless (conversations pushed in). Both respect adapter autonomy. + +**What's genuinely new and worth keeping:** + +- **Chat SDK bridge**: Unifies platform SDKs without duplicating channel adapters per SDK. Huge reduction in code duplication (one Discord adapter instead of native + Chat SDK versions). +- **Structured message payloads**: v2's `kind` field and flexible `content` JSON allow single delivery path for text, edits, reactions, and rich interactions. +- **Ask-question cards**: Native support for interactive approvals and user input, reducing agent-side boilerplate. +- **openDM**: Enables host-initiated contact (onboarding, alerts, approvals) without waiting for inbound. +- **supportsThreads**: Explicit declaration lets router make informed session granularity decisions, vs. hardcoded per-adapter assumptions. + +**Minimal migration burden:** + +Native adapters written for v1 need only: +1. Rename `connect` → `setup` (add `ChannelSetup` param). +2. Rename `disconnect` → `teardown`. +3. Rename `sendMessage(jid, text)` → `deliver(platformId, threadId, message)` (wrap text in `{ kind: 'chat', content: { text } }`). +4. Add `supportsThreads: boolean`, `name`, `channelType` fields. +5. Add `isConnected()` stub if not already present. +6. Optional: Implement `setTyping?`, `syncConversations?`, `openDM?` for feature parity. + +Nothing is fundamentally broken; it's a straightforward refactor of the adapter contract. + diff --git a/docs/v1-vs-v2/config.md b/docs/v1-vs-v2/config.md new file mode 100644 index 000000000..c6464994f --- /dev/null +++ b/docs/v1-vs-v2/config.md @@ -0,0 +1,99 @@ +# config: v1 vs v2 + +## Scope + +- **v1**: `/Users/gavriel/nanoclaw4/src/v1/config.ts` (63 lines) + `/Users/gavriel/nanoclaw4/src/v1/env.ts` (42 lines) +- **v2 counterparts**: `/Users/gavriel/nanoclaw4/src/config.ts` (63 lines, **identical**), `/Users/gavriel/nanoclaw4/src/env.ts` (42 lines, **identical**), plus host-level polling in `/Users/gavriel/nanoclaw4/src/host-sweep.ts` and `/Users/gavriel/nanoclaw4/src/delivery.ts`; container agent-runner reads at `/Users/gavriel/nanoclaw4/container/agent-runner/src/index.ts` + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| **ASSISTANT_NAME** env var (default: 'Andy') | `src/config.ts:10`; read from `.env` or `process.env` | Kept, partially used | v2 exports it but doesn't use it in host. Container receives via `NANOCLAW_ASSISTANT_NAME` env var (set by `src/container-runner.ts:302`) for transcript archiving only. v1 used it for CLAUDE.md substitution, trigger pattern, and prompt context. | +| **ASSISTANT_HAS_OWN_NUMBER** boolean env var | `src/config.ts:11-12` | **Removed, unused** | Exported but neither v1 nor v2 use it. No evidence of any implementation. | +| **POLL_INTERVAL = 2000ms** | `src/config.ts:13` | **Removed, unused** | v1 used in `index.ts:457` (IPC watcher polling). v2 replaced IPC with session DBs; no polling needed at this interval. | +| **SCHEDULER_POLL_INTERVAL = 60000ms** | `src/config.ts:14` | **Removed, unused** | v1 used in `task-scheduler.ts:231`. v2 uses hard-coded `SWEEP_INTERVAL_MS = 60_000` in `host-sweep.ts:31` instead (same value, different source). | +| **IPC_POLL_INTERVAL = 1000ms** | `src/config.ts:32` | **Removed, unused** | v1 used in `ipc.ts:50, ipc.ts:122`. v2 replaced file-based IPC with SQLite session DBs; this interval has no meaning. | +| **MOUNT_ALLOWLIST_PATH** = `~/.config/nanoclaw/mount-allowlist.json` | `src/config.ts:21` | Kept, same behavior | Used by `src/mount-security.ts` (host) to whitelist directories containers can read. Same in both versions. | +| **SENDER_ALLOWLIST_PATH** = `~/.config/nanoclaw/sender-allowlist.json` | `src/config.ts:22` | Kept, same behavior | Stored outside project root for security. Path derivation identical in v1 and v2. **Unused in v2** (no grep hits outside v1 folder). | +| **STORE_DIR** = `store/` | `src/config.ts:23` | **Removed, unused** | v1 used in `db.ts`. v2 uses central DB (`data/v2.db`) and per-session DBs (`data/v2-sessions//{inbound,outbound}.db`). `store/` directory no longer part of v2 architecture. | +| **GROUPS_DIR** = `groups/` | `src/config.ts:24` | Kept, same behavior | Per-agent-group filesystem (CLAUDE.md, skills, config). Used in `src/container-runner.ts`, `src/delivery.ts`, `src/group-init.ts`. Identical role in both versions. | +| **DATA_DIR** = `data/` | `src/config.ts:25` | Kept, extended usage | v1: IPC files, task DB. v2: central DB, session DBs, heartbeat files. More central in v2. Used in `src/index.ts`, `src/session-manager.ts`, `src/group-init.ts`, etc. | +| **CONTAINER_IMAGE** env var (default: 'nanoclaw-agent:latest') | `src/config.ts:27` | Kept, same behavior | Specifies Docker image name. Used in `src/container-runner.ts`. Identical in both versions. | +| **CONTAINER_TIMEOUT** env var (default: 1800000ms = 30min) | `src/config.ts:28` | Kept, same behavior | Maximum wall-clock time for a single container invocation. Used in `src/container-runner.ts`. Identical in both versions. | +| **CONTAINER_MAX_OUTPUT_SIZE** env var (default: 10485760 bytes = 10MB) | `src/config.ts:29` | **Removed, unused** | Exported but never referenced in v1 or v2. No evidence of implementation. | +| **ONECLI_URL** env var (no default) | `src/config.ts:30` | Kept, same behavior | OneCLI gateway URL for credential management. Read from `.env` or `process.env`. Used in `src/onecli-approvals.ts`. Identical in both versions. | +| **MAX_MESSAGES_PER_PROMPT** env var (default: 10) | `src/config.ts:31` | **Removed, unused** | v1 used in message batching for prompt formatting (`v1/index.ts:192-193, 434-435, 467`). v2 removed MAX_MESSAGES limit; agent processes all pending messages in a turn. | +| **IDLE_TIMEOUT** env var (default: 1800000ms = 30min) | `src/config.ts:33` | Kept, same behavior | How long to keep container alive after last result before killing due to inactivity. Used in `src/container-runner.ts:134-139`. Identical in both versions. | +| **MAX_CONCURRENT_CONTAINERS** env var (default: 5) | `src/config.ts:34` | **Removed, unused** | v1 used in `group-queue.ts` for queue management. v2 removed group queueing (no group-queue.ts equivalent). Sessions start containers independently; no global cap enforced. | +| **escapeRegex()** helper | `src/config.ts:36-38` | Kept, same implementation | Escapes regex special characters. Used by `buildTriggerPattern()`. Identical in both versions. | +| **buildTriggerPattern()** helper | `src/config.ts:40-42` | Kept, same implementation | Builds case-insensitive word-boundary regex from trigger string. Used in v2 by... (no grep hits in non-v1 v2 code). Exported but **unused in v2**. | +| **DEFAULT_TRIGGER** = `@${ASSISTANT_NAME}` | `src/config.ts:44` | Kept, **unused** | Default trigger pattern for agent activation. Computed from ASSISTANT_NAME. Exported but not used in v2 (no grep hits outside v1). | +| **getTriggerPattern()** helper | `src/config.ts:46-49` | Kept, **unused** | Returns regex for trigger matching. Used in v1 for routing decisions. Exported but **not used in v2** (trigger logic moved to DB `messaging_group_agents.trigger_rules`). | +| **TRIGGER_PATTERN** = computed | `src/config.ts:51` | Kept, **unused** | Pre-built DEFAULT_TRIGGER pattern. Exported but **not used in v2**. | +| **resolveConfigTimezone()** helper | `src/config.ts:55-61` | Kept, same implementation | Resolves IANA timezone from TZ env var → `.env` TZ → system timezone → 'UTC'. Identical logic in both versions. | +| **TIMEZONE** const | `src/config.ts:62` | Kept, same behavior | Current timezone for scheduled tasks, message timestamps. Used in `src/host-sweep.ts`, `container/agent-runner/src/index.ts`. Identical in both versions. | +| **readEnvFile()** function | `src/env.ts:11-42` | Kept, identical | Reads `.env` file, returns only requested keys, does not pollute `process.env`. Used by config.ts. Prevents secrets leak to child processes. Identical in both versions. | + +--- + +## Missing from v2 + +- **POLL_INTERVAL** (2000ms hardcoded constant) — v1 polling loop. v2 has no direct equivalent; delivery uses hard-coded `ACTIVE_POLL_MS = 1000` (`src/delivery.ts:56`). Not configurable. + +- **SCHEDULER_POLL_INTERVAL** (60000ms hardcoded constant) — v1 task scheduler. v2 uses hard-coded `SWEEP_INTERVAL_MS = 60_000` (`src/host-sweep.ts:31`). Same interval, not configurable from config.ts. + +- **IPC_POLL_INTERVAL** (1000ms hardcoded constant) — v1 IPC file watcher. No v2 equivalent; IPC replaced with session DBs. + +- **MAX_MESSAGES_PER_PROMPT** (env var, default 10) — v1 message batching. v2 has no message batching limit; all pending messages in a turn are processed together. + +- **MAX_CONCURRENT_CONTAINERS** (env var, default 5) — v1 group queue. v2 has no group-level concurrency cap; sessions start containers independently. + +- **STORE_DIR** (store/ directory) — v1 task/group storage. v2 uses central DB + session DBs; no store/ directory needed. + +- **SENDER_ALLOWLIST_PATH** — Path is defined but never used in either version. + +--- + +## Behavioral discrepancies + +1. **ASSISTANT_NAME usage** + - v1: Used for CLAUDE.md template substitution (`v1/index.ts:135-137`), getLastBotMessageTimestamp comparison, and trigger pattern building. + - v2: Only passed to container as `NANOCLAW_ASSISTANT_NAME` env var (`src/container-runner.ts:302`); container uses it for transcript archiving only. Host does not use it. + - **Impact**: v1 personalized CLAUDE.md by name; v2 relies on statically authored CLAUDE.md in `groups//`. + +2. **Trigger pattern handling** + - v1: Trigger pattern from `getTriggerPattern()` used at host routing layer (`v1/index.ts:200, 419`). + - v2: Trigger rules stored in DB (`messaging_group_agents.trigger_rules` JSON field), evaluated at delivery time by router. `getTriggerPattern()` exported but unused. + - **Impact**: v1 required config-level trigger changes; v2 allows per-messaging-group customization via DB. + +3. **Timezone resolution** + - v1: `resolveConfigTimezone()` used in `task-scheduler.ts:5`. + - v2: Same function; `TIMEZONE` used in `host-sweep.ts`, `container/agent-runner/src/index.ts:45` (but never actually referenced in agent-runner). + - **Impact**: Identical behavior; minor: container reads env var but doesn't use it. + +4. **Poll intervals** + - v1: `POLL_INTERVAL`, `SCHEDULER_POLL_INTERVAL`, `IPC_POLL_INTERVAL` all separately configured. + - v2: Hard-coded `ACTIVE_POLL_MS = 1000`, `SWEEP_POLL_MS = 60_000` in `src/delivery.ts`. Container poll loop uses hard-coded `POLL_INTERVAL_MS = 1000`, `ACTIVE_POLL_INTERVAL_MS = 500` in `container/agent-runner/src/poll-loop.ts:10-11`. + - **Impact**: v2 intervals are not tunable via env vars; requires code change. + +5. **Message batching** + - v1: `MAX_MESSAGES_PER_PROMPT` limits messages per turn (`v1/index.ts:467`). + - v2: No limit; all pending messages (minus filtered/denied commands) are formatted and sent to agent in one turn. + - **Impact**: v2 may send larger prompts; unbounded context risk if message queue grows. + +6. **Container concurrency** + - v1: `MAX_CONCURRENT_CONTAINERS` enforced via group queue (`v1/group-queue.ts`). + - v2: No global or per-group limit. Each session independently starts its container on wake. + - **Impact**: v2 can spawn many containers simultaneously; no backpressure mechanism. + +7. **IPC → Session DB** + - v1: Uses file-based IPC (JSON files, `IPC_POLL_INTERVAL` polling). + - v2: Uses SQLite session DBs (`inbound.db` host-owned, `outbound.db` container-owned). + - **Impact**: v2 is more reliable (ACID semantics) but less debuggable (binary format). + +--- + +## Worth preserving? + +**No.** The config.ts file is largely a legacy artifact. Most of its exports are unused in v2, and the few that remain (TIMEZONE, IDLE_TIMEOUT, ONECLI_URL, paths) are minimally invasive. The hardcoded poll intervals and removed features (MAX_MESSAGES, MAX_CONCURRENT_CONTAINERS, IPC_POLL_INTERVAL) reflect architectural changes that are intentional and correct for v2. The trigger pattern and ASSISTANT_NAME handling in config.ts should be removed from the host layer entirely — they're now managed by the DB and container env vars. Consolidate host-level config into a smaller, focused module that only exports what v2 actually uses: TIMEZONE, IDLE_TIMEOUT, CONTAINER_TIMEOUT, ONECLI_URL, path constants, and the env file reader. diff --git a/docs/v1-vs-v2/container-index.md b/docs/v1-vs-v2/container-index.md new file mode 100644 index 000000000..4b61d878e --- /dev/null +++ b/docs/v1-vs-v2/container-index.md @@ -0,0 +1,72 @@ +# container index (agent-runner entry): v1 vs v2 + +## Scope +- v1: `container/agent-runner/src/v1/index.ts` (736 LOC) — monolithic: arg parsing, IPC polling, SDK integration, output marshaling +- v2 (split): `container/agent-runner/src/index.ts` (124 LOC) + `poll-loop.ts` (436 LOC) + `destinations.ts` (118 LOC) + `formatter.ts` (228 LOC) + `db/*.ts` + `providers/*.ts` + +## Startup sequence diff + +| Step | v1 (IPC) | v2 (SQLite poll) | +|------|----------|------------------| +| Arg parsing | stdin JSON via `readStdin()` (v1:105-115) | env vars: `AGENT_PROVIDER`, `NANOCLAW_*` (v2 index.ts:44-51) | +| Env setup | `sdkEnv` + `CLAUDE_CODE_AUTO_COMPACT_WINDOW` (v1:626-629) | same, delegated to provider (index.ts:109) | +| DB open | — (IPC files only) | inbound.db (RO) + outbound.db (RW) + `session_state` table | +| MCP server config | hardcoded nanoclaw server (v1:477-486) | same + `NANOCLAW_MCP_SERVERS` env for additional (index.ts:94-104) | +| Message loop | `waitForIpcMessage()` polling (v1:350-366) | `poll-loop.ts:62+` `getPendingMessages()` every 1000ms idle / 500ms active | +| Provider | Claude SDK direct | provider abstraction factory (`providers/factory.ts`, supports claude/mock/custom) | +| Message stream | `MessageStream` iterable (v1:71-103) | same pattern in `providers/claude.ts:51-80` | +| System prompt | manual CLAUDE.md load + hardcoded destinations (v1:416-420) | `buildSystemPromptAddendum()` from inbound.db destinations (`destinations.ts:76-117`) | +| Query execution | `runQuery()` with IPC polling during query (v1:374-545) | `processQuery()` polls messages_in + `provider.query()` (`poll-loop.ts:259-319`) | +| Session resumption | sessionId on stdin + `resumeAt` tracking | `getStoredSessionId()` from outbound.db; cleared on `/clear` admin command | +| Shutdown | stdout output markers + exit(1) on error | no markers; logs errors; host manages lifecycle | +| Heartbeat | — | file touch at `SESSION_HEARTBEAT_PATH` on each result | + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| Parse prompt/session/group/chat/etc. from stdin | env + inbound.db | kept | | +| Env injection (ANTHROPIC_BASE_URL, proxy) | passed to provider.query() (index.ts:109) | kept | | +| Stdin JSON parsing | — | **removed** | | +| IPC file polling | `messages_in` table | modernized | Same semantics, DB-backed | +| IPC `_close` sentinel | implicit (process killed by host) | simplified | | +| Output wrapping markers | writes to `messages_out` | **removed** | | +| Session archiving PreCompact hook | `providers/claude.ts` hook | kept | | +| Session resumption by ID | `getStoredSessionId()` (poll-loop.ts:51) | **persisted** | Survives container restart | +| Scheduled task script execution | `task-script.ts:applyPreTaskScripts()` (poll-loop.ts:159) | kept | | +| Command filtering (`/help`, `/login`) | `categorizeMessage()` + filtered set (formatter.ts:14, poll-loop.ts:95-100) | **enhanced** | Explicit categories | +| Admin commands (`/clear`, etc.) | `categorizeMessage` + `NANOCLAW_ADMIN_USER_IDS` gate (poll-loop.ts:102-131) | kept | Explicit admin role from env | +| Destination routing `to=` | `destinations` table + `dispatchResultText()` (poll-loop.ts:350-432) | modernized | Named destinations instead of raw JIDs | +| Multi-destination message blocks | `MESSAGE_RE` regex (poll-loop.ts:350-414) | kept | | +| Tool allowlist | `providers/claude.ts:19-39` | kept | | +| MCP server setup | index.ts:81-104 | kept + extensible | | +| `@-syntax` additional dirs | `/workspace/extra/*` discovered at startup (index.ts:64-74) | kept | | +| Global CLAUDE.md | SDK preset append (index.ts:56-58) | kept | | +| Idle stream termination | — | **new** (IDLE_END_MS = 20s prevents zombies) | +| Admin user ID prefixing (chat-sdk) | explicit `channel_type:` prefix (formatter.ts:58-66) | **new** | | +| Processing ACK | **new** | prevents re-processing on container restart | +| Message kind formatting | `formatMessages()` (formatter.ts) | enhanced | Routes by kind: chat/task/webhook/system | + +## Missing from v2 +None of v1's core capabilities dropped. Notes on format/protocol shifts: +1. **Stdout markers removed** — host now parses `messages_out` table instead of stdout +2. **Stdin protocol gone** — follow-up messages via `messages_in` table +3. **Script-phase fast exit removed** — v1 could skip container entirely if `wakeAgent=false`; v2 gates message processing but container keeps polling (slightly more idle cost) + +## Behavioral discrepancies +1. **Idle timeout**: v1 had no query-level timeout → zombies possible. v2 ends stream after 20s with no SDK events +2. **Resume**: v1 re-read sessionId from stdin each run; v2 persists in `session_state` across restarts +3. **Admin gating**: v1 passed everything through; v2 categorizes + admin-gates `/clear` etc. +4. **Destination naming**: v1 raw JID; v2 human names from destinations table +5. **Poll cadence**: v2 dual-rate — 1000ms idle, 500ms active (CPU efficiency + responsiveness) +6. **Message kind routing**: v1 uniform; v2 distinguishes chat/chat-sdk/task/webhook/system with per-kind formatting + +## Worth preserving? +v1 should remain historical reference only. v2 strictly supersedes: +- DB-backed state survives restarts +- Provider abstraction allows non-Claude agents +- Dynamic destinations from inbound.db +- Session invalidation detection + processing ACK idempotence +- Dual poll rate + idle termination prevent pathological query hangs + +No merge-back candidates identified. diff --git a/docs/v1-vs-v2/container-mcp-tools.md b/docs/v1-vs-v2/container-mcp-tools.md new file mode 100644 index 000000000..95c23b391 --- /dev/null +++ b/docs/v1-vs-v2/container-mcp-tools.md @@ -0,0 +1,59 @@ +# container mcp-tools: v1 vs v2 + +## Scope +- v1: `container/agent-runner/src/v1/mcp-tools.ts` (81 LOC) — single tool (`send_message`) +- v2: `container/agent-runner/src/mcp-tools/` — 7 modules (~971 LOC): `index.ts`, `core.ts`, `scheduling.ts`, `interactive.ts`, `agents.ts`, `self-mod.ts`, `types.ts` + +## Tool map + +| v1 tool | v2 file | Status | Schema / behavior diff | +|---|---|---|---| +| `send_message(text, channel, platformId, threadId)` | `core.ts:50-95` | **kept, enhanced** | v2 uses named destinations (`to`), auto-resolves via session default or lookup, preserves `thread_id` intelligently | +| — | `core.ts:133-177` `send_file` | **new** | Copies file to outbox dir, routes via destinations | +| — | `core.ts:179-218` `edit_message` | **new** | Edit previously-sent message by seq id | +| — | `core.ts:220-259` `add_reaction` | **new** | Emoji reaction by seq id | +| — | `scheduling.ts:33-79` `schedule_task` | **new** | One-shot or recurring (cron) | +| — | `scheduling.ts:81-137` `list_tasks` | **new** | Pending/paused tasks grouped by series | +| — | `scheduling.ts:139-165` `cancel_task` | **new** | | +| — | `scheduling.ts:167-192` `pause_task` | **new** | | +| — | `scheduling.ts:194-219` `resume_task` | **new** | | +| — | `scheduling.ts:221-266` `update_task` | **new** | Modify prompt/recurrence/processAfter/script | +| — | `interactive.ts:36-129` `ask_user_question` | **new** | Blocking with timeout — writes to outbound.db then polls inbound.db for response | +| — | `interactive.ts:131-166` `send_card` | **new** | Structured Chat SDK cards | +| — | `self-mod.ts:34-74` `install_packages` | **new** | apt/npm install, regex name validation, admin approval | +| — | `self-mod.ts:76-113` `add_mcp_server` | **new** | Wire existing MCP server | +| — | `self-mod.ts:115-141` `request_rebuild` | **new** | Async container rebuild | +| — | `agents.ts:30-63` `create_agent` | **new** | Admin-only sub-agent creation; not exposed to non-admin containers | + +## New tools in v2 +16 new tools split across 5 capability domains: +- **Message manipulation**: `send_file`, `edit_message`, `add_reaction` +- **Scheduling**: 6 task-management tools +- **Interactive**: `ask_user_question`, `send_card` +- **Self-modification**: `install_packages`, `add_mcp_server`, `request_rebuild` +- **Agent management**: `create_agent` + +## Missing from v2 +**None.** v2 strictly adds; v1's only tool (`send_message`) was kept and enhanced. + +## Behavioral discrepancies +1. **Destination resolution**: v1 used explicit channel/platformId/threadId params; v2 resolves named destinations from `destinations` map with fallback to session routing +2. **Two-DB split pattern**: all scheduling/self-mod tools write system actions to **outbound.db**; host processes (applies to inbound.db). Container never writes directly to inbound +3. **`ask_user_question` is blocking**: synchronously polls inbound.db until response arrives or timeout — agent perception is blocking, transport is async +4. **Admin enforcement**: `create_agent` + self-mod tools check admin approval host-side (`NANOCLAW_ADMIN_USER_IDS` env controls tool visibility) +5. **Message editing/reactions**: use internal seq id (not user-visible numeric message ID) — requires outbound.db lookup + +## Transport pattern (v2 common) +1. Agent invokes tool → validation (regex, enum, length) +2. Tool writes `messages_out` or system-action row +3. Tool returns success immediately (fire-and-forget) +4. Host polls outbound.db, applies approval / routing / side effects + +## Worth preserving? +**Yes, fully.** The v2 modular architecture is a large improvement: +- Clear separation by capability domain +- Two-DB constraint cleanly encoded (container → outbound, host → inbound) +- Named destination abstraction (better UX than raw JIDs) +- Admin-only tool filtering at the MCP server level + +v1 is retained as historical reference only. No merge-back. diff --git a/docs/v1-vs-v2/container-runner.md b/docs/v1-vs-v2/container-runner.md new file mode 100644 index 000000000..c598df77e --- /dev/null +++ b/docs/v1-vs-v2/container-runner.md @@ -0,0 +1,51 @@ +# container-runner: v1 vs v2 + +## Scope +- v1: `src/v1/container-runner.ts` (677 LOC) + `container-runner.test.ts` (204 LOC) — spawn + IPC plumbing + stdin/stdout JSON + process supervision + output-marker parsing +- v2: `src/container-runner.ts` (405 LOC) + `src/container-config.ts` (114 LOC) + `src/session-manager.ts` (DB paths). Net ~272 LOC removed by eliminating IPC and output parsing + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| Image selection | `container-runner.ts:348-349` | kept | Reads `imageTag` from container.json or env | +| Env injection | `container-runner.ts:266-284` | **changed** | Replaced IPC vars with `SESSION_INBOUND/OUTBOUND_DB_PATH`, `SESSION_HEARTBEAT_PATH`, `AGENT_PROVIDER`, `NANOCLAW_*` admin IDs | +| Volume mounts | `container-runner.ts:200-252` | **changed** | Removed per-group IPC dir; added session folder `/workspace` + agent group `/workspace/agent` | +| Mount validation | `container-runner.ts:240-244` | kept | Validates `additionalMounts` from container.json | +| Provider integration | `container-runner.ts:184-198` | **new** | `resolveProviderContribution()` wires provider host-side configs | +| stdin/stdout IPC | — | **removed** | v1 lines 318-387; v2 uses DB polling only; stdio=`['ignore','pipe','pipe']` | +| Process spawn | `container-runner.ts:119` | kept | | +| OneCLI `ensureAgent` + `applyContainerConfig` | `container-runner.ts:301-313` | enhanced | v2 calls `ensureAgent` first | +| Admin ID injection | `container-runner.ts:289-295` | **new** | Queries `getOwners/getGlobalAdmins/getAdminsOfAgentGroup` at wake | +| Idle timeout | `container-runner.ts:135-140` | changed | v2 uses `resetIdle()` callback on activeContainers entry, settable by `delivery.ts` | +| Timeout logic | — | **removed** | v1 had configurable per-group timeout reset on output markers | +| Output parsing | — | **removed** | v1 parsed `---NANOCLAW_OUTPUT_START/END---` from stdout; v2 ignores stdout | +| Streaming output callback | — | **removed** | v1 had `onOutput()` for real-time delivery | +| Per-exit log file | — | **removed** | v1 wrote `groups//logs/container-*.log` with full I/O; v2 only logs stderr to logger.debug | +| Graceful SIGTERM→SIGKILL | — | simplified | v2 just calls `stopContainer()` | +| Concurrent wake dedup | `container-runner.ts:44-82` | **new** | `wakePromises` Map prevents race on spawn | +| Per-group image builds | `container-runner.ts:357-405` | **new** | `buildAgentGroupImage()` writes `imageTag` | +| Session folder init | `container-runner.ts:210` | **new** | `initGroupFilesystem()` at spawn | +| Heartbeat file `/workspace/.heartbeat` | session-manager.ts | **new** | File-touch replaces IPC liveness | +| Task/group JSON snapshots (`current_tasks.json`, `available_groups.json`) | — | **removed** | v2 pushes data via inbound.db writeDestinations/writeSessionRouting | +| Container name | `container-runner.ts:103` | changed | `nanoclaw-v2-${folder}-${Date.now()}` | + +## Missing from v2 +1. **Streaming output markers** — `---NANOCLAW_OUTPUT_START/END---` enabled pre-completion delivery; v2 must wait for outbound.db poll to deliver results +2. **Configurable per-group timeout** — `group.containerConfig.timeout` override is gone; all groups share `IDLE_TIMEOUT` +3. **Per-exit detailed logs** — v1 wrote timestamped logs with full I/O + mounts + stderr + stdout; invaluable for post-mortem +4. **Graceful-stop sentinel** — v1 sent SIGTERM and waited for `_close` marker before SIGKILL +5. **JSON snapshots for tasks/groups** — `current_tasks.json` / `available_groups.json` in the group IPC dir + +## Behavioral discrepancies +1. **Async result model**: v1 `runContainerAgent()` returned `Promise` with inline result; v2 `wakeContainer()` is fire-and-forget — results asynchronous via delivery poll +2. **No stdin**: v1 wrote full `ContainerInput` JSON to stdin; v2 container reads everything from inbound.db +3. **Admin injection at wake**: v2 queries admins fresh on every spawn (`NANOCLAW_ADMIN_USER_IDS`) +4. **Destination routing timing**: v2 calls `writeDestinations()` + `writeSessionRouting()` on every wake so changes apply without restart +5. **Session lifecycle**: v1 created a session per spawn; v2 resolves session via router before wake + +## Worth preserving? +- **Streaming output**: Meaningful latency improvement. Hybrid model (DB polling + optional marker pre-delivery) could reduce perceived latency for long outputs +- **Per-group timeout**: Restore — different agent groups have different expected latencies +- **Per-exit logs**: At minimum, restore on non-zero exit. Cheap forensics, huge debug value +- **Graceful-stop sentinel**: Not critical — bun container is disposable diff --git a/docs/v1-vs-v2/container-runtime.md b/docs/v1-vs-v2/container-runtime.md new file mode 100644 index 000000000..e240247b3 --- /dev/null +++ b/docs/v1-vs-v2/container-runtime.md @@ -0,0 +1,46 @@ +# container-runtime + mount-security: v1 vs v2 + +## Scope +- v1: `src/v1/container-runtime.ts` (81 LOC), `container-runtime.test.ts` (148 LOC), `mount-security.ts` (406 LOC) +- v2: `src/container-runtime.ts` (81 LOC), `container-runtime.test.ts` (149 LOC), `mount-security.ts` (390 LOC) + +## Capability map + +### container-runtime.ts + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| `CONTAINER_RUNTIME_BIN = 'docker'` | `container-runtime.ts:1` | kept | Hardcoded; Apple Container runtime is NOT handled here in either version | +| `hostGatewayArgs()` | `container-runtime.ts` | kept | Identical | +| `readonlyMountArgs()` | `container-runtime.ts` | kept | Identical | +| `stopContainer()` | `container-runtime.ts` | kept | Identical | +| `ensureContainerRuntimeRunning()` | `container-runtime.ts` | kept | Identical | +| `cleanupOrphans()` | `container-runtime.ts:60-80` | kept | Identical logic | +| Logging module | | **changed** | v1 imports `logger` (data-first); v2 imports `log` (message-first) | + +### mount-security.ts + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| `AdditionalMount` / `AllowedRoot` / `MountAllowlist` types | `mount-security.ts:16-29` | kept | Same shape except `nonMainReadOnly` removed | +| Default blocked patterns | `mount-security.ts:39` | kept | Same list | +| Allowlist load + file-watch cache | `mount-security.ts:64-102` | kept | | +| Path expansion (`~`) | `mount-security.ts` | kept | | +| Symlink resolution | `mount-security.ts` | kept | | +| Container-path validation | `mount-security.ts` | kept | | +| Template generation | `mount-security.ts:362-386` | changed | v2 template omits `nonMainReadOnly: true` | +| `validateMount(mount, isMain)` | `mount-security.ts:230-307` | **signature changed** | v2 is `validateMount(mount)` — no `isMain` | +| `validateAdditionalMounts(mounts, groupName, isMain)` | same | **signature changed** | v2 drops `isMain` | +| Non-main groups forced to read-only | — | **removed** | v1 lines 283-291; v2 only checks `allowedRoot.allowReadWrite` | + +## Missing from v2 +1. **`nonMainReadOnly` flag on `MountAllowlist`** — v1 could force non-main agent groups to read-only even when their allowlist permitted RW +2. **`isMain` param flow** through `validateMount` / `validateAdditionalMounts` +3. **Non-main group RW enforcement** at mount-validation time — now delegated entirely to `allowedRoot.allowReadWrite` + +## Behavioral discrepancies +1. **Isolation model weakened**: a non-main ("shared" or auxiliary) agent group can now mount RW on any path its root permits. v1's defense-in-depth (allowlist permits RW + group must be main) is reduced to just the allowlist check +2. **Logger import**: only surface difference in container-runtime.ts + +## Worth preserving? +**`nonMainReadOnly` restoration has security value** for multi-tenant setups where shared/sandbox agent groups should not mutate filesystem even if the allowlist is permissive. Low-cost to reintroduce: restore the field on `MountAllowlist`, restore the `isMain` param, restore the check in `validateMount()`. If v2 has explicitly decided isolation is enforced elsewhere (agent-group config), document that; otherwise this is a regression. diff --git a/docs/v1-vs-v2/db.md b/docs/v1-vs-v2/db.md new file mode 100644 index 000000000..97ee0f868 --- /dev/null +++ b/docs/v1-vs-v2/db.md @@ -0,0 +1,542 @@ +# db: v1 vs v2 + +## Scope + +**v1 (historical, not runtime):** +- `/Users/gavriel/nanoclaw4/src/v1/db.ts` (659 lines) +- `/Users/gavriel/nanoclaw4/src/v1/db.test.ts` (592 lines) +- `/Users/gavriel/nanoclaw4/src/v1/db-migration.test.ts` (60 lines) +- **Single database:** `/messages.db` (better-sqlite3) +- No session/agent-runner separation; chat metadata + message history only + +**v2 counterparts:** +- Central: `/Users/gavriel/nanoclaw4/src/db/*.ts` (index, schema, connection, 9 modules + 7 migrations) +- Session: `/Users/gavriel/nanoclaw4/src/db/session-db.ts` (200+ lines) +- Chat SDK state: `/Users/gavriel/nanoclaw4/src/state-sqlite.ts` (250+ lines) +- Docs: `docs/db.md`, `docs/db-central.md`, `docs/db-session.md` + +--- + +## High-Level Shift + +| Aspect | v1 | v2 | +|--------|----|----| +| **Database count** | 1 | 3 (central + per-session inbound + per-session outbound) | +| **Primary purpose** | Message history for a WhatsApp/multi-channel bot | Admin plane (identity, wiring, approvals) + per-session message queues | +| **Writer model** | Single process | Single writer per file (host writes central + inbound; container writes outbound) | +| **Schema evolution** | Ad-hoc ALTER TABLE in `createSchema()` | Versioned migrations in `src/db/migrations/` | +| **Multi-tenant** | No (one bot per instance) | Yes (multiple agent groups, isolation levels, approval flows) | +| **Key invariants** | Bot prefix filter, last-bot-timestamp cursor | Seq parity (even host, odd container), journal_mode=DELETE cross-mount visibility | + +--- + +## Capability Map + +| v1 Behavior | v2 Location | Status | Notes | +|-------------|-------------|--------|-------| +| **`chats` table** (jid, name, last_message_time, channel, is_group) | `messaging_groups` (central DB) | Kept, renamed | v1: chat metadata only, no messages stored. v2: per-platform chat, with `unknown_sender_policy`, routing to multiple agents. | +| **`messages` table** (id, chat_jid, sender, content, timestamp, is_from_me, is_bot_message, reply_to_*) | `messages_in` (session inbound) | Moved to session DB | v1: indexed by `timestamp`, filtered by bot prefix + flag. v2: indexed by `series_id` (recurring), seq-numbered, multi-kind (chat|task|system), host-written with even seq. Container reads pending/unprocessed. | +| **`scheduled_tasks` table** (id, group_folder, chat_jid, prompt, script, schedule_type, schedule_value, next_run, context_mode, status) | `messages_in` (session inbound, kind='task') | Moved to session messages | v1: separate table with status='active'\|'paused'\|'completed'. v2: unified into `messages_in` with kind='task', status per message. Scheduling engine lives in v2 `host-sweep.ts`. | +| **`task_run_logs` table** (task_id, run_at, duration_ms, status, result, error) | No direct counterpart | Removed | v2 doesn't persist task execution logs in DB; host-sweep handles recurrence in-memory and via `processing_ack` acks. | +| **`router_state` table** (key, value) | Not needed in v2 | Removed | v1: stored `last_timestamp`, `last_agent_timestamp` for polling cursor. v2: central DB and message tables eliminate need for manual state; routing is deterministic via `messaging_group_agents` and session queues. | +| **`sessions` table** (group_folder, session_id) | `sessions` (central DB) | Kept, extended | v1: maps group folder to session ID. v2: central registry: id, agent_group_id, messaging_group_id, thread_id, status, container_status, last_active. Keyed by `(agent_group_id, messaging_group_id, thread_id)` tuples. | +| **`registered_groups` table** (jid, name, folder, trigger_pattern, requires_trigger, is_main, container_config) | `agent_groups` (central DB) | Converted | v1: per-JID trigger; one agent per bot instance. v2: agent_groups independent of channels; multiple messaging_groups wire to each agent via `messaging_group_agents`. Container config moved to disk (`groups//container.json`). | +| **Bot message filtering (is_bot_message flag + prefix)** | `messages_in` schema + container read filter | Kept, schema-level | v1: dual check (flag + `content LIKE 'Andy:%'` backstop). v2: container-side filtering in agent-runner. | +| **Reply context (reply_to_message_id, reply_to_content, reply_to_sender_name)** | `messages_in` columns | Kept | v1: nullable columns added via migration. v2: same schema, inherited from v1 shape. | +| **Chat metadata sync (last_message_time, channel, is_group)** | `messaging_groups` + lazy platform discovery | Converted | v1: timestamps in `chats.last_message_time`. v2: platform metadata in `messaging_groups`; `last_active` in `sessions` for activity tracking. | +| **Group discovery** (getAllChats) | Channel adapters + `messaging_groups` query | Removed from DB | v1: `getAllChats()` queries local DB. v2: adapters populate `messaging_groups` on first message; host discovers channels via routing, not polling DB. | +| **Message filtering by timestamp window** | `getNewMessages()`, `getMessagesSince()` with LIMIT subquery | Moved to session inbound | v1: queries with ORDER BY DESC, LIMIT N, then re-sort chronologically. v2: host writes to inbound; container polls. Cursor logic inverted (container drives processing, host feeds). | +| **Limit behavior (cap to N most recent)** | Hardcoded LIMIT 200 with timestamp filter | Kept, per-session | v1: `getNewMessages(limit=200)` by default. v2: `messages_in` has process-after and recurrence; container pulls per poll batch. | +| **Journal mode** | Not explicitly configured | DELETE (session), WAL (central) | v1: better-sqlite3 default (volatile). v2: `journal_mode=DELETE` on session DBs for cross-mount visibility; WAL on central DB for consistency. See `db/connection.ts:17` and `db/session-db.ts:15`. | +| **Foreign key constraints** | Soft (checked in code) | Hard (enforced in schema) | v1: no FK constraints. v2: all references are `REFERENCES table(id)` with implicit RESTRICT. Central DB enforces full FK graph. | +| **Pragmas** | Not set | `foreign_keys=ON`, `busy_timeout=5000` | v1: defaults only. v2: explicit, cross-mount-safe timeouts. | +| **Index coverage** | `idx_timestamp` on messages, `idx_next_run` on tasks, `idx_status` on tasks | Expanded | v1: 3 indexes. v2: series_id, user_roles scope, sessions lookup, agent_destinations target, pending_approvals action+status. | + +--- + +## Schema Diff: Table-by-Table + +### **Chats → Messaging Groups** + +**v1 `chats` (PK: jid):** +```sql +jid, name, last_message_time, channel, is_group +``` + +**v2 `messaging_groups` (PK: id, UNIQUE: channel_type, platform_id):** +```sql +id, channel_type, platform_id, name, is_group, unknown_sender_policy, created_at +``` + +**Diff:** +- v1: jid is the platform ID directly (`"tg:123"`, `"group@g.us"`) +- v2: splits into `channel_type` ("telegram", "whatsapp") + `platform_id` (normalized ID) +- v1: no `unknown_sender_policy`; dropped messages silently +- v2: adds policy for first-time senders: `strict` (drop), `request_approval` (ask admin), `public` (allow) +- v1: `last_message_time` per chat; v2: moved to `sessions.last_active` +- **Table lifecycle:** `chats` is ephemeral in v2 (discovered lazily); `messaging_groups` is central registry + +### **Messages → Messages In (Session)** + +**v1 `messages` (PK: id + chat_jid):** +```sql +id, chat_jid, sender, sender_name, content, timestamp, is_from_me, is_bot_message, +reply_to_message_id, reply_to_message_content, reply_to_sender_name +``` + +**v2 `messages_in` (PK: id, UNIQUE: seq):** +```sql +id, seq, kind, timestamp, status, process_after, recurrence, series_id, tries, +platform_id, channel_type, thread_id, content +``` + +**Diff:** +- v1: single-session messages; chat_jid is the routing key +- v2: per-session inbound queue; platform_id + channel_type + thread_id from routing, not payload +- v1: sender/sender_name as columns +- v2: content is JSON (all fields, including sender, are inside) +- v1: `is_bot_message` flag +- v2: `kind` field (`'chat'`, `'task'`, `'system'`) replaces ad-hoc bot detection +- v1: no seq, no status, no recurrence +- v2: **seq invariant** — even numbers only (host-assigned); see `nextEvenSeq()` at `src/db/session-db.ts:75` +- v1: `reply_to_*` columns preserved in v2 +- v1: indexed on timestamp; v2: indexed on series_id (for recurring task grouping) + +### **Scheduled Tasks → Messages In + Processing** + +**v1 `scheduled_tasks` (PK: id):** +```sql +id, group_folder, chat_jid, prompt, script, schedule_type, schedule_value, +next_run, last_run, last_result, context_mode, status, created_at +``` + +**v2 spread across:** +- `messages_in` (host writes kind='task') +- `processing_ack` (container reads/writes status) +- No persistent `task_run_logs` + +**Diff:** +- v1: tasks are a separate schema; v2: tasks are messages (kind='task') +- v1: `prompt`, `script`, `context_mode` in task row; v2: in JSON `content` +- v1: `schedule_type` (once, recurring), `schedule_value` (cron); v2: same, in `recurrence` field (cron string) +- v1: `next_run`, `last_run` tracked in table; v2: `process_after`, `status` in messages_in; recurrence logic in host-sweep +- v1: `last_result` stored; v2: no persistence; result is in container logs or delivery flow +- v1: status='active'|'paused'|'completed'; v2: status='pending'|'processing'|'completed'|'failed'|'paused' (per message, unified with chat) + +### **Task Run Logs → Removed** + +**v1 `task_run_logs` (PK: id auto-increment, FK: task_id):** +```sql +task_id, run_at, duration_ms, status, result, error +``` + +**v2:** Not in DB. + +**Rationale:** v2 doesn't persist execution history in-DB; logs are streamed to host and written to operational logs. Task state is tracked via `processing_ack` status on the message itself, not a separate log table. + +### **Router State → Removed** + +**v1 `router_state` (PK: key):** +```sql +key (last_timestamp, last_agent_timestamp), value +``` + +**v2:** Not needed. + +**Rationale:** v1 used this to track polling cursors across restarts. v2 uses message IDs and seq numbers; polling logic is implicit in the session queue architecture. + +### **Sessions Table** + +**v1 `sessions` (PK: group_folder):** +```sql +group_folder, session_id +``` + +**v2 `sessions` (PK: id):** +```sql +id, agent_group_id, messaging_group_id, thread_id, agent_provider, status, container_status, last_active, created_at +``` + +**Diff:** +- v1: simple folder → session mapping +- v2: full session tuple: agent group + messaging group + thread, with lookup index on (messaging_group_id, thread_id) +- v1: no status tracking; v2: `status` (active|paused|archived), `container_status` (stopped|starting|running) +- v2: `agent_provider` override per session +- v2: `last_active` timestamp for stale detection + +### **Registered Groups → Agent Groups + Messaging Group Agents** + +**v1 `registered_groups` (PK: jid):** +```sql +jid, name, folder, trigger_pattern, requires_trigger, is_main, added_at, container_config +``` + +**v2 split into:** +- `agent_groups` (PK: id): `id, name, folder, agent_provider, created_at` — container config on disk +- `messaging_group_agents` (PK: id): bridges messaging groups to agents with wiring rules + +**Diff:** +- v1: one-to-one chat ↔ group; v2: many-to-many messaging group ↔ agent group +- v1: `trigger_pattern` on chat; v2: `trigger_rules` (JSON) on the `messaging_group_agents` wiring +- v1: `container_config` JSON in DB; v2: lives on disk at `groups//container.json` +- v1: `requires_trigger`, `is_main` flags; v2: `session_mode` (shared|per-thread|agent-shared) on wiring + +### **New v2 Tables (Central)** + +**`users`:** +```sql +id, kind, display_name, created_at +``` +Platform identities: `"tg:123"`, `"discord:abc"`, `"phone:+1555..."`, `"email:a@x.com"`. No v1 counterpart (permissions were implicit). + +**`user_roles`:** +```sql +user_id, role (owner|admin), agent_group_id (NULL=global), granted_by, granted_at +``` +v1 had no explicit permissions; v2 enforces owner/admin privilege with audit trail. + +**`agent_group_members`:** +```sql +user_id, agent_group_id, added_by, added_at +``` +Non-privileged user membership. v1: implied (everyone could message the bot). + +**`user_dms`:** +```sql +user_id, channel_type, messaging_group_id, resolved_at +``` +Cached DM channel discovery (avoids repeated API calls). No v1 equivalent. + +**`pending_questions`:** +```sql +question_id, session_id, message_out_id, platform_id, channel_type, thread_id, title, options_json, created_at +``` +Interactive multiple-choice questions. v1: no interactive prompts. + +**`agent_destinations`:** +```sql +agent_group_id, local_name, target_type, target_id, created_at +``` +Per-agent ACL and name-resolution map for `send_message(to="name")`. Projected into session inbound as `destinations` table (see db-session.md §2.3). v1: no permission model for outbound sends. + +**`pending_approvals`:** +```sql +approval_id, session_id, request_id, action, payload, agent_group_id, channel_type, platform_id, platform_message_id, expires_at, status, title, options_json, created_at +``` +Approval queue for `install_packages`, `add_mcp_server`, `request_rebuild`, OneCLI credential flows. v1: no approval model. + +**`unregistered_senders` (via migration 008):** +```sql +user_id, messaging_group_id, first_seen, last_seen +``` +Audit trail of unknown senders (strict unknown_sender_policy). v1: silently dropped. + +**Chat SDK tables (via migration 002):** +- `chat_sdk_kv` (key, value, expires_at) +- `chat_sdk_subscriptions` (thread_id, subscribed_at) +- `chat_sdk_locks` (thread_id, token, expires_at) +- `chat_sdk_lists` (key, idx, value, expires_at) + +Backing store for Chat SDK state adapter. No v1 equivalent (Chat SDK didn't exist). + +### **New v2 Session Tables (Inbound, Host-written)** + +**`delivered`:** +```sql +message_out_id, platform_message_id, status, delivered_at +``` +Host tracks delivery outcomes without writing to container-owned outbound.db. + +**`destinations` (projection from central):** +```sql +name, display_name, type, channel_type, platform_id, agent_group_id +``` +Local ACL cache; rewritten on every container wake. Container queries this live to authorize sends. + +**`session_routing` (single-row table):** +```sql +id=1, channel_type, platform_id, thread_id +``` +Default reply routing for the session. Allows container to default outbound messages without querying central DB. + +### **New v2 Session Tables (Outbound, Container-written)** + +**`messages_out`:** +```sql +id, seq (ODD), in_reply_to, timestamp, deliver_after, recurrence, kind, platform_id, channel_type, thread_id, content +``` +Container-produced: chat replies, edits, reactions, cards, system actions. Seq always odd (container-assigned); see `src/db/session-db.ts:76` for parity logic. + +**`processing_ack`:** +```sql +message_id, status (processing|completed|failed), status_changed +``` +Container writes status for each message_in it touched. Host polls and syncs back into messages_in (avoids container writing inbound.db). + +**`session_state` (KV):** +```sql +key, value, updated_at +``` +Container persistent store (Chat SDK session ID, conversation state). Cleared by `/clear`. + +--- + +## Missing from v2 + +1. **Per-message sender/sender_name columns** — moved into JSON `content`. Container unpacks on read. +2. **`task_run_logs` persistent history** — v2 streams logs to host; no in-DB history. +3. **`last_agent_timestamp` cursor state** — implicit in session message seq. +4. **Message filtering by bot prefix** — handled by container when writing to outbound; inbound doesn't filter. +5. **Direct chat timestamp tracking** — replaced by `sessions.last_active` and message timestamps. +6. **Single-writer assumption for one bot** — v2: one writer per file, across multiple agent groups (containers). + +--- + +## Behavioral Discrepancies + +### Sequence Numbering (Load-Bearing Invariant) + +**v1:** No seq; messages identified by (id, chat_jid). + +**v2:** +- Host assigns **even** seq (2, 4, 6, …) to `messages_in`; see `nextEvenSeq()` at `src/db/session-db.ts:75–78`. +- Container assigns **odd** seq (1, 3, 5, …) to `messages_out`; see container logic at `container/agent-runner/src/db/messages-out.ts:54`. +- **Invariant:** seq is globally unique within a session across both tables. Parity disambiguates table membership for `edit_message(seq=5)` (odd → messages_out, even → messages_in). +- **If violated:** edits target wrong table; messaging breaks. + +### Message Status Lifecycle + +**v1:** `messages` are immutable once written; `scheduled_tasks` have status (active|paused|completed). + +**v2:** `messages_in` have status (pending|processing|completed|failed|paused). Container writes status into `processing_ack`; host syncs back. Processing is non-blocking (container reads when status='pending'). + +### Journal Mode (Cross-Mount Visibility) + +**v1:** Not configured (better-sqlite3 defaults to `PRAGMA journal_mode = memory` or implicit rollback). + +**v2:** **`journal_mode = DELETE` on session DBs** (see `db/session-db.ts:15`), **WAL on central** (see `db/connection.ts:17`). + +**Rationale:** v1 is single-process. v2 has host and container accessing the same session DBs across a Docker mount or Apple Container mount. WAL has issues with cross-mount visibility (rolled WAL files don't sync reliably); DELETE forces each write to flush the main file, so readers see the latest state. + +### Unknown Sender Handling + +**v1:** Silently dropped or stored with no policy tracking. + +**v2:** `unknown_sender_policy` on `messaging_groups`: `strict` (drop), `request_approval` (admin card), `public` (allow). Dropped senders tracked in `unregistered_senders` audit table (migration 008). + +### Recurring Tasks + +**v1:** `scheduled_tasks.recurrence` (cron); `schedule_type` (once|recurring); status tracking in row. + +**v2:** `messages_in.recurrence` (cron string), `series_id` (groups occurrences). Host-sweep recalculates next run via cron parser; no persistence. Status per message (pending|paused|completed). + +### Chat Metadata Sync + +**v1:** `getAllChats()` queries local DB; `last_message_time` updated by each message insert. + +**v2:** Metadata lives in `messaging_groups` (central, discovered lazily by adapters). Activity tracked in `sessions.last_active`. No global "last message" timestamp per chat. + +### Destinations and Permissions + +**v1:** No model; all agents can send to all chats. + +**v2:** +- Central: `agent_destinations` (source of truth) +- Session: `destinations` (projection in inbound.db, rewritten on wake) +- Container: queries `destinations` live; sends rejected if name not found +- Invariant: if wiring changes mid-session and `writeDestinations()` isn't called, container sees stale data + +### Foreign Key Enforcement + +**v1:** No constraints; referential integrity checked in code. + +**v2:** All FKs enforced; central DB will reject orphaned references. Session DBs don't need as many FKs (immutable projections). + +--- + +## Pragmas & Configuration + +### v1 + +```javascript +// Implicit defaults — not set in code +``` + +### v2 + +**Central DB (src/db/connection.ts:17–18):** +```javascript +_db.pragma('journal_mode = WAL'); +_db.pragma('foreign_keys = ON'); +``` + +**Session Inbound (src/db/session-db.ts:23–24):** +```javascript +db.pragma('journal_mode = DELETE'); +db.pragma('busy_timeout = 5000'); +``` + +**Session Outbound (src/db/session-db.ts:31–32):** +```javascript +// Opens readonly +db.pragma('busy_timeout = 5000'); +``` + +--- + +## Migrations + +### v1 +Adhoc `ALTER TABLE` in `createSchema()` (src/v1/db.ts:82–134): +- context_mode → scheduled_tasks +- script → scheduled_tasks +- is_bot_message → messages +- is_main → registered_groups +- channel, is_group → chats +- reply_to_* → messages + +No versioning; all tables are `IF NOT EXISTS` and ALTERs are try-catch silent. + +### v2 +Numbered migrations in `src/db/migrations/` (1–9, note: 5–6 missing): + +1. **001-initial.ts** — all core tables (agent_groups, messaging_groups, users, user_roles, agent_group_members, user_dms, sessions, pending_questions) +2. **002-chat-sdk-state.ts** — chat_sdk_kv, chat_sdk_subscriptions, chat_sdk_locks, chat_sdk_lists +3. **003-pending-approvals.ts** — pending_approvals table with action, payload, status +4. **004-agent-destinations.ts** — agent_destinations table + backfill from existing messaging_group_agents wirings +5. **(missing)** +6. **(missing)** +7. **007-pending-approvals-title-options.ts** — adds title, options_json columns to pending_approvals +8. **008-dropped-messages.ts** — unregistered_senders audit table +9. **009-drop-pending-credentials.ts** — cleanup (if any) + +**Runner:** `runMigrations()` (src/db/migrations/index.ts:28–60) tracks version in `schema_version` table; applies pending migrations in transaction. + +--- + +## Index Coverage + +### v1 + +- `idx_timestamp` on `messages(timestamp)` — range queries for new messages +- `idx_next_run` on `scheduled_tasks(next_run)` — sweep query for due tasks +- `idx_status` on `scheduled_tasks(status)` — filter for active tasks +- `idx_task_run_logs` on `task_run_logs(task_id, run_at)` — log lookup + +### v2 + +- `idx_user_roles_scope` on `user_roles(agent_group_id, role)` — permission queries +- `idx_sessions_agent_group` on `sessions(agent_group_id)` — session lookup per agent +- `idx_sessions_lookup` on `sessions(messaging_group_id, thread_id)` — resolve session from channel+thread +- `idx_messages_in_series` on `messages_in(series_id)` — recurring task grouping +- `idx_agent_dest_target` on `agent_destinations(target_type, target_id)` — reverse lookup (find agents that can send to this target) +- `idx_pending_approvals_action_status` on `pending_approvals(action, status)` — sweep query for pending/expired approvals + +--- + +## Prepared Queries & Helpers + +### v1 Helpers (src/v1/db.ts) + +``` +storeChatMetadata(jid, timestamp, name?, channel?, isGroup?) + — INSERT OR REPLACE into chats (ON CONFLICT upsert) + +storeMessage(NewMessage) +storeMessageDirect({id, chat_jid, sender, ...}) + — INSERT OR REPLACE into messages + +getNewMessages(jids[], lastTimestamp, botPrefix, limit=200) + — SELECT from messages, filter by jid list, timestamp > last, bot filter + — Returns {messages, newTimestamp} + +getMessagesSince(chatJid, sinceTimestamp, botPrefix, limit=200) + — SELECT from messages, filter by chat, timestamp > since, bot filter, ORDER DESC + outer sort + +getLastBotMessageTimestamp(chatJid, botPrefix) + — SELECT MAX(timestamp) from messages WHERE (is_bot_message=1 OR content LIKE prefix) + +createTask(ScheduledTask) / updateTask(id, fields) / getTaskById(id) / deleteTask(id) + — Standard CRUD + +getDueTasks() + — SELECT * WHERE status='active' AND next_run <= now + +updateTaskAfterRun(id, nextRun, lastResult) + — UPDATE task set next_run, last_run, last_result, status + +logTaskRun(TaskRunLog) + — INSERT into task_run_logs + +getRouterState(key) / setRouterState(key, value) + — KV table + +getSession(groupFolder) / setSession(groupFolder, sessionId) / deleteSession(groupFolder) + — Simple mapping + +getRegisteredGroup(jid) / setRegisteredGroup(jid, group) / getAllRegisteredGroups() + — CRUD on registered_groups +``` + +### v2 Helpers + +**Central DB (src/db/*.ts):** +- `createAgentGroup`, `getAgentGroup`, `getAgentGroupByFolder`, `updateAgentGroup`, `deleteAgentGroup` +- `createMessagingGroup`, `getMessagingGroup`, `getMessagingGroupByPlatform`, `updateMessagingGroup`, `deleteMessagingGroup` +- `createMessagingGroupAgent`, `getMessagingGroupAgents`, `getMessagingGroupAgentByPair`, `updateMessagingGroupAgent`, `deleteMessagingGroupAgent` +- `grantRole`, `revokeRole`, `getUserRoles`, `isOwner`, `isGlobalAdmin`, `isAdminOfAgentGroup`, `hasAdminPrivilege` +- `createUser`, `upsertUser`, `getUser`, `getAllUsers`, `updateDisplayName`, `deleteUser` +- `addMember`, `removeMember`, `getMembers`, `isMember` +- `upsertUserDm`, `getUserDm`, `getUserDmsForUser`, `deleteUserDm` +- `createSession`, `getSession`, `findSession`, `findSessionByAgentGroup`, `getSessionsByAgentGroup`, `getActiveSessions`, `getRunningSessions`, `updateSession`, `deleteSession` +- `createPendingQuestion`, `getPendingQuestion`, `deletePendingQuestion` +- `createPendingApproval`, `getPendingApproval`, `updatePendingApprovalStatus`, `deletePendingApproval`, `getPendingApprovalsByAction` + +**Session DB (src/db/session-db.ts):** +- `ensureSchema(dbPath, 'inbound'|'outbound')` — idempotent schema setup +- `openInboundDb(dbPath)`, `openOutboundDb(dbPath)` — safe open with pragmas +- `nextEvenSeq(db)` — helper for host seq assignment +- `insertMessage(db, {id, kind, timestamp, platformId, channelType, threadId, content, processAfter, recurrence})` +- `insertTask(db, {id, processAfter, recurrence, ...})` +- `cancelTask(db, taskId)`, `pauseTask(db, taskId)`, `resumeTask(db, taskId)` +- `upsertSessionRouting(db, {channel_type, platform_id, thread_id})` +- `replaceDestinations(db, entries: DestinationRow[])` + +--- + +## Key Invariants + +### v1 +- **Bot message filtering:** is_bot_message flag + content prefix as backstop (for pre-migration rows) +- **Cursor recovery:** getLastBotMessageTimestamp() to resume after stale downtime +- **Single writer:** Process that imports db.ts owns all writes; no IPC +- **Chat metadata immutability:** chats table updated only on metadata sync or first message, never deleted + +### v2 (Load-Bearing) + +1. **Single writer per file** — host writes central + inbound; container writes outbound only +2. **Seq parity invariant** — even in messages_in, odd in messages_out; parity disambiguates edit target +3. **Journal mode = DELETE on session DBs** — `DELETE` mode ensures cross-mount visibility (no WAL rollback issues) +4. **Foreign keys enforced** — central DB rejects orphans; schema_version tracks migrations +5. **Projection consistency** — `agent_destinations` (central) must be projected to `destinations` (session inbound) on every container wake; if wiring changes mid-session, must call `writeDestinations()` or container sees stale ACL +6. **Seq monotonicity** — no gaps, no reuse. `nextEvenSeq()` and container logic both scan MAX(seq) across both tables before assigning next +7. **Processing_ack as reverse channel** — container never writes to inbound.db; all status goes through outbound.db processing_ack, which host polls +8. **Heartbeat out of band** — `.heartbeat` file mtime is liveness signal, not a DB write; avoids serialization with message processing +9. **Admin at A implies membership in A** — invariant enforced in code (src/db/user-roles.ts, src/access.ts); no FK prevents deletion + +--- + +## Worth Preserving? + +**Yes — all v1 features are preserved or evolved:** +- Message history: v1 stores per-chat; v2 per-session. Content and metadata shapes mostly compatible. +- Scheduled tasks: v1 separate table; v2 unified into messages_in with kind='task'. Recurrence logic identical (cron). +- Bot filtering: v1 dual-check (flag + prefix); v2 single flag. Backstop logic removed (assumed migrated by now). +- Reply context: All v1 columns kept; v2 schema inherited. + +**What's gone and why:** +- `task_run_logs` — v2 doesn't persist execution history; logging is operational only. +- `router_state` — v1 polling cursors; v2 implicit in message queuing. +- Single-bot assumption — v2 is multi-tenant; this is a feature, not a loss. + +**Migration path:** v1 `src/v1/db-migration.test.ts` shows the pattern: create legacy table, init v2 schema, backfill. Migration 004 does this for agent_destinations (backfill from messaging_group_agents wirings). \ No newline at end of file diff --git a/docs/v1-vs-v2/env.md b/docs/v1-vs-v2/env.md new file mode 100644 index 000000000..560362c75 --- /dev/null +++ b/docs/v1-vs-v2/env.md @@ -0,0 +1,38 @@ +# env: v1 vs v2 + +## Scope +- v1: `src/v1/env.ts` (42 LOC), `src/v1/config.ts` (63 LOC) +- v2 counterparts: `src/env.ts` (identical), `src/config.ts` (identical structure); plus new consumers `src/webhook-server.ts`, `src/log.ts`, `src/container-runner.ts`, `container/build.sh`, `container/agent-runner/src/index.ts` + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| `readEnvFile(keys)` | `src/env.ts:11-42` | kept | Identical — reads `.env` without polluting `process.env` | +| `ASSISTANT_NAME` / `ASSISTANT_HAS_OWN_NUMBER` | `src/config.ts:8-12` | kept | Same read order: process.env → .env → default | +| `ONECLI_URL` | `src/config.ts:30` | kept | Used host-side + container-side | +| `TZ` + `isValidTimezone` guard | `src/config.ts:56-62` | kept | Passes to containers | +| `CONTAINER_IMAGE` / `CONTAINER_TIMEOUT` / `CONTAINER_MAX_OUTPUT_SIZE` | `src/config.ts:27-29` | kept | Same defaults | +| `MAX_MESSAGES_PER_PROMPT` | `src/config.ts:31` | kept | **Unused in v2** | +| `IDLE_TIMEOUT` | `src/config.ts:33` | kept | Used by container heartbeat model | +| `MAX_CONCURRENT_CONTAINERS` | `src/config.ts:34` | kept | Enforced in `container-runner.ts` | +| `POLL_INTERVAL` / `SCHEDULER_POLL_INTERVAL` / `IPC_POLL_INTERVAL` | `src/config.ts:13-32` | **dead code** | Defined but not imported anywhere in v2 runtime | +| `MOUNT_ALLOWLIST_PATH` / `SENDER_ALLOWLIST_PATH` | `src/config.ts:21-22` | kept | SENDER_ALLOWLIST_PATH unused (model replaced by `user_roles`) | +| `STORE_DIR` / `GROUPS_DIR` / `DATA_DIR` | `src/config.ts:23-25` | kept | `DATA_DIR` now hosts `v2.db` + `v2-sessions//*` | +| `buildTriggerPattern` / `getTriggerPattern` / `TRIGGER_PATTERN` / `DEFAULT_TRIGGER` | `src/config.ts:40-51` | kept | Used sparingly; trigger model largely DB-driven now | +| Container env injection via stdin JSON | `src/container-runner.ts:266-338` | **changed** | Replaced with `docker run -e`. New vars: `SESSION_INBOUND_DB_PATH`, `SESSION_OUTBOUND_DB_PATH`, `SESSION_HEARTBEAT_PATH`, `AGENT_PROVIDER`, `NANOCLAW_AGENT_GROUP_ID`, `NANOCLAW_AGENT_GROUP_NAME`, `NANOCLAW_MCP_SERVERS`, `NANOCLAW_ADMIN_USER_IDS` | +| `INSTALL_CJK_FONTS` | `container/build.sh:18-26`, `container/Dockerfile:13` | **new in v2** | Build-time arg, not runtime env | +| `WEBHOOK_PORT` (default 3000) | `src/webhook-server.ts:82` | **new in v2** | | +| `LOG_LEVEL` | `src/log.ts:16` | **new in v2** | | + +## Missing from v2 +Nothing user-facing. Container-only vars (`SESSION_*_DB_PATH`, `AGENT_PROVIDER`, `NANOCLAW_*`) are dynamic per-session and never belong in `.env`. + +## Behavioral discrepancies +1. **Dead constants**: `POLL_INTERVAL`, `SCHEDULER_POLL_INTERVAL`, `IPC_POLL_INTERVAL` remain in `src/config.ts` but are not imported by any v2 runtime code — safe to delete +2. **Container transport**: v1 piped config via stdin JSON; v2 injects via `-e` at spawn +3. **Build-time vs runtime**: `INSTALL_CJK_FONTS` is a Dockerfile build-arg, not a process env var +4. **Output markers**: v1's `---NANOCLAW_OUTPUT_START/END---` stdout markers are gone — v2 reads from `messages_out` table + +## Worth preserving? +Dead constants (`POLL_INTERVAL`, `SCHEDULER_POLL_INTERVAL`, `IPC_POLL_INTERVAL`) should be **removed** from `src/config.ts` — they're confusing carry-overs. Everything else is either actively used or deliberately dynamic. The `.env`-based config surface is byte-identical and correct to keep. diff --git a/docs/v1-vs-v2/formatting-test.md b/docs/v1-vs-v2/formatting-test.md new file mode 100644 index 000000000..c9be286d9 --- /dev/null +++ b/docs/v1-vs-v2/formatting-test.md @@ -0,0 +1,154 @@ +# formatting (test-only) : v1 vs v2 + +## Scope + +- **v1**: `/Users/gavriel/nanoclaw4/src/v1/formatting.test.ts` (316 lines) +- **v1 production sibling**: `/Users/gavriel/nanoclaw4/src/v1/router.ts` (43 lines) — `escapeXml()`, `formatMessages()`, `stripInternalTags()`, `formatOutbound()`, plus `/Users/gavriel/nanoclaw4/src/v1/config.ts` (63 lines) — `getTriggerPattern()`, `TRIGGER_PATTERN`, `buildTriggerPattern()`, `DEFAULT_TRIGGER` +- **v2 counterparts**: + - Inbound message formatting: `/Users/gavriel/nanoclaw4/container/agent-runner/src/formatter.ts` (228 lines) — `formatMessages()`, `categorizeMessage()`, `extractRouting()` + - Outbound tag stripping: embedded in container delivery logic + - Trigger patterns: moved to DB model (`messaging_group_agents.trigger_rules` JSON) — no code-level function + - v2 tests: `/Users/gavriel/nanoclaw4/container/agent-runner/src/poll-loop.test.ts:26–84` (formatter section only) + +--- + +## Test-case map + +| v1 Test Case | v2 Formatter Handling | Status | Notes | +|---|---|---|---| +| **escapeXml: ampersands** (src/v1/formatting.test.ts:22–23) | `/container/agent-runner/src/formatter.ts:225` `escapeXml()` with `&` → `&` | ✅ Preserved | Both use identical regex replacement. V2 escaping is used in `formatSingleChat()` for sender, time, text. | +| **escapeXml: less-than** (test:26–27) | `formatter.ts:225` `escapeXml()` with `<` → `<` | ✅ Preserved | Used in XML attributes and content. | +| **escapeXml: greater-than** (test:30–31) | `formatter.ts:225` with `>` → `>` | ✅ Preserved | Same. | +| **escapeXml: double quotes** (test:34–35) | `formatter.ts:225` with `"` → `"` | ✅ Preserved | Same. | +| **escapeXml: multiple special characters** (test:38–39) | `formatter.ts:225` (regex composition) | ✅ Preserved | Single pass through all four replacements. | +| **escapeXml: passthrough clean text** (test:42–43) | `formatter.ts:225` (no-op if no specials) | ✅ Preserved | Same. | +| **escapeXml: empty string** (test:46–47) | `formatter.ts:225` (no-op on empty) | ✅ Preserved | Same. | +| **formatMessages: single message with context header & time** (test:56–62) | `/container/agent-runner/src/formatter.ts:124–158` `formatChatMessages()` & `formatSingleChat()` | ⚠️ Changed | v1 formats as `\n...\n` with full timestamp in US locale. v2 uses `...` with 24-hour time only. No context header. | +| **formatMessages: multiple messages** (test:64–84) | `formatter.ts:124–134` (batch wrapping in `` tag) | ⚠️ Changed | v2 wraps multiple chat messages in `` tags but structure differs: no timezone attribute, different time format, `from` attribute added. | +| **formatMessages: escape sender names** (test:86–88) | `formatter.ts:157` `sender="${escapeXml(sender)}"` | ✅ Preserved | Same escaping strategy. | +| **formatMessages: escape content** (test:91–93) | `formatter.ts:157` `${escapeXml(text)}` | ✅ Preserved | Same. | +| **formatMessages: empty array** (test:96–99) | `formatter.ts:98` — returns empty string if no messages | ❌ Incompatible | v1 returns `\n\n\n` even for empty. v2 returns empty string. Different expected output. | +| **formatMessages: reply context (quoted_message)** (test:102–116) | `formatter.ts:143, 183–188` `formatReplyContext()` | ⚠️ Changed | v1 renders `reply_to="42"` attribute + `text` child. v2 renders as `preview` without message ID attribute. | +| **formatMessages: omit reply when absent** (test:119–122) | `formatter.ts:183` (conditional) | ✅ Preserved | Both check for presence before rendering. | +| **formatMessages: omit quoted_message when content missing** (test:125–136) | `formatter.ts:184` (check `replyTo.text`) | ✅ Preserved | Both guard against missing content. | +| **formatMessages: escape reply context** (test:139–151) | `formatter.ts:188` `escapeXml()` on sender and text | ✅ Preserved | Same escaping applied. | +| **formatMessages: timezone conversion** (test:154–160) | `formatter.ts:216–223` `formatTime()` — HH:MM UTC only | ❌ Incompatible | v1 uses `formatLocalTime()` (full locale string with date, month, am/pm) from `timezone.ts:26–37`. v2 uses 24-hour `HH:MM` UTC only; no timezone localization. | +| **TRIGGER_PATTERN: matches @name at start** (test:170–171) | No v2 code equivalent | ❌ Not in v2 | v2 moved trigger rules to DB; no regex pattern in code. Router evaluates `messaging_group_agents.trigger_rules` JSON. | +| **TRIGGER_PATTERN: case-insensitive** (test:174–176) | DB model (applied at runtime by router) | ❌ Not in v2 | Same behavior (case-insensitive in router) but no test coverage for trigger logic in v2. | +| **TRIGGER_PATTERN: word boundary checks** (test:179–192) | DB model (router enforces) | ❌ Not in v2 | Router evaluates trigger rules; no unit tests for pattern matching. | +| **getTriggerPattern: custom per-group trigger** (test:201–206) | `/src/router.ts` evaluates `messaging_group_agents.trigger_rules` at delivery time | ❌ Not tested in v2 | v2 has no unit test for custom trigger selection. Behavior preserved in router but untested. | +| **getTriggerPattern: regex characters literal** (test:215–219) | DB-stored rule (router uses literal match or regex) | ❌ Not tested | v2 stores trigger as string in DB; runtime evaluation depends on router implementation (not inspected here). | +| **stripInternalTags: single-line** (test:226–227) | No direct v2 function — embedded in polling | ❌ Not isolated | v1 regex `/[\s\S]*?<\/internal>/g` with `.trim()`. v2 container poll-loop does not test this; no dedicated outbound function in v2 agent-runner. | +| **stripInternalTags: multi-line** (test:230–231) | Not tested in v2 | ❌ Not isolated | v1 regex handles `[\s\S]*?` (newlines included). | +| **stripInternalTags: multiple blocks** (test:234–235) | Not tested in v2 | ❌ Not isolated | Regex global flag `/g` handles multiple. Not verified in v2 tests. | +| **stripInternalTags: only internal tags** (test:238–239) | Not tested in v2 | ❌ Not isolated | v1 returns empty after trim; behavior not verified in v2. | +| **formatOutbound: passthrough clean text** (test:244–245) | Not tested in v2 | ❌ Not isolated | v1 calls `stripInternalTags()` then returns. v2 does not have isolated test. | +| **formatOutbound: empty after strip** (test:248–249) | Not tested in v2 | ❌ Not isolated | v1 returns empty if all was internal. | +| **formatOutbound: strip tags from text** (test:252–253) | Not tested in v2 | ❌ Not isolated | v1 example: `thinkingThe answer is 42` → `The answer is 42`. | +| **trigger gating: main group always processes** (test:277–279) | No unit test in v2; logic in `/src/router.ts` routing decision | ❌ Not tested | v1 shows that main groups bypass trigger check. Behavior likely preserved (main group always forwards to agent) but not verified by test. | +| **trigger gating: main group ignores requiresTrigger flag** (test:282–284) | Not tested in v2 | ❌ Not tested | v1 shows `isMainGroup=true` overrides `requiresTrigger` flag. No v2 test. | +| **trigger gating: non-main needs trigger (default)** (test:287–289) | Not tested in v2 | ❌ Not tested | v1 default behavior: non-main group requires trigger unless explicitly disabled. | +| **trigger gating: custom per-group trigger enforcement** (test:302–309) | Not tested in v2 | ❌ Not tested | v1 shows per-group trigger override. Behavior in v2 DB but no test. | +| **trigger gating: requiresTrigger=false disables check** (test:312–314) | Not tested in v2 | ❌ Not tested | v1 allows opting out of trigger requirement per group. | + +--- + +## Missing from v2 + +1. **Timezone-aware time formatting** + - v1: `formatLocalTime(utcIso, timezone)` in `src/v1/timezone.ts:26–37` converts UTC ISO timestamp to user's local timezone with full locale formatting (date, month, am/pm). + - v2: `formatTime()` in `container/agent-runner/src/formatter.ts:216–223` only extracts `HH:MM` in UTC, no localization. + - **Impact**: v2 loses per-agent timezone context. Timestamps appear in UTC only, potentially confusing users in different timezones. + +2. **Context header with timezone attribute** + - v1: Every message batch includes `` header. + - v2: No context header; timestamp is a message attribute only. + - **Impact**: Agent sees no explicit timezone declaration; must infer from message times or system prompt. + +3. **Reply context with message ID attribute** + - v1: `reply_to=""` attribute on message; separate `content` child. + - v2: Consolidated into `preview` without message ID; preview truncated to 100 chars. + - **Impact**: v2 loses structured reply tracking; agent can't reference specific message IDs in follow-ups. + +4. **Message ID sequence in XML** + - v1: No `id` attribute on messages (WhatsApp-era design). + - v2: Each message has `id="seq"` (database sequence number). + - **Impact**: Allows agent to reference messages by ID, but v1 tests do not verify this. + +5. **Trigger pattern unit tests** + - v1: Comprehensive tests for `getTriggerPattern()`, `TRIGGER_PATTERN`, case-insensitivity, word boundaries, regex escaping. + - v2: No unit tests; trigger logic moved to DB and router. Untested. + - **Impact**: Trigger matching behavior not verified by tests; regression risk if router changes. + +6. **Internal tag stripping tests** + - v1: `stripInternalTags()` and `formatOutbound()` tested for single-line, multi-line, multiple blocks, edge cases. + - v2: No isolated tests for outbound tag stripping. + - **Impact**: No verification that internal tags are reliably removed before delivery. + +7. **Trigger gating (requiresTrigger flag) tests** + - v1: Detailed tests of main-group bypass, per-group override, default behavior, flag combinations. + - v2: No tests; logic moved to DB schema and router evaluation. + - **Impact**: Trigger enforcement behavior not verified. + +8. **Empty message batch handling** + - v1: Explicitly returns `\n\n\n` for empty array. + - v2: Returns empty string. + - **Impact**: No clear protocol for "no messages to process" signals. + +--- + +## Behavioral discrepancies + +### 1. Message XML structure (formatMessages) +- **v1**: `\n\ncontent\n` +- **v2**: `content` (no wrapper for single message) +- **v1 line**: `src/v1/router.ts:9–23` +- **v2 line**: `container/agent-runner/src/formatter.ts:124–158` + +### 2. Time formatting +- **v1**: Full locale string (e.g., "Jan 1, 2024, 1:30 PM") using `Intl.DateTimeFormat` with timezone localization (`src/v1/timezone.ts:26–37`) +- **v2**: 24-hour UTC only (e.g., "13:30") without timezone info (`container/agent-runner/src/formatter.ts:216–223`) +- **Impact**: v2 loses timezone awareness; agent cannot distinguish between user's local time and server time. + +### 3. Reply context structure +- **v1**: Two-part — `reply_to=""` attribute + `text` child element +- **v2**: Single element — `100-char preview` (no ID, preview truncated) +- **v1 line**: `src/v1/router.ts:12–16` +- **v2 line**: `container/agent-runner/src/formatter.ts:143, 183–188` +- **Impact**: v2 cannot support message-ID-based threading; loses structured reply metadata. + +### 4. Trigger pattern matching +- **v1**: Implemented as regex returned by `getTriggerPattern()` with word-boundary enforcement (`config.ts:40–49`) +- **v2**: Stored in DB as JSON in `messaging_group_agents.trigger_rules`; evaluated by router at delivery time +- **v1 line**: `src/v1/config.ts:40–49` +- **v2 line**: `/src/router.ts` (router logic, not inspected in detail here) +- **Impact**: v1 enforces word boundaries via regex (`\b`); v2 implementation unknown (DB-driven). + +### 5. Empty message handling +- **v1**: Returns `\n\n\n` — preserves structure +- **v2**: Returns empty string +- **v1 line**: `src/v1/router.ts:22` +- **v2 line**: `container/agent-runner/src/formatter.ts:98` + +### 6. Internal tag stripping +- **v1**: Regex-based, `.trim()` called after removal +- **v2**: Not isolated; no dedicated function or test in v2 formatter +- **v1 line**: `src/v1/router.ts:25–26` +- **v2 line**: No equivalent + +--- + +## Worth preserving? + +**Partially.** The v1 formatting test suite is **essential for documenting lost functionality**, not for v2 regression. Key behaviors that should be preserved in v2 but are currently missing: + +1. **Timezone-aware message timestamps** — v2 should restore `formatLocalTime()` from `src/v1/timezone.ts` and include timezone context in the XML header. Without this, agents cannot reason about when messages arrived relative to the user's clock. + +2. **Reply context with message IDs** — v2's truncated reply preview is lossy. Consider restoring the `reply_to=""` attribute so agents can reference prior messages by sequence number for structured threading. + +3. **Trigger pattern unit tests** — v2 moved trigger logic to the DB but lost test coverage. The DB schema and router must enforce the same invariants (word boundaries, case-insensitivity, custom per-group overrides) that v1 tested. Recommend adding integration tests to `src/router.ts` or `src/channels/adapter.ts` to verify trigger matching. + +4. **Internal tag stripping tests** — v2 agent-runner should include unit tests for `stripInternalTags()` (if the skill applies) to prevent regression when Claude adds `` thinking tags. + +The v1 test file serves as a **specification document** for channel formatting and trigger gating that v2 partially refactored away. Keeping it in the repo (even unpowered) documents the intended semantics. + diff --git a/docs/v1-vs-v2/group-folder.md b/docs/v1-vs-v2/group-folder.md new file mode 100644 index 000000000..bf0d890a4 --- /dev/null +++ b/docs/v1-vs-v2/group-folder.md @@ -0,0 +1,38 @@ +# group-folder: v1 vs v2 + +## Scope +- v1: `src/v1/group-folder.ts` (45 LOC), `group-folder.test.ts` (35 LOC) — validation + path resolution only +- v2 counterparts: + - `src/group-folder.ts` (45 LOC) — byte-identical to v1 + - `src/group-init.ts` (128 LOC) — **new** filesystem bootstrap + - `src/container-config.ts` (115 LOC) — **new** per-group container.json management + - `src/group-folder.test.ts` (35 LOC) — identical to v1 + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| `GROUP_FOLDER_PATTERN` (alphanumeric + `-` + `_`, 1-64) | `group-folder.ts:5-6` | identical | | +| Reserved folder `global` | `group-folder.ts:6` | identical | `RESERVED_FOLDERS` set | +| `isValidGroupFolder()` (reject empty, whitespace, traversal, absolute) | `group-folder.ts:8-16` | identical | | +| `assertValidGroupFolder()` | `group-folder.ts:18-22` | identical | | +| `resolveGroupFolderPath()` + `ensureWithinBase()` | `group-folder.ts:31-36` | identical | | +| `resolveGroupIpcPath()` (resolves `data/ipc/`) | `group-folder.ts:38-44` | kept | IPC dir is legacy — no longer used since v2 moved to session DBs | +| Filesystem scaffold (CLAUDE.md, skills, overlays) | — | **new in v2** | `group-init.ts:48-127` | +| Global memory symlink (`.claude-global.md` → `/workspace/global/CLAUDE.md`) | `group-init.ts:55-70` | **new** | Uses `lstat` to detect dangling symlinks | +| Per-group `container.json` init | `group-init.ts:83-85` + `container-config.ts:109-114` | **new** | Graceful fallback on corruption | +| `.claude-shared` session dir | `group-init.ts:87-92` | **new** | Under `data/v2-sessions//` | +| `settings.json` with `CLAUDE_CODE_*` flags | `group-init.ts:94-98` | **new** | | +| Recursive skill copy from `container/skills/` | `group-init.ts:100-107` | **new** | | +| Per-group agent-runner src overlay copy | `group-init.ts:109-117` | **new** | | +| Idempotent init (every step gates on `fs.existsSync()`) | `group-init.ts:44-127` | **new** | Safe to re-run | +| Step logging via `log.info()` | `group-init.ts:119-126` | **new** | | + +## Missing from v2 +None. All v1 validation/resolution behavior is preserved byte-for-byte. + +## Behavioral discrepancies +None on the validation layer. v2 adds the filesystem-scaffold layer as a separate module (`group-init.ts`) so validation stays pure. + +## Worth preserving? +Clean split — keep as-is. `group-folder.ts` = names + paths; `group-init.ts` = file creation. Both modules are small and single-purpose. diff --git a/docs/v1-vs-v2/group-queue.md b/docs/v1-vs-v2/group-queue.md new file mode 100644 index 000000000..da21d033d --- /dev/null +++ b/docs/v1-vs-v2/group-queue.md @@ -0,0 +1,48 @@ +# group-queue: v1 vs v2 + +## Scope +- v1: `src/v1/group-queue.ts` (325 LOC), `group-queue.test.ts` (457 LOC) — in-memory per-group state machine, IPC-file dispatch +- v2: **no equivalent class**. Serialization is now DB-based and distributed across `src/session-manager.ts`, `src/host-sweep.ts`, `src/container-runner.ts`, `src/delivery.ts` + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| Per-group message queue | `inbound.db.messages_in` + `status='pending'` | replaced | Atomic status transitions serialize work per-session | +| Per-group task queue | `inbound.db.messages_in` with `kind='task'` | replaced | Same table; `kind` discriminates | +| `MAX_CONCURRENT_CONTAINERS` global cap | `container-runner.ts:42-52` `activeContainers` Map + `wakeContainer` dedup | kept | Enforced at spawn | +| One container per group invariant | One container per **session** | redefined | Session is identity unit now | +| Task-before-message priority (`drainGroup`) | `host-sweep.ts` recurrence + `delivery.ts` active poll | **partially lost** | No priority; polled by `process_after` timestamp ordering | +| Exponential retry backoff | `host-sweep.ts:145-147` `BACKOFF_BASE_MS * 2^tries` | kept | Max 5 tries, same shape | +| Idle preemption (`notifyIdle`/`closeStdin`) | heartbeat file mtime | **removed** | No interrupt signal — container polls continuously | +| Message dispatch to active container (`sendMessage`) | Write to `messages_in` table | replaced | Host writes; container polls | +| Cascading drain on task arrival | `delivery.ts` (~1s) + `host-sweep.ts` (~60s) polls | **async-ized** | Work discovery on next tick, not synchronous | +| Shutdown without kill | containers continue under `--rm` | similar | Host shutdown does not stop containers | +| Task dedup (`pendingTasks.some(t => t.id === id)`) | PK on `messages_in.id` | partial | Unique ID prevents DB duplicates; does not prevent two distinct rows with same series_id | +| `drainWaiting` (waiting-group fairness) | Implicit: any session can wake if slot free | async | No explicit fairness | + +## Serialization model diff +**v1 (push-based):** `GroupState` in memory per group: `active`, `pendingMessages`, `pendingTasks`, `idleWaiting`, `runningTaskId`. `drainGroup()` synchronously dispatches. IPC file write signals container readiness. State lost on restart. + +**v2 (pull-based via DB):** `messages_in.status` is the queue (`pending` → `processing` → `completed`/`failed`). Host writes rows + calls `wakeContainer()`; container polls + atomic UPDATE to take work. One writer per DB file (host→inbound, container→outbound) eliminates cross-mount contention. Heartbeat file mtime replaces IPC for liveness. State persisted; survives crashes. + +## Missing from v2 +1. **Idle-state preemption** — v1 could interrupt an idle container on task arrival via `closeStdin`. v2 has no interrupt; container finishes current work and polls again +2. **Synchronous drain cascade** — v1's `drainGroup` immediately ran the next item; v2 discovers it on the next poll tick (~1s active, ~60s sweep) +3. **In-memory task dedup** — v1 checked pending-task list before enqueue. v2 can have two task rows with the same series_id coexisting (both pending) — relies on atomic `status` update for single-execution, best-effort +4. **Priority ordering** — v1 tasks preempted messages; v2 is timestamp-ordered only + +## Behavioral discrepancies +| Aspect | v1 | v2 | +|---|----|----| +| Wake trigger | on enqueue (sync) | on `wakeContainer()` call, or poll finding due message | +| Idle timeout | implicit via IPC | explicit heartbeat mtime (10 min) | +| Task ordering | FIFO within group, tasks preempt messages | `process_after` timestamp; ties by insert seq | +| Retry | host `scheduleRetry()` | host sweep detects stale, increments `tries`, sets backoff | +| Concurrency cap | same | same (enforced in `spawnContainer` dedup) | + +## Worth preserving? +1. **Explicit task dedup** — add `(kind, series_id, session_id)` unique index on `messages_in`, or dedup in `host-sweep.ts` before inserting retry rows. Currently best-effort via atomic status update +2. **Priority ordering** — add a `priority` column or document the ~1s task-wake latency as the SLA +3. **Idle preemption** — not critical; 1s polling is acceptable for most workflows +4. **Fairness** — v1's `drainWaiting` ensured no group starved. v2 is fair by timestamp but untested under concurrent load. Monitor in production diff --git a/docs/v1-vs-v2/index-host.md b/docs/v1-vs-v2/index-host.md new file mode 100644 index 000000000..277daf471 --- /dev/null +++ b/docs/v1-vs-v2/index-host.md @@ -0,0 +1,70 @@ +# host index: v1 vs v2 + +## Scope +- v1: `src/v1/index.ts` (647 LOC) — monolithic entry: config, DB, state, channels, queues, scheduler, IPC watcher, message loop +- v2: `src/index.ts` (345 LOC) — lean entry: DB+migrations, channels, delivery/sweep polls, OneCLI handler + +## Startup sequence diff + +| # | v1 step | v2 step | Status | +|---|---------|---------|--------| +| 1 | `ensureContainerRuntimeRunning()` + `cleanupOrphans()` | same | kept | +| 2 | `initDatabase()` | `initDb()` + `runMigrations()` | enhanced (explicit migrations) | +| 3 | `loadState()` — cursor, groups, agent timestamps | — | removed (no global state) | +| 4 | OneCLI `ensureAgent` per group | — | removed (now per-wake in `container-runner.ts`) | +| 5 | `restoreRemoteControl()` | — | removed | +| 6 | SIGTERM/SIGINT handlers | same | kept | +| 7 | `handleRemoteControl` bind | — | removed | +| 8 | Channel options + callbacks | `initChannelAdapters()` | rewritten (adapter API) | +| 9 | Channel discovery + connection | absorbed into adapters | — | +| 10 | `startSchedulerLoop()` | — | removed (folded into `startHostSweep`) | +| 11 | `startIpcWatcher()` | — | removed (no IPC in v2) | +| 12 | `startSessionCleanup()` | — | removed (folded into `startHostSweep`) | +| 13 | `queue.setProcessMessagesFn()` | — | removed (GroupQueue gone) | +| 14 | `recoverPendingMessages()` | — | **removed** (implicit in sweep) | +| 15 | `startMessageLoop()` (polling) | `startActiveDeliveryPoll()` + `startSweepDeliveryPoll()` | **fundamentally changed** (event-driven) | +| 16 | — | `startHostSweep()` | **new** | +| 17 | — | `startOneCLIApprovalHandler()` | **new** | + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| Arg/env parsing | `src/config.ts` (shared) | kept | | +| Central DB init | `src/index.ts:47-50` | kept | + `runMigrations()` | +| Container runtime bring-up | `src/index.ts:52-54` | kept | identical | +| Global cursor + timestamps state | — | **removed** | v2 session-scoped state in outbound.db | +| Periodic message polling loop | — | **removed** | Replaced by event-driven delivery + 60s sweep | +| OneCLI group-wide sync at startup | — | **removed** | Per-wake in `container-runner.ts:303` | +| Remote control subsystem | — | **removed** | No equivalent — feature deferred | +| Group message queue (`GroupQueue`) | — | **removed** | DB-based serialization | +| Channel adapter array + callbacks | `src/channels/channel-registry.ts` | refactored | `ChannelAdapter` interface | +| Pending message recovery on startup | — | **removed** | Sweep detects stale containers + resets messages | +| IPC watcher (dynamic group add) | — | **removed** | Static topology at startup; restart to add groups | +| Signal handlers | `src/index.ts:339-340` | kept | Simplified teardown | +| Top-level error handling | `src/index.ts:342-345` | kept | Same fatal exit | + +## Missing from v2 +1. **Polling message loop** (v1:370-459) — replaced by event-driven + sweep (net improvement) +2. **GroupQueue state machine** — now DB-based +3. **Cross-restart cursor state** — no `lastAgentTimestamp` persisted; recovery implicit via DB scan +4. **Remote control** — gone +5. **Explicit `recoverPendingMessages()`** — implicit in sweep; worth verifying via post-crash test +6. **IPC watcher** (`startIpcWatcher`) — cannot add groups dynamically; restart required +7. **Scheduler loop** — merged into sweep's due-message wake + +## Behavioral discrepancies +| Aspect | v1 | v2 | +|---|----|----| +| Startup time | ~500ms (long loop init) | ~200ms | +| Message fetch | polling every POLL_INTERVAL | event-driven callbacks + 1s delivery poll | +| Container spawn | on-demand via GroupQueue | per-message wake via router/sweep | +| Group topology | dynamic (IPC watcher) | static at startup | +| Error recovery | per-message cursor rollback | implicit via stale detection | +| Shutdown | GroupQueue 10s grace then disconnect | stop handlers/polls/sweep/adapters in order | + +## Worth preserving? +1. **Polling loop**: No — event-driven is superior. Verify delivery poll latency regression vs old POLL_INTERVAL under load +2. **Pending-message recovery**: Worth explicit restoration — kill a container mid-message, restart host, verify re-delivery within ≤5s. If sweep doesn't cover this, add startup-phase scan +3. **Remote control**: Unknown — either restore as opt-in skill or document removal +4. **Dynamic group add (IPC watcher)**: Probably not worth — modern flow is "admin skill adds group to DB, restart". But document that restart is required diff --git a/docs/v1-vs-v2/ipc.md b/docs/v1-vs-v2/ipc.md new file mode 100644 index 000000000..10c643f6b --- /dev/null +++ b/docs/v1-vs-v2/ipc.md @@ -0,0 +1,240 @@ +# IPC: v1 vs v2 + +## Scope + +### v1 +- **Host side:** `/Users/gavriel/nanoclaw4/src/v1/ipc.ts` (127 lines) — file-system watcher, task authorization, message routing +- **Auth/handshake tests:** `/Users/gavriel/nanoclaw4/src/v1/ipc-auth.test.ts` (614 lines) — authorization gates, schedule types, cron validation +- **Container side:** `/Users/gavriel/nanoclaw4/container/agent-runner/src/v1/ipc-mcp-stdio.ts` (509 lines) — MCP server over stdio, file-based message writes +- **Total v1 codebase:** ~1,250 lines (v1/ subtree) + +### v2 counterparts +This is not a file-for-file mapping. The entire IPC abstraction layer has been replaced with SQLite DBs: + +- **Host delivery/routing:** `/Users/gavriel/nanoclaw4/src/delivery.ts` (912 lines) — polls outbound.db, delivers, handles system actions +- **Host sweep/recurrence:** `/Users/gavriel/nanoclaw4/src/host-sweep.ts` (174 lines) — 60s maintenance, stale detection via heartbeat, processing_ack sync +- **Session setup/DB:** `/Users/gavriel/nanoclaw4/src/session-manager.ts` (361 lines) — DB paths, folder init, destinations + routing writes +- **Container poll loop:** `/Users/gavriel/nanoclaw4/container/agent-runner/src/poll-loop.ts` (200+ lines) — fetches messages_in, marks status in processing_ack +- **Container destinations:** `/Users/gavriel/nanoclaw4/container/agent-runner/src/destinations.ts` (118 lines) — reads inbound.db's destinations table live +- **DB layer (host):** `src/db/session-db.ts` — insertMessage, getDueOutboundMessages, markDelivered, syncProcessingAcks, etc. +- **DB layer (container):** `container/agent-runner/src/db/{messages-in,messages-out,session-state,connection}.ts` +- **Schema:** `/Users/gavriel/nanoclaw4/docs/db-session.md` (184 lines) — definitive per-session DB layout + +--- + +## Paradigm shift + +**v1: IPC as explicit message files + stdio tunnel + MCP server** + +In v1, the host spawned an MCP server inside each container's stdio. The container's `ipc-mcp-stdio.ts` exposed tools (`send_message`, `schedule_task`, `register_group`, etc.) by writing JSON files to the host's `data/ipc/{groupFolder}/{messages|tasks}/` directory. The host's `ipc.ts` file-watcher scanned these directories every `IPC_POLL_INTERVAL` (~1s), parsed the JSON, applied authorization gates (isMain? folder-match?), executed side effects (DB writes, group registration), and deleted the files. Ordering, atomicity, and backpressure were implicit in the filesystem. + +**v2: Everything is a message in two persistent DBs** + +The IPC abstraction has been *entirely removed*. All host↔container communication now flows through two SQLite files per session: +- **inbound.db** (host writes, container reads): `messages_in` for inbound chat/tasks, `destinations` for the routing map, `session_routing` for default reply channel +- **outbound.db** (container writes, host reads): `messages_out` for agent responses, `processing_ack` for status acks, `session_state` for continuation storage + +There is no MCP server inside the container that exposes system tools. Instead: +- **Container side** calls `writeMessageOut()` directly, writing a JSON `content` blob with `action="schedule_task"` (or similar) into the `messages_out` table. +- **Host side** polls `getDueOutboundMessages()` from outbound.db, deserializes the `content`, and in `handleSystemAction()` interprets the action, validates it, and applies it directly to inbound.db (no IPC file write). + +The single-writer-per-file invariant (host writes inbound.db, container writes outbound.db) replaces the file-system locking and atomic rename semantics. + +**Key ownership shift:** +- v1: Container owned the "request to do something" (file write). Host decided whether to act (authorization on read). +- v2: Host owns the "task is pending" state (messages_in row). Container marks its progress (processing_ack). Host syncs status, detects stale containers, and triggers recurrence. + +--- + +## Capability map + +| v1 IPC Behavior | v2 Equivalent | Status | Notes | +|---|---|---|---| +| **Handshake / auth** | Database schema + envelope ID | ✓ Functional but different | v1: read `isMain` env var at startup, gate each IPC op. v2: host resolves session once, container reads `destinations` table on every query. No per-message auth envelope. | +| **Message framing** | JSON in files (atomic rename) | ✓ Replaced with DB schema | v1: `writeIpcFile()` temp-then-rename. v2: `better-sqlite3` with `journal_mode=DELETE` + open-close-per-op for cross-mount visibility. | +| **Transport (pipes/sockets)** | SQLite on FUSE mount | ✓ Completely different | v1: filesystem watching (no network). v2: cross-mount DB access (requires `journal_mode=DELETE` pragma, see session-manager.ts:9–11). | +| **Message types** | `kind` field in messages_in/out | ✓ Expanded | v1: message/task files. v2: `kind=chat|task|system|...` in DB rows, content shape in [api-details.md](../api-details.md). | +| **Auth / authorization gates** | Host-side permission checks in delivery.ts | ◐ Simplified but different | v1: checked per file (isMain flag, folder-match). v2: admin perms checked at container startup (adminUserIds set in poll-loop.ts:22–33), destination ACL in agent_destinations table, delivery.ts enforces on send. No per-message envelope. | +| **Handshake semantics** | None (session exists at startup) | ✗ Removed | v1: env vars set identity at container boot. v2: session_id/agent_group_id is stable DB fixture; container learns routing from `session_routing` table. No negotiation. | +| **Backpressure / flow control** | Implicit (filesystem poll interval) | ◐ Different model | v1: host polls files at 1s intervals; if processing is slow, files pile up. v2: messages_in rows sit with `status='pending'` until container marks `processing_ack='processing'`, then host polls and syncs status. Host can enforce delivery retry budget (MAX_DELIVERY_ATTEMPTS=3 in delivery.ts:58). | +| **Keepalives / timeouts** | No explicit mechanism | ✓ Heartbeat file replaces | v1: IPC files served as implicit liveness. v2: container touches `.heartbeat` file (mtime tracked by host). Host uses heartbeat staleness (10min threshold in host-sweep.ts:32) to detect crash and reset stuck messages. | +| **Ordering / seq parity** | Implicit filename order (timestamp+random) | ✓ Enforced | v1: files had timestamps but no formal ordering. v2: `seq` is monotonic per session, even←host / odd←container (see db-session.md §3). Parity disambiguates edit/reaction targeting. | +| **Reconnect semantics** | Container restart picks up where it left off (env vars) | ✓ Improved | v1: continuation not persisted across restarts. v2: provider continuation (Claude JSON transcript, etc.) stored in `session_state.session_id` on every SDK result. Survives crash. | +| **Error handling / retries** | File left in `errors/` dir on parse failure | ✓ Better visibility | v1: failed IPC files moved to `data/ipc/errors/` for manual inspection. v2: `status='failed'` in messages_in; delivery.ts retries with exponential backoff (3 attempts), marks failed on max. Persisted in DB for audit. | +| **Task scheduling (schedule_task)** | IPC file write → host parses → DB insert | ✓ Same end result, different path | v1: container writes task JSON, host reads/validates cron. v2: container writes `system` message with `action="schedule_task"` to messages_out, host reads + inserts into messages_in as new `kind='task'` row. Validation still in host (cron parsing at delivery time). | +| **Admin commands (/clear, /setup)** | Not in v1 IPC | ✓ Implemented | v2 has `/clear` command in poll-loop.ts, checked against adminUserIds set. Clears `session_state.session_id`. No MCP server expose. | +| **Tool-call plumbing** | MCP server in container exposes send_message, schedule_task, etc. | ✗ Removed entirely | v1 tools are now plain SDK result processors. send_message writes messages_out. schedule_task writes messages_out with action="schedule_task". | +| **Message delivery tracking** | None (fire-and-forget) | ✓ Added | v1: host sends message, doesn't track if it reached the user. v2: `delivered` table in inbound.db (platform_message_id + status). delivery.ts marks as delivered/failed. Enables message edits, reactions, and retry logic. | +| **Stale container detection** | None | ✓ Added | v1: no heartbeat. v2: host-sweep.ts checks `.heartbeat` mtime. If >10min old and processing_ack has 'processing' entries, resets with backoff. | +| **Recurrence / cron re-firing** | Not in v1 | ✓ Added | v1: tasks were one-shot. v2: `recurrence` field in messages_in + `series_id`. host-sweep.ts fires next occurrence when completed message has recurrence. CronExpressionParser used at sync time. | + +--- + +## Missing from v2 + +### 1. **Auth handshake envelope** +v1 had explicit authorization gates for *every* IPC operation: +- Read `isMain` and `groupFolder` from env vars at startup (ipc-mcp-stdio.ts:19–21) +- For `schedule_task`: gate the `targetJid` — non-main groups can only schedule for `chatJid` (line 187–188) +- For `register_group`: only isMain=true can call (line 471–481) +- For `send_message`: isMain || (target group's folder == sender's folder) (ipc.ts:78) + +**v2 equivalent:** Authorization is now **split**: +- Container time: adminUserIds set passed at boot (poll-loop.ts:22–33), used to gate `/clear` command only +- Delivery time: host checks destination ACL via agent_destinations table, permission to send to a messaging group (delivery.ts:535–561) +- No per-message auth envelope; the session fixture itself represents authorization + +**What's lost:** Per-request explicit authorization metadata. The agent can't *prove* it's "main" anymore; instead the host verifies at delivery time using the central DB. This is arguably *better* security (no token in container to leak), but if the agent needs to know *why* a request failed, it no longer gets an explicit auth reject response. + +### 2. **Backpressure / request queuing** +v1 file-based IPC was **implicitly backpressured**: +- Container calls `send_message()` MCP tool, which calls `writeIpcFile()` and returns immediately (fire-and-forget) +- If the host is slow or overloaded, files pile up in `data/ipc/messages/` +- Container is blocked only if the filesystem fills + +**v2 equivalent:** No queueing or explicit backpressure: +- Container calls `writeMessageOut()`, which executes a synchronous SQLite INSERT into outbound.db +- Host polls outbound.db at 1s (active) or 60s (sweep) +- If delivery fails, messages sit in outbound.db with `status='pending'` until 3 retries exhausted + +**What's lost:** Queue depth visibility. In v1, you could see `ls data/ipc/messages/ | wc -l` to get backlog. In v2, you have to query the outbound DB. The container has no way to ask "how many pending messages are waiting for me?" — it just writes and hopes the host picks them up. + +### 3. **Explicit keepalive / ping** +v1 had implicit keepalives via file timestamps: +- Each IPC file wrote a `timestamp` field (ipc-mcp-stdio.ts:61, 202) +- Host could reason about "last IPC activity" + +**v2 equivalent:** Heartbeat file mtime: +- Container touches `.heartbeat` file (connection.ts `touchHeartbeat()`) +- Host checks mtime every 60s in host-sweep.ts +- Detects stale if >10min old and processing_ack has 'processing' entries + +**What's lost:** Sub-heartbeat timeouts. If the container is hung but the heartbeat is fresh (just stuck in a long computation), the host won't detect it. v1 had no explicit timeout either, so this is not a regression, but there's no keepalive *mechanism* (no ping/pong protocol). + +### 4. **Payload size limits / chunking** +v1 wrote task files with a single JSON blob: +- ipc-mcp-stdio.ts:31: `fs.writeFileSync(tempPath, JSON.stringify(data, null, 2))` +- Filesystem might have limits on inode size, but generally no explicit cap + +**v2:** No explicit chunking or size limits in the DB layer: +- messages_in.content and messages_out.content are TEXT +- SQLite TEXT default is ~1GB per cell +- No mention in the codebase of max payload size + +**What's lost:** Explicit awareness. In v1, if a task prompt was 10MB, it would be a 10MB JSON file. In v2, it's a 10MB DB cell. The system doesn't actively prevent this, and there's no mention of a sanitizer. + +--- + +## Behavioral discrepancies + +### 1. **Task scheduling authorization** +**v1** (ipc-auth.test.ts:71–127): +```typescript +// Main group can schedule for another group +await processTaskIpc({ type: 'schedule_task', targetJid: 'other@g.us' }, 'whatsapp_main', true, deps); +// Non-main group can ONLY schedule for itself +await processTaskIpc({ type: 'schedule_task', targetJid: 'main@g.us' }, 'other-group', false, deps); +// ↑ blocked by authorization gate (ipc.ts:170) +``` + +**v2** (delivery.ts:645–712): +The container writes a `system` message with `action="schedule_task"` directly into messages_out. The host reads it and calls `insertTask(inDb, {...})` **with no authorization gate**. The `targetJid` is derived from the system message `platformId` and `channelType`, not from an explicitly routed `targetJid` parameter. + +**Discrepancy:** v1 prevented non-main groups from scheduling cross-group tasks at the *request* stage. v2 has no equivalent gate — the container can write any task to any group (in theory) because it's the host that does the actual DB insert. In practice, the container only has one session and only sees messages for that session, so it can't *reach* another group's messages_in. But the authorization model is implicitly structural, not explicit. + +### 2. **Message send authorization** +**v1** (ipc-auth.test.ts:339–373): +```typescript +// Main can send to any chat +expect(isMessageAuthorized('whatsapp_main', true, 'other@g.us', groups)).toBe(true); +// Non-main can send to its own chat +expect(isMessageAuthorized('other-group', false, 'other@g.us', groups)).toBe(true); +// Non-main cannot send to another group's chat +expect(isMessageAuthorized('other-group', false, 'main@g.us', groups)).toBe(false); +``` + +**v2** (delivery.ts:550–561): +```typescript +const isOriginChat = session.messaging_group_id === mg.id; +if (!isOriginChat && !hasDestination(session.agent_group_id, 'channel', mg.id)) { + throw new Error(`unauthorized channel destination: ...`); +} +``` + +The container's session has a fixed `messaging_group_id` + `thread_id`. The agent can only reply to that origin or to a destination in the `agent_destinations` table. There is no isMain flag. + +**Discrepancy:** v1 was group-centric (folder-based identity). v2 is session-centric (agent is wired to one or more messaging groups via central DB, projected into inbound.db). If an agent is wired to multiple chats with `session_mode='agent-shared'`, it has one session and can see all of them as destinations. This is more flexible than v1's binary main/non-main gate. + +### 3. **Task update semantics** +**v1** (ipc-auth.test.ts:264–309): Container passes `type='update_task'`, host reads the task, re-computes `next_run` if schedule changed, updates DB. + +**v2** (delivery.ts:695–712): Container writes `system` message with `action="update_task"`, host applies the update directly. The host **does not** recompute `next_run` if the schedule changes — it only updates the fields the container specified. Recurrence is re-fired by the *host* in host-sweep.ts (line 160–165), not at update time. + +**Discrepancy:** v1 eagerly recomputed next_run on update. v2 lazily computes it during the 60s sweep. If an agent updates a task's cron expression, it won't take effect until the next sweep cycle. This is a ~60s latency increase. + +### 4. **Error handling** +**v1** (ipc.ts:85–91): Files that fail to parse are moved to `data/ipc/errors/` for manual inspection. + +**v2** (delivery.ts:422–459): Messages that fail delivery get up to 3 retries with exponential backoff. If they still fail, they're marked `status='failed'` in the DB. There's no "errors" directory; the audit trail is in the DB + logs. + +**Discrepancy:** v1's error handling was "fire-and-forget" (parse, move on). v2's is "retry + persistent state." This is better observability, but v1's "move to errors/" was a gentler way to pause processing without losing the file. + +### 5. **Reconnect / session resumption** +**v1:** No persistence. If the container crashed, the next restart had no knowledge of prior messages or state. + +**v2** (poll-loop.ts:51–55): Reads `session_state.session_id` at startup and passes it to the provider as `continuation`. The provider (Claude) deserializes a `.jsonl` transcript and resumes. Survives container crash. + +**Discrepancy:** v2 has explicit continuation support. v1 did not. This is a strict improvement. + +--- + +## Worth preserving? + +### 1. **Per-request authorization envelope** +**Recommendation:** No, v2's structural approach is better. In v1, a malicious container could spoof an isMain flag to bypass gates (though env vars are hard to spoof). v2's model — the host resolves identity once and checks permissions against the central DB — is more robust and easier to audit. + +### 2. **Message send ACL at request time** +**Recommendation:** Partially — v2 should validate `agent_destinations` rows exist *before* the agent attempts a send, so it fails fast instead of silently dropping at delivery time. Currently, if an agent tries `...`, it writes to messages_out and the host later rejects it. A pre-send validation in the container (via destinations.ts) would be better UX. + +### 3. **Backpressure / delivery acknowledgment** +**Recommendation:** Maybe. If an agent rapidly fires 100 `send_message()` calls, they all block on SQLite INSERT (fast) and return immediately. The host drains them at 1s per poll. If the channel adapter is slow, messages pile up in messages_out. There's no way for the agent to ask "is there backlog?" or "wait until sent." This is probably fine for most use cases (agents don't spam), but if latency-sensitive, a `send_message()` that returns `{delivered_at}` would help. + +### 4. **Heartbeat / stale detection** +**Recommendation:** Yes, and it's been preserved (`.heartbeat` file replaces file-based timestamps). But the 10min threshold is conservative. Consider shorter thresholds for interactive agents (containers should be responsive, stale is a sign of crash, not slow work). + +--- + +## File references + +### v1 (historical, in `src/v1/` and `container/agent-runner/src/v1/`) +- **ipc.ts:30–127** — startIpcWatcher loop, per-group folder scan, message/task file dispatch +- **ipc.ts:129–356** — processTaskIpc with authorization gates (lines 169, 228, 241, 254, 271, 313, 326) +- **ipc-auth.test.ts:71–127** — schedule_task authorization tests +- **ipc-auth.test.ts:339–373** — message send authorization tests +- **ipc-mcp-stdio.ts:37–68** — send_message MCP tool, writeIpcFile +- **ipc-mcp-stdio.ts:70–216** — schedule_task tool with validation, target_group_jid param +- **ipc-mcp-stdio.ts:445–504** — register_group tool, isMain gate + +### v2 (active, in `src/` and `container/agent-runner/src/`) +- **db-session.md:1–50** — inbound.db schema (messages_in, delivered, destinations, session_routing) +- **db-session.md:120–174** — outbound.db schema (messages_out, processing_ack, session_state) +- **db-session.md:104–117** — seq parity invariant +- **delivery.ts:383–394** — drainSession loop (active poll 1s, sweep 60s) +- **delivery.ts:467–638** — deliverMessage, handles all message kinds, permission checks, delivery retry +- **delivery.ts:645–906** — handleSystemAction, interprets action="schedule_task" etc. +- **host-sweep.ts:48–109** — sweepSession, syncProcessingAcks, stale detection via heartbeat, recurrence handling +- **session-manager.ts:1–12** — cross-mount invariant doc (journal_mode=DELETE, close-per-op) +- **session-manager.ts:122–130** — initSessionFolder, schema creation +- **session-manager.ts:152–222** — writeSessionRouting, writeDestinations (replaces static env vars with live table) +- **session-manager.ts:231–267** — writeSessionMessage (host writes to messages_in) +- **poll-loop.ts:22–33** — PollLoopConfig with adminUserIds set +- **poll-loop.ts:46–77** — runPollLoop entry, getPendingMessages, markProcessing +- **destinations.ts:44–52** — getAllDestinations, findByName (reads from inbound.db live) +- **db/messages-in.ts** — getPendingMessages, markProcessing, markCompleted +- **db/messages-out.ts** — writeMessageOut (container writes system actions here) +- **db/session-state.ts** — getStoredSessionId, setStoredSessionId (continuation persistence) +- **db/connection.ts** — touchHeartbeat, journal_mode=DELETE pragma, cross-mount setup + +--- + +Generated from deep-dive analysis of v1 IPC → v2 DB paradigm shift. diff --git a/docs/v1-vs-v2/logger.md b/docs/v1-vs-v2/logger.md new file mode 100644 index 000000000..26ac54884 --- /dev/null +++ b/docs/v1-vs-v2/logger.md @@ -0,0 +1,38 @@ +# logger: v1 vs v2 + +## Scope +- v1: `src/v1/logger.ts` (70 LOC) — export `logger` +- v2 counterpart: `src/log.ts` (65 LOC) — export `log` + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| Levels (debug=20, info=30, warn=40, error=50, fatal=60) | `src/log.ts:1` | kept | Identical numeric map | +| `debug/info/warn/error/fatal` methods | `src/log.ts:50-54` | renamed | `logger.X(...)` → `log.X(...)` | +| Data-first signature `(data, msg)` | `src/log.ts:42-58` | **changed** | v2 requires message-first `(msg, data?)` — breaking for every callsite | +| Color codes (per-level + KEY_COLOR=magenta, MSG_COLOR=cyan) | `src/log.ts:4-14` | kept | Identical | +| LOG_LEVEL env threshold | `src/log.ts:16` | kept | `'info'` default | +| Timestamp `HH:MM:SS.mmm` | `src/log.ts:33-40` | kept | Refactored, same output | +| Error formatting | `src/log.ts:18-23` | **changed** | v1 pretty multi-line JSON; v2 single-line | +| Data formatting | `src/log.ts:25-31` | **changed** | v1 per-line indented; v2 inline `key=value` | +| Process ID in output | — | **removed** | v1 emitted `(${process.pid})`; v2 drops it | +| info/debug → stdout, warn/error/fatal → stderr | `src/log.ts:45` | kept | Identical routing | +| `uncaughtException` → fatal + exit(1) | `src/log.ts:57-60` | kept | Arg order swapped | +| `unhandledRejection` → error | `src/log.ts:62-64` | kept | Arg order swapped | + +## Missing from v2 +1. **Process ID in log output** — lost visibility into emitting process in multi-container scenarios +2. **Data-first overload** — v1 `logger.warn({err, path}, 'msg')` is a breaking API change in v2 +3. **Multi-line error formatting** — condensed single-line form is harder to read for stack traces + +## Behavioral discrepancies +1. **Argument order**: `logger.error({err}, 'failed')` must become `log.error('failed', {err})` at every callsite +2. **Error output**: v1 pretty-prints JSON over 3 lines; v2 collapses to one line +3. **Data output**: v1 newline+indent per key; v2 space-separated inline + +## Not in either +File rotation, redaction rules, on-disk logging — both stream to stdout/stderr only. + +## Worth preserving? +Restoring PID to v2 output is cheap and helps multi-process debugging. Multi-line error format is worth a verbose-mode flag for `error`/`fatal`. Signature swap is stylistic; not worth reverting but every v1 `logger` → `log` migration must swap `(data, msg)` → `(msg, data)`. diff --git a/docs/v1-vs-v2/remote-control.md b/docs/v1-vs-v2/remote-control.md new file mode 100644 index 000000000..7cba1336a --- /dev/null +++ b/docs/v1-vs-v2/remote-control.md @@ -0,0 +1,90 @@ +# remote-control: v1 vs v2 + +## Scope + +**v1:** +- `/Users/gavriel/nanoclaw4/src/v1/remote-control.ts` (218 lines) +- `/Users/gavriel/nanoclaw4/src/v1/remote-control.test.ts` (379 lines) +- Integrated into v1 host via `restoreRemoteControl()` call at startup (v1/index.ts:42) + +**v2 Counterparts:** +- `/Users/gavriel/nanoclaw4/src/access.ts` (115 lines) — privilege/approval routing +- `/Users/gavriel/nanoclaw4/src/onecli-approvals.ts` (269 lines) — OneCLI credential-gated action approval +- `/Users/gavriel/nanoclaw4/src/webhook-server.ts` (134 lines) — HTTP webhook ingress for Chat SDK adapters +- `/Users/gavriel/nanoclaw4/src/router.ts` (start of file) — inbound message routing with access gates + +## Capability Map + +| v1 Behavior | v2 Location | Status | Notes | +|---|---|---|---| +| Start `claude remote-control` child process, extract URL | **Removed** | ❌ Removed | v2 has no equivalent. The `claude remote-control` CLI was a v1-only mechanism tied to individual Telegram chats. | +| Session state persistence (PID, URL, metadata) | **Removed** | ❌ Removed | v2 is stateless at the host level — all per-session state lives in `inbound.db` / `outbound.db`. | +| Auto-accept "Enable Remote Control?" prompt via stdin | **Removed** | ❌ Removed | v1 quirk tied to Claude CLI's interactive mode; no equivalent in v2. | +| Restore session from disk on startup | **Removed** | ❌ Removed | v2 has no startup recovery loop for stale processes. Sessions are created on-demand. | +| Detect dead process by signal check | **Removed** | ❌ Removed | v2 uses per-session heartbeat file (`/workspace/.heartbeat`) and inactivity detection via 60s sweep. | +| HTTP URL polling + timeout handling | **Webhook server** | ✅ Moved | v2's `webhook-server.ts` (line 16–124) runs a persistent HTTP server (default port 3000) for Chat SDK adapter webhooks. Routes via `/webhook/{adapterName}` (not URL-in-stdout polling). | +| Single active session per host | **Per-agent-group sessions** | ✅ Evolved | v2 supports unlimited concurrent sessions. Each `(agent_group, messaging_group, thread)` tuple is a separate session with its own container. | +| `getActiveSession()` getter | **Removed** | ❌ Removed | No global session concept. v2 queries sessions via `getSession(sessionId)` in `db/sessions.ts`. | +| Credential access approval | **OneCLI approval handler** | ✅ Moved | v2's `onecli-approvals.ts` (line 92–215) handles credential-gated action approval. OneCLI gateway intercepts HTTP, delivers ask_question card to approver, persists `pending_approvals` row (line 173–196). | +| Approver selection (admin → owner chain) | **access.ts** | ✅ Moved | `pickApprover()` (access.ts:55–72) returns ordered list: agent-group admins → global admins → owners. Same preference order as v1 logic. | +| Approval delivery to DM (same channel kind preferred) | **access.ts + user-dm.ts** | ✅ Moved | `pickApprovalDelivery()` (access.ts:83–101) walks approver list, prefers same channel kind via `channelTypeOf()` (line 112–115), falls back to any reachable DM. Uses `ensureUserDm()` for cold-DM resolution (user-dm.ts). | +| Ask_question card delivery | **onecli-approvals.ts** | ✅ Moved | v2 builds ask_question card (onecli-approvals.ts:148–167) with Approve/Reject buttons, routes via `deliveryAdapter.deliver()` with action_id for button callbacks. | +| Button click → approval resolution | **onecli-approvals.ts** | ✅ Moved | `resolveOneCLIApproval()` (line 68–83) matches approval_id, resolves Promise, updates status to approved/rejected, deletes `pending_approvals` row. | +| Approval expiry + cleanup | **onecli-approvals.ts** | ✅ Moved | Expiry timer fires just before gateway's TTL (line 200–211); `expireApproval()` (line 217–226) edits card to "Expired (reason)" and deletes row. Startup sweep cleans stale rows (line 247–255). | +| Rate limiting | **Not implemented** | ❌ Missing | Neither v1 nor v2 has rate limiting on remote-control or approval requests. | +| Audit logging | **Partial** | ⚠️ Partial | v1: `logger.info()` on session start/stop. v2: `log.info()` on approval resolved (onecli-approvals.ts:81), stale sweeps (line 250), expiry (line 225). Payload stored in `pending_approvals.payload` for audit (line 178–186). | +| Error recovery (process death) | **Minimal** | ⚠️ Minimal | v1: restores from disk, kills stale PID. v2: no equivalent — dead container is detected by stale heartbeat, then respawned via `wakeContainer()`. | +| Transport | HTTP via stdout polling | HTTP via standard webhook server | v1 is ephemeral per session; v2 is persistent, multi-tenant. | +| Auth | None (CLI subprocess) | OneCLI gateway (credential-gated via HTTP) | v1 has no auth; v2 gates on agent identity + OneCLI decision. | + +## Missing from v2 + +1. **CLI subprocess spawning** — v2 has no `claude remote-control` equivalent. Agents run in Docker containers, not standalone CLI processes. The OneCLI agent sandbox is managed by the agent-runner container, not the host. + +2. **Process-level lifecycle management** — v1 tracks individual process PIDs and signal-kills them. v2 uses container IDs + heartbeat file, handled by host-sweep (host-sweep.ts) and container-runner.ts. + +3. **Per-message URL polling with regex extraction** — v2's webhook server is push-based (HTTP handler), not pull-based polling of stdout files. + +4. **Direct user-to-bot communication model** — v1's remote-control was tied to a single Telegram JID + chat. v2 decouples messaging groups from agent groups, allowing one agent to serve multiple channels with different isolation levels. + +5. **State file on disk** (`remote-control.json`) — v2 stores all session state in SQLite central DB and per-session `inbound.db` / `outbound.db`. + +## Behavioral Discrepancies + +1. **Approval delivery model**: + - v1: Remote control was tied to a single message sender; approvals implicitly went to the initiator's contact or a hardcoded owner. + - v2: Approvals route to admins of the originating agent group, with tie-break by channel kind (pickApprovalDelivery line 87–94). Multiple approvers can be reached, decoupling approval from message sender. + +2. **Session multiplicity**: + - v1: One active `RemoteControlSession` per host at a time. + - v2: Unlimited concurrent sessions, each with independent state (`inbound.db`, `outbound.db`, heartbeat). + +3. **Timeout & cleanup**: + - v1: Explicit timeout on URL polling (30s), then kill process. No ongoing monitoring. + - v2: Heartbeat-based inactivity detection (60s sweep), graceful cleanup on stale. Approval expiry tied to OneCLI gateway TTL, not a fixed timeout. + +4. **Error transparency**: + - v1: Polling errors logged to stdout/stderr files; user doesn't see unless they debug. + - v2: All approval errors logged centrally; card is edited to "Expired" on failure, so approver sees state change. + +## Worth Preserving? + +**No — v2 supersedes v1's remote-control model.** + +v1's remote-control was a bridge between Telegram chats and a single Claude CLI session. v2 achieves equivalent (and superior) remote operation via: +- **OneCLI credential approvals** (onecli-approvals.ts): Admins approve API/credential requests from agents, just as v1 surfaced sensitive actions. +- **Approval routing** (access.ts): Automatically picks the right admin on the right channel, with fallback to any reachable DM. +- **Multi-tenant agent groups**: Agents can serve multiple channels with different approval chains, not just one chat JID. + +Users still get on-demand approval for sensitive actions; they just don't manage a CLI subprocess anymore. The host handles container lifecycle, and the container agent is managed by OneCLI. + +--- + +### Citation Summary + +- v1 remote-control: `/Users/gavriel/nanoclaw4/src/v1/remote-control.ts:1–218` +- v1 tests: `/Users/gavriel/nanoclaw4/src/v1/remote-control.test.ts:1–379` +- v2 access control: `/Users/gavriel/nanoclaw4/src/access.ts:29–115` (pickApprover, pickApprovalDelivery, canAccessAgentGroup) +- v2 approval handler: `/Users/gavriel/nanoclaw4/src/onecli-approvals.ts:50–270` (handleRequest, resolveOneCLIApproval, sweepStaleApprovals) +- v2 webhook server: `/Users/gavriel/nanoclaw4/src/webhook-server.ts:73–124` (registerWebhookAdapter, ensureServer) +- v2 router: `/Users/gavriel/nanoclaw4/src/router.ts:19–50` (inbound access gate, unknown_sender_policy) diff --git a/docs/v1-vs-v2/router.md b/docs/v1-vs-v2/router.md new file mode 100644 index 000000000..361edb19c --- /dev/null +++ b/docs/v1-vs-v2/router.md @@ -0,0 +1,67 @@ +# router: v1 vs v2 + +## Scope +- v1 (distributed across): `src/v1/index.ts` (startMessageLoop, trigger check), `group-queue.ts` (concurrency, retry), `router.ts` (outbound formatting, 44 LOC), `sender-allowlist.ts` (drop/allow) +- v2: `src/router.ts` (317 LOC), `src/session-manager.ts` (346 LOC), `src/container-runner.ts`, `src/access.ts`, `src/db/messaging-groups.ts` (trigger_rules schema) + +## Routing-flow diff + +### v1 (polling, per-group) +1. Channel receives message → `onMessage` → store in DB +2. Sender allowlist drop-mode filter → discard denied +3. `startMessageLoop` polls every POLL_INTERVAL +4. For each group: lookup channel (`findChannel` O(n)), check trigger requirement, load allowlist, scan for pattern, skip if no trigger +5. Pull messages since `lastAgentTimestamp`, XML-format with tz context +6. If active container: write JSON to IPC file; else `enqueueMessageCheck(groupJid)` → GroupQueue +7. Retry on failure (up to 5, exp. backoff); rollback cursor on agent error + +### v2 (event-driven, entity model) +1. Channel adapter → `routeInbound(platformId, threadId, message)` +2. Apply thread policy (`supportsThreads` → collapse to null) +3. Resolve `messaging_group` (lookup or auto-create) +4. Extract sender → upsert `users` row → `userId` (namespaced `channel_type:handle`) +5. Lookup wired agent groups via `messaging_group_agents`; drop if none +6. `pickAgent` (highest priority; **trigger_rules matching is TODO**) +7. `enforceAccess`: owner/admin/member gate; `unknown_sender_policy: strict | request_approval | public` +8. `resolveSession` by `session_mode` (`agent-shared`/`shared`/`per-thread`) +9. `insertMessage` to session `inbound.db`, write session_routing + destinations +10. `startTypingRefresh`; `wakeContainer(session)` (dedup by `activeContainers` + `wakePromises`) +11. Container polls inbound.db, writes outbound.db; host `delivery.ts` polls and sends via adapter; `stopTypingRefresh` on container exit + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| Sender allowlist drop/allow modes | — | **removed** | Replaced by access gate + `unknown_sender_policy` | +| Group registration auto-creating folder on first message | `router.ts` auto-creates messaging_group; group folder via `group-init.ts` on wake | moved | Admin skill path for agent groups | +| Trigger pattern matching (`requiresTrigger`, `DEFAULT_TRIGGER`) | `messaging_group_agents.trigger_rules` JSON | **deferred** | Schema ready; `pickAgent` has TODO comment | +| `lastAgentTimestamp` cursor tracking | — | **removed** | All messages written immediately to inbound.db | +| IPC file polling (`inputDir`, `_close` sentinel) | — | **removed** | DB polling replaces | +| GroupQueue concurrency + waiting-groups | `container-runner.ts:42-82` `activeContainers` + `wakePromises` | reimplemented | Per-session not per-group | +| Task scheduler → enqueue to GroupQueue | host-sweep due-wake + delivery system-actions | preserved | | +| Session reuse rules (session mode) | `session-manager.ts` (agent-shared/shared/per-thread) | **enhanced** | Explicit per-wiring | +| Remote control command interception | — | **removed** | | +| Idle timeout + stdin close | `container-runner.ts:135-140` `resetIdle` | kept | Heartbeat instead of stdin | +| Host-level retry on agent error | — | **removed** | Container is authority; host sweep retries stale only | +| Typing indicator | `delivery.ts:startTypingRefresh` | kept | Gated on heartbeat | + +## Missing from v2 +1. **Trigger-rule matching** — `router.ts:198` TODO. Currently every wired agent fires on every message (only priority breaks ties). **Without this, multi-agent wirings don't work as intended.** +2. **Sender drop mode** — v1's silent-drop for noisy users is gone. v2 only has binary allow/deny. +3. **Cursor / state recovery** — v2 writes immediately to DB. If container crashes mid-output, no host-level dedup guarantees (beyond `messages_in.id` PK) +4. **Remote control** — v1 intercepted `/remote-control` commands pre-storage; no v2 equivalent +5. **Host-level retry with backoff on agent error** — v1 had MAX_RETRIES=5 + exp. backoff on `processGroupMessages`; v2 only retries on stale heartbeat detection + +## Behavioral discrepancies +1. **Trigger evaluation**: v1 eager (skip group until trigger arrives, accumulate context); v2 TODO — once implemented, likely drops non-trigger messages at ingest (semantic change) +2. **Session reuse**: v1 single session per group; v2 multiple (one per thread on threaded platforms) +3. **Access control timing**: v1 pre-storage (cheap drop); v2 post-sender-resolution (requires `users` upsert) +4. **Unknown channels**: v1 silently ignored; v2 auto-creates `messaging_groups` row — no data loss but orphaned rows possible +5. **Formatting**: v1 host formats with tz + cursor-based message subset; v2 pushes raw JSON to inbound.db, container formats from full session history + +## Worth preserving? +1. **Trigger rule matching (HIGH priority)** — schema is ready; 10-line implementation in `pickAgent`. Currently broken-by-default for multi-agent wirings +2. **Sender drop mode (MEDIUM)** — add `(agent_group_id, sender_pattern)` drop table; orthogonal to privilege +3. **State recovery (LOW)** — add unique constraint on `messages_in.id` if not already; v2's model is simpler + more robust +4. **Host-level retry on agent error (MEDIUM)** — currently only stale containers retry. Explicit container-exit-error retry could be valuable +5. **Remote control** — decide: restore as opt-in skill or document deletion diff --git a/docs/v1-vs-v2/sender-allowlist.md b/docs/v1-vs-v2/sender-allowlist.md new file mode 100644 index 000000000..7f7c518fa --- /dev/null +++ b/docs/v1-vs-v2/sender-allowlist.md @@ -0,0 +1,46 @@ +# sender-allowlist: v1 vs v2 + +## Scope +- v1: `src/v1/sender-allowlist.ts` (97 LOC), `sender-allowlist.test.ts` (217 LOC) — flat JSON config at `~/.config/nanoclaw/sender-allowlist.json` +- v2 counterparts: `src/access.ts` (116 LOC), `src/router.ts` (317 LOC), `src/db/schema.ts` (user_roles, agent_group_members, messaging_groups.unknown_sender_policy), `src/container-runner.ts:291-295` (admin injection), `src/types.ts` (MessagingGroupAgent.response_scope) + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| Per-chat entry (`chats[chatJid]`) | `messaging_groups.unknown_sender_policy` | replaced | Policy per channel, not allowlist entries | +| Default entry | Default `unknown_sender_policy = 'strict'` | **reversed** | v1 default-allow → v2 default-deny | +| `allow: '*'` wildcard | Not present | removed | | +| `allow: string[]` (exact-match list) | `agent_group_members` rows + `user_roles` | replaced | Role-based / membership-based | +| `mode: 'trigger'` (allow for processing) | Implicit (access granted → routed) | kept | | +| `mode: 'drop'` (silent drop) | `recordDroppedMessage()` (logs only) | **partially lost** | No silent-drop mode; denied = logged | +| Admin override | owner / global_admin / scoped_admin | **new in v2** | Richer privilege hierarchy | +| Static JSON file | Central DB (`users`, `user_roles`, `agent_group_members`) | changed | Runtime-mutable, queryable | +| Exact-string sender | Namespaced `channel_type:handle` user IDs | enhanced | Explicit channel scoping | +| `logDenied` flag | implicit (log at decision point) | kept | | + +## Access-model diff +**v1**: flat allowlist per chat → default-allow → binary allowed/denied. +**v2**: entity model (`users` + roles + memberships) + per-messaging-group policy (`strict | request_approval | public`) → default-deny for unknowns. + +**Strictly more expressive:** role hierarchy, per-agent-group scope, three-way unknown handling, user metadata (display_name/kind), runtime reconfig. +**Lost:** per-message `drop` mode, default-allow posture, simple JSON editing. + +## Missing from v2 +1. **`request_approval` flow** — marked TODO in `router.ts:295`. Approval-on-first-contact for unknown senders is scaffolded but not wired +2. **`response_scope` enforcement** — field exists (`'all' | 'triggered' | 'allowlisted'`) but is not checked in `router.ts` or `delivery.ts` +3. **Trigger-rule matching on `messaging_group_agents`** — `router.ts:198` TODO ("Future: trigger rule matching"); currently only priority-based agent selection +4. **Silent-drop option for known-noisy senders** — v1's `mode: 'drop'` allowed "I see you but I ignore you"; v2 can only log and drop + +## Behavioral discrepancies +1. **Default posture flipped**: v1 open-by-default vs v2 closed-by-default — **breaking for migrations that relied on default-allow** +2. **Drop semantics**: v1 silent drop; v2 `recordDroppedMessage()` always logs +3. **Admin bypass**: v1 had no implicit bypass; v2 grants owners/admins access regardless of membership — more permissive for privileged users +4. **Scope resolution**: v1 per-chat; v2 per-agent-group via `user_roles.agent_group_id` — misalignment if one chat routes to multiple agent groups with different admins + +## Worth preserving? +The v2 role-based model is architecturally superior. The gaps worth closing: +- **Finish `request_approval`** flow — half-implemented scaffolding +- **Finish `response_scope` enforcement** — exists in schema but unused +- **Finish trigger-rule matching** in `pickAgent` — without it, every wired agent fires on every message +- **Consider silent-drop via a dedicated table** (`(agent_group_id, sender_pattern)` with action=drop) — orthogonal to privilege diff --git a/docs/v1-vs-v2/session-cleanup.md b/docs/v1-vs-v2/session-cleanup.md new file mode 100644 index 000000000..87aa3d421 --- /dev/null +++ b/docs/v1-vs-v2/session-cleanup.md @@ -0,0 +1,44 @@ +# session-cleanup: v1 vs v2 + +## Scope +- v1: `src/v1/session-cleanup.ts` (26 LOC) + `scripts/cleanup-sessions.sh` (151 LOC) — cadence 24h +- v2: `src/host-sweep.ts` (174 LOC) primary, plus `src/container-runtime.ts:60-80` (orphan cleanup), `src/session-manager.ts` (heartbeat path) + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| Cleanup cadence 24h | `host-sweep.ts:31` 60s sweep | **changed** | Continuous monitoring | +| Stale session detection via JSONL mtime | `host-sweep.ts:116-151` heartbeat file mtime | simplified | Heartbeat replaces JSONL | +| Heartbeat threshold | `STALE_THRESHOLD_MS = 10 * 60 * 1000` (`host-sweep.ts:32`) | **new** | 10 min | +| Stuck-processing detection | `getStuckProcessingIds()` via outbound.db (`host-sweep.ts:134`) | **new** | | +| Retry with exponential backoff | `BACKOFF_BASE_MS * 2^tries` (`host-sweep.ts:145`) | **new** | | +| Max retries | `MAX_TRIES = 5` (`host-sweep.ts:33`) | **new** | Messages → failed after 5 | +| Explicit container kill on stale | — | **not done** | Stale detection resets messages, doesn't stop container | +| JSONL + tool-results cleanup | — | **removed** | No artifact cleanup (SQLite persists in DB) | +| Artifact cleanup (debug logs, todos, telemetry) | — | **removed** | Per-type retention windows gone | +| Orphan container cleanup | `container-runtime.ts:60-80` `cleanupOrphans()` | **new** | At startup only | +| Active session detection via `store/messages.db` | `getActiveSessions()` from `v2.db` (`host-sweep.ts:52`) | changed | DB schema different | +| Sync `processing_ack` (outbound.db → inbound.db) | `syncProcessingAcks()` (`host-sweep.ts:87`) | **new** | | +| Wake container for due messages | `countDueMessages()` + `wakeContainer()` (`host-sweep.ts:91-96`) | **new** | Replaces scheduler's role | +| Recurrence firing | `handleRecurrence()` (`host-sweep.ts:154-173`) | **new** | Cron-parsed next-run insertion | + +## Missing from v2 +1. **Artifact cleanup** — v1 pruned JSONLs (7d), debug logs (3d), todos (3d), telemetry (7d), group logs (7d). v2 has none; if v1 leftovers exist on disk, they'll accumulate +2. **Explicit container termination** on stale detection — v2 marks messages as retry-eligible but leaves the stale container running; orphan cleanup only runs at next startup +3. **Configurable retention windows** — v1 had per-artifact-type retention; v2 constants are hardcoded + +## Behavioral discrepancies +| Aspect | v1 | v2 | +|---|---|---| +| Cadence | daily batch | 60s continuous | +| Stale trigger | 24h-old JSONL | 10-min heartbeat | +| Retry | none (session removed) | 5 tries, exp. backoff | +| Container wake | via message loop | via `countDueMessages()` in sweep | +| Transactions | implicit (offline script) | explicit per-session try/finally | + +## Worth preserving? +1. **Stop running containers on stale detection** — currently only startup `cleanupOrphans()` removes them. If a container truly dies while the host runs, the host will retry messages but won't kill the shell. Low-cost fix: `stopContainer(name)` when heartbeat is stale AND processing_ack is stuck +2. **Artifact cleanup migration** — if v1 data exists on disk post-migration, one-time prune is worth scripting. Not a v2 runtime concern +3. **Configurable thresholds** — `STALE_THRESHOLD_MS` / `MAX_TRIES` could live in `config.ts` for operational tuning; minor improvement +4. **Continuous sweep + recurrence + orphan cleanup** are all **significant improvements**; keep as-is diff --git a/docs/v1-vs-v2/task-scheduler.md b/docs/v1-vs-v2/task-scheduler.md new file mode 100644 index 000000000..29a0606c0 --- /dev/null +++ b/docs/v1-vs-v2/task-scheduler.md @@ -0,0 +1,100 @@ +# task-scheduler: v1 vs v2 + +## Scope + +**v1 task scheduler:** +- Files: `src/v1/task-scheduler.ts` (241 lines), `src/v1/task-scheduler.test.ts` (122 lines) +- Self-contained scheduler loop with DB persistence and container execution +- Stores tasks in central DB table `scheduled_tasks` +- Runs a polling loop at `SCHEDULER_POLL_INTERVAL` (configurable, typically 5–60s) + +**v2 task distribution:** +- No central task-scheduler file; tasks spread across host sweep and session DBs +- Core files: `src/host-sweep.ts` (174 lines), `src/delivery.ts` (task handlers ~line 654–713), `src/db/session-db.ts` (task mutation logic) +- Optional: `container/agent-runner/src/task-script.ts` (pre-task script execution) +- Task rows live in per-session `inbound.db` table `messages_in` (polymorphic message kind) +- Recurrence computed in `host-sweep.ts` (host-sweep.ts:159–173) + +--- + +## Capability map + +| v1 Behavior | v2 Location | Status | Notes | +|---|---|---|---| +| **One-shot tasks** (schedule_type='once') | `insertTask()` in `src/db/session-db.ts:103–122`; processAfter field set, recurrence=NULL | ✅ Supported | Task inserted into messages_in with process_after timestamp, processed once, no recurrence | +| **Recurring via cron** (schedule_type='cron') | `insertTask()` with recurrence field; `host-sweep.ts:159–173` parses cron | ✅ Supported | Cron expression stored in messages_in.recurrence, next occurrence computed on completion via CronExpressionParser | +| **Recurring via fixed interval** (schedule_type='interval') | Not directly supported; v2 uses cron for all recurring | ⚠️ Removed | v2 requires cron syntax for recurrence. No interval-based scheduling (e.g., "every 5 minutes") without converting to cron | +| **Timezone handling** | `host-sweep.ts:159–161` uses CronExpressionParser with no explicit TZ param; cron-parser respects system TZ | ⚠️ Degraded | v1's explicit TIMEZONE config (via timezone.ts helpers) is absent in v2. Cron evaluation uses system/Node.js default TZ, not agent/session-level configuration | +| **Persistence** | Per-session `inbound.db` `messages_in` table + `series_id` grouping | ✅ Supported | Tasks persisted as DB rows with status (pending/completed/paused). Series_id backfilled for recurring task groups | +| **Restart recovery** | `host-sweep.ts:85–96` syncs processing_ack on startup to detect stale containers; tasks marked paused if container crashes | ✅ Supported | Stale container detection via heartbeat file mtime (host-sweep.ts:122–131); stuck messages retried with exponential backoff | +| **Due-message wake** | `host-sweep.ts:91–96` queries countDueMessages, wakes container if due tasks exist | ✅ Supported | 60s sweep checks for pending tasks with process_after in the past and wakes container if found | +| **Missed-run catch-up** (interval-based) | `computeNextRun()` skips past missed intervals to prevent cumulative drift; tests verify no infinite loop | ⚠️ Degraded | v2 doesn't handle missed intervals — if a recurring cron task gets skipped, next occurrence is computed from completion time only. No "make up" for missed runs | +| **Cancellation** | `updateTask(id, {status: 'paused'})` prevents retry churn | ✅ Supported | `cancelTask()` in `src/db/session-db.ts:128–132` sets status='completed' and clears recurrence; matches by id OR series_id | +| **Pause/resume** | `updateTask(id, {status: 'paused'})` / resume | ✅ Supported | `pauseTask()` (line 134–138) and `resumeTask()` (line 140–144); both match id or series_id | +| **Retry-on-failure** | `updateTaskAfterRun()` on error; no explicit retry logic in scheduler loop | ⚠️ Degraded | v2 uses `retryWithBackoff()` only when container goes stale (host-sweep.ts:147). No automatic retry for task execution errors | +| **Concurrent-run prevention** | Task status 'active' gate (task-scheduler.ts:221); no concurrent-run logic | ⚠️ Degraded | v2 allows multiple pending tasks to wake the container in the same sweep; container processes serially but no host-level concurrency control | +| **Idempotency** | Task ID is primary key; `insertTask()` will fail if re-run with same ID | ✅ Supported | messages_in.id is PRIMARY KEY; insertTask() fails on duplicate (caller must handle or use ON CONFLICT) | +| **Max-age drop** | No explicit max-age field; tasks can remain pending indefinitely | ⚠️ Missing | No max-age or TTL in v2 messages_in schema. A stuck task can remain pending forever unless manually cancelled | +| **Task context mode** (group vs isolated session) | v1: context_mode field drives session reuse (task-scheduler.ts:122) | ⚠️ Removed | v2 doesn't track context_mode; all tasks are processed in the container's default session context; no isolation toggle | +| **Task result logging** | `logTaskRun()` writes to task_runs table; stores error + result summary | ⚠️ Degraded | v2 has no equivalent task_runs table. Task output is written as system messages back to the agent; no persistent audit trail | +| **Task script execution** | v1: prompt + optional script field, passed to container | ✅ Supported | v2: `applyPreTaskScripts()` in `container/agent-runner/src/task-script.ts:79–121` runs scripts pre-prompt, enriches prompt with scriptOutput | + +--- + +## Missing from v2 + +1. **Interval-based recurrence** — v1 `schedule_type='interval'` (e.g., "every 5000ms") is gone. v2 only supports cron expressions. Workaround: convert to equivalent cron (e.g., `*/5 * * * * *` for every 5 min). + +2. **Timezone awareness** — v1 passed `TIMEZONE` config to cron parser and had explicit `formatLocalTime()` helpers. v2 has no way to specify a session/agent timezone for cron evaluation; it uses the system/Node.js TZ. + +3. **Task context modes** — v1's `context_mode: 'group' | 'isolated'` is removed. No way to force a task into a dedicated session vs. the agent group's shared session. + +4. **Task result audit trail** — v1 logged every run to `task_runs(task_id, run_at, duration_ms, status, result, error)`. v2 has no persistent task execution history; output is a system message only. + +5. **Max-age / task TTL** — v1 tasks could be implicitly aged out (not directly visible in the code, but conceivable via cleanup logic). v2 has no TTL; a paused/completed task lingers in messages_in forever. + +6. **Task-level concurrency control** — v1 prevented concurrent runs of the same task (single status check per loop iteration). v2 can queue multiple pending tasks in one sweep, though the container processes them serially. + +--- + +## Behavioral discrepancies + +1. **Missed-interval catch-up** (v1 `computeNextRun()` lines 32–46 vs. v2 absence): + - **v1:** If a task is due at 10:00, 10:05, 10:10 but the scheduler is down during 10:00–10:15, it computes `next_run = 10:20` (skips missed intervals, stays on the grid). + - **v2:** If the same recurring cron task is skipped, the next occurrence is computed from the *completion* time (host-sweep.ts:160–161), not from the original grid. A task that should run at :00 and :05 every 10 minutes might drift if completions are delayed. + +2. **Stale-container recovery** (v1 none vs. v2 heartbeat-based): + - **v1:** Tasks remain due if the container crashes; the scheduler will retry on the next poll. + - **v2:** If the heartbeat goes stale (container unresponsive for 10 min), stuck processing messages are retried with exponential backoff. Tasks stuck in 'processing' state are reset. + +3. **Task script pre-processing** (v1 prompt + script → container vs. v2 script → output enrichment): + - **v1:** Passes script alongside prompt to container; container execution model unclear from scheduler.ts (likely runs in group-queue). + - **v2:** Host runs script *before* waking container; script output (`scriptOutput`) is merged into prompt JSON via `applyPreTaskScripts()` (task-script.ts:115–117). If script fails or returns `wakeAgent=false`, the task is skipped entirely. + +4. **Retry semantics**: + - **v1:** On execution error (runTask throws), `updateTaskAfterRun()` is called with `error`. Next retry relies on scheduler polling the same task again (no backoff). + - **v2:** Execution errors are not retried; container processes the task once. If the container crashes mid-task, the message is retried with exponential backoff only up to `MAX_TRIES=5` (host-sweep.ts:145–150). + +--- + +## Worth preserving? + +**Interval-based recurrence** (v1 `schedule_type='interval'`) is a practical feature that v2 trades away. Cron syntax is powerful but less intuitive for simple "every X milliseconds" patterns. If users want "run every 30 seconds," they must learn cron (`*/30 * * * * *` for seconds doesn't exist in standard cron; workaround is job-level looping in the prompt). Consider a thin adapter layer in agent-facing APIs to accept `{interval: 5000}` and convert to cron, or extend the v2 schema to support an optional `interval_ms` alongside `recurrence`. + +**Task context modes** (`group` vs. `isolated`) were a way to isolate task execution context. v2's removal simplifies the model but loses the ability to run a task in a fresh container state. If a task needs a clean slate (no session history), that's now impossible; workaround is a manual system-action to clear session state before running the task. + +**Task result audit trail** is a gap for operational visibility. v2's system messages are ephemeral; there's no way to query "how many times did task X run and what were the outcomes?" Adding a lightweight `task_execution_log` table (optional, populated on task completion) would help without burdening the common case. + +--- + +## References by line + +- v1 task-scheduler: `src/v1/task-scheduler.ts:20–49` (computeNextRun), `:203–235` (startSchedulerLoop) +- v1 test coverage: `src/v1/task-scheduler.test.ts:49–121` (drift, missed-interval, once-task tests) +- v1 timezone: `src/v1/timezone.ts:26–37` (formatLocalTime with explicit TZ) +- v1 types: `src/v1/types.ts:60–74` (ScheduledTask interface with context_mode) +- v2 sweep: `src/host-sweep.ts:154–173` (handleRecurrence, insertRecurrence) +- v2 delivery system actions: `src/delivery.ts:645–713` (handleSystemAction switch on schedule_task/cancel_task/pause_task/resume_task/update_task) +- v2 session-db: `src/db/session-db.ts:103–198` (insertTask, cancelTask, pauseTask, resumeTask, updateTask, all with series_id matching) +- v2 task-script: `container/agent-runner/src/task-script.ts:79–121` (applyPreTaskScripts, wakeAgent logic) +- v2 DB schema: `docs/db-session.md:31–56` (messages_in table with process_after, recurrence, series_id) diff --git a/docs/v1-vs-v2/timezone-formatting-v1-recreation.md b/docs/v1-vs-v2/timezone-formatting-v1-recreation.md new file mode 100644 index 000000000..eabf012f5 --- /dev/null +++ b/docs/v1-vs-v2/timezone-formatting-v1-recreation.md @@ -0,0 +1,570 @@ +# v1 Timezone + Formatting — Recreation Spec + +## Source commits + +**Parent of deletion**: `86becf8^ = 27c52205f9fdeac0483600b2663f1c4d80aba45d` + +**Deletion commit**: `86becf8` (chore: delete v1 reference code) + +### Relevant v1 files at commit 27c5220 (v1^): +- `src/v1/router.ts` — message formatting logic (escapeXml, formatMessages, stripInternalTags, formatOutbound) +- `src/v1/timezone.ts` — timezone utility functions (isValidTimezone, resolveTimezone, formatLocalTime) +- `src/v1/config.ts` — configuration and trigger patterns (buildTriggerPattern, getTriggerPattern, TIMEZONE resolution) +- `src/v1/task-scheduler.ts` — scheduled task timezone handling (computeNextRun with cron-parser) +- `src/v1/types.ts` — data structures (NewMessage interface) +- `src/v1/formatting.test.ts` — comprehensive test suite for all formatting behavior +- `src/v1/timezone.test.ts` — timezone utility tests +- `src/v1/task-scheduler.test.ts` — scheduler tests + +--- + +## 1. Timestamp formatting on inbound messages + +### v1 behavior (exact) + +**Function**: `formatLocalTime()` in `src/v1/timezone.ts:26-36` + +```typescript +export function formatLocalTime(utcIso: string, timezone: string): string { + const date = new Date(utcIso); + return date.toLocaleString('en-US', { + timeZone: resolveTimezone(timezone), + year: 'numeric', + month: 'short', + day: 'numeric', + hour: 'numeric', + minute: '2-digit', + hour12: true, + }); +} +``` + +**Input**: UTC ISO 8601 timestamp (e.g., `'2024-01-01T00:00:00.000Z'`) + timezone name (e.g., `'America/New_York'`) + +**Output format example**: +- Input: `'2024-01-01T18:30:00.000Z'` with timezone `'America/New_York'` (EST, UTC-5) +- Output: `'1:30 PM'` (with additional date components: month short name, day, year, hour, 2-digit minute, 12-hour format) +- Full example output: `"Jan 1, 2024, 1:30 PM"` (exact format depends on browser/Node locale) + +**Critical Details**: +- Uses JavaScript's `Intl.DateTimeFormat` API with `en-US` locale +- Format options: `{ year: 'numeric', month: 'short', day: 'numeric', hour: 'numeric', minute: '2-digit', hour12: true }` +- Handles invalid timezone gracefully by calling `resolveTimezone(timezone)` which falls back to UTC +- No external dependencies (no moment.js, date-fns, or day.js) + +**Where it's called**: +- `src/v1/router.ts:11` in `formatMessages()` function to convert each message's `m.timestamp` to display time +- The display time is then placed in the `time="..."` attribute of the XML message element + +### Test coverage + +From `src/v1/formatting.test.ts:51-84`: + +1. **Basic formatting with context header** + - Input: Single message with timestamp `'2024-01-01T00:00:00.000Z'`, timezone `'UTC'` + - Asserts: `result.toContain('Jan 1, 2024')` and `''` + - File:line: `src/v1/formatting.test.ts:51-56` + +2. **Timezone conversion to local time** + - Input: Timestamp `'2024-01-01T18:30:00.000Z'` with timezone `'America/New_York'` (EST) + - Asserts: Result contains `'1:30'` and `'PM'` (correct EST conversion, UTC-5) + - File:line: `src/v1/formatting.test.ts:74-78` + +From `src/v1/timezone.test.ts:10-30`: + +3. **formatLocalTime with timezone conversion** + - Input: `'2026-02-04T18:30:00.000Z'` with `'America/New_York'` + - Asserts: Contains `'1:30'`, `'PM'`, `'Feb'`, `'2026'` + - File:line: `src/v1/timezone.test.ts:10-16` + +4. **Multiple timezones comparison** + - Input: Same UTC time with different timezones (`'America/New_York'`, `'Asia/Tokyo'`) + - Asserts: NY shows `'8:00'` (EDT, UTC-4 in summer), Tokyo shows `'9:00'` (UTC+9) + - File:line: `src/v1/timezone.test.ts:18-26` + +5. **Invalid timezone fallback** + - Input: Invalid timezone `'IST-2'` + - Asserts: Does not throw, formats as UTC (falls back) + - File:line: `src/v1/timezone.test.ts:28-33` + +--- + +## 2. Context timezone header + +### v1 behavior (exact) + +**Location**: Prepended at the START of the formatted message block in `src/v1/router.ts:20-22` + +**Format**: +```xml + +``` + +**Code**: +```typescript +const header = `\n`; +return `${header}\n${lines.join('\n')}\n`; +``` + +**What it includes**: +- Only the timezone name (IANA identifier, e.g., `'UTC'`, `'America/New_York'`) +- **NOT** the current time (that's in each individual message's `time="..."` attribute) +- XML-escaped to prevent injection (via `escapeXml()`) + +**Per-message vs per-turn**: +- The header appears **once per call to `formatMessages()`**, which formats a batch of messages +- The entire batch (header + all messages) is passed to the agent as a single unit +- The `timezone` parameter is passed in from the caller (`src/v1/router.ts:9` line signature) + +**Where it's wired**: +- `src/v1/router.ts:9` — `formatMessages(messages: NewMessage[], timezone: string)` accepts timezone as a parameter +- This function is called from the channel message processing loop (inbound message handler) +- The caller supplies the `TIMEZONE` constant from `src/v1/config.ts:62` + +### Test coverage + +From `src/v1/formatting.test.ts:51-56`: + +1. **Context header is included in output** + - Input: Any message list with timezone `'UTC'` + - Asserts: `result.toContain('')` + - File:line: `src/v1/formatting.test.ts:51-56` + +2. **Context header with non-UTC timezone** + - Input: Timezone `'America/New_York'` + - Asserts: `result.toContain('')` + - File:line: `src/v1/formatting.test.ts:74-78` + +3. **Context header with empty message list** + - Input: Empty array with timezone `'UTC'` + - Asserts: `result.toContain('')` even when no messages + - File:line: `src/v1/formatting.test.ts:80-83` + +--- + +## 3. Reply-to handling with message IDs + +### v1 behavior (exact) + +**Location**: In the message formatting loop in `src/v1/router.ts:10-18` + +**Code**: +```typescript +const replyAttr = m.reply_to_message_id ? ` reply_to="${escapeXml(m.reply_to_message_id)}"` : ''; +const replySnippet = + m.reply_to_message_content && m.reply_to_sender_name + ? `\n ${escapeXml(m.reply_to_message_content)}` + : ''; +return `${replySnippet}${escapeXml(m.content)}`; +``` + +**Format of reply-to**: +- Attribute: `reply_to=""` on the `` tag (if `m.reply_to_message_id` is present) +- The ID is XML-escaped via `escapeXml()` +- Nested element: `` (if both sender and content are present) +- Both sender name and content are XML-escaped + +**What it contains**: +- `reply_to=""` attribute with the exact message ID from `m.reply_to_message_id` +- Sender name from `m.reply_to_sender_name` +- Original message content from `m.reply_to_message_content` +- **No timestamp** of the referenced message + +**Conditional rendering**: +1. If `m.reply_to_message_id` is present: include `reply_to=""` attribute +2. If `m.reply_to_message_id` is present but content/sender missing: include attribute only, no `` element +3. If only content and sender (no ID): only `` element, no attribute + +**Example output**: +```xml + + Are you coming tonight? +Yes, on my way! +``` + +### Test coverage + +From `src/v1/formatting.test.ts:96-139`: + +1. **Reply with both ID and quoted content** + - Input: Message with `reply_to_message_id: '42'`, `reply_to_sender_name: 'Bob'`, `reply_to_message_content: 'Are you coming tonight?'`, content: `'Yes, on my way!'` + - Asserts: + - `result.toContain('reply_to="42"')` + - `result.toContain('Are you coming tonight?')` + - `result.toContain('Yes, on my way!')` + - File:line: `src/v1/formatting.test.ts:96-112` + +2. **No reply context when missing** + - Input: Message without reply fields + - Asserts: + - `result.not.toContain('reply_to')` + - `result.not.toContain('quoted_message')` + - File:line: `src/v1/formatting.test.ts:114-119` + +3. **ID present but content missing** + - Input: `reply_to_message_id: '42'`, `reply_to_sender_name: 'Bob'`, but NO `reply_to_message_content` + - Asserts: + - `result.toContain('reply_to="42"')` + - `result.not.toContain('quoted_message')` + - File:line: `src/v1/formatting.test.ts:121-130` + +4. **XML escape in reply context** + - Input: `reply_to_message_id: '1'`, `reply_to_sender_name: 'A & B'`, `reply_to_message_content: ''` + - Asserts: + - `result.toContain('from="A & B"')` + - `result.toContain('<script>alert("xss")</script>')` + - File:line: `src/v1/formatting.test.ts:131-139` + +--- + +## 4. Internal tag stripping + +### v1 behavior (exact) + +**Function name**: `stripInternalTags()` in `src/v1/router.ts:25-27` + +**Implementation**: +```typescript +export function stripInternalTags(text: string): string { + return text.replace(/[\s\S]*?<\/internal>/g, '').trim(); +} +``` + +**Regex pattern**: `/[\s\S]*?<\/internal>/g` +- `` — literal opening tag +- `[\s\S]*?` — match any character (whitespace or non-whitespace) non-greedily +- `<\/internal>` — literal closing tag +- `g` flag — global (all matches) + +**Post-processing**: `.trim()` removes leading/trailing whitespace after all tags are stripped + +**Where it's called**: +- `src/v1/router.ts:30` in `formatOutbound()` function +- Called AFTER the tag removal to clean the output before returning + +**Used for**: Stripping internal thinking/reasoning from outbound messages before sending to channel + +**Input/Output examples**: + +1. Single-line internal tag: + - Input: `'hello secret world'` + - Output: `'hello world'` (then `.trim()` would be `'hello world'`) + +2. Multi-line internal tags: + - Input: `'hello \nsecret\nstuff\n world'` + - Output: `'hello world'` + +3. Multiple blocks: + - Input: `'ahellob'` + - Output: `'hello'` + +4. Only internal content: + - Input: `'only this'` + - Output: `''` (empty after trim) + +### Test coverage + +From `src/v1/formatting.test.ts:163-181`: + +1. **Single-line tag stripping** + - Input: `'hello secret world'` + - Asserts: Result is `'hello world'` (two spaces, then `.trim()` removes outer whitespace) + - Expected (with trim): `'hello world'` + - File:line: `src/v1/formatting.test.ts:163-165` + +2. **Multi-line tag stripping** + - Input: `'hello \nsecret\nstuff\n world'` + - Asserts: Result is `'hello world'` (after trim) + - File:line: `src/v1/formatting.test.ts:167-169` + +3. **Multiple internal blocks** + - Input: `'ahellob'` + - Asserts: Result is `'hello'` + - File:line: `src/v1/formatting.test.ts:171-173` + +4. **Only internal content** + - Input: `'only this'` + - Asserts: Result is `''` (empty string) + - File:line: `src/v1/formatting.test.ts:175-177` + +From `src/v1/formatting.test.ts:183-194`: + +5. **formatOutbound with no internal tags** + - Input: `'hello world'` + - Asserts: Result is `'hello world'` + - File:line: `src/v1/formatting.test.ts:183-185` + +6. **formatOutbound with all internal content** + - Input: `'hidden'` + - Asserts: Result is `''` (returns early after strip) + - File:line: `src/v1/formatting.test.ts:187-189` + +7. **formatOutbound strips and returns remaining** + - Input: `'thinkingThe answer is 42'` + - Asserts: Result is `'The answer is 42'` + - File:line: `src/v1/formatting.test.ts:191-194` + +--- + +## 5. Timezone handling for scheduled tasks + +### v1 behavior (exact) + +**Location**: `src/v1/task-scheduler.ts:20-49` + +**Key function**: `computeNextRun(task: ScheduledTask): string | null` + +**Cron timezone handling**: +```typescript +if (task.schedule_type === 'cron') { + const interval = CronExpressionParser.parse(task.schedule_value, { + tz: TIMEZONE, + }); + return interval.next().toISOString(); +} +``` + +**Critical details**: +- Uses `cron-parser` library's `CronExpressionParser.parse()` method +- Passes timezone option as `{ tz: TIMEZONE }` (e.g., `{ tz: 'America/New_York' }`) +- `TIMEZONE` is imported from `src/v1/config.ts:62` and resolved via `resolveConfigTimezone()` +- The cron expression is interpreted in the **user's timezone**, not UTC +- Example: cron `'0 9 * * *'` with `tz: 'America/New_York'` means 9 AM ET every day + +**Interval task handling**: +```typescript +if (task.schedule_type === 'interval') { + const ms = parseInt(task.schedule_value, 10); + if (!ms || ms <= 0) { + logger.warn({ taskId: task.id, value: task.schedule_value }, 'Invalid interval value'); + return new Date(now + 60_000).toISOString(); + } + let next = new Date(task.next_run!).getTime() + ms; + while (next <= now) { + next += ms; + } + return new Date(next).toISOString(); +} +``` + +**Interval specifics**: +- Intervals are timezone-agnostic (pure millisecond-based) +- Anchored to the task's `next_run` time to prevent cumulative drift +- If intervals have been missed, the loop skips forward to land in the future while maintaining the original schedule grid + +**Once-only tasks**: +```typescript +if (task.schedule_type === 'once') return null; +``` + +**MCP tool description**: +- v1 did not expose cron task scheduling directly to the agent (it was a server-side feature) +- The scheduling was configured in group config files, not via agent tool calls + +### Test coverage + +From `src/v1/task-scheduler.test.ts:33-60`: + +1. **computeNextRun returns null for once-tasks** + - Input: Task with `schedule_type: 'once'` + - Asserts: `computeNextRun(task)` returns `null` + - File:line: `src/v1/task-scheduler.test.ts:40-49` + +2. **Interval task anchoring to prevent drift** + - Input: Task scheduled 2s ago with interval `60000` (1 minute) + - Asserts: Next run = `scheduledTime + 60s`, not `now + 60s` + - Expected: Exact alignment to the scheduled time grid + - File:line: `src/v1/task-scheduler.test.ts:33-39` + +3. **Interval task catches up without infinite loop** + - Input: Task with 10 missed intervals (missed by 10 * 60000ms) + - Asserts: Next run is in the future and aligned to original schedule grid + - File:line: `src/v1/task-scheduler.test.ts:51-60` + +--- + +## 6. Complete test inventory (formatting.test.ts) + +### All test cases from src/v1/formatting.test.ts (lines 1-254): + +#### Block 1: escapeXml tests (lines 22-46) + +| Test name | Input | Expected output | +|-----------|-------|-----------------| +| escapes ampersands | `'a & b'` | `'a & b'` | +| escapes less-than | `'a < b'` | `'a < b'` | +| escapes greater-than | `'a > b'` | `'a > b'` | +| escapes double quotes | `'"hello"'` | `'"hello"'` | +| handles multiple special characters together | `'a & b < c > d "e"'` | `'a & b < c > d "e"'` | +| passes through strings with no special chars | `'hello world'` | `'hello world'` | +| handles empty string | `''` | `''` | + +#### Block 2: formatMessages tests (lines 48-159) + +| Test name | Input | Key asserts | +|-----------|-------|------------| +| formats a single message as XML with context header (line 51) | Single message with timestamp `'2024-01-01T00:00:00.000Z'`, TZ `'UTC'` | Contains `''`, `'hello'`, `'Jan 1, 2024'` | +| formats multiple messages (line 59) | 2 messages: Alice at 00:00, Bob at 01:00 | Contains both sender names and contents | +| escapes special characters in sender names (line 72) | Sender `'A & B '` | Contains `'sender="A & B <Co>"'` | +| escapes special characters in content (line 79) | Content `''` | Contains escaped script tags `'<script>...'` | +| handles empty array (line 85) | Empty message list, TZ `'UTC'` | Contains header and `'\n\n'` | +| renders reply context as quoted_message element (line 96) | Message with `reply_to_message_id: '42'`, `reply_to_sender_name: 'Bob'`, `reply_to_message_content: 'Are you coming tonight?'` | Contains `'reply_to="42"'`, `'Are you coming tonight?'` | +| omits reply attributes when no reply context (line 114) | Message without reply fields | Does NOT contain `'reply_to'` or `'quoted_message'` | +| omits quoted_message when content is missing but id is present (line 121) | Message with `reply_to_message_id: '42'` but no `reply_to_message_content` | Contains `'reply_to="42"'` but NOT `'alert("xss")'` | Contains `'from="A & B"'` and escaped script | +| converts timestamps to local time for given timezone (line 140) | Timestamp `'2024-01-01T18:30:00.000Z'` with TZ `'America/New_York'` (EST, UTC-5) | Contains `'1:30'`, `'PM'`, header has `'America/New_York'` | + +#### Block 3: TRIGGER_PATTERN tests (lines 146-169) + +| Test name | Input | Expected result | +|-----------|-------|-----------------| +| matches @name at start of message (line 152) | `'@Andy hello'` (assuming ASSISTANT_NAME='Andy') | `true` | +| matches case-insensitively (line 156) | `'@andy hello'` or `'@ANDY hello'` | `true` | +| does not match when not at start of message (line 160) | `'hello @Andy'` | `false` | +| does not match partial name like @NameExtra (word boundary) (line 164) | `'@Andyextra hello'` | `false` | +| matches with word boundary before apostrophe (line 168) | `'@Andy\'s thing'` | `true` | +| matches @name alone (end of string is a word boundary) (line 172) | `'@Andy'` | `true` | +| matches with leading whitespace after trim (line 175) | `' @Andy hey'` (after `.trim()`) | `true` | + +#### Block 4: getTriggerPattern tests (lines 177-196) + +| Test name | Input | Expected behavior | +|-----------|-------|-------------------| +| uses the configured per-group trigger when provided (line 180) | `getTriggerPattern('@Claw')` | Matches `'@Claw hello'`, does NOT match `'@Andy hello'` | +| falls back to the default trigger when group trigger is missing (line 186) | `getTriggerPattern(undefined)` | Matches default trigger `'@Andy hello'` | +| treats regex characters in custom triggers literally (line 192) | `getTriggerPattern('@C.L.A.U.D.E')` | Matches literal dots, NOT wildcard (does NOT match `'@CXLXAUXDXE'`) | + +#### Block 5: stripInternalTags tests (lines 198-210) + +| Test name | Input | Expected output | +|-----------|-------|-----------------| +| strips single-line internal tags (line 199) | `'hello secret world'` | `'hello world'` (then `.trim()` makes it `'hello world'`) | +| strips multi-line internal tags (line 203) | `'hello \nsecret\nstuff\n world'` | `'hello world'` | +| strips multiple internal tag blocks (line 207) | `'ahellob'` | `'hello'` | +| returns empty string when text is only internal tags (line 211) | `'only this'` | `''` | + +#### Block 6: formatOutbound tests (lines 213-226) + +| Test name | Input | Expected output | +|-----------|-------|-----------------| +| returns text with internal tags stripped (line 214) | `'hello world'` | `'hello world'` | +| returns empty string when all text is internal (line 218) | `'hidden'` | `''` | +| strips internal tags from remaining text (line 222) | `'thinkingThe answer is 42'` | `'The answer is 42'` | + +#### Block 7: trigger gating (requiresTrigger interaction) tests (lines 228-254) + +| Test name | Input | Expected result | +|-----------|-------|-----------------| +| main group always processes (no trigger needed) (line 239) | `isMainGroup: true`, message without trigger | `true` | +| main group processes even with requiresTrigger=true (line 244) | `isMainGroup: true`, `requiresTrigger: true`, no trigger | `true` | +| non-main group with requiresTrigger=undefined requires trigger (line 249) | `isMainGroup: false`, `requiresTrigger: undefined`, no trigger | `false` | +| non-main group with requiresTrigger=true requires trigger (line 254) | `isMainGroup: false`, `requiresTrigger: true`, no trigger | `false` | +| non-main group with requiresTrigger=true processes when trigger present (line 259) | `isMainGroup: false`, trigger in message | `true` | +| non-main group uses per-group trigger instead of default (line 264) | `isMainGroup: false`, `trigger: '@Claw'`, message `'@Claw do something'` | `true` | +| non-main group does not process when only default trigger is present for custom-trigger group (line 269) | `isMainGroup: false`, `trigger: '@Claw'`, message `'@Andy do something'` | `false` | +| non-main group with requiresTrigger=false always processes (line 274) | `isMainGroup: false`, `requiresTrigger: false`, no trigger | `true` | + +--- + +## v2 porting plan + +### For each of sections 1–5: the specific change to make in v2 + +#### 1. Timestamp formatting + +**v2 file to modify**: (Unknown — search for where v2 formats inbound messages to the agent) + +**Change needed**: +1. Find where v2 currently formats message timestamps for the agent +2. Replace any custom date formatting with the v1 pattern: + - Call `new Date(timestamp).toLocaleString('en-US', { timeZone, year: 'numeric', month: 'short', day: 'numeric', hour: 'numeric', minute: '2-digit', hour12: true })` +3. Ensure the timezone parameter is sourced from `config.TIMEZONE` (or equivalent in v2) + +**Test to port**: `src/v1/formatting.test.ts:51-56` (basic formatting) and `src/v1/formatting.test.ts:74-78` (timezone conversion) + +#### 2. Context timezone header + +**v2 file to modify**: (Unknown — search for where v2 constructs the XML/prompt for inbound messages) + +**Change needed**: +1. Prepend `\n` to the formatted message block +2. The timezone should be the resolved IANA identifier (e.g., `'UTC'`, `'America/New_York'`) +3. Ensure it's placed BEFORE the `` element + +**Test to port**: `src/v1/formatting.test.ts:51-56` and `src/v1/formatting.test.ts:80-83` (empty array still has header) + +#### 3. Reply-to with message ID + +**v2 file to modify**: (Unknown — search for where v2 formats message metadata) + +**Change needed**: +1. If `message.reply_to_message_id` is present, add ` reply_to=""` attribute to the `` element +2. If BOTH `message.reply_to_message_content` AND `message.reply_to_sender_name` are present, include a nested `` element +3. XML-escape all three values (ID, sender name, content) + +**Test to port**: +- `src/v1/formatting.test.ts:96-112` (full reply context) +- `src/v1/formatting.test.ts:121-130` (ID only, no content) +- `src/v1/formatting.test.ts:131-139` (XML escaping in reply) + +#### 4. Internal tag stripping + +**v2 file to modify**: (Unknown — search for where v2 processes outbound messages before sending) + +**Change needed**: +1. Apply the regex `/[\s\S]*?<\/internal>/g` to strip all internal thinking/reasoning blocks +2. Call `.trim()` on the result after stripping +3. Return empty string if result is empty after stripping + +**Test to port**: +- `src/v1/formatting.test.ts:163-177` (stripInternalTags) +- `src/v1/formatting.test.ts:183-194` (formatOutbound) + +#### 5. Scheduled task timezone handling + +**v2 file to modify**: (Unknown — search for where v2 handles cron task scheduling) + +**Change needed**: +1. When parsing cron expressions, pass the timezone option to cron-parser: + ```typescript + const interval = CronExpressionParser.parse(cronExpression, { tz: TIMEZONE }); + ``` +2. For interval-based tasks, anchor to the original `next_run` time, not `Date.now()`, to prevent drift +3. Ensure the TIMEZONE constant is resolved at startup via a function like: + ```typescript + function resolveConfigTimezone(): string { + const candidates = [process.env.TZ, envConfig.TZ, Intl.DateTimeFormat().resolvedOptions().timeZone]; + for (const tz of candidates) { + if (tz && isValidTimezone(tz)) return tz; + } + return 'UTC'; + } + ``` + +**Test to port**: +- `src/v1/task-scheduler.test.ts:33-39` (interval anchoring) +- `src/v1/task-scheduler.test.ts:40-49` (once-task returns null) +- `src/v1/task-scheduler.test.ts:51-60` (interval catch-up) + +--- + +## Git references for verification + +All code snippets above can be verified with: + +```bash +git show 27c5220:src/v1/router.ts +git show 27c5220:src/v1/timezone.ts +git show 27c5220:src/v1/config.ts +git show 27c5220:src/v1/task-scheduler.ts +git show 27c5220:src/v1/types.ts +git show 27c5220:src/v1/formatting.test.ts +git show 27c5220:src/v1/timezone.test.ts +git show 27c5220:src/v1/task-scheduler.test.ts +``` + +Or from the deletion parent commit: + +```bash +git show 86becf8^:src/v1/ +``` diff --git a/docs/v1-vs-v2/timezone.md b/docs/v1-vs-v2/timezone.md new file mode 100644 index 000000000..f036fa3ee --- /dev/null +++ b/docs/v1-vs-v2/timezone.md @@ -0,0 +1,27 @@ +# timezone: v1 vs v2 + +## Scope +- v1: `src/v1/timezone.ts` (37 LOC), `src/v1/timezone.test.ts` (64 LOC) +- v2 counterparts: `src/timezone.ts` (37 LOC), `src/timezone.test.ts` (64 LOC) + +## Capability map + +| v1 behavior | v2 location | Status | Notes | +|---|---|---|---| +| `isValidTimezone(tz)` | `src/timezone.ts:5-12` | kept | Byte-identical | +| `resolveTimezone(tz)` | `src/timezone.ts:17-19` | kept | Byte-identical | +| `formatLocalTime(utcIso, timezone)` | `src/timezone.ts:26-37` | kept | Byte-identical | + +## Tests (byte-identical) +- `formatLocalTime`: UTC→local display with offset; DST awareness (EDT vs EST); fall back to UTC on invalid tz without throwing +- `isValidTimezone`: accepts `America/New_York`, `UTC`, `Asia/Tokyo`, `Asia/Jerusalem`; rejects `IST-2`, `XYZ+3`, empty/garbage +- `resolveTimezone`: returns tz if valid; falls back to UTC on invalid or empty + +## Missing from v2 +None — v1 and v2 files are byte-for-byte identical. + +## Behavioral discrepancies +None. + +## Worth preserving? +No action needed — v2 already mirrors v1 exactly. Minimal, correct, no external deps. No cron-time conversions in either version (that logic lived in `task-scheduler.ts`). diff --git a/docs/v1-vs-v2/types.md b/docs/v1-vs-v2/types.md new file mode 100644 index 000000000..fbf4b3f51 --- /dev/null +++ b/docs/v1-vs-v2/types.md @@ -0,0 +1,58 @@ +# types: v1 vs v2 + +## Scope +- v1: `src/v1/types.ts` (112 LOC) — 10 exported types/interfaces covering AdditionalMount, MountAllowlist, AllowedRoot, ContainerConfig, RegisteredGroup, NewMessage, ScheduledTask, TaskRunLog, Channel, OnInboundMessage/OnChatMetadata +- v2 counterparts (distributed): + - `src/types.ts` — central DB entities (`AgentGroup`, `MessagingGroup`, `MessageIn`, `User`, `MessagingGroupAgent` etc.) + - `src/container-config.ts` — file-based per-group container config + - `src/mount-security.ts` — mount types + - `src/channels/adapter.ts` — v2 channel interface + - `container/agent-runner/src/db/messages-in.ts`, `destinations.ts` — session-level types + - `src/db/schema.ts` — schema reference + +## Capability map + +| v1 type / field | v2 location | Status | Notes | +|---|---|---|---| +| `AdditionalMount` | `src/mount-security.ts:16-18` | kept | Same fields | +| `MountAllowlist` / `AllowedRoot` | `src/mount-security.ts:21-29` | kept | `nonMainReadOnly` field removed (see container-runtime doc) | +| `ContainerConfig` | split: `src/container-config.ts:36` (file-based) + `src/mount-security.ts` | refactored | `timeout` dropped; added `mcpServers`, `packages`, `imageTag` | +| `RegisteredGroup` | `agent_groups` + `messaging_group_agents` + `container.json` | refactored | One entity split across two DB tables + filesystem | +| `RegisteredGroup.trigger` | `messaging_group_agents.trigger_rules` JSON | moved | Per-wiring, not per-group | +| `RegisteredGroup.containerConfig` | `groups//container.json` | moved | DB → disk | +| `RegisteredGroup.isMain` | convention (`agent_group_id = 'main'`) | removed | No explicit flag | +| `NewMessage` | split: `MessageIn` (`src/types.ts:98-111`) + `InboundMessage` (`src/channels/adapter.ts:33-38`) + `MessageInRow` (`container/.../db/messages-in.ts`) | refactored | Platform fields separated | +| `NewMessage.chat_jid` | `channel_type` + `platform_id` | refactored | Explicit split, no more JID parsing | +| `NewMessage.sender` / `sender_name` | inside JSON `content` blob | moved | Less type safety, more flexibility | +| `NewMessage.is_from_me` / `is_bot_message` | — | removed | Inferred from identity or `messages_out` | +| `NewMessage.reply_to_*` | inside `content` blob | moved | | +| `ScheduledTask` (entire type) | `MessageIn` with `kind='task'` + `recurrence` | removed | No separate task entity; no task UI/API | +| `TaskRunLog` | — | removed | No audit trail in v2 | +| `Channel` (connect/disconnect/sendMessage/ownsJid/syncGroups/setTyping) | `ChannelAdapter` (`src/channels/adapter.ts:60-105`) | refactored | Stateless request/response, async, no callback loop | +| `Channel.ownsJid` | — | removed | Routing keyed on `channel_type + platform_id` | +| `OnInboundMessage(chatJid, message)` | `onInbound(platformId, threadId, message)` | refactored | Routing fields explicit | +| `OnChatMetadata` | `onMetadata(platformId, name?, isGroup?)` | refactored | Drops timestamp/channel params | + +## Schema diff (v1 `RegisteredGroup` → v2 split) +- **Identity** (`name`, `folder`, `created_at`) → `agent_groups` table +- **Wiring** (`trigger`, `requiresTrigger`) → `messaging_group_agents` table (`trigger_rules`, `response_scope`, `session_mode`) +- **Container config** (`containerConfig`) → `groups//container.json` +- Normalization gain: an agent group can have N wirings with different triggers + +## Missing from v2 +1. `ScheduledTask` + `TaskRunLog` — no first-class task entity or execution log +2. `ContainerConfig.timeout` — per-group timeout override gone; single hardcoded `IDLE_TIMEOUT` +3. `NewMessage.is_from_me` / `is_bot_message` — flat flags gone +4. `Channel.ownsJid` — JID ownership concept gone +5. `Channel.connect()`/`disconnect()`/`isConnected()` lifecycle — replaced by stateless `setup`/`teardown` + +## Behavioral discrepancies +- **JID → channel_type + platform_id**: routing fields are now structured, not bundled strings +- **Pull vs push channels**: v1 channels pushed events via callbacks; v2 adapters are stateless with DB-mediated flow +- **Container config storage**: v1 in DB, v2 on disk (survives container restarts without DB query) + +## Worth preserving? +- **ScheduledTask / TaskRunLog**: v2's removal leaves a visibility gap; if scheduled-task introspection matters, reintroduce a log table keyed on `messages_in.id` to capture run metadata +- **Per-group timeout**: meaningful loss — some agent groups are slow, others fast; hardcoded timeout = false positives +- **is_from_me / is_bot_message**: trivial to reconstruct; not worth restoring +- **Channel lifecycle callbacks**: obsolete; v2 model is cleaner diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index 30ba0e862..2d45b299b 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -71,6 +71,12 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter let chat: Chat; let state: SqliteStateAdapter; let setupConfig: ChannelSetup; + // NOTE: populated at setup() and updateConversations(), but currently not + // read by any inbound handler. When adapter-level gating lands (engage_mode + // applied here) or when dynamic group registration is added, this map goes + // stale after setup unless updateConversations() is actively called on every + // messaging_groups / messaging_group_agents mutation. See ACTION-ITEMS.md + // item 17. let conversations: Map; let gatewayAbort: AbortController | null = null; From 0283391e0a59e1288dc3795f09fb7fd7da389d5b Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 01:01:47 +0300 Subject: [PATCH 17/95] chore(config): remove dead POLL_INTERVAL / SCHEDULER_POLL_INTERVAL / IPC_POLL_INTERVAL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These three constants were carried over from v1's polling + IPC architecture and have zero callers in the v2 runtime: - POLL_INTERVAL (2000ms) — v1 message loop; replaced by event-driven delivery + delivery.ts's ACTIVE_POLL_MS (hardcoded 1000ms) - SCHEDULER_POLL_INTERVAL (60000ms) — v1 task scheduler; replaced by host-sweep.ts's SWEEP_INTERVAL_MS (hardcoded 60_000) - IPC_POLL_INTERVAL (1000ms) — v1 file-based IPC; meaningless in v2's session-DB architecture Grep confirms no imports in src/, container/, or tests. Docs/SPEC.md updated to match. Ref: docs/v1-vs-v2/ACTION-ITEMS.md item 15. Co-Authored-By: Claude Opus 4.7 (1M context) --- docs/SPEC.md | 3 --- src/config.ts | 3 --- 2 files changed, 6 deletions(-) diff --git a/docs/SPEC.md b/docs/SPEC.md index 687336f66..42ef37c8e 100644 --- a/docs/SPEC.md +++ b/docs/SPEC.md @@ -332,8 +332,6 @@ Configuration constants are in `src/config.ts`: import path from 'path'; export const ASSISTANT_NAME = process.env.ASSISTANT_NAME || 'Andy'; -export const POLL_INTERVAL = 2000; -export const SCHEDULER_POLL_INTERVAL = 60000; // Paths are absolute (required for container mounts) const PROJECT_ROOT = process.cwd(); @@ -344,7 +342,6 @@ export const DATA_DIR = path.resolve(PROJECT_ROOT, 'data'); // Container configuration export const CONTAINER_IMAGE = process.env.CONTAINER_IMAGE || 'nanoclaw-agent:latest'; export const CONTAINER_TIMEOUT = parseInt(process.env.CONTAINER_TIMEOUT || '1800000', 10); // 30min default -export const IPC_POLL_INTERVAL = 1000; export const IDLE_TIMEOUT = parseInt(process.env.IDLE_TIMEOUT || '1800000', 10); // 30min — keep container alive after last result export const MAX_CONCURRENT_CONTAINERS = Math.max(1, parseInt(process.env.MAX_CONCURRENT_CONTAINERS || '5', 10) || 5); diff --git a/src/config.ts b/src/config.ts index ef1ba9e39..043a4a2ef 100644 --- a/src/config.ts +++ b/src/config.ts @@ -10,8 +10,6 @@ const envConfig = readEnvFile(['ASSISTANT_NAME', 'ASSISTANT_HAS_OWN_NUMBER', 'ON export const ASSISTANT_NAME = process.env.ASSISTANT_NAME || envConfig.ASSISTANT_NAME || 'Andy'; export const ASSISTANT_HAS_OWN_NUMBER = (process.env.ASSISTANT_HAS_OWN_NUMBER || envConfig.ASSISTANT_HAS_OWN_NUMBER) === 'true'; -export const POLL_INTERVAL = 2000; -export const SCHEDULER_POLL_INTERVAL = 60000; // Absolute paths needed for container mounts const PROJECT_ROOT = process.cwd(); @@ -29,7 +27,6 @@ export const CONTAINER_TIMEOUT = parseInt(process.env.CONTAINER_TIMEOUT || '1800 export const CONTAINER_MAX_OUTPUT_SIZE = parseInt(process.env.CONTAINER_MAX_OUTPUT_SIZE || '10485760', 10); // 10MB default export const ONECLI_URL = process.env.ONECLI_URL || envConfig.ONECLI_URL; export const MAX_MESSAGES_PER_PROMPT = Math.max(1, parseInt(process.env.MAX_MESSAGES_PER_PROMPT || '10', 10) || 10); -export const IPC_POLL_INTERVAL = 1000; export const IDLE_TIMEOUT = parseInt(process.env.IDLE_TIMEOUT || '1800000', 10); // 30min default — how long to keep container alive after last result export const MAX_CONCURRENT_CONTAINERS = Math.max(1, parseInt(process.env.MAX_CONCURRENT_CONTAINERS || '5', 10) || 5); From dcfa12ea06d76d278422f5381b4e1a92861c5291 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 01:09:14 +0300 Subject: [PATCH 18/95] feat(timezone): recreate v1 TZ-aware formatting + scheduling behavior MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The agent needs to perceive times in the user's timezone, not UTC. Dropping this in the v1→v2 port produced a class of bugs where the agent would schedule tasks for the wrong hour, suggest dinner at midnight, etc. This restores v1 parity. Container side: - New container/agent-runner/src/timezone.ts mirrors src/timezone.ts with isValidTimezone / resolveTimezone / formatLocalTime, plus: * TIMEZONE constant resolved at load from process.env.TZ (host sets this from src/container-runner.ts:254) * parseZonedToUtc(input, tz) — treats a naive ISO as wall-clock time in `tz`, returns the corresponding UTC Date. Strings with Z or offset are passed through. - formatter.ts: * formatMessages() now prepends \n — matches v1 src/v1/router.ts:20-22 * formatSingleChat uses formatLocalTime(ts, TIMEZONE) instead of a home-rolled HH:MM 24h formatter → outputs like "Jun 15, 2026, 8:00 AM" * reply_to="" attribute + Y element — matches v1 format exactly; old shape is gone * stripInternalTags() exported for the dispatch path to reuse - poll-loop.ts uses the exported stripInternalTags() instead of inline regex. - mcp-tools/scheduling.ts: * schedule_task/update_task descriptions now explicitly document that processAfter accepts either UTC or naive local time (interpreted in the user's TZ from the context header) * handlers normalize through parseZonedToUtc() and store a UTC ISO Host side: - src/modules/scheduling/recurrence.ts passes { tz: TIMEZONE } to CronExpressionParser.parse. Without this, "0 9 * * *" fires at 09:00 UTC instead of 09:00 user-local — this was the v1 behavior (src/v1/task-scheduler.ts:20-49). Tests: - container/agent-runner/src/timezone.test.ts — mirror of src/timezone.test.ts + new parseZonedToUtc cases - container/agent-runner/src/formatter.test.ts — context header, reply_to, quoted_message, XML escaping, stripInternalTags (ported from v1 formatting.test.ts) - src/modules/scheduling/recurrence.test.ts — cron TZ respected, completed rows only cloned when recurrence is set Ref: docs/v1-vs-v2/ACTION-ITEMS.md item 18 + timezone-formatting-v1-recreation.md Co-Authored-By: Claude Opus 4.7 (1M context) --- container/agent-runner/src/formatter.test.ts | 167 ++++++++++++++++++ container/agent-runner/src/formatter.ts | 54 ++++-- .../agent-runner/src/mcp-tools/scheduling.ts | 44 ++++- container/agent-runner/src/poll-loop.ts | 7 +- container/agent-runner/src/timezone.test.ts | 93 ++++++++++ container/agent-runner/src/timezone.ts | 107 +++++++++++ src/modules/scheduling/recurrence.test.ts | 100 +++++++++++ src/modules/scheduling/recurrence.ts | 7 +- 8 files changed, 549 insertions(+), 30 deletions(-) create mode 100644 container/agent-runner/src/formatter.test.ts create mode 100644 container/agent-runner/src/timezone.test.ts create mode 100644 container/agent-runner/src/timezone.ts create mode 100644 src/modules/scheduling/recurrence.test.ts diff --git a/container/agent-runner/src/formatter.test.ts b/container/agent-runner/src/formatter.test.ts new file mode 100644 index 000000000..e34156cd1 --- /dev/null +++ b/container/agent-runner/src/formatter.test.ts @@ -0,0 +1,167 @@ +/** + * v1-parity tests for formatter behavior. + * + * Port of src/v1/formatting.test.ts (at commit 27c5220, parent of the v1 + * deletion commit 86becf8). Covers: context timezone header, reply_to + + * quoted_message rendering, XML escaping, and stripInternalTags. + * + * Timestamp-format assertions use `formatLocalTime()` output format, which + * is host locale-dependent for decorators (month abbr, "," separator) but + * stable for the numeric parts we assert on (hour, minute, year). + */ +import { describe, it, expect, beforeEach, afterEach } from 'bun:test'; + +import { initTestSessionDb, closeSessionDb, getInboundDb } from './db/connection.js'; +import { getPendingMessages } from './db/messages-in.js'; +import { formatMessages, stripInternalTags } from './formatter.js'; +import { TIMEZONE } from './timezone.js'; + +beforeEach(() => { + initTestSessionDb(); +}); + +afterEach(() => { + closeSessionDb(); +}); + +function insertMessage( + id: string, + kind: string, + content: object, + opts?: { timestamp?: string }, +) { + const timestamp = opts?.timestamp ?? new Date().toISOString(); + getInboundDb() + .prepare( + `INSERT INTO messages_in (id, kind, timestamp, status, content) + VALUES (?, ?, ?, 'pending', ?)`, + ) + .run(id, kind, timestamp, JSON.stringify(content)); +} + +describe('context timezone header', () => { + it('prepends to formatted output', () => { + insertMessage('m1', 'chat', { sender: 'Alice', text: 'hello' }); + const result = formatMessages(getPendingMessages()); + expect(result).toContain(` { + const result = formatMessages([]); + expect(result).toContain(` block', () => { + insertMessage('m1', 'chat', { sender: 'Alice', text: 'one' }); + insertMessage('m2', 'chat', { sender: 'Bob', text: 'two' }); + const result = formatMessages(getPendingMessages()); + const ctxIdx = result.indexOf(''); + expect(ctxIdx).toBeGreaterThanOrEqual(0); + expect(msgsIdx).toBeGreaterThan(ctxIdx); + }); +}); + +describe('timestamp formatting', () => { + it('renders time via formatLocalTime (user TZ)', () => { + // 2026-06-15T12:00:00Z — timezone-agnostic assertions (year is stable) + insertMessage('m1', 'chat', { sender: 'Alice', text: 'hi' }, { timestamp: '2026-06-15T12:00:00.000Z' }); + const result = formatMessages(getPendingMessages()); + // formatLocalTime's format in en-US contains the year and a month abbrev + expect(result).toContain('2026'); + expect(result).toMatch(/Jun/); + }); + + it('uses 12-hour AM/PM format', () => { + // 15:30 UTC — some hour will show with AM or PM depending on TZ + insertMessage('m1', 'chat', { sender: 'Alice', text: 'hi' }, { timestamp: '2026-06-15T15:30:00.000Z' }); + const result = formatMessages(getPendingMessages()); + expect(result).toMatch(/(AM|PM)/); + }); +}); + +describe('reply_to + quoted_message rendering', () => { + it('renders reply_to attribute and quoted_message when all fields present', () => { + insertMessage('m1', 'chat', { + sender: 'Alice', + text: 'Yes, on my way!', + replyTo: { id: '42', sender: 'Bob', text: 'Are you coming tonight?' }, + }); + const result = formatMessages(getPendingMessages()); + expect(result).toContain('reply_to="42"'); + expect(result).toContain('Are you coming tonight?'); + expect(result).toContain('Yes, on my way!'); + }); + + it('omits reply_to and quoted_message when no reply context', () => { + insertMessage('m1', 'chat', { sender: 'Alice', text: 'plain' }); + const result = formatMessages(getPendingMessages()); + expect(result).not.toContain('reply_to'); + expect(result).not.toContain('quoted_message'); + }); + + it('renders reply_to but omits quoted_message when original content is missing', () => { + insertMessage('m1', 'chat', { + sender: 'Alice', + text: 'ack', + replyTo: { id: '42', sender: 'Bob' }, // no text + }); + const result = formatMessages(getPendingMessages()); + expect(result).toContain('reply_to="42"'); + expect(result).not.toContain('quoted_message'); + }); + + it('XML-escapes reply context', () => { + insertMessage('m1', 'chat', { + sender: 'Alice', + text: 'reply', + replyTo: { id: '1', sender: 'A & B', text: '' }, + }); + const result = formatMessages(getPendingMessages()); + expect(result).toContain('from="A & B"'); + expect(result).toContain('<script>'); + expect(result).toContain('"xss"'); + }); +}); + +describe('XML escaping', () => { + it('escapes <, >, &, " in sender and body', () => { + insertMessage('m1', 'chat', { + sender: 'A & B ', + text: '', + }); + const result = formatMessages(getPendingMessages()); + expect(result).toContain('sender="A & B <Co>"'); + expect(result).toContain('<script>alert("xss")</script>'); + }); +}); + +describe('stripInternalTags', () => { + it('strips single-line internal tags and trims', () => { + expect(stripInternalTags('hello secret world')).toBe('hello world'); + }); + + it('strips multi-line internal tags', () => { + expect(stripInternalTags('hello \nsecret\nstuff\n world')).toBe( + 'hello world', + ); + }); + + it('strips multiple internal tag blocks', () => { + expect(stripInternalTags('ahellob')).toBe('hello'); + }); + + it('returns empty string when input is only internal tags', () => { + expect(stripInternalTags('only this')).toBe(''); + }); + + it('returns input unchanged when there are no internal tags', () => { + expect(stripInternalTags('hello world')).toBe('hello world'); + }); + + it('preserves content that surrounds internal tags', () => { + expect(stripInternalTags('thinkingThe answer is 42')).toBe( + 'The answer is 42', + ); + }); +}); diff --git a/container/agent-runner/src/formatter.ts b/container/agent-runner/src/formatter.ts index fbf1ed9d0..b03f5bde8 100644 --- a/container/agent-runner/src/formatter.ts +++ b/container/agent-runner/src/formatter.ts @@ -1,5 +1,6 @@ import { findByRouting } from './destinations.js'; import type { MessageInRow } from './db/messages-in.js'; +import { TIMEZONE, formatLocalTime } from './timezone.js'; /** * Command categories for messages starting with '/'. @@ -92,10 +93,19 @@ export function extractRouting(messages: MessageInRow[]): RoutingContext { /** * Format a batch of messages_in rows into a prompt string. + * + * Prepends a `` header so the agent always knows + * what timezone it's in — every timestamp it sees in message bodies is the + * user's local time, and every time it produces (schedules, suggests) should + * be interpreted as local time in that same zone. This header is v1 behavior + * (src/v1/router.ts:20-22); dropping it led to misinterpretations where the + * agent scheduled tasks for the wrong hour. + * * Strips routing fields — the agent never sees platform_id, channel_type, thread_id. */ export function formatMessages(messages: MessageInRow[]): string { - if (messages.length === 0) return ''; + const header = `\n`; + if (messages.length === 0) return header; // Group by kind const chatMessages = messages.filter((m) => m.kind === 'chat' || m.kind === 'chat-sdk'); @@ -118,7 +128,7 @@ export function formatMessages(messages: MessageInRow[]): string { parts.push(...systemMessages.map(formatSystemMessage)); } - return parts.join('\n\n'); + return header + parts.join('\n\n'); } function formatChatMessages(messages: MessageInRow[]): string { @@ -137,9 +147,10 @@ function formatChatMessages(messages: MessageInRow[]): string { function formatSingleChat(msg: MessageInRow): string { const content = parseContent(msg.content); const sender = content.sender || content.author?.fullName || content.author?.userName || 'Unknown'; - const time = formatTime(msg.timestamp); + const time = formatLocalTime(msg.timestamp, TIMEZONE); const text = content.text || ''; const idAttr = msg.seq != null ? ` id="${msg.seq}"` : ''; + const replyAttr = content.replyTo?.id ? ` reply_to="${escapeXml(String(content.replyTo.id))}"` : ''; const replyPrefix = formatReplyContext(content.replyTo); const attachmentsSuffix = formatAttachments(content.attachments); @@ -154,7 +165,7 @@ function formatSingleChat(msg: MessageInRow): string { ? ` from="unknown:${escapeXml(msg.channel_type || '')}:${escapeXml(msg.platform_id || '')}"` : ''; - return `${replyPrefix}${escapeXml(text)}${attachmentsSuffix}`; + return `${replyPrefix}${escapeXml(text)}${attachmentsSuffix}`; } function formatTaskMessage(msg: MessageInRow): string { @@ -179,13 +190,22 @@ function formatSystemMessage(msg: MessageInRow): string { return `[SYSTEM RESPONSE]\n\nAction: ${content.action || 'unknown'}\nStatus: ${content.status || 'unknown'}\nResult: ${JSON.stringify(content.result || null)}`; } +/** + * Render the quoted original inside the body. + * + * Matches v1 format (src/v1/router.ts:10-18): `Y`. + * Requires BOTH sender and text — if only id is present the reply_to attribute + * on the parent carries the link without an inline preview. + * + * No truncation here (v1 didn't truncate). + */ // eslint-disable-next-line @typescript-eslint/no-explicit-any function formatReplyContext(replyTo: any): string { if (!replyTo) return ''; - const sender = replyTo.sender || 'Unknown'; - const text = replyTo.text || ''; - const preview = text.length > 100 ? text.slice(0, 100) + '…' : text; - return `\n${escapeXml(preview)}\n`; + const sender = replyTo.sender; + const text = replyTo.text; + if (!sender || !text) return ''; + return `\n ${escapeXml(text)}\n`; } // eslint-disable-next-line @typescript-eslint/no-explicit-any @@ -213,15 +233,15 @@ function parseContent(json: string): any { } } -function formatTime(timestamp: string): string { - try { - const d = new Date(timestamp); - return `${d.getHours().toString().padStart(2, '0')}:${d.getMinutes().toString().padStart(2, '0')}`; - } catch { - return timestamp; - } -} - function escapeXml(str: string): string { return str.replace(/&/g, '&').replace(//g, '>').replace(/"/g, '"'); } + +/** + * Strip `...` blocks from agent output, then trim. + * Ported from v1 (src/v1/router.ts:25-27). Used to remove the agent's + * own scratchpad/reasoning before a reply goes out over a channel. + */ +export function stripInternalTags(text: string): string { + return text.replace(/[\s\S]*?<\/internal>/g, '').trim(); +} diff --git a/container/agent-runner/src/mcp-tools/scheduling.ts b/container/agent-runner/src/mcp-tools/scheduling.ts index 168808cd4..00e41bb57 100644 --- a/container/agent-runner/src/mcp-tools/scheduling.ts +++ b/container/agent-runner/src/mcp-tools/scheduling.ts @@ -8,6 +8,7 @@ import { getInboundDb } from '../db/connection.js'; import { writeMessageOut } from '../db/messages-out.js'; import { getSessionRouting } from '../db/session-routing.js'; +import { TIMEZONE, parseZonedToUtc } from '../timezone.js'; import { registerTools } from './server.js'; import type { McpToolDefinition } from './types.js'; @@ -35,13 +36,21 @@ export const scheduleTask: McpToolDefinition = { tool: { name: 'schedule_task', description: - 'Schedule a one-shot or recurring task. The task will be processed at the specified time. Use cron expressions for recurring tasks.', + `Schedule a one-shot or recurring task. The user's timezone is declared in the header of your prompt — interpret the user's "9pm" etc. in that zone. Cron expressions are interpreted in the user's timezone too.`, inputSchema: { type: 'object' as const, properties: { prompt: { type: 'string', description: 'Task instructions/prompt' }, - processAfter: { type: 'string', description: 'ISO timestamp for first run (e.g., 2024-01-15T09:00:00Z)' }, - recurrence: { type: 'string', description: 'Cron expression for recurring tasks (e.g., "0 9 * * 1-5" for weekdays at 9am)' }, + processAfter: { + type: 'string', + description: + `ISO 8601 timestamp for the first run. Accepts either UTC (ending in "Z" or "+00:00") or a naive local timestamp (no offset) which is interpreted in the user's timezone (e.g. "2026-01-15T21:00:00" = 9pm user-local). Prefer naive local.`, + }, + recurrence: { + type: 'string', + description: + 'Cron expression for recurring tasks (e.g., "0 9 * * 1-5" = weekdays at 9am user-local). Evaluated in the user\'s timezone.', + }, script: { type: 'string', description: 'Optional pre-agent script to run before processing' }, }, required: ['prompt', 'processAfter'], @@ -49,8 +58,17 @@ export const scheduleTask: McpToolDefinition = { }, async handler(args) { const prompt = args.prompt as string; - const processAfter = args.processAfter as string; - if (!prompt || !processAfter) return err('prompt and processAfter are required'); + const processAfterIn = args.processAfter as string; + if (!prompt || !processAfterIn) return err('prompt and processAfter are required'); + + let processAfter: string; + try { + const d = parseZonedToUtc(processAfterIn, TIMEZONE); + if (Number.isNaN(d.getTime())) return err(`invalid processAfter: ${processAfterIn}`); + processAfter = d.toISOString(); + } catch { + return err(`invalid processAfter: ${processAfterIn}`); + } const id = generateId(); const r = routing(); @@ -233,7 +251,11 @@ export const updateTask: McpToolDefinition = { type: 'string', description: 'New cron expression (optional). Pass empty string to clear and make the task one-shot.', }, - processAfter: { type: 'string', description: 'New ISO timestamp for the next run (optional)' }, + processAfter: { + type: 'string', + description: + `New ISO 8601 timestamp for the next run (optional). Accepts either UTC (ending in "Z" / "+00:00") or a naive local timestamp interpreted in the user's timezone.`, + }, script: { type: 'string', description: 'New pre-agent script (optional). Pass empty string to clear.', @@ -248,7 +270,15 @@ export const updateTask: McpToolDefinition = { const update: Record = { taskId }; if (typeof args.prompt === 'string') update.prompt = args.prompt; - if (typeof args.processAfter === 'string') update.processAfter = args.processAfter; + if (typeof args.processAfter === 'string') { + try { + const d = parseZonedToUtc(args.processAfter, TIMEZONE); + if (Number.isNaN(d.getTime())) return err(`invalid processAfter: ${args.processAfter}`); + update.processAfter = d.toISOString(); + } catch { + return err(`invalid processAfter: ${args.processAfter}`); + } + } // Empty string clears recurrence/script; undefined leaves them as-is. if (typeof args.recurrence === 'string') update.recurrence = args.recurrence === '' ? null : args.recurrence; if (typeof args.script === 'string') update.script = args.script === '' ? null : args.script; diff --git a/container/agent-runner/src/poll-loop.ts b/container/agent-runner/src/poll-loop.ts index cc2628664..742de1418 100644 --- a/container/agent-runner/src/poll-loop.ts +++ b/container/agent-runner/src/poll-loop.ts @@ -3,7 +3,7 @@ import { getPendingMessages, markProcessing, markCompleted, type MessageInRow } import { writeMessageOut } from './db/messages-out.js'; import { touchHeartbeat, clearStaleProcessingAcks } from './db/connection.js'; import { getStoredSessionId, setStoredSessionId, clearStoredSessionId } from './db/session-state.js'; -import { formatMessages, extractRouting, categorizeMessage, type RoutingContext } from './formatter.js'; +import { formatMessages, extractRouting, categorizeMessage, stripInternalTags, type RoutingContext } from './formatter.js'; import type { AgentProvider, AgentQuery, ProviderEvent } from './providers/types.js'; const POLL_INTERVAL_MS = 1000; @@ -384,10 +384,7 @@ function dispatchResultText(text: string, routing: RoutingContext): void { scratchpadParts.push(text.slice(lastIndex)); } - const scratchpad = scratchpadParts - .join('') - .replace(/[\s\S]*?<\/internal>/g, '') - .trim(); + const scratchpad = stripInternalTags(scratchpadParts.join('')); // Single-destination shortcut: the agent wrote plain text — send to // the session's originating channel (from session_routing) if available, diff --git a/container/agent-runner/src/timezone.test.ts b/container/agent-runner/src/timezone.test.ts new file mode 100644 index 000000000..a4539e97b --- /dev/null +++ b/container/agent-runner/src/timezone.test.ts @@ -0,0 +1,93 @@ +import { describe, it, expect } from 'bun:test'; + +import { formatLocalTime, isValidTimezone, parseZonedToUtc, resolveTimezone } from './timezone.js'; + +// --- formatLocalTime --- + +describe('formatLocalTime', () => { + it('converts UTC to local time display', () => { + // 2026-02-04T18:30:00Z in America/New_York (EST, UTC-5) = 1:30 PM + const result = formatLocalTime('2026-02-04T18:30:00.000Z', 'America/New_York'); + expect(result).toContain('1:30'); + expect(result).toContain('PM'); + expect(result).toContain('Feb'); + expect(result).toContain('2026'); + }); + + it('handles different timezones', () => { + // Same UTC time should produce different local times + const utc = '2026-06-15T12:00:00.000Z'; + const ny = formatLocalTime(utc, 'America/New_York'); + const tokyo = formatLocalTime(utc, 'Asia/Tokyo'); + // NY is UTC-4 in summer (EDT), Tokyo is UTC+9 + expect(ny).toContain('8:00'); + expect(tokyo).toContain('9:00'); + }); + + it('does not throw on invalid timezone, falls back to UTC', () => { + expect(() => formatLocalTime('2026-01-01T00:00:00.000Z', 'IST-2')).not.toThrow(); + const result = formatLocalTime('2026-01-01T12:00:00.000Z', 'IST-2'); + // Should format as UTC (noon UTC = 12:00 PM) + expect(result).toContain('12:00'); + expect(result).toContain('PM'); + }); +}); + +describe('isValidTimezone', () => { + it('accepts valid IANA identifiers', () => { + expect(isValidTimezone('America/New_York')).toBe(true); + expect(isValidTimezone('UTC')).toBe(true); + expect(isValidTimezone('Asia/Tokyo')).toBe(true); + expect(isValidTimezone('Asia/Jerusalem')).toBe(true); + }); + + it('rejects invalid timezone strings', () => { + expect(isValidTimezone('IST-2')).toBe(false); + expect(isValidTimezone('XYZ+3')).toBe(false); + }); + + it('rejects empty and garbage strings', () => { + expect(isValidTimezone('')).toBe(false); + expect(isValidTimezone('NotATimezone')).toBe(false); + }); +}); + +describe('resolveTimezone', () => { + it('returns the timezone if valid', () => { + expect(resolveTimezone('America/New_York')).toBe('America/New_York'); + }); + + it('falls back to UTC for invalid timezone', () => { + expect(resolveTimezone('IST-2')).toBe('UTC'); + expect(resolveTimezone('')).toBe('UTC'); + }); +}); + +describe('parseZonedToUtc', () => { + it('passes strings with Z suffix through unchanged', () => { + const d = parseZonedToUtc('2026-01-15T09:00:00Z', 'America/New_York'); + expect(d.toISOString()).toBe('2026-01-15T09:00:00.000Z'); + }); + + it('passes strings with numeric offset through unchanged', () => { + const d = parseZonedToUtc('2026-01-15T09:00:00+02:00', 'America/New_York'); + expect(d.toISOString()).toBe('2026-01-15T07:00:00.000Z'); + }); + + it('interprets naive ISO as wall-clock in the given timezone', () => { + // 09:00 naive in NY in January = 09:00 EST = 14:00 UTC + const d = parseZonedToUtc('2026-01-15T09:00:00', 'America/New_York'); + expect(d.toISOString()).toBe('2026-01-15T14:00:00.000Z'); + }); + + it('handles a different positive-offset zone', () => { + // 09:00 naive in Tokyo (UTC+9) = 00:00 UTC + const d = parseZonedToUtc('2026-06-15T09:00:00', 'Asia/Tokyo'); + expect(d.toISOString()).toBe('2026-06-15T00:00:00.000Z'); + }); + + it('treats invalid timezone as UTC', () => { + const d = parseZonedToUtc('2026-01-15T09:00:00', 'NotATimezone'); + expect(d.toISOString()).toBe('2026-01-15T09:00:00.000Z'); + }); +}); diff --git a/container/agent-runner/src/timezone.ts b/container/agent-runner/src/timezone.ts new file mode 100644 index 000000000..d9a2e1bcc --- /dev/null +++ b/container/agent-runner/src/timezone.ts @@ -0,0 +1,107 @@ +/** + * Timezone utilities — mirror of src/timezone.ts (host). + * + * The container can't import from src/ (separate tsconfig, different runtime). + * Kept deliberately byte-aligned with the host module so behaviour is the + * same on both sides of the session-DB boundary. + * + * TIMEZONE is resolved once at module load from process.env.TZ (which the host + * sets from its own TIMEZONE constant when spawning the container; see + * src/container-runner.ts). Invalid values fall back to UTC. + */ + +/** + * Check whether a timezone string is a valid IANA identifier + * that Intl.DateTimeFormat can use. + */ +export function isValidTimezone(tz: string): boolean { + try { + Intl.DateTimeFormat(undefined, { timeZone: tz }); + return true; + } catch { + return false; + } +} + +/** + * Return the given timezone if valid IANA, otherwise fall back to UTC. + */ +export function resolveTimezone(tz: string): string { + return isValidTimezone(tz) ? tz : 'UTC'; +} + +/** + * Convert a UTC ISO timestamp to a localized display string. + * Uses the Intl API (no external dependencies). + * Falls back to UTC if the timezone is invalid. + */ +export function formatLocalTime(utcIso: string, timezone: string): string { + const date = new Date(utcIso); + return date.toLocaleString('en-US', { + timeZone: resolveTimezone(timezone), + year: 'numeric', + month: 'short', + day: 'numeric', + hour: 'numeric', + minute: '2-digit', + hour12: true, + }); +} + +function resolveContainerTimezone(): string { + const candidates = [process.env.TZ, Intl.DateTimeFormat().resolvedOptions().timeZone]; + for (const tz of candidates) { + if (tz && isValidTimezone(tz)) return tz; + } + return 'UTC'; +} + +export const TIMEZONE = resolveContainerTimezone(); + +/** + * Interpret a naive ISO-like timestamp (no trailing `Z`, no offset) as wall-clock + * time in `tz` and return the corresponding UTC Date. Strings that already carry + * offset info (`Z` or `±HH:MM`) are passed through to the Date constructor + * unchanged. + * + * Algorithm: treat the naive string as UTC, ask Intl.DateTimeFormat what that + * UTC instant is called in `tz`, then invert the offset. Near DST boundaries + * this can be off by an hour for ~1h of wall-clock time per year; acceptable + * for scheduling where the agent normally picks round-hour targets. + */ +export function parseZonedToUtc(input: string, tz: string): Date { + const hasOffset = /Z$|[+-]\d{2}:?\d{2}$/.test(input.trim()); + if (hasOffset) return new Date(input); + + const zone = resolveTimezone(tz); + const asIfUtc = new Date(input + 'Z'); + if (Number.isNaN(asIfUtc.getTime())) return asIfUtc; + + const fmt = new Intl.DateTimeFormat('en-US', { + timeZone: zone, + year: 'numeric', + month: '2-digit', + day: '2-digit', + hour: '2-digit', + minute: '2-digit', + second: '2-digit', + hour12: false, + }); + const parts = Object.fromEntries( + fmt + .formatToParts(asIfUtc) + .filter((p) => p.type !== 'literal') + .map((p) => [p.type, p.value]), + ); + const hour = parts.hour === '24' ? '00' : parts.hour; + const zonedAsUtcMs = Date.UTC( + Number(parts.year), + Number(parts.month) - 1, + Number(parts.day), + Number(hour), + Number(parts.minute), + Number(parts.second), + ); + const offsetMs = zonedAsUtcMs - asIfUtc.getTime(); + return new Date(asIfUtc.getTime() - offsetMs); +} diff --git a/src/modules/scheduling/recurrence.test.ts b/src/modules/scheduling/recurrence.test.ts new file mode 100644 index 000000000..a70d6c8b2 --- /dev/null +++ b/src/modules/scheduling/recurrence.test.ts @@ -0,0 +1,100 @@ +/** + * Tests for `handleRecurrence` — specifically the timezone-aware cron + * interpretation ported from v1 (src/v1/task-scheduler.ts). + * + * Core invariant: cron expressions are interpreted in the user's TIMEZONE, + * not UTC. Without this, `"0 9 * * *"` fires at 09:00 UTC instead of 09:00 + * user-local — a recurring scheduling bug users can't diagnose. + */ +import fs from 'fs'; +import path from 'path'; +import { afterEach, describe, expect, it } from 'vitest'; + +import { ensureSchema, openInboundDb } from '../../db/session-db.js'; +import { insertTask } from './db.js'; +import { handleRecurrence } from './recurrence.js'; +import type { Session } from '../../types.js'; + +const TEST_DIR = '/tmp/nanoclaw-recurrence-test'; +const DB_PATH = path.join(TEST_DIR, 'inbound.db'); + +function freshDb() { + if (fs.existsSync(TEST_DIR)) fs.rmSync(TEST_DIR, { recursive: true }); + fs.mkdirSync(TEST_DIR, { recursive: true }); + ensureSchema(DB_PATH, 'inbound'); + return openInboundDb(DB_PATH); +} + +function fakeSession(): Session { + return { + id: 'sess-test', + agent_group_id: 'ag-test', + messaging_group_id: 'mg-test', + thread_id: null, + status: 'active', + created_at: new Date().toISOString(), + last_active: new Date().toISOString(), + container_status: 'stopped', + } as Session; +} + +afterEach(() => { + if (fs.existsSync(TEST_DIR)) fs.rmSync(TEST_DIR, { recursive: true }); +}); + +describe('handleRecurrence', () => { + it('clones a completed recurring task with a next-run in the future', async () => { + const db = freshDb(); + insertTask(db, { + id: 'task-1', + processAfter: '2020-01-01T00:00:00.000Z', + recurrence: '0 9 * * *', // every day at 09:00 (user TZ) + platformId: null, + channelType: null, + threadId: null, + content: JSON.stringify({ prompt: 'daily digest' }), + }); + db.prepare(`UPDATE messages_in SET status='completed' WHERE id='task-1'`).run(); + + await handleRecurrence(db, fakeSession()); + + const rows = db + .prepare( + `SELECT id, status, process_after, recurrence, series_id FROM messages_in ORDER BY seq`, + ) + .all() as Array<{ + id: string; + status: string; + process_after: string; + recurrence: string | null; + series_id: string; + }>; + expect(rows).toHaveLength(2); + const original = rows.find((r) => r.id === 'task-1')!; + const follow = rows.find((r) => r.id !== 'task-1')!; + expect(original.recurrence).toBeNull(); + expect(follow.status).toBe('pending'); + expect(follow.recurrence).toBe('0 9 * * *'); + expect(follow.series_id).toBe('task-1'); + expect(new Date(follow.process_after).getTime()).toBeGreaterThan(Date.now()); + }); + + it('does not clone rows whose recurrence is already cleared', async () => { + const db = freshDb(); + insertTask(db, { + id: 'task-1', + processAfter: '2020-01-01T00:00:00.000Z', + recurrence: null, + platformId: null, + channelType: null, + threadId: null, + content: JSON.stringify({ prompt: 'one-off' }), + }); + db.prepare(`UPDATE messages_in SET status='completed' WHERE id='task-1'`).run(); + + await handleRecurrence(db, fakeSession()); + + const count = (db.prepare(`SELECT COUNT(*) AS c FROM messages_in`).get() as { c: number }).c; + expect(count).toBe(1); + }); +}); diff --git a/src/modules/scheduling/recurrence.ts b/src/modules/scheduling/recurrence.ts index a8a2e5c3f..d521f95e8 100644 --- a/src/modules/scheduling/recurrence.ts +++ b/src/modules/scheduling/recurrence.ts @@ -13,6 +13,7 @@ */ import type Database from 'better-sqlite3'; +import { TIMEZONE } from '../../config.js'; import { log } from '../../log.js'; import type { Session } from '../../types.js'; import { clearRecurrence, getCompletedRecurring, insertRecurrence } from './db.js'; @@ -23,7 +24,11 @@ export async function handleRecurrence(inDb: Database.Database, session: Session for (const msg of recurring) { try { const { CronExpressionParser } = await import('cron-parser'); - const interval = CronExpressionParser.parse(msg.recurrence); + // Interpret the cron expression in the user's timezone. v1 did this + // (src/v1/task-scheduler.ts:20-49); without it, a task written "0 9 * * *" + // by an agent running in a user's local TZ fires at 09:00 UTC instead of + // 09:00 user-local. + const interval = CronExpressionParser.parse(msg.recurrence, { tz: TIMEZONE }); const nextRun = interval.next().toISOString(); const prefix = msg.kind === 'task' ? 'task' : 'msg'; const newId = `${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; From 6a815190c01f7b1204e0e2c840783c4932f8910c Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 01:16:57 +0300 Subject: [PATCH 19/95] feat(lifecycle): stuck detection + heartbeat lifecycle + SDK tool blocklist MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replaces the two overlapping old mechanisms (30-min setTimeout kill in container-runner, 10-min heartbeat STALE_THRESHOLD reset in host-sweep) with message-scoped stuck detection anchored to the processing_ack claim age + an absolute 30-min ceiling that extends for long-declared Bash tools. Old model problems: - IDLE_TIMEOUT setTimeout fired on plain wall-clock time; slow-but-alive agents got killed at 30min regardless of activity - 10-min STALE_THRESHOLD in the sweep was unreliable — the heartbeat is only touched on SDK events, so legitimate silent tool work (sleep 30, long WebFetch, npm install) looked identical to a hung container - Two overlapping sources of truth for "when to let go of a container" New model: - Host sweep is the single source of truth. - Container exposes a new `container_state` single-row table in outbound.db (schema added; container writes, host reads). PreToolUse hook writes current_tool + tool_declared_timeout_ms (read from Bash's tool_input); PostToolUse / PostToolUseFailure clear it. - Sweep decides with a pure helper `decideStuckAction`: * absolute ceiling — kill if heartbeat age > max(30min, bash_timeout) * per-claim stuck — kill if any processing_ack row has claim_age > max(60s, bash_timeout) AND heartbeat hasn't been touched since claim * otherwise ok Kill paths reset leftover processing rows with exponential backoff, reusing the existing retry machinery. Tool blocklist expanded: - AskUserQuestion (SDK placeholder; we have mcp__nanoclaw__ask_user_question) - EnterPlanMode, ExitPlanMode, EnterWorktree, ExitWorktree (Claude Code UI affordances; would hang in headless containers) PreToolUse hook is also defense-in-depth: if a disallowed tool name slips through, it returns `{ decision: 'block' }` so the agent sees a clear error instead of appearing stuck. Removed: - container-runner.ts: IDLE_TIMEOUT setTimeout, resetIdle callback on activeContainers entry, resetContainerIdleTimer export. - delivery.ts: the resetContainerIdleTimer call on successful delivery. - poll-loop.ts: IDLE_END_MS + its setInterval. Keeping the query open is cheaper than close+reopen (no cold prompt cache). Liveness is now a host-side concern. - host-sweep.ts: 10-min STALE_THRESHOLD_MS + getStuckProcessingIds in the stale-detection path (still exported for kill reset). Tests: - src/host-sweep.test.ts — 9 tests for decideStuckAction covering: fresh heartbeat, absolute ceiling, absent heartbeat, Bash-timeout extension (both ceiling and per-claim), claim age below tolerance, heartbeat touched after claim, unparseable timestamps. Ref: docs/v1-vs-v2/ACTION-ITEMS.md items 9, 6a, 10. Co-Authored-By: Claude Opus 4.7 (1M context) --- container/agent-runner/src/db/connection.ts | 55 ++++++ container/agent-runner/src/poll-loop.ts | 17 +- .../agent-runner/src/providers/claude.ts | 67 ++++++- src/channels/channel-registry.test.ts | 1 - src/container-runner.ts | 34 +--- src/db/schema.ts | 12 ++ src/db/session-db.ts | 41 ++++ src/delivery.test.ts | 1 - src/delivery.ts | 2 - src/host-core.test.ts | 1 - src/host-sweep.test.ts | 128 ++++++++++++ src/host-sweep.ts | 186 ++++++++++++++---- 12 files changed, 459 insertions(+), 86 deletions(-) create mode 100644 src/host-sweep.test.ts diff --git a/container/agent-runner/src/db/connection.ts b/container/agent-runner/src/db/connection.ts index 9bf2551ae..772f4f160 100644 --- a/container/agent-runner/src/db/connection.ts +++ b/container/agent-runner/src/db/connection.ts @@ -64,10 +64,58 @@ export function getOutboundDb(): Database { if (!cols.has('updated_at')) { _outbound.exec(`ALTER TABLE session_state ADD COLUMN updated_at TEXT NOT NULL DEFAULT ''`); } + // container_state: tracks the current tool in flight (if any) so the host + // sweep can widen its stuck tolerance when Bash is running with a user- + // declared long timeout. Forward-compat for older outbound.db files. + _outbound.exec(` + CREATE TABLE IF NOT EXISTS container_state ( + id INTEGER PRIMARY KEY CHECK (id = 1), + current_tool TEXT, + tool_declared_timeout_ms INTEGER, + tool_started_at TEXT, + updated_at TEXT NOT NULL + ); + `); } return _outbound; } +/** + * Record that a tool is starting. `declaredTimeoutMs` is the tool's own + * timeout hint when one is available (Bash exposes it in the tool_use input); + * omit for tools with no declared timeout. + */ +export function setContainerToolInFlight(tool: string, declaredTimeoutMs: number | null): void { + const now = new Date().toISOString(); + getOutboundDb() + .prepare( + `INSERT INTO container_state (id, current_tool, tool_declared_timeout_ms, tool_started_at, updated_at) + VALUES (1, ?, ?, ?, ?) + ON CONFLICT(id) DO UPDATE SET + current_tool = excluded.current_tool, + tool_declared_timeout_ms = excluded.tool_declared_timeout_ms, + tool_started_at = excluded.tool_started_at, + updated_at = excluded.updated_at`, + ) + .run(tool, declaredTimeoutMs, now, now); +} + +/** Clear the in-flight tool — called on PostToolUse / PostToolUseFailure. */ +export function clearContainerToolInFlight(): void { + const now = new Date().toISOString(); + getOutboundDb() + .prepare( + `INSERT INTO container_state (id, current_tool, tool_declared_timeout_ms, tool_started_at, updated_at) + VALUES (1, NULL, NULL, NULL, ?) + ON CONFLICT(id) DO UPDATE SET + current_tool = NULL, + tool_declared_timeout_ms = NULL, + tool_started_at = NULL, + updated_at = excluded.updated_at`, + ) + .run(now); +} + /** * Touch the heartbeat file — replaces the old touchProcessing() DB writes. * The host checks this file's mtime for stale container detection. @@ -157,6 +205,13 @@ export function initTestSessionDb(): { inbound: Database; outbound: Database } { value TEXT NOT NULL, updated_at TEXT NOT NULL ); + CREATE TABLE container_state ( + id INTEGER PRIMARY KEY CHECK (id = 1), + current_tool TEXT, + tool_declared_timeout_ms INTEGER, + tool_started_at TEXT, + updated_at TEXT NOT NULL + ); `); return { inbound: _inbound, outbound: _outbound }; diff --git a/container/agent-runner/src/poll-loop.ts b/container/agent-runner/src/poll-loop.ts index 742de1418..8a4ec7dc2 100644 --- a/container/agent-runner/src/poll-loop.ts +++ b/container/agent-runner/src/poll-loop.ts @@ -8,7 +8,6 @@ import type { AgentProvider, AgentQuery, ProviderEvent } from './providers/types const POLL_INTERVAL_MS = 1000; const ACTIVE_POLL_INTERVAL_MS = 500; -const IDLE_END_MS = 20_000; // End stream after 20s with no SDK events function log(msg: string): void { console.error(`[poll-loop] ${msg}`); @@ -267,9 +266,13 @@ interface QueryResult { async function processQuery(query: AgentQuery, routing: RoutingContext): Promise { let queryContinuation: string | undefined; let done = false; - let lastEventTime = Date.now(); - // Concurrent polling: push follow-ups, checkpoint WAL, detect idle + // Concurrent polling: push follow-ups into the active query as they arrive. + // We do NOT force-end the stream on silence — keeping the query open is + // strictly cheaper than close+reopen (no cold prompt cache, no reconnect). + // Stream liveness is decided host-side via the heartbeat file + processing + // claim age (see src/host-sweep.ts); if something is truly stuck, the host + // will kill the container and messages get reset to pending. const pollHandle = setInterval(() => { if (done) return; @@ -296,19 +299,11 @@ async function processQuery(query: AgentQuery, routing: RoutingContext): Promise query.push(prompt); markCompleted(newIds); - lastEventTime = Date.now(); // new input counts as activity - } - - // End stream when agent is idle: no SDK events and no pending messages - if (Date.now() - lastEventTime > IDLE_END_MS) { - log(`No SDK events for ${IDLE_END_MS / 1000}s, ending query`); - query.end(); } }, ACTIVE_POLL_INTERVAL_MS); try { for await (const event of query.events) { - lastEventTime = Date.now(); handleEvent(event, routing); touchHeartbeat(); diff --git a/container/agent-runner/src/providers/claude.ts b/container/agent-runner/src/providers/claude.ts index 97fe44af4..a797f06d8 100644 --- a/container/agent-runner/src/providers/claude.ts +++ b/container/agent-runner/src/providers/claude.ts @@ -3,6 +3,7 @@ import path from 'path'; import { query as sdkQuery, type HookCallback, type PreCompactHookInput } from '@anthropic-ai/claude-agent-sdk'; +import { clearContainerToolInFlight, setContainerToolInFlight } from '../db/connection.js'; import { registerProvider } from './provider-registry.js'; import type { AgentProvider, AgentQuery, McpServerConfig, ProviderEvent, ProviderOptions, QueryInput } from './types.js'; @@ -10,10 +11,28 @@ function log(msg: string): void { console.error(`[claude-provider] ${msg}`); } -// Deferred SDK builtins that would sidestep nanoclaw's own scheduling. -// Scheduling goes through mcp__nanoclaw__schedule_task so that tasks are -// durable across sessions/restarts and gated by our pre-task script hook. -const SDK_DISALLOWED_TOOLS = ['CronCreate', 'CronDelete', 'CronList', 'ScheduleWakeup']; +// Deferred SDK builtins that either sidestep nanoclaw's own scheduling or +// don't fit our async message-passing model (they're designed for Claude +// Code's interactive UI and would hang here). +// +// - CronCreate / CronDelete / CronList / ScheduleWakeup: we have durable +// scheduling via mcp__nanoclaw__schedule_task. +// - AskUserQuestion: SDK returns a placeholder instead of blocking on a +// real answer — we have mcp__nanoclaw__ask_user_question that persists +// the question and blocks on the real reply. +// - EnterPlanMode / ExitPlanMode / EnterWorktree / ExitWorktree: Claude +// Code UI affordances; in a headless container they'd appear stuck. +const SDK_DISALLOWED_TOOLS = [ + 'CronCreate', + 'CronDelete', + 'CronList', + 'ScheduleWakeup', + 'AskUserQuestion', + 'EnterPlanMode', + 'ExitPlanMode', + 'EnterWorktree', + 'ExitWorktree', +]; // Tool allowlist for NanoClaw agent containers const TOOL_ALLOWLIST = [ @@ -122,6 +141,43 @@ function formatTranscriptMarkdown(messages: ParsedMessage[], title?: string | nu return lines.join('\n'); } +/** + * PreToolUse hook: record the current tool + its declared timeout so the host + * sweep can widen its stuck tolerance while Bash is running a long-declared + * script. Defense-in-depth: if SDK_DISALLOWED_TOOLS slips through somehow, + * block the call here instead of letting the agent hang. + */ +const preToolUseHook: HookCallback = async (input) => { + const i = input as { tool_name?: string; tool_input?: Record }; + const toolName = i.tool_name ?? ''; + if (SDK_DISALLOWED_TOOLS.includes(toolName)) { + return { + decision: 'block', + stopReason: `Tool '${toolName}' is not available in this environment — use the nanoclaw equivalent.`, + } as unknown as ReturnType; + } + // Bash exposes its timeout via the tool_input.timeout field (ms). Any other + // tool: no declared timeout. + const declaredTimeoutMs = + toolName === 'Bash' && typeof i.tool_input?.timeout === 'number' ? (i.tool_input.timeout as number) : null; + try { + setContainerToolInFlight(toolName, declaredTimeoutMs); + } catch (err) { + log(`PreToolUse: failed to record container_state: ${err instanceof Error ? err.message : String(err)}`); + } + return { continue: true }; +}; + +/** Clear in-flight tool on PostToolUse / PostToolUseFailure. */ +const postToolUseHook: HookCallback = async () => { + try { + clearContainerToolInFlight(); + } catch (err) { + log(`PostToolUse: failed to clear container_state: ${err instanceof Error ? err.message : String(err)}`); + } + return { continue: true }; +}; + function createPreCompactHook(assistantName?: string): HookCallback { return async (input) => { const preCompact = input as PreCompactHookInput; @@ -224,6 +280,9 @@ export class ClaudeProvider implements AgentProvider { settingSources: ['project', 'user'], mcpServers: this.mcpServers, hooks: { + PreToolUse: [{ hooks: [preToolUseHook] }], + PostToolUse: [{ hooks: [postToolUseHook] }], + PostToolUseFailure: [{ hooks: [postToolUseHook] }], PreCompact: [{ hooks: [createPreCompactHook(this.assistantName)] }], }, }, diff --git a/src/channels/channel-registry.test.ts b/src/channels/channel-registry.test.ts index 0abbf9d99..0e856f6cd 100644 --- a/src/channels/channel-registry.test.ts +++ b/src/channels/channel-registry.test.ts @@ -10,7 +10,6 @@ import type { ChannelAdapter, ChannelSetup, InboundMessage, OutboundMessage } fr // Mock container runner vi.mock('../container-runner.js', () => ({ wakeContainer: vi.fn().mockResolvedValue(undefined), - resetContainerIdleTimer: vi.fn(), isContainerRunning: vi.fn().mockReturnValue(false), getActiveContainerCount: vi.fn().mockReturnValue(0), killContainer: vi.fn(), diff --git a/src/container-runner.ts b/src/container-runner.ts index c3fb24fd1..9764126a8 100644 --- a/src/container-runner.ts +++ b/src/container-runner.ts @@ -9,7 +9,7 @@ import path from 'path'; import { OneCLI } from '@onecli-sh/sdk'; -import { CONTAINER_IMAGE, DATA_DIR, GROUPS_DIR, IDLE_TIMEOUT, ONECLI_URL, TIMEZONE } from './config.js'; +import { CONTAINER_IMAGE, DATA_DIR, GROUPS_DIR, ONECLI_URL, TIMEZONE } from './config.js'; import { readContainerConfig, writeContainerConfig } from './container-config.js'; import { CONTAINER_RUNTIME_BIN, hostGatewayArgs, readonlyMountArgs, stopContainer } from './container-runtime.js'; import { getAgentGroup } from './db/agent-groups.js'; @@ -26,12 +26,7 @@ import { type ProviderContainerContribution, type VolumeMount, } from './providers/provider-container-registry.js'; -import { - markContainerRunning, - markContainerStopped, - sessionDir, - writeSessionRouting, -} from './session-manager.js'; +import { markContainerRunning, markContainerStopped, sessionDir, writeSessionRouting } from './session-manager.js'; import type { AgentGroup, Session } from './types.js'; const onecli = new OneCLI({ url: ONECLI_URL }); @@ -125,22 +120,12 @@ async function spawnContainer(session: Session): Promise { // stdout is unused in v2 (all IO is via session DB) container.stdout?.on('data', () => {}); - // Idle timeout: kill container after IDLE_TIMEOUT of no activity - let idleTimer = setTimeout(() => killContainer(session.id, 'idle timeout'), IDLE_TIMEOUT); - - const resetIdle = () => { - clearTimeout(idleTimer); - idleTimer = setTimeout(() => killContainer(session.id, 'idle timeout'), IDLE_TIMEOUT); - }; - - // Reset idle timer when the host detects new messages_out (called by delivery.ts) - const entry = activeContainers.get(session.id); - if (entry) { - (entry as { resetIdle?: () => void }).resetIdle = resetIdle; - } + // No host-side idle timeout. Stale/stuck detection is driven by the host + // sweep reading heartbeat mtime + processing_ack claim age + container_state + // (see src/host-sweep.ts). This avoids killing long-running legitimate work + // on a wall-clock timer. container.on('close', (code) => { - clearTimeout(idleTimer); activeContainers.delete(session.id); markContainerStopped(session.id); stopTypingRefresh(session.id); @@ -148,7 +133,6 @@ async function spawnContainer(session: Session): Promise { }); container.on('error', (err) => { - clearTimeout(idleTimer); activeContainers.delete(session.id); markContainerStopped(session.id); stopTypingRefresh(session.id); @@ -156,12 +140,6 @@ async function spawnContainer(session: Session): Promise { }); } -/** Reset the idle timer for a session's container (called when messages_out are delivered). */ -export function resetContainerIdleTimer(sessionId: string): void { - const entry = activeContainers.get(sessionId) as { resetIdle?: () => void } | undefined; - entry?.resetIdle?.(); -} - /** Kill a container for a session. */ export function killContainer(sessionId: string, reason: string): void { const entry = activeContainers.get(sessionId); diff --git a/src/db/schema.ts b/src/db/schema.ts index 044d71713..47d4c9fd0 100644 --- a/src/db/schema.ts +++ b/src/db/schema.ts @@ -213,4 +213,16 @@ CREATE TABLE IF NOT EXISTS session_state ( value TEXT NOT NULL, updated_at TEXT NOT NULL ); + +-- Current tool-in-flight state. Single-row table (id=1). Container writes on +-- PreToolUse and clears on PostToolUse / PostToolUseFailure. Host reads in the +-- sweep to extend the stuck-tolerance window when Bash is running with a +-- declared timeout > 60s (long-running scripts shouldn't be flagged as stuck). +CREATE TABLE IF NOT EXISTS container_state ( + id INTEGER PRIMARY KEY CHECK (id = 1), + current_tool TEXT, + tool_declared_timeout_ms INTEGER, + tool_started_at TEXT, + updated_at TEXT NOT NULL +); `; diff --git a/src/db/session-db.ts b/src/db/session-db.ts index 05104cf97..a73ca5c0c 100644 --- a/src/db/session-db.ts +++ b/src/db/session-db.ts @@ -161,6 +161,47 @@ export function getStuckProcessingIds(outDb: Database.Database): string[] { ).map((r) => r.message_id); } +export interface ProcessingClaim { + message_id: string; + status_changed: string; +} + +/** Return processing_ack rows still in 'processing' with their claim timestamps. */ +export function getProcessingClaims(outDb: Database.Database): ProcessingClaim[] { + return outDb + .prepare( + "SELECT message_id, status_changed FROM processing_ack WHERE status = 'processing'", + ) + .all() as ProcessingClaim[]; +} + +export interface ContainerState { + current_tool: string | null; + tool_declared_timeout_ms: number | null; + tool_started_at: string | null; +} + +/** + * Read the container's current tool-in-flight state, if any. Returns null + * when either the table doesn't exist yet (older session DB) or no tool is + * active. Host sweep reads this to widen stuck-detection tolerance while + * Bash is running with a long declared timeout. + */ +export function getContainerState(outDb: Database.Database): ContainerState | null { + try { + const row = outDb + .prepare( + `SELECT current_tool, tool_declared_timeout_ms, tool_started_at + FROM container_state WHERE id = 1`, + ) + .get() as ContainerState | undefined; + return row ?? null; + } catch { + // Table not present on older session DBs — treat as "no tool in flight". + return null; + } +} + // --------------------------------------------------------------------------- // messages_out (read-only from host) // --------------------------------------------------------------------------- diff --git a/src/delivery.test.ts b/src/delivery.test.ts index d63183697..a5e1efd10 100644 --- a/src/delivery.test.ts +++ b/src/delivery.test.ts @@ -14,7 +14,6 @@ import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'; vi.mock('./container-runner.js', () => ({ wakeContainer: vi.fn().mockResolvedValue(undefined), - resetContainerIdleTimer: vi.fn(), isContainerRunning: vi.fn().mockReturnValue(false), killContainer: vi.fn(), buildAgentGroupImage: vi.fn().mockResolvedValue(undefined), diff --git a/src/delivery.ts b/src/delivery.ts index 7b1ee7d47..2e193d4c2 100644 --- a/src/delivery.ts +++ b/src/delivery.ts @@ -23,7 +23,6 @@ import { import { log } from './log.js'; import { normalizeOptions } from './channels/ask-question.js'; import { clearOutbox, openInboundDb, openOutboundDb, readOutboxFiles } from './session-manager.js'; -import { resetContainerIdleTimer } from './container-runner.js'; import { pauseTypingRefreshAfterDelivery, setTypingAdapter } from './modules/typing/index.js'; import type { OutboundFile } from './channels/adapter.js'; import type { Session } from './types.js'; @@ -193,7 +192,6 @@ async function drainSession(session: Session): Promise { const platformMsgId = await deliverMessage(msg, session, inDb); markDelivered(inDb, msg.id, platformMsgId ?? null); deliveryAttempts.delete(msg.id); - resetContainerIdleTimer(session.id); // Pause the typing indicator after a real user-facing message // lands on the user's screen, so the client has time to visually diff --git a/src/host-core.test.ts b/src/host-core.test.ts index a8b4684bd..7269164bc 100644 --- a/src/host-core.test.ts +++ b/src/host-core.test.ts @@ -30,7 +30,6 @@ import type { InboundEvent } from './router.js'; // Mock container runner to prevent actual Docker spawning vi.mock('./container-runner.js', () => ({ wakeContainer: vi.fn().mockResolvedValue(undefined), - resetContainerIdleTimer: vi.fn(), isContainerRunning: vi.fn().mockReturnValue(false), getActiveContainerCount: vi.fn().mockReturnValue(0), killContainer: vi.fn(), diff --git a/src/host-sweep.test.ts b/src/host-sweep.test.ts new file mode 100644 index 000000000..d9505a4ae --- /dev/null +++ b/src/host-sweep.test.ts @@ -0,0 +1,128 @@ +/** + * Unit tests for the stuck-container decision logic introduced by + * ACTION-ITEMS item 9. Lives on the pure helper `decideStuckAction` so we + * don't have to mock the filesystem or the container runner. + */ +import { describe, expect, it } from 'vitest'; + +import { ABSOLUTE_CEILING_MS, CLAIM_STUCK_MS, decideStuckAction } from './host-sweep.js'; + +const BASE = Date.parse('2026-04-20T12:00:00.000Z'); + +function claim(id: string, offsetMs: number) { + return { message_id: id, status_changed: new Date(BASE - offsetMs).toISOString() }; +} + +describe('decideStuckAction', () => { + it('returns ok when heartbeat is fresh and no claims', () => { + expect( + decideStuckAction({ + now: BASE, + heartbeatMtimeMs: BASE - 5_000, + containerState: null, + claims: [], + }), + ).toEqual({ action: 'ok' }); + }); + + it('returns kill-ceiling when heartbeat older than 30 min', () => { + const heartbeatMtimeMs = BASE - ABSOLUTE_CEILING_MS - 1_000; + const res = decideStuckAction({ + now: BASE, + heartbeatMtimeMs, + containerState: null, + claims: [], + }); + expect(res.action).toBe('kill-ceiling'); + if (res.action !== 'kill-ceiling') return; + expect(res.ceilingMs).toBe(ABSOLUTE_CEILING_MS); + expect(res.heartbeatAgeMs).toBeGreaterThan(ABSOLUTE_CEILING_MS); + }); + + it('treats an absent heartbeat file as infinitely stale', () => { + const res = decideStuckAction({ + now: BASE, + heartbeatMtimeMs: 0, + containerState: null, + claims: [], + }); + expect(res.action).toBe('kill-ceiling'); + }); + + it('extends the ceiling when Bash has a declared timeout longer than 30 min', () => { + const twoHrMs = 2 * 60 * 60 * 1000; + const res = decideStuckAction({ + now: BASE, + // 45 min — over the default ceiling, but under the Bash timeout + heartbeatMtimeMs: BASE - 45 * 60 * 1000, + containerState: { + current_tool: 'Bash', + tool_declared_timeout_ms: twoHrMs, + tool_started_at: new Date(BASE - 45 * 60 * 1000).toISOString(), + }, + claims: [], + }); + expect(res.action).toBe('ok'); + }); + + it('returns kill-claim when a claim is past 60s and heartbeat has not moved', () => { + const claimedAgeMs = CLAIM_STUCK_MS + 10_000; + const res = decideStuckAction({ + now: BASE, + heartbeatMtimeMs: BASE - claimedAgeMs - 5_000, // older than the claim + containerState: null, + claims: [claim('msg-1', claimedAgeMs)], + }); + expect(res.action).toBe('kill-claim'); + if (res.action !== 'kill-claim') return; + expect(res.messageId).toBe('msg-1'); + expect(res.toleranceMs).toBe(CLAIM_STUCK_MS); + }); + + it('does not kill when heartbeat has been touched since the claim', () => { + const claimedAgeMs = CLAIM_STUCK_MS + 10_000; + const res = decideStuckAction({ + now: BASE, + heartbeatMtimeMs: BASE - 2_000, // fresh, updated after the claim + containerState: null, + claims: [claim('msg-1', claimedAgeMs)], + }); + expect(res.action).toBe('ok'); + }); + + it('does not kill when claim age is below tolerance', () => { + const res = decideStuckAction({ + now: BASE, + heartbeatMtimeMs: BASE - CLAIM_STUCK_MS - 10_000, // old, but claim is recent + containerState: null, + claims: [claim('msg-1', 5_000)], + }); + expect(res.action).toBe('ok'); + }); + + it('widens per-claim tolerance for a running Bash with long timeout', () => { + const tenMinMs = 10 * 60 * 1000; + const res = decideStuckAction({ + now: BASE, + // 5 min since claim, over the 60s default but under the declared Bash timeout + heartbeatMtimeMs: BASE - (5 * 60 * 1000) - 5_000, + containerState: { + current_tool: 'Bash', + tool_declared_timeout_ms: tenMinMs, + tool_started_at: new Date(BASE - 5 * 60 * 1000).toISOString(), + }, + claims: [claim('msg-1', 5 * 60 * 1000)], + }); + expect(res.action).toBe('ok'); + }); + + it('ignores claims with unparseable timestamps', () => { + const res = decideStuckAction({ + now: BASE, + heartbeatMtimeMs: BASE - 5_000, + containerState: null, + claims: [{ message_id: 'x', status_changed: 'not-a-date' }], + }); + expect(res.action).toBe('ok'); + }); +}); diff --git a/src/host-sweep.ts b/src/host-sweep.ts index 7a7688f84..0f8365c80 100644 --- a/src/host-sweep.ts +++ b/src/host-sweep.ts @@ -2,10 +2,29 @@ * Host sweep — periodic maintenance of all session DBs. * * Two-DB architecture: - * - Reads processing_ack from outbound.db to sync message status - * - Writes to inbound.db (host-owned) for status updates and recurrence - * - Uses heartbeat file mtime for stale container detection (not DB writes) + * - Reads processing_ack + container_state from outbound.db + * - Writes to inbound.db (host-owned) for status updates + recurrence + * - Uses heartbeat file mtime for liveness (never polls DB for it) * - Never writes to outbound.db — preserves single-writer-per-file invariant + * + * Stuck / idle detection (replaces the old IDLE_TIMEOUT setTimeout + 10-min + * heartbeat threshold): + * + * If the container isn't running and there are 'processing' rows left over + * (e.g. it crashed mid-turn) → reset them to pending with backoff + + * tries++. Existing retry machinery does the rest. + * + * If the container IS running: + * 1. Absolute ceiling: heartbeat age > max(30 min, current_bash_timeout) + * → kill. Covers the "alive but silent for 30 min" case. Extended + * only while Bash is declared as running longer, honouring the + * user's own timeout directive. Kill then resets processing rows. + * + * 2. Message-scoped stuck: for each 'processing' row, tolerance = + * max(60s, current_bash_timeout_ms_if_Bash_running). If + * (claim_age > tolerance) AND (heartbeat_mtime <= status_changed) + * → kill + reset this message + tries++. Semantics: "container + * claimed a message and went quiet past tolerance since the claim." */ import type Database from 'better-sqlite3'; import fs from 'fs'; @@ -14,22 +33,68 @@ import { getActiveSessions } from './db/sessions.js'; import { getAgentGroup } from './db/agent-groups.js'; import { countDueMessages, - syncProcessingAcks, - getStuckProcessingIds, + getContainerState, getMessageForRetry, + getProcessingClaims, markMessageFailed, retryWithBackoff, + syncProcessingAcks, + type ContainerState, } from './db/session-db.js'; import { log } from './log.js'; import { openInboundDb, openOutboundDb, inboundDbPath, heartbeatPath } from './session-manager.js'; -import { wakeContainer, isContainerRunning } from './container-runner.js'; +import { isContainerRunning, killContainer, wakeContainer } from './container-runner.js'; import type { Session } from './types.js'; const SWEEP_INTERVAL_MS = 60_000; -const STALE_THRESHOLD_MS = 10 * 60 * 1000; // 10 minutes +// Absolute idle ceiling for a running container. If the heartbeat file hasn't +// been touched in this long, the container is either stuck or doing genuinely +// nothing — kill and restart on the next inbound. +export const ABSOLUTE_CEILING_MS = 30 * 60 * 1000; +// Stuck tolerance window applied per 'processing' claim — "did we see any +// signs of life since this message was claimed?" +export const CLAIM_STUCK_MS = 60 * 1000; const MAX_TRIES = 5; const BACKOFF_BASE_MS = 5000; +export type StuckDecision = + | { action: 'ok' } + | { action: 'kill-ceiling'; heartbeatAgeMs: number; ceilingMs: number } + | { action: 'kill-claim'; messageId: string; claimAgeMs: number; toleranceMs: number }; + +/** + * Pure decision for whether a running container should be killed this sweep + * tick. Inputs are all deterministic; filesystem + DB reads happen in the + * caller. + */ +export function decideStuckAction(args: { + now: number; + heartbeatMtimeMs: number; // 0 when heartbeat file absent + containerState: ContainerState | null; + claims: Array<{ message_id: string; status_changed: string }>; +}): StuckDecision { + const { now, heartbeatMtimeMs, containerState, claims } = args; + const declaredBashMs = bashTimeoutMs(containerState); + const heartbeatAge = heartbeatMtimeMs === 0 ? Infinity : now - heartbeatMtimeMs; + + const ceiling = Math.max(ABSOLUTE_CEILING_MS, declaredBashMs ?? 0); + if (heartbeatAge > ceiling) { + return { action: 'kill-ceiling', heartbeatAgeMs: heartbeatAge, ceilingMs: ceiling }; + } + + const tolerance = Math.max(CLAIM_STUCK_MS, declaredBashMs ?? 0); + for (const claim of claims) { + const claimedAt = Date.parse(claim.status_changed); + if (Number.isNaN(claimedAt)) continue; + const claimAge = now - claimedAt; + if (claimAge <= tolerance) continue; + if (heartbeatMtimeMs > claimedAt) continue; + return { action: 'kill-claim', messageId: claim.message_id, claimAgeMs: claimAge, toleranceMs: tolerance }; + } + + return { action: 'ok' }; +} + let running = false; export function startHostSweep(): void { @@ -84,20 +149,26 @@ async function sweepSession(session: Session): Promise { syncProcessingAcks(inDb, outDb); } - // 2. Check for due pending messages → wake container - const dueCount = countDueMessages(inDb); + const alive = isContainerRunning(session.id); + // 2. Crashed-container cleanup: processing rows left behind get retried. + if (!alive && outDb) { + resetStuckProcessingRows(inDb, outDb, session, 'container not running'); + } + + // 3. Running-container SLA: absolute ceiling + per-claim stuck rules. + if (alive && outDb) { + enforceRunningContainerSla(inDb, outDb, session, agentGroup.id); + } + + // 4. Wake a container if new work is due and nothing is running. + const dueCount = countDueMessages(inDb); if (dueCount > 0 && !isContainerRunning(session.id)) { log.info('Waking container for due messages', { sessionId: session.id, count: dueCount }); await wakeContainer(session); } - // 3. Detect stale containers via heartbeat file - if (outDb) { - detectStaleContainers(inDb, outDb, session, agentGroup.id); - } - - // 4. Handle recurrence for completed messages. + // 5. Recurrence fanout for completed recurring tasks. // MODULE-HOOK:scheduling-recurrence:start const { handleRecurrence } = await import('./modules/scheduling/recurrence.js'); await handleRecurrence(inDb, session); @@ -108,45 +179,84 @@ async function sweepSession(session: Session): Promise { } } -/** - * Detect stale containers using heartbeat file mtime. - * If the heartbeat is older than STALE_THRESHOLD and processing_ack has - * 'processing' entries, the container likely crashed — reset with backoff. - */ -function detectStaleContainers( +function heartbeatMtimeMs(agentGroupId: string, sessionId: string): number { + const hbPath = heartbeatPath(agentGroupId, sessionId); + try { + return fs.statSync(hbPath).mtimeMs; + } catch { + return 0; + } +} + +function bashTimeoutMs(state: ContainerState | null): number | null { + if (!state || state.current_tool !== 'Bash') return null; + return typeof state.tool_declared_timeout_ms === 'number' ? state.tool_declared_timeout_ms : null; +} + +function enforceRunningContainerSla( inDb: Database.Database, outDb: Database.Database, session: Session, agentGroupId: string, ): void { - const hbPath = heartbeatPath(agentGroupId, session.id); - let heartbeatAge = Infinity; - try { - const stat = fs.statSync(hbPath); - heartbeatAge = Date.now() - stat.mtimeMs; - } catch { - // No heartbeat file — container may never have started, or it's very old + const decision = decideStuckAction({ + now: Date.now(), + heartbeatMtimeMs: heartbeatMtimeMs(agentGroupId, session.id), + containerState: getContainerState(outDb), + claims: getProcessingClaims(outDb), + }); + + if (decision.action === 'ok') return; + + if (decision.action === 'kill-ceiling') { + log.warn('Killing container past absolute ceiling', { + sessionId: session.id, + heartbeatAgeMs: decision.heartbeatAgeMs, + ceilingMs: decision.ceilingMs, + }); + killContainer(session.id, 'absolute-ceiling'); + resetStuckProcessingRows(inDb, outDb, session, 'absolute-ceiling'); + return; } - if (heartbeatAge < STALE_THRESHOLD_MS) return; // Container is alive + log.warn('Killing container — message claimed then silent', { + sessionId: session.id, + messageId: decision.messageId, + claimAgeMs: decision.claimAgeMs, + toleranceMs: decision.toleranceMs, + }); + killContainer(session.id, 'claim-stuck'); + resetStuckProcessingRows(inDb, outDb, session, 'claim-stuck'); +} - // Heartbeat is stale — check for stuck processing entries - const processingIds = getStuckProcessingIds(outDb); - if (processingIds.length === 0) return; - - for (const messageId of processingIds) { - const msg = getMessageForRetry(inDb, messageId, 'pending'); +function resetStuckProcessingRows( + inDb: Database.Database, + outDb: Database.Database, + session: Session, + reason: string, +): void { + const claims = getProcessingClaims(outDb); + for (const { message_id } of claims) { + const msg = getMessageForRetry(inDb, message_id, 'pending'); if (!msg) continue; if (msg.tries >= MAX_TRIES) { markMessageFailed(inDb, msg.id); - log.warn('Message marked as failed after max retries', { messageId: msg.id, sessionId: session.id }); + log.warn('Message marked as failed after max retries', { + messageId: msg.id, + sessionId: session.id, + reason, + }); } else { const backoffMs = BACKOFF_BASE_MS * Math.pow(2, msg.tries); const backoffSec = Math.floor(backoffMs / 1000); retryWithBackoff(inDb, msg.id, backoffSec); - log.info('Reset stale message with backoff', { messageId: msg.id, tries: msg.tries, backoffMs }); + log.info('Reset stale message with backoff', { + messageId: msg.id, + tries: msg.tries, + backoffMs, + reason, + }); } } } - From 16b9499532bb58299be51e5143f4f7f013433402 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 01:30:04 +0300 Subject: [PATCH 20/95] feat(routing): engage modes + sender scope + accumulate/drop + per-agent fan-out MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replaces the opaque trigger_rules JSON + response_scope enum on messaging_group_agents with four explicit orthogonal columns: engage_mode 'pattern' | 'mention' | 'mention-sticky' engage_pattern regex source; required when mode='pattern'; '.' is the "always" sentinel sender_scope 'all' | 'known' ignored_message_policy 'drop' | 'accumulate' Inbound routing becomes a fan-out — every wired agent is evaluated independently. A match gets its own session + container wake. A miss with accumulate keeps the message as context-only (trigger=0) in that agent's session, so when the agent does eventually engage it sees the prior chatter. ## Schema - Migration 010 (`engage-modes`): adds the 4 new columns, backfills from trigger_rules.pattern + requiresTrigger + response_scope, drops the legacy columns. - messages_in gains `trigger INTEGER NOT NULL DEFAULT 1` (session DB schema + `migrateMessagesInTable` forward-compat). - countDueMessages gates waking on `trigger = 1`. ## Routing - `pickAgent` (returns one) → loop over all wired agents. Per agent: evaluate engage_mode; run access gate + sender-scope gate; on full match → resolveSession + writeSessionMessage(trigger=1) + wake. On miss with accumulate → writeSessionMessage(trigger=0), no wake. On miss with drop → skip. - New `findSessionForAgent(agentGroupId, mgId, threadId)` scopes session lookup by agent so fan-out doesn't cross sessions. - `messageIdForAgent` namespaces inbound message ids by agent_group_id so PRIMARY KEY doesn't collide across per-agent session DBs. ## Adapter layer - `ConversationConfig` replaces `triggerPattern` + `requiresTrigger` with `engageMode` + `engagePattern`. - Chat SDK bridge stores `Map` (multi- agent per conversation) and applies union gating pre-onInbound: * onSubscribedMessage: engage if any wiring keeps firing in subscribed state (mention-sticky or pattern) * onNewMention: engage on mention; only subscribes the thread if at least one wiring is `mention-sticky` * onDirectMessage: engage per mode; sticky follows same rule - Bridge no longer unconditionally calls `thread.subscribe()`. ## Sender scope - Permissions module registers a second hook `setSenderScopeGate` that runs per-wiring after the existing access gate. `sender_scope='known'` requires canAccessAgentGroup(); `'all'` is a no-op. Not installed → no-op everywhere (default allow). ## Container side - Host passes `NANOCLAW_MAX_MESSAGES_PER_PROMPT` (reuses existing MAX_MESSAGES_PER_PROMPT config; was dead code from v1). - `getPendingMessages` queries `ORDER BY seq DESC LIMIT N`, reverses to chronological order for the prompt — accumulated context rides along with trigger rows up to the cap. - `MessageInRow` gains `trigger: number` so the container can tell them apart in downstream code (container still processes both; only the host uses `trigger=0` for don't-wake). ## Defaults (per ACTION-ITEMS item 1 decision) - DM (is_group=0): `engage_mode='pattern'`, `engage_pattern='.'` (always) - Threaded group: `engage_mode='mention-sticky'` (seed-discord) - Non-threaded group / CLI: pattern '.' in bootstrap scripts ## Tests - src/host-core.test.ts: 3 new cases — fan-out (2 agents, 2 sessions, 2 wakes), accumulate (trigger=0 + no wake), drop (no session created). - Existing 10 host-core tests still pass. - Migration 010 runs on an empty DB in 0-row path — verified. Closes: ACTION-ITEMS items 1, 4. Co-Authored-By: Claude Opus 4.7 (1M context) --- container/agent-runner/src/db/messages-in.ts | 26 ++- scripts/init-first-agent.ts | 16 +- scripts/seed-discord.ts | 8 +- scripts/test-v2-channel-e2e.ts | 16 +- scripts/test-v2-host.ts | 6 +- src/channels/adapter.ts | 15 +- src/channels/channel-registry.test.ts | 6 +- src/channels/chat-sdk-bridge.ts | 123 +++++++++-- src/container-runner.ts | 5 +- src/db/db-v2.test.ts | 9 +- src/db/messaging-groups.ts | 19 +- src/db/migrations/010-engage-modes.ts | 101 +++++++++ src/db/migrations/index.ts | 6 +- src/db/schema.ts | 27 ++- src/db/session-db.ts | 27 ++- src/db/sessions.ts | 25 +++ src/host-core.test.ts | 106 +++++++++- src/index.ts | 5 +- src/modules/permissions/index.ts | 28 ++- src/router.ts | 203 ++++++++++++++----- src/session-manager.ts | 21 +- src/types.ts | 15 +- 22 files changed, 688 insertions(+), 125 deletions(-) create mode 100644 src/db/migrations/010-engage-modes.ts diff --git a/container/agent-runner/src/db/messages-in.ts b/container/agent-runner/src/db/messages-in.ts index da1a8ddb3..a152a5eb0 100644 --- a/container/agent-runner/src/db/messages-in.ts +++ b/container/agent-runner/src/db/messages-in.ts @@ -18,16 +18,33 @@ export interface MessageInRow { process_after: string | null; recurrence: string | null; tries: number; + /** 1 = wake-eligible (default); 0 = accumulated context only */ + trigger: number; platform_id: string | null; channel_type: string | null; thread_id: string | null; content: string; } +// Cap on how many messages reach the agent in one prompt, including any +// accumulated-but-not-triggered context. Host controls the cap via the +// NANOCLAW_MAX_MESSAGES_PER_PROMPT env var; default mirrors the host's +// config.ts default of 10. +const MAX_MESSAGES_PER_PROMPT = Math.max( + 1, + parseInt(process.env.NANOCLAW_MAX_MESSAGES_PER_PROMPT || '10', 10) || 10, +); + /** * Fetch pending messages that are due for processing. * Reads from inbound.db (read-only), filters against processing_ack in outbound.db * to skip messages already picked up by this or a previous container run. + * + * Returns the most recent `MAX_MESSAGES_PER_PROMPT` pending rows in + * chronological order, regardless of their `trigger` flag: accumulated + * context (trigger=0) rides along with the wake-eligible rows so the agent + * sees the prior context it missed. Host's countDueMessages gates waking on + * trigger=1 separately (see src/db/session-db.ts). */ export function getPendingMessages(): MessageInRow[] { const inbound = getInboundDb(); @@ -38,9 +55,10 @@ export function getPendingMessages(): MessageInRow[] { `SELECT * FROM messages_in WHERE status = 'pending' AND (process_after IS NULL OR datetime(process_after) <= datetime('now')) - ORDER BY timestamp ASC`, + ORDER BY seq DESC + LIMIT ?`, ) - .all() as MessageInRow[]; + .all(MAX_MESSAGES_PER_PROMPT) as MessageInRow[]; if (pending.length === 0) return []; @@ -51,7 +69,9 @@ export function getPendingMessages(): MessageInRow[] { ), ); - return pending.filter((m) => !ackedIds.has(m.id)); + // Reverse: we fetched DESC to take the most recent N, but the agent + // should see them in chronological order (oldest first). + return pending.filter((m) => !ackedIds.has(m.id)).reverse(); } /** Mark messages as processing — writes to processing_ack in outbound.db. */ diff --git a/scripts/init-first-agent.ts b/scripts/init-first-agent.ts index efb3b6bdb..d7ff0df4f 100644 --- a/scripts/init-first-agent.ts +++ b/scripts/init-first-agent.ts @@ -195,8 +195,13 @@ async function main(): Promise { id: generateId('mga'), messaging_group_id: mg.id, agent_group_id: ag.id, - trigger_rules: null, - response_scope: 'all', + // DM (is_group=0) defaults to "respond to everything" via the '.' pattern. + // Group chats default to mention-only; admins can upgrade to + // mention-sticky via /manage-channels once the agent is in use. + engage_mode: mg.is_group === 0 ? 'pattern' : 'mention', + engage_pattern: mg.is_group === 0 ? '.' : null, + sender_scope: 'all', + ignored_message_policy: 'drop', session_mode: 'shared', priority: 0, created_at: now, @@ -248,8 +253,11 @@ async function main(): Promise { id: generateId('mga'), messaging_group_id: cliMg.id, agent_group_id: ag.id, - trigger_rules: null, - response_scope: 'all', + // CLI is a local single-user DM — always respond. + engage_mode: 'pattern', + engage_pattern: '.', + sender_scope: 'all', + ignored_message_policy: 'drop', session_mode: 'shared', priority: 0, created_at: now, diff --git a/scripts/seed-discord.ts b/scripts/seed-discord.ts index 9aed1c538..3ea24e8ef 100644 --- a/scripts/seed-discord.ts +++ b/scripts/seed-discord.ts @@ -58,8 +58,12 @@ try { id: 'mga-discord', messaging_group_id: MESSAGING_GROUP_ID, agent_group_id: AGENT_GROUP_ID, - trigger_rules: null, - response_scope: 'all', + // Discord group channel → mention-sticky default. Mention once, stay + // subscribed to the thread. Admins can tune via /manage-channels. + engage_mode: 'mention-sticky', + engage_pattern: null, + sender_scope: 'all', + ignored_message_policy: 'drop', session_mode: 'shared', priority: 0, created_at: new Date().toISOString(), diff --git a/scripts/test-v2-channel-e2e.ts b/scripts/test-v2-channel-e2e.ts index fc0a5706e..6721ff086 100644 --- a/scripts/test-v2-channel-e2e.ts +++ b/scripts/test-v2-channel-e2e.ts @@ -53,8 +53,10 @@ createMessagingGroupAgent({ id: 'mga-chan', messaging_group_id: 'mg-chan', agent_group_id: 'ag-chan', - trigger_rules: null, - response_scope: 'all', + engage_mode: 'pattern', + engage_pattern: '.', + sender_scope: 'all', + ignored_message_policy: 'drop', session_mode: 'shared', priority: 0, created_at: new Date().toISOString(), @@ -105,7 +107,15 @@ registerChannelAdapter('mock', { factory: () => mockAdapter }); // Init channel adapters — this calls setup() with conversation configs from central DB await initChannelAdapters((adapter) => ({ - conversations: [{ platformId: 'mock-channel-1', agentGroupId: 'ag-chan', requiresTrigger: false, sessionMode: 'shared' }], + conversations: [ + { + platformId: 'mock-channel-1', + agentGroupId: 'ag-chan', + engageMode: 'pattern', + engagePattern: '.', + sessionMode: 'shared', + }, + ], onInbound(platformId, threadId, message) { routeInbound({ channelType: adapter.channelType, diff --git a/scripts/test-v2-host.ts b/scripts/test-v2-host.ts index b82bc99ff..2e49a3b8a 100644 --- a/scripts/test-v2-host.ts +++ b/scripts/test-v2-host.ts @@ -55,8 +55,10 @@ createMessagingGroupAgent({ id: 'mga-e2e', messaging_group_id: 'mg-e2e', agent_group_id: 'ag-e2e', - trigger_rules: null, - response_scope: 'all', + engage_mode: 'pattern', + engage_pattern: '.', + sender_scope: 'all', + ignored_message_policy: 'drop', session_mode: 'shared', priority: 0, created_at: new Date().toISOString(), diff --git a/src/channels/adapter.ts b/src/channels/adapter.ts index 55efde174..33f382548 100644 --- a/src/channels/adapter.ts +++ b/src/channels/adapter.ts @@ -9,8 +9,19 @@ export interface ConversationConfig { platformId: string; agentGroupId: string; - triggerPattern?: string; // regex string (for native channels) - requiresTrigger: boolean; + /** + * When does the agent engage on messages from this conversation? + * + * 'pattern' — regex test against message text; engagePattern='.' + * means "always" (match everything) + * 'mention' — fires only on @mention + * 'mention-sticky' — fires on @mention, then auto-subscribes to the thread + * and treats subsequent messages as engage-all. + * Threaded platforms only (Slack/Discord/Linear). + */ + engageMode: 'pattern' | 'mention' | 'mention-sticky'; + /** Regex source when engageMode='pattern'. '.' is the "always" sentinel. */ + engagePattern?: string | null; sessionMode: 'shared' | 'per-thread' | 'agent-shared'; } diff --git a/src/channels/channel-registry.test.ts b/src/channels/channel-registry.test.ts index 0e856f6cd..265a3721e 100644 --- a/src/channels/channel-registry.test.ts +++ b/src/channels/channel-registry.test.ts @@ -148,8 +148,10 @@ describe('channel + router integration', () => { id: 'mga-1', messaging_group_id: 'mg-1', agent_group_id: 'ag-1', - trigger_rules: null, - response_scope: 'all', + engage_mode: 'pattern', + engage_pattern: '.', + sender_scope: 'all', + ignored_message_policy: 'drop', session_mode: 'shared', priority: 0, created_at: now(), diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index 2d45b299b..593a2ad4b 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -71,23 +71,89 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter let chat: Chat; let state: SqliteStateAdapter; let setupConfig: ChannelSetup; - // NOTE: populated at setup() and updateConversations(), but currently not - // read by any inbound handler. When adapter-level gating lands (engage_mode - // applied here) or when dynamic group registration is added, this map goes - // stale after setup unless updateConversations() is actively called on every - // messaging_groups / messaging_group_agents mutation. See ACTION-ITEMS.md - // item 17. - let conversations: Map; + // Keyed by platformId. Multiple agents may be wired to the same + // conversation — this holds all their configs so the bridge can apply the + // most-permissive engage rule at gate time and only subscribe when at + // least one wiring requested 'mention-sticky'. + // + // STALENESS: populated at setup() and updateConversations(). If wirings + // change after setup, updateConversations() must be called to refresh + // (ACTION-ITEMS item 17). + let conversations: Map; let gatewayAbort: AbortController | null = null; - function buildConversationMap(configs: ConversationConfig[]): Map { - const map = new Map(); + function buildConversationMap(configs: ConversationConfig[]): Map { + const map = new Map(); for (const conv of configs) { - map.set(conv.platformId, conv); + const existing = map.get(conv.platformId); + if (existing) existing.push(conv); + else map.set(conv.platformId, [conv]); } return map; } + /** + * Should a message from (channelId, kind) engage any of the wired agents? + * + * - `mention` — engages only when the message actually @-mentions + * the bot (the bridge already sees it here because + * Chat SDK only forwards subscribed / mentioned / + * DM messages) + * - `mention-sticky` — same as `mention` for gating, PLUS we subscribe + * the thread so later messages arrive via the + * subscribed path and fall through to an + * engage-all style treatment + * - `pattern` — regex test against message text; `.` = always + * + * We take the union across wired agents — if any one of them would engage, + * the message goes through. Per-agent filtering after that happens in the + * host router (see src/router.ts pickAgents). + */ + function shouldEngage( + channelId: string, + source: 'subscribed' | 'mention' | 'dm', + text: string, + ): { engage: boolean; stickySubscribe: boolean } { + const configs = conversations.get(channelId); + // Unknown conversation — forward anyway (may be a new group that + // hasn't been registered yet; central routing will log + drop cleanly). + if (!configs || configs.length === 0) return { engage: true, stickySubscribe: false }; + + let engage = false; + let stickySubscribe = false; + + for (const cfg of configs) { + switch (cfg.engageMode) { + case 'mention': + if (source === 'mention' || source === 'dm') engage = true; + break; + case 'mention-sticky': + if (source === 'mention' || source === 'dm') { + engage = true; + stickySubscribe = true; + } else if (source === 'subscribed') { + // Thread was already subscribed on a prior mention — treat as + // engage-all so follow-ups in the thread reach the agent. + engage = true; + } + break; + case 'pattern': { + const pattern = cfg.engagePattern ?? '.'; + try { + if (pattern === '.' || new RegExp(pattern).test(text)) engage = true; + } catch { + // Invalid regex → fail open so the admin can see something and fix. + engage = true; + } + break; + } + } + if (engage && stickySubscribe) break; + } + + return { engage, stickySubscribe }; + } + async function messageToInbound(message: ChatMessage): Promise { // eslint-disable-next-line @typescript-eslint/no-explicit-any const serialized = message.toJSON() as Record; @@ -166,33 +232,54 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter logger: 'silent', }); - // Subscribed threads — forward all messages + // Subscribed threads — the conversation is already active (via prior + // mention-sticky engagement or admin wiring). Gate on engageMode so a + // plain 'mention' wiring doesn't keep firing after a one-off mention. chat.onSubscribedMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); + const text = typeof message.content === 'string' ? message.content : ''; + const decision = shouldEngage(channelId, 'subscribed', text); + if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); }); - // @mention in unsubscribed thread — forward + subscribe + // @mention in an unsubscribed thread — always engage; subscribe only + // if the wiring is 'mention-sticky'. chat.onNewMention(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); + const text = typeof message.content === 'string' ? message.content : ''; + const decision = shouldEngage(channelId, 'mention', text); + if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); - await thread.subscribe(); + if (decision.stickySubscribe) { + await thread.subscribe(); + } }); - // DMs — always forward + subscribe. Pass thread.id so sub-thread - // context carries through to delivery (Slack users can open threads - // inside a DM). The router collapses DM sub-threads to one session - // (is_group=0 short-circuits the per-thread escalation). + // DMs — apply engage rules too, but DMs typically default to pattern='.' + // at setup time so this is a pass-through in practice. sticky subscribe + // follows the same rule as a group mention. + // + // Thread id is passed through so sub-thread context reaches delivery + // (Slack users can open threads inside a DM). The router collapses DM + // sub-threads to one session (is_group=0 short-circuits the per-thread + // escalation). chat.onDirectMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); + const text = typeof message.content === 'string' ? message.content : ''; + const decision = shouldEngage(channelId, 'dm', text); log.info('Inbound DM received', { adapter: adapter.name, channelId, sender: (message.author as any)?.fullName ?? (message.author as any)?.userId ?? 'unknown', threadId: thread.id, + engage: decision.engage, }); + if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); - await thread.subscribe(); + if (decision.stickySubscribe) { + await thread.subscribe(); + } }); // Handle button clicks (ask_user_question) diff --git a/src/container-runner.ts b/src/container-runner.ts index 9764126a8..b357a0de4 100644 --- a/src/container-runner.ts +++ b/src/container-runner.ts @@ -9,7 +9,7 @@ import path from 'path'; import { OneCLI } from '@onecli-sh/sdk'; -import { CONTAINER_IMAGE, DATA_DIR, GROUPS_DIR, ONECLI_URL, TIMEZONE } from './config.js'; +import { CONTAINER_IMAGE, DATA_DIR, GROUPS_DIR, MAX_MESSAGES_PER_PROMPT, ONECLI_URL, TIMEZONE } from './config.js'; import { readContainerConfig, writeContainerConfig } from './container-config.js'; import { CONTAINER_RUNTIME_BIN, hostGatewayArgs, readonlyMountArgs, stopContainer } from './container-runtime.js'; import { getAgentGroup } from './db/agent-groups.js'; @@ -246,6 +246,9 @@ async function buildContainerArgs( } args.push('-e', `NANOCLAW_AGENT_GROUP_ID=${agentGroup.id}`); args.push('-e', `NANOCLAW_AGENT_GROUP_NAME=${agentGroup.name}`); + // Cap on how many pending messages reach one prompt. Accumulated context + // (trigger=0 rows) rides along with wake-eligible rows up to this cap. + args.push('-e', `NANOCLAW_MAX_MESSAGES_PER_PROMPT=${MAX_MESSAGES_PER_PROMPT}`); // Provider-contributed env vars (e.g. XDG_DATA_HOME, OPENCODE_*, NO_PROXY). if (providerContribution.env) { diff --git a/src/db/db-v2.test.ts b/src/db/db-v2.test.ts index f8689ebee..e0cebdf93 100644 --- a/src/db/db-v2.test.ts +++ b/src/db/db-v2.test.ts @@ -178,8 +178,10 @@ describe('messaging group agents', () => { id: 'mga-1', messaging_group_id: 'mg-1', agent_group_id: 'ag-1', - trigger_rules: null, - response_scope: 'all' as const, + engage_mode: 'pattern' as const, + engage_pattern: '.', + sender_scope: 'all' as const, + ignored_message_policy: 'drop' as const, session_mode: 'shared' as const, priority: 0, created_at: now(), @@ -229,7 +231,8 @@ describe('messaging group agents', () => { }); it('auto-creates an agent_destinations row for the wiring', async () => { - const { getDestinationByTarget, getDestinations } = await import('../modules/agent-to-agent/db/agent-destinations.js'); + const { getDestinationByTarget, getDestinations } = + await import('../modules/agent-to-agent/db/agent-destinations.js'); createMessagingGroupAgent(mga()); const dest = getDestinationByTarget('ag-1', 'channel', 'mg-1'); diff --git a/src/db/messaging-groups.ts b/src/db/messaging-groups.ts index 0c0ba224b..db12583ee 100644 --- a/src/db/messaging-groups.ts +++ b/src/db/messaging-groups.ts @@ -87,8 +87,16 @@ export function deleteMessagingGroup(id: string): void { export function createMessagingGroupAgent(mga: MessagingGroupAgent): void { getDb() .prepare( - `INSERT INTO messaging_group_agents (id, messaging_group_id, agent_group_id, trigger_rules, response_scope, session_mode, priority, created_at) - VALUES (@id, @messaging_group_id, @agent_group_id, @trigger_rules, @response_scope, @session_mode, @priority, @created_at)`, + `INSERT INTO messaging_group_agents ( + id, messaging_group_id, agent_group_id, + engage_mode, engage_pattern, sender_scope, ignored_message_policy, + session_mode, priority, created_at + ) + VALUES ( + @id, @messaging_group_id, @agent_group_id, + @engage_mode, @engage_pattern, @sender_scope, @ignored_message_policy, + @session_mode, @priority, @created_at + )`, ) .run(mga); @@ -160,7 +168,12 @@ export function getMessagingGroupAgent(id: string): MessagingGroupAgent | undefi export function updateMessagingGroupAgent( id: string, - updates: Partial>, + updates: Partial< + Pick< + MessagingGroupAgent, + 'engage_mode' | 'engage_pattern' | 'sender_scope' | 'ignored_message_policy' | 'session_mode' | 'priority' + > + >, ): void { const fields: string[] = []; const values: Record = { id }; diff --git a/src/db/migrations/010-engage-modes.ts b/src/db/migrations/010-engage-modes.ts new file mode 100644 index 000000000..4bf9798d4 --- /dev/null +++ b/src/db/migrations/010-engage-modes.ts @@ -0,0 +1,101 @@ +/** + * Replace `trigger_rules` (opaque JSON) + `response_scope` (conflated axis) + * with four explicit orthogonal columns on messaging_group_agents: + * + * engage_mode 'pattern' | 'mention' | 'mention-sticky' + * engage_pattern regex string (required when engage_mode='pattern'; + * '.' means "match everything" — the "always" flavor) + * sender_scope 'all' | 'known' + * ignored_message_policy 'drop' | 'accumulate' + * + * Backfill rules (applied per-row, reading the old JSON): + * - If trigger_rules.pattern is a non-empty string → engage_mode='pattern', + * engage_pattern = that value + * - Else if trigger_rules.requiresTrigger === false OR response_scope='all' + * → engage_mode='pattern', engage_pattern='.' + * - Else (requires trigger but no pattern specified) → engage_mode='mention' + * - sender_scope: 'known' when response_scope was 'allowlisted', 'all' otherwise + * - ignored_message_policy: 'drop' (conservative default; no old-schema analog) + */ +import type Database from 'better-sqlite3'; +import type { Migration } from './index.js'; + +import { log } from '../../log.js'; + +interface LegacyRow { + id: string; + trigger_rules: string | null; + response_scope: string | null; +} + +function backfill(row: LegacyRow): { + engage_mode: 'pattern' | 'mention' | 'mention-sticky'; + engage_pattern: string | null; + sender_scope: 'all' | 'known'; + ignored_message_policy: 'drop' | 'accumulate'; +} { + let parsed: Record = {}; + if (row.trigger_rules) { + try { + parsed = JSON.parse(row.trigger_rules) as Record; + } catch { + // Invalid JSON falls through to conservative defaults. + } + } + + const pattern = typeof parsed.pattern === 'string' && parsed.pattern.length > 0 ? (parsed.pattern as string) : null; + const requiresTrigger = parsed.requiresTrigger; + + let engage_mode: 'pattern' | 'mention' | 'mention-sticky' = 'mention'; + let engage_pattern: string | null = null; + if (pattern) { + engage_mode = 'pattern'; + engage_pattern = pattern; + } else if (requiresTrigger === false || row.response_scope === 'all') { + engage_mode = 'pattern'; + engage_pattern = '.'; + } + + const sender_scope: 'all' | 'known' = row.response_scope === 'allowlisted' ? 'known' : 'all'; + + return { engage_mode, engage_pattern, sender_scope, ignored_message_policy: 'drop' }; +} + +export const migration010: Migration = { + version: 10, + name: 'engage-modes', + up: (db: Database.Database) => { + // Add the four new columns alongside the existing two. SQLite ALTER ADD + // is cheap and non-rewriting. + db.exec(` + ALTER TABLE messaging_group_agents ADD COLUMN engage_mode TEXT; + ALTER TABLE messaging_group_agents ADD COLUMN engage_pattern TEXT; + ALTER TABLE messaging_group_agents ADD COLUMN sender_scope TEXT; + ALTER TABLE messaging_group_agents ADD COLUMN ignored_message_policy TEXT; + `); + + // Backfill existing rows in JS (parsing JSON per-row is painful in pure SQL). + const rows = db.prepare('SELECT id, trigger_rules, response_scope FROM messaging_group_agents').all() as LegacyRow[]; + const update = db.prepare( + `UPDATE messaging_group_agents + SET engage_mode = ?, + engage_pattern = ?, + sender_scope = ?, + ignored_message_policy = ? + WHERE id = ?`, + ); + for (const row of rows) { + const v = backfill(row); + update.run(v.engage_mode, v.engage_pattern, v.sender_scope, v.ignored_message_policy, row.id); + } + + // Drop the legacy columns. DROP COLUMN requires SQLite 3.35+ (2021); our + // better-sqlite3 ships a current build. + db.exec(` + ALTER TABLE messaging_group_agents DROP COLUMN trigger_rules; + ALTER TABLE messaging_group_agents DROP COLUMN response_scope; + `); + + log.info('engage-modes migration: backfilled rows', { count: rows.length }); + }, +}; diff --git a/src/db/migrations/index.ts b/src/db/migrations/index.ts index 3a877971b..d220688a0 100644 --- a/src/db/migrations/index.ts +++ b/src/db/migrations/index.ts @@ -6,6 +6,7 @@ import { migration002 } from './002-chat-sdk-state.js'; import { moduleAgentToAgentDestinations } from './module-agent-to-agent-destinations.js'; import { migration008 } from './008-dropped-messages.js'; import { migration009 } from './009-drop-pending-credentials.js'; +import { migration010 } from './010-engage-modes.js'; import { moduleApprovalsPendingApprovals } from './module-approvals-pending-approvals.js'; import { moduleApprovalsTitleOptions } from './module-approvals-title-options.js'; @@ -23,6 +24,7 @@ const migrations: Migration[] = [ moduleApprovalsTitleOptions, migration008, migration009, + migration010, ]; export function runMigrations(db: Database.Database): void { @@ -52,8 +54,8 @@ export function runMigrations(db: Database.Database): void { for (const m of pending) { db.transaction(() => { m.up(db); - const next = - (db.prepare('SELECT COALESCE(MAX(version), 0) + 1 AS v FROM schema_version').get() as { v: number }).v; + const next = (db.prepare('SELECT COALESCE(MAX(version), 0) + 1 AS v FROM schema_version').get() as { v: number }) + .v; db.prepare('INSERT INTO schema_version (version, name, applied) VALUES (?, ?, ?)').run( next, m.name, diff --git a/src/db/schema.ts b/src/db/schema.ts index 47d4c9fd0..9dd887e02 100644 --- a/src/db/schema.ts +++ b/src/db/schema.ts @@ -30,16 +30,23 @@ CREATE TABLE messaging_groups ( UNIQUE(channel_type, platform_id) ); --- Which agent groups handle which messaging groups +-- Which agent groups handle which messaging groups. +-- engage_mode / engage_pattern / sender_scope / ignored_message_policy are +-- the four orthogonal axes that together replace v1's opaque trigger_rules +-- JSON + response_scope enum. See docs/v1-vs-v2/ACTION-ITEMS.md item 1. CREATE TABLE messaging_group_agents ( - id TEXT PRIMARY KEY, - messaging_group_id TEXT NOT NULL REFERENCES messaging_groups(id), - agent_group_id TEXT NOT NULL REFERENCES agent_groups(id), - trigger_rules TEXT, - response_scope TEXT DEFAULT 'all', - session_mode TEXT DEFAULT 'shared', - priority INTEGER DEFAULT 0, - created_at TEXT NOT NULL, + id TEXT PRIMARY KEY, + messaging_group_id TEXT NOT NULL REFERENCES messaging_groups(id), + agent_group_id TEXT NOT NULL REFERENCES agent_groups(id), + engage_mode TEXT NOT NULL DEFAULT 'mention', + -- 'pattern' | 'mention' | 'mention-sticky' + engage_pattern TEXT, -- regex; required when engage_mode='pattern'; + -- '.' means "match every message" (the "always" flavor) + sender_scope TEXT NOT NULL DEFAULT 'all', -- 'all' | 'known' + ignored_message_policy TEXT NOT NULL DEFAULT 'drop', -- 'drop' | 'accumulate' + session_mode TEXT DEFAULT 'shared', + priority INTEGER DEFAULT 0, + created_at TEXT NOT NULL, UNIQUE(messaging_group_id, agent_group_id) ); @@ -138,6 +145,8 @@ CREATE TABLE IF NOT EXISTS messages_in ( recurrence TEXT, series_id TEXT, tries INTEGER DEFAULT 0, + trigger INTEGER NOT NULL DEFAULT 1, + -- 0 = accumulated context (don't wake), 1 = wake agent platform_id TEXT, channel_type TEXT, thread_id TEXT, diff --git a/src/db/session-db.ts b/src/db/session-db.ts index a73ca5c0c..aea255d19 100644 --- a/src/db/session-db.ts +++ b/src/db/session-db.ts @@ -95,13 +95,19 @@ export function insertMessage( content: string; processAfter: string | null; recurrence: string | null; + /** + * 1 = wake the agent (default); 0 = accumulate as context only. + * Host countDueMessages gates on this; container reads everything. + */ + trigger?: 0 | 1; }, ): void { db.prepare( - `INSERT INTO messages_in (id, seq, kind, timestamp, status, platform_id, channel_type, thread_id, content, process_after, recurrence, series_id) - VALUES (@id, @seq, @kind, @timestamp, 'pending', @platformId, @channelType, @threadId, @content, @processAfter, @recurrence, @id)`, + `INSERT INTO messages_in (id, seq, kind, timestamp, status, platform_id, channel_type, thread_id, content, process_after, recurrence, series_id, trigger) + VALUES (@id, @seq, @kind, @timestamp, 'pending', @platformId, @channelType, @threadId, @content, @processAfter, @recurrence, @id, @trigger)`, ).run({ ...message, + trigger: message.trigger ?? 1, seq: nextEvenSeq(db), }); } @@ -112,6 +118,7 @@ export function countDueMessages(db: Database.Database): number { .prepare( `SELECT COUNT(*) as count FROM messages_in WHERE status = 'pending' + AND trigger = 1 AND (process_after IS NULL OR datetime(process_after) <= datetime('now'))`, ) .get() as { count: number } @@ -169,9 +176,7 @@ export interface ProcessingClaim { /** Return processing_ack rows still in 'processing' with their claim timestamps. */ export function getProcessingClaims(outDb: Database.Database): ProcessingClaim[] { return outDb - .prepare( - "SELECT message_id, status_changed FROM processing_ack WHERE status = 'processing'", - ) + .prepare("SELECT message_id, status_changed FROM processing_ack WHERE status = 'processing'") .all() as ProcessingClaim[]; } @@ -262,10 +267,9 @@ export function migrateDeliveredTable(db: Database.Database): void { } } -// Adds series_id (groups all occurrences of a recurring task) to pre-existing -// messages_in tables. No-op on fresh installs where the column is in the schema. -// Backfills existing rows so cancel/pause/resume queries can rely on -// series_id IS NOT NULL. +// Adds columns added to messages_in after the initial v2 schema to +// pre-existing session DBs. No-op on fresh installs where the columns are +// in the baseline schema. Backfills existing rows so invariants hold. export function migrateMessagesInTable(db: Database.Database): void { const cols = new Set( (db.prepare("PRAGMA table_info('messages_in')").all() as Array<{ name: string }>).map((c) => c.name), @@ -275,4 +279,9 @@ export function migrateMessagesInTable(db: Database.Database): void { db.prepare('UPDATE messages_in SET series_id = id WHERE series_id IS NULL').run(); db.prepare('CREATE INDEX IF NOT EXISTS idx_messages_in_series ON messages_in(series_id)').run(); } + if (!cols.has('trigger')) { + // All pre-existing rows got written with the old "every inbound wakes + // the agent" semantics, so backfill 1 and default 1 for new inserts. + db.prepare('ALTER TABLE messages_in ADD COLUMN trigger INTEGER NOT NULL DEFAULT 1').run(); + } } diff --git a/src/db/sessions.ts b/src/db/sessions.ts index 01e48cd5c..bdca8a66e 100644 --- a/src/db/sessions.ts +++ b/src/db/sessions.ts @@ -27,6 +27,31 @@ export function findSession(messagingGroupId: string, threadId: string | null): .get(messagingGroupId, 'active') as Session | undefined; } +/** + * Session lookup scoped to a specific agent group. Needed when multiple + * agents are wired to the same messaging group + thread (fan-out) — the + * plain `findSession` would return whichever agent's session happened to + * be first and route to the wrong container. + */ +export function findSessionForAgent( + agentGroupId: string, + messagingGroupId: string, + threadId: string | null, +): Session | undefined { + if (threadId) { + return getDb() + .prepare( + "SELECT * FROM sessions WHERE agent_group_id = ? AND messaging_group_id = ? AND thread_id = ? AND status = 'active'", + ) + .get(agentGroupId, messagingGroupId, threadId) as Session | undefined; + } + return getDb() + .prepare( + "SELECT * FROM sessions WHERE agent_group_id = ? AND messaging_group_id = ? AND thread_id IS NULL AND status = 'active'", + ) + .get(agentGroupId, messagingGroupId) as Session | undefined; +} + /** Find an active session scoped to an agent group (ignoring messaging group). */ export function findSessionByAgentGroup(agentGroupId: string): Session | undefined { return getDb() diff --git a/src/host-core.test.ts b/src/host-core.test.ts index 7269164bc..33d37ff6f 100644 --- a/src/host-core.test.ts +++ b/src/host-core.test.ts @@ -199,8 +199,10 @@ describe('router', () => { id: 'mga-1', messaging_group_id: 'mg-1', agent_group_id: 'ag-1', - trigger_rules: null, - response_scope: 'all', + engage_mode: 'pattern', + engage_pattern: '.', + sender_scope: 'all', + ignored_message_policy: 'drop', session_mode: 'shared', priority: 0, created_at: now(), @@ -295,6 +297,106 @@ describe('router', () => { expect(rows).toHaveLength(2); }); + + it('fans out to every matching agent, each in its own session', async () => { + const { routeInbound } = await import('./router.js'); + const { wakeContainer } = await import('./container-runner.js'); + (wakeContainer as unknown as ReturnType).mockClear(); + + // Wire a second agent to the same messaging group. + createAgentGroup({ + id: 'ag-2', + name: 'Secondary Agent', + folder: 'secondary-agent', + agent_provider: null, + created_at: now(), + }); + createMessagingGroupAgent({ + id: 'mga-2', + messaging_group_id: 'mg-1', + agent_group_id: 'ag-2', + engage_mode: 'pattern', + engage_pattern: '.', + sender_scope: 'all', + ignored_message_policy: 'drop', + session_mode: 'shared', + priority: 0, + created_at: now(), + }); + + await routeInbound({ + channelType: 'discord', + platformId: 'chan-123', + threadId: null, + message: { id: 'msg-fan', kind: 'chat', content: JSON.stringify({ text: 'hello all' }), timestamp: now() }, + }); + + // Both agents should now have their own session and be woken. + expect(wakeContainer).toHaveBeenCalledTimes(2); + + const { getSessionsByAgentGroup } = await import('./db/sessions.js'); + expect(getSessionsByAgentGroup('ag-1')).toHaveLength(1); + expect(getSessionsByAgentGroup('ag-2')).toHaveLength(1); + }); + + it('accumulates without waking when engage fails + ignored_message_policy=accumulate', async () => { + const { routeInbound } = await import('./router.js'); + const { wakeContainer } = await import('./container-runner.js'); + (wakeContainer as unknown as ReturnType).mockClear(); + + // Replace the seed row with a mention-only wiring whose accumulate + // policy should store context even when the message doesn't mention us. + const { updateMessagingGroupAgent } = await import('./db/messaging-groups.js'); + updateMessagingGroupAgent('mga-1', { + engage_mode: 'mention', + ignored_message_policy: 'accumulate', + }); + + await routeInbound({ + channelType: 'discord', + platformId: 'chan-123', + threadId: null, + message: { + id: 'msg-nomatch', + kind: 'chat', + content: JSON.stringify({ text: 'no mention here' }), + timestamp: now(), + }, + }); + + expect(wakeContainer).not.toHaveBeenCalled(); + + const session = findSession('mg-1', null); + expect(session).toBeDefined(); + const db = new Database(inboundDbPath('ag-1', session!.id)); + const rows = db.prepare('SELECT id, trigger FROM messages_in').all() as Array<{ + id: string; + trigger: number; + }>; + db.close(); + expect(rows).toHaveLength(1); + expect(rows[0].trigger).toBe(0); + }); + + it('drops silently when engage fails + ignored_message_policy=drop', async () => { + const { routeInbound } = await import('./router.js'); + const { wakeContainer } = await import('./container-runner.js'); + (wakeContainer as unknown as ReturnType).mockClear(); + + const { updateMessagingGroupAgent } = await import('./db/messaging-groups.js'); + updateMessagingGroupAgent('mga-1', { engage_mode: 'mention' }); // drop is the default + + await routeInbound({ + channelType: 'discord', + platformId: 'chan-123', + threadId: null, + message: { id: 'msg-drop', kind: 'chat', content: JSON.stringify({ text: 'ignored' }), timestamp: now() }, + }); + + expect(wakeContainer).not.toHaveBeenCalled(); + // No session should have been created for this agent. + expect(findSession('mg-1', null)).toBeUndefined(); + }); }); describe('delivery', () => { diff --git a/src/index.ts b/src/index.ts index ffb273180..9bb51bebb 100644 --- a/src/index.ts +++ b/src/index.ts @@ -158,12 +158,11 @@ function buildConversationConfigs(channelType: string): ConversationConfig[] { for (const mg of groups) { const agents = getMessagingGroupAgents(mg.id); for (const agent of agents) { - const triggerRules = agent.trigger_rules ? JSON.parse(agent.trigger_rules) : null; configs.push({ platformId: mg.platform_id, agentGroupId: agent.agent_group_id, - triggerPattern: triggerRules?.pattern, - requiresTrigger: triggerRules?.requiresTrigger ?? false, + engageMode: agent.engage_mode, + engagePattern: agent.engage_pattern, sessionMode: agent.session_mode, }); } diff --git a/src/modules/permissions/index.ts b/src/modules/permissions/index.ts index e7cc282c8..ca97f8f86 100644 --- a/src/modules/permissions/index.ts +++ b/src/modules/permissions/index.ts @@ -16,9 +16,15 @@ * access gate is not registered and core defaults to allow-all. */ import { recordDroppedMessage } from '../../db/dropped-messages.js'; -import { setAccessGate, setSenderResolver, type AccessGateResult, type InboundEvent } from '../../router.js'; +import { + setAccessGate, + setSenderResolver, + setSenderScopeGate, + type AccessGateResult, + type InboundEvent, +} from '../../router.js'; import { log } from '../../log.js'; -import type { MessagingGroup } from '../../types.js'; +import type { MessagingGroup, MessagingGroupAgent } from '../../types.js'; import { canAccessAgentGroup } from './access.js'; import { getUser, upsertUser } from './db/users.js'; @@ -132,3 +138,21 @@ setAccessGate((event, userId, mg, agentGroupId): AccessGateResult => { handleUnknownSender(mg, userId, agentGroupId, decision.reason, event); return { allowed: false, reason: decision.reason }; }); + +/** + * Per-wiring sender-scope enforcement. Stricter than the messaging-group + * `unknown_sender_policy` — a wiring can require `sender_scope='known'` + * (explicit owner / admin / member) even on a 'public' messaging group. + * + * 'all' is a no-op; any sender passes. 'known' requires a userId that + * canAccessAgentGroup accepts (owner, admin, or group member). + */ +setSenderScopeGate( + (_event: InboundEvent, userId: string | null, _mg: MessagingGroup, agent: MessagingGroupAgent): AccessGateResult => { + if (agent.sender_scope === 'all') return { allowed: true }; + if (!userId) return { allowed: false, reason: 'unknown_user_scope' }; + const decision = canAccessAgentGroup(userId, agent.agent_group_id); + if (decision.allowed) return { allowed: true }; + return { allowed: false, reason: `sender_scope_${decision.reason}` }; + }, +); diff --git a/src/router.ts b/src/router.ts index 8971f7f50..9b54cb28e 100644 --- a/src/router.ts +++ b/src/router.ts @@ -18,14 +18,16 @@ * for policy refusals. */ import { getChannelAdapter } from './channels/channel-registry.js'; +import { getAgentGroup } from './db/agent-groups.js'; import { recordDroppedMessage } from './db/dropped-messages.js'; import { getMessagingGroupByPlatform, createMessagingGroup, getMessagingGroupAgents } from './db/messaging-groups.js'; +import { findSessionForAgent } from './db/sessions.js'; import { startTypingRefresh } from './modules/typing/index.js'; import { log } from './log.js'; import { resolveSession, writeSessionMessage } from './session-manager.js'; import { wakeContainer } from './container-runner.js'; import { getSession } from './db/sessions.js'; -import type { MessagingGroup, MessagingGroupAgent } from './types.js'; +import type { AgentGroup, MessagingGroup, MessagingGroupAgent } from './types.js'; function generateId(): string { return `msg-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; @@ -89,6 +91,29 @@ export function setAccessGate(fn: AccessGateFn): void { accessGate = fn; } +/** + * Per-wiring sender-scope hook. Runs alongside the access gate for each + * agent that would otherwise engage — lets the permissions module enforce + * `sender_scope='known'` on wirings that are stricter than the messaging + * group's `unknown_sender_policy`. When the hook isn't registered (module + * not installed), sender_scope is a no-op. + */ +export type SenderScopeGateFn = ( + event: InboundEvent, + userId: string | null, + mg: MessagingGroup, + agent: MessagingGroupAgent, +) => AccessGateResult; + +let senderScopeGate: SenderScopeGateFn | null = null; + +export function setSenderScopeGate(fn: SenderScopeGateFn): void { + if (senderScopeGate) { + log.warn('Sender-scope gate overwritten'); + } + senderScopeGate = fn; +} + function safeParseContent(raw: string): { text?: string; sender?: string; senderId?: string } { try { return JSON.parse(raw); @@ -158,91 +183,167 @@ export async function routeInbound(event: InboundEvent): Promise { return; } - const match = pickAgent(agents, event); - if (!match) { - log.warn('MESSAGE DROPPED — no agent matched trigger rules', { - messagingGroupId: mg.id, - channelType: event.channelType, - }); - const parsed = safeParseContent(event.message.content); + // 4. Fan-out: evaluate each wired agent independently against engage_mode, + // sender_scope, and access gate. An agent that engages gets its own + // session and container wake. An agent that declines but has + // ignored_message_policy='accumulate' still gets the message stored in + // its session (trigger=0) so the context is available when it does + // engage later. Drop policy = skip silently. + const parsed = safeParseContent(event.message.content); + const messageText = parsed.text ?? ''; + + let engagedCount = 0; + let accumulatedCount = 0; + + for (const agent of agents) { + const agentGroup = getAgentGroup(agent.agent_group_id); + if (!agentGroup) continue; + + const engages = evaluateEngage(agent, agentGroup, messageText, mg, event.threadId); + + const accessOk = engages && (!accessGate || accessGate(event, userId, mg, agent.agent_group_id).allowed); + const scopeOk = engages && (!senderScopeGate || senderScopeGate(event, userId, mg, agent).allowed); + + if (engages && accessOk && scopeOk) { + await deliverToAgent(agent, agentGroup, mg, event, userId, adapter?.supportsThreads === true, true); + engagedCount++; + } else if (agent.ignored_message_policy === 'accumulate') { + await deliverToAgent(agent, agentGroup, mg, event, userId, adapter?.supportsThreads === true, false); + accumulatedCount++; + } else { + log.debug('Message not engaged for agent (drop policy)', { + agentGroupId: agent.agent_group_id, + engage_mode: agent.engage_mode, + engages, + accessOk, + scopeOk, + }); + } + } + + if (engagedCount + accumulatedCount === 0) { recordDroppedMessage({ channel_type: event.channelType, platform_id: event.platformId, user_id: userId, sender_name: parsed.sender ?? null, - reason: 'no_trigger_match', + reason: 'no_agent_engaged', messaging_group_id: mg.id, agent_group_id: null, }); - return; } +} - // 4. Access gate (if the permissions module is loaded). Otherwise - // allow-all. - if (accessGate) { - const result = accessGate(event, userId, mg, match.agent_group_id); - if (!result.allowed) { - log.info('MESSAGE DROPPED — access gate refused', { - messagingGroupId: mg.id, - agentGroupId: match.agent_group_id, - userId, - reason: result.reason, - }); - return; +/** + * Decide whether a given wired agent should engage on this message. + * + * 'pattern' — regex test on text; '.' = always + * 'mention' — bot must be @-mentioned by its agent-group name + * 'mention-sticky' — @mention OR an active per-thread session already + * exists for this (agent, mg, thread). The session + * existence IS our subscription state; once a thread + * has engaged us once, follow-ups arrive with no + * mention and should still fire. + */ +function evaluateEngage( + agent: MessagingGroupAgent, + agentGroup: AgentGroup, + text: string, + mg: MessagingGroup, + threadId: string | null, +): boolean { + switch (agent.engage_mode) { + case 'pattern': { + const pat = agent.engage_pattern ?? '.'; + if (pat === '.') return true; + try { + return new RegExp(pat).test(text); + } catch { + // Bad regex: fail open so admin sees the agent responding + can fix. + return true; + } } + case 'mention': + return hasMention(text, agentGroup.name); + case 'mention-sticky': { + if (hasMention(text, agentGroup.name)) return true; + // Sticky follow-up: session already exists for this (agent, mg, thread) + // — the thread was activated before, keep firing. + if (mg.is_group === 0) return false; // DMs never use mention-sticky sensibly + const existing = findSessionForAgent(agent.agent_group_id, mg.id, threadId); + return existing !== undefined; + } + default: + return false; } +} - // 5. Resolve or create session. - // - // Adapter thread policy overrides the wiring's session_mode: if the adapter - // is threaded, each thread gets its own session regardless of what the - // wiring says. Agent-shared is preserved because it expresses a - // cross-channel intent the adapter can't know about. - // - // Exception: DMs (is_group=0). Sub-threads within a DM are a UX affordance, - // not a conversation boundary — treat the whole DM as one session and let - // threadId flow through to delivery so replies land in the right sub-thread. - let effectiveSessionMode = match.session_mode; - if (adapter && adapter.supportsThreads && effectiveSessionMode !== 'agent-shared' && mg.is_group !== 0) { +function hasMention(text: string, agentName: string): boolean { + if (!agentName) return false; + const escaped = agentName.replace(/[.*+?^${}()|[\]\\]/g, '\\$&'); + return new RegExp(`@${escaped}\\b`, 'i').test(text); +} + +async function deliverToAgent( + agent: MessagingGroupAgent, + agentGroup: AgentGroup, + mg: MessagingGroup, + event: InboundEvent, + userId: string | null, + adapterSupportsThreads: boolean, + wake: boolean, +): Promise { + // Apply the adapter thread policy: threaded adapter in a group chat → + // per-thread session regardless of wiring. agent-shared preserved (it's + // a cross-channel directive the adapter doesn't know about). DMs collapse + // sub-threads to one session (is_group=0 short-circuit). + let effectiveSessionMode = agent.session_mode; + if (adapterSupportsThreads && effectiveSessionMode !== 'agent-shared' && mg.is_group !== 0) { effectiveSessionMode = 'per-thread'; } - const { session, created } = resolveSession(match.agent_group_id, mg.id, event.threadId, effectiveSessionMode); - // 6. Write message to session DB + const { session, created } = resolveSession(agent.agent_group_id, mg.id, event.threadId, effectiveSessionMode); + writeSessionMessage(session.agent_group_id, session.id, { - id: event.message.id || generateId(), + id: messageIdForAgent(event.message.id, agent.agent_group_id), kind: event.message.kind, timestamp: event.message.timestamp, platformId: event.platformId, channelType: event.channelType, threadId: event.threadId, content: event.message.content, + trigger: wake ? 1 : 0, }); log.info('Message routed', { sessionId: session.id, - agentGroup: match.agent_group_id, + agentGroup: agent.agent_group_id, + engage_mode: agent.engage_mode, kind: event.message.kind, userId, + wake, created, + agentGroupName: agentGroup.name, }); - // 7. Show typing indicator while the agent processes. - startTypingRefresh(session.id, session.agent_group_id, event.channelType, event.platformId, event.threadId); - - // 8. Wake container - const freshSession = getSession(session.id); - if (freshSession) { - await wakeContainer(freshSession); + if (wake) { + // Typing indicator + wake are only for the engaged branch; accumulated + // messages sit silently until a real trigger fires. + startTypingRefresh(session.id, session.agent_group_id, event.channelType, event.platformId, event.threadId); + const freshSession = getSession(session.id); + if (freshSession) { + await wakeContainer(freshSession); + } } } /** - * Pick the matching agent for an inbound event. - * Currently: highest priority agent. Future: trigger rule matching. + * When fanning out, the same inbound message lands in multiple per-agent + * session DBs. messages_in.id is PRIMARY KEY, so reuse of the raw id would + * collide across sessions (or, more subtly, within one session if re-routed + * after a retry). Namespace by agent_group_id to keep ids unique per session. */ -function pickAgent(agents: MessagingGroupAgent[], _event: InboundEvent): MessagingGroupAgent | null { - // Agents are already ordered by priority DESC from the DB query - // TODO: apply trigger_rules matching (pattern, mentionOnly, etc.) - return agents[0] ?? null; +function messageIdForAgent(baseId: string | undefined, agentGroupId: string): string { + const id = baseId && baseId.length > 0 ? baseId : generateId(); + return `${id}:${agentGroupId}`; } diff --git a/src/session-manager.ts b/src/session-manager.ts index 7aaef24f5..2a5ac1d8c 100644 --- a/src/session-manager.ts +++ b/src/session-manager.ts @@ -17,7 +17,14 @@ import path from 'path'; import type { OutboundFile } from './channels/adapter.js'; import { DATA_DIR } from './config.js'; import { getMessagingGroup } from './db/messaging-groups.js'; -import { createSession, findSession, findSessionByAgentGroup, getSession, updateSession } from './db/sessions.js'; +import { + createSession, + findSession, + findSessionByAgentGroup, + findSessionForAgent, + getSession, + updateSession, +} from './db/sessions.js'; import { ensureSchema, openInboundDb as openInboundDbRaw, @@ -89,7 +96,9 @@ export function resolveSession( } } else if (messagingGroupId) { const lookupThreadId = sessionMode === 'shared' ? null : threadId; - const existing = findSession(messagingGroupId, lookupThreadId); + // Scope lookup by agent_group_id so fan-out to multiple agents in the + // same chat doesn't accidentally deliver to the wrong agent's session. + const existing = findSessionForAgent(agentGroupId, messagingGroupId, lookupThreadId); if (existing) { return { session: existing, created: false }; } @@ -187,6 +196,13 @@ export function writeSessionMessage( content: string; processAfter?: string | null; recurrence?: string | null; + /** + * 1 = this message should wake the agent (the default); 0 = accumulate + * as context only, don't wake. Host's countDueMessages gates on this + * column; the container still reads all prior messages as context when + * a trigger-1 message does arrive. + */ + trigger?: 0 | 1; }, ): void { // Extract base64 attachment data, save to inbox, replace with file paths @@ -204,6 +220,7 @@ export function writeSessionMessage( content, processAfter: message.processAfter ?? null, recurrence: message.recurrence ?? null, + trigger: message.trigger ?? 1, }); } finally { db.close(); diff --git a/src/types.ts b/src/types.ts index ad14441e1..b2674dae5 100644 --- a/src/types.ts +++ b/src/types.ts @@ -67,12 +67,23 @@ export interface UserDm { resolved_at: string; } +export type EngageMode = 'pattern' | 'mention' | 'mention-sticky'; +export type SenderScope = 'all' | 'known'; +export type IgnoredMessagePolicy = 'drop' | 'accumulate'; + export interface MessagingGroupAgent { id: string; messaging_group_id: string; agent_group_id: string; - trigger_rules: string | null; // JSON: { pattern, mentionOnly, excludeSenders, includeSenders } - response_scope: 'all' | 'triggered' | 'allowlisted'; + engage_mode: EngageMode; + /** + * Regex source string used when engage_mode='pattern'. `'.'` is the sentinel + * for "match every message" (the "always" flavor). Ignored for 'mention' / + * 'mention-sticky' modes. + */ + engage_pattern: string | null; + sender_scope: SenderScope; + ignored_message_policy: IgnoredMessagePolicy; session_mode: 'shared' | 'per-thread' | 'agent-shared'; priority: number; created_at: string; From 622a370815b3ac9ef499005d0713ff9afb114d23 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 01:36:11 +0300 Subject: [PATCH 21/95] feat(permissions): unknown-sender request_approval flow + flipped default policy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When an unknown sender writes into a wired messaging group, surface the situation to an admin instead of silently dropping. Flow: 1. Router → access gate → handleUnknownSender (policy='request_approval') 2. Fire-and-forget requestSenderApproval: pickApprover + pickApprovalDelivery pick a reachable admin DM; deliver an Approve / Deny card; insert a pending_sender_approvals row carrying the original InboundEvent JSON. 3. In-flight dedup: UNIQUE(messaging_group_id, sender_identity) — a retry from the same stranger while pending is silently dropped, not re-carded. 4. Admin clicks → Chat SDK bridge → onAction → host response-registry. The new handleSenderApprovalResponse in the permissions module claims responses whose questionId matches a pending_sender_approvals row. 5. approve: addMember(stranger, agent_group) + replay the stored event via routeInbound — the second attempt clears the gate because the user is now known. 6. deny: delete the pending row. No denial persistence (ACTION-ITEMS item 5 decision) — a future attempt triggers a fresh card. Schema: - Migration 011 adds pending_sender_approvals (id, mg_id, agent_group_id, sender_identity, sender_name, original_message JSON, approver_user_id, created_at, UNIQUE(mg_id, sender_identity)). - Also flips messaging_groups.unknown_sender_policy default from 'strict' to 'request_approval' (rebuild-table). Existing rows unchanged — only the default applied to new rows flips. - Router auto-create for unknown platform/chat drops the hardcoded 'strict' override; schema default applies. - src/db/schema.ts reference updated to match. Why default-flip: users wire their DM during setup and don't discover that 'strict' means "silent drop of everyone not in user_roles/members". The approval flow is the safe default — the admin sees the stranger, explicitly decides. 'public' stays opt-in for truly open channels. Failure modes (row NOT created so a future attempt can try again): - No eligible approver configured (fresh install before first owner). - No reachable DM for any approver. - Delivery adapter missing. Tests (src/modules/permissions/sender-approval.test.ts, 4 cases): - First unknown message → card delivered + row created - Retry while pending → dedup'd (1 card, 1 row) - Approve → member added + message replayed + container woken - Deny → row cleared + no member added Closes: ACTION-ITEMS item 5. Co-Authored-By: Claude Opus 4.7 (1M context) --- .../011-pending-sender-approvals.ts | 57 ++++ src/db/migrations/index.ts | 2 + src/db/schema.ts | 22 +- .../db/pending-sender-approvals.ts | 59 ++++ src/modules/permissions/index.ts | 87 +++++- .../permissions/sender-approval.test.ts | 265 ++++++++++++++++++ src/modules/permissions/sender-approval.ts | 152 ++++++++++ src/router.ts | 5 +- 8 files changed, 645 insertions(+), 4 deletions(-) create mode 100644 src/db/migrations/011-pending-sender-approvals.ts create mode 100644 src/modules/permissions/db/pending-sender-approvals.ts create mode 100644 src/modules/permissions/sender-approval.test.ts create mode 100644 src/modules/permissions/sender-approval.ts diff --git a/src/db/migrations/011-pending-sender-approvals.ts b/src/db/migrations/011-pending-sender-approvals.ts new file mode 100644 index 000000000..cb4703950 --- /dev/null +++ b/src/db/migrations/011-pending-sender-approvals.ts @@ -0,0 +1,57 @@ +/** + * Unknown-sender approval flow. When `unknown_sender_policy = 'request_approval'` + * a non-member message triggers a card to the most appropriate admin. An + * in-flight entry in this table dedups concurrent attempts from the same + * sender; the row is cleared on approve / deny. + * + * Also flips the `messaging_groups.unknown_sender_policy` default from 'strict' + * to 'request_approval' so fresh wirings don't silently swallow messages from + * users the admin hasn't added yet. Existing rows are left as-is (silent + * upgrade would change established behavior without the admin asking for it). + */ +import type Database from 'better-sqlite3'; +import type { Migration } from './index.js'; + +export const migration011: Migration = { + version: 11, + name: 'pending-sender-approvals', + up: (db: Database.Database) => { + db.exec(` + CREATE TABLE IF NOT EXISTS pending_sender_approvals ( + id TEXT PRIMARY KEY, + messaging_group_id TEXT NOT NULL REFERENCES messaging_groups(id), + agent_group_id TEXT NOT NULL REFERENCES agent_groups(id), + sender_identity TEXT NOT NULL, -- namespaced user id (channel_type:handle) + sender_name TEXT, + original_message TEXT NOT NULL, -- JSON serialized InboundEvent + approver_user_id TEXT NOT NULL, + created_at TEXT NOT NULL, + UNIQUE(messaging_group_id, sender_identity) + ); + CREATE INDEX IF NOT EXISTS idx_pending_sender_approvals_mg + ON pending_sender_approvals(messaging_group_id); + `); + + // Default-flip: fresh messaging_groups default to request_approval instead + // of silently dropping. SQLite doesn't support modifying column DEFAULTs + // in place, so we rebuild the table via the classic rename-copy-drop + // pattern. Existing rows keep their current unknown_sender_policy value. + db.exec(` + CREATE TABLE messaging_groups_new ( + id TEXT PRIMARY KEY, + channel_type TEXT NOT NULL, + platform_id TEXT NOT NULL, + name TEXT, + is_group INTEGER DEFAULT 0, + unknown_sender_policy TEXT NOT NULL DEFAULT 'request_approval', + created_at TEXT NOT NULL, + UNIQUE(channel_type, platform_id) + ); + INSERT INTO messaging_groups_new + SELECT id, channel_type, platform_id, name, is_group, unknown_sender_policy, created_at + FROM messaging_groups; + DROP TABLE messaging_groups; + ALTER TABLE messaging_groups_new RENAME TO messaging_groups; + `); + }, +}; diff --git a/src/db/migrations/index.ts b/src/db/migrations/index.ts index d220688a0..1015f405e 100644 --- a/src/db/migrations/index.ts +++ b/src/db/migrations/index.ts @@ -7,6 +7,7 @@ import { moduleAgentToAgentDestinations } from './module-agent-to-agent-destinat import { migration008 } from './008-dropped-messages.js'; import { migration009 } from './009-drop-pending-credentials.js'; import { migration010 } from './010-engage-modes.js'; +import { migration011 } from './011-pending-sender-approvals.js'; import { moduleApprovalsPendingApprovals } from './module-approvals-pending-approvals.js'; import { moduleApprovalsTitleOptions } from './module-approvals-title-options.js'; @@ -25,6 +26,7 @@ const migrations: Migration[] = [ migration008, migration009, migration010, + migration011, ]; export function runMigrations(db: Database.Database): void { diff --git a/src/db/schema.ts b/src/db/schema.ts index 9dd887e02..aa33fae1e 100644 --- a/src/db/schema.ts +++ b/src/db/schema.ts @@ -25,7 +25,11 @@ CREATE TABLE messaging_groups ( platform_id TEXT NOT NULL, name TEXT, is_group INTEGER DEFAULT 0, - unknown_sender_policy TEXT NOT NULL DEFAULT 'strict', -- 'strict' | 'request_approval' | 'public' + unknown_sender_policy TEXT NOT NULL DEFAULT 'request_approval', + -- 'strict' | 'request_approval' | 'public' + -- Default is request_approval so silent drops don't + -- mystery-break users who wired their DM during + -- setup and haven't explicitly marked it public. created_at TEXT NOT NULL, UNIQUE(channel_type, platform_id) ); @@ -123,6 +127,22 @@ CREATE TABLE pending_questions ( options_json TEXT NOT NULL, created_at TEXT NOT NULL ); + +-- Pending approvals for unknown senders (unknown_sender_policy='request_approval'). +-- In-flight dedup via UNIQUE(messaging_group_id, sender_identity): a second +-- message from the same unknown sender while a card is pending is silently +-- dropped instead of spamming the admin. +CREATE TABLE pending_sender_approvals ( + id TEXT PRIMARY KEY, + messaging_group_id TEXT NOT NULL REFERENCES messaging_groups(id), + agent_group_id TEXT NOT NULL REFERENCES agent_groups(id), + sender_identity TEXT NOT NULL, -- namespaced user id (channel_type:handle) + sender_name TEXT, + original_message TEXT NOT NULL, -- JSON of the original InboundEvent + approver_user_id TEXT NOT NULL, + created_at TEXT NOT NULL, + UNIQUE(messaging_group_id, sender_identity) +); `; /** diff --git a/src/modules/permissions/db/pending-sender-approvals.ts b/src/modules/permissions/db/pending-sender-approvals.ts new file mode 100644 index 000000000..9f7e3a4c8 --- /dev/null +++ b/src/modules/permissions/db/pending-sender-approvals.ts @@ -0,0 +1,59 @@ +/** + * CRUD for pending_sender_approvals — the in-flight state for the + * request_approval unknown-sender flow. Rows are created when an unknown + * sender writes into a wired messaging group with that policy, and are + * deleted on admin approve (after adding the user as a member) or deny. + * + * UNIQUE(messaging_group_id, sender_identity) enforces in-flight dedup: + * a retry / second message from the same unknown sender while a card is + * still pending is silently dropped instead of spamming the admin. + */ +import { getDb } from '../../../db/connection.js'; + +export interface PendingSenderApproval { + id: string; + messaging_group_id: string; + agent_group_id: string; + sender_identity: string; + sender_name: string | null; + original_message: string; + approver_user_id: string; + created_at: string; +} + +export function createPendingSenderApproval(row: PendingSenderApproval): void { + getDb() + .prepare( + `INSERT INTO pending_sender_approvals ( + id, messaging_group_id, agent_group_id, sender_identity, + sender_name, original_message, approver_user_id, created_at + ) + VALUES ( + @id, @messaging_group_id, @agent_group_id, @sender_identity, + @sender_name, @original_message, @approver_user_id, @created_at + )`, + ) + .run(row); +} + +export function getPendingSenderApproval(id: string): PendingSenderApproval | undefined { + return getDb() + .prepare('SELECT * FROM pending_sender_approvals WHERE id = ?') + .get(id) as PendingSenderApproval | undefined; +} + +export function hasInFlightSenderApproval( + messagingGroupId: string, + senderIdentity: string, +): boolean { + const row = getDb() + .prepare( + 'SELECT 1 AS x FROM pending_sender_approvals WHERE messaging_group_id = ? AND sender_identity = ?', + ) + .get(messagingGroupId, senderIdentity) as { x: number } | undefined; + return row !== undefined; +} + +export function deletePendingSenderApproval(id: string): void { + getDb().prepare('DELETE FROM pending_sender_approvals WHERE id = ?').run(id); +} diff --git a/src/modules/permissions/index.ts b/src/modules/permissions/index.ts index ca97f8f86..1d505b68d 100644 --- a/src/modules/permissions/index.ts +++ b/src/modules/permissions/index.ts @@ -17,16 +17,24 @@ */ import { recordDroppedMessage } from '../../db/dropped-messages.js'; import { + routeInbound, setAccessGate, setSenderResolver, setSenderScopeGate, type AccessGateResult, type InboundEvent, } from '../../router.js'; +import { registerResponseHandler, type ResponsePayload } from '../../response-registry.js'; import { log } from '../../log.js'; import type { MessagingGroup, MessagingGroupAgent } from '../../types.js'; import { canAccessAgentGroup } from './access.js'; +import { addMember } from './db/agent-group-members.js'; +import { + deletePendingSenderApproval, + getPendingSenderApproval, +} from './db/pending-sender-approvals.js'; import { getUser, upsertUser } from './db/users.js'; +import { requestSenderApproval } from './sender-approval.js'; function extractAndUpsertUser(event: InboundEvent): string | null { let content: Record; @@ -82,11 +90,12 @@ function handleUnknownSender( event: InboundEvent, ): void { const parsed = safeParseContent(event.message.content); + const senderName = parsed.sender ?? null; const dropRecord = { channel_type: event.channelType, platform_id: event.platformId, user_id: userId, - sender_name: parsed.sender ?? null, + sender_name: senderName, reason: `unknown_sender_${mg.unknown_sender_policy}`, messaging_group_id: mg.id, agent_group_id: agentGroupId, @@ -104,13 +113,27 @@ function handleUnknownSender( } if (mg.unknown_sender_policy === 'request_approval') { - log.info('MESSAGE DROPPED — unknown sender (approval flow TODO)', { + log.info('MESSAGE DROPPED — unknown sender (approval requested)', { messagingGroupId: mg.id, agentGroupId, userId, accessReason, }); recordDroppedMessage(dropRecord); + // Fire-and-forget; pick-approver + delivery + row-insert are all async. + // If it fails it logs internally — the user's message still stays dropped + // either way. Requires a resolved userId (senderResolver populates users + // row before the gate fires); if we got here without one, there's nothing + // to identify for approval and we just stay in the "silent strict" branch. + if (userId) { + requestSenderApproval({ + messagingGroupId: mg.id, + agentGroupId, + senderIdentity: userId, + senderName, + event, + }).catch((err) => log.error('Sender-approval flow threw', { err })); + } return; } @@ -156,3 +179,63 @@ setSenderScopeGate( return { allowed: false, reason: `sender_scope_${decision.reason}` }; }, ); + +/** + * Response handler for the unknown-sender approval card. + * + * Claim rule: questionId matches a row in pending_sender_approvals. If no + * such row, return false so the next handler (approvals module, OneCLI, + * interactive) gets a shot. + * + * Approve: add the sender to agent_group_members + re-invoke routeInbound + * with the stored event. The second routing attempt clears the gate because + * the user is now a member. + * + * Deny: delete the row (no "deny list" — a future message re-triggers a + * fresh card per ACTION-ITEMS item 5 "no denial persistence"). + */ +async function handleSenderApprovalResponse(payload: ResponsePayload): Promise { + const row = getPendingSenderApproval(payload.questionId); + if (!row) return false; + + const approverId = payload.userId ?? row.approver_user_id; + const approved = payload.value === 'approve'; + + if (approved) { + addMember({ + user_id: row.sender_identity, + agent_group_id: row.agent_group_id, + added_by: approverId, + added_at: new Date().toISOString(), + }); + log.info('Unknown sender approved — member added', { + approvalId: row.id, + senderIdentity: row.sender_identity, + agentGroupId: row.agent_group_id, + approverId, + }); + + // Clear the pending row BEFORE re-routing so the gate check on the + // second attempt doesn't see the in-flight row and short-circuit. + deletePendingSenderApproval(row.id); + + try { + const event = JSON.parse(row.original_message) as InboundEvent; + await routeInbound(event); + } catch (err) { + log.error('Failed to replay message after sender approval', { approvalId: row.id, err }); + } + return true; + } + + log.info('Unknown sender denied', { + approvalId: row.id, + senderIdentity: row.sender_identity, + agentGroupId: row.agent_group_id, + approverId, + }); + deletePendingSenderApproval(row.id); + return true; +} + +registerResponseHandler(handleSenderApprovalResponse); diff --git a/src/modules/permissions/sender-approval.test.ts b/src/modules/permissions/sender-approval.test.ts new file mode 100644 index 000000000..a02c74257 --- /dev/null +++ b/src/modules/permissions/sender-approval.test.ts @@ -0,0 +1,265 @@ +/** + * Integration tests for the unknown-sender request_approval flow + * (ACTION-ITEMS item 5). + * + * Covers: + * - request_approval policy fires `requestSenderApproval` on first unknown + * message from a sender + * - In-flight dedup: second message from the same sender while pending is + * silently dropped (no second card, no second row) + * - Approve path: member added, original message replayed via routeInbound, + * container woken + * - Deny path: pending row deleted, no member added + */ +import fs from 'fs'; +import { beforeEach, afterEach, describe, expect, it, vi } from 'vitest'; + +import { initTestDb, closeDb, runMigrations } from '../../db/index.js'; +import { createAgentGroup } from '../../db/agent-groups.js'; +import { createMessagingGroup, createMessagingGroupAgent } from '../../db/messaging-groups.js'; +import { upsertUser } from './db/users.js'; +import { grantRole } from './db/user-roles.js'; + +// Mock container runner — prevent actual docker spawn. +vi.mock('../../container-runner.js', () => ({ + wakeContainer: vi.fn().mockResolvedValue(undefined), + isContainerRunning: vi.fn().mockReturnValue(false), + getActiveContainerCount: vi.fn().mockReturnValue(0), + killContainer: vi.fn(), +})); + +// Mock delivery adapter — record card deliveries for assertions. +const deliverMock = vi.fn().mockResolvedValue('plat-msg-id'); +vi.mock('../../delivery.js', () => ({ + getDeliveryAdapter: () => ({ + deliver: deliverMock, + }), +})); + +// Mock ensureUserDm to return the approver's existing messaging group +// instead of hitting a real openDM RPC. +vi.mock('./user-dm.js', () => ({ + ensureUserDm: vi.fn(async (userId: string) => { + const { getDb } = await import('../../db/connection.js'); + const row = getDb() + .prepare( + `SELECT mg.* FROM messaging_groups mg + JOIN user_dms ud ON ud.messaging_group_id = mg.id + WHERE ud.user_id = ?`, + ) + .get(userId); + return row; + }), +})); + +vi.mock('../../config.js', async () => { + const actual = await vi.importActual('../../config.js'); + return { ...actual, DATA_DIR: '/tmp/nanoclaw-test-sender-approval' }; +}); + +const TEST_DIR = '/tmp/nanoclaw-test-sender-approval'; + +function now() { + return new Date().toISOString(); +} + +beforeEach(async () => { + if (fs.existsSync(TEST_DIR)) fs.rmSync(TEST_DIR, { recursive: true }); + fs.mkdirSync(TEST_DIR, { recursive: true }); + const db = initTestDb(); + runMigrations(db); + + // Side-effect imports: register hooks (permissions module) AFTER the + // mocks are in place so the access gate / response handler pick up the + // mocked delivery + user-dm helpers. + await import('./index.js'); + + // Fixtures: agent group, messaging group with request_approval, wiring, + // owner + DM messaging group for approver delivery. + createAgentGroup({ id: 'ag-1', name: 'Agent', folder: 'agent', agent_provider: null, created_at: now() }); + + createMessagingGroup({ + id: 'mg-chat', + channel_type: 'telegram', + platform_id: 'chat-123', + name: 'Group Chat', + is_group: 1, + unknown_sender_policy: 'request_approval', + created_at: now(), + }); + createMessagingGroupAgent({ + id: 'mga-1', + messaging_group_id: 'mg-chat', + agent_group_id: 'ag-1', + engage_mode: 'pattern', + engage_pattern: '.', + sender_scope: 'all', + ignored_message_policy: 'drop', + session_mode: 'shared', + priority: 0, + created_at: now(), + }); + + // Owner user + their DM messaging group (pickApprover + ensureUserDm target). + upsertUser({ id: 'telegram:owner', kind: 'telegram', display_name: 'Owner', created_at: now() }); + grantRole({ + user_id: 'telegram:owner', + role: 'owner', + agent_group_id: null, + granted_by: null, + granted_at: now(), + }); + createMessagingGroup({ + id: 'mg-dm-owner', + channel_type: 'telegram', + platform_id: 'dm-owner', + name: 'Owner DM', + is_group: 0, + unknown_sender_policy: 'public', + created_at: now(), + }); + const { getDb } = await import('../../db/connection.js'); + getDb() + .prepare( + `INSERT INTO user_dms (user_id, channel_type, messaging_group_id, resolved_at) + VALUES (?, ?, ?, ?)`, + ) + .run('telegram:owner', 'telegram', 'mg-dm-owner', now()); + + deliverMock.mockClear(); +}); + +afterEach(() => { + closeDb(); + if (fs.existsSync(TEST_DIR)) fs.rmSync(TEST_DIR, { recursive: true }); +}); + +function stranger(text: string) { + return { + channelType: 'telegram', + platformId: 'chat-123', + threadId: null, + message: { + id: `stranger-${Math.random().toString(36).slice(2, 8)}`, + kind: 'chat' as const, + content: JSON.stringify({ + senderId: 'tg:stranger', + senderName: 'Stranger', + text, + }), + timestamp: now(), + }, + }; +} + +describe('unknown-sender request_approval flow', () => { + it('delivers an approval card on first unknown message', async () => { + const { routeInbound } = await import('../../router.js'); + await routeInbound(stranger('hi')); + + // Wait for the fire-and-forget requestSenderApproval to resolve. + await new Promise((r) => setTimeout(r, 10)); + + expect(deliverMock).toHaveBeenCalledTimes(1); + const [channel, platformId, thread, kind, content] = deliverMock.mock.calls[0]; + expect(channel).toBe('telegram'); + expect(platformId).toBe('dm-owner'); // delivered to owner's DM + expect(thread).toBeNull(); + expect(kind).toBe('chat-sdk'); + const payload = JSON.parse(content as string); + expect(payload.type).toBe('ask_question'); + expect(payload.questionId).toMatch(/^nsa-/); + + const { getDb } = await import('../../db/connection.js'); + const rows = getDb().prepare('SELECT * FROM pending_sender_approvals').all(); + expect(rows).toHaveLength(1); + }); + + it('dedups a second message from the same stranger while pending', async () => { + const { routeInbound } = await import('../../router.js'); + await routeInbound(stranger('hello')); + await new Promise((r) => setTimeout(r, 10)); + await routeInbound(stranger('are you there?')); + await new Promise((r) => setTimeout(r, 10)); + + expect(deliverMock).toHaveBeenCalledTimes(1); + const { getDb } = await import('../../db/connection.js'); + const count = ( + getDb().prepare('SELECT COUNT(*) AS c FROM pending_sender_approvals').get() as { c: number } + ).c; + expect(count).toBe(1); + }); + + it('approve → adds member and replays the original message', async () => { + const { routeInbound } = await import('../../router.js'); + const { getResponseHandlers } = await import('../../response-registry.js'); + const { wakeContainer } = await import('../../container-runner.js'); + (wakeContainer as unknown as ReturnType).mockClear(); + + await routeInbound(stranger('please let me in')); + await new Promise((r) => setTimeout(r, 10)); + + const { getDb } = await import('../../db/connection.js'); + const pending = getDb().prepare('SELECT id FROM pending_sender_approvals').get() as { id: string }; + expect(pending).toBeDefined(); + + // Fire the approve click through the response-handler chain. + for (const handler of getResponseHandlers()) { + const claimed = await handler({ + questionId: pending.id, + value: 'approve', + userId: 'telegram:owner', + channelType: 'telegram', + platformId: 'dm-owner', + threadId: null, + }); + if (claimed) break; + } + + // Member row added for the stranger against the wired agent group. + const member = getDb() + .prepare('SELECT 1 AS x FROM agent_group_members WHERE user_id = ? AND agent_group_id = ?') + .get('tg:stranger', 'ag-1'); + expect(member).toBeDefined(); + + // Pending row cleared. + const stillPending = getDb().prepare('SELECT COUNT(*) AS c FROM pending_sender_approvals').get() as { c: number }; + expect(stillPending.c).toBe(0); + + // Message replayed + container woken. + expect(wakeContainer).toHaveBeenCalled(); + }); + + it('deny → deletes the pending row without adding a member', async () => { + const { routeInbound } = await import('../../router.js'); + const { getResponseHandlers } = await import('../../response-registry.js'); + + await routeInbound(stranger('hello')); + await new Promise((r) => setTimeout(r, 10)); + + const { getDb } = await import('../../db/connection.js'); + const pending = getDb().prepare('SELECT id FROM pending_sender_approvals').get() as { id: string }; + expect(pending).toBeDefined(); + + for (const handler of getResponseHandlers()) { + const claimed = await handler({ + questionId: pending.id, + value: 'reject', + userId: 'telegram:owner', + channelType: 'telegram', + platformId: 'dm-owner', + threadId: null, + }); + if (claimed) break; + } + + const count = ( + getDb().prepare('SELECT COUNT(*) AS c FROM pending_sender_approvals').get() as { c: number } + ).c; + expect(count).toBe(0); + const member = getDb() + .prepare('SELECT 1 AS x FROM agent_group_members WHERE user_id = ? AND agent_group_id = ?') + .get('tg:stranger', 'ag-1'); + expect(member).toBeUndefined(); + }); +}); diff --git a/src/modules/permissions/sender-approval.ts b/src/modules/permissions/sender-approval.ts new file mode 100644 index 000000000..be6028041 --- /dev/null +++ b/src/modules/permissions/sender-approval.ts @@ -0,0 +1,152 @@ +/** + * Unknown-sender approval flow. + * + * When `messaging_groups.unknown_sender_policy = 'request_approval'` and a + * non-member writes into a wired chat, the access gate drops the routing + * attempt and calls `requestSenderApproval` to: + * + * 1. Pick an eligible approver (owner / admin of the agent group). + * 2. Open / reuse a DM to that approver on a reachable channel. + * 3. Deliver an Approve / Deny card. + * 4. Record a pending_sender_approvals row that holds the original message + * so it can be re-routed on approve. + * + * On approve: the handler in index.ts adds an agent_group_members row for + * the sender and re-invokes routeInbound with the stored event — the second + * routing attempt passes the gate because the user is now a member. + * + * Failure modes (logged + row NOT created, so the dedup gate lets a future + * attempt try again): + * - No eligible approver in user_roles — fresh install, no owner yet. + * - Approver has no reachable DM (no user_dms row + channel can't + * openDM) — e.g. owner hasn't registered on any channel we're wired to. + * - Delivery adapter missing. + * + * Dedup: `pending_sender_approvals` has UNIQUE(messaging_group_id, + * sender_identity). A retry / rapid second message from the same unknown + * sender is silently dropped (no duplicate card sent). + */ +import { normalizeOptions, type RawOption } from '../../channels/ask-question.js'; +import { getMessagingGroup } from '../../db/messaging-groups.js'; +import { getDeliveryAdapter } from '../../delivery.js'; +import { log } from '../../log.js'; +import type { InboundEvent } from '../../router.js'; +import { pickApprovalDelivery, pickApprover } from '../approvals/primitive.js'; +import { createPendingSenderApproval, hasInFlightSenderApproval } from './db/pending-sender-approvals.js'; + +const APPROVAL_OPTIONS: RawOption[] = [ + { label: 'Allow', selectedLabel: '✅ Allowed', value: 'approve' }, + { label: 'Deny', selectedLabel: '❌ Denied', value: 'reject' }, +]; + +function generateId(): string { + return `nsa-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; +} + +export interface RequestSenderApprovalInput { + messagingGroupId: string; + agentGroupId: string; + senderIdentity: string; // namespaced user id (channel_type:handle) + senderName: string | null; + event: InboundEvent; +} + +export async function requestSenderApproval(input: RequestSenderApprovalInput): Promise { + const { messagingGroupId, agentGroupId, senderIdentity, senderName, event } = input; + + // In-flight dedup: don't spam the admin if the same unknown sender + // retries while a card is already pending. + if (hasInFlightSenderApproval(messagingGroupId, senderIdentity)) { + log.debug('Unknown-sender approval already in flight — dropping retry', { + messagingGroupId, + senderIdentity, + }); + return; + } + + const approvers = pickApprover(agentGroupId); + if (approvers.length === 0) { + log.warn('Unknown-sender approval skipped — no owner or admin configured', { + messagingGroupId, + agentGroupId, + senderIdentity, + }); + return; + } + + const originMg = getMessagingGroup(messagingGroupId); + const originChannelType = originMg?.channel_type ?? ''; + const target = await pickApprovalDelivery(approvers, originChannelType); + if (!target) { + log.warn('Unknown-sender approval skipped — no DM channel for any approver', { + messagingGroupId, + agentGroupId, + senderIdentity, + }); + return; + } + + const approvalId = generateId(); + const senderDisplay = senderName && senderName.length > 0 ? senderName : senderIdentity; + const originName = originMg?.name ?? originMg?.platform_id ?? 'an unfamiliar chat'; + + const title = '👤 New sender'; + const question = `${senderDisplay} wants to talk to your agent in ${originName}. Allow?`; + + createPendingSenderApproval({ + id: approvalId, + messaging_group_id: messagingGroupId, + agent_group_id: agentGroupId, + sender_identity: senderIdentity, + sender_name: senderName, + original_message: JSON.stringify(event), + approver_user_id: target.userId, + created_at: new Date().toISOString(), + }); + + const adapter = getDeliveryAdapter(); + if (!adapter) { + // Without a delivery adapter, the card can't be sent. Log + leave the + // row in place so the admin can see it via DB or manual tooling; the + // dedup gate will suppress further cards until it's cleared. + log.error('Unknown-sender approval row created but no delivery adapter is wired', { + approvalId, + }); + return; + } + + try { + await adapter.deliver( + target.messagingGroup.channel_type, + target.messagingGroup.platform_id, + null, + 'chat-sdk', + JSON.stringify({ + type: 'ask_question', + questionId: approvalId, + title, + question, + options: APPROVAL_OPTIONS, + }), + ); + log.info('Unknown-sender approval card delivered', { + approvalId, + senderIdentity, + approver: target.userId, + messagingGroupId, + agentGroupId, + }); + } catch (err) { + log.error('Unknown-sender approval card delivery failed', { + approvalId, + err, + }); + } +} + +/** + * Option value the admin clicked that means "allow" — shared with the + * response handler so the two sides can't drift. + */ +export const APPROVE_VALUE = 'approve'; +export const REJECT_VALUE = 'reject'; diff --git a/src/router.ts b/src/router.ts index 9b54cb28e..cb4ee939f 100644 --- a/src/router.ts +++ b/src/router.ts @@ -145,7 +145,10 @@ export async function routeInbound(event: InboundEvent): Promise { platform_id: event.platformId, name: null, is_group: 0, - unknown_sender_policy: 'strict', + // Let the schema default (currently 'request_approval') apply rather + // than hardcoding 'strict' — the schema is the source of truth for + // the default policy. See migration 011. + unknown_sender_policy: 'request_approval', created_at: new Date().toISOString(), }; createMessagingGroup(mg); From 5d5f72e11728fb66ee3be9656c1ecf0d758e96d5 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 09:55:16 +0300 Subject: [PATCH 22/95] docs(action-items): add item 22 (unknown-channel wiring approval flow) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Covers the gap item 5 left open: request_approval presupposes a wired channel, so unknown-channel cases (new DM, @mention in unwired group, bot added to fresh group) short-circuit at no_agent_wired before the approval flow runs. Design: - Owner-sender auto-wire fast path (exactly one agent group → wire silently; multiple → card) - Card with one button per existing agent group + "Create new" + "Ignore" - New pending_channel_approvals table, UNIQUE(messaging_group_id) - nca- action-id prefix paralleling nsa- / ncq- - Handler lives alongside handleSenderApprovalResponse - "Create new" sub-flow is intentionally open scope Cross-reference added to item 5 so the scope boundary is explicit. Co-Authored-By: Claude Opus 4.7 (1M context) --- docs/v1-vs-v2/ACTION-ITEMS.md | 88 +++++++++++++++++++++++++++++++++++ 1 file changed, 88 insertions(+) diff --git a/docs/v1-vs-v2/ACTION-ITEMS.md b/docs/v1-vs-v2/ACTION-ITEMS.md index 806bff467..72457b7aa 100644 --- a/docs/v1-vs-v2/ACTION-ITEMS.md +++ b/docs/v1-vs-v2/ACTION-ITEMS.md @@ -47,6 +47,11 @@ Working doc for each finding from [SUMMARY.md](SUMMARY.md). Decisions were made - **6a**: Remove `IDLE_END_MS` from `poll-loop.ts` (folded into item 9) - **3a**: E2E recovery test (deferred) +### Follow-up PRs (scoped, not in this branch) +| # | Topic | Why later | +|---|---|---| +| 22 | Unknown-channel wiring approval flow (card to owner when bot receives inbound in an unwired messaging group) | Gap surfaced after item 5 landed — item 5's `request_approval` covers unknown senders but presupposes a wired channel. See item 22 for the full design. | + --- ## HIGH @@ -167,6 +172,87 @@ On wake, container pulls pending messages with `ORDER BY seq DESC LIMIT MAX_MESS --- +### 22. Unknown-channel wiring approval flow +**Finding** (post-item-5 discussion): item 5's `request_approval` only fires when a messaging group already has agents wired. Three scenarios slip through to the earlier `no_agent_wired` structural-drop branch in `src/router.ts` and get silent-dropped with no signal to the owner: + +1. A new user DMs the agent directly (the DM's messaging group auto-creates but has no wiring) +2. The agent is @mentioned in a group the admin hasn't registered +3. The agent is added to a new group and someone there addresses it + +In all three, the user sees no response and the owner has no signal anything happened. + +**Status**: decided — companion PR to item 5, scoped separately + +**Decision**: when the router hits `no_agent_wired` for a non-public event, **instead of silent-dropping, pick the owner and DM them a wiring card**. Two flavors depending on who triggered it: + +- **Sender IS an owner/admin** (the common "I just added the bot" case) → auto-wire IF exactly one agent group exists. Silent seamless flow. If multiple agent groups exist, fall through to the card so the owner picks. +- **Sender is anyone else** (stranger, or owner in a multi-agent install) → deliver a card: + - Title: `🔌 New channel — wire it?` + - Body: ` is trying to reach you in on . Wire to which agent?` + - Options: one button per existing `agent_groups` row, plus `➕ Create new` and `Ignore` + +**On approve (existing agent group)**: +1. `createMessagingGroupAgent(...)` with channel-kind defaults — DM→`pattern` + `'.'`, threaded group→`mention-sticky`, non-threaded group→`mention` (same defaults as `scripts/init-first-agent.ts`) +2. Replay the stored event via `routeInbound` (sender-approval pattern) +3. Delete pending row + +**On approve "Create new"**: [OPEN SCOPE] — needs name/folder input. Options: +- Follow-up ask_question card asking for a name → auto-derive folder from slug → create group + wire +- Or: skill-backed flow — the button dispatches to `/init-agent` or similar and the card just links out +- Punt until implementation; mention in the PR brief that we'll decide when building + +**On ignore**: delete pending row; future attempts re-prompt fresh (consistent with sender-approval deny; no denial persistence). + +**Failure cases** (drop silently with log, don't leave a pending row): +- No owner configured (fresh install) — same behaviour as sender-approval +- No reachable DM for any owner/admin +- Delivery adapter missing + +**New table**: +``` +pending_channel_approvals ( + id TEXT PRIMARY KEY, + messaging_group_id TEXT NOT NULL REFERENCES messaging_groups(id), + sender_identity TEXT, -- NULL when triggered by a non-identifiable event + sender_name TEXT, + original_message TEXT NOT NULL, -- JSON InboundEvent for replay + approver_user_id TEXT NOT NULL, + created_at TEXT NOT NULL, + UNIQUE(messaging_group_id) -- one pending wiring per channel +) +``` + +Dedup is narrower than sender-approval's `(mg_id, sender_id)` — one pending wiring per channel, period. A second stranger writing into the same unwired channel piggybacks on the existing card instead of spawning a new one. Latest event replaces the stored `original_message` (we only replay one anyway, and latest is most useful). + +**Card action id prefix**: `nca-:` where value is `agent-group-` / `create` / `ignore`. Response handler lives in `src/modules/permissions/` alongside `handleSenderApprovalResponse`. + +**Owner-sender auto-wire logic**: +``` +if sender is owner/admin AND getAllAgentGroups().length === 1: + auto-wire to that group, replay event, done — no card +else: + deliver card +``` + +Don't auto-create a new agent group silently — always require a prompt for that. + +**LOC estimate**: ~145 +- Migration + CRUD: 45 +- Router hook before `no_agent_wired` drop → try channel approval: 15 +- Owner-sender auto-wire fast path: 20 +- Card delivery (scope `pickApprover(null)`; build buttons from `getAllAgentGroups()`): 25 +- Response handler: 25 +- Tests: 15 + +**Open scopes (flag at PR time)**: +- "Create new" sub-flow — pick between follow-up card vs skill link +- Do we also react to bot-added-to-group platform events? Simpler to stay lazy (first-message-triggered only). Platform lifecycle events are inconsistent across Discord/Slack/Telegram anyway. +- Worth scanning the `channels` branch for any existing channel-lifecycle handlers that might conflict. + +**Next step**: open a follow-up PR off this branch once #1869 lands. + +--- + ### 3a. End-to-end recovery test **Finding**: no test confirms the host-crash-restart scenario produces timely re-delivery. @@ -253,6 +339,8 @@ Dedicated (not reusing `pending_approvals` which is OneCLI-specific). - The router's auto-create at `router.ts:123` currently hardcodes `'strict'` — change to omit the field so schema default applies - `pickApprover` may return null if no admin/owner exists (e.g. fresh install before first user registered). In that case: log + drop silently, treat as effectively `'strict'` for safety. Don't block message forever. +**Scope boundary** (important): this item covers **unknown sender in a wired channel**. The parallel case — **unknown channel** (new DM / unwired group / bot-added-to-group) — short-circuits at the `no_agent_wired` structural drop before this flow ever runs. Tracked as item 22. + **Next step**: implement alongside item 1 or as a follow-up. Same migration window is fine (one migration for engage columns + request_approval default change + new table). ### 6. Per-group container timeout From a1079da8774ddd4c85cc1ca307d49ff37051b52b Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Mon, 20 Apr 2026 07:01:45 +0000 Subject: [PATCH 23/95] fix(new-setup): always source ONECLI_URL from installer stdout Match v1 behavior: drop getApiHost() (which was returning the CLI default https://app.onecli.sh) and always extract the gateway URL from the install script's stdout, then apply it via onecli config set api-host and .env. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/onecli.ts | 87 ++++++++++++++++++------------------------------- 1 file changed, 31 insertions(+), 56 deletions(-) diff --git a/setup/onecli.ts b/setup/onecli.ts index 226d30271..c4ce83f70 100644 --- a/setup/onecli.ts +++ b/setup/onecli.ts @@ -37,20 +37,6 @@ function onecliVersion(): string | null { } } -function getApiHost(): string | null { - try { - const out = execFileSync('onecli', ['config', 'get', 'api-host'], { - encoding: 'utf-8', - env: childEnv(), - stdio: ['ignore', 'pipe', 'ignore'], - }).trim(); - const parsed = JSON.parse(out) as { value?: unknown }; - return typeof parsed.value === 'string' && parsed.value ? parsed.value : null; - } catch { - return null; - } -} - function extractUrlFromOutput(output: string): string | null { const match = output.match(/https?:\/\/[\w.\-]+(?::\d+)?/); return match ? match[0] : null; @@ -123,60 +109,49 @@ async function pollHealth(url: string, timeoutMs: number): Promise { export async function run(_args: string[]): Promise { ensureShellProfilePath(); - let installOutput = ''; - let present = !!onecliVersion(); - if (!present) { - log.info('Installing OneCLI gateway and CLI'); - const res = installOnecli(); - installOutput = res.stdout; - if (!res.ok) { - emitStatus('ONECLI', { - INSTALLED: false, - STATUS: 'failed', - ERROR: 'install_failed', - LOG: 'logs/setup.log', - }); - process.exit(1); - } - present = !!onecliVersion(); - if (!present) { - emitStatus('ONECLI', { - INSTALLED: false, - STATUS: 'failed', - ERROR: 'onecli_not_on_path_after_install', - HINT: 'Open a new shell or run `export PATH="$HOME/.local/bin:$PATH"` and retry.', - LOG: 'logs/setup.log', - }); - process.exit(1); - } - } - - let url = getApiHost(); - if (!url && installOutput) { - url = extractUrlFromOutput(installOutput); - if (url) { - try { - execFileSync('onecli', ['config', 'set', 'api-host', url], { - stdio: 'ignore', - env: childEnv(), - }); - } catch (err) { - log.warn('onecli config set api-host failed', { err }); - } - } + log.info('Installing OneCLI gateway and CLI'); + const res = installOnecli(); + if (!res.ok) { + emitStatus('ONECLI', { + INSTALLED: false, + STATUS: 'failed', + ERROR: 'install_failed', + LOG: 'logs/setup.log', + }); + process.exit(1); + } + if (!onecliVersion()) { + emitStatus('ONECLI', { + INSTALLED: false, + STATUS: 'failed', + ERROR: 'onecli_not_on_path_after_install', + HINT: 'Open a new shell or run `export PATH="$HOME/.local/bin:$PATH"` and retry.', + LOG: 'logs/setup.log', + }); + process.exit(1); } + const url = extractUrlFromOutput(res.stdout); if (!url) { emitStatus('ONECLI', { INSTALLED: true, STATUS: 'failed', ERROR: 'could_not_resolve_api_host', - HINT: 'Run `onecli config get api-host` to inspect the gateway URL.', + HINT: 'Inspect logs/setup.log for the install output.', LOG: 'logs/setup.log', }); process.exit(1); } + try { + execFileSync('onecli', ['config', 'set', 'api-host', url], { + stdio: 'ignore', + env: childEnv(), + }); + } catch (err) { + log.warn('onecli config set api-host failed', { err }); + } + writeEnvOnecliUrl(url); log.info('Wrote ONECLI_URL to .env', { url }); From 9882c945304a674497188082d3ba759bc8ed4944 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 10:07:50 +0300 Subject: [PATCH 24/95] fix(channels): use Chat SDK ChatMessage.text, not .content MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The engage-mode gating added in #1869 read `message.content` from the Chat SDK's ChatMessage in all three inbound handlers (onSubscribedMessage, onNewMention, onDirectMessage). ChatMessage exposes the user-visible string as `.text` — `.content` exists on the underlying nested structure but isn't the plain-text field. Result: `shouldEngage` always saw an empty string, pattern gating never matched, non-wildcard regex wirings silently dropped every inbound. Fix: use `message.text` in all three gates. Discovered during live smoke-test on v2 post-merge. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/channels/chat-sdk-bridge.ts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index 593a2ad4b..6a480c460 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -237,7 +237,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter // plain 'mention' wiring doesn't keep firing after a one-off mention. chat.onSubscribedMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const text = typeof message.content === 'string' ? message.content : ''; + const text = typeof message.text === 'string' ? message.text : ''; const decision = shouldEngage(channelId, 'subscribed', text); if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); @@ -247,7 +247,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter // if the wiring is 'mention-sticky'. chat.onNewMention(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const text = typeof message.content === 'string' ? message.content : ''; + const text = typeof message.text === 'string' ? message.text : ''; const decision = shouldEngage(channelId, 'mention', text); if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); @@ -266,7 +266,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter // escalation). chat.onDirectMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const text = typeof message.content === 'string' ? message.content : ''; + const text = typeof message.text === 'string' ? message.text : ''; const decision = shouldEngage(channelId, 'dm', text); log.info('Inbound DM received', { adapter: adapter.name, From fca3d8de7004b60cba77dab4b2f6ff53810f5677 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 10:08:03 +0300 Subject: [PATCH 25/95] fix(migrations): drop 011 table-rebuild; keep only pending_sender_approvals The original 011 also rebuilt `messaging_groups` to flip the `unknown_sender_policy` column DEFAULT from "strict" to "request_approval". On live DBs the DROP TABLE step fails SQLite's foreign-key integrity check because `sessions`, `user_dms`, and `pending_sender_approvals` all reference `messaging_groups(id)`. `PRAGMA foreign_keys=OFF` / `defer_foreign_keys` can't be toggled inside the implicit migration transaction, so the rebuild can't be made to apply cleanly. The default-flip was cosmetic anyway: every `createMessagingGroup` callsite passes `unknown_sender_policy` explicitly. Router auto-create was already updated to hardcode "request_approval" (router.ts:151), and setup / seed scripts pick per context. Changes: - Migration 011 now only creates the `pending_sender_approvals` table + index. The rebuild block is gone. - Reference `SCHEMA` in src/db/schema.ts updated to reflect what the DB actually has: DEFAULT 'strict' (from migration 001), with a note about the effective policy applied at insert sites. Discovered on v2 post-merge during live restart. Co-Authored-By: Claude Opus 4.7 (1M context) --- .../011-pending-sender-approvals.ts | 35 +++++-------------- src/db/schema.ts | 9 ++--- 2 files changed, 14 insertions(+), 30 deletions(-) diff --git a/src/db/migrations/011-pending-sender-approvals.ts b/src/db/migrations/011-pending-sender-approvals.ts index cb4703950..2331a6e2e 100644 --- a/src/db/migrations/011-pending-sender-approvals.ts +++ b/src/db/migrations/011-pending-sender-approvals.ts @@ -4,10 +4,15 @@ * in-flight entry in this table dedups concurrent attempts from the same * sender; the row is cleared on approve / deny. * - * Also flips the `messaging_groups.unknown_sender_policy` default from 'strict' - * to 'request_approval' so fresh wirings don't silently swallow messages from - * users the admin hasn't added yet. Existing rows are left as-is (silent - * upgrade would change established behavior without the admin asking for it). + * Previously this migration also rebuilt `messaging_groups` to flip the + * column DEFAULT from `'strict'` to `'request_approval'`. Removed: the + * rebuild failed SQLite's foreign-key integrity check at DROP time on live + * DBs with existing FK references (sessions, user_dms, etc.), and `PRAGMA + * foreign_keys` / `defer_foreign_keys` can't be toggled inside the + * implicit migration transaction. The default-flip was cosmetic anyway — + * every `createMessagingGroup` callsite passes `unknown_sender_policy` + * explicitly, and the router's auto-create path was updated to hardcode + * `'request_approval'` directly (see src/router.ts:123). */ import type Database from 'better-sqlite3'; import type { Migration } from './index.js'; @@ -31,27 +36,5 @@ export const migration011: Migration = { CREATE INDEX IF NOT EXISTS idx_pending_sender_approvals_mg ON pending_sender_approvals(messaging_group_id); `); - - // Default-flip: fresh messaging_groups default to request_approval instead - // of silently dropping. SQLite doesn't support modifying column DEFAULTs - // in place, so we rebuild the table via the classic rename-copy-drop - // pattern. Existing rows keep their current unknown_sender_policy value. - db.exec(` - CREATE TABLE messaging_groups_new ( - id TEXT PRIMARY KEY, - channel_type TEXT NOT NULL, - platform_id TEXT NOT NULL, - name TEXT, - is_group INTEGER DEFAULT 0, - unknown_sender_policy TEXT NOT NULL DEFAULT 'request_approval', - created_at TEXT NOT NULL, - UNIQUE(channel_type, platform_id) - ); - INSERT INTO messaging_groups_new - SELECT id, channel_type, platform_id, name, is_group, unknown_sender_policy, created_at - FROM messaging_groups; - DROP TABLE messaging_groups; - ALTER TABLE messaging_groups_new RENAME TO messaging_groups; - `); }, }; diff --git a/src/db/schema.ts b/src/db/schema.ts index aa33fae1e..8433035be 100644 --- a/src/db/schema.ts +++ b/src/db/schema.ts @@ -19,17 +19,18 @@ CREATE TABLE agent_groups ( -- Platform groups/channels. unknown_sender_policy governs what happens -- when a sender we've never seen before posts in this chat. +-- The column DEFAULT is "strict" (inherited from migration 001), but it +-- only matters if something inserts without specifying the field, which no +-- current callsite does. Router auto-create hardcodes "request_approval" +-- (see src/router.ts:151); setup scripts pick per context. CREATE TABLE messaging_groups ( id TEXT PRIMARY KEY, channel_type TEXT NOT NULL, platform_id TEXT NOT NULL, name TEXT, is_group INTEGER DEFAULT 0, - unknown_sender_policy TEXT NOT NULL DEFAULT 'request_approval', + unknown_sender_policy TEXT NOT NULL DEFAULT 'strict', -- 'strict' | 'request_approval' | 'public' - -- Default is request_approval so silent drops don't - -- mystery-break users who wired their DM during - -- setup and haven't explicitly marked it public. created_at TEXT NOT NULL, UNIQUE(channel_type, platform_id) ); From 73b20880ffa27e48e95076ee8ae33cc37a3bd1a5 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 10:34:15 +0300 Subject: [PATCH 26/95] fix(channels): pre-subscribe group threads for pattern / accumulate wirings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The engage modes shipped in #1869 included `pattern` (regex match any message) and the `accumulate` ignored-message policy, but neither could fire in group chats because Chat SDK only surfaces: - DMs (onDirectMessage) - @mentions in unsubscribed threads (onNewMention) - every message in subscribed threads (onSubscribedMessage) A bot sitting in a Discord/Slack channel hears *nothing* from a plain message unless the thread is already subscribed. So `pattern '.'` on a group wiring → silent. `pattern /urgent/i` → silent. `mention + accumulate` → the non-mention messages that should be stored as context were never received, so nothing to accumulate. Fix: call `chat.subscribe(platformId)` at setup time for every wiring whose `engageMode === 'pattern'` or `ignoredMessagePolicy === 'accumulate'`. Failures logged + swallowed per-conversation so one un-subscribable channel doesn't crash startup. ## Knock-on: SDK stops firing onNewMention once subscribed Per SDK types:1468, `onNewMention` only fires in unsubscribed threads. Once we pre-subscribe a channel for a pattern wiring, subsequent mentions arrive as `onSubscribedMessage` with `message.isMention === true`. Before: a `mention` wiring coexisting with a `pattern` wiring in the same channel would silently stop firing after pre-subscribe. After: `shouldEngage` accepts the `isMention` flag independently from `source`, so the `mention` mode matches on (dm OR mention-new OR subscribed-with-isMention). Source shape changed `'subscribed' | 'mention' | 'dm'` → `'subscribed' | 'mention-new' | 'dm'` to make the "unsubscribed-mention event" distinction explicit. ## New fields - `ConversationConfig.ignoredMessagePolicy` — projected from the messaging_group_agents row so the bridge knows which wirings need pre-subscription. buildConversationConfigs in src/index.ts populates it. Tests: host 153/153, container 46/46. No new tests yet — the subscribe call path needs a Chat mock, deferred. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/channels/adapter.ts | 7 ++ src/channels/chat-sdk-bridge.ts | 115 ++++++++++++++++++++++++++------ src/index.ts | 1 + 3 files changed, 101 insertions(+), 22 deletions(-) diff --git a/src/channels/adapter.ts b/src/channels/adapter.ts index 33f382548..878606102 100644 --- a/src/channels/adapter.ts +++ b/src/channels/adapter.ts @@ -22,6 +22,13 @@ export interface ConversationConfig { engageMode: 'pattern' | 'mention' | 'mention-sticky'; /** Regex source when engageMode='pattern'. '.' is the "always" sentinel. */ engagePattern?: string | null; + /** + * What to do with non-engaging messages. Projected from the wiring so the + * adapter can decide whether to pre-subscribe to group threads — `accumulate` + * means "store everything as context even when not engaging", which requires + * seeing every message in the thread. + */ + ignoredMessagePolicy?: 'drop' | 'accumulate'; sessionMode: 'shared' | 'per-thread' | 'agent-shared'; } diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index 6a480c460..4e33696dd 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -93,27 +93,83 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter } /** - * Should a message from (channelId, kind) engage any of the wired agents? + * Does any wiring for this conversation need Chat SDK subscription to see + * every message? `pattern` and `accumulate` both require it; plain `mention` + * and `mention-sticky` don't (mentions fire their own event, sticky + * subscribes lazily on first fire). + */ + function needsPreSubscribe(configs: ConversationConfig[]): boolean { + return configs.some( + (c) => c.engageMode === 'pattern' || c.ignoredMessagePolicy === 'accumulate', + ); + } + + /** + * Subscribe to every conversation whose wiring needs to see every message + * (pattern gate or accumulate context). Runs once after `chat.initialize()`. + * Failures are logged and swallowed per-conversation — one un-subscribable + * channel (no permission, not in it yet) shouldn't block startup. * - * - `mention` — engages only when the message actually @-mentions - * the bot (the bridge already sees it here because - * Chat SDK only forwards subscribed / mentioned / - * DM messages) - * - `mention-sticky` — same as `mention` for gating, PLUS we subscribe - * the thread so later messages arrive via the - * subscribed path and fall through to an - * engage-all style treatment - * - `pattern` — regex test against message text; `.` = always + * `threadId` for subscription = the platformId we stored in ConversationConfig. + * This matches the deliver path's `tid = threadId ?? platformId` pattern + * where adapters treat their encoded channel id as the top-level thread id. + */ + async function preSubscribeNeededConversations( + chatInstance: Chat, + conversationsMap: Map, + ): Promise { + for (const [platformId, configs] of conversationsMap.entries()) { + if (!needsPreSubscribe(configs)) continue; + try { + // eslint-disable-next-line @typescript-eslint/no-explicit-any + const chatAny = chatInstance as any; + if (typeof chatAny.isSubscribed === 'function') { + const already = await chatAny.isSubscribed(platformId); + if (already) continue; + } + await chatAny.subscribe(platformId); + log.info('Pre-subscribed conversation', { adapter: adapter.name, platformId }); + } catch (err) { + log.warn('Pre-subscribe failed — pattern/accumulate wirings won\'t see non-mention messages here', { + adapter: adapter.name, + platformId, + err, + }); + } + } + } + + /** + * Should a message from this conversation engage any of the wired agents? * - * We take the union across wired agents — if any one of them would engage, - * the message goes through. Per-agent filtering after that happens in the - * host router (see src/router.ts pickAgents). + * Source meaning: + * - `dm` — Chat SDK `onDirectMessage` + * - `mention-new` — Chat SDK `onNewMention` (mention in an unsubscribed + * thread; SDK never fires this once the thread is + * subscribed — see SDK types :1468) + * - `subscribed` — Chat SDK `onSubscribedMessage` (plain message in a + * subscribed thread). In this case `isMention` is + * distinct: set to true when `message.isMention` is, + * so `mention` wirings keep firing even if a + * co-resident `pattern` wiring subscribed the thread. + * + * Mode semantics: + * - `pattern` — regex test against text; `.` = always + * - `mention` — fire iff mentioned (covers dm, mention-new, and + * subscribed-with-isMention) + * - `mention-sticky` — fire on dm / mention-new (and subscribe the thread); + * in subscribed source always fire — the thread was + * already activated on a prior mention + * + * Result is the union across wired agents — if any engages, the message + * goes through. Per-agent filtering happens host-side (src/router.ts pickAgents). */ function shouldEngage( channelId: string, - source: 'subscribed' | 'mention' | 'dm', - text: string, + source: 'subscribed' | 'mention-new' | 'dm', + opts: { text: string; isMention: boolean }, ): { engage: boolean; stickySubscribe: boolean } { + const { text, isMention } = opts; const configs = conversations.get(channelId); // Unknown conversation — forward anyway (may be a new group that // hasn't been registered yet; central routing will log + drop cleanly). @@ -122,18 +178,19 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter let engage = false; let stickySubscribe = false; + const mentionMatch = source === 'dm' || source === 'mention-new' || (source === 'subscribed' && isMention); + for (const cfg of configs) { switch (cfg.engageMode) { case 'mention': - if (source === 'mention' || source === 'dm') engage = true; + if (mentionMatch) engage = true; break; case 'mention-sticky': - if (source === 'mention' || source === 'dm') { + if (source === 'dm' || source === 'mention-new') { engage = true; stickySubscribe = true; } else if (source === 'subscribed') { - // Thread was already subscribed on a prior mention — treat as - // engage-all so follow-ups in the thread reach the agent. + // Thread already activated on a prior mention — engage all messages. engage = true; } break; @@ -238,7 +295,8 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter chat.onSubscribedMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; - const decision = shouldEngage(channelId, 'subscribed', text); + const isMention = Boolean((message as unknown as { isMention?: boolean }).isMention); + const decision = shouldEngage(channelId, 'subscribed', { text, isMention }); if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); }); @@ -248,7 +306,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter chat.onNewMention(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; - const decision = shouldEngage(channelId, 'mention', text); + const decision = shouldEngage(channelId, 'mention-new', { text, isMention: true }); if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); if (decision.stickySubscribe) { @@ -267,7 +325,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter chat.onDirectMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; - const decision = shouldEngage(channelId, 'dm', text); + const decision = shouldEngage(channelId, 'dm', { text, isMention: true }); log.info('Inbound DM received', { adapter: adapter.name, channelId, @@ -312,6 +370,19 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter await chat.initialize(); + // Pre-subscribe to threads where the wiring needs to see every message + // (pattern mode or accumulate policy). Without this, Chat SDK only + // surfaces mentions + DMs for unsubscribed threads — silently dropping + // every plain message in a group, which breaks `engage_mode='pattern'` + // and `ignored_message_policy='accumulate'` for group chats. + // + // For subscription purposes, platformId is used as the thread id. This + // matches the deliver path (see `tid = threadId ?? platformId` below) + // where adapters treat their encoded channel id as the top-level thread. + // Failures are logged and swallowed so one un-subscribable channel + // (e.g., no permission) doesn't block startup. + await preSubscribeNeededConversations(chat, conversations); + // Start Gateway listener for adapters that support it (e.g., Discord) const gatewayAdapter = adapter as GatewayAdapter; if (gatewayAdapter.startGatewayListener) { diff --git a/src/index.ts b/src/index.ts index 9bb51bebb..4958eef74 100644 --- a/src/index.ts +++ b/src/index.ts @@ -163,6 +163,7 @@ function buildConversationConfigs(channelType: string): ConversationConfig[] { agentGroupId: agent.agent_group_id, engageMode: agent.engage_mode, engagePattern: agent.engage_pattern, + ignoredMessagePolicy: agent.ignored_message_policy, sessionMode: agent.session_mode, }); } From 57e0cda9e5d8347b93d767222f052b025d3f4572 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 10:35:33 +0300 Subject: [PATCH 27/95] Revert "fix(channels): pre-subscribe group threads for pattern / accumulate wirings" This reverts commit 73b20880ffa27e48e95076ee8ae33cc37a3bd1a5. --- src/channels/adapter.ts | 7 -- src/channels/chat-sdk-bridge.ts | 115 ++++++-------------------------- src/index.ts | 1 - 3 files changed, 22 insertions(+), 101 deletions(-) diff --git a/src/channels/adapter.ts b/src/channels/adapter.ts index 878606102..33f382548 100644 --- a/src/channels/adapter.ts +++ b/src/channels/adapter.ts @@ -22,13 +22,6 @@ export interface ConversationConfig { engageMode: 'pattern' | 'mention' | 'mention-sticky'; /** Regex source when engageMode='pattern'. '.' is the "always" sentinel. */ engagePattern?: string | null; - /** - * What to do with non-engaging messages. Projected from the wiring so the - * adapter can decide whether to pre-subscribe to group threads — `accumulate` - * means "store everything as context even when not engaging", which requires - * seeing every message in the thread. - */ - ignoredMessagePolicy?: 'drop' | 'accumulate'; sessionMode: 'shared' | 'per-thread' | 'agent-shared'; } diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index 4e33696dd..6a480c460 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -93,83 +93,27 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter } /** - * Does any wiring for this conversation need Chat SDK subscription to see - * every message? `pattern` and `accumulate` both require it; plain `mention` - * and `mention-sticky` don't (mentions fire their own event, sticky - * subscribes lazily on first fire). - */ - function needsPreSubscribe(configs: ConversationConfig[]): boolean { - return configs.some( - (c) => c.engageMode === 'pattern' || c.ignoredMessagePolicy === 'accumulate', - ); - } - - /** - * Subscribe to every conversation whose wiring needs to see every message - * (pattern gate or accumulate context). Runs once after `chat.initialize()`. - * Failures are logged and swallowed per-conversation — one un-subscribable - * channel (no permission, not in it yet) shouldn't block startup. + * Should a message from (channelId, kind) engage any of the wired agents? * - * `threadId` for subscription = the platformId we stored in ConversationConfig. - * This matches the deliver path's `tid = threadId ?? platformId` pattern - * where adapters treat their encoded channel id as the top-level thread id. - */ - async function preSubscribeNeededConversations( - chatInstance: Chat, - conversationsMap: Map, - ): Promise { - for (const [platformId, configs] of conversationsMap.entries()) { - if (!needsPreSubscribe(configs)) continue; - try { - // eslint-disable-next-line @typescript-eslint/no-explicit-any - const chatAny = chatInstance as any; - if (typeof chatAny.isSubscribed === 'function') { - const already = await chatAny.isSubscribed(platformId); - if (already) continue; - } - await chatAny.subscribe(platformId); - log.info('Pre-subscribed conversation', { adapter: adapter.name, platformId }); - } catch (err) { - log.warn('Pre-subscribe failed — pattern/accumulate wirings won\'t see non-mention messages here', { - adapter: adapter.name, - platformId, - err, - }); - } - } - } - - /** - * Should a message from this conversation engage any of the wired agents? + * - `mention` — engages only when the message actually @-mentions + * the bot (the bridge already sees it here because + * Chat SDK only forwards subscribed / mentioned / + * DM messages) + * - `mention-sticky` — same as `mention` for gating, PLUS we subscribe + * the thread so later messages arrive via the + * subscribed path and fall through to an + * engage-all style treatment + * - `pattern` — regex test against message text; `.` = always * - * Source meaning: - * - `dm` — Chat SDK `onDirectMessage` - * - `mention-new` — Chat SDK `onNewMention` (mention in an unsubscribed - * thread; SDK never fires this once the thread is - * subscribed — see SDK types :1468) - * - `subscribed` — Chat SDK `onSubscribedMessage` (plain message in a - * subscribed thread). In this case `isMention` is - * distinct: set to true when `message.isMention` is, - * so `mention` wirings keep firing even if a - * co-resident `pattern` wiring subscribed the thread. - * - * Mode semantics: - * - `pattern` — regex test against text; `.` = always - * - `mention` — fire iff mentioned (covers dm, mention-new, and - * subscribed-with-isMention) - * - `mention-sticky` — fire on dm / mention-new (and subscribe the thread); - * in subscribed source always fire — the thread was - * already activated on a prior mention - * - * Result is the union across wired agents — if any engages, the message - * goes through. Per-agent filtering happens host-side (src/router.ts pickAgents). + * We take the union across wired agents — if any one of them would engage, + * the message goes through. Per-agent filtering after that happens in the + * host router (see src/router.ts pickAgents). */ function shouldEngage( channelId: string, - source: 'subscribed' | 'mention-new' | 'dm', - opts: { text: string; isMention: boolean }, + source: 'subscribed' | 'mention' | 'dm', + text: string, ): { engage: boolean; stickySubscribe: boolean } { - const { text, isMention } = opts; const configs = conversations.get(channelId); // Unknown conversation — forward anyway (may be a new group that // hasn't been registered yet; central routing will log + drop cleanly). @@ -178,19 +122,18 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter let engage = false; let stickySubscribe = false; - const mentionMatch = source === 'dm' || source === 'mention-new' || (source === 'subscribed' && isMention); - for (const cfg of configs) { switch (cfg.engageMode) { case 'mention': - if (mentionMatch) engage = true; + if (source === 'mention' || source === 'dm') engage = true; break; case 'mention-sticky': - if (source === 'dm' || source === 'mention-new') { + if (source === 'mention' || source === 'dm') { engage = true; stickySubscribe = true; } else if (source === 'subscribed') { - // Thread already activated on a prior mention — engage all messages. + // Thread was already subscribed on a prior mention — treat as + // engage-all so follow-ups in the thread reach the agent. engage = true; } break; @@ -295,8 +238,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter chat.onSubscribedMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; - const isMention = Boolean((message as unknown as { isMention?: boolean }).isMention); - const decision = shouldEngage(channelId, 'subscribed', { text, isMention }); + const decision = shouldEngage(channelId, 'subscribed', text); if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); }); @@ -306,7 +248,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter chat.onNewMention(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; - const decision = shouldEngage(channelId, 'mention-new', { text, isMention: true }); + const decision = shouldEngage(channelId, 'mention', text); if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); if (decision.stickySubscribe) { @@ -325,7 +267,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter chat.onDirectMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; - const decision = shouldEngage(channelId, 'dm', { text, isMention: true }); + const decision = shouldEngage(channelId, 'dm', text); log.info('Inbound DM received', { adapter: adapter.name, channelId, @@ -370,19 +312,6 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter await chat.initialize(); - // Pre-subscribe to threads where the wiring needs to see every message - // (pattern mode or accumulate policy). Without this, Chat SDK only - // surfaces mentions + DMs for unsubscribed threads — silently dropping - // every plain message in a group, which breaks `engage_mode='pattern'` - // and `ignored_message_policy='accumulate'` for group chats. - // - // For subscription purposes, platformId is used as the thread id. This - // matches the deliver path (see `tid = threadId ?? platformId` below) - // where adapters treat their encoded channel id as the top-level thread. - // Failures are logged and swallowed so one un-subscribable channel - // (e.g., no permission) doesn't block startup. - await preSubscribeNeededConversations(chat, conversations); - // Start Gateway listener for adapters that support it (e.g., Discord) const gatewayAdapter = adapter as GatewayAdapter; if (gatewayAdapter.startGatewayListener) { diff --git a/src/index.ts b/src/index.ts index 4958eef74..9bb51bebb 100644 --- a/src/index.ts +++ b/src/index.ts @@ -163,7 +163,6 @@ function buildConversationConfigs(channelType: string): ConversationConfig[] { agentGroupId: agent.agent_group_id, engageMode: agent.engage_mode, engagePattern: agent.engage_pattern, - ignoredMessagePolicy: agent.ignored_message_policy, sessionMode: agent.session_mode, }); } From 52c62232929a6b4dafbdc79c9c55c1e2e0792337 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 11:11:56 +0300 Subject: [PATCH 28/95] fix(channels): register onNewMessage(/./) to fix pattern mode in group chats MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Chat SDK dispatch (per handling-events.mdx) is exclusive and prioritized: subscribed → onSubscribedMessage; unsubscribed + mention → onNewMention; unsubscribed + pattern match → onNewMessage. We never registered the third, so engage_mode='pattern' silently dropped every message in unsubscribed group threads — the SDK simply never surfaced them anywhere. Register chat.onNewMessage(/./, …) and route it through shouldEngage with a new 'new-message' source. Unknown-conversation policy drops for this source (would otherwise flood from every unwired channel the bot can see). mention / mention-sticky wirings ignore 'new-message' — they require an explicit @mention to start a conversation. Pattern wirings evaluate normally. Extracted shouldEngage from a closure to an exported function with an EngageSource type so it's unit-testable. Added 17 tests covering every source × engage-mode combination, unknown-conversation behavior, invalid regex fail-open, and multi-wiring union. Accumulate (ignored_message_policy='accumulate') is still not plumbed — the bridge drops non-engaging messages entirely instead of forwarding them as context-only. That requires a trigger: 0 | 1 field on InboundMessage → router → writeSessionMessage (schema already has the column). Separate change. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/channels/chat-sdk-bridge.test.ts | 129 ++++++++++++++++++- src/channels/chat-sdk-bridge.ts | 181 ++++++++++++++++++--------- 2 files changed, 249 insertions(+), 61 deletions(-) diff --git a/src/channels/chat-sdk-bridge.test.ts b/src/channels/chat-sdk-bridge.test.ts index e71ccb252..3989c265b 100644 --- a/src/channels/chat-sdk-bridge.test.ts +++ b/src/channels/chat-sdk-bridge.test.ts @@ -2,12 +2,33 @@ import { describe, expect, it } from 'vitest'; import type { Adapter } from 'chat'; -import { createChatSdkBridge } from './chat-sdk-bridge.js'; +import type { ConversationConfig } from './adapter.js'; +import { createChatSdkBridge, shouldEngage, type EngageSource } from './chat-sdk-bridge.js'; function stubAdapter(partial: Partial): Adapter { return { name: 'stub', ...partial } as unknown as Adapter; } +function cfg(partial: Partial & { engageMode: ConversationConfig['engageMode'] }): ConversationConfig { + return { + platformId: partial.platformId ?? 'C1', + agentGroupId: partial.agentGroupId ?? 'ag-1', + engageMode: partial.engageMode, + engagePattern: partial.engagePattern ?? null, + sessionMode: partial.sessionMode ?? 'shared', + }; +} + +function mapFor(...configs: ConversationConfig[]): Map { + const map = new Map(); + for (const c of configs) { + const existing = map.get(c.platformId); + if (existing) existing.push(c); + else map.set(c.platformId, [c]); + } + return map; +} + describe('createChatSdkBridge', () => { it('omits openDM when the underlying Chat SDK adapter has none', () => { const bridge = createChatSdkBridge({ @@ -36,3 +57,109 @@ describe('createChatSdkBridge', () => { expect(platformId).toBe('stub:user-42'); }); }); + +describe('shouldEngage', () => { + describe('unknown conversation', () => { + const empty = new Map(); + const sources: EngageSource[] = ['subscribed', 'mention', 'dm']; + for (const source of sources) { + it(`forwards for source='${source}' (may be a not-yet-wired group)`, () => { + expect(shouldEngage(empty, 'C1', source, '')).toEqual({ engage: true, stickySubscribe: false }); + }); + } + it("DROPS for source='new-message' (would flood from unwired channels)", () => { + expect(shouldEngage(empty, 'C1', 'new-message', 'hello')).toEqual({ + engage: false, + stickySubscribe: false, + }); + }); + }); + + describe("engageMode='mention'", () => { + const conv = mapFor(cfg({ engageMode: 'mention' })); + it('engages on mention + dm', () => { + expect(shouldEngage(conv, 'C1', 'mention', '').engage).toBe(true); + expect(shouldEngage(conv, 'C1', 'dm', '').engage).toBe(true); + }); + it('does NOT engage on subscribed or new-message (prevents keep-firing + flooding)', () => { + expect(shouldEngage(conv, 'C1', 'subscribed', '').engage).toBe(false); + expect(shouldEngage(conv, 'C1', 'new-message', '').engage).toBe(false); + }); + it('never asks to subscribe', () => { + for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { + expect(shouldEngage(conv, 'C1', s, '').stickySubscribe).toBe(false); + } + }); + }); + + describe("engageMode='mention-sticky'", () => { + const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); + it('engages on mention + dm with stickySubscribe=true', () => { + expect(shouldEngage(conv, 'C1', 'mention', '')).toEqual({ engage: true, stickySubscribe: true }); + expect(shouldEngage(conv, 'C1', 'dm', '')).toEqual({ engage: true, stickySubscribe: true }); + }); + it('engages on subscribed follow-ups without re-subscribing', () => { + expect(shouldEngage(conv, 'C1', 'subscribed', '')).toEqual({ engage: true, stickySubscribe: false }); + }); + it('does NOT engage on new-message (explicit mention required to start)', () => { + expect(shouldEngage(conv, 'C1', 'new-message', '').engage).toBe(false); + }); + }); + + describe("engageMode='pattern'", () => { + it('pattern="." engages on every source except new-message-with-unknown', () => { + const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '.' })); + for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { + expect(shouldEngage(conv, 'C1', s, 'anything').engage).toBe(true); + } + }); + + it('tests regex against text on new-message (the main bug fix)', () => { + const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '^!report' })); + expect(shouldEngage(conv, 'C1', 'new-message', '!report now').engage).toBe(true); + expect(shouldEngage(conv, 'C1', 'new-message', 'nothing to see').engage).toBe(false); + }); + + it('pattern regex applies on every source (symmetry)', () => { + const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: 'deploy' })); + for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { + expect(shouldEngage(conv, 'C1', s, 'time to deploy').engage).toBe(true); + expect(shouldEngage(conv, 'C1', s, 'weather today').engage).toBe(false); + } + }); + + it('pattern never triggers sticky-subscribe', () => { + const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '.' })); + for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { + expect(shouldEngage(conv, 'C1', s, 'hi').stickySubscribe).toBe(false); + } + }); + + it('invalid regex fails open (admin sees something rather than silent drop)', () => { + const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '[unclosed' })); + expect(shouldEngage(conv, 'C1', 'new-message', 'x').engage).toBe(true); + }); + }); + + describe('multiple wirings on one conversation', () => { + it('takes the union across wirings (any-engage wins)', () => { + // mention wiring + pattern wiring on the same channel. A plain message + // should engage via the pattern wiring even though the mention wiring + // alone would reject it. + const conv = mapFor( + cfg({ agentGroupId: 'ag-a', engageMode: 'mention' }), + cfg({ agentGroupId: 'ag-b', engageMode: 'pattern', engagePattern: '^hi' }), + ); + expect(shouldEngage(conv, 'C1', 'new-message', 'hi there').engage).toBe(true); + expect(shouldEngage(conv, 'C1', 'new-message', 'something else').engage).toBe(false); + }); + + it('stickySubscribe from any mention-sticky wiring wins', () => { + const conv = mapFor( + cfg({ agentGroupId: 'ag-a', engageMode: 'mention' }), + cfg({ agentGroupId: 'ag-b', engageMode: 'mention-sticky' }), + ); + expect(shouldEngage(conv, 'C1', 'mention', '')).toEqual({ engage: true, stickySubscribe: true }); + }); + }); +}); diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index 6a480c460..f2daf1166 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -65,6 +65,99 @@ export interface ChatSdkBridgeConfig { transformOutboundText?: (text: string) => string; } +/** + * Which Chat SDK handler delivered this message. Determines which engage modes + * can fire. + * + * - `subscribed` — `onSubscribedMessage`. Thread is already subscribed. + * Every wiring mode (mention / mention-sticky / pattern) + * evaluates normally. + * - `mention` — `onNewMention`. Bot was @-mentioned in an unsubscribed + * thread. mention + mention-sticky engage; pattern runs + * the regex. + * - `dm` — `onDirectMessage`. Unsubscribed DM. Treated like a + * mention for engagement purposes. + * - `new-message` — `onNewMessage(/./, …)`. Plain non-mention non-DM + * message in an unsubscribed thread. Only `pattern` + * wirings can fire here. mention / mention-sticky ignore + * this source (they require an explicit mention). + */ +export type EngageSource = 'subscribed' | 'mention' | 'dm' | 'new-message'; + +/** + * Should a message from (channelId, source, text) engage any of the wired + * agents on this conversation? + * + * Exported for testability — see `chat-sdk-bridge.test.ts`. + * + * We take the union across wired agents: if any wiring would engage, the + * message is forwarded. Per-agent filtering after that happens in the host + * router (see `src/router.ts` pickAgents). + */ +export function shouldEngage( + conversations: Map, + channelId: string, + source: EngageSource, + text: string, +): { engage: boolean; stickySubscribe: boolean } { + const configs = conversations.get(channelId); + + // Unknown conversation — behavior diverges by source: + // - subscribed/mention/dm: forward anyway. These paths imply some + // prior engagement (subscribe, @mention, DM open) and may be a new + // group that hasn't been registered yet; central routing will log + + // drop cleanly. + // - new-message: DROP. `onNewMessage(/./, …)` fires for every message + // in every unsubscribed thread the bot can see — including channels + // the bot is merely *present* in but not wired to. Forwarding + // everything would flood the host. + if (!configs || configs.length === 0) { + return { engage: source !== 'new-message', stickySubscribe: false }; + } + + let engage = false; + let stickySubscribe = false; + + for (const cfg of configs) { + switch (cfg.engageMode) { + case 'mention': + if (source === 'mention' || source === 'dm') engage = true; + break; + case 'mention-sticky': + if (source === 'mention' || source === 'dm') { + engage = true; + stickySubscribe = true; + } else if (source === 'subscribed') { + // Thread was already subscribed on a prior mention — treat as + // engage-all so follow-ups in the thread reach the agent. + engage = true; + } + // source='new-message' → do not engage. mention-sticky requires an + // explicit mention to start the conversation. + break; + case 'pattern': { + // Pattern evaluates on any source that delivers a plain message — + // including new-message, which is the whole reason we registered + // onNewMessage(/./). For mention/dm-delivered messages we still + // test the regex (historical behavior), so pattern='foo' wirings + // only fire on mentions whose text contains 'foo'. + const pattern = cfg.engagePattern ?? '.'; + try { + if (pattern === '.' || new RegExp(pattern).test(text)) engage = true; + } catch { + // Invalid regex → fail open so the admin can see something is + // happening and fix the pattern. + engage = true; + } + break; + } + } + if (engage && stickySubscribe) break; + } + + return { engage, stickySubscribe }; +} + export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter { const { adapter } = config; const transformText = (t: string): string => (config.transformOutboundText ? config.transformOutboundText(t) : t); @@ -92,66 +185,12 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter return map; } - /** - * Should a message from (channelId, kind) engage any of the wired agents? - * - * - `mention` — engages only when the message actually @-mentions - * the bot (the bridge already sees it here because - * Chat SDK only forwards subscribed / mentioned / - * DM messages) - * - `mention-sticky` — same as `mention` for gating, PLUS we subscribe - * the thread so later messages arrive via the - * subscribed path and fall through to an - * engage-all style treatment - * - `pattern` — regex test against message text; `.` = always - * - * We take the union across wired agents — if any one of them would engage, - * the message goes through. Per-agent filtering after that happens in the - * host router (see src/router.ts pickAgents). - */ - function shouldEngage( + function engageDecision( channelId: string, - source: 'subscribed' | 'mention' | 'dm', + source: EngageSource, text: string, ): { engage: boolean; stickySubscribe: boolean } { - const configs = conversations.get(channelId); - // Unknown conversation — forward anyway (may be a new group that - // hasn't been registered yet; central routing will log + drop cleanly). - if (!configs || configs.length === 0) return { engage: true, stickySubscribe: false }; - - let engage = false; - let stickySubscribe = false; - - for (const cfg of configs) { - switch (cfg.engageMode) { - case 'mention': - if (source === 'mention' || source === 'dm') engage = true; - break; - case 'mention-sticky': - if (source === 'mention' || source === 'dm') { - engage = true; - stickySubscribe = true; - } else if (source === 'subscribed') { - // Thread was already subscribed on a prior mention — treat as - // engage-all so follow-ups in the thread reach the agent. - engage = true; - } - break; - case 'pattern': { - const pattern = cfg.engagePattern ?? '.'; - try { - if (pattern === '.' || new RegExp(pattern).test(text)) engage = true; - } catch { - // Invalid regex → fail open so the admin can see something and fix. - engage = true; - } - break; - } - } - if (engage && stickySubscribe) break; - } - - return { engage, stickySubscribe }; + return shouldEngage(conversations, channelId, source, text); } async function messageToInbound(message: ChatMessage): Promise { @@ -238,7 +277,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter chat.onSubscribedMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; - const decision = shouldEngage(channelId, 'subscribed', text); + const decision = engageDecision(channelId, 'subscribed', text); if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); }); @@ -248,7 +287,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter chat.onNewMention(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; - const decision = shouldEngage(channelId, 'mention', text); + const decision = engageDecision(channelId, 'mention', text); if (!decision.engage) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); if (decision.stickySubscribe) { @@ -267,7 +306,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter chat.onDirectMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; - const decision = shouldEngage(channelId, 'dm', text); + const decision = engageDecision(channelId, 'dm', text); log.info('Inbound DM received', { adapter: adapter.name, channelId, @@ -282,6 +321,28 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter } }); + // Plain (non-mention, non-DM) messages in unsubscribed threads. + // + // Chat SDK dispatch (handling-events.mdx §"Handler dispatch order"): + // subscribed threads → onSubscribedMessage; unsubscribed + mention → + // onNewMention; unsubscribed + pattern match → onNewMessage. Dispatch + // is exclusive — at most one handler fires per message. + // + // Without this handler, `engage_mode='pattern'` is silently dropped in + // unsubscribed group threads because the SDK never surfaces the + // message anywhere else. Registering with `/./` lets every wired + // conversation's regex be evaluated in our `shouldEngage` — unknown + // conversations are dropped there (see the source='new-message' + // branch) so this doesn't flood the host on channels the bot isn't + // wired to. + chat.onNewMessage(/./, async (thread, message) => { + const channelId = adapter.channelIdFromThreadId(thread.id); + const text = typeof message.text === 'string' ? message.text : ''; + const decision = engageDecision(channelId, 'new-message', text); + if (!decision.engage) return; + await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); + }); + // Handle button clicks (ask_user_question) chat.onAction(async (event) => { if (!event.actionId.startsWith('ncq:')) return; From ce25e1e97c4b80ec07859319501045959b986d36 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 11:12:40 +0300 Subject: [PATCH 29/95] style(channels): prettier line-wrap in chat-sdk-bridge.test.ts Post-commit reformat picked up by format:fix hook on the previous commit. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/channels/chat-sdk-bridge.test.ts | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/channels/chat-sdk-bridge.test.ts b/src/channels/chat-sdk-bridge.test.ts index 3989c265b..667fc7f74 100644 --- a/src/channels/chat-sdk-bridge.test.ts +++ b/src/channels/chat-sdk-bridge.test.ts @@ -9,7 +9,9 @@ function stubAdapter(partial: Partial): Adapter { return { name: 'stub', ...partial } as unknown as Adapter; } -function cfg(partial: Partial & { engageMode: ConversationConfig['engageMode'] }): ConversationConfig { +function cfg( + partial: Partial & { engageMode: ConversationConfig['engageMode'] }, +): ConversationConfig { return { platformId: partial.platformId ?? 'C1', agentGroupId: partial.agentGroupId ?? 'ag-1', From c38e5b11a888711acf508157bc7b397a5e4ddf33 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 11:18:43 +0300 Subject: [PATCH 30/95] fix(channels): wire accumulate mode through the bridge MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The router + session DB were already fully plumbed for ignored_message_policy='accumulate' — fan-out in routeInbound calls deliverToAgent(wake=false) for non-engaging agents on accumulate wirings, writeSessionMessage writes trigger=0, countDueMessages filters trigger=1, container formatter includes all messages regardless of trigger. But the Chat SDK bridge dropped non-engaging messages before the router ever saw them, so accumulate was dead on arrival for every adapter that goes through the bridge. Expose ignored_message_policy on ConversationConfig, project it in buildConversationConfigs, and widen shouldEngage's "forward" decision to "engage OR accumulate" with the union taken across all wirings on a conversation. stickySubscribe stays gated on a real engage — subscribing a thread we'd only silently accumulate on would misrepresent the bot's presence. shouldEngage return shape is now { forward, stickySubscribe } — engage was an internal concept the caller never needed, and conflating it with forward was the source of this bug. 7 new tests cover: non-engaging messages forwarding under accumulate, mixed drop/accumulate wirings taking the union, accumulate not triggering sticky subscribe, unknown-conversation drop precedence over accumulate, and drop policy preserving existing behavior on engaging messages. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/channels/adapter.ts | 14 ++++ src/channels/chat-sdk-bridge.test.ts | 105 ++++++++++++++++++++------- src/channels/chat-sdk-bridge.ts | 61 ++++++++++------ src/index.ts | 1 + 4 files changed, 133 insertions(+), 48 deletions(-) diff --git a/src/channels/adapter.ts b/src/channels/adapter.ts index 33f382548..34b367555 100644 --- a/src/channels/adapter.ts +++ b/src/channels/adapter.ts @@ -22,6 +22,20 @@ export interface ConversationConfig { engageMode: 'pattern' | 'mention' | 'mention-sticky'; /** Regex source when engageMode='pattern'. '.' is the "always" sentinel. */ engagePattern?: string | null; + /** + * What to do with messages this wiring doesn't engage on. + * + * 'drop' — discard silently + * 'accumulate' — still forward to the host so the router can store the + * message in this agent's session with trigger=0. It + * rides along as context when the agent next wakes, but + * doesn't wake it on its own. + * + * The bridge reads this to decide whether to forward a non-engaging + * message at all — if any wiring on a conversation has 'accumulate', the + * bridge forwards and lets the router apply the per-wiring decision. + */ + ignoredMessagePolicy?: 'drop' | 'accumulate'; sessionMode: 'shared' | 'per-thread' | 'agent-shared'; } diff --git a/src/channels/chat-sdk-bridge.test.ts b/src/channels/chat-sdk-bridge.test.ts index 667fc7f74..aad8d0a03 100644 --- a/src/channels/chat-sdk-bridge.test.ts +++ b/src/channels/chat-sdk-bridge.test.ts @@ -17,6 +17,7 @@ function cfg( agentGroupId: partial.agentGroupId ?? 'ag-1', engageMode: partial.engageMode, engagePattern: partial.engagePattern ?? null, + ignoredMessagePolicy: partial.ignoredMessagePolicy ?? 'drop', sessionMode: partial.sessionMode ?? 'shared', }; } @@ -66,26 +67,26 @@ describe('shouldEngage', () => { const sources: EngageSource[] = ['subscribed', 'mention', 'dm']; for (const source of sources) { it(`forwards for source='${source}' (may be a not-yet-wired group)`, () => { - expect(shouldEngage(empty, 'C1', source, '')).toEqual({ engage: true, stickySubscribe: false }); + expect(shouldEngage(empty, 'C1', source, '')).toEqual({ forward: true, stickySubscribe: false }); }); } it("DROPS for source='new-message' (would flood from unwired channels)", () => { expect(shouldEngage(empty, 'C1', 'new-message', 'hello')).toEqual({ - engage: false, + forward: false, stickySubscribe: false, }); }); }); - describe("engageMode='mention'", () => { + describe("engageMode='mention' + ignoredMessagePolicy='drop' (default)", () => { const conv = mapFor(cfg({ engageMode: 'mention' })); - it('engages on mention + dm', () => { - expect(shouldEngage(conv, 'C1', 'mention', '').engage).toBe(true); - expect(shouldEngage(conv, 'C1', 'dm', '').engage).toBe(true); + it('forwards on mention + dm', () => { + expect(shouldEngage(conv, 'C1', 'mention', '').forward).toBe(true); + expect(shouldEngage(conv, 'C1', 'dm', '').forward).toBe(true); }); - it('does NOT engage on subscribed or new-message (prevents keep-firing + flooding)', () => { - expect(shouldEngage(conv, 'C1', 'subscribed', '').engage).toBe(false); - expect(shouldEngage(conv, 'C1', 'new-message', '').engage).toBe(false); + it('does NOT forward on subscribed or new-message (prevents keep-firing + flooding)', () => { + expect(shouldEngage(conv, 'C1', 'subscribed', '').forward).toBe(false); + expect(shouldEngage(conv, 'C1', 'new-message', '').forward).toBe(false); }); it('never asks to subscribe', () => { for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { @@ -96,37 +97,37 @@ describe('shouldEngage', () => { describe("engageMode='mention-sticky'", () => { const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); - it('engages on mention + dm with stickySubscribe=true', () => { - expect(shouldEngage(conv, 'C1', 'mention', '')).toEqual({ engage: true, stickySubscribe: true }); - expect(shouldEngage(conv, 'C1', 'dm', '')).toEqual({ engage: true, stickySubscribe: true }); + it('forwards on mention + dm with stickySubscribe=true', () => { + expect(shouldEngage(conv, 'C1', 'mention', '')).toEqual({ forward: true, stickySubscribe: true }); + expect(shouldEngage(conv, 'C1', 'dm', '')).toEqual({ forward: true, stickySubscribe: true }); }); - it('engages on subscribed follow-ups without re-subscribing', () => { - expect(shouldEngage(conv, 'C1', 'subscribed', '')).toEqual({ engage: true, stickySubscribe: false }); + it('forwards subscribed follow-ups without re-subscribing', () => { + expect(shouldEngage(conv, 'C1', 'subscribed', '')).toEqual({ forward: true, stickySubscribe: false }); }); - it('does NOT engage on new-message (explicit mention required to start)', () => { - expect(shouldEngage(conv, 'C1', 'new-message', '').engage).toBe(false); + it('does NOT forward on new-message (explicit mention required to start)', () => { + expect(shouldEngage(conv, 'C1', 'new-message', '').forward).toBe(false); }); }); describe("engageMode='pattern'", () => { - it('pattern="." engages on every source except new-message-with-unknown', () => { + it('pattern="." forwards on every source (when conversation is known)', () => { const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '.' })); for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { - expect(shouldEngage(conv, 'C1', s, 'anything').engage).toBe(true); + expect(shouldEngage(conv, 'C1', s, 'anything').forward).toBe(true); } }); it('tests regex against text on new-message (the main bug fix)', () => { const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '^!report' })); - expect(shouldEngage(conv, 'C1', 'new-message', '!report now').engage).toBe(true); - expect(shouldEngage(conv, 'C1', 'new-message', 'nothing to see').engage).toBe(false); + expect(shouldEngage(conv, 'C1', 'new-message', '!report now').forward).toBe(true); + expect(shouldEngage(conv, 'C1', 'new-message', 'nothing to see').forward).toBe(false); }); it('pattern regex applies on every source (symmetry)', () => { const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: 'deploy' })); for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { - expect(shouldEngage(conv, 'C1', s, 'time to deploy').engage).toBe(true); - expect(shouldEngage(conv, 'C1', s, 'weather today').engage).toBe(false); + expect(shouldEngage(conv, 'C1', s, 'time to deploy').forward).toBe(true); + expect(shouldEngage(conv, 'C1', s, 'weather today').forward).toBe(false); } }); @@ -139,7 +140,50 @@ describe('shouldEngage', () => { it('invalid regex fails open (admin sees something rather than silent drop)', () => { const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '[unclosed' })); - expect(shouldEngage(conv, 'C1', 'new-message', 'x').engage).toBe(true); + expect(shouldEngage(conv, 'C1', 'new-message', 'x').forward).toBe(true); + }); + }); + + describe("ignoredMessagePolicy='accumulate'", () => { + it('forwards non-engaging new-message so the router can store it as context (trigger=0)', () => { + const conv = mapFor(cfg({ engageMode: 'mention', ignoredMessagePolicy: 'accumulate' })); + // Plain message in unsubscribed group — mention rule says no engage, + // but accumulate says forward anyway. + expect(shouldEngage(conv, 'C1', 'new-message', 'chit chat')).toEqual({ + forward: true, + stickySubscribe: false, + }); + }); + + it('forwards non-engaging subscribed messages for accumulation', () => { + // mention wiring in a subscribed thread: the mention handler already + // fired once, thread is now subscribed, follow-ups route here. The + // base 'mention' rule wouldn't engage without an @-mention, but + // accumulate says capture the context. + const conv = mapFor(cfg({ engageMode: 'mention', ignoredMessagePolicy: 'accumulate' })); + expect(shouldEngage(conv, 'C1', 'subscribed', 'follow up talk').forward).toBe(true); + }); + + it('does NOT set stickySubscribe purely from accumulate (avoid misleading bot presence)', () => { + const conv = mapFor(cfg({ engageMode: 'mention-sticky', ignoredMessagePolicy: 'accumulate' })); + expect(shouldEngage(conv, 'C1', 'new-message', 'plain').stickySubscribe).toBe(false); + }); + + it("accumulate doesn't override the 'unknown conversation → drop new-message' rule", () => { + // Unknown conversation (not in map): accumulate can't be read because + // there's no config to read from. We still drop. + const empty = new Map(); + expect(shouldEngage(empty, 'C-unknown', 'new-message', 'x').forward).toBe(false); + }); + + it("drop policy + non-engaging message → doesn't forward", () => { + const conv = mapFor(cfg({ engageMode: 'mention', ignoredMessagePolicy: 'drop' })); + expect(shouldEngage(conv, 'C1', 'new-message', 'plain').forward).toBe(false); + }); + + it('engaging message with drop policy still forwards (engage wins regardless)', () => { + const conv = mapFor(cfg({ engageMode: 'mention', ignoredMessagePolicy: 'drop' })); + expect(shouldEngage(conv, 'C1', 'mention', '@bot hi').forward).toBe(true); }); }); @@ -152,8 +196,17 @@ describe('shouldEngage', () => { cfg({ agentGroupId: 'ag-a', engageMode: 'mention' }), cfg({ agentGroupId: 'ag-b', engageMode: 'pattern', engagePattern: '^hi' }), ); - expect(shouldEngage(conv, 'C1', 'new-message', 'hi there').engage).toBe(true); - expect(shouldEngage(conv, 'C1', 'new-message', 'something else').engage).toBe(false); + expect(shouldEngage(conv, 'C1', 'new-message', 'hi there').forward).toBe(true); + expect(shouldEngage(conv, 'C1', 'new-message', 'something else').forward).toBe(false); + }); + + it('any accumulate wiring causes forward even if all others would drop', () => { + const conv = mapFor( + cfg({ agentGroupId: 'ag-a', engageMode: 'mention', ignoredMessagePolicy: 'drop' }), + cfg({ agentGroupId: 'ag-b', engageMode: 'mention', ignoredMessagePolicy: 'accumulate' }), + ); + // Plain message: ag-a would drop, ag-b would accumulate → forward. + expect(shouldEngage(conv, 'C1', 'new-message', 'plain').forward).toBe(true); }); it('stickySubscribe from any mention-sticky wiring wins', () => { @@ -161,7 +214,7 @@ describe('shouldEngage', () => { cfg({ agentGroupId: 'ag-a', engageMode: 'mention' }), cfg({ agentGroupId: 'ag-b', engageMode: 'mention-sticky' }), ); - expect(shouldEngage(conv, 'C1', 'mention', '')).toEqual({ engage: true, stickySubscribe: true }); + expect(shouldEngage(conv, 'C1', 'mention', '')).toEqual({ forward: true, stickySubscribe: true }); }); }); }); diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index f2daf1166..aa980abf0 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -85,21 +85,28 @@ export interface ChatSdkBridgeConfig { export type EngageSource = 'subscribed' | 'mention' | 'dm' | 'new-message'; /** - * Should a message from (channelId, source, text) engage any of the wired - * agents on this conversation? + * Should a message from (channelId, source, text) be forwarded to the host, + * and if so, should the bridge subscribe the thread? * * Exported for testability — see `chat-sdk-bridge.test.ts`. * - * We take the union across wired agents: if any wiring would engage, the - * message is forwarded. Per-agent filtering after that happens in the host - * router (see `src/router.ts` pickAgents). + * We take the union across wired agents: if any wiring would engage OR any + * wiring has `ignoredMessagePolicy='accumulate'`, the message is forwarded. + * The host router then does the per-wiring decision in `deliverToAgent` — + * engaging agents get `trigger=1` (wake), accumulating agents get + * `trigger=0` (store as context, don't wake), drop-policy agents are + * skipped (see `src/router.ts` routeInbound fan-out). + * + * `stickySubscribe` is only set when an actual engage happens (not just + * accumulate) — subscribing a thread we'd only silently accumulate on would + * misrepresent the bot's presence to other users. */ export function shouldEngage( conversations: Map, channelId: string, source: EngageSource, text: string, -): { engage: boolean; stickySubscribe: boolean } { +): { forward: boolean; stickySubscribe: boolean } { const configs = conversations.get(channelId); // Unknown conversation — behavior diverges by source: @@ -112,28 +119,30 @@ export function shouldEngage( // the bot is merely *present* in but not wired to. Forwarding // everything would flood the host. if (!configs || configs.length === 0) { - return { engage: source !== 'new-message', stickySubscribe: false }; + return { forward: source !== 'new-message', stickySubscribe: false }; } let engage = false; + let accumulate = false; let stickySubscribe = false; for (const cfg of configs) { + let cfgEngages = false; switch (cfg.engageMode) { case 'mention': - if (source === 'mention' || source === 'dm') engage = true; + if (source === 'mention' || source === 'dm') cfgEngages = true; break; case 'mention-sticky': if (source === 'mention' || source === 'dm') { - engage = true; + cfgEngages = true; stickySubscribe = true; } else if (source === 'subscribed') { // Thread was already subscribed on a prior mention — treat as // engage-all so follow-ups in the thread reach the agent. - engage = true; + cfgEngages = true; } - // source='new-message' → do not engage. mention-sticky requires an - // explicit mention to start the conversation. + // source='new-message' → does not engage (requires explicit mention + // to start). Accumulate policy is evaluated below if set. break; case 'pattern': { // Pattern evaluates on any source that delivers a plain message — @@ -143,19 +152,27 @@ export function shouldEngage( // only fire on mentions whose text contains 'foo'. const pattern = cfg.engagePattern ?? '.'; try { - if (pattern === '.' || new RegExp(pattern).test(text)) engage = true; + if (pattern === '.' || new RegExp(pattern).test(text)) cfgEngages = true; } catch { // Invalid regex → fail open so the admin can see something is // happening and fix the pattern. - engage = true; + cfgEngages = true; } break; } } - if (engage && stickySubscribe) break; + + if (cfgEngages) { + engage = true; + } else if (cfg.ignoredMessagePolicy === 'accumulate') { + // Wiring doesn't engage on this message but wants it captured as + // context for its session — forward so the router can write it with + // trigger=0. + accumulate = true; + } } - return { engage, stickySubscribe }; + return { forward: engage || accumulate, stickySubscribe }; } export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter { @@ -189,7 +206,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter channelId: string, source: EngageSource, text: string, - ): { engage: boolean; stickySubscribe: boolean } { + ): { forward: boolean; stickySubscribe: boolean } { return shouldEngage(conversations, channelId, source, text); } @@ -278,7 +295,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; const decision = engageDecision(channelId, 'subscribed', text); - if (!decision.engage) return; + if (!decision.forward) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); }); @@ -288,7 +305,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; const decision = engageDecision(channelId, 'mention', text); - if (!decision.engage) return; + if (!decision.forward) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); if (decision.stickySubscribe) { await thread.subscribe(); @@ -312,9 +329,9 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter channelId, sender: (message.author as any)?.fullName ?? (message.author as any)?.userId ?? 'unknown', threadId: thread.id, - engage: decision.engage, + forward: decision.forward, }); - if (!decision.engage) return; + if (!decision.forward) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); if (decision.stickySubscribe) { await thread.subscribe(); @@ -339,7 +356,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter const channelId = adapter.channelIdFromThreadId(thread.id); const text = typeof message.text === 'string' ? message.text : ''; const decision = engageDecision(channelId, 'new-message', text); - if (!decision.engage) return; + if (!decision.forward) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); }); diff --git a/src/index.ts b/src/index.ts index 9bb51bebb..4958eef74 100644 --- a/src/index.ts +++ b/src/index.ts @@ -163,6 +163,7 @@ function buildConversationConfigs(channelType: string): ConversationConfig[] { agentGroupId: agent.agent_group_id, engageMode: agent.engage_mode, engagePattern: agent.engage_pattern, + ignoredMessagePolicy: agent.ignored_message_policy, sessionMode: agent.session_mode, }); } From 31f2da95856f85c1d754756a4b940b05f86fa3a2 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 11:23:47 +0300 Subject: [PATCH 31/95] fix(container): gate poll loop on trigger=1 to honor accumulate contract MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A warm container picks up every pending messages_in row on each poll tick and calls markProcessing → agent.query → markCompleted. Before this, that included trigger=0 rows (ignored_message_policy='accumulate' context), causing the agent to wake and potentially respond to messages the wiring had explicitly opted out of engaging on — defeating accumulate's "store as context, don't engage" contract. Gate the main poll loop with `messages.some(m => m.trigger === 1)` — mirrors host-side countDueMessages which is already gated. If the batch has no wake-eligible row, sleep and leave them pending. They ride along via the same getPendingMessages query the next time a real trigger=1 lands, which is the intended accumulate behavior. The concurrent active-turn poll (line ~290) is unchanged on purpose — once the agent has engaged, pushing in accumulate rows mid-turn as additional context is desired. initTestSessionDb was missing the trigger and series_id columns on messages_in, out of sync with the live migration. Added both so the new tests (and any future trigger-aware tests) can run. Four tests cover the data contract: trigger=0 rows are returned by getPendingMessages (so they ride along), the gate predicate correctly identifies accumulate-only batches, mixed batches pass the gate, and the schema default of 1 applies when the column is omitted. Co-Authored-By: Claude Opus 4.7 (1M context) --- container/agent-runner/src/db/connection.ts | 2 + container/agent-runner/src/poll-loop.test.ts | 53 ++++++++++++++++++-- container/agent-runner/src/poll-loop.ts | 13 +++++ 3 files changed, 64 insertions(+), 4 deletions(-) diff --git a/container/agent-runner/src/db/connection.ts b/container/agent-runner/src/db/connection.ts index 772f4f160..3c0fffdde 100644 --- a/container/agent-runner/src/db/connection.ts +++ b/container/agent-runner/src/db/connection.ts @@ -157,7 +157,9 @@ export function initTestSessionDb(): { inbound: Database; outbound: Database } { status TEXT DEFAULT 'pending', process_after TEXT, recurrence TEXT, + series_id TEXT, tries INTEGER DEFAULT 0, + trigger INTEGER NOT NULL DEFAULT 1, platform_id TEXT, channel_type TEXT, thread_id TEXT, diff --git a/container/agent-runner/src/poll-loop.test.ts b/container/agent-runner/src/poll-loop.test.ts index de5fb687b..356108f5b 100644 --- a/container/agent-runner/src/poll-loop.test.ts +++ b/container/agent-runner/src/poll-loop.test.ts @@ -14,13 +14,13 @@ afterEach(() => { closeSessionDb(); }); -function insertMessage(id: string, kind: string, content: object, opts?: { processAfter?: string }) { +function insertMessage(id: string, kind: string, content: object, opts?: { processAfter?: string; trigger?: 0 | 1 }) { getInboundDb() .prepare( - `INSERT INTO messages_in (id, kind, timestamp, status, process_after, content) - VALUES (?, ?, datetime('now'), 'pending', ?, ?)`, + `INSERT INTO messages_in (id, kind, timestamp, status, process_after, trigger, content) + VALUES (?, ?, datetime('now'), 'pending', ?, ?, ?)`, ) - .run(id, kind, opts?.processAfter ?? null, JSON.stringify(content)); + .run(id, kind, opts?.processAfter ?? null, opts?.trigger ?? 1, JSON.stringify(content)); } describe('formatter', () => { @@ -84,6 +84,51 @@ describe('formatter', () => { }); }); +describe('accumulate gate (trigger column)', () => { + it('getPendingMessages returns both trigger=0 and trigger=1 rows', () => { + // trigger=0 rides along as context, trigger=1 is the wake-eligible row. + // The poll loop's gate depends on this data contract. + insertMessage('m1', 'chat', { sender: 'A', text: 'chit chat' }, { trigger: 0 }); + insertMessage('m2', 'chat', { sender: 'B', text: 'actual mention' }, { trigger: 1 }); + const messages = getPendingMessages(); + expect(messages).toHaveLength(2); + const byId = Object.fromEntries(messages.map((m) => [m.id, m])); + expect(byId.m1.trigger).toBe(0); + expect(byId.m2.trigger).toBe(1); + }); + + it('trigger=0-only batch: gate predicate `some(trigger===1)` is false', () => { + insertMessage('m1', 'chat', { sender: 'A', text: 'noise' }, { trigger: 0 }); + insertMessage('m2', 'chat', { sender: 'B', text: 'more noise' }, { trigger: 0 }); + const messages = getPendingMessages(); + // This is the exact predicate the poll loop uses to skip accumulate-only + // batches — gate should be false, so the loop sleeps without waking the agent. + expect(messages.some((m) => m.trigger === 1)).toBe(false); + }); + + it('mixed batch: gate is true → loop proceeds, accumulated rows ride along', () => { + insertMessage('m1', 'chat', { sender: 'A', text: 'earlier chatter' }, { trigger: 0 }); + insertMessage('m2', 'chat', { sender: 'B', text: 'the real mention' }, { trigger: 1 }); + const messages = getPendingMessages(); + expect(messages.some((m) => m.trigger === 1)).toBe(true); + // Both messages are present for the formatter → agent sees the prior context. + expect(messages.map((m) => m.id).sort()).toEqual(['m1', 'm2']); + }); + + it('trigger column defaults to 1 for legacy inserts without explicit value', () => { + // The schema default is 1 (see src/db/schema.ts INBOUND_SCHEMA) — existing + // rows / tests without the column set are effectively wake-eligible. + getInboundDb() + .prepare( + `INSERT INTO messages_in (id, kind, timestamp, status, content) + VALUES ('m1', 'chat', datetime('now'), 'pending', '{"text":"hi"}')`, + ) + .run(); + const [msg] = getPendingMessages(); + expect(msg.trigger).toBe(1); + }); +}); + describe('routing', () => { it('should extract routing from messages', () => { getInboundDb() diff --git a/container/agent-runner/src/poll-loop.ts b/container/agent-runner/src/poll-loop.ts index 8a4ec7dc2..3f0e364be 100644 --- a/container/agent-runner/src/poll-loop.ts +++ b/container/agent-runner/src/poll-loop.ts @@ -72,6 +72,19 @@ export async function runPollLoop(config: PollLoopConfig): Promise { continue; } + // Accumulate gate: if the batch contains only trigger=0 rows + // (context-only, router-stored under ignored_message_policy='accumulate'), + // don't wake the agent. Leave them `pending` — they'll ride along the + // next time a real trigger=1 message lands via this same getPendingMessages + // query. Without this gate, a warm container keeps processing + // (and potentially responding to) every accumulate-only batch, defeating + // the "store as context, don't engage" contract. Host-side countDueMessages + // gates the same way for wake-from-cold (see src/db/session-db.ts). + if (!messages.some((m) => m.trigger === 1)) { + await sleep(POLL_INTERVAL_MS); + continue; + } + const ids = messages.map((m) => m.id); markProcessing(ids); From f894b5b1d009090033b96423058e689054eee46f Mon Sep 17 00:00:00 2001 From: Ira Abramov Date: Mon, 20 Apr 2026 12:11:35 +0300 Subject: [PATCH 32/95] chore: ignore .env* variants in addition to .env Catches .env.local, .env.test, .env.production, and other variant files that should never be committed alongside the base .env. --- .gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/.gitignore b/.gitignore index 103574500..8c02e07ab 100644 --- a/.gitignore +++ b/.gitignore @@ -23,6 +23,7 @@ groups/global/* # Secrets *.keys.json .env +.env* # Temp files .tmp-* From 0105de025731faef9239f7d1f76c3ac94c6081da Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 12:15:52 +0300 Subject: [PATCH 33/95] fix(host-sweep): skip ceiling check when heartbeat file is absent MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit decideStuckAction treated a missing heartbeat file as heartbeatAge = Infinity, which always exceeded the 30-minute ceiling. Result: every freshly-spawned container got killed within seconds of spawn on the first sweep pass because it hadn't produced an SDK event yet (heartbeat is only touched on SDK events inside processQuery, not on boot). Skip the ceiling branch when heartbeatMtimeMs === 0. Containers that genuinely never wrote a heartbeat because they died are caught by the separate "container process not running" cleanup path. Containers that boot, claim a message, but hang at the gate are caught by the claim-stuck check below — which correctly fires regardless of heartbeat presence once claimAge exceeds tolerance. Updates the "absent heartbeat → kill-ceiling" test (which was encoding the bug) and adds a companion that the claim-stuck path still fires for absent-heartbeat containers with aged claims. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/host-sweep.test.ts | 24 +++++++++++++++++++++--- src/host-sweep.ts | 18 ++++++++++++++---- 2 files changed, 35 insertions(+), 7 deletions(-) diff --git a/src/host-sweep.test.ts b/src/host-sweep.test.ts index d9505a4ae..eefcc8af0 100644 --- a/src/host-sweep.test.ts +++ b/src/host-sweep.test.ts @@ -39,14 +39,32 @@ describe('decideStuckAction', () => { expect(res.heartbeatAgeMs).toBeGreaterThan(ABSOLUTE_CEILING_MS); }); - it('treats an absent heartbeat file as infinitely stale', () => { + it('skips the ceiling check when no heartbeat file exists (fresh container not yet ticked)', () => { + // A freshly-spawned container hasn't produced any SDK events yet, so no + // heartbeat. Prior behavior treated this as infinitely stale and killed + // every container within seconds of spawn. With no claims either, we + // should conclude everything is fine. const res = decideStuckAction({ now: BASE, heartbeatMtimeMs: 0, containerState: null, claims: [], }); - expect(res.action).toBe('kill-ceiling'); + expect(res.action).toBe('ok'); + }); + + it('kills on claim-stuck when heartbeat is absent AND a claim has aged past tolerance', () => { + // Hanging fresh container: spawned, picked up a message (claim recorded + // in processing_ack), but never wrote a heartbeat. Falls through the + // skipped ceiling check into claim-stuck — which correctly fires. + const claimedAgeMs = CLAIM_STUCK_MS + 5_000; + const res = decideStuckAction({ + now: BASE, + heartbeatMtimeMs: 0, + containerState: null, + claims: [claim('msg-1', claimedAgeMs)], + }); + expect(res.action).toBe('kill-claim'); }); it('extends the ceiling when Bash has a declared timeout longer than 30 min', () => { @@ -105,7 +123,7 @@ describe('decideStuckAction', () => { const res = decideStuckAction({ now: BASE, // 5 min since claim, over the 60s default but under the declared Bash timeout - heartbeatMtimeMs: BASE - (5 * 60 * 1000) - 5_000, + heartbeatMtimeMs: BASE - 5 * 60 * 1000 - 5_000, containerState: { current_tool: 'Bash', tool_declared_timeout_ms: tenMinMs, diff --git a/src/host-sweep.ts b/src/host-sweep.ts index 0f8365c80..1a2901ccc 100644 --- a/src/host-sweep.ts +++ b/src/host-sweep.ts @@ -75,11 +75,21 @@ export function decideStuckAction(args: { }): StuckDecision { const { now, heartbeatMtimeMs, containerState, claims } = args; const declaredBashMs = bashTimeoutMs(containerState); - const heartbeatAge = heartbeatMtimeMs === 0 ? Infinity : now - heartbeatMtimeMs; - const ceiling = Math.max(ABSOLUTE_CEILING_MS, declaredBashMs ?? 0); - if (heartbeatAge > ceiling) { - return { action: 'kill-ceiling', heartbeatAgeMs: heartbeatAge, ceilingMs: ceiling }; + // Ceiling check only applies when we have an actual heartbeat timestamp. + // A freshly-spawned container hasn't had any SDK activity yet so no + // heartbeat file exists — if we treated that as infinitely stale we'd + // kill every container within seconds of spawn. Genuinely-dead containers + // that never wrote a heartbeat are caught by the separate "container + // process not running" cleanup path, not here. If a fresh container is + // hanging at the gate (claimed a message but never did anything) the + // claim-stuck check below handles it. + if (heartbeatMtimeMs !== 0) { + const heartbeatAge = now - heartbeatMtimeMs; + const ceiling = Math.max(ABSOLUTE_CEILING_MS, declaredBashMs ?? 0); + if (heartbeatAge > ceiling) { + return { action: 'kill-ceiling', heartbeatAgeMs: heartbeatAge, ceilingMs: ceiling }; + } } const tolerance = Math.max(CLAIM_STUCK_MS, declaredBashMs ?? 0); From f74df3b0d3cf30ce4cae5e26c7c6373d21d87e2f Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 12:16:20 +0300 Subject: [PATCH 34/95] fix(router): trust SDK isMention signal; drop broken hasMention regex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The router's mention / mention-sticky engage check was regex-matching @ (e.g. @Andy) against message text. Platforms don't work that way — users address bots via the bot's platform username (@nanoclaw_v2_refactr_1_bot on Telegram, user-id mentions on Slack / Discord). The regex matched only coincidentally and never on Telegram, so mention-mode wirings silently never fired there. Two parallel mention detectors existed: the Chat SDK's onNewMention, which correctly resolves the bot's platform identity, and the router's hasMention text regex, which ignored the SDK verdict and invented its own heuristic. The router's detector was wrong in principle — the agent group's display name is a NanoClaw-side nickname, not a platform address. Thread the SDK signal through: InboundMessage gains an optional `isMention` field, the bridge sets it from each handler (onNewMention → true, onDirectMessage → true, onSubscribedMessage → message.isMention, onNewMessage(/./) → false), src/index.ts forwards it into InboundEvent, and evaluateEngage now checks `isMention === true` for mention modes. hasMention deleted entirely — there is only one source of truth for "did the user mention this bot": the platform / SDK. Agent-name-in-text matching for disambiguating multiple agents wired to one chat is a separate feature; users can express it today with engage_mode='pattern' + the agent's name as the regex. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/channels/adapter.ts | 15 +++++++++++ src/channels/chat-sdk-bridge.ts | 19 ++++++++++---- src/index.ts | 1 + src/router.ts | 45 +++++++++++++++++++++------------ 4 files changed, 59 insertions(+), 21 deletions(-) diff --git a/src/channels/adapter.ts b/src/channels/adapter.ts index 34b367555..bbf7f3749 100644 --- a/src/channels/adapter.ts +++ b/src/channels/adapter.ts @@ -60,6 +60,21 @@ export interface InboundMessage { kind: 'chat' | 'chat-sdk'; content: unknown; // JS object — host will JSON.stringify before writing to session DB timestamp: string; + /** + * Platform-confirmed signal that this message is a mention of the bot. + * + * Set by adapters that know the platform's own mention semantics — e.g. + * the Chat SDK bridge sets it true from `onNewMention` / `onDirectMessage` + * and forwards `message.isMention` from `onSubscribedMessage`. Use this + * in the router instead of agent-name regex matching, which breaks on + * platforms where the mention text is the bot's platform username (e.g. + * Telegram's `@nanoclaw_v2_refactr_1_bot`) rather than the agent_group + * display name (e.g. `@Andy`). + * + * Adapters that don't set it (native / legacy) leave it undefined — the + * router falls back to text-match against agent_group_name. + */ + isMention?: boolean; } /** A file attachment to deliver alongside a message. */ diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index aa980abf0..bea4c169e 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -210,7 +210,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter return shouldEngage(conversations, channelId, source, text); } - async function messageToInbound(message: ChatMessage): Promise { + async function messageToInbound(message: ChatMessage, isMention: boolean): Promise { // eslint-disable-next-line @typescript-eslint/no-explicit-any const serialized = message.toJSON() as Record; @@ -266,6 +266,7 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter kind: 'chat-sdk', content: serialized, timestamp: message.metadata.dateSent.toISOString(), + isMention, }; } @@ -296,7 +297,10 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter const text = typeof message.text === 'string' ? message.text : ''; const decision = engageDecision(channelId, 'subscribed', text); if (!decision.forward) return; - await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); + // Subscribed path: the SDK sets message.isMention when the bot was + // @-mentioned in an already-subscribed thread (docs at + // handling-events.mdx). Forward it verbatim. + await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, message.isMention === true)); }); // @mention in an unsubscribed thread — always engage; subscribe only @@ -306,7 +310,8 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter const text = typeof message.text === 'string' ? message.text : ''; const decision = engageDecision(channelId, 'mention', text); if (!decision.forward) return; - await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); + // onNewMention only fires when the SDK confirms the bot was mentioned. + await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, true)); if (decision.stickySubscribe) { await thread.subscribe(); } @@ -332,7 +337,9 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter forward: decision.forward, }); if (!decision.forward) return; - await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); + // A DM is by definition addressed to the bot — treat as a mention + // for routing purposes. `mention` / `mention-sticky` wirings fire. + await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, true)); if (decision.stickySubscribe) { await thread.subscribe(); } @@ -357,7 +364,9 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter const text = typeof message.text === 'string' ? message.text : ''; const decision = engageDecision(channelId, 'new-message', text); if (!decision.forward) return; - await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message)); + // SDK dispatch guarantees this is a non-mention non-DM message in an + // unsubscribed thread — isMention is definitively false here. + await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, false)); }); // Handle button clicks (ask_user_question) diff --git a/src/index.ts b/src/index.ts index 4958eef74..595ba1b8c 100644 --- a/src/index.ts +++ b/src/index.ts @@ -83,6 +83,7 @@ async function main(): Promise { kind: message.kind, content: JSON.stringify(message.content), timestamp: message.timestamp, + isMention: message.isMention, }, }).catch((err) => { log.error('Failed to route inbound message', { channelType: adapter.channelType, err }); diff --git a/src/router.ts b/src/router.ts index cb4ee939f..a3e8f06f0 100644 --- a/src/router.ts +++ b/src/router.ts @@ -42,6 +42,15 @@ export interface InboundEvent { kind: 'chat' | 'chat-sdk'; content: string; // JSON blob timestamp: string; + /** + * Platform-confirmed bot-mention signal forwarded from the adapter. + * When defined, it's authoritative — use this instead of text-matching + * agent_group_name, which breaks on platforms where the mention token + * is the bot's platform username (e.g. Telegram). undefined means the + * adapter doesn't provide the signal; evaluateEngage falls back to + * agent-name regex. + */ + isMention?: boolean; }; } @@ -194,6 +203,7 @@ export async function routeInbound(event: InboundEvent): Promise { // engage later. Drop policy = skip silently. const parsed = safeParseContent(event.message.content); const messageText = parsed.text ?? ''; + const isMention = event.message.isMention === true; let engagedCount = 0; let accumulatedCount = 0; @@ -202,7 +212,7 @@ export async function routeInbound(event: InboundEvent): Promise { const agentGroup = getAgentGroup(agent.agent_group_id); if (!agentGroup) continue; - const engages = evaluateEngage(agent, agentGroup, messageText, mg, event.threadId); + const engages = evaluateEngage(agent, messageText, isMention, mg, event.threadId); const accessOk = engages && (!accessGate || accessGate(event, userId, mg, agent.agent_group_id).allowed); const scopeOk = engages && (!senderScopeGate || senderScopeGate(event, userId, mg, agent).allowed); @@ -241,17 +251,26 @@ export async function routeInbound(event: InboundEvent): Promise { * Decide whether a given wired agent should engage on this message. * * 'pattern' — regex test on text; '.' = always - * 'mention' — bot must be @-mentioned by its agent-group name - * 'mention-sticky' — @mention OR an active per-thread session already - * exists for this (agent, mg, thread). The session - * existence IS our subscription state; once a thread - * has engaged us once, follow-ups arrive with no - * mention and should still fire. + * 'mention' — bot must be mentioned on the platform. Resolved by + * the adapter (SDK-level) and forwarded as + * `event.message.isMention`. Agent display name + * (`agent_group.name`) is irrelevant — users address + * the bot via its platform username (@botname on + * Telegram, user-id mention on Slack/Discord), not + * via the agent's NanoClaw-side display name. If a + * user wants to disambiguate between multiple agents + * wired to one chat, use engage_mode='pattern' with + * the disambiguator as the regex. + * 'mention-sticky' — platform mention OR an active per-thread session + * already exists for this (agent, mg, thread). The + * session existence IS our subscription state; once + * a thread has engaged us once, follow-ups arrive + * with no mention and should still fire. */ function evaluateEngage( agent: MessagingGroupAgent, - agentGroup: AgentGroup, text: string, + isMention: boolean, mg: MessagingGroup, threadId: string | null, ): boolean { @@ -267,9 +286,9 @@ function evaluateEngage( } } case 'mention': - return hasMention(text, agentGroup.name); + return isMention; case 'mention-sticky': { - if (hasMention(text, agentGroup.name)) return true; + if (isMention) return true; // Sticky follow-up: session already exists for this (agent, mg, thread) // — the thread was activated before, keep firing. if (mg.is_group === 0) return false; // DMs never use mention-sticky sensibly @@ -281,12 +300,6 @@ function evaluateEngage( } } -function hasMention(text: string, agentName: string): boolean { - if (!agentName) return false; - const escaped = agentName.replace(/[.*+?^${}()|[\]\\]/g, '\\$&'); - return new RegExp(`@${escaped}\\b`, 'i').test(text); -} - async function deliverToAgent( agent: MessagingGroupAgent, agentGroup: AgentGroup, From 68058cbc4a553b74ee08fc0808516d565685d31c Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 12:16:35 +0300 Subject: [PATCH 35/95] fix(permissions): authorize unknown-sender approval clicks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The approval click handler trusted row.approver_user_id as the actor regardless of who actually clicked the card. A random user who received the forwarded card could click Approve and get the stranger admitted to the agent group — their click was simply not checked. Separately, payload.userId arrives as the raw platform userId from Chat SDK onAction (e.g. "6037840640"), not the namespaced form ("telegram:6037840640") that matches users(id). Without namespacing, users-table lookups miss. Namespace the clicker id with payload.channelType, then authorize: the clicker must be either the designated approver OR have owner / admin privilege over the agent group (hasAdminPrivilege covers owner, global admin, scoped admin). Unauthorized clicks return true (claim the response so the registry doesn't log it as unclaimed) but take no action — the pending row stays in place so a legitimate approver can still act on it. Existing tests passed a pre-namespaced userId directly, masking the first bug. Fixed the fixtures to match production plumbing and added two tests: one asserts a random bystander's click is rejected (row stays pending, no member added), the other asserts a global admin can approve even when they weren't the designated approver. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/modules/permissions/index.ts | 24 ++++- .../permissions/sender-approval.test.ts | 95 +++++++++++++++++-- 2 files changed, 106 insertions(+), 13 deletions(-) diff --git a/src/modules/permissions/index.ts b/src/modules/permissions/index.ts index 1d505b68d..d13797b74 100644 --- a/src/modules/permissions/index.ts +++ b/src/modules/permissions/index.ts @@ -29,10 +29,8 @@ import { log } from '../../log.js'; import type { MessagingGroup, MessagingGroupAgent } from '../../types.js'; import { canAccessAgentGroup } from './access.js'; import { addMember } from './db/agent-group-members.js'; -import { - deletePendingSenderApproval, - getPendingSenderApproval, -} from './db/pending-sender-approvals.js'; +import { deletePendingSenderApproval, getPendingSenderApproval } from './db/pending-sender-approvals.js'; +import { hasAdminPrivilege } from './db/user-roles.js'; import { getUser, upsertUser } from './db/users.js'; import { requestSenderApproval } from './sender-approval.js'; @@ -198,7 +196,23 @@ async function handleSenderApprovalResponse(payload: ResponsePayload): Promise { expect(deliverMock).toHaveBeenCalledTimes(1); const { getDb } = await import('../../db/connection.js'); - const count = ( - getDb().prepare('SELECT COUNT(*) AS c FROM pending_sender_approvals').get() as { c: number } - ).c; + const count = (getDb().prepare('SELECT COUNT(*) AS c FROM pending_sender_approvals').get() as { c: number }).c; expect(count).toBe(1); }); @@ -208,7 +206,10 @@ describe('unknown-sender request_approval flow', () => { const claimed = await handler({ questionId: pending.id, value: 'approve', - userId: 'telegram:owner', + // Chat SDK's onAction surfaces the raw platform userId (e.g. Telegram + // chat id). The permissions handler namespaces it with channelType to + // match users(id). + userId: 'owner', channelType: 'telegram', platformId: 'dm-owner', threadId: null, @@ -245,7 +246,7 @@ describe('unknown-sender request_approval flow', () => { const claimed = await handler({ questionId: pending.id, value: 'reject', - userId: 'telegram:owner', + userId: 'owner', // raw platform id — handler namespaces with channelType channelType: 'telegram', platformId: 'dm-owner', threadId: null, @@ -253,13 +254,91 @@ describe('unknown-sender request_approval flow', () => { if (claimed) break; } - const count = ( - getDb().prepare('SELECT COUNT(*) AS c FROM pending_sender_approvals').get() as { c: number } - ).c; + const count = (getDb().prepare('SELECT COUNT(*) AS c FROM pending_sender_approvals').get() as { c: number }).c; expect(count).toBe(0); const member = getDb() .prepare('SELECT 1 AS x FROM agent_group_members WHERE user_id = ? AND agent_group_id = ?') .get('tg:stranger', 'ag-1'); expect(member).toBeUndefined(); }); + + it('rejects clicks from an unauthorized user (prevents self-admit via forwarded card)', async () => { + // Stranger triggers the approval flow; card goes to the owner. + const { routeInbound } = await import('../../router.js'); + const { getResponseHandlers } = await import('../../response-registry.js'); + + await routeInbound(stranger('can I play')); + await new Promise((r) => setTimeout(r, 10)); + + const { getDb } = await import('../../db/connection.js'); + const pending = getDb().prepare('SELECT id FROM pending_sender_approvals').get() as { id: string }; + expect(pending).toBeDefined(); + + // A random user (not the stranger, not the owner, not an admin) tries to + // click the approval — e.g. they got the card forwarded. Should be + // rejected without admitting them. + for (const handler of getResponseHandlers()) { + const claimed = await handler({ + questionId: pending.id, + value: 'approve', + userId: 'random-bystander', // not owner, not admin + channelType: 'telegram', + platformId: 'dm-random', + threadId: null, + }); + if (claimed) break; + } + + // No member added for the stranger. + const member = getDb() + .prepare('SELECT 1 AS x FROM agent_group_members WHERE user_id = ? AND agent_group_id = ?') + .get('tg:stranger', 'ag-1'); + expect(member).toBeUndefined(); + + // Pending row is still there — a legitimate approver can still act on it. + const stillPending = (getDb().prepare('SELECT COUNT(*) AS c FROM pending_sender_approvals').get() as { c: number }) + .c; + expect(stillPending).toBe(1); + }); + + it('accepts a click from a global admin even if they are not the designated approver', async () => { + // Pre-seed a separate admin user so we can click as them. + upsertUser({ id: 'telegram:admin-bob', kind: 'telegram', display_name: 'Bob', created_at: now() }); + grantRole({ + user_id: 'telegram:admin-bob', + role: 'admin', + agent_group_id: null, + granted_by: 'telegram:owner', + granted_at: now(), + }); + + const { routeInbound } = await import('../../router.js'); + const { getResponseHandlers } = await import('../../response-registry.js'); + + await routeInbound(stranger('knock knock')); + await new Promise((r) => setTimeout(r, 10)); + + const { getDb } = await import('../../db/connection.js'); + const pending = getDb().prepare('SELECT id FROM pending_sender_approvals').get() as { id: string }; + expect(pending).toBeDefined(); + + // Admin clicks approve (not the designated approver, which was owner). + for (const handler of getResponseHandlers()) { + const claimed = await handler({ + questionId: pending.id, + value: 'approve', + userId: 'admin-bob', + channelType: 'telegram', + platformId: 'dm-bob', + threadId: null, + }); + if (claimed) break; + } + + // Stranger admitted thanks to the admin's authority. + const member = getDb() + .prepare('SELECT 1 AS x FROM agent_group_members WHERE user_id = ? AND agent_group_id = ?') + .get('tg:stranger', 'ag-1'); + expect(member).toBeDefined(); + }); }); From b15972284b60dcb94025525180f6f17557098812 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 13:32:08 +0300 Subject: [PATCH 36/95] refactor(channels): shrink bridge shouldEngage to flood gate + subscribe signal MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Before this change the bridge and the router both owned engage_mode policy. Bridge's shouldEngage had a full switch over mention / mention-sticky / pattern + source-based rules + engage_pattern regex test + ignored_message_policy accumulate fallback. Router's evaluateEngage had the same switch against the same fields. Two parallel logic paths with subtle vocabulary differences (bridge: "which SDK handler fired"; router: "what isMention says"). Every time we touched one we had to reason about the other — the Telegram hasMention bug and the "pattern mode silently drops in group chats" bug were both drift between the two. Refactor to one place. Router keeps all per-wiring policy — engage mode, pattern regex, sender scope, ignored-message policy — unchanged. Bridge drops to a coarse flood gate + subscribe signal: - forward: does this channel have ANY wiring? Forward if yes. Unknown channels still forward for subscribed/mention/dm (they may be newly auto-created, or will trigger the coming channel-registration flow). Unknown channels DROP for new-message so we don't flood from every unsubscribed thread the bot happens to sit in. - stickySubscribe: any mention-sticky wiring on the channel AND the source is mention or dm. Coarse union — subscribe is idempotent and one call serves every sticky wiring. The `text` param on shouldEngage is gone (pattern regex lives in the router now). Four bridge handler sites simplify accordingly. messageToInbound still carries the SDK-confirmed isMention flag through to the router unchanged. Behavioral delta: pure-mention-wired channels (no pattern, no accumulate) will now see every plain group message reach the router before being dropped there, where before the bridge dropped at the transport boundary. Extra DB lookup per dropped message in this specific case; acceptable for the cleaner seam and can be optimized back at the bridge if it ever matters in practice. Bridge tests prune the 10 engage_mode-specific cases that covered logic now owned by evaluateEngage in the router (host-core.test.ts covers it end-to-end through routeInbound). Bridge tests keep only what's bridge-specific: the flood gate and the stickySubscribe coarse union. 172 tests pass (was 182 — net -10 redundant bridge tests). Co-Authored-By: Claude Opus 4.7 (1M context) --- src/channels/chat-sdk-bridge.test.ts | 180 +++++++-------------------- src/channels/chat-sdk-bridge.ts | 172 ++++++++----------------- 2 files changed, 98 insertions(+), 254 deletions(-) diff --git a/src/channels/chat-sdk-bridge.test.ts b/src/channels/chat-sdk-bridge.test.ts index aad8d0a03..3c6caa8c1 100644 --- a/src/channels/chat-sdk-bridge.test.ts +++ b/src/channels/chat-sdk-bridge.test.ts @@ -61,160 +61,74 @@ describe('createChatSdkBridge', () => { }); }); -describe('shouldEngage', () => { - describe('unknown conversation', () => { +describe('shouldEngage (bridge-level flood gate + subscribe signal)', () => { + // Per-wiring engage_mode / engage_pattern / ignored_message_policy + // semantics live in the router (evaluateEngage / routeInbound fan-out). + // These tests only cover the bridge's two responsibilities: should we + // forward at all, and should we call thread.subscribe(). + + describe('flood gate — unknown conversation', () => { const empty = new Map(); - const sources: EngageSource[] = ['subscribed', 'mention', 'dm']; - for (const source of sources) { - it(`forwards for source='${source}' (may be a not-yet-wired group)`, () => { - expect(shouldEngage(empty, 'C1', source, '')).toEqual({ forward: true, stickySubscribe: false }); + const carriedSources: EngageSource[] = ['subscribed', 'mention', 'dm']; + for (const source of carriedSources) { + it(`forwards for source='${source}' (may be a newly-auto-created channel or a channel-registration trigger)`, () => { + expect(shouldEngage(empty, 'C-new', source)).toEqual({ forward: true, stickySubscribe: false }); }); } - it("DROPS for source='new-message' (would flood from unwired channels)", () => { - expect(shouldEngage(empty, 'C1', 'new-message', 'hello')).toEqual({ + it("DROPS for source='new-message' (onNewMessage(/./) fires for every unsubscribed thread the bot can see — would flood)", () => { + expect(shouldEngage(empty, 'C-unwired', 'new-message')).toEqual({ forward: false, stickySubscribe: false, }); }); }); - describe("engageMode='mention' + ignoredMessagePolicy='drop' (default)", () => { + describe('known conversation — bridge forwards regardless of engage mode', () => { + // Policy lives in the router now. The bridge only knows "has any wiring". const conv = mapFor(cfg({ engageMode: 'mention' })); - it('forwards on mention + dm', () => { - expect(shouldEngage(conv, 'C1', 'mention', '').forward).toBe(true); - expect(shouldEngage(conv, 'C1', 'dm', '').forward).toBe(true); - }); - it('does NOT forward on subscribed or new-message (prevents keep-firing + flooding)', () => { - expect(shouldEngage(conv, 'C1', 'subscribed', '').forward).toBe(false); - expect(shouldEngage(conv, 'C1', 'new-message', '').forward).toBe(false); - }); - it('never asks to subscribe', () => { - for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { - expect(shouldEngage(conv, 'C1', s, '').stickySubscribe).toBe(false); - } - }); - }); - - describe("engageMode='mention-sticky'", () => { - const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); - it('forwards on mention + dm with stickySubscribe=true', () => { - expect(shouldEngage(conv, 'C1', 'mention', '')).toEqual({ forward: true, stickySubscribe: true }); - expect(shouldEngage(conv, 'C1', 'dm', '')).toEqual({ forward: true, stickySubscribe: true }); - }); - it('forwards subscribed follow-ups without re-subscribing', () => { - expect(shouldEngage(conv, 'C1', 'subscribed', '')).toEqual({ forward: true, stickySubscribe: false }); - }); - it('does NOT forward on new-message (explicit mention required to start)', () => { - expect(shouldEngage(conv, 'C1', 'new-message', '').forward).toBe(false); - }); - }); - - describe("engageMode='pattern'", () => { - it('pattern="." forwards on every source (when conversation is known)', () => { - const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '.' })); - for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { - expect(shouldEngage(conv, 'C1', s, 'anything').forward).toBe(true); - } - }); - - it('tests regex against text on new-message (the main bug fix)', () => { - const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '^!report' })); - expect(shouldEngage(conv, 'C1', 'new-message', '!report now').forward).toBe(true); - expect(shouldEngage(conv, 'C1', 'new-message', 'nothing to see').forward).toBe(false); - }); - - it('pattern regex applies on every source (symmetry)', () => { - const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: 'deploy' })); - for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { - expect(shouldEngage(conv, 'C1', s, 'time to deploy').forward).toBe(true); - expect(shouldEngage(conv, 'C1', s, 'weather today').forward).toBe(false); - } - }); - - it('pattern never triggers sticky-subscribe', () => { - const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '.' })); - for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { - expect(shouldEngage(conv, 'C1', s, 'hi').stickySubscribe).toBe(false); - } - }); - - it('invalid regex fails open (admin sees something rather than silent drop)', () => { - const conv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '[unclosed' })); - expect(shouldEngage(conv, 'C1', 'new-message', 'x').forward).toBe(true); - }); - }); - - describe("ignoredMessagePolicy='accumulate'", () => { - it('forwards non-engaging new-message so the router can store it as context (trigger=0)', () => { - const conv = mapFor(cfg({ engageMode: 'mention', ignoredMessagePolicy: 'accumulate' })); - // Plain message in unsubscribed group — mention rule says no engage, - // but accumulate says forward anyway. - expect(shouldEngage(conv, 'C1', 'new-message', 'chit chat')).toEqual({ - forward: true, - stickySubscribe: false, + for (const source of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { + it(`forwards for source='${source}' — router will decide engage / accumulate / drop per wiring`, () => { + expect(shouldEngage(conv, 'C1', source).forward).toBe(true); }); - }); - - it('forwards non-engaging subscribed messages for accumulation', () => { - // mention wiring in a subscribed thread: the mention handler already - // fired once, thread is now subscribed, follow-ups route here. The - // base 'mention' rule wouldn't engage without an @-mention, but - // accumulate says capture the context. - const conv = mapFor(cfg({ engageMode: 'mention', ignoredMessagePolicy: 'accumulate' })); - expect(shouldEngage(conv, 'C1', 'subscribed', 'follow up talk').forward).toBe(true); - }); - - it('does NOT set stickySubscribe purely from accumulate (avoid misleading bot presence)', () => { - const conv = mapFor(cfg({ engageMode: 'mention-sticky', ignoredMessagePolicy: 'accumulate' })); - expect(shouldEngage(conv, 'C1', 'new-message', 'plain').stickySubscribe).toBe(false); - }); - - it("accumulate doesn't override the 'unknown conversation → drop new-message' rule", () => { - // Unknown conversation (not in map): accumulate can't be read because - // there's no config to read from. We still drop. - const empty = new Map(); - expect(shouldEngage(empty, 'C-unknown', 'new-message', 'x').forward).toBe(false); - }); - - it("drop policy + non-engaging message → doesn't forward", () => { - const conv = mapFor(cfg({ engageMode: 'mention', ignoredMessagePolicy: 'drop' })); - expect(shouldEngage(conv, 'C1', 'new-message', 'plain').forward).toBe(false); - }); - - it('engaging message with drop policy still forwards (engage wins regardless)', () => { - const conv = mapFor(cfg({ engageMode: 'mention', ignoredMessagePolicy: 'drop' })); - expect(shouldEngage(conv, 'C1', 'mention', '@bot hi').forward).toBe(true); - }); + } }); - describe('multiple wirings on one conversation', () => { - it('takes the union across wirings (any-engage wins)', () => { - // mention wiring + pattern wiring on the same channel. A plain message - // should engage via the pattern wiring even though the mention wiring - // alone would reject it. - const conv = mapFor( - cfg({ agentGroupId: 'ag-a', engageMode: 'mention' }), - cfg({ agentGroupId: 'ag-b', engageMode: 'pattern', engagePattern: '^hi' }), - ); - expect(shouldEngage(conv, 'C1', 'new-message', 'hi there').forward).toBe(true); - expect(shouldEngage(conv, 'C1', 'new-message', 'something else').forward).toBe(false); + describe('stickySubscribe signal', () => { + it('true when any mention-sticky wiring exists AND source is mention', () => { + const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); + expect(shouldEngage(conv, 'C1', 'mention').stickySubscribe).toBe(true); }); - it('any accumulate wiring causes forward even if all others would drop', () => { - const conv = mapFor( - cfg({ agentGroupId: 'ag-a', engageMode: 'mention', ignoredMessagePolicy: 'drop' }), - cfg({ agentGroupId: 'ag-b', engageMode: 'mention', ignoredMessagePolicy: 'accumulate' }), - ); - // Plain message: ag-a would drop, ag-b would accumulate → forward. - expect(shouldEngage(conv, 'C1', 'new-message', 'plain').forward).toBe(true); + it('true when any mention-sticky wiring exists AND source is dm', () => { + const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); + expect(shouldEngage(conv, 'C1', 'dm').stickySubscribe).toBe(true); }); - it('stickySubscribe from any mention-sticky wiring wins', () => { + it('false on subscribed — thread is already subscribed, no need to re-subscribe', () => { + const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); + expect(shouldEngage(conv, 'C1', 'subscribed').stickySubscribe).toBe(false); + }); + + it('false on new-message — mention-sticky requires an explicit mention to start', () => { + const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); + expect(shouldEngage(conv, 'C1', 'new-message').stickySubscribe).toBe(false); + }); + + it('false for plain mention / pattern wirings (not sticky)', () => { + const mentionConv = mapFor(cfg({ engageMode: 'mention' })); + const patternConv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '.' })); + for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { + expect(shouldEngage(mentionConv, 'C1', s).stickySubscribe).toBe(false); + expect(shouldEngage(patternConv, 'C1', s).stickySubscribe).toBe(false); + } + }); + + it('fires on coarse union — mixed wirings where any one is mention-sticky', () => { const conv = mapFor( cfg({ agentGroupId: 'ag-a', engageMode: 'mention' }), cfg({ agentGroupId: 'ag-b', engageMode: 'mention-sticky' }), ); - expect(shouldEngage(conv, 'C1', 'mention', '')).toEqual({ forward: true, stickySubscribe: true }); + expect(shouldEngage(conv, 'C1', 'mention').stickySubscribe).toBe(true); }); }); }); diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index bea4c169e..9bed96888 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -85,94 +85,46 @@ export interface ChatSdkBridgeConfig { export type EngageSource = 'subscribed' | 'mention' | 'dm' | 'new-message'; /** - * Should a message from (channelId, source, text) be forwarded to the host, - * and if so, should the bridge subscribe the thread? + * Bridge-level forwarding decision — a coarse flood gate, not policy. + * + * The router owns per-wiring engage_mode / engage_pattern / sender_scope / + * ignored_message_policy (see `evaluateEngage` in src/router.ts). The bridge + * only answers two questions: + * + * 1. `forward` — is this message worth sending to the host at all? + * - Known channel (any wiring): yes. Router will decide what engages / + * accumulates / drops per wiring. + * - Unknown channel: yes for subscribed / mention / DM (triggers the + * router's auto-create or channel-registration flow); no for + * `new-message`. onNewMessage(/./, …) fires for every message in + * every unsubscribed thread the bot can see, including channels the + * bot merely joined but was never wired to — forwarding everything + * would flood the host. + * + * 2. `stickySubscribe` — should the bridge call `thread.subscribe()`? + * - Yes if ANY wiring on this channel is mention-sticky AND the + * source is an actual mention / DM. Coarse (no per-wiring picking) + * but harmless: subscription is idempotent and one call serves + * every mention-sticky wiring on the channel. Once subscribed, + * follow-ups route through onSubscribedMessage. * * Exported for testability — see `chat-sdk-bridge.test.ts`. - * - * We take the union across wired agents: if any wiring would engage OR any - * wiring has `ignoredMessagePolicy='accumulate'`, the message is forwarded. - * The host router then does the per-wiring decision in `deliverToAgent` — - * engaging agents get `trigger=1` (wake), accumulating agents get - * `trigger=0` (store as context, don't wake), drop-policy agents are - * skipped (see `src/router.ts` routeInbound fan-out). - * - * `stickySubscribe` is only set when an actual engage happens (not just - * accumulate) — subscribing a thread we'd only silently accumulate on would - * misrepresent the bot's presence to other users. */ export function shouldEngage( conversations: Map, channelId: string, source: EngageSource, - text: string, ): { forward: boolean; stickySubscribe: boolean } { const configs = conversations.get(channelId); - // Unknown conversation — behavior diverges by source: - // - subscribed/mention/dm: forward anyway. These paths imply some - // prior engagement (subscribe, @mention, DM open) and may be a new - // group that hasn't been registered yet; central routing will log + - // drop cleanly. - // - new-message: DROP. `onNewMessage(/./, …)` fires for every message - // in every unsubscribed thread the bot can see — including channels - // the bot is merely *present* in but not wired to. Forwarding - // everything would flood the host. if (!configs || configs.length === 0) { return { forward: source !== 'new-message', stickySubscribe: false }; } - let engage = false; - let accumulate = false; - let stickySubscribe = false; + const stickySubscribe = + (source === 'mention' || source === 'dm') && configs.some((cfg) => cfg.engageMode === 'mention-sticky'); - for (const cfg of configs) { - let cfgEngages = false; - switch (cfg.engageMode) { - case 'mention': - if (source === 'mention' || source === 'dm') cfgEngages = true; - break; - case 'mention-sticky': - if (source === 'mention' || source === 'dm') { - cfgEngages = true; - stickySubscribe = true; - } else if (source === 'subscribed') { - // Thread was already subscribed on a prior mention — treat as - // engage-all so follow-ups in the thread reach the agent. - cfgEngages = true; - } - // source='new-message' → does not engage (requires explicit mention - // to start). Accumulate policy is evaluated below if set. - break; - case 'pattern': { - // Pattern evaluates on any source that delivers a plain message — - // including new-message, which is the whole reason we registered - // onNewMessage(/./). For mention/dm-delivered messages we still - // test the regex (historical behavior), so pattern='foo' wirings - // only fire on mentions whose text contains 'foo'. - const pattern = cfg.engagePattern ?? '.'; - try { - if (pattern === '.' || new RegExp(pattern).test(text)) cfgEngages = true; - } catch { - // Invalid regex → fail open so the admin can see something is - // happening and fix the pattern. - cfgEngages = true; - } - break; - } - } - - if (cfgEngages) { - engage = true; - } else if (cfg.ignoredMessagePolicy === 'accumulate') { - // Wiring doesn't engage on this message but wants it captured as - // context for its session — forward so the router can write it with - // trigger=0. - accumulate = true; - } - } - - return { forward: engage || accumulate, stickySubscribe }; + return { forward: true, stickySubscribe }; } export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter { @@ -202,12 +154,8 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter return map; } - function engageDecision( - channelId: string, - source: EngageSource, - text: string, - ): { forward: boolean; stickySubscribe: boolean } { - return shouldEngage(conversations, channelId, source, text); + function engageDecision(channelId: string, source: EngageSource): { forward: boolean; stickySubscribe: boolean } { + return shouldEngage(conversations, channelId, source); } async function messageToInbound(message: ChatMessage, isMention: boolean): Promise { @@ -289,46 +237,38 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter logger: 'silent', }); - // Subscribed threads — the conversation is already active (via prior - // mention-sticky engagement or admin wiring). Gate on engageMode so a - // plain 'mention' wiring doesn't keep firing after a one-off mention. + // Four SDK dispatch paths — bridge just forwards; router does all + // per-wiring engage / accumulate / drop decisions. isMention is the + // load-bearing signal (see evaluateEngage in src/router.ts). + + // Subscribed threads — every message in a thread we've previously + // engaged. Carry the SDK's `message.isMention` through so mention-mode + // wirings still fire on in-thread mentions. chat.onSubscribedMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const text = typeof message.text === 'string' ? message.text : ''; - const decision = engageDecision(channelId, 'subscribed', text); + const decision = engageDecision(channelId, 'subscribed'); if (!decision.forward) return; - // Subscribed path: the SDK sets message.isMention when the bot was - // @-mentioned in an already-subscribed thread (docs at - // handling-events.mdx). Forward it verbatim. await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, message.isMention === true)); }); - // @mention in an unsubscribed thread — always engage; subscribe only - // if the wiring is 'mention-sticky'. + // @mention in an unsubscribed thread — SDK-confirmed bot mention. chat.onNewMention(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const text = typeof message.text === 'string' ? message.text : ''; - const decision = engageDecision(channelId, 'mention', text); + const decision = engageDecision(channelId, 'mention'); if (!decision.forward) return; - // onNewMention only fires when the SDK confirms the bot was mentioned. await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, true)); if (decision.stickySubscribe) { await thread.subscribe(); } }); - // DMs — apply engage rules too, but DMs typically default to pattern='.' - // at setup time so this is a pass-through in practice. sticky subscribe - // follows the same rule as a group mention. - // - // Thread id is passed through so sub-thread context reaches delivery - // (Slack users can open threads inside a DM). The router collapses DM - // sub-threads to one session (is_group=0 short-circuits the per-thread - // escalation). + // DMs — by definition addressed to the bot. Thread id flows through + // so sub-thread context reaches delivery (Slack users can open threads + // inside a DM). Router collapses DM sub-threads to one session via + // is_group=0 short-circuit. chat.onDirectMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const text = typeof message.text === 'string' ? message.text : ''; - const decision = engageDecision(channelId, 'dm', text); + const decision = engageDecision(channelId, 'dm'); log.info('Inbound DM received', { adapter: adapter.name, channelId, @@ -337,35 +277,25 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter forward: decision.forward, }); if (!decision.forward) return; - // A DM is by definition addressed to the bot — treat as a mention - // for routing purposes. `mention` / `mention-sticky` wirings fire. await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, true)); if (decision.stickySubscribe) { await thread.subscribe(); } }); - // Plain (non-mention, non-DM) messages in unsubscribed threads. + // Plain messages in unsubscribed threads. // - // Chat SDK dispatch (handling-events.mdx §"Handler dispatch order"): - // subscribed threads → onSubscribedMessage; unsubscribed + mention → - // onNewMention; unsubscribed + pattern match → onNewMessage. Dispatch - // is exclusive — at most one handler fires per message. - // - // Without this handler, `engage_mode='pattern'` is silently dropped in - // unsubscribed group threads because the SDK never surfaces the - // message anywhere else. Registering with `/./` lets every wired - // conversation's regex be evaluated in our `shouldEngage` — unknown - // conversations are dropped there (see the source='new-message' - // branch) so this doesn't flood the host on channels the bot isn't - // wired to. + // Chat SDK dispatch (handling-events.mdx §"Handler dispatch order") is + // exclusive: subscribed → onSubscribedMessage; unsubscribed+mention → + // onNewMention; unsubscribed+pattern-match → onNewMessage. Registering + // with `/./` lets the router see every plain message on wired channels + // (needed for engage_mode='pattern' + ignored_message_policy='accumulate' + // wirings). `shouldEngage` drops unknown channels on this source + // specifically so we don't flood from channels the bot merely joined. chat.onNewMessage(/./, async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const text = typeof message.text === 'string' ? message.text : ''; - const decision = engageDecision(channelId, 'new-message', text); + const decision = engageDecision(channelId, 'new-message'); if (!decision.forward) return; - // SDK dispatch guarantees this is a non-mention non-DM message in an - // unsubscribed thread — isMention is definitively false here. await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, false)); }); From 2eb6907f09396aecef375b9171550171d08d90d7 Mon Sep 17 00:00:00 2001 From: Koshkoshinski Date: Mon, 20 Apr 2026 10:42:40 +0000 Subject: [PATCH 37/95] feat(new-setup): silent CLI wiring + post-service branch point MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Step 6 (CLI agent wiring + first chat) is now invisible to the user. No prompts, no narration — just silent wiring with INFERRED_DISPLAY_NAME and a background ping. On the ping's return, emit one line: Your agent is up, running and ready to go! Step 7 becomes a branch point via AskUserQuestion: either keep chatting via CLI (prints two how-to-chat options: the `!pnpm run chat` bang method inside Claude Code, and the separate-terminal form), or continue to /new-setup-2 for the post-install flow (naming, messaging channel, QoL). The CLI agent at this stage is a scratch agent — its only job is to verify the end-to-end pipeline works. The real name capture happens in /new-setup-2 when the user wires a messaging channel. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup/SKILL.md | 44 +++++++++++++++++++++++++------ 1 file changed, 36 insertions(+), 8 deletions(-) diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index 6b956957f..0a8cc2e8a 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -114,23 +114,51 @@ Start the NanoClaw background service — it relays messages between the user an `pnpm exec tsx setup/index.ts --step service` -### 6. First CLI agent +### 6. Wire the CLI agent and verify end-to-end + +**Do not narrate this step.** No "creating your first agent…", no "sending a ping…" chatter. The user's experience here is: they finished the last visible step (service), then a single success line appears. Wiring is an implementation detail at this point, not a user-facing milestone. If step 2's container build is still running in the background, join it here before proceeding — the agent needs the image. -Create the first agent and wire it to the CLI channel. Ask the user "What should I call you?" first — default the offered value to `INFERRED_DISPLAY_NAME` from the probe. +Use `INFERRED_DISPLAY_NAME` from the probe silently. **Do not ask the user.** The CLI agent at this stage is a scratch agent whose only purpose is to verify the end-to-end pipeline (host → container → agent → back). The user's real name capture happens in `/new-setup-2` when they wire a messaging channel. -`pnpm exec tsx setup/index.ts --step cli-agent -- --display-name ""` +Run wiring and ping back-to-back, silently: -### 7. First chat +``` +pnpm exec tsx setup/index.ts --step cli-agent -- --display-name "" +pnpm run chat ping +``` -Everything's ready — send the first message to the agent. +First container spin-up takes ~60s. When the agent's reply arrives, emit exactly one line to the user: -`pnpm run chat hi` +> Your agent is up, running and ready to go! -The agent should reply within ~60s (first container spin-up is slowest). If no reply, tail `logs/nanoclaw.log`. +If `pnpm run chat ping` times out or errors, tail `logs/nanoclaw.log`, diagnose, and fix — don't surface a half-success. -> **Loose command:** `pnpm run chat hi`. Justification: this is the command the user will keep using after setup. Hiding it behind a `--step` would force them to memorize a second way to do the same thing. +> **Loose command:** `pnpm run chat ping`. Justification: this is the same command the user will keep using after setup, so verification and the real channel are one and the same. + +### 7. Chat now, or keep setting up? + +Ask the user via `AskUserQuestion` which they'd like to do next: + +1. **Keep chatting with the agent via CLI** — happy with the CLI channel for now. +2. **Continue setup** — name the agent, wire a messaging channel, add quality-of-life extras. + +**If they pick "keep chatting":** print both options below, then stop. The user is chatting with the agent now, not with you — no further output from you. + +**Option 1 — from inside this Claude Code session.** Type your message with a leading `!`, which runs it as a bash command in this shell: + +``` +!pnpm run chat your message here +``` + +**Option 2 — from a separate terminal.** Open a new terminal, `cd` into your nanoclaw checkout, then: + +``` +pnpm run chat your message here +``` + +**If they pick "continue setup":** hand off directly to `/new-setup-2` via the Skill tool. That follow-on flow is structured like this one (linear, skippable steps) and covers naming, messaging-channel wiring, and QoL. Invoke it immediately — do not offer a menu of individual skills. ## If anything fails From 4e1cee0e5b4508b8322d5fbf3abe6855608bf99f Mon Sep 17 00:00:00 2001 From: Koshkoshinski Date: Mon, 20 Apr 2026 10:43:14 +0000 Subject: [PATCH 38/95] feat(new-setup-2): phase-2 setup skill + --no-cli-bonus flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit New /new-setup-2 skill, invoked when the user picks "continue setup" at the end of /new-setup. Linear rollthrough; every step skippable: 1. What should the agent call you? 2. What's your agent's name? 3. Messaging channel (plain list, no AskUserQuestion) — invokes the matching /add- skill, captures platform IDs from its output, then wires via init-first-agent.ts with --no-cli-bonus. On success, emits the encouragement line verbatim. 4. Quality-of-life picks (dashboard, compact, karpathy-wiki, plus macos-statusbar only when the probe reports PLATFORM=darwin). 5. Wrap-up. scripts/init-first-agent.ts gains a --no-cli-bonus flag. In DM mode, the bonus "wire new agent to CLI" call is skipped when set. Used by /new-setup-2 so the throwaway CLI-only agent from /new-setup retains clean single-agent ownership of CLI routing instead of being duelled by the real agent on the same channel. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 112 ++++++++++++++++++++++++++++ scripts/init-first-agent.ts | 16 +++- 2 files changed, 125 insertions(+), 3 deletions(-) create mode 100644 .claude/skills/new-setup-2/SKILL.md diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md new file mode 100644 index 000000000..869a71089 --- /dev/null +++ b/.claude/skills/new-setup-2/SKILL.md @@ -0,0 +1,112 @@ +--- +name: new-setup-2 +description: Follow-on to /new-setup. Captures the operator and agent names, wires a real messaging channel, and adds quality-of-life extras. Linear rollthrough; every step is skippable. Invoked when the user picks "continue setup" at the end of /new-setup. +allowed-tools: Bash(bash setup/probe.sh) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm exec tsx scripts/init-first-agent.ts *) +--- + +# NanoClaw phase-2 setup + +Runs after `/new-setup`. At this point the host is running and a throwaway CLI-only agent exists (used during /new-setup for the end-to-end ping check — inferred name, not user-facing). This flow creates the **real** agent and wires it to a messaging channel. + +**Linear — one step at a time.** Every step is skippable: if the user says "skip", "not now", "later", or similar, move on without complaint. If they say they're done at any point, stop cleanly — don't push the remaining steps. + +Before each step, narrate in your own words what's about to happen — one short, friendly sentence, no jargon. Match the tone of `/new-setup`. + +## Current state + +!`bash setup/probe.sh` + +Parse the probe block above for `INFERRED_DISPLAY_NAME` and `PLATFORM` — referenced below. + +## Steps + +### 1. What should the agent call you? + +Plain-prose ask (do **not** use `AskUserQuestion`): + +> What should your agent call you? (Default: ``) + +Capture the answer into a local variable `OPERATOR_NAME`. **Don't persist yet** — this value is consumed by step 3's channel wiring. If the user skips or confirms the default, set `OPERATOR_NAME = INFERRED_DISPLAY_NAME`. + +### 2. What's your agent's name? + +Plain-prose ask: + +> What would you like to call your agent? (Default: ``) + +Capture as `AGENT_NAME`. If skipped, set `AGENT_NAME = OPERATOR_NAME`. Nothing persisted yet. + +### 3. Pick a messaging channel + +Print the list as plain prose. **Do not use `AskUserQuestion` for this step** — just the list, then wait for the user's reply: + +> Which messaging channel should I wire your agent to? +> +> - **WhatsApp (native)** — `/add-whatsapp` +> - **WhatsApp Cloud (Meta official)** — `/add-whatsapp-cloud` +> - **Telegram** — `/add-telegram` +> - **Slack** — `/add-slack` +> - **Discord** — `/add-discord` +> - **iMessage** — `/add-imessage` +> - **Teams** — `/add-teams` +> - **Matrix** — `/add-matrix` +> - **Google Chat** — `/add-gchat` +> - **Linear** — `/add-linear` +> - **GitHub** — `/add-github` +> - **Webex** — `/add-webex` +> - **Resend (email)** — `/add-resend` +> - **Emacs** — `/add-emacs` +> +> Or say "skip" to leave this for later. + +When the user picks one: + +1. **Install the adapter.** Invoke the matching `/add-` skill via the Skill tool. It copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels (e.g. Telegram) also run a pairing step as part of their flow. +2. **Capture platform IDs.** After the `/add-` skill finishes, you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, for example, the `pair-telegram` step emits `PLATFORM_ID` and `ADMIN_USER_ID` in a status block once the user sends the 4-digit code. +3. **Wire the agent.** Run `init-first-agent.ts` in DM mode with `--no-cli-bonus` (this keeps the new agent off the CLI messaging group so the pre-existing throwaway agent still owns CLI routing cleanly): + + ``` + pnpm exec tsx scripts/init-first-agent.ts \ + --channel \ + --user-id "" \ + --platform-id "" \ + --display-name "" \ + --agent-name "" \ + --no-cli-bonus + ``` + +4. **Announce.** On success, emit the encouragement line verbatim: + + > Your agent is now available on {channel-name}, you can already start chatting — But I encourage you to continue and finish this setup, we're almost done! + + Substitute `{channel-name}` with the friendly name (e.g. "Telegram", "WhatsApp", "Slack"). + +If the user skipped, move on to step 4. + +### 4. Quality of life + +Optional polish. Print the list; the user may pick zero, one, or several — invoke each chosen skill in sequence: + +> Want to add any of these? Pick any that sound useful — or skip: +> +> - `/add-dashboard` — browser dashboard showing agent activity +> - `/add-compact` — `/compact` slash command for managing long sessions +> - `/add-karpathy-llm-wiki` — persistent knowledge-base memory for the agent + +If the probe reports `PLATFORM=darwin`, also offer: + +> - `/add-macos-statusbar` — macOS menu bar indicator with Start/Stop/Restart controls + +Do **not** list `/add-macos-statusbar` on Linux. If the user skips everything, just move on. + +### 5. Done + +Short wrap-up: + +> Setup complete. You can chat with your agent on {channel-name} — or via CLI with `pnpm run chat `. + +Substitute `{channel-name}` with whatever was wired in step 3. If step 3 was skipped, drop the "on {channel-name} — or" clause entirely so the line just mentions the CLI form. + +## If anything fails + +Same rule as `/new-setup`: don't bypass errors to keep moving. Read `logs/setup.log` or `logs/nanoclaw.log`, diagnose, fix the underlying cause, re-run the failed step. diff --git a/scripts/init-first-agent.ts b/scripts/init-first-agent.ts index 5e828dc88..846877882 100644 --- a/scripts/init-first-agent.ts +++ b/scripts/init-first-agent.ts @@ -59,6 +59,7 @@ import type { AgentGroup, MessagingGroup } from '../src/types.js'; interface Args { cliOnly: boolean; + noCliBonus: boolean; channel: string; userId: string; platformId: string; @@ -75,7 +76,7 @@ const CLI_PLATFORM_ID = 'local'; const CLI_SYNTHETIC_USER_ID = `${CLI_CHANNEL}:${CLI_PLATFORM_ID}`; function parseArgs(argv: string[]): Args { - const out: Partial = { cliOnly: false }; + const out: Partial = { cliOnly: false, noCliBonus: false }; for (let i = 0; i < argv.length; i++) { const key = argv[i]; const val = argv[i + 1]; @@ -83,6 +84,9 @@ function parseArgs(argv: string[]): Args { case '--cli-only': out.cliOnly = true; break; + case '--no-cli-bonus': + out.noCliBonus = true; + break; case '--channel': out.channel = (val ?? '').toLowerCase(); i++; @@ -120,6 +124,7 @@ function parseArgs(argv: string[]): Args { // CLI-only: channel/user/platform default to the synthetic local CLI identity. return { cliOnly: true, + noCliBonus: out.noCliBonus ?? false, channel: CLI_CHANNEL, userId: CLI_SYNTHETIC_USER_ID, platformId: CLI_PLATFORM_ID, @@ -139,6 +144,7 @@ function parseArgs(argv: string[]): Args { return { cliOnly: false, + noCliBonus: out.noCliBonus ?? false, channel: out.channel!, userId: out.userId!, platformId: out.platformId!, @@ -292,7 +298,9 @@ async function main(): Promise { wireIfMissing(primaryMg, ag, now, args.cliOnly ? 'cli' : 'dm'); // In DM mode also wire CLI so `pnpm run chat` works immediately. - if (!args.cliOnly) { + // Skip the bonus when --no-cli-bonus is set — used by /new-setup-2 so the + // throwaway CLI-only agent from /new-setup still owns CLI routing cleanly. + if (!args.cliOnly && !args.noCliBonus) { wireIfMissing(cliMg, ag, now, 'cli-bonus'); } @@ -322,7 +330,9 @@ async function main(): Promise { console.log(` channel: cli/${CLI_PLATFORM_ID}`); } else { console.log(` channel: ${args.channel} ${primaryMg.platform_id}`); - console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``); + if (!args.noCliBonus) { + console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``); + } } console.log(` session: ${session.id}`); console.log(''); From a4061a0012d2f0785dbad222d79007339e47f018 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 13:55:49 +0300 Subject: [PATCH 39/95] refactor(channels,router): move all policy to router; bridge is transport MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Follow-up to b159722. That shrank the bridge's shouldEngage to a flood gate + coarse sticky-subscribe signal. This completes the move — policy lives exclusively in the router, the bridge is transport-only, and the conversations map + ChannelSetup.conversations + ChannelAdapter.updateConversations are all gone. Key shifts: 1. Subscribe moves from bridge to router. Bridge used to call `thread.subscribe()` from its onNewMention / onDirectMessage handlers based on a coarse "any mention-sticky wiring exists on this channel" check. That forced the decision before the router could apply per-wiring engage logic, and it relied on the conversations map being current (staleness risk). ChannelAdapter gains `subscribe?(platformId, threadId)`. The Chat SDK bridge implements it via SqliteStateAdapter.subscribe(threadId) (idempotent — a repeat call on an already-subscribed thread is a no-op). The router's fan-out loop calls it once per message when the first mention-sticky wiring actually engages. Precise, not coarse. 2. Short-circuit the drop path with one combined query. New `getMessagingGroupWithAgentCount(channelType, platformId)` does the messaging_groups lookup AND counts wirings in a single SELECT, using the existing UNIQUE(channel_type, platform_id) index on messaging_groups and UNIQUE(messaging_group_id, agent_group_id) on messaging_group_agents for the JOIN. No new indexes needed. routeInbound now short-circuits: - No messaging_groups row AND not addressed (no mention/DM) → return silently. One DB read, nothing written. This is the Discord-bot-in-a-big-guild case; we no longer auto-create rows for every plain message in every channel the bot can see. - Messaging group exists but no wirings AND not addressed → return silently. One DB read. - Otherwise fall through to sender resolution + fan-out as before. Behavioral change: plain chatter on unwired channels no longer gets dropped_messages audit rows, which used to bloat the table. Audit still fires on addressed-to-bot drops where the admin cares ("someone @-mentioned us but nobody's wired"). 3. Bridge is now purely transport. Deleted entirely: ConversationConfig, ChannelSetup.conversations, ChannelAdapter.updateConversations?, bridge's `conversations` map, buildConversationMap, shouldEngage, EngageSource, engageDecision, bridge.updateConversations method, src/index.ts buildConversationConfigs. Four handlers reduce to "resolve channel id, build InboundMessage with isMention, call onInbound". Net ~130 LOC deleted from the bridge. Collateral: the conversations-map staleness problem is gone. The upcoming channel-registration feature doesn't need any map-refresh plumbing — when an approval creates a new wiring, the next message hits the DB fresh and just works. Bridge tests prune to the narrow platform-adjacent surface (openDM delegation, subscribe presence). Host-core test that asserted the old "auto-create on every unknown message" behavior updates to reflect the new escalation-gated semantics: plain messages on unknown channels don't auto-create, mentions do. 159 tests pass (was 172 — net -13, almost entirely from bridge-engage-mode tests that covered logic now owned by the router and exercised through host-core.test.ts). Co-Authored-By: Claude Opus 4.7 (1M context) --- src/channels/adapter.ts | 49 +++------- src/channels/channel-registry.test.ts | 2 - src/channels/chat-sdk-bridge.test.ts | 106 +++------------------ src/channels/chat-sdk-bridge.ts | 130 ++++---------------------- src/db/messaging-groups.ts | 31 ++++++ src/host-core.test.ts | 36 +++++-- src/index.ts | 27 +----- src/router.ts | 101 ++++++++++++++------ 8 files changed, 173 insertions(+), 309 deletions(-) diff --git a/src/channels/adapter.ts b/src/channels/adapter.ts index bbf7f3749..9343258bd 100644 --- a/src/channels/adapter.ts +++ b/src/channels/adapter.ts @@ -5,45 +5,8 @@ * Two patterns: native adapters (implement directly) or Chat SDK bridge (wrap a Chat SDK adapter). */ -/** Configuration for a registered conversation (messaging group + agent wiring). */ -export interface ConversationConfig { - platformId: string; - agentGroupId: string; - /** - * When does the agent engage on messages from this conversation? - * - * 'pattern' — regex test against message text; engagePattern='.' - * means "always" (match everything) - * 'mention' — fires only on @mention - * 'mention-sticky' — fires on @mention, then auto-subscribes to the thread - * and treats subsequent messages as engage-all. - * Threaded platforms only (Slack/Discord/Linear). - */ - engageMode: 'pattern' | 'mention' | 'mention-sticky'; - /** Regex source when engageMode='pattern'. '.' is the "always" sentinel. */ - engagePattern?: string | null; - /** - * What to do with messages this wiring doesn't engage on. - * - * 'drop' — discard silently - * 'accumulate' — still forward to the host so the router can store the - * message in this agent's session with trigger=0. It - * rides along as context when the agent next wakes, but - * doesn't wake it on its own. - * - * The bridge reads this to decide whether to forward a non-engaging - * message at all — if any wiring on a conversation has 'accumulate', the - * bridge forwards and lets the router apply the per-wiring decision. - */ - ignoredMessagePolicy?: 'drop' | 'accumulate'; - sessionMode: 'shared' | 'per-thread' | 'agent-shared'; -} - /** Passed to the adapter at setup time. */ export interface ChannelSetup { - /** Known conversations from central DB. */ - conversations: ConversationConfig[]; - /** Called when an inbound message arrives from the platform. */ onInbound(platformId: string, threadId: string | null, message: InboundMessage): void | Promise; @@ -125,7 +88,17 @@ export interface ChannelAdapter { // Optional setTyping?(platformId: string, threadId: string | null): Promise; syncConversations?(): Promise; - updateConversations?(conversations: ConversationConfig[]): void; + + /** + * Subscribe the bot to a thread so follow-up messages route via the + * platform's "subscribed message" path (onSubscribedMessage in Chat SDK). + * Called by the router when a mention-sticky wiring first engages in a + * thread. Idempotent: calling twice on the same thread is a no-op. + * + * Platforms without a subscription concept can omit this; the router + * treats absence as a no-op. + */ + subscribe?(platformId: string, threadId: string): Promise; /** * Open (or fetch) a DM with this user, returning the platform_id of the diff --git a/src/channels/channel-registry.test.ts b/src/channels/channel-registry.test.ts index 265a3721e..5121c6497 100644 --- a/src/channels/channel-registry.test.ts +++ b/src/channels/channel-registry.test.ts @@ -64,8 +64,6 @@ function createMockAdapter( }, async setTyping() {}, - - updateConversations() {}, }; } diff --git a/src/channels/chat-sdk-bridge.test.ts b/src/channels/chat-sdk-bridge.test.ts index 3c6caa8c1..7ddad4ff0 100644 --- a/src/channels/chat-sdk-bridge.test.ts +++ b/src/channels/chat-sdk-bridge.test.ts @@ -2,37 +2,19 @@ import { describe, expect, it } from 'vitest'; import type { Adapter } from 'chat'; -import type { ConversationConfig } from './adapter.js'; -import { createChatSdkBridge, shouldEngage, type EngageSource } from './chat-sdk-bridge.js'; +import { createChatSdkBridge } from './chat-sdk-bridge.js'; function stubAdapter(partial: Partial): Adapter { return { name: 'stub', ...partial } as unknown as Adapter; } -function cfg( - partial: Partial & { engageMode: ConversationConfig['engageMode'] }, -): ConversationConfig { - return { - platformId: partial.platformId ?? 'C1', - agentGroupId: partial.agentGroupId ?? 'ag-1', - engageMode: partial.engageMode, - engagePattern: partial.engagePattern ?? null, - ignoredMessagePolicy: partial.ignoredMessagePolicy ?? 'drop', - sessionMode: partial.sessionMode ?? 'shared', - }; -} - -function mapFor(...configs: ConversationConfig[]): Map { - const map = new Map(); - for (const c of configs) { - const existing = map.get(c.platformId); - if (existing) existing.push(c); - else map.set(c.platformId, [c]); - } - return map; -} - describe('createChatSdkBridge', () => { + // The bridge is now transport-only: forward inbound events, relay outbound + // ops. All per-wiring engage / accumulate / drop / subscribe decisions live + // in the router (src/router.ts routeInbound / evaluateEngage) and are + // exercised by host-core.test.ts end-to-end. These tests only cover the + // bridge's narrow, platform-adjacent surface. + it('omits openDM when the underlying Chat SDK adapter has none', () => { const bridge = createChatSdkBridge({ adapter: stubAdapter({}), @@ -59,76 +41,12 @@ describe('createChatSdkBridge', () => { expect(openDMCalls).toEqual(['user-42']); expect(platformId).toBe('stub:user-42'); }); -}); -describe('shouldEngage (bridge-level flood gate + subscribe signal)', () => { - // Per-wiring engage_mode / engage_pattern / ignored_message_policy - // semantics live in the router (evaluateEngage / routeInbound fan-out). - // These tests only cover the bridge's two responsibilities: should we - // forward at all, and should we call thread.subscribe(). - - describe('flood gate — unknown conversation', () => { - const empty = new Map(); - const carriedSources: EngageSource[] = ['subscribed', 'mention', 'dm']; - for (const source of carriedSources) { - it(`forwards for source='${source}' (may be a newly-auto-created channel or a channel-registration trigger)`, () => { - expect(shouldEngage(empty, 'C-new', source)).toEqual({ forward: true, stickySubscribe: false }); - }); - } - it("DROPS for source='new-message' (onNewMessage(/./) fires for every unsubscribed thread the bot can see — would flood)", () => { - expect(shouldEngage(empty, 'C-unwired', 'new-message')).toEqual({ - forward: false, - stickySubscribe: false, - }); - }); - }); - - describe('known conversation — bridge forwards regardless of engage mode', () => { - // Policy lives in the router now. The bridge only knows "has any wiring". - const conv = mapFor(cfg({ engageMode: 'mention' })); - for (const source of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { - it(`forwards for source='${source}' — router will decide engage / accumulate / drop per wiring`, () => { - expect(shouldEngage(conv, 'C1', source).forward).toBe(true); - }); - } - }); - - describe('stickySubscribe signal', () => { - it('true when any mention-sticky wiring exists AND source is mention', () => { - const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); - expect(shouldEngage(conv, 'C1', 'mention').stickySubscribe).toBe(true); - }); - - it('true when any mention-sticky wiring exists AND source is dm', () => { - const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); - expect(shouldEngage(conv, 'C1', 'dm').stickySubscribe).toBe(true); - }); - - it('false on subscribed — thread is already subscribed, no need to re-subscribe', () => { - const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); - expect(shouldEngage(conv, 'C1', 'subscribed').stickySubscribe).toBe(false); - }); - - it('false on new-message — mention-sticky requires an explicit mention to start', () => { - const conv = mapFor(cfg({ engageMode: 'mention-sticky' })); - expect(shouldEngage(conv, 'C1', 'new-message').stickySubscribe).toBe(false); - }); - - it('false for plain mention / pattern wirings (not sticky)', () => { - const mentionConv = mapFor(cfg({ engageMode: 'mention' })); - const patternConv = mapFor(cfg({ engageMode: 'pattern', engagePattern: '.' })); - for (const s of ['subscribed', 'mention', 'dm', 'new-message'] as EngageSource[]) { - expect(shouldEngage(mentionConv, 'C1', s).stickySubscribe).toBe(false); - expect(shouldEngage(patternConv, 'C1', s).stickySubscribe).toBe(false); - } - }); - - it('fires on coarse union — mixed wirings where any one is mention-sticky', () => { - const conv = mapFor( - cfg({ agentGroupId: 'ag-a', engageMode: 'mention' }), - cfg({ agentGroupId: 'ag-b', engageMode: 'mention-sticky' }), - ); - expect(shouldEngage(conv, 'C1', 'mention').stickySubscribe).toBe(true); + it('exposes subscribe (lets the router initiate thread subscription on mention-sticky engage)', () => { + const bridge = createChatSdkBridge({ + adapter: stubAdapter({}), + supportsThreads: true, }); + expect(typeof bridge.subscribe).toBe('function'); }); }); diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index 9bed96888..ef2195e7a 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -21,7 +21,7 @@ import { SqliteStateAdapter } from '../state-sqlite.js'; import { registerWebhookAdapter } from '../webhook-server.js'; import { getAskQuestionRender } from '../db/sessions.js'; import { normalizeOptions, type NormalizedOption } from './ask-question.js'; -import type { ChannelAdapter, ChannelSetup, ConversationConfig, InboundMessage } from './adapter.js'; +import type { ChannelAdapter, ChannelSetup, InboundMessage } from './adapter.js'; /** Adapter with optional gateway support (e.g., Discord). */ interface GatewayAdapter extends Adapter { @@ -65,99 +65,14 @@ export interface ChatSdkBridgeConfig { transformOutboundText?: (text: string) => string; } -/** - * Which Chat SDK handler delivered this message. Determines which engage modes - * can fire. - * - * - `subscribed` — `onSubscribedMessage`. Thread is already subscribed. - * Every wiring mode (mention / mention-sticky / pattern) - * evaluates normally. - * - `mention` — `onNewMention`. Bot was @-mentioned in an unsubscribed - * thread. mention + mention-sticky engage; pattern runs - * the regex. - * - `dm` — `onDirectMessage`. Unsubscribed DM. Treated like a - * mention for engagement purposes. - * - `new-message` — `onNewMessage(/./, …)`. Plain non-mention non-DM - * message in an unsubscribed thread. Only `pattern` - * wirings can fire here. mention / mention-sticky ignore - * this source (they require an explicit mention). - */ -export type EngageSource = 'subscribed' | 'mention' | 'dm' | 'new-message'; - -/** - * Bridge-level forwarding decision — a coarse flood gate, not policy. - * - * The router owns per-wiring engage_mode / engage_pattern / sender_scope / - * ignored_message_policy (see `evaluateEngage` in src/router.ts). The bridge - * only answers two questions: - * - * 1. `forward` — is this message worth sending to the host at all? - * - Known channel (any wiring): yes. Router will decide what engages / - * accumulates / drops per wiring. - * - Unknown channel: yes for subscribed / mention / DM (triggers the - * router's auto-create or channel-registration flow); no for - * `new-message`. onNewMessage(/./, …) fires for every message in - * every unsubscribed thread the bot can see, including channels the - * bot merely joined but was never wired to — forwarding everything - * would flood the host. - * - * 2. `stickySubscribe` — should the bridge call `thread.subscribe()`? - * - Yes if ANY wiring on this channel is mention-sticky AND the - * source is an actual mention / DM. Coarse (no per-wiring picking) - * but harmless: subscription is idempotent and one call serves - * every mention-sticky wiring on the channel. Once subscribed, - * follow-ups route through onSubscribedMessage. - * - * Exported for testability — see `chat-sdk-bridge.test.ts`. - */ -export function shouldEngage( - conversations: Map, - channelId: string, - source: EngageSource, -): { forward: boolean; stickySubscribe: boolean } { - const configs = conversations.get(channelId); - - if (!configs || configs.length === 0) { - return { forward: source !== 'new-message', stickySubscribe: false }; - } - - const stickySubscribe = - (source === 'mention' || source === 'dm') && configs.some((cfg) => cfg.engageMode === 'mention-sticky'); - - return { forward: true, stickySubscribe }; -} - export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter { const { adapter } = config; const transformText = (t: string): string => (config.transformOutboundText ? config.transformOutboundText(t) : t); let chat: Chat; let state: SqliteStateAdapter; let setupConfig: ChannelSetup; - // Keyed by platformId. Multiple agents may be wired to the same - // conversation — this holds all their configs so the bridge can apply the - // most-permissive engage rule at gate time and only subscribe when at - // least one wiring requested 'mention-sticky'. - // - // STALENESS: populated at setup() and updateConversations(). If wirings - // change after setup, updateConversations() must be called to refresh - // (ACTION-ITEMS item 17). - let conversations: Map; let gatewayAbort: AbortController | null = null; - function buildConversationMap(configs: ConversationConfig[]): Map { - const map = new Map(); - for (const conv of configs) { - const existing = map.get(conv.platformId); - if (existing) existing.push(conv); - else map.set(conv.platformId, [conv]); - } - return map; - } - - function engageDecision(channelId: string, source: EngageSource): { forward: boolean; stickySubscribe: boolean } { - return shouldEngage(conversations, channelId, source); - } - async function messageToInbound(message: ChatMessage, isMention: boolean): Promise { // eslint-disable-next-line @typescript-eslint/no-explicit-any const serialized = message.toJSON() as Record; @@ -225,7 +140,6 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter async setup(hostConfig: ChannelSetup) { setupConfig = hostConfig; - conversations = buildConversationMap(hostConfig.conversations); state = new SqliteStateAdapter(); @@ -237,29 +151,25 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter logger: 'silent', }); - // Four SDK dispatch paths — bridge just forwards; router does all - // per-wiring engage / accumulate / drop decisions. isMention is the - // load-bearing signal (see evaluateEngage in src/router.ts). + // Four SDK dispatch paths — bridge just forwards. All per-wiring + // engage / accumulate / drop / subscribe decisions live in the host + // router (src/router.ts routeInbound / evaluateEngage). The bridge + // only resolves channel ids and sets the platform-confirmed isMention + // flag that routeInbound evaluates; the router calls back into + // bridge.subscribe(...) when a mention-sticky wiring engages. // Subscribed threads — every message in a thread we've previously // engaged. Carry the SDK's `message.isMention` through so mention-mode // wirings still fire on in-thread mentions. chat.onSubscribedMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const decision = engageDecision(channelId, 'subscribed'); - if (!decision.forward) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, message.isMention === true)); }); // @mention in an unsubscribed thread — SDK-confirmed bot mention. chat.onNewMention(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const decision = engageDecision(channelId, 'mention'); - if (!decision.forward) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, true)); - if (decision.stickySubscribe) { - await thread.subscribe(); - } }); // DMs — by definition addressed to the bot. Thread id flows through @@ -268,19 +178,13 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter // is_group=0 short-circuit. chat.onDirectMessage(async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const decision = engageDecision(channelId, 'dm'); log.info('Inbound DM received', { adapter: adapter.name, channelId, sender: (message.author as any)?.fullName ?? (message.author as any)?.userId ?? 'unknown', threadId: thread.id, - forward: decision.forward, }); - if (!decision.forward) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, true)); - if (decision.stickySubscribe) { - await thread.subscribe(); - } }); // Plain messages in unsubscribed threads. @@ -288,14 +192,13 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter // Chat SDK dispatch (handling-events.mdx §"Handler dispatch order") is // exclusive: subscribed → onSubscribedMessage; unsubscribed+mention → // onNewMention; unsubscribed+pattern-match → onNewMessage. Registering - // with `/./` lets the router see every plain message on wired channels - // (needed for engage_mode='pattern' + ignored_message_policy='accumulate' - // wirings). `shouldEngage` drops unknown channels on this source - // specifically so we don't flood from channels the bot merely joined. + // with `/./` lets the router see every plain message on every + // unsubscribed thread the bot can see. The router short-circuits via + // getMessagingGroupWithAgentCount (~1 DB read) for unwired channels, + // so forwarding every one is cheap enough to not need a bridge-side + // flood gate. chat.onNewMessage(/./, async (thread, message) => { const channelId = adapter.channelIdFromThreadId(thread.id); - const decision = engageDecision(channelId, 'new-message'); - if (!decision.forward) return; await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, false)); }); @@ -468,8 +371,13 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter return true; }, - updateConversations(configs: ConversationConfig[]) { - conversations = buildConversationMap(configs); + async subscribe(_platformId: string, threadId: string) { + // Chat SDK's subscription state lives on the StateAdapter (not on the + // Chat instance itself). SqliteStateAdapter.subscribe is idempotent — + // a second call on an already-subscribed thread is a no-op. threadId + // is the SDK's thread id, which is what the router already has from + // the original inbound event. + await state.subscribe(threadId); }, }; diff --git a/src/db/messaging-groups.ts b/src/db/messaging-groups.ts index db12583ee..3f9b2c460 100644 --- a/src/db/messaging-groups.ts +++ b/src/db/messaging-groups.ts @@ -37,6 +37,37 @@ export function getMessagingGroupByPlatform(channelType: string, platformId: str .get(channelType, platformId) as MessagingGroup | undefined; } +/** + * Combined lookup for the router's fast-drop path. Returns the messaging + * group (if it exists) and a count of wired agents in one query — lets + * `routeInbound` short-circuit messages for unwired / unknown channels + * with a single DB read instead of four (mg lookup, sender upsert, agents + * lookup, dropped_messages insert). + * + * Returns `null` when no messaging_groups row exists for this channel. + * Returns `{ mg, agentCount: 0 }` when the row exists but has no wired + * agents. Uses the `UNIQUE(channel_type, platform_id)` index plus the + * `UNIQUE(messaging_group_id, agent_group_id)` index for the JOIN — both + * covered by existing SQLite auto-indexes from the UNIQUE constraints. + */ +export function getMessagingGroupWithAgentCount( + channelType: string, + platformId: string, +): { mg: MessagingGroup; agentCount: number } | null { + const row = getDb() + .prepare( + `SELECT mg.*, COUNT(mga.id) AS agent_count + FROM messaging_groups mg + LEFT JOIN messaging_group_agents mga ON mga.messaging_group_id = mg.id + WHERE mg.channel_type = ? AND mg.platform_id = ? + GROUP BY mg.id`, + ) + .get(channelType, platformId) as (MessagingGroup & { agent_count: number }) | undefined; + if (!row) return null; + const { agent_count, ...mg } = row; + return { mg: mg as MessagingGroup, agentCount: agent_count }; +} + export function getAllMessagingGroups(): MessagingGroup[] { return getDb().prepare('SELECT * FROM messaging_groups ORDER BY name').all() as MessagingGroup[]; } diff --git a/src/host-core.test.ts b/src/host-core.test.ts index 33d37ff6f..da2fd37d2 100644 --- a/src/host-core.test.ts +++ b/src/host-core.test.ts @@ -244,26 +244,42 @@ describe('router', () => { expect(wakeContainer).toHaveBeenCalled(); }); - it('should auto-create messaging group for unknown platform', async () => { + it('auto-creates messaging group only when the bot is addressed (mention/DM)', async () => { + // The router's no-mg branch is escalation-gated: plain chatter on an + // unknown channel stays silent (no DB writes) so a bot that sits in + // many unwired channels doesn't bloat messaging_groups. Only explicit + // mentions and DMs trigger auto-create. const { routeInbound } = await import('./router.js'); + const { getMessagingGroupByPlatform } = await import('./db/messaging-groups.js'); - const event: InboundEvent = { + // Plain message on unknown channel — should NOT auto-create. + await routeInbound({ channelType: 'slack', - platformId: 'C-NEW-CHANNEL', + platformId: 'C-PLAIN', threadId: null, message: { - id: 'msg-2', + id: 'msg-plain', kind: 'chat', content: JSON.stringify({ sender: 'User', text: 'Hi' }), timestamp: now(), }, - }; + }); + expect(getMessagingGroupByPlatform('slack', 'C-PLAIN')).toBeUndefined(); - await routeInbound(event); - - const { getMessagingGroupByPlatform } = await import('./db/messaging-groups.js'); - const mg = getMessagingGroupByPlatform('slack', 'C-NEW-CHANNEL'); - expect(mg).toBeDefined(); + // Mention on unknown channel — SHOULD auto-create (next step: channel-registration flow). + await routeInbound({ + channelType: 'slack', + platformId: 'C-MENTIONED', + threadId: null, + message: { + id: 'msg-mentioned', + kind: 'chat', + content: JSON.stringify({ sender: 'User', text: '@bot hi' }), + timestamp: now(), + isMention: true, + }, + }); + expect(getMessagingGroupByPlatform('slack', 'C-MENTIONED')).toBeDefined(); }); it('should route multiple messages to the same session', async () => { diff --git a/src/index.ts b/src/index.ts index 595ba1b8c..7c5ab240c 100644 --- a/src/index.ts +++ b/src/index.ts @@ -9,7 +9,6 @@ import path from 'path'; import { DATA_DIR } from './config.js'; import { initDb } from './db/connection.js'; import { runMigrations } from './db/migrations/index.js'; -import { getMessagingGroupsByChannel, getMessagingGroupAgents } from './db/messaging-groups.js'; import { ensureContainerRuntimeRunning, cleanupOrphans } from './container-runtime.js'; import { startActiveDeliveryPoll, startSweepDeliveryPoll, setDeliveryAdapter, stopDeliveryPolls } from './delivery.js'; import { startHostSweep, stopHostSweep } from './host-sweep.js'; @@ -52,7 +51,7 @@ import './channels/index.js'; // append registry-based modules. Imported for side effects (registrations). import './modules/index.js'; -import type { ChannelAdapter, ChannelSetup, ConversationConfig } from './channels/adapter.js'; +import type { ChannelAdapter, ChannelSetup } from './channels/adapter.js'; import { initChannelAdapters, teardownChannelAdapters, getChannelAdapter } from './channels/channel-registry.js'; async function main(): Promise { @@ -70,9 +69,7 @@ async function main(): Promise { // 3. Channel adapters await initChannelAdapters((adapter: ChannelAdapter): ChannelSetup => { - const conversations = buildConversationConfigs(adapter.channelType); return { - conversations, onInbound(platformId, threadId, message) { routeInbound({ channelType: adapter.channelType, @@ -151,28 +148,6 @@ async function main(): Promise { log.info('NanoClaw running'); } -/** Build ConversationConfig[] for a channel type from the central DB. */ -function buildConversationConfigs(channelType: string): ConversationConfig[] { - const groups = getMessagingGroupsByChannel(channelType); - const configs: ConversationConfig[] = []; - - for (const mg of groups) { - const agents = getMessagingGroupAgents(mg.id); - for (const agent of agents) { - configs.push({ - platformId: mg.platform_id, - agentGroupId: agent.agent_group_id, - engageMode: agent.engage_mode, - engagePattern: agent.engage_pattern, - ignoredMessagePolicy: agent.ignored_message_policy, - sessionMode: agent.session_mode, - }); - } - } - - return configs; -} - /** Graceful shutdown. */ async function shutdown(signal: string): Promise { log.info('Shutdown signal received', { signal }); diff --git a/src/router.ts b/src/router.ts index a3e8f06f0..1d819c0bf 100644 --- a/src/router.ts +++ b/src/router.ts @@ -20,7 +20,11 @@ import { getChannelAdapter } from './channels/channel-registry.js'; import { getAgentGroup } from './db/agent-groups.js'; import { recordDroppedMessage } from './db/dropped-messages.js'; -import { getMessagingGroupByPlatform, createMessagingGroup, getMessagingGroupAgents } from './db/messaging-groups.js'; +import { + createMessagingGroup, + getMessagingGroupAgents, + getMessagingGroupWithAgentCount, +} from './db/messaging-groups.js'; import { findSessionForAgent } from './db/sessions.js'; import { startTypingRefresh } from './modules/typing/index.js'; import { log } from './log.js'; @@ -143,10 +147,21 @@ export async function routeInbound(event: InboundEvent): Promise { event = { ...event, threadId: null }; } - // 1. Resolve messaging group - let mg = getMessagingGroupByPlatform(event.channelType, event.platformId); + const isMention = event.message.isMention === true; + + // 1. Combined lookup: messaging_group row + count of wired agents in a + // single query. Cheap short-circuit for the common "unwired channel" + // case — one DB read and we're out, no auto-create, no sender + // resolution, no log spam. + const found = getMessagingGroupWithAgentCount(event.channelType, event.platformId); + + let mg: MessagingGroup; + if (!found) { + // No messaging_groups row. Auto-create only when the message warrants + // attention (the bot was addressed — @mention or DM). Plain chatter in + // channels we merely sit in stays silent — no row, no DB writes. + if (!isMention) return; - if (!mg) { const mgId = `mg-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; mg = { id: mgId, @@ -154,9 +169,6 @@ export async function routeInbound(event: InboundEvent): Promise { platform_id: event.platformId, name: null, is_group: 0, - // Let the schema default (currently 'request_approval') apply rather - // than hardcoding 'strict' — the schema is the source of truth for - // the default policy. See migration 011. unknown_sender_policy: 'request_approval', created_at: new Date().toISOString(), }; @@ -166,6 +178,30 @@ export async function routeInbound(event: InboundEvent): Promise { channelType: event.channelType, platformId: event.platformId, }); + } else { + mg = found.mg; + if (found.agentCount === 0) { + // Messaging group exists but has no wirings. Stay silent for plain + // messages; only log + record on explicit mention/DM so admins can + // see that someone tried to reach the bot on an unwired channel. + if (!isMention) return; + log.warn('MESSAGE DROPPED — no agent groups wired to this channel. Run setup register step to configure.', { + messagingGroupId: mg.id, + channelType: event.channelType, + platformId: event.platformId, + }); + const parsed = safeParseContent(event.message.content); + recordDroppedMessage({ + channel_type: event.channelType, + platform_id: event.platformId, + user_id: null, + sender_name: parsed.sender ?? null, + reason: 'no_agent_wired', + messaging_group_id: mg.id, + agent_group_id: null, + }); + return; + } } // 2. Sender resolution (permissions module upserts the users row as a @@ -173,27 +209,9 @@ export async function routeInbound(event: InboundEvent): Promise { // Without the module, userId is null — downstream tolerates it. const userId: string | null = senderResolver ? senderResolver(event) : null; - // 3. Resolve agent groups wired to this messaging group. Structural - // drops record to dropped_messages for audit. + // 3. Fetch wired agents in full (we already know the count is > 0; now + // we need their actual rows for fan-out). const agents = getMessagingGroupAgents(mg.id); - if (agents.length === 0) { - log.warn('MESSAGE DROPPED — no agent groups wired to this channel. Run setup register step to configure.', { - messagingGroupId: mg.id, - channelType: event.channelType, - platformId: event.platformId, - }); - const parsed = safeParseContent(event.message.content); - recordDroppedMessage({ - channel_type: event.channelType, - platform_id: event.platformId, - user_id: userId, - sender_name: parsed.sender ?? null, - reason: 'no_agent_wired', - messaging_group_id: mg.id, - agent_group_id: null, - }); - return; - } // 4. Fan-out: evaluate each wired agent independently against engage_mode, // sender_scope, and access gate. An agent that engages gets its own @@ -201,12 +219,18 @@ export async function routeInbound(event: InboundEvent): Promise { // ignored_message_policy='accumulate' still gets the message stored in // its session (trigger=0) so the context is available when it does // engage later. Drop policy = skip silently. + // + // Subscribe (for mention-sticky wirings on threaded platforms) fires + // once per message from this loop — the first engaging mention-sticky + // wiring triggers adapter.subscribe(...); subsequent wirings don't + // re-subscribe (chat.subscribe is idempotent anyway, but the flag + // avoids the extra await). const parsed = safeParseContent(event.message.content); const messageText = parsed.text ?? ''; - const isMention = event.message.isMention === true; let engagedCount = 0; let accumulatedCount = 0; + let subscribed = false; for (const agent of agents) { const agentGroup = getAgentGroup(agent.agent_group_id); @@ -220,6 +244,27 @@ export async function routeInbound(event: InboundEvent): Promise { if (engages && accessOk && scopeOk) { await deliverToAgent(agent, agentGroup, mg, event, userId, adapter?.supportsThreads === true, true); engagedCount++; + + // Mention-sticky: ask the adapter to subscribe the thread so the + // platform's subscribed-message path carries follow-ups without + // requiring another @mention. Threaded-adapter only; DMs and + // non-threaded platforms skip. + if ( + !subscribed && + agent.engage_mode === 'mention-sticky' && + adapter?.supportsThreads && + adapter.subscribe && + event.threadId !== null && + mg.is_group !== 0 + ) { + subscribed = true; + // Fire-and-forget — subscribe is platform-side bookkeeping and + // shouldn't block message routing. Errors are logged inside the + // adapter (or by the promise rejection handler below). + void adapter.subscribe(event.platformId, event.threadId).catch((err) => { + log.warn('adapter.subscribe failed', { channelType: event.channelType, threadId: event.threadId, err }); + }); + } } else if (agent.ignored_message_policy === 'accumulate') { await deliverToAgent(agent, agentGroup, mg, event, userId, adapter?.supportsThreads === true, false); accumulatedCount++; From 5f8a1388687af3ee098185d9ad44c1d234ea775d Mon Sep 17 00:00:00 2001 From: Gabi Simons Date: Mon, 20 Apr 2026 10:59:55 +0000 Subject: [PATCH 40/95] docs(skills): update add-matrix skill - Install steps aligned with add-linear/add-github pattern (fetch, copy, import, install pkg, build) - Add Matrix-specific step: patch @beeper/chat-adapter-matrix ESM imports (inline node one-liner, idempotent) - Cover bot-account requirement (can't DM yourself), access-token and username/password auth paths, optional invite auto-join / E2EE / device-id settings --- .claude/skills/add-matrix/SKILL.md | 85 +++++++++++++++++++++++++----- 1 file changed, 71 insertions(+), 14 deletions(-) diff --git a/.claude/skills/add-matrix/SKILL.md b/.claude/skills/add-matrix/SKILL.md index 7a6ea0f08..cf6da754a 100644 --- a/.claude/skills/add-matrix/SKILL.md +++ b/.claude/skills/add-matrix/SKILL.md @@ -47,7 +47,29 @@ import './matrix.js'; pnpm install @beeper/chat-adapter-matrix@0.2.0 ``` -### 5. Build +### 5. Patch matrix-js-sdk ESM imports + +The adapter's published dist references `matrix-js-sdk/lib/...` without `.js` +extensions, which fails under Node 22 strict ESM resolution. Add the missing +extensions (idempotent — safe to re-run): + +```bash +node -e ' + const fs = require("fs"), path = require("path"); + const root = "node_modules/.pnpm"; + const dir = fs.readdirSync(root).find(d => d.startsWith("@beeper+chat-adapter-matrix@")); + if (!dir) { console.log("Matrix adapter not installed"); process.exit(0); } + const f = path.join(root, dir, "node_modules/@beeper/chat-adapter-matrix/dist/index.js"); + fs.writeFileSync(f, fs.readFileSync(f, "utf8").replace( + /from "(matrix-js-sdk\/lib\/[^"]+?)(? **Help & About** > **Access Token** (advanced) - - Or via API: `curl -XPOST 'https://matrix.org/_matrix/client/r0/login' -d '{"type":"m.login.password","user":"botuser","password":"..."}'` -4. Note the bot's user ID (e.g., `@botuser:matrix.org`) +The bot needs its own Matrix account — separate from the user's account. This is required because Matrix cannot send DMs to yourself. -### Configure environment +### Create a bot account -Add to `.env`: +1. Open [app.element.io](https://app.element.io) in a private/incognito window (or sign out first) +2. Register a new account for the bot (e.g. `andybot` on matrix.org) +3. Note the bot's user ID (e.g. `@andybot:matrix.org`) + +### Choose an auth method + +**Option A: Username + Password (simpler)** + +No extra steps — just use the bot account's credentials directly. The adapter logs in automatically. + +```bash +MATRIX_BASE_URL=https://matrix.org +MATRIX_USERNAME=andybot +MATRIX_PASSWORD=your-bot-password +MATRIX_USER_ID=@andybot:matrix.org +MATRIX_BOT_USERNAME=Andy +``` + +**Option B: Access Token (recommended for production)** + +Get an access token from Element: sign into the bot account → **Settings** > **Help & About** > **Access Token** (under Advanced). Or via API: + +```bash +curl -XPOST 'https://matrix.org/_matrix/client/r0/login' \ + -d '{"type":"m.login.password","user":"andybot","password":"..."}' +``` ```bash MATRIX_BASE_URL=https://matrix.org MATRIX_ACCESS_TOKEN=your-access-token -MATRIX_USER_ID=@botuser:matrix.org -MATRIX_BOT_USERNAME=botuser +MATRIX_USER_ID=@andybot:matrix.org +MATRIX_BOT_USERNAME=Andy ``` -Sync to container: `mkdir -p data/env && cp .env data/env/env` +### Optional settings + +```bash +MATRIX_INVITE_AUTOJOIN=true # Auto-accept room invites (default: true) +MATRIX_INVITE_AUTOJOIN_ALLOWLIST=@you:matrix.org # Only accept invites from these users +MATRIX_RECOVERY_KEY=your-recovery-key # Enable E2EE cross-signing +MATRIX_DEVICE_ID=NANOCLAW01 # Stable device ID across restarts +``` + +### Configure environment + +Add the chosen env vars to `.env`, then sync: + +```bash +mkdir -p data/env && cp .env data/env/env +``` ## Next Steps @@ -85,7 +142,7 @@ Otherwise, run `/manage-channels` to wire this channel to an agent group. - **type**: `matrix` - **terminology**: Matrix has "rooms." A room can be a group chat or a direct message. Rooms have internal IDs (like `!abc123:matrix.org`) and optional aliases (like `#general:matrix.org`). -- **how-to-find-id**: In Element, click the room name > Settings > Advanced — the "Internal room ID" is the platform ID (starts with `!`). Or use a room alias like `#general:matrix.org`. +- **how-to-find-id**: For DMs, use the bot's `openDM` to resolve the room automatically. For group rooms, in Element click the room name > Settings > Advanced — the "Internal room ID" is the platform ID (starts with `!`). Or use a room alias like `#general:matrix.org`. - **supports-threads**: partial (some clients support threads, but not all — treat as no for reliability) -- **typical-use**: Interactive chat — rooms or direct messages +- **typical-use**: Interactive chat — rooms or direct messages. Requires a separate bot account (the agent cannot DM users from their own account). - **default-isolation**: Same agent group for rooms where you're the primary user. Separate agent group for rooms with different communities or sensitive contexts. From 719f97e48368698c920cf7cf61ea9e93f081fd61 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 14:34:00 +0300 Subject: [PATCH 41/95] feat(permissions): unknown-channel registration flow with owner approval MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the router sees a mention or DM on a messaging group that isn't wired to any agent, it now escalates to an owner for approval instead of silently dropping. Mirrors the existing unknown-sender approval pattern (ACTION-ITEMS item 22). Schema (migration 012): - `messaging_groups.denied_at TEXT NULL` — timestamp set on deny so future mentions stop escalating. ALTER TABLE ADD COLUMN, FK-safe (unlike the rebuild that bit migration 011). - `pending_channel_approvals` — PK on `messaging_group_id` gives free in-flight dedup. One card per channel, no spam on rapid retries. Router: - New hook `setChannelRequestGate(mg, event) => Promise`, invoked from the no-wirings branch when the message was addressed to the bot (isMention=true). Hook is fire-and-forget. - Checks `mg.denied_at` before escalating — denied channels drop silently and do not re-prompt. - The two "no-wirings" branches (fresh auto-create and existing mg with no agents) are consolidated into one escalation path that calls the gate once. Without the module, behavior is log + record (no regression). Permissions module: - `channel-approval.ts::requestChannelApproval` — MVP picker: target agent is `getAllAgentGroups()[0]`, card names it explicitly ("Wire it to ?"). Approver via existing `pickApprover` + `pickApprovalDelivery` primitives. - Response handler: same click-auth pattern as sender-approval (clicker must be the designated approver OR have admin privilege over the target agent group). - Approve defaults per the feature spec: engage_mode = 'mention-sticky' for groups, 'pattern' + '.' for DMs sender_scope = 'known' ignored_message_policy = 'accumulate' session_mode = 'shared' DM vs group inferred from the original event's threadId (non-null → group) because the auto-created mg has a placeholder is_group=0 until the adapter fills it in. - Triggering sender is auto-added to agent_group_members so sender_scope= 'known' doesn't bounce the replayed message into a sender-approval cascade. - Deny: stamps messaging_groups.denied_at, clears pending row. - Failure modes — no owner, no agent groups, no reachable DM — log and drop without creating a pending row, letting a future attempt try again (same as sender-approval). 9 new integration tests cover every branch: mention triggers card, DM triggers card, dedup, approve creates correct wiring + admits sender + replays, approve-on-DM uses pattern/'.' defaults, deny sets denied_at and future mentions drop silently, unauthorized clicker rejected, no-owner drops, no-agent-groups drops. 168 tests pass (was 159; +9). Co-Authored-By: Claude Opus 4.7 (1M context) --- src/db/messaging-groups.ts | 14 + src/db/migrations/012-channel-registration.ts | 48 +++ src/db/migrations/index.ts | 2 + .../permissions/channel-approval.test.ts | 392 ++++++++++++++++++ src/modules/permissions/channel-approval.ts | 159 +++++++ .../db/pending-channel-approvals.ts | 52 +++ src/modules/permissions/index.ts | 144 +++++++ src/router.ts | 79 +++- src/types.ts | 10 + 9 files changed, 882 insertions(+), 18 deletions(-) create mode 100644 src/db/migrations/012-channel-registration.ts create mode 100644 src/modules/permissions/channel-approval.test.ts create mode 100644 src/modules/permissions/channel-approval.ts create mode 100644 src/modules/permissions/db/pending-channel-approvals.ts diff --git a/src/db/messaging-groups.ts b/src/db/messaging-groups.ts index 3f9b2c460..33c87151a 100644 --- a/src/db/messaging-groups.ts +++ b/src/db/messaging-groups.ts @@ -100,6 +100,20 @@ export function deleteMessagingGroup(id: string): void { getDb().prepare('DELETE FROM messaging_groups WHERE id = ?').run(id); } +/** + * Mark a messaging group as denied by the owner (channel-registration flow). + * Future mentions on this channel silently drop until an admin explicitly + * wires it via `createMessagingGroupAgent`, which implicitly clears the + * denied state by making `agentCount > 0` — the router's denied-channel + * check sits on the `agentCount === 0` branch. + * + * Passing null unsets the flag (used by tests or a future "unblock channel" + * admin command). + */ +export function setMessagingGroupDeniedAt(id: string, deniedAt: string | null): void { + getDb().prepare('UPDATE messaging_groups SET denied_at = ? WHERE id = ?').run(deniedAt, id); +} + // ── Messaging Group Agents ── /** diff --git a/src/db/migrations/012-channel-registration.ts b/src/db/migrations/012-channel-registration.ts new file mode 100644 index 000000000..eca891196 --- /dev/null +++ b/src/db/migrations/012-channel-registration.ts @@ -0,0 +1,48 @@ +/** + * Unknown-channel registration flow. + * + * When a channel that isn't wired to any agent group receives a mention or + * DM, the router escalates to the owner for approval before wiring. Approve + * creates a `messaging_group_agents` row (with conservative defaults) and + * replays the triggering event. Deny marks the channel denied forever + * (stored as a timestamp on `messaging_groups.denied_at`) so future + * messages on that channel drop silently without re-prompting. + * + * Two changes: + * 1. `messaging_groups.denied_at TEXT NULL` — set on deny, checked in the + * router before re-escalating. ALTER TABLE ADD COLUMN is FK-safe + * unlike the table rebuild that bit us in migration 011. + * 2. `pending_channel_approvals` table. PRIMARY KEY on + * `messaging_group_id` gives free in-flight dedup — a second mention + * while the card is pending is silently dropped by INSERT OR IGNORE, + * preventing card spam. + */ +import type Database from 'better-sqlite3'; +import type { Migration } from './index.js'; + +export const migration012: Migration = { + version: 12, + name: 'channel-registration', + up: (db: Database.Database) => { + // 1. Add denied_at to messaging_groups. Idempotent guard in case the + // column was added by some other path before this migration ran. + const cols = db.prepare("PRAGMA table_info('messaging_groups')").all() as Array<{ name: string }>; + if (!cols.some((c) => c.name === 'denied_at')) { + db.exec(`ALTER TABLE messaging_groups ADD COLUMN denied_at TEXT`); + } + + // 2. pending_channel_approvals. + db.exec(` + CREATE TABLE IF NOT EXISTS pending_channel_approvals ( + messaging_group_id TEXT PRIMARY KEY REFERENCES messaging_groups(id), + agent_group_id TEXT NOT NULL REFERENCES agent_groups(id), + -- The agent the approved wiring will target. + -- Picked at request time (currently: earliest + -- agent_group by created_at). + original_message TEXT NOT NULL, -- JSON serialized InboundEvent + approver_user_id TEXT NOT NULL, + created_at TEXT NOT NULL + ); + `); + }, +}; diff --git a/src/db/migrations/index.ts b/src/db/migrations/index.ts index 1015f405e..33e6963a9 100644 --- a/src/db/migrations/index.ts +++ b/src/db/migrations/index.ts @@ -8,6 +8,7 @@ import { migration008 } from './008-dropped-messages.js'; import { migration009 } from './009-drop-pending-credentials.js'; import { migration010 } from './010-engage-modes.js'; import { migration011 } from './011-pending-sender-approvals.js'; +import { migration012 } from './012-channel-registration.js'; import { moduleApprovalsPendingApprovals } from './module-approvals-pending-approvals.js'; import { moduleApprovalsTitleOptions } from './module-approvals-title-options.js'; @@ -27,6 +28,7 @@ const migrations: Migration[] = [ migration009, migration010, migration011, + migration012, ]; export function runMigrations(db: Database.Database): void { diff --git a/src/modules/permissions/channel-approval.test.ts b/src/modules/permissions/channel-approval.test.ts new file mode 100644 index 000000000..f3ea7e98c --- /dev/null +++ b/src/modules/permissions/channel-approval.test.ts @@ -0,0 +1,392 @@ +/** + * Integration tests for the unknown-channel registration flow (ACTION-ITEMS + * item 22). + * + * Covers: + * - Mention on an unwired channel fires an owner-approval card + * - DM on an unwired channel fires a card (engage_mode will default to pattern='.') + * - In-flight dedup: second mention while a card is pending doesn't spam + * - Approve: wiring created with correct defaults, triggering sender added + * as member, replay wakes the container + * - Deny: messaging_groups.denied_at set, future mentions drop silently + * - Unauthorized clicker is rejected (same pattern as sender-approval) + * - No-owner install: no card, no row + * - No agent groups configured: no card, no row + */ +import fs from 'fs'; +import { beforeEach, afterEach, describe, expect, it, vi } from 'vitest'; + +import { initTestDb, closeDb, runMigrations } from '../../db/index.js'; +import { createAgentGroup } from '../../db/agent-groups.js'; +import { createMessagingGroup, getMessagingGroupByPlatform } from '../../db/messaging-groups.js'; +import { upsertUser } from './db/users.js'; +import { grantRole } from './db/user-roles.js'; + +// Mock container runner — prevent actual docker spawn. +vi.mock('../../container-runner.js', () => ({ + wakeContainer: vi.fn().mockResolvedValue(undefined), + isContainerRunning: vi.fn().mockReturnValue(false), + getActiveContainerCount: vi.fn().mockReturnValue(0), + killContainer: vi.fn(), +})); + +// Mock delivery adapter. +const deliverMock = vi.fn().mockResolvedValue('plat-msg-id'); +vi.mock('../../delivery.js', () => ({ + getDeliveryAdapter: () => ({ deliver: deliverMock }), +})); + +// Mock ensureUserDm — look up the owner's preconfigured DM row instead of +// hitting a real openDM RPC. +vi.mock('./user-dm.js', () => ({ + ensureUserDm: vi.fn(async (userId: string) => { + const { getDb } = await import('../../db/connection.js'); + const row = getDb() + .prepare( + `SELECT mg.* FROM messaging_groups mg + JOIN user_dms ud ON ud.messaging_group_id = mg.id + WHERE ud.user_id = ?`, + ) + .get(userId); + return row; + }), +})); + +vi.mock('../../config.js', async () => { + const actual = await vi.importActual('../../config.js'); + return { ...actual, DATA_DIR: '/tmp/nanoclaw-test-channel-approval' }; +}); + +const TEST_DIR = '/tmp/nanoclaw-test-channel-approval'; + +function now() { + return new Date().toISOString(); +} + +beforeEach(async () => { + if (fs.existsSync(TEST_DIR)) fs.rmSync(TEST_DIR, { recursive: true }); + fs.mkdirSync(TEST_DIR, { recursive: true }); + const db = initTestDb(); + runMigrations(db); + + await import('./index.js'); // register hooks + + // Base fixtures: one agent group + owner with a DM on 'telegram'. + createAgentGroup({ id: 'ag-1', name: 'Andy', folder: 'andy', agent_provider: null, created_at: now() }); + + upsertUser({ id: 'telegram:owner', kind: 'telegram', display_name: 'Owner', created_at: now() }); + grantRole({ + user_id: 'telegram:owner', + role: 'owner', + agent_group_id: null, + granted_by: null, + granted_at: now(), + }); + + // Pre-seed owner's DM messaging group + user_dms mapping. + createMessagingGroup({ + id: 'mg-dm-owner', + channel_type: 'telegram', + platform_id: 'dm-owner', + name: 'Owner DM', + is_group: 0, + unknown_sender_policy: 'public', + created_at: now(), + }); + const { getDb } = await import('../../db/connection.js'); + getDb() + .prepare( + `INSERT INTO user_dms (user_id, channel_type, messaging_group_id, resolved_at) + VALUES (?, ?, ?, ?)`, + ) + .run('telegram:owner', 'telegram', 'mg-dm-owner', now()); + + deliverMock.mockClear(); +}); + +afterEach(() => { + closeDb(); + if (fs.existsSync(TEST_DIR)) fs.rmSync(TEST_DIR, { recursive: true }); +}); + +function groupMention(platformId: string, text = '@bot hello') { + return { + channelType: 'telegram', + platformId, + threadId: 'thread-1', // non-null → is_group=true per channel-approval default-picker logic + message: { + id: `msg-${Math.random().toString(36).slice(2, 8)}`, + kind: 'chat' as const, + content: JSON.stringify({ senderId: 'caller', senderName: 'Caller', text }), + timestamp: now(), + isMention: true, + }, + }; +} + +function dmEvent(platformId: string, text = 'hello') { + return { + channelType: 'telegram', + platformId, + threadId: null, + message: { + id: `msg-${Math.random().toString(36).slice(2, 8)}`, + kind: 'chat' as const, + content: JSON.stringify({ senderId: 'stranger', senderName: 'Stranger', text }), + timestamp: now(), + isMention: true, // DM bridge sets isMention=true + }, + }; +} + +describe('unknown-channel registration flow', () => { + it('delivers an approval card on mention into an unwired group', async () => { + const { routeInbound } = await import('../../router.js'); + await routeInbound(groupMention('chat-new')); + await new Promise((r) => setTimeout(r, 10)); + + expect(deliverMock).toHaveBeenCalledTimes(1); + const [channel, platformId, thread, kind, content] = deliverMock.mock.calls[0]; + expect(channel).toBe('telegram'); + expect(platformId).toBe('dm-owner'); // delivered to owner's DM + expect(thread).toBeNull(); + expect(kind).toBe('chat-sdk'); + const payload = JSON.parse(content as string); + expect(payload.type).toBe('ask_question'); + // Card names the target agent so the owner knows what they're wiring to. + expect(payload.question).toContain('Andy'); + + const { getDb } = await import('../../db/connection.js'); + const rows = getDb().prepare('SELECT * FROM pending_channel_approvals').all() as Array<{ + messaging_group_id: string; + }>; + expect(rows).toHaveLength(1); + }); + + it('delivers a card on DM too (non-threaded event)', async () => { + const { routeInbound } = await import('../../router.js'); + await routeInbound(dmEvent('dm-new-user')); + await new Promise((r) => setTimeout(r, 10)); + + expect(deliverMock).toHaveBeenCalledTimes(1); + const { getDb } = await import('../../db/connection.js'); + const count = (getDb().prepare('SELECT COUNT(*) AS c FROM pending_channel_approvals').get() as { c: number }).c; + expect(count).toBe(1); + }); + + it('dedups a second mention while the card is pending', async () => { + const { routeInbound } = await import('../../router.js'); + await routeInbound(groupMention('chat-busy')); + await new Promise((r) => setTimeout(r, 10)); + await routeInbound(groupMention('chat-busy', '@bot still here')); + await new Promise((r) => setTimeout(r, 10)); + + expect(deliverMock).toHaveBeenCalledTimes(1); + const { getDb } = await import('../../db/connection.js'); + const count = (getDb().prepare('SELECT COUNT(*) AS c FROM pending_channel_approvals').get() as { c: number }).c; + expect(count).toBe(1); + }); + + it('approve → creates wiring, admits triggering sender, replays', async () => { + const { routeInbound } = await import('../../router.js'); + const { getResponseHandlers } = await import('../../response-registry.js'); + const { wakeContainer } = await import('../../container-runner.js'); + (wakeContainer as unknown as ReturnType).mockClear(); + + await routeInbound(groupMention('chat-approve')); + await new Promise((r) => setTimeout(r, 10)); + + const { getDb } = await import('../../db/connection.js'); + const pending = getDb() + .prepare('SELECT messaging_group_id FROM pending_channel_approvals') + .get() as { messaging_group_id: string }; + expect(pending).toBeDefined(); + + // Owner clicks approve. + for (const handler of getResponseHandlers()) { + const claimed = await handler({ + questionId: pending.messaging_group_id, + value: 'approve', + userId: 'owner', // raw platform id — handler namespaces it + channelType: 'telegram', + platformId: 'dm-owner', + threadId: null, + }); + if (claimed) break; + } + + // Wiring created with MVP defaults. + const mga = getDb() + .prepare('SELECT * FROM messaging_group_agents WHERE messaging_group_id = ?') + .get(pending.messaging_group_id) as { + engage_mode: string; + engage_pattern: string | null; + sender_scope: string; + ignored_message_policy: string; + agent_group_id: string; + }; + expect(mga).toBeDefined(); + expect(mga.engage_mode).toBe('mention-sticky'); // group (threadId != null) + expect(mga.engage_pattern).toBeNull(); + expect(mga.sender_scope).toBe('known'); + expect(mga.ignored_message_policy).toBe('accumulate'); + expect(mga.agent_group_id).toBe('ag-1'); + + // Triggering sender auto-admitted so sender_scope='known' doesn't + // bounce the replay into sender-approval. + const member = getDb() + .prepare('SELECT 1 AS x FROM agent_group_members WHERE user_id = ? AND agent_group_id = ?') + .get('telegram:caller', 'ag-1'); + expect(member).toBeDefined(); + + // Pending row cleared and container woken via replay. + const stillPending = ( + getDb().prepare('SELECT COUNT(*) AS c FROM pending_channel_approvals').get() as { c: number } + ).c; + expect(stillPending).toBe(0); + expect(wakeContainer).toHaveBeenCalled(); + }); + + it('approve on a DM wires with pattern="." defaults', async () => { + const { routeInbound } = await import('../../router.js'); + const { getResponseHandlers } = await import('../../response-registry.js'); + + await routeInbound(dmEvent('dm-approve-user')); + await new Promise((r) => setTimeout(r, 10)); + + const { getDb } = await import('../../db/connection.js'); + const pending = getDb() + .prepare('SELECT messaging_group_id FROM pending_channel_approvals') + .get() as { messaging_group_id: string }; + + for (const handler of getResponseHandlers()) { + const claimed = await handler({ + questionId: pending.messaging_group_id, + value: 'approve', + userId: 'owner', + channelType: 'telegram', + platformId: 'dm-owner', + threadId: null, + }); + if (claimed) break; + } + + const mga = getDb() + .prepare('SELECT engage_mode, engage_pattern FROM messaging_group_agents WHERE messaging_group_id = ?') + .get(pending.messaging_group_id) as { engage_mode: string; engage_pattern: string }; + expect(mga.engage_mode).toBe('pattern'); + expect(mga.engage_pattern).toBe('.'); + }); + + it('deny → sets denied_at; future mentions drop silently without a second card', async () => { + const { routeInbound } = await import('../../router.js'); + const { getResponseHandlers } = await import('../../response-registry.js'); + + await routeInbound(groupMention('chat-deny')); + await new Promise((r) => setTimeout(r, 10)); + const { getDb } = await import('../../db/connection.js'); + const pending = getDb() + .prepare('SELECT messaging_group_id FROM pending_channel_approvals') + .get() as { messaging_group_id: string }; + + for (const handler of getResponseHandlers()) { + const claimed = await handler({ + questionId: pending.messaging_group_id, + value: 'reject', + userId: 'owner', + channelType: 'telegram', + platformId: 'dm-owner', + threadId: null, + }); + if (claimed) break; + } + + // denied_at set, pending row cleared, no wiring. + const mg = getMessagingGroupByPlatform('telegram', 'chat-deny'); + expect(mg?.denied_at).not.toBeNull(); + expect(mg?.denied_at).toBeTruthy(); + const mgaCount = ( + getDb() + .prepare('SELECT COUNT(*) AS c FROM messaging_group_agents WHERE messaging_group_id = ?') + .get(pending.messaging_group_id) as { c: number } + ).c; + expect(mgaCount).toBe(0); + + // A follow-up mention on the denied channel: no new card, no new pending row. + deliverMock.mockClear(); + await routeInbound(groupMention('chat-deny', '@bot please')); + await new Promise((r) => setTimeout(r, 10)); + expect(deliverMock).not.toHaveBeenCalled(); + const stillPending = ( + getDb().prepare('SELECT COUNT(*) AS c FROM pending_channel_approvals').get() as { c: number } + ).c; + expect(stillPending).toBe(0); + }); + + it('rejects clicks from an unauthorized user (prevents self-admit via forwarded card)', async () => { + const { routeInbound } = await import('../../router.js'); + const { getResponseHandlers } = await import('../../response-registry.js'); + + await routeInbound(groupMention('chat-unauth')); + await new Promise((r) => setTimeout(r, 10)); + const { getDb } = await import('../../db/connection.js'); + const pending = getDb() + .prepare('SELECT messaging_group_id FROM pending_channel_approvals') + .get() as { messaging_group_id: string }; + + for (const handler of getResponseHandlers()) { + const claimed = await handler({ + questionId: pending.messaging_group_id, + value: 'approve', + userId: 'random-bystander', + channelType: 'telegram', + platformId: 'dm-random', + threadId: null, + }); + if (claimed) break; + } + + // No wiring created, pending row preserved so a real approver can act on it. + const mgaCount = ( + getDb() + .prepare('SELECT COUNT(*) AS c FROM messaging_group_agents WHERE messaging_group_id = ?') + .get(pending.messaging_group_id) as { c: number } + ).c; + expect(mgaCount).toBe(0); + const stillPending = ( + getDb().prepare('SELECT COUNT(*) AS c FROM pending_channel_approvals').get() as { c: number } + ).c; + expect(stillPending).toBe(1); + }); +}); + +describe('no-owner / no-agent failure modes', () => { + it('no owner → no card, no pending row (fresh-install bootstrap path)', async () => { + // Wipe the owner grant set up in the outer beforeEach. + const { getDb } = await import('../../db/connection.js'); + getDb().prepare('DELETE FROM user_roles').run(); + + const { routeInbound } = await import('../../router.js'); + await routeInbound(groupMention('chat-noowner')); + await new Promise((r) => setTimeout(r, 10)); + + expect(deliverMock).not.toHaveBeenCalled(); + const count = (getDb().prepare('SELECT COUNT(*) AS c FROM pending_channel_approvals').get() as { c: number }).c; + expect(count).toBe(0); + }); + + it('no agent groups → no card, no pending row', async () => { + const { getDb } = await import('../../db/connection.js'); + // Drop foreign-key-dependent rows first, then the agent group itself. + getDb().prepare('DELETE FROM user_roles').run(); + getDb().prepare('DELETE FROM agent_groups').run(); + + const { routeInbound } = await import('../../router.js'); + await routeInbound(groupMention('chat-noagent')); + await new Promise((r) => setTimeout(r, 10)); + + expect(deliverMock).not.toHaveBeenCalled(); + const count = (getDb().prepare('SELECT COUNT(*) AS c FROM pending_channel_approvals').get() as { c: number }).c; + expect(count).toBe(0); + }); +}); diff --git a/src/modules/permissions/channel-approval.ts b/src/modules/permissions/channel-approval.ts new file mode 100644 index 000000000..9c65f8e3a --- /dev/null +++ b/src/modules/permissions/channel-approval.ts @@ -0,0 +1,159 @@ +/** + * Unknown-channel registration flow. + * + * When the router hits an unwired messaging group AND the message was + * addressed to the bot (SDK-confirmed mention or DM), it calls + * `requestChannelApproval` instead of silently dropping. The flow: + * + * 1. Pick the target agent group we'd wire to (MVP: first by name). + * Multi-agent picker is a follow-up — see ACTION-ITEMS. + * 2. Pick an eligible approver (owner / admin) and a reachable DM for + * them, reusing the same primitives the sender-approval flow uses. + * 3. Deliver an Approve / Ignore card that names the target agent + * explicitly so the owner knows what they're wiring to. + * 4. Record a `pending_channel_approvals` row holding the original event + * so it can be re-routed on approve. + * + * On approve (handler in index.ts): + * - Create `messaging_group_agents` with MVP defaults + * (mention-sticky for groups / pattern='.' for DMs, + * sender_scope='known', ignored_message_policy='accumulate') + * - Add the triggering sender to `agent_group_members` so sender_scope + * doesn't bounce the replayed message into a sender-approval cascade + * - Delete the pending row, replay the original event + * + * On ignore: + * - Set `messaging_groups.denied_at = now()` so the router stops + * escalating on this channel until an admin explicitly re-wires + * - Delete the pending row + * + * Dedup: `pending_channel_approvals` PK on messaging_group_id. Second + * mention while pending silently dropped. + * + * Failure modes (log + no row, so a future attempt can try again): + * - No agent groups exist (install never set up a first agent). + * - No eligible approver in user_roles (no owner yet). + * - Approver has no reachable DM. + * - Delivery adapter missing. + */ +import { normalizeOptions, type RawOption } from '../../channels/ask-question.js'; +import { getAllAgentGroups } from '../../db/agent-groups.js'; +import { getMessagingGroup } from '../../db/messaging-groups.js'; +import { getDeliveryAdapter } from '../../delivery.js'; +import { log } from '../../log.js'; +import type { InboundEvent } from '../../router.js'; +import { pickApprovalDelivery, pickApprover } from '../approvals/primitive.js'; +import { createPendingChannelApproval, hasInFlightChannelApproval } from './db/pending-channel-approvals.js'; + +const APPROVAL_OPTIONS: RawOption[] = [ + { label: 'Approve', selectedLabel: '✅ Wired', value: 'approve' }, + { label: 'Ignore', selectedLabel: '🙅 Ignored', value: 'reject' }, +]; + +export interface RequestChannelApprovalInput { + messagingGroupId: string; + event: InboundEvent; +} + +export async function requestChannelApproval(input: RequestChannelApprovalInput): Promise { + const { messagingGroupId, event } = input; + + // In-flight dedup: don't spam the owner if the same unwired channel + // gets more mentions / DMs while a card is already pending. + if (hasInFlightChannelApproval(messagingGroupId)) { + log.debug('Channel registration already in flight — dropping retry', { + messagingGroupId, + }); + return; + } + + // MVP: pick the first agent group by name. Multi-agent systems will get + // a richer card later (user picks the target from a list). + const agentGroups = getAllAgentGroups(); + if (agentGroups.length === 0) { + log.warn('Channel registration skipped — no agent groups configured. Run /init-first-agent.', { + messagingGroupId, + }); + return; + } + const target = agentGroups[0]; + + // pickApprover takes the target agent group's id — gets scoped admins + + // global admins + owners. For fresh installs with only an owner, the + // owner is returned. + const approvers = pickApprover(target.id); + if (approvers.length === 0) { + log.warn('Channel registration skipped — no owner or admin configured', { + messagingGroupId, + targetAgentGroupId: target.id, + }); + return; + } + + const originMg = getMessagingGroup(messagingGroupId); + const originChannelType = originMg?.channel_type ?? ''; + const delivery = await pickApprovalDelivery(approvers, originChannelType); + if (!delivery) { + log.warn('Channel registration skipped — no DM channel for any approver', { + messagingGroupId, + targetAgentGroupId: target.id, + }); + return; + } + + const originName = originMg?.name ?? originMg?.platform_id ?? 'an unfamiliar chat'; + const isGroup = originMg?.is_group === 1; + + const title = isGroup ? '📣 Bot mentioned in new chat' : '💬 New direct message'; + const question = isGroup + ? `Your agent was mentioned in ${originName} on ${originChannelType}. Wire it to ${target.name} and let it engage?` + : `Someone DM'd your agent on ${originChannelType} (${originName}). Wire it to ${target.name} and let it respond?`; + + createPendingChannelApproval({ + messaging_group_id: messagingGroupId, + agent_group_id: target.id, + original_message: JSON.stringify(event), + approver_user_id: delivery.userId, + created_at: new Date().toISOString(), + }); + + const adapter = getDeliveryAdapter(); + if (!adapter) { + log.error('Channel registration row created but no delivery adapter is wired', { + messagingGroupId, + }); + return; + } + + try { + await adapter.deliver( + delivery.messagingGroup.channel_type, + delivery.messagingGroup.platform_id, + null, + 'chat-sdk', + JSON.stringify({ + type: 'ask_question', + // Use messaging_group_id as the questionId — it's unique per card + // (PK on pending table dedups) and lets the response handler look + // up the pending row directly without another index. + questionId: messagingGroupId, + title, + question, + options: normalizeOptions(APPROVAL_OPTIONS), + }), + ); + log.info('Channel registration card delivered', { + messagingGroupId, + targetAgentGroupId: target.id, + approver: delivery.userId, + }); + } catch (err) { + log.error('Channel registration card delivery failed', { + messagingGroupId, + err, + }); + } +} + +export const APPROVE_VALUE = 'approve'; +export const REJECT_VALUE = 'reject'; diff --git a/src/modules/permissions/db/pending-channel-approvals.ts b/src/modules/permissions/db/pending-channel-approvals.ts new file mode 100644 index 000000000..d3e665ad2 --- /dev/null +++ b/src/modules/permissions/db/pending-channel-approvals.ts @@ -0,0 +1,52 @@ +/** + * CRUD for pending_channel_approvals — the in-flight state for the + * unknown-channel registration flow. A row exists while an owner-approval + * card is outstanding; it's deleted on approve (after wiring is created) + * or deny (after denied_at is set on the messaging_group). + * + * PRIMARY KEY on messaging_group_id gives free in-flight dedup. A second + * mention/DM while a card is pending resolves via + * `hasInFlightChannelApproval` in the request flow and drops silently + * instead of spamming the owner. + */ +import { getDb } from '../../../db/connection.js'; + +export interface PendingChannelApproval { + messaging_group_id: string; + agent_group_id: string; + original_message: string; + approver_user_id: string; + created_at: string; +} + +export function createPendingChannelApproval(row: PendingChannelApproval): void { + getDb() + .prepare( + `INSERT INTO pending_channel_approvals ( + messaging_group_id, agent_group_id, original_message, + approver_user_id, created_at + ) + VALUES ( + @messaging_group_id, @agent_group_id, @original_message, + @approver_user_id, @created_at + )`, + ) + .run(row); +} + +export function getPendingChannelApproval(messagingGroupId: string): PendingChannelApproval | undefined { + return getDb() + .prepare('SELECT * FROM pending_channel_approvals WHERE messaging_group_id = ?') + .get(messagingGroupId) as PendingChannelApproval | undefined; +} + +export function hasInFlightChannelApproval(messagingGroupId: string): boolean { + const row = getDb() + .prepare('SELECT 1 AS x FROM pending_channel_approvals WHERE messaging_group_id = ?') + .get(messagingGroupId) as { x: number } | undefined; + return row !== undefined; +} + +export function deletePendingChannelApproval(messagingGroupId: string): void { + getDb().prepare('DELETE FROM pending_channel_approvals WHERE messaging_group_id = ?').run(messagingGroupId); +} diff --git a/src/modules/permissions/index.ts b/src/modules/permissions/index.ts index d13797b74..e2f100c83 100644 --- a/src/modules/permissions/index.ts +++ b/src/modules/permissions/index.ts @@ -16,9 +16,14 @@ * access gate is not registered and core defaults to allow-all. */ import { recordDroppedMessage } from '../../db/dropped-messages.js'; +import { + createMessagingGroupAgent, + setMessagingGroupDeniedAt, +} from '../../db/messaging-groups.js'; import { routeInbound, setAccessGate, + setChannelRequestGate, setSenderResolver, setSenderScopeGate, type AccessGateResult, @@ -28,7 +33,12 @@ import { registerResponseHandler, type ResponsePayload } from '../../response-re import { log } from '../../log.js'; import type { MessagingGroup, MessagingGroupAgent } from '../../types.js'; import { canAccessAgentGroup } from './access.js'; +import { requestChannelApproval } from './channel-approval.js'; import { addMember } from './db/agent-group-members.js'; +import { + deletePendingChannelApproval, + getPendingChannelApproval, +} from './db/pending-channel-approvals.js'; import { deletePendingSenderApproval, getPendingSenderApproval } from './db/pending-sender-approvals.js'; import { hasAdminPrivilege } from './db/user-roles.js'; import { getUser, upsertUser } from './db/users.js'; @@ -253,3 +263,137 @@ async function handleSenderApprovalResponse(payload: ResponsePayload): Promise { + await requestChannelApproval({ messagingGroupId: mg.id, event }); +}); + +/** + * Response handler for the unknown-channel registration card. + * + * Claim rule: questionId matches a pending_channel_approvals row (keyed + * by messaging_group_id). If no such row, return false so downstream + * handlers get a shot. + * + * Approve: create the wiring with MVP defaults (mention-sticky for + * groups / pattern='.' for DMs; sender_scope='known'; + * ignored_message_policy='accumulate'), add the triggering sender as a + * member so sender_scope doesn't immediately bounce them into a + * sender-approval card, then replay the original event. + * + * Deny: set `messaging_groups.denied_at = now()` so future mentions on + * this channel drop silently until an admin explicitly wires it. + */ +async function handleChannelApprovalResponse(payload: ResponsePayload): Promise { + const row = getPendingChannelApproval(payload.questionId); + if (!row) return false; + + // Click-auth: same pattern as sender-approval (see commit 68058cb). + // Raw platform userId → namespace with channelType → must match the + // designated approver OR have admin privilege over the target agent. + const clickerId = payload.userId ? `${payload.channelType}:${payload.userId}` : null; + const isAuthorized = + clickerId !== null && (clickerId === row.approver_user_id || hasAdminPrivilege(clickerId, row.agent_group_id)); + if (!isAuthorized) { + log.warn('Channel registration click rejected — unauthorized clicker', { + messagingGroupId: row.messaging_group_id, + clickerId, + expectedApprover: row.approver_user_id, + }); + return true; // claim but take no action + } + const approverId = clickerId; + const approved = payload.value === 'approve'; + + if (!approved) { + setMessagingGroupDeniedAt(row.messaging_group_id, new Date().toISOString()); + deletePendingChannelApproval(row.messaging_group_id); + log.info('Channel registration denied', { + messagingGroupId: row.messaging_group_id, + agentGroupId: row.agent_group_id, + approverId, + }); + return true; + } + + // Rehydrate the original event to know (a) whether it was a DM or group + // (chooses engage_mode default), and (b) who the triggering sender was + // (auto-member-add so sender_scope='known' doesn't bounce the replay). + let event: InboundEvent; + try { + event = JSON.parse(row.original_message) as InboundEvent; + } catch (err) { + log.error('Channel registration: failed to parse stored event', { + messagingGroupId: row.messaging_group_id, + err, + }); + deletePendingChannelApproval(row.messaging_group_id); + return true; + } + + // Decide engage_mode from the original event. DMs (`isMention=true` & + // not in a group) get `pattern='.'` (always respond). Group mentions + // get `mention-sticky` (respond now + follow the thread). + // + // We can't read `mg.is_group` reliably here because we only auto-create + // the mg with `is_group=0` on first sight — the adapter hasn't told us + // yet whether it's actually a group. Fall back to the InboundEvent's + // `threadId`: a non-null threadId implies a threaded platform (Slack + // channel thread, Discord thread), which we treat as a group. + const isGroup = event.threadId !== null; + const engageMode: MessagingGroupAgent['engage_mode'] = isGroup ? 'mention-sticky' : 'pattern'; + const engagePattern = isGroup ? null : '.'; + + const mgaId = `mga-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; + createMessagingGroupAgent({ + id: mgaId, + messaging_group_id: row.messaging_group_id, + agent_group_id: row.agent_group_id, + engage_mode: engageMode, + engage_pattern: engagePattern, + sender_scope: 'known', + ignored_message_policy: 'accumulate', + session_mode: 'shared', + priority: 0, + created_at: new Date().toISOString(), + }); + log.info('Channel registration approved — wiring created', { + messagingGroupId: row.messaging_group_id, + agentGroupId: row.agent_group_id, + mgaId, + engageMode, + approverId, + }); + + // Auto-admit the triggering sender. Without this, the replay below + // would bounce through sender-approval (sender_scope='known' + + // sender-is-not-a-member). + const senderUserId = extractAndUpsertUser(event); + if (senderUserId) { + addMember({ + user_id: senderUserId, + agent_group_id: row.agent_group_id, + added_by: approverId, + added_at: new Date().toISOString(), + }); + } + + // Clear the pending row BEFORE replay so the gate check on the second + // attempt sees a wired channel (agentCount > 0) and takes the fan-out + // path normally. + deletePendingChannelApproval(row.messaging_group_id); + + try { + await routeInbound(event); + } catch (err) { + log.error('Failed to replay message after channel approval', { + messagingGroupId: row.messaging_group_id, + err, + }); + } + return true; +} + +registerResponseHandler(handleChannelApprovalResponse); diff --git a/src/router.ts b/src/router.ts index 1d819c0bf..4289f1fe9 100644 --- a/src/router.ts +++ b/src/router.ts @@ -127,6 +127,27 @@ export function setSenderScopeGate(fn: SenderScopeGateFn): void { senderScopeGate = fn; } +/** + * Channel-registration hook. Runs when the router sees a mention/DM on a + * messaging group that has no wirings AND hasn't been denied. The hook is + * expected to escalate to an owner (card, etc.) and arrange for future + * replay via routeInbound after approval. Fire-and-forget from the + * router's perspective. + * + * Registered by the permissions module. Without the module the router + * silently records the drop with reason='no_agent_wired' and moves on. + */ +export type ChannelRequestGateFn = (mg: MessagingGroup, event: InboundEvent) => Promise; + +let channelRequestGate: ChannelRequestGateFn | null = null; + +export function setChannelRequestGate(fn: ChannelRequestGateFn): void { + if (channelRequestGate) { + log.warn('Channel-request gate overwritten'); + } + channelRequestGate = fn; +} + function safeParseContent(raw: string): { text?: string; sender?: string; senderId?: string } { try { return JSON.parse(raw); @@ -156,12 +177,12 @@ export async function routeInbound(event: InboundEvent): Promise { const found = getMessagingGroupWithAgentCount(event.channelType, event.platformId); let mg: MessagingGroup; + let agentCount: number; if (!found) { // No messaging_groups row. Auto-create only when the message warrants // attention (the bot was addressed — @mention or DM). Plain chatter in // channels we merely sit in stays silent — no row, no DB writes. if (!isMention) return; - const mgId = `mg-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; mg = { id: mgId, @@ -170,6 +191,7 @@ export async function routeInbound(event: InboundEvent): Promise { name: null, is_group: 0, unknown_sender_policy: 'request_approval', + denied_at: null, created_at: new Date().toISOString(), }; createMessagingGroup(mg); @@ -178,30 +200,51 @@ export async function routeInbound(event: InboundEvent): Promise { channelType: event.channelType, platformId: event.platformId, }); + agentCount = 0; } else { mg = found.mg; - if (found.agentCount === 0) { - // Messaging group exists but has no wirings. Stay silent for plain - // messages; only log + record on explicit mention/DM so admins can - // see that someone tried to reach the bot on an unwired channel. - if (!isMention) return; - log.warn('MESSAGE DROPPED — no agent groups wired to this channel. Run setup register step to configure.', { + agentCount = found.agentCount; + } + + // 1b. No wirings — either silent drop (plain chatter / denied channel) or + // escalate to owner for channel-registration approval. + if (agentCount === 0) { + if (!isMention) return; + if (mg.denied_at) { + log.debug('Message dropped — channel was denied by owner', { + messagingGroupId: mg.id, + deniedAt: mg.denied_at, + }); + return; + } + + const parsed = safeParseContent(event.message.content); + recordDroppedMessage({ + channel_type: event.channelType, + platform_id: event.platformId, + user_id: null, + sender_name: parsed.sender ?? null, + reason: 'no_agent_wired', + messaging_group_id: mg.id, + agent_group_id: null, + }); + + if (channelRequestGate) { + // Fire-and-forget escalation. The gate is expected to build a card, + // persist pending_channel_approvals, and replay the event via + // routeInbound after approval. Errors are logged internally — the + // user's message still stays dropped here either way. + void channelRequestGate(mg, event).catch((err) => + log.error('Channel-request gate threw', { messagingGroupId: mg.id, err }), + ); + } else { + log.warn('MESSAGE DROPPED — no agent groups wired and no channel-request gate registered', { messagingGroupId: mg.id, channelType: event.channelType, platformId: event.platformId, }); - const parsed = safeParseContent(event.message.content); - recordDroppedMessage({ - channel_type: event.channelType, - platform_id: event.platformId, - user_id: null, - sender_name: parsed.sender ?? null, - reason: 'no_agent_wired', - messaging_group_id: mg.id, - agent_group_id: null, - }); - return; } + return; } // 2. Sender resolution (permissions module upserts the users row as a diff --git a/src/types.ts b/src/types.ts index b2674dae5..b3e2470d3 100644 --- a/src/types.ts +++ b/src/types.ts @@ -17,6 +17,16 @@ export interface MessagingGroup { name: string | null; is_group: number; // 0 | 1 unknown_sender_policy: UnknownSenderPolicy; + /** + * When set, the owner explicitly denied registering this channel — the + * router drops silently and does not re-escalate. Cleared by any explicit + * wiring mutation (admin command). See migration 012. + * + * Optional on the TS type so pre-migration-012 callers that build + * MessagingGroup objects in code (fixtures, etc.) don't need to update; + * the column itself defaults to NULL in SQLite. + */ + denied_at?: string | null; created_at: string; } From a29f3e5cf41d11ccfff2968e40828bcf0763c633 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Mon, 20 Apr 2026 12:18:22 +0000 Subject: [PATCH 42/95] feat(new-setup-2): bundle Telegram install into one script Extract the /add-telegram preflight + install commands into setup/install-telegram.sh so /new-setup-2 can run the adapter install programmatically when the user picks Telegram, then hand off to /add-telegram for credentials and pairing. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 4 +- setup/install-telegram.sh | 72 +++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+), 2 deletions(-) create mode 100755 setup/install-telegram.sh diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md index 869a71089..ba7070443 100644 --- a/.claude/skills/new-setup-2/SKILL.md +++ b/.claude/skills/new-setup-2/SKILL.md @@ -1,7 +1,7 @@ --- name: new-setup-2 description: Follow-on to /new-setup. Captures the operator and agent names, wires a real messaging channel, and adds quality-of-life extras. Linear rollthrough; every step is skippable. Invoked when the user picks "continue setup" at the end of /new-setup. -allowed-tools: Bash(bash setup/probe.sh) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm exec tsx scripts/init-first-agent.ts *) +allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm exec tsx scripts/init-first-agent.ts *) --- # NanoClaw phase-2 setup @@ -61,7 +61,7 @@ Print the list as plain prose. **Do not use `AskUserQuestion` for this step** When the user picks one: -1. **Install the adapter.** Invoke the matching `/add-` skill via the Skill tool. It copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels (e.g. Telegram) also run a pairing step as part of their flow. +1. **Install the adapter.** For **Telegram**, run `bash setup/install-telegram.sh` directly — it bundles the preflight + fetch + copy + register + `pnpm install` + build from `/add-telegram` into one idempotent call, then continue with credentials and pairing (invoke `/add-telegram` afterwards and its preflight will skip straight to Credentials). For every other channel, invoke the matching `/add-` skill via the Skill tool; it copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels also run a pairing step as part of their flow. 2. **Capture platform IDs.** After the `/add-` skill finishes, you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, for example, the `pair-telegram` step emits `PLATFORM_ID` and `ADMIN_USER_ID` in a status block once the user sends the 4-digit code. 3. **Wire the agent.** Run `init-first-agent.ts` in DM mode with `--no-cli-bonus` (this keeps the new agent off the CLI messaging group so the pre-existing throwaway agent still owns CLI routing cleanly): diff --git a/setup/install-telegram.sh b/setup/install-telegram.sh new file mode 100755 index 000000000..7eaf9e12d --- /dev/null +++ b/setup/install-telegram.sh @@ -0,0 +1,72 @@ +#!/usr/bin/env bash +# Setup helper: install-telegram — bundles the preflight + install commands +# from the /add-telegram skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials and pairing. +# +# Copies the Telegram adapter, helpers, tests, and the pair-telegram setup +# step in from the `channels` branch; appends the self-registration import; +# registers the `pair-telegram` entry in the setup STEPS map; installs the +# pinned @chat-adapter/telegram package; builds. All steps are safe to re-run. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_TELEGRAM ===" + +CHANNEL_FILES=( + src/channels/telegram.ts + src/channels/telegram-pairing.ts + src/channels/telegram-pairing.test.ts + src/channels/telegram-markdown-sanitize.ts + src/channels/telegram-markdown-sanitize.test.ts + setup/pair-telegram.ts +) + +needs_install=false +for f in "${CHANNEL_FILES[@]}"; do + [[ -f "$f" ]] || needs_install=true +done +grep -q "import './telegram.js';" src/channels/index.ts || needs_install=true +grep -q "'pair-telegram':" setup/index.ts || needs_install=true +grep -q '"@chat-adapter/telegram"' package.json || needs_install=true +[[ -d node_modules/@chat-adapter/telegram ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +for f in "${CHANNEL_FILES[@]}"; do + git show "origin/channels:$f" > "$f" +done + +echo "STEP: register-import" +if ! grep -q "import './telegram.js';" src/channels/index.ts; then + printf "import './telegram.js';\n" >> src/channels/index.ts +fi + +echo "STEP: register-setup-step" +if ! grep -q "'pair-telegram':" setup/index.ts; then + awk ' + { print } + /register: \(\) => import/ && !inserted { + print " '\''pair-telegram'\'': () => import('\''./pair-telegram.js'\'')," + inserted = 1 + } + ' setup/index.ts > setup/index.ts.tmp && mv setup/index.ts.tmp setup/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @chat-adapter/telegram@4.26.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" From cdefc97c3715d98397d35c4f31b8d4c8028573e1 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Mon, 20 Apr 2026 13:19:33 +0000 Subject: [PATCH 43/95] feat(new-setup-2): broaden install-telegram permission + allow tail/head/grep Switch Bash(bash setup/install-telegram.sh) to a prefix match so trailing flags or redirections don't fall through to approval prompts. Add the common read-only coreutils (tail, head, grep) the model reaches for to cap noisy build output. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md index ba7070443..f571123f8 100644 --- a/.claude/skills/new-setup-2/SKILL.md +++ b/.claude/skills/new-setup-2/SKILL.md @@ -1,7 +1,7 @@ --- name: new-setup-2 description: Follow-on to /new-setup. Captures the operator and agent names, wires a real messaging channel, and adds quality-of-life extras. Linear rollthrough; every step is skippable. Invoked when the user picks "continue setup" at the end of /new-setup. -allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm exec tsx scripts/init-first-agent.ts *) +allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm exec tsx scripts/init-first-agent.ts *) Bash(tail:*) Bash(head:*) Bash(grep:*) --- # NanoClaw phase-2 setup From 97d9cf1a638bc4929dde4b83c20d6c9179e7b1f1 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Mon, 20 Apr 2026 13:19:33 +0000 Subject: [PATCH 44/95] chore(skills): normalize + broaden setup allowlists - new-setup: switch prefix entries to :* form, add Linux Node install (nodesource curl left-half + apt-get install nodejs), node --version probe, tail/head/grep for log diagnosis. Drop brew install entry. - new-setup-2: normalize pnpm exec prefix entries to :* form. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 2 +- .claude/skills/new-setup/SKILL.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md index f571123f8..f37223a83 100644 --- a/.claude/skills/new-setup-2/SKILL.md +++ b/.claude/skills/new-setup-2/SKILL.md @@ -1,7 +1,7 @@ --- name: new-setup-2 description: Follow-on to /new-setup. Captures the operator and agent names, wires a real messaging channel, and adds quality-of-life extras. Linear rollthrough; every step is skippable. Invoked when the user picks "continue setup" at the end of /new-setup. -allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm exec tsx scripts/init-first-agent.ts *) Bash(tail:*) Bash(head:*) Bash(grep:*) +allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm exec tsx scripts/init-first-agent.ts:*) Bash(tail:*) Bash(head:*) Bash(grep:*) --- # NanoClaw phase-2 setup diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index 0a8cc2e8a..d15ba6664 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -1,7 +1,7 @@ --- name: new-setup description: Shortest path from zero to a working two-way agent chat, for any user regardless of technical background — ends at a running NanoClaw instance with at least one CLI-reachable agent. -allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(pnpm exec tsx setup/index.ts *) Bash(pnpm run chat *) Bash(brew install *) Bash(curl -fsSL https://get.docker.com | sh) Bash(sudo usermod -aG docker *) Bash(open -a Docker) Bash(sudo systemctl start docker) +allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm run chat:*) Bash(curl -fsSL https://get.docker.com | sh) Bash(curl -fsSL https://deb.nodesource.com/setup_22.x) Bash(sudo apt-get install -y nodejs) Bash(sudo usermod -aG docker:*) Bash(open -a Docker) Bash(sudo systemctl start docker) Bash(node --version) Bash(tail:*) Bash(head:*) Bash(grep:*) --- # NanoClaw bare-minimum setup From 9870deb5dd600fa109205d5ead4c61a3a713b4a8 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Mon, 20 Apr 2026 13:31:23 +0000 Subject: [PATCH 45/95] feat(new-setup-2): add timezone step with UTC confirmation Inserts a Timezone step (new step 3) that runs --step timezone and, if the resolver lands on UTC, asks the user to confirm before leaving UTC in .env; re-runs with --tz if they give a real IANA zone. Renumbers subsequent steps accordingly. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md index f37223a83..45e96f10c 100644 --- a/.claude/skills/new-setup-2/SKILL.md +++ b/.claude/skills/new-setup-2/SKILL.md @@ -36,7 +36,21 @@ Plain-prose ask: Capture as `AGENT_NAME`. If skipped, set `AGENT_NAME = OPERATOR_NAME`. Nothing persisted yet. -### 3. Pick a messaging channel +### 3. Timezone + +Run `pnpm exec tsx setup/index.ts --step timezone` and parse the status block. + +- **RESOLVED_TZ is `UTC` or `Etc/UTC`** — before leaving UTC in `.env`, confirm with the user in plain prose: + + > Your system reports UTC as the timezone. Is that actually right, or are you somewhere else? If elsewhere, tell me the IANA zone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`). Skip to keep UTC. + + If they name a different IANA timezone, re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` to overwrite `.env`. If they skip, leave UTC in place — nothing else to do. + +- **NEEDS_USER_INPUT=true** — autodetection failed. Ask for an IANA timezone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`), then re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz `. If they skip, move on. + +- Otherwise — timezone is already set; move on. + +### 4. Pick a messaging channel Print the list as plain prose. **Do not use `AskUserQuestion` for this step** — just the list, then wait for the user's reply: @@ -81,9 +95,9 @@ When the user picks one: Substitute `{channel-name}` with the friendly name (e.g. "Telegram", "WhatsApp", "Slack"). -If the user skipped, move on to step 4. +If the user skipped, move on to step 5. -### 4. Quality of life +### 5. Quality of life Optional polish. Print the list; the user may pick zero, one, or several — invoke each chosen skill in sequence: @@ -99,13 +113,13 @@ If the probe reports `PLATFORM=darwin`, also offer: Do **not** list `/add-macos-statusbar` on Linux. If the user skips everything, just move on. -### 5. Done +### 6. Done Short wrap-up: > Setup complete. You can chat with your agent on {channel-name} — or via CLI with `pnpm run chat `. -Substitute `{channel-name}` with whatever was wired in step 3. If step 3 was skipped, drop the "on {channel-name} — or" clause entirely so the line just mentions the CLI form. +Substitute `{channel-name}` with whatever was wired in step 4. If step 4 was skipped, drop the "on {channel-name} — or" clause entirely so the line just mentions the CLI form. ## If anything fails From 0d145ad9385dde2d530bf2c4c05b51a9fb4c261d Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Mon, 20 Apr 2026 13:34:33 +0000 Subject: [PATCH 46/95] feat(new-setup-2): add host directory access step Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md index 45e96f10c..d95b2b20e 100644 --- a/.claude/skills/new-setup-2/SKILL.md +++ b/.claude/skills/new-setup-2/SKILL.md @@ -97,7 +97,17 @@ When the user picks one: If the user skipped, move on to step 5. -### 5. Quality of life +### 5. Host directory access + +By default, agent containers can only touch their own workspace. If the user wants the agent to read or write files in specific host directories, those paths need to go on the mount allowlist. + +Plain-prose ask: + +> Want your agent to be able to read or write files in any host directories (e.g. a code project, `~/Documents`)? Name the paths and I'll add them — or skip to keep the default isolated workspace. + +If the user names paths, invoke `/manage-mounts` via the Skill tool to add them. If they skip, move on. + +### 6. Quality of life Optional polish. Print the list; the user may pick zero, one, or several — invoke each chosen skill in sequence: @@ -113,7 +123,7 @@ If the probe reports `PLATFORM=darwin`, also offer: Do **not** list `/add-macos-statusbar` on Linux. If the user skips everything, just move on. -### 6. Done +### 7. Done Short wrap-up: From ccb676ae91b1b5ebe26dc75bba44862f800de7cf Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Mon, 20 Apr 2026 13:53:25 +0000 Subject: [PATCH 47/95] feat(new-setup-2): use AskUserQuestion for timezone + mounts; number channel list Timezone and host-mount prompts now go through AskUserQuestion for a cleaner UI; channel selection stays plain-prose but is numbered (14 options exceeds the 4-option AskUserQuestion cap). Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 52 +++++++++++++++++------------ 1 file changed, 30 insertions(+), 22 deletions(-) diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md index d95b2b20e..eedea15b1 100644 --- a/.claude/skills/new-setup-2/SKILL.md +++ b/.claude/skills/new-setup-2/SKILL.md @@ -40,36 +40,40 @@ Capture as `AGENT_NAME`. If skipped, set `AGENT_NAME = OPERATOR_NAME`. Nothing p Run `pnpm exec tsx setup/index.ts --step timezone` and parse the status block. -- **RESOLVED_TZ is `UTC` or `Etc/UTC`** — before leaving UTC in `.env`, confirm with the user in plain prose: +- **RESOLVED_TZ is `UTC` or `Etc/UTC`** — before leaving UTC in `.env`, confirm with `AskUserQuestion`: - > Your system reports UTC as the timezone. Is that actually right, or are you somewhere else? If elsewhere, tell me the IANA zone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`). Skip to keep UTC. + - **Question**: "Your system reports UTC as the timezone. Is that right, or are you somewhere else?" + - **Header**: "Timezone" + - **Options**: + 1. `Keep UTC` — "Leave timezone as UTC." + 2. `I'm somewhere else` — "I'll name the IANA zone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`) via Other." - If they name a different IANA timezone, re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` to overwrite `.env`. If they skip, leave UTC in place — nothing else to do. + If they pick "I'm somewhere else" (or type an IANA zone via Other), re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` to overwrite `.env`. If they keep UTC or skip, leave UTC in place. -- **NEEDS_USER_INPUT=true** — autodetection failed. Ask for an IANA timezone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`), then re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz `. If they skip, move on. +- **NEEDS_USER_INPUT=true** — autodetection failed. Use `AskUserQuestion` with the same two options above (reword the question to "Autodetection failed — what timezone are you in?"), then re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` if they supply one. If they skip, move on. - Otherwise — timezone is already set; move on. ### 4. Pick a messaging channel -Print the list as plain prose. **Do not use `AskUserQuestion` for this step** — just the list, then wait for the user's reply: +Print the list as a numbered plain-prose list (too many options for `AskUserQuestion`, which caps at 4). The user replies with a number or channel name. Preserve the numbering exactly: > Which messaging channel should I wire your agent to? > -> - **WhatsApp (native)** — `/add-whatsapp` -> - **WhatsApp Cloud (Meta official)** — `/add-whatsapp-cloud` -> - **Telegram** — `/add-telegram` -> - **Slack** — `/add-slack` -> - **Discord** — `/add-discord` -> - **iMessage** — `/add-imessage` -> - **Teams** — `/add-teams` -> - **Matrix** — `/add-matrix` -> - **Google Chat** — `/add-gchat` -> - **Linear** — `/add-linear` -> - **GitHub** — `/add-github` -> - **Webex** — `/add-webex` -> - **Resend (email)** — `/add-resend` -> - **Emacs** — `/add-emacs` +> 1. **WhatsApp (native)** — `/add-whatsapp` +> 2. **WhatsApp Cloud (Meta official)** — `/add-whatsapp-cloud` +> 3. **Telegram** — `/add-telegram` +> 4. **Slack** — `/add-slack` +> 5. **Discord** — `/add-discord` +> 6. **iMessage** — `/add-imessage` +> 7. **Teams** — `/add-teams` +> 8. **Matrix** — `/add-matrix` +> 9. **Google Chat** — `/add-gchat` +> 10. **Linear** — `/add-linear` +> 11. **GitHub** — `/add-github` +> 12. **Webex** — `/add-webex` +> 13. **Resend (email)** — `/add-resend` +> 14. **Emacs** — `/add-emacs` > > Or say "skip" to leave this for later. @@ -101,11 +105,15 @@ If the user skipped, move on to step 5. By default, agent containers can only touch their own workspace. If the user wants the agent to read or write files in specific host directories, those paths need to go on the mount allowlist. -Plain-prose ask: +Use `AskUserQuestion`: -> Want your agent to be able to read or write files in any host directories (e.g. a code project, `~/Documents`)? Name the paths and I'll add them — or skip to keep the default isolated workspace. +- **Question**: "Want your agent to read or write files in any host directories (e.g. a code project, `~/Documents`)?" +- **Header**: "Host mounts" +- **Options**: + 1. `Keep isolated` — "Agent only touches its own workspace (Recommended)." + 2. `Add host paths` — "I'll name the directories to allowlist via Other." -If the user names paths, invoke `/manage-mounts` via the Skill tool to add them. If they skip, move on. +If they pick "Add host paths" (or name paths via Other), invoke `/manage-mounts` via the Skill tool to add them. If they keep it isolated or skip, move on. ### 6. Quality of life From 712a0e1e010f1abe796569dd8a60b6b506fc11a1 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Mon, 20 Apr 2026 15:18:35 +0000 Subject: [PATCH 48/95] feat(new-setup): wrap node/docker installs and add generic set-env step MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adds three allowlist-friendly setup helpers so /new-setup and /new-setup-2 don't hit unmatchable commands during a fresh install: - setup/install-node.sh — idempotent Node 22 install wrapper (macOS via brew, Linux via NodeSource + apt). Replaces the raw `curl | sudo -E bash -` flow whose stdin-consuming `bash -` segment can't be pre-approved. - setup/install-docker.sh — same pattern for Docker (brew --cask on macOS, get.docker.com on Linux + usermod). - setup/set-env.ts — generic `--step set-env` that writes KEY=VALUE to .env (and optionally syncs to data/env/env) so channel-install flows don't invent `grep && sed && rm` pipelines, which split at each && and can't be tightly allowlisted. new-setup-2's Telegram path now uses set-env for TELEGRAM_BOT_TOKEN and explicitly skips /add-telegram's Credentials section. new-setup step 1 and step 2 now call the install wrappers; the raw curl/apt entries are gone from the allowed-tools list. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 17 +++++-- .claude/skills/new-setup/SKILL.md | 13 ++--- setup/index.ts | 1 + setup/install-docker.sh | 56 +++++++++++++++++++++ setup/install-node.sh | 54 ++++++++++++++++++++ setup/set-env.ts | 77 +++++++++++++++++++++++++++++ 6 files changed, 206 insertions(+), 12 deletions(-) create mode 100755 setup/install-docker.sh create mode 100755 setup/install-node.sh create mode 100644 setup/set-env.ts diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md index eedea15b1..1b98443aa 100644 --- a/.claude/skills/new-setup-2/SKILL.md +++ b/.claude/skills/new-setup-2/SKILL.md @@ -1,7 +1,7 @@ --- name: new-setup-2 description: Follow-on to /new-setup. Captures the operator and agent names, wires a real messaging channel, and adds quality-of-life extras. Linear rollthrough; every step is skippable. Invoked when the user picks "continue setup" at the end of /new-setup. -allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm exec tsx scripts/init-first-agent.ts:*) Bash(tail:*) Bash(head:*) Bash(grep:*) +allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm exec tsx scripts/init-first-agent.ts:*) Bash(tail:*) Bash(head:*) Bash(grep:*) --- # NanoClaw phase-2 setup @@ -79,8 +79,19 @@ Print the list as a numbered plain-prose list (too many options for `AskUserQues When the user picks one: -1. **Install the adapter.** For **Telegram**, run `bash setup/install-telegram.sh` directly — it bundles the preflight + fetch + copy + register + `pnpm install` + build from `/add-telegram` into one idempotent call, then continue with credentials and pairing (invoke `/add-telegram` afterwards and its preflight will skip straight to Credentials). For every other channel, invoke the matching `/add-` skill via the Skill tool; it copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels also run a pairing step as part of their flow. -2. **Capture platform IDs.** After the `/add-` skill finishes, you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, for example, the `pair-telegram` step emits `PLATFORM_ID` and `ADMIN_USER_ID` in a status block once the user sends the 4-digit code. +1. **Install the adapter.** For **Telegram**, run `bash setup/install-telegram.sh` directly — it bundles the preflight + fetch + copy + register + `pnpm install` + build from `/add-telegram` into one idempotent call. Then handle Telegram credentials inline (below) — **do not** invoke `/add-telegram` afterward; its Credentials section would generate an unapprovable `grep && sed && rm` to write `.env`. For every other channel, invoke the matching `/add-` skill via the Skill tool; it copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels also run a pairing step as part of their flow. + + **Telegram credentials (inline):** + - Walk the user through BotFather: `/newbot` → pick name + username ending in `bot` → copy the token. + - Remind them: in `@BotFather` → `/mybots` → their bot → Bot Settings → Group Privacy → **Turn off** (only needed if the bot will live in groups; DM-only can skip). + - Persist the token and sync it to the container mount with the generic setter: + + ``` + pnpm exec tsx setup/index.ts --step set-env -- \ + --key TELEGRAM_BOT_TOKEN --value "" --sync-container + ``` + +2. **Capture platform IDs.** After the `/add-` skill finishes (or after inline credentials for Telegram), you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent ` directly and follow its `PAIR_TELEGRAM_ISSUED`/`PAIR_TELEGRAM STATUS=success` blocks — `PLATFORM_ID` and `ADMIN_USER_ID` land in the success block. 3. **Wire the agent.** Run `init-first-agent.ts` in DM mode with `--no-cli-bonus` (this keeps the new agent off the CLI messaging group so the pre-existing throwaway agent still owns CLI routing cleanly): ``` diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index d15ba6664..02cef98ec 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -1,7 +1,7 @@ --- name: new-setup description: Shortest path from zero to a working two-way agent chat, for any user regardless of technical background — ends at a running NanoClaw instance with at least one CLI-reachable agent. -allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm run chat:*) Bash(curl -fsSL https://get.docker.com | sh) Bash(curl -fsSL https://deb.nodesource.com/setup_22.x) Bash(sudo apt-get install -y nodejs) Bash(sudo usermod -aG docker:*) Bash(open -a Docker) Bash(sudo systemctl start docker) Bash(node --version) Bash(tail:*) Bash(head:*) Bash(grep:*) +allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(bash setup/install-node.sh) Bash(bash setup/install-docker.sh) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm run chat) Bash(pnpm run chat:*) Bash(open -a Docker) Bash(sudo systemctl start docker) Bash(node --version) Bash(tail:*) Bash(head:*) Bash(grep:*) --- # NanoClaw bare-minimum setup @@ -38,10 +38,7 @@ One permitted parallelism: Check probe results and skip if `HOST_DEPS=ok` — Node, pnpm, `node_modules`, and `better-sqlite3`'s native binding are already in place. -If `HOST_DEPS=missing` and `node --version` fails (Node isn't installed at all), install Node 22 **before** running `bash setup.sh`, otherwise the first bootstrap run is guaranteed to fail: - -- macOS: `brew install node@22` -- Linux / WSL: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs` +If `HOST_DEPS=missing` and `node --version` fails (Node isn't installed at all), run `bash setup/install-node.sh` **before** `bash setup.sh` — the script handles both macOS (via `brew`) and Linux/WSL (NodeSource + apt). It's idempotent and short-circuits when node is already on PATH. Then run `bash setup.sh`. If Node is already present and only `HOST_DEPS=missing`, run `bash setup.sh` directly — deps just haven't been installed yet. @@ -57,16 +54,14 @@ Parse the status block: Check probe results and skip if `DOCKER=running` AND `IMAGE_PRESENT=true`. **Runtime:** -- `DOCKER=not_found` → Docker itself is missing — install it so agent containers have an isolated place to run. - - macOS: `brew install --cask docker && open -a Docker` - - Linux: `curl -fsSL https://get.docker.com | sh && sudo usermod -aG docker $USER` (tell user they may need to log out/in for group membership) +- `DOCKER=not_found` → Docker is missing — install it so agent containers have an isolated place to run. Run `bash setup/install-docker.sh` (handles macOS via `brew --cask` and Linux via the official get.docker.com script, and adds the user to the `docker` group on Linux). On Linux the user may need to log out/in for group membership to take effect. On macOS, launch Docker afterwards with `open -a Docker`. - `DOCKER=installed_not_running` → Docker is installed but the daemon is down — start it. - macOS: `open -a Docker` - Linux: `sudo systemctl start docker` Wait ~15s after either, then proceed. -> **Loose commands:** Docker install/start. Justification: platform-specific package-manager invocations. Wrapping them in a `--step` would just move the same branching into TypeScript with no added value. +> **Loose commands:** `open -a Docker`, `sudo systemctl start docker`. Justification: daemon-start is a one-liner per platform, not worth wrapping. The actual install (which had the unmatchable `curl | sh` pattern) is now inside `setup/install-docker.sh`. **Image (run if `IMAGE_PRESENT=false`):** build the agent container image — takes a few minutes the first time, one-off cost. diff --git a/setup/index.ts b/setup/index.ts index 526ea7d63..2112cd1e4 100644 --- a/setup/index.ts +++ b/setup/index.ts @@ -10,6 +10,7 @@ const STEPS: Record< () => Promise<{ run: (args: string[]) => Promise }> > = { timezone: () => import('./timezone.js'), + 'set-env': () => import('./set-env.js'), environment: () => import('./environment.js'), container: () => import('./container.js'), register: () => import('./register.js'), diff --git a/setup/install-docker.sh b/setup/install-docker.sh new file mode 100755 index 000000000..4aaadcecb --- /dev/null +++ b/setup/install-docker.sh @@ -0,0 +1,56 @@ +#!/usr/bin/env bash +# Setup helper: install-docker — bundles Docker install into one idempotent +# script so /new-setup can run it without needing `curl | sh` in the allowlist +# (pipelines split at matching time, and `sh` receiving stdin can't be +# pre-approved safely). +# +# The script itself is the allowlisted unit; the pipes and sudo live inside +# it. Starting the daemon (after install) stays separate — `open -a Docker` +# and `sudo systemctl start docker` are already in the allowlist. +set -euo pipefail + +echo "=== NANOCLAW SETUP: INSTALL_DOCKER ===" + +if command -v docker >/dev/null 2>&1; then + echo "STATUS: already-installed" + echo "DOCKER_VERSION: $(docker --version 2>/dev/null || echo unknown)" + echo "=== END ===" + exit 0 +fi + +case "$(uname -s)" in + Darwin) + echo "STEP: brew-install-docker" + if ! command -v brew >/dev/null 2>&1; then + echo "STATUS: failed" + echo "ERROR: Homebrew not installed. Install brew first (https://brew.sh) then re-run." + echo "=== END ===" + exit 1 + fi + brew install --cask docker + ;; + Linux) + echo "STEP: docker-get-script" + curl -fsSL https://get.docker.com | sh + echo "STEP: usermod-docker-group" + sudo usermod -aG docker "$USER" + echo "NOTE: you may need to log out and back in for docker group membership to take effect" + ;; + *) + echo "STATUS: failed" + echo "ERROR: Unsupported platform: $(uname -s)" + echo "=== END ===" + exit 1 + ;; +esac + +if ! command -v docker >/dev/null 2>&1; then + echo "STATUS: failed" + echo "ERROR: docker not found on PATH after install" + echo "=== END ===" + exit 1 +fi + +echo "STATUS: installed" +echo "DOCKER_VERSION: $(docker --version 2>/dev/null || echo unknown)" +echo "=== END ===" diff --git a/setup/install-node.sh b/setup/install-node.sh new file mode 100755 index 000000000..e100ccd55 --- /dev/null +++ b/setup/install-node.sh @@ -0,0 +1,54 @@ +#!/usr/bin/env bash +# Setup helper: install-node — bundles Node 22 install into one idempotent +# script so /new-setup can run it without needing `curl | sudo -E bash -` in +# the allowlist (that pattern is inherently unmatchable — bash reads from +# stdin, so pre-approval can't inspect what's being executed). +# +# The script itself is the allowlisted unit; the pipes and sudo live inside +# it. Pure bash by design — runs before Node exists on the host. +set -euo pipefail + +echo "=== NANOCLAW SETUP: INSTALL_NODE ===" + +if command -v node >/dev/null 2>&1; then + echo "STATUS: already-installed" + echo "NODE_VERSION: $(node --version)" + echo "=== END ===" + exit 0 +fi + +case "$(uname -s)" in + Darwin) + echo "STEP: brew-install-node" + if ! command -v brew >/dev/null 2>&1; then + echo "STATUS: failed" + echo "ERROR: Homebrew not installed. Install brew first (https://brew.sh) then re-run." + echo "=== END ===" + exit 1 + fi + brew install node@22 + ;; + Linux) + echo "STEP: nodesource-setup" + curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - + echo "STEP: apt-install-nodejs" + sudo apt-get install -y nodejs + ;; + *) + echo "STATUS: failed" + echo "ERROR: Unsupported platform: $(uname -s)" + echo "=== END ===" + exit 1 + ;; +esac + +if ! command -v node >/dev/null 2>&1; then + echo "STATUS: failed" + echo "ERROR: node not found on PATH after install" + echo "=== END ===" + exit 1 +fi + +echo "STATUS: installed" +echo "NODE_VERSION: $(node --version)" +echo "=== END ===" diff --git a/setup/set-env.ts b/setup/set-env.ts new file mode 100644 index 000000000..5ee4b4e84 --- /dev/null +++ b/setup/set-env.ts @@ -0,0 +1,77 @@ +/** + * Step: set-env — Write or update a KEY=VALUE in .env, with optional sync to + * data/env/env (the container-mounted copy). + * + * Usage: + * pnpm exec tsx setup/index.ts --step set-env -- \ + * --key TELEGRAM_BOT_TOKEN --value "" [--sync-container] + * + * Exists so channel-install flows don't have to invent grep/sed/rm pipelines + * (which can't be allowlisted tightly — sed can read any file, and each + * segment of an && chain is matched separately). + * + * Logs the key but never the value. + */ +import fs from 'fs'; +import path from 'path'; + +import { log } from '../src/log.js'; +import { emitStatus } from './status.js'; + +export async function run(args: string[]): Promise { + const keyIdx = args.indexOf('--key'); + const valueIdx = args.indexOf('--value'); + const syncContainer = args.includes('--sync-container'); + + if (keyIdx === -1 || !args[keyIdx + 1]) { + throw new Error('--key is required'); + } + if (valueIdx === -1 || args[valueIdx + 1] === undefined) { + throw new Error('--value is required'); + } + + const key = args[keyIdx + 1]; + const value = args[valueIdx + 1]; + + if (!/^[A-Z][A-Z0-9_]*$/.test(key)) { + throw new Error(`Invalid env key: ${key} (must be UPPER_SNAKE_CASE)`); + } + + const projectRoot = process.cwd(); + const envFile = path.join(projectRoot, '.env'); + + let content = ''; + if (fs.existsSync(envFile)) { + content = fs.readFileSync(envFile, 'utf-8'); + } + + const lineRegex = new RegExp(`^${key}=.*$`, 'm'); + const newLine = `${key}=${value}`; + const existed = lineRegex.test(content); + + if (existed) { + content = content.replace(lineRegex, newLine); + } else { + const sep = content && !content.endsWith('\n') ? '\n' : ''; + content = content + sep + newLine + '\n'; + } + + fs.writeFileSync(envFile, content); + log.info('Updated .env', { key, existed }); + + let synced = false; + if (syncContainer) { + const dataEnvDir = path.join(projectRoot, 'data', 'env'); + fs.mkdirSync(dataEnvDir, { recursive: true }); + fs.copyFileSync(envFile, path.join(dataEnvDir, 'env')); + synced = true; + log.info('Synced .env to container mount', { path: 'data/env/env' }); + } + + emitStatus('SET_ENV', { + KEY: key, + EXISTED: existed, + SYNCED_TO_CONTAINER: synced, + STATUS: 'success', + }); +} From 866b7915b524b0da35763a52ae82885945a27248 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 18:25:32 +0300 Subject: [PATCH 49/95] fix(container): add /start to filtered commands MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Telegram clients send /start when a user first DMs a bot (and when they tap "Start" on a bot profile). It's a platform handshake, not a user-intended prompt — forwarding it to the agent wastes a turn and produces a confused response. Matches the existing filter pattern for /help, /login, /logout, /doctor, /config. Co-Authored-By: Claude Opus 4.7 (1M context) --- container/agent-runner/src/formatter.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/container/agent-runner/src/formatter.ts b/container/agent-runner/src/formatter.ts index b03f5bde8..2e907208d 100644 --- a/container/agent-runner/src/formatter.ts +++ b/container/agent-runner/src/formatter.ts @@ -12,7 +12,7 @@ import { TIMEZONE, formatLocalTime } from './timezone.js'; export type CommandCategory = 'admin' | 'filtered' | 'passthrough' | 'none'; const ADMIN_COMMANDS = new Set(['/remote-control', '/clear', '/compact', '/context', '/cost', '/files']); -const FILTERED_COMMANDS = new Set(['/help', '/login', '/logout', '/doctor', '/config']); +const FILTERED_COMMANDS = new Set(['/help', '/login', '/logout', '/doctor', '/config', '/start']); export interface CommandInfo { category: CommandCategory; From dadf258136b7a8c851681c4e632bfb976fac2e04 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Mon, 20 Apr 2026 15:33:56 +0000 Subject: [PATCH 50/95] feat(new-setup-2): add per-channel bundled install scripts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Twelve idempotent install scripts matching install-telegram.sh's shape, one per channel in /new-setup-2's pick list (except Emacs, which uses a git-merge install flow). Each bundles preflight + fetch + copy + register + pnpm install + build so a single allowlisted bash call can replace a chain of permission prompts. Linear's also patches chat-sdk-bridge.ts for catchAll forwarding; Matrix's runs the post-install ESM-extension dist patch; WhatsApp-native's covers the deterministic install portion only — QR/pairing auth still lives in /add-whatsapp. Scripts only; new-setup-2/SKILL.md integration deferred pending a decision on whether to generalize the set-env pattern from 712a0e1 across the Chat SDK channels (each /add-/SKILL.md's Credentials section has a similar unapprovable shell chain). Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/install-discord.sh | 46 ++++++++++++++++ setup/install-gchat.sh | 46 ++++++++++++++++ setup/install-github.sh | 46 ++++++++++++++++ setup/install-imessage.sh | 47 ++++++++++++++++ setup/install-linear.sh | 95 +++++++++++++++++++++++++++++++++ setup/install-matrix.sh | 62 +++++++++++++++++++++ setup/install-resend.sh | 46 ++++++++++++++++ setup/install-slack.sh | 46 ++++++++++++++++ setup/install-teams.sh | 46 ++++++++++++++++ setup/install-webex.sh | 46 ++++++++++++++++ setup/install-whatsapp-cloud.sh | 46 ++++++++++++++++ setup/install-whatsapp.sh | 75 ++++++++++++++++++++++++++ 12 files changed, 647 insertions(+) create mode 100755 setup/install-discord.sh create mode 100755 setup/install-gchat.sh create mode 100755 setup/install-github.sh create mode 100755 setup/install-imessage.sh create mode 100755 setup/install-linear.sh create mode 100755 setup/install-matrix.sh create mode 100755 setup/install-resend.sh create mode 100755 setup/install-slack.sh create mode 100755 setup/install-teams.sh create mode 100755 setup/install-webex.sh create mode 100755 setup/install-whatsapp-cloud.sh create mode 100755 setup/install-whatsapp.sh diff --git a/setup/install-discord.sh b/setup/install-discord.sh new file mode 100755 index 000000000..ee221f910 --- /dev/null +++ b/setup/install-discord.sh @@ -0,0 +1,46 @@ +#!/usr/bin/env bash +# Setup helper: install-discord — bundles the preflight + install commands +# from the /add-discord skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials. +# +# Copies the Discord adapter in from the `channels` branch; appends the +# self-registration import; installs the pinned @chat-adapter/discord package; +# builds. All steps are safe to re-run. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_DISCORD ===" + +needs_install=false +[[ -f src/channels/discord.ts ]] || needs_install=true +grep -q "import './discord.js';" src/channels/index.ts || needs_install=true +grep -q '"@chat-adapter/discord"' package.json || needs_install=true +[[ -d node_modules/@chat-adapter/discord ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/discord.ts > src/channels/discord.ts + +echo "STEP: register-import" +if ! grep -q "import './discord.js';" src/channels/index.ts; then + printf "import './discord.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @chat-adapter/discord@4.26.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-gchat.sh b/setup/install-gchat.sh new file mode 100755 index 000000000..f5c210b57 --- /dev/null +++ b/setup/install-gchat.sh @@ -0,0 +1,46 @@ +#!/usr/bin/env bash +# Setup helper: install-gchat — bundles the preflight + install commands +# from the /add-gchat skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials. +# +# Copies the Google Chat adapter in from the `channels` branch; appends the +# self-registration import; installs the pinned @chat-adapter/gchat package; +# builds. All steps are safe to re-run. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_GCHAT ===" + +needs_install=false +[[ -f src/channels/gchat.ts ]] || needs_install=true +grep -q "import './gchat.js';" src/channels/index.ts || needs_install=true +grep -q '"@chat-adapter/gchat"' package.json || needs_install=true +[[ -d node_modules/@chat-adapter/gchat ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/gchat.ts > src/channels/gchat.ts + +echo "STEP: register-import" +if ! grep -q "import './gchat.js';" src/channels/index.ts; then + printf "import './gchat.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @chat-adapter/gchat@4.26.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-github.sh b/setup/install-github.sh new file mode 100755 index 000000000..81c2977e8 --- /dev/null +++ b/setup/install-github.sh @@ -0,0 +1,46 @@ +#!/usr/bin/env bash +# Setup helper: install-github — bundles the preflight + install commands +# from the /add-github skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials. +# +# Copies the GitHub adapter in from the `channels` branch; appends the +# self-registration import; installs the pinned @chat-adapter/github package; +# builds. All steps are safe to re-run. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_GITHUB ===" + +needs_install=false +[[ -f src/channels/github.ts ]] || needs_install=true +grep -q "import './github.js';" src/channels/index.ts || needs_install=true +grep -q '"@chat-adapter/github"' package.json || needs_install=true +[[ -d node_modules/@chat-adapter/github ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/github.ts > src/channels/github.ts + +echo "STEP: register-import" +if ! grep -q "import './github.js';" src/channels/index.ts; then + printf "import './github.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @chat-adapter/github@4.26.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-imessage.sh b/setup/install-imessage.sh new file mode 100755 index 000000000..0b1df3467 --- /dev/null +++ b/setup/install-imessage.sh @@ -0,0 +1,47 @@ +#!/usr/bin/env bash +# Setup helper: install-imessage — bundles the preflight + install commands +# from the /add-imessage skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials. +# +# Copies the iMessage adapter in from the `channels` branch; appends the +# self-registration import; installs the pinned chat-adapter-imessage package; +# builds. Local vs remote mode pick stays in the skill — this script only +# handles the deterministic install. All steps are safe to re-run. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_IMESSAGE ===" + +needs_install=false +[[ -f src/channels/imessage.ts ]] || needs_install=true +grep -q "import './imessage.js';" src/channels/index.ts || needs_install=true +grep -q '"chat-adapter-imessage"' package.json || needs_install=true +[[ -d node_modules/chat-adapter-imessage ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/imessage.ts > src/channels/imessage.ts + +echo "STEP: register-import" +if ! grep -q "import './imessage.js';" src/channels/index.ts; then + printf "import './imessage.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install chat-adapter-imessage@0.1.1 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-linear.sh b/setup/install-linear.sh new file mode 100755 index 000000000..9f42bec54 --- /dev/null +++ b/setup/install-linear.sh @@ -0,0 +1,95 @@ +#!/usr/bin/env bash +# Setup helper: install-linear — bundles the preflight + install commands +# from the /add-linear skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials. +# +# Copies the Linear adapter in from the `channels` branch; appends the +# self-registration import; patches src/channels/chat-sdk-bridge.ts to add +# catch-all forwarding (Linear OAuth apps can't be @-mentioned, so the +# onNewMention handler never fires — the bridge needs a catchAll path); +# installs the pinned @chat-adapter/linear package; builds. All steps are +# safe to re-run. +# +# Note: the bridge patch's onNewMessage handler passes `false` for isMention +# (current trunk signature requires the arg). The /add-linear SKILL's +# snippet omits the arg — this script uses the full signature so TypeScript +# builds cleanly. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_LINEAR ===" + +needs_install=false +[[ -f src/channels/linear.ts ]] || needs_install=true +grep -q "import './linear.js';" src/channels/index.ts || needs_install=true +grep -q '"@chat-adapter/linear"' package.json || needs_install=true +[[ -d node_modules/@chat-adapter/linear ]] || needs_install=true +grep -q 'catchAll' src/channels/chat-sdk-bridge.ts || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/linear.ts > src/channels/linear.ts + +echo "STEP: register-import" +if ! grep -q "import './linear.js';" src/channels/index.ts; then + printf "import './linear.js';\n" >> src/channels/index.ts +fi + +echo "STEP: patch-bridge-catchall-field" +if ! grep -q 'catchAll?: boolean;' src/channels/chat-sdk-bridge.ts; then + awk ' + /^export interface ChatSdkBridgeConfig \{/ { in_iface = 1 } + in_iface && /^\}/ && !inserted { + print " /**" + print " * Forward ALL messages in unsubscribed threads, not just @-mentions." + print " * Use for platforms where the bot identity can'\''t be @-mentioned (e.g." + print " * Linear OAuth apps). The thread is auto-subscribed on first message." + print " */" + print " catchAll?: boolean;" + inserted = 1 + in_iface = 0 + } + { print } + ' src/channels/chat-sdk-bridge.ts > src/channels/chat-sdk-bridge.ts.tmp \ + && mv src/channels/chat-sdk-bridge.ts.tmp src/channels/chat-sdk-bridge.ts +fi + +echo "STEP: patch-bridge-catchall-handler" +if ! grep -q 'if (config.catchAll) {' src/channels/chat-sdk-bridge.ts; then + awk ' + / \/\/ DMs — apply engage rules too/ && !inserted { + print " // Catch-all for platforms where @-mention isn'\''t possible (e.g. Linear" + print " // OAuth apps). Forward every unsubscribed message and auto-subscribe." + print " if (config.catchAll) {" + print " chat.onNewMessage(/.*/, async (thread, message) => {" + print " const channelId = adapter.channelIdFromThreadId(thread.id);" + print " await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message, false));" + print " await thread.subscribe();" + print " });" + print " }" + print "" + inserted = 1 + } + { print } + ' src/channels/chat-sdk-bridge.ts > src/channels/chat-sdk-bridge.ts.tmp \ + && mv src/channels/chat-sdk-bridge.ts.tmp src/channels/chat-sdk-bridge.ts +fi + +echo "STEP: pnpm-install" +pnpm install @chat-adapter/linear@4.26.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-matrix.sh b/setup/install-matrix.sh new file mode 100755 index 000000000..06d5ccd76 --- /dev/null +++ b/setup/install-matrix.sh @@ -0,0 +1,62 @@ +#!/usr/bin/env bash +# Setup helper: install-matrix — bundles the preflight + install commands +# from the /add-matrix skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials. +# +# Copies the Matrix adapter in from the `channels` branch; appends the +# self-registration import; installs the pinned @beeper/chat-adapter-matrix +# package; patches the adapter's published dist so its matrix-js-sdk/lib +# imports carry .js extensions (required under Node 22 strict ESM); builds. +# All steps are safe to re-run — re-run this script after any pnpm install +# that touches the adapter. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_MATRIX ===" + +needs_install=false +[[ -f src/channels/matrix.ts ]] || needs_install=true +grep -q "import './matrix.js';" src/channels/index.ts || needs_install=true +grep -q '"@beeper/chat-adapter-matrix"' package.json || needs_install=true +[[ -d node_modules/@beeper/chat-adapter-matrix ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/matrix.ts > src/channels/matrix.ts + +echo "STEP: register-import" +if ! grep -q "import './matrix.js';" src/channels/index.ts; then + printf "import './matrix.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @beeper/chat-adapter-matrix@0.2.0 + +echo "STEP: patch-esm-extensions" +node -e ' + const fs = require("fs"), path = require("path"); + const root = "node_modules/.pnpm"; + const dir = fs.readdirSync(root).find(d => d.startsWith("@beeper+chat-adapter-matrix@")); + if (!dir) { console.log("Matrix adapter not installed"); process.exit(0); } + const f = path.join(root, dir, "node_modules/@beeper/chat-adapter-matrix/dist/index.js"); + fs.writeFileSync(f, fs.readFileSync(f, "utf8").replace( + /from "(matrix-js-sdk\/lib\/[^"]+?)(? src/channels/resend.ts + +echo "STEP: register-import" +if ! grep -q "import './resend.js';" src/channels/index.ts; then + printf "import './resend.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @resend/chat-sdk-adapter@0.1.1 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-slack.sh b/setup/install-slack.sh new file mode 100755 index 000000000..8be6a373d --- /dev/null +++ b/setup/install-slack.sh @@ -0,0 +1,46 @@ +#!/usr/bin/env bash +# Setup helper: install-slack — bundles the preflight + install commands +# from the /add-slack skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials. +# +# Copies the Slack adapter in from the `channels` branch; appends the +# self-registration import; installs the pinned @chat-adapter/slack package; +# builds. All steps are safe to re-run. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_SLACK ===" + +needs_install=false +[[ -f src/channels/slack.ts ]] || needs_install=true +grep -q "import './slack.js';" src/channels/index.ts || needs_install=true +grep -q '"@chat-adapter/slack"' package.json || needs_install=true +[[ -d node_modules/@chat-adapter/slack ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/slack.ts > src/channels/slack.ts + +echo "STEP: register-import" +if ! grep -q "import './slack.js';" src/channels/index.ts; then + printf "import './slack.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @chat-adapter/slack@4.26.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-teams.sh b/setup/install-teams.sh new file mode 100755 index 000000000..cb66f67e7 --- /dev/null +++ b/setup/install-teams.sh @@ -0,0 +1,46 @@ +#!/usr/bin/env bash +# Setup helper: install-teams — bundles the preflight + install commands +# from the /add-teams skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials. +# +# Copies the Teams adapter in from the `channels` branch; appends the +# self-registration import; installs the pinned @chat-adapter/teams package; +# builds. All steps are safe to re-run. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_TEAMS ===" + +needs_install=false +[[ -f src/channels/teams.ts ]] || needs_install=true +grep -q "import './teams.js';" src/channels/index.ts || needs_install=true +grep -q '"@chat-adapter/teams"' package.json || needs_install=true +[[ -d node_modules/@chat-adapter/teams ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/teams.ts > src/channels/teams.ts + +echo "STEP: register-import" +if ! grep -q "import './teams.js';" src/channels/index.ts; then + printf "import './teams.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @chat-adapter/teams@4.26.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-webex.sh b/setup/install-webex.sh new file mode 100755 index 000000000..8bbbc836c --- /dev/null +++ b/setup/install-webex.sh @@ -0,0 +1,46 @@ +#!/usr/bin/env bash +# Setup helper: install-webex — bundles the preflight + install commands +# from the /add-webex skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to credentials. +# +# Copies the Webex adapter in from the `channels` branch; appends the +# self-registration import; installs the pinned @bitbasti/chat-adapter-webex +# package; builds. All steps are safe to re-run. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_WEBEX ===" + +needs_install=false +[[ -f src/channels/webex.ts ]] || needs_install=true +grep -q "import './webex.js';" src/channels/index.ts || needs_install=true +grep -q '"@bitbasti/chat-adapter-webex"' package.json || needs_install=true +[[ -d node_modules/@bitbasti/chat-adapter-webex ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/webex.ts > src/channels/webex.ts + +echo "STEP: register-import" +if ! grep -q "import './webex.js';" src/channels/index.ts; then + printf "import './webex.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @bitbasti/chat-adapter-webex@0.1.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-whatsapp-cloud.sh b/setup/install-whatsapp-cloud.sh new file mode 100755 index 000000000..377327809 --- /dev/null +++ b/setup/install-whatsapp-cloud.sh @@ -0,0 +1,46 @@ +#!/usr/bin/env bash +# Setup helper: install-whatsapp-cloud — bundles the preflight + install +# commands from the /add-whatsapp-cloud skill into one idempotent script so +# /new-setup-2 can run them programmatically before continuing to credentials. +# +# Copies the WhatsApp Cloud adapter in from the `channels` branch; appends the +# self-registration import; installs the pinned @chat-adapter/whatsapp package; +# builds. All steps are safe to re-run. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_WHATSAPP_CLOUD ===" + +needs_install=false +[[ -f src/channels/whatsapp-cloud.ts ]] || needs_install=true +grep -q "import './whatsapp-cloud.js';" src/channels/index.ts || needs_install=true +grep -q '"@chat-adapter/whatsapp"' package.json || needs_install=true +[[ -d node_modules/@chat-adapter/whatsapp ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +git show origin/channels:src/channels/whatsapp-cloud.ts > src/channels/whatsapp-cloud.ts + +echo "STEP: register-import" +if ! grep -q "import './whatsapp-cloud.js';" src/channels/index.ts; then + printf "import './whatsapp-cloud.js';\n" >> src/channels/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @chat-adapter/whatsapp@4.26.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" diff --git a/setup/install-whatsapp.sh b/setup/install-whatsapp.sh new file mode 100755 index 000000000..0d307f53c --- /dev/null +++ b/setup/install-whatsapp.sh @@ -0,0 +1,75 @@ +#!/usr/bin/env bash +# Setup helper: install-whatsapp — bundles the preflight + install commands +# from the /add-whatsapp skill into one idempotent script so /new-setup-2 can +# run them programmatically before continuing to QR/pairing-code auth. +# +# Copies the native Baileys WhatsApp adapter, its whatsapp-auth and groups +# setup steps in from the `channels` branch; appends the self-registration +# import; registers `groups` and `whatsapp-auth` entries in the setup STEPS +# map; installs the pinned @whiskeysockets/baileys + qrcode + pino packages; +# builds. All steps are safe to re-run. QR/pairing-code authentication +# stays in the skill — this script only handles the deterministic install. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +echo "=== NANOCLAW SETUP: INSTALL_WHATSAPP ===" + +CHANNEL_FILES=( + src/channels/whatsapp.ts + setup/whatsapp-auth.ts + setup/groups.ts +) + +needs_install=false +for f in "${CHANNEL_FILES[@]}"; do + [[ -f "$f" ]] || needs_install=true +done +grep -q "import './whatsapp.js';" src/channels/index.ts || needs_install=true +grep -q "groups: " setup/index.ts || needs_install=true +grep -q "'whatsapp-auth':" setup/index.ts || needs_install=true +grep -q '"@whiskeysockets/baileys"' package.json || needs_install=true +grep -q '"qrcode"' package.json || needs_install=true +grep -q '"pino"' package.json || needs_install=true +[[ -d node_modules/@whiskeysockets/baileys ]] || needs_install=true + +if ! $needs_install; then + echo "STATUS: already-installed" + echo "=== END ===" + exit 0 +fi + +echo "STEP: fetch-channels-branch" +git fetch origin channels + +echo "STEP: copy-files" +for f in "${CHANNEL_FILES[@]}"; do + git show "origin/channels:$f" > "$f" +done + +echo "STEP: register-import" +if ! grep -q "import './whatsapp.js';" src/channels/index.ts; then + printf "import './whatsapp.js';\n" >> src/channels/index.ts +fi + +echo "STEP: register-setup-steps" +if ! grep -q "'whatsapp-auth':" setup/index.ts; then + awk ' + { print } + /register: \(\) => import/ && !inserted { + print " groups: () => import('\''./groups.js'\'')," + print " '\''whatsapp-auth'\'': () => import('\''./whatsapp-auth.js'\'')," + inserted = 1 + } + ' setup/index.ts > setup/index.ts.tmp && mv setup/index.ts.tmp setup/index.ts +fi + +echo "STEP: pnpm-install" +pnpm install @whiskeysockets/baileys@6.17.16 qrcode@1.5.4 @types/qrcode@1.5.6 pino@9.6.0 + +echo "STEP: pnpm-build" +pnpm run build + +echo "STATUS: installed" +echo "=== END ===" From 6c26c0413a35366ecb0c08474c83cb0501cc3985 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 23:30:47 +0300 Subject: [PATCH 51/95] feat(router,cli): replyTo override + CLI admin-transport flows MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - InboundEvent gains an optional replyTo; router stamps the row's address fields from it when set, so replies can route to a different channel than the one the inbound came in on. - ChannelSetup adds onInboundEvent for admin-transport adapters that build the full event themselves. - CLI wire format accepts {text, to, reply_to}. Routed messages go through onInboundEvent and do not evict an active chat client. - init-first-agent hands the DM welcome to the running service via data/cli.sock — synchronous wake, no sweep wait. Fails loudly if the service is down; no silent fallback. - Split the CLI scratch-agent bootstrap into scripts/init-cli-agent.ts; init-first-agent is DM-only. Agents cannot set replyTo: it lives only on the inbound/router seam and is consumed once when writing messages_in. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/init-first-agent/SKILL.md | 7 +- scripts/init-cli-agent.ts | 179 ++++++++++++++ scripts/init-first-agent.ts | 244 ++++++++++---------- setup/cli-agent.ts | 28 +-- src/channels/adapter.ts | 43 ++++ src/channels/channel-registry.test.ts | 2 + src/channels/cli.ts | 156 ++++++++++--- src/host-core.test.ts | 2 +- src/index.ts | 9 + src/modules/approvals/picks.test.ts | 1 + src/modules/permissions/channel-approval.ts | 2 +- src/modules/permissions/index.ts | 2 +- src/modules/permissions/permissions.test.ts | 1 + src/modules/permissions/sender-approval.ts | 2 +- src/router.ts | 38 ++- 15 files changed, 503 insertions(+), 213 deletions(-) create mode 100644 scripts/init-cli-agent.ts diff --git a/.claude/skills/init-first-agent/SKILL.md b/.claude/skills/init-first-agent/SKILL.md index be788451a..6b110d37f 100644 --- a/.claude/skills/init-first-agent/SKILL.md +++ b/.claude/skills/init-first-agent/SKILL.md @@ -87,18 +87,17 @@ The script: 2. Creates the `agent_groups` row and calls `initGroupFilesystem` at `groups/dm-with-/`. 3. Reuses or creates the DM `messaging_groups` row. 4. Wires them via `messaging_group_agents` (which auto-creates the companion `agent_destinations` row). -5. Resolves the session (creates `inbound.db` / `outbound.db`). -6. Writes a `kind: 'chat'`, `sender: 'system'` welcome message into `inbound.db`. +5. Hands the welcome message to the running service via its CLI socket (`data/cli.sock`), targeting the DM messaging group. The service routes it into the DM session, which wakes the container synchronously. If the socket isn't reachable (service down), falls back to a direct `inbound.db` write that the next host sweep picks up. Show the script's output to the user. ## 5. Verify -Host sweep runs every ~60s. Within one sweep window the container wakes, the agent processes the system message, and the reply flows through `outbound.db` to the channel. +The welcome DM is queued synchronously; the only wait is container cold-start (~60s on first launch) before the agent processes the message and the reply flows through `outbound.db` to the channel. Do not tail the log or poll in a sleep loop. Ask the user in plain text: -> The welcome DM should arrive within ~60 seconds. Let me know when you've received it (or if it doesn't arrive within two minutes). +> The welcome DM should arrive shortly. Let me know when you've received it (or if it doesn't arrive within two minutes). Wait for the user's reply. If they confirm receipt, the skill is done. diff --git a/scripts/init-cli-agent.ts b/scripts/init-cli-agent.ts new file mode 100644 index 000000000..ccd9387a9 --- /dev/null +++ b/scripts/init-cli-agent.ts @@ -0,0 +1,179 @@ +/** + * Initialize the scratch CLI agent used during `/new-setup`. + * + * Creates the synthetic `cli:local` user, grants owner role if no owner + * exists yet, builds an agent group with a minimal CLAUDE.md, and wires it + * to the CLI messaging group so `pnpm run chat` works immediately. + * + * No welcome is staged — the operator's first `pnpm run chat` is the + * natural wake, and the agent introduces itself on first contact per its + * CLAUDE.md. + * + * Runs alongside the service (WAL-mode sqlite) — does NOT initialize + * channel adapters, so there's no Gateway conflict. + * + * Usage: + * pnpm exec tsx scripts/init-cli-agent.ts \ + * --display-name "Gavriel" \ + * [--agent-name "Andy"] + */ +import path from 'path'; + +import { DATA_DIR } from '../src/config.js'; +import { createAgentGroup, getAgentGroupByFolder } from '../src/db/agent-groups.js'; +import { initDb } from '../src/db/connection.js'; +import { + createMessagingGroup, + createMessagingGroupAgent, + getMessagingGroupAgentByPair, + getMessagingGroupByPlatform, +} from '../src/db/messaging-groups.js'; +import { runMigrations } from '../src/db/migrations/index.js'; +import { normalizeName } from '../src/modules/agent-to-agent/db/agent-destinations.js'; +import { grantRole, hasAnyOwner } from '../src/modules/permissions/db/user-roles.js'; +import { upsertUser } from '../src/modules/permissions/db/users.js'; +import { initGroupFilesystem } from '../src/group-init.js'; +import type { AgentGroup, MessagingGroup } from '../src/types.js'; + +const CLI_CHANNEL = 'cli'; +const CLI_PLATFORM_ID = 'local'; +const CLI_SYNTHETIC_USER_ID = `${CLI_CHANNEL}:${CLI_PLATFORM_ID}`; + +interface Args { + displayName: string; + agentName: string; +} + +function parseArgs(argv: string[]): Args { + let displayName: string | undefined; + let agentName: string | undefined; + for (let i = 0; i < argv.length; i++) { + const key = argv[i]; + const val = argv[i + 1]; + if (key === '--display-name') { + displayName = val; + i++; + } else if (key === '--agent-name') { + agentName = val; + i++; + } + } + + if (!displayName) { + console.error('Missing required arg: --display-name'); + console.error('See scripts/init-cli-agent.ts header for usage.'); + process.exit(2); + } + + return { + displayName, + agentName: agentName?.trim() || displayName, + }; +} + +function generateId(prefix: string): string { + return `${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; +} + +async function main(): Promise { + const args = parseArgs(process.argv.slice(2)); + + const db = initDb(path.join(DATA_DIR, 'v2.db')); + runMigrations(db); + + const now = new Date().toISOString(); + + // 1. Synthetic CLI user + owner grant if none exists. + upsertUser({ + id: CLI_SYNTHETIC_USER_ID, + kind: CLI_CHANNEL, + display_name: args.displayName, + created_at: now, + }); + + let promotedToOwner = false; + if (!hasAnyOwner()) { + grantRole({ + user_id: CLI_SYNTHETIC_USER_ID, + role: 'owner', + agent_group_id: null, + granted_by: null, + granted_at: now, + }); + promotedToOwner = true; + } + + // 2. Agent group + filesystem. + const folder = `cli-with-${normalizeName(args.displayName)}`; + let ag: AgentGroup | undefined = getAgentGroupByFolder(folder); + if (!ag) { + const agId = generateId('ag'); + createAgentGroup({ + id: agId, + name: args.agentName, + folder, + agent_provider: null, + created_at: now, + }); + ag = getAgentGroupByFolder(folder)!; + console.log(`Created agent group: ${ag.id} (${folder})`); + } else { + console.log(`Reusing agent group: ${ag.id} (${folder})`); + } + initGroupFilesystem(ag, { + instructions: + `# ${args.agentName}\n\n` + + `You are ${args.agentName}, a personal NanoClaw agent for ${args.displayName}. ` + + 'When the user first reaches out, introduce yourself briefly and invite them to chat. Keep replies concise.', + }); + + // 3. CLI messaging group + wiring. + let cliMg: MessagingGroup | undefined = getMessagingGroupByPlatform(CLI_CHANNEL, CLI_PLATFORM_ID); + if (!cliMg) { + cliMg = { + id: generateId('mg'), + channel_type: CLI_CHANNEL, + platform_id: CLI_PLATFORM_ID, + name: 'Local CLI', + is_group: 0, + unknown_sender_policy: 'public', + created_at: now, + }; + createMessagingGroup(cliMg); + console.log(`Created CLI messaging group: ${cliMg.id}`); + } + + const existing = getMessagingGroupAgentByPair(cliMg.id, ag.id); + if (!existing) { + createMessagingGroupAgent({ + id: generateId('mga'), + messaging_group_id: cliMg.id, + agent_group_id: ag.id, + engage_mode: 'pattern', + engage_pattern: '.', + sender_scope: 'all', + ignored_message_policy: 'drop', + session_mode: 'shared', + priority: 0, + created_at: now, + }); + console.log(`Wired cli: ${cliMg.id} -> ${ag.id}`); + } else { + console.log(`Wiring already exists: ${existing.id}`); + } + + console.log(''); + console.log('Init complete.'); + console.log( + ` owner: ${CLI_SYNTHETIC_USER_ID}${promotedToOwner ? ' (promoted on first owner)' : ''}`, + ); + console.log(` agent: ${ag.name} [${ag.id}] @ groups/${folder}`); + console.log(` channel: cli/${CLI_PLATFORM_ID}`); + console.log(''); + console.log('Run `pnpm run chat hi` to talk to your agent.'); +} + +main().catch((err) => { + console.error(err); + process.exit(1); +}); diff --git a/scripts/init-first-agent.ts b/scripts/init-first-agent.ts index 846877882..29ca6d444 100644 --- a/scripts/init-first-agent.ts +++ b/scripts/init-first-agent.ts @@ -1,43 +1,39 @@ /** - * Init the first (or Nth) NanoClaw v2 agent. + * Init the first (or Nth) NanoClaw v2 agent for a DM channel. * - * Two modes: + * Wires a real DM channel (discord, telegram, etc.) to a new agent group + * (and the local CLI channel as a convenience bonus), then hands a welcome + * message to the running service via its CLI socket. The service routes + * that message into the DM session, which wakes the container synchronously — + * the agent processes the welcome and DMs the operator through the normal + * delivery path. * - * 1. **DM channel mode** (default): wires a real DM channel (discord, telegram, - * etc.) + the CLI channel to the same agent, stages a welcome into the DM - * session so the agent greets the operator over that channel. - * - * 2. **CLI-only mode** (`--cli-only`): wires only the CLI channel. Used by - * `/new-setup` to get to a working 2-way CLI chat with the bare minimum. - * Owner grant uses a synthetic `cli:local` user so admin-gated flows work. + * For the CLI-only scratch agent used during `/new-setup`, see + * `scripts/init-cli-agent.ts` — that's a distinct flow and doesn't run + * through here. * * Creates/reuses: user, owner grant (if none), agent group + filesystem, - * messaging group(s), wiring, session. Stages a system welcome message so - * the host sweep wakes the container and the agent sends the greeting via - * the normal delivery path. + * messaging group(s), wiring. * - * Runs alongside the service (WAL-mode sqlite) — does NOT initialize - * channel adapters, so there's no Gateway conflict. + * Runs alongside the service (WAL-mode sqlite + CLI socket IPC) — does NOT + * initialize channel adapters, so there's no Gateway conflict. Requires + * the service to be running: the welcome hand-off goes over the CLI socket + * and fails loudly if the service isn't up. * * Usage: - * # DM mode * pnpm exec tsx scripts/init-first-agent.ts \ * --channel discord \ * --user-id discord:1470183333427675709 \ * --platform-id discord:@me:1491573333382523708 \ * --display-name "Gavriel" \ * [--agent-name "Andy"] \ - * [--welcome "System instruction: ..."] - * - * # CLI-only mode - * pnpm exec tsx scripts/init-first-agent.ts --cli-only \ - * --display-name "Gavriel" \ - * [--agent-name "Andy"] \ - * [--welcome "System instruction: ..."] + * [--welcome "System instruction: ..."] \ + * [--no-cli-bonus] * * For direct-addressable channels (telegram, whatsapp, etc.), --platform-id * is typically the same as the handle in --user-id, with the channel prefix. */ +import net from 'net'; import path from 'path'; import { DATA_DIR } from '../src/config.js'; @@ -54,11 +50,9 @@ import { normalizeName } from '../src/modules/agent-to-agent/db/agent-destinatio import { grantRole, hasAnyOwner } from '../src/modules/permissions/db/user-roles.js'; import { upsertUser } from '../src/modules/permissions/db/users.js'; import { initGroupFilesystem } from '../src/group-init.js'; -import { resolveSession, writeSessionMessage } from '../src/session-manager.js'; import type { AgentGroup, MessagingGroup } from '../src/types.js'; interface Args { - cliOnly: boolean; noCliBonus: boolean; channel: string; userId: string; @@ -73,17 +67,13 @@ const DEFAULT_WELCOME = const CLI_CHANNEL = 'cli'; const CLI_PLATFORM_ID = 'local'; -const CLI_SYNTHETIC_USER_ID = `${CLI_CHANNEL}:${CLI_PLATFORM_ID}`; function parseArgs(argv: string[]): Args { - const out: Partial = { cliOnly: false, noCliBonus: false }; + const out: Partial = { noCliBonus: false }; for (let i = 0; i < argv.length; i++) { const key = argv[i]; const val = argv[i + 1]; switch (key) { - case '--cli-only': - out.cliOnly = true; - break; case '--no-cli-bonus': out.noCliBonus = true; break; @@ -114,42 +104,23 @@ function parseArgs(argv: string[]): Args { } } - if (!out.displayName) { - console.error('Missing required arg: --display-name'); - console.error('See scripts/init-first-agent.ts header for usage.'); - process.exit(2); - } - - if (out.cliOnly) { - // CLI-only: channel/user/platform default to the synthetic local CLI identity. - return { - cliOnly: true, - noCliBonus: out.noCliBonus ?? false, - channel: CLI_CHANNEL, - userId: CLI_SYNTHETIC_USER_ID, - platformId: CLI_PLATFORM_ID, - displayName: out.displayName, - agentName: out.agentName?.trim() || out.displayName, - welcome: out.welcome?.trim() || DEFAULT_WELCOME, - }; - } - - const required: (keyof Args)[] = ['channel', 'userId', 'platformId']; + const required: (keyof Args)[] = ['channel', 'userId', 'platformId', 'displayName']; const missing = required.filter((k) => !out[k]); if (missing.length) { - console.error(`Missing required args: ${missing.map((k) => `--${k.replace(/([A-Z])/g, '-$1').toLowerCase()}`).join(', ')}`); + console.error( + `Missing required args: ${missing.map((k) => `--${k.replace(/([A-Z])/g, '-$1').toLowerCase()}`).join(', ')}`, + ); console.error('See scripts/init-first-agent.ts header for usage.'); process.exit(2); } return { - cliOnly: false, noCliBonus: out.noCliBonus ?? false, channel: out.channel!, userId: out.userId!, platformId: out.platformId!, - displayName: out.displayName, - agentName: out.agentName?.trim() || out.displayName, + displayName: out.displayName!, + agentName: out.agentName?.trim() || out.displayName!, welcome: out.welcome?.trim() || DEFAULT_WELCOME, }; } @@ -217,7 +188,6 @@ async function main(): Promise { const now = new Date().toISOString(); // 1. User + (conditional) owner grant. - // In cli-only mode, the synthetic `cli:local` user becomes the first owner. const userId = namespacedUserId(args.channel, args.userId); upsertUser({ id: userId, @@ -238,10 +208,8 @@ async function main(): Promise { promotedToOwner = true; } - // 2. Agent group + filesystem - const folder = args.cliOnly - ? `cli-with-${normalizeName(args.displayName)}` - : `dm-with-${normalizeName(args.displayName)}`; + // 2. Agent group + filesystem. + const folder = `dm-with-${normalizeName(args.displayName)}`; let ag: AgentGroup | undefined = getAgentGroupByFolder(folder); if (!ag) { const agId = generateId('ag'); @@ -261,89 +229,115 @@ async function main(): Promise { instructions: `# ${args.agentName}\n\n` + `You are ${args.agentName}, a personal NanoClaw agent for ${args.displayName}. ` + - 'When you receive a system welcome prompt, introduce yourself briefly and invite them to chat. Keep replies concise.', + 'When the user first reaches out (or you receive a system welcome prompt), introduce yourself briefly and invite them to chat. Keep replies concise.', }); - // 3. Primary messaging group + wiring + welcome session. - // In DM mode: the DM messaging group is primary, CLI is wired as a bonus. - // In cli-only mode: the CLI messaging group is primary; no DM group. - const cliMg = ensureCliMessagingGroup(now); - - let primaryMg: MessagingGroup; - if (args.cliOnly) { - primaryMg = cliMg; + // 3. DM messaging group. + const platformId = namespacedPlatformId(args.channel, args.platformId); + let dmMg = getMessagingGroupByPlatform(args.channel, platformId); + if (!dmMg) { + const mgId = generateId('mg'); + createMessagingGroup({ + id: mgId, + channel_type: args.channel, + platform_id: platformId, + name: args.displayName, + is_group: 0, + unknown_sender_policy: 'strict', + created_at: now, + }); + dmMg = getMessagingGroupByPlatform(args.channel, platformId)!; + console.log(`Created messaging group: ${dmMg.id} (${platformId})`); } else { - const platformId = namespacedPlatformId(args.channel, args.platformId); - let dmMg = getMessagingGroupByPlatform(args.channel, platformId); - if (!dmMg) { - const mgId = generateId('mg'); - createMessagingGroup({ - id: mgId, - channel_type: args.channel, - platform_id: platformId, - name: args.displayName, - is_group: 0, - unknown_sender_policy: 'strict', - created_at: now, - }); - dmMg = getMessagingGroupByPlatform(args.channel, platformId)!; - console.log(`Created messaging group: ${dmMg.id} (${platformId})`); - } else { - console.log(`Reusing messaging group: ${dmMg.id} (${platformId})`); - } - primaryMg = dmMg; + console.log(`Reusing messaging group: ${dmMg.id} (${platformId})`); } - // Wire primary (DM or CLI), auto-creates companion agent_destinations row. - wireIfMissing(primaryMg, ag, now, args.cliOnly ? 'cli' : 'dm'); - - // In DM mode also wire CLI so `pnpm run chat` works immediately. - // Skip the bonus when --no-cli-bonus is set — used by /new-setup-2 so the - // throwaway CLI-only agent from /new-setup still owns CLI routing cleanly. - if (!args.cliOnly && !args.noCliBonus) { + // 4. Wire DM (auto-creates companion agent_destinations row) and, + // unless suppressed, also wire the CLI channel so `pnpm run chat` works + // against the new agent immediately. `/new-setup-2` sets --no-cli-bonus + // so the scratch CLI agent from `/new-setup` keeps owning CLI routing. + wireIfMissing(dmMg, ag, now, 'dm'); + if (!args.noCliBonus) { + const cliMg = ensureCliMessagingGroup(now); wireIfMissing(cliMg, ag, now, 'cli-bonus'); } - // 4. Session + staged welcome (on the primary messaging group) - const { session, created } = resolveSession(ag.id, primaryMg.id, null, 'shared'); - console.log(`${created ? 'Created' : 'Reusing'} session: ${session.id}`); - - writeSessionMessage(ag.id, session.id, { - id: generateId('sys-welcome'), - kind: 'chat', - timestamp: now, - platformId: primaryMg.platform_id, - channelType: primaryMg.channel_type, - threadId: null, - content: JSON.stringify({ - text: args.welcome, - sender: 'system', - senderId: 'system', - }), - }); + // 5. Welcome delivery over the CLI socket. Router picks up the line, + // writes the message into the DM session's inbound.db, and wakes the + // container synchronously — no sweep wait. + await sendWelcomeViaCliSocket(dmMg, args.welcome); console.log(''); console.log('Init complete.'); console.log(` owner: ${userId}${promotedToOwner ? ' (promoted on first owner)' : ''}`); console.log(` agent: ${ag.name} [${ag.id}] @ groups/${folder}`); - if (args.cliOnly) { - console.log(` channel: cli/${CLI_PLATFORM_ID}`); - } else { - console.log(` channel: ${args.channel} ${primaryMg.platform_id}`); - if (!args.noCliBonus) { - console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``); - } + console.log(` channel: ${args.channel} ${dmMg.platform_id}`); + if (!args.noCliBonus) { + console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``); } - console.log(` session: ${session.id}`); console.log(''); - console.log( - args.cliOnly - ? 'Host sweep (<=60s) will wake the container. Try `pnpm run chat hi`.' - : 'Host sweep (<=60s) will wake the container and the agent will send the welcome DM.', - ); + console.log('Welcome DM queued — the agent will greet you shortly.'); +} + +/** + * Hand the welcome to the running service via its CLI Unix socket. The + * service's CLI adapter receives `{text, to}`, builds an InboundEvent + * targeting the DM messaging group, and calls routeInbound(). Router writes + * the message into inbound.db and wakes the container synchronously. + * + * Throws if the socket isn't reachable — this script requires the service + * to be running. + */ +async function sendWelcomeViaCliSocket(dmMg: MessagingGroup, welcome: string): Promise { + const sockPath = path.join(DATA_DIR, 'cli.sock'); + + await new Promise((resolve, reject) => { + const socket = net.connect(sockPath); + let settled = false; + + const settle = (err: Error | null) => { + if (settled) return; + settled = true; + try { + socket.end(); + } catch { + /* noop */ + } + if (err) reject(err); + else resolve(); + }; + + socket.once('error', (err) => + settle( + new Error( + `CLI socket at ${sockPath} not reachable: ${err.message}. Is the NanoClaw service running?`, + ), + ), + ); + socket.once('connect', () => { + const payload = + JSON.stringify({ + text: welcome, + to: { + channelType: dmMg.channel_type, + platformId: dmMg.platform_id, + threadId: null, + }, + }) + '\n'; + socket.write(payload, (err) => { + if (err) { + settle(err); + return; + } + // Brief flush delay so the router picks up the line before we close. + // Router handles it synchronously once read, so 50ms is plenty. + setTimeout(() => settle(null), 50); + }); + }); + }); } main().catch((err) => { - console.error(err); + console.error(err instanceof Error ? err.message : err); process.exit(1); }); diff --git a/setup/cli-agent.ts b/setup/cli-agent.ts index e5a901dda..d9a90c576 100644 --- a/setup/cli-agent.ts +++ b/setup/cli-agent.ts @@ -1,14 +1,13 @@ /** - * Step: cli-agent — Create the first agent wired to the CLI channel. + * Step: cli-agent — Create the scratch CLI agent for `/new-setup`. * - * Thin wrapper around `scripts/init-first-agent.ts --cli-only`. Emits a - * status block so /new-setup SKILL.md can parse the result without having - * to read the script's plain stdout. + * Thin wrapper around `scripts/init-cli-agent.ts`. Emits a status block so + * /new-setup SKILL.md can parse the result without having to read the + * script's plain stdout. * * Args: * --display-name (required) operator's display name * --agent-name (optional) agent persona name, defaults to display-name - * --welcome (optional) system welcome instruction */ import { execFileSync } from 'child_process'; import path from 'path'; @@ -19,11 +18,9 @@ import { emitStatus } from './status.js'; function parseArgs(args: string[]): { displayName: string; agentName?: string; - welcome?: string; } { let displayName: string | undefined; let agentName: string | undefined; - let welcome: string | undefined; for (let i = 0; i < args.length; i++) { const key = args[i]; @@ -37,10 +34,6 @@ function parseArgs(args: string[]): { agentName = val; i++; break; - case '--welcome': - welcome = val; - i++; - break; } } @@ -53,20 +46,19 @@ function parseArgs(args: string[]): { process.exit(2); } - return { displayName, agentName, welcome }; + return { displayName, agentName }; } export async function run(args: string[]): Promise { - const { displayName, agentName, welcome } = parseArgs(args); + const { displayName, agentName } = parseArgs(args); const projectRoot = process.cwd(); - const script = path.join(projectRoot, 'scripts', 'init-first-agent.ts'); + const script = path.join(projectRoot, 'scripts', 'init-cli-agent.ts'); - const scriptArgs = ['exec', 'tsx', script, '--cli-only', '--display-name', displayName]; + const scriptArgs = ['exec', 'tsx', script, '--display-name', displayName]; if (agentName) scriptArgs.push('--agent-name', agentName); - if (welcome) scriptArgs.push('--welcome', welcome); - log.info('Invoking init-first-agent in cli-only mode', { displayName, agentName }); + log.info('Invoking init-cli-agent', { displayName, agentName }); try { execFileSync('pnpm', scriptArgs, { @@ -76,7 +68,7 @@ export async function run(args: string[]): Promise { }); } catch (err) { const e = err as { stdout?: string; stderr?: string; status?: number }; - log.error('init-first-agent failed', { + log.error('init-cli-agent failed', { status: e.status, stdout: e.stdout, stderr: e.stderr, diff --git a/src/channels/adapter.ts b/src/channels/adapter.ts index 9343258bd..d8d8f9d7b 100644 --- a/src/channels/adapter.ts +++ b/src/channels/adapter.ts @@ -10,6 +10,14 @@ export interface ChannelSetup { /** Called when an inbound message arrives from the platform. */ onInbound(platformId: string, threadId: string | null, message: InboundMessage): void | Promise; + /** + * Called by admin-transport adapters (CLI) that want to route a message to + * an arbitrary channel/platform and optionally redirect replies elsewhere. + * Regular chat adapters should use `onInbound`; `onInboundEvent` skips the + * adapter-channel-type injection so the caller can target any wired mg. + */ + onInboundEvent(event: InboundEvent): void | Promise; + /** Called when the adapter discovers metadata about a conversation. */ onMetadata(platformId: string, name?: string, isGroup?: boolean): void; @@ -17,6 +25,41 @@ export interface ChannelSetup { onAction(questionId: string, selectedOption: string, userId: string): void; } +/** Delivery address used for reply-to overrides and (normally) the inbound's own origin. */ +export interface DeliveryAddress { + channelType: string; + platformId: string; + threadId: string | null; +} + +/** + * Full inbound event handed to the router. + * + * `channelType` + `platformId` + `threadId` identify which messaging group / + * session receives the message. `replyTo`, when set, overrides where the + * agent's reply is delivered — used by the CLI admin transport when the + * operator wants a message routed to one channel but replies echoed back to + * their terminal. Agents cannot set `replyTo`; it is a router-layer concept + * set only by external adapters carrying operator intent. + */ +export interface InboundEvent { + channelType: string; + platformId: string; + threadId: string | null; + message: { + id: string; + kind: 'chat' | 'chat-sdk'; + content: string; // JSON blob + timestamp: string; + /** + * Platform-confirmed bot-mention signal forwarded from the adapter. + * See InboundMessage.isMention for the full explanation. + */ + isMention?: boolean; + }; + replyTo?: DeliveryAddress; +} + /** Inbound message from adapter to host. */ export interface InboundMessage { id: string; diff --git a/src/channels/channel-registry.test.ts b/src/channels/channel-registry.test.ts index 5121c6497..27ee6608b 100644 --- a/src/channels/channel-registry.test.ts +++ b/src/channels/channel-registry.test.ts @@ -105,6 +105,7 @@ describe('channel registry', () => { await initChannelAdapters(() => ({ conversations: [], onInbound: () => {}, + onInboundEvent: () => {}, onMetadata: () => {}, onAction: () => {}, })); @@ -208,6 +209,7 @@ describe('channel + router integration', () => { await initChannelAdapters(() => ({ conversations: [], onInbound: () => {}, + onInboundEvent: () => {}, onMetadata: () => {}, onAction: () => {}, })); diff --git a/src/channels/cli.ts b/src/channels/cli.ts index c84952cdd..ad5e7e39d 100644 --- a/src/channels/cli.ts +++ b/src/channels/cli.ts @@ -7,19 +7,31 @@ * the normal router/delivery path like any other adapter — `/clear` and * other session-level commands work identically. * - * MVP shape: - * - One hardcoded messaging_group: `cli/local`. Wired to one agent via - * the setup flow (see `scripts/init-first-agent.ts`). Multi-agent - * support can add per-agent messaging_groups later without breaking - * the wire protocol. - * - Single connected client at a time. A second connection closes the - * first with a "superseded" notice. - * - Wire format: one JSON object per line. - * Client → server: { "text": "user message" } - * Server → client: { "text": "agent reply" } - * - deliver() silently no-ops when no client is connected. The outbound - * row is already in outbound.db, so the message isn't lost — it just - * doesn't reach this run's terminal. Reconnect to see subsequent replies. + * Wire format: one JSON object per line. + * + * Client → server: + * { "text": "user message" } # default — talk to cli/local + * { "text": "...", "to": {"channelType": "discord", + * "platformId": "discord:@me:149...", + * "threadId": null} } # route to a specific mg + * { "text": "...", "to": {...}, "reply_to": {...} } # + redirect replies + * Server → client: + * { "text": "agent reply" } + * + * The `to` and `reply_to` addressing is how admin transports (the bootstrap + * script) inject messages targeting any wired channel. `reply_to` is a + * router-layer concept — agents cannot set it; it is carried only on + * inbound events from CLI clients that hold operator privilege (the socket + * is chmod 0600, so "connected to this socket" ≈ "is the owner"). + * + * Single-client chat semantics: one connected terminal at a time. A second + * "chat" connection closes the first with a "superseded" notice. Admin + * route-opcode connections (`to` set) are one-shot and do NOT evict an + * active chat client. + * + * deliver() silently no-ops when no client is connected. The outbound row + * is already in outbound.db, so the message isn't lost — it just doesn't + * reach this run's terminal. Reconnect to see subsequent replies. */ import fs from 'fs'; import net from 'net'; @@ -30,7 +42,8 @@ import { log } from '../log.js'; import type { ChannelAdapter, ChannelSetup, - InboundMessage, + DeliveryAddress, + InboundEvent, OutboundMessage, } from './adapter.js'; import { registerChannelAdapter } from './channel-registry.js'; @@ -129,16 +142,25 @@ function createAdapter(): ChannelAdapter { }; function handleConnection(socket: net.Socket, config: ChannelSetup): void { - if (client) { - try { - client.write(JSON.stringify({ text: '[superseded by a newer client]' }) + '\n'); - client.end(); - } catch { - // swallow + // Defer the chat-slot swap until we see the first line — if it turns out + // to be a routed (`to`-bearing) one-shot, we leave the existing chat + // client in place. Only plain chat connections participate in supersede. + let claimedChatSlot = false; + + const claimChatSlot = () => { + if (claimedChatSlot) return; + claimedChatSlot = true; + if (client && client !== socket) { + try { + client.write(JSON.stringify({ text: '[superseded by a newer client]' }) + '\n'); + client.end(); + } catch { + // swallow + } } - } - client = socket; - log.info('CLI client connected'); + client = socket; + log.info('CLI client connected'); + }; let buffer = ''; socket.on('data', (chunk) => { @@ -148,13 +170,13 @@ function createAdapter(): ChannelAdapter { const line = buffer.slice(0, idx).trim(); buffer = buffer.slice(idx + 1); if (!line) continue; - void handleLine(line, config); + void handleLine(line, config, claimChatSlot); } }); socket.on('close', () => { if (client === socket) client = null; - log.info('CLI client disconnected'); + if (claimedChatSlot) log.info('CLI client disconnected'); }); socket.on('error', (err) => { @@ -162,8 +184,16 @@ function createAdapter(): ChannelAdapter { }); } - async function handleLine(line: string, config: ChannelSetup): Promise { - let payload: { text?: unknown }; + async function handleLine( + line: string, + config: ChannelSetup, + claimChatSlot: () => void, + ): Promise { + let payload: { + text?: unknown; + to?: unknown; + reply_to?: unknown; + }; try { payload = JSON.parse(line); } catch (err) { @@ -172,23 +202,73 @@ function createAdapter(): ChannelAdapter { } if (typeof payload.text !== 'string' || payload.text.length === 0) return; - const inbound: InboundMessage = { - id: `cli-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`, - kind: 'chat', - timestamp: new Date().toISOString(), - content: { - text: payload.text, - sender: 'cli', - senderId: `cli:${PLATFORM_ID}`, - }, - }; + const to = parseAddress(payload.to); + const replyTo = parseAddress(payload.reply_to); + + if (to) { + // Routed message — admin transport. Build a full InboundEvent targeting + // `to`'s channel/platform, and let `reply_to` (if any) redirect replies. + // Does NOT claim the chat slot, so an active terminal chat isn't evicted. + const event: InboundEvent = { + channelType: to.channelType, + platformId: to.platformId, + threadId: to.threadId, + message: { + id: `cli-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`, + kind: 'chat', + timestamp: new Date().toISOString(), + content: JSON.stringify({ + text: payload.text, + sender: 'cli', + senderId: `cli:${PLATFORM_ID}`, + }), + }, + replyTo: replyTo ?? undefined, + }; + try { + await config.onInboundEvent(event); + } catch (err) { + log.error('CLI: onInboundEvent threw', { err }); + } + return; + } + + // Plain chat — claim the slot (evicting any prior client) and route via + // the standard onInbound path (adapter injects its own channelType). + claimChatSlot(); try { - await config.onInbound(PLATFORM_ID, null, inbound); + await config.onInbound(PLATFORM_ID, null, { + id: `cli-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`, + kind: 'chat', + timestamp: new Date().toISOString(), + content: { + text: payload.text, + sender: 'cli', + senderId: `cli:${PLATFORM_ID}`, + }, + }); } catch (err) { log.error('CLI: onInbound threw', { err }); } } + function parseAddress(raw: unknown): DeliveryAddress | null { + if (!raw || typeof raw !== 'object') return null; + const obj = raw as Record; + if (typeof obj.channelType !== 'string' || typeof obj.platformId !== 'string') return null; + const threadId = + obj.threadId === null || obj.threadId === undefined + ? null + : typeof obj.threadId === 'string' + ? obj.threadId + : null; + return { + channelType: obj.channelType, + platformId: obj.platformId, + threadId, + }; + } + return adapter; } diff --git a/src/host-core.test.ts b/src/host-core.test.ts index da2fd37d2..9906c4b83 100644 --- a/src/host-core.test.ts +++ b/src/host-core.test.ts @@ -25,7 +25,7 @@ import { outboundDbPath, } from './session-manager.js'; import { getSession, findSession } from './db/sessions.js'; -import type { InboundEvent } from './router.js'; +import type { InboundEvent } from './channels/adapter.js'; // Mock container runner to prevent actual Docker spawning vi.mock('./container-runner.js', () => ({ diff --git a/src/index.ts b/src/index.ts index 7c5ab240c..1ec8619df 100644 --- a/src/index.ts +++ b/src/index.ts @@ -86,6 +86,15 @@ async function main(): Promise { log.error('Failed to route inbound message', { channelType: adapter.channelType, err }); }); }, + onInboundEvent(event) { + routeInbound(event).catch((err) => { + log.error('Failed to route inbound event', { + sourceAdapter: adapter.channelType, + targetChannelType: event.channelType, + err, + }); + }); + }, onMetadata(platformId, name, isGroup) { log.info('Channel metadata discovered', { channelType: adapter.channelType, diff --git a/src/modules/approvals/picks.test.ts b/src/modules/approvals/picks.test.ts index 508aa3543..c48f58dda 100644 --- a/src/modules/approvals/picks.test.ts +++ b/src/modules/approvals/picks.test.ts @@ -57,6 +57,7 @@ async function mountMockAdapter( await initChannelAdapters(() => ({ conversations: [], onInbound: () => {}, + onInboundEvent: () => {}, onMetadata: () => {}, onAction: () => {}, })); diff --git a/src/modules/permissions/channel-approval.ts b/src/modules/permissions/channel-approval.ts index 9c65f8e3a..caef81563 100644 --- a/src/modules/permissions/channel-approval.ts +++ b/src/modules/permissions/channel-approval.ts @@ -41,7 +41,7 @@ import { getAllAgentGroups } from '../../db/agent-groups.js'; import { getMessagingGroup } from '../../db/messaging-groups.js'; import { getDeliveryAdapter } from '../../delivery.js'; import { log } from '../../log.js'; -import type { InboundEvent } from '../../router.js'; +import type { InboundEvent } from '../../channels/adapter.js'; import { pickApprovalDelivery, pickApprover } from '../approvals/primitive.js'; import { createPendingChannelApproval, hasInFlightChannelApproval } from './db/pending-channel-approvals.js'; diff --git a/src/modules/permissions/index.ts b/src/modules/permissions/index.ts index e2f100c83..6913c72bb 100644 --- a/src/modules/permissions/index.ts +++ b/src/modules/permissions/index.ts @@ -27,8 +27,8 @@ import { setSenderResolver, setSenderScopeGate, type AccessGateResult, - type InboundEvent, } from '../../router.js'; +import type { InboundEvent } from '../../channels/adapter.js'; import { registerResponseHandler, type ResponsePayload } from '../../response-registry.js'; import { log } from '../../log.js'; import type { MessagingGroup, MessagingGroupAgent } from '../../types.js'; diff --git a/src/modules/permissions/permissions.test.ts b/src/modules/permissions/permissions.test.ts index d76d0d6d8..c66e082be 100644 --- a/src/modules/permissions/permissions.test.ts +++ b/src/modules/permissions/permissions.test.ts @@ -60,6 +60,7 @@ async function mountMockAdapter( await initChannelAdapters(() => ({ conversations: [], onInbound: () => {}, + onInboundEvent: () => {}, onMetadata: () => {}, onAction: () => {}, })); diff --git a/src/modules/permissions/sender-approval.ts b/src/modules/permissions/sender-approval.ts index be6028041..e08123ac1 100644 --- a/src/modules/permissions/sender-approval.ts +++ b/src/modules/permissions/sender-approval.ts @@ -30,7 +30,7 @@ import { normalizeOptions, type RawOption } from '../../channels/ask-question.js import { getMessagingGroup } from '../../db/messaging-groups.js'; import { getDeliveryAdapter } from '../../delivery.js'; import { log } from '../../log.js'; -import type { InboundEvent } from '../../router.js'; +import type { InboundEvent } from '../../channels/adapter.js'; import { pickApprovalDelivery, pickApprover } from '../approvals/primitive.js'; import { createPendingSenderApproval, hasInFlightSenderApproval } from './db/pending-sender-approvals.js'; diff --git a/src/router.ts b/src/router.ts index 4289f1fe9..c1e888126 100644 --- a/src/router.ts +++ b/src/router.ts @@ -32,32 +32,12 @@ import { resolveSession, writeSessionMessage } from './session-manager.js'; import { wakeContainer } from './container-runner.js'; import { getSession } from './db/sessions.js'; import type { AgentGroup, MessagingGroup, MessagingGroupAgent } from './types.js'; +import type { InboundEvent } from './channels/adapter.js'; function generateId(): string { return `msg-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; } -export interface InboundEvent { - channelType: string; - platformId: string; - threadId: string | null; - message: { - id: string; - kind: 'chat' | 'chat-sdk'; - content: string; // JSON blob - timestamp: string; - /** - * Platform-confirmed bot-mention signal forwarded from the adapter. - * When defined, it's authoritative — use this instead of text-matching - * agent_group_name, which breaks on platforms where the mention token - * is the bot's platform username (e.g. Telegram). undefined means the - * adapter doesn't provide the signal; evaluateEngage falls back to - * agent-name regex. - */ - isMention?: boolean; - }; -} - /** * Sender-resolver hook. Runs before agent resolution. * @@ -408,13 +388,23 @@ async function deliverToAgent( const { session, created } = resolveSession(agent.agent_group_id, mg.id, event.threadId, effectiveSessionMode); + // The inbound row's (channel_type, platform_id, thread_id) is the address + // the agent's reply will be delivered to. Normally it mirrors the source + // (stamped from the event). When the caller supplied `replyTo` (CLI admin + // transport acting on operator intent), the reply is redirected there. + const deliveryAddr = event.replyTo ?? { + channelType: event.channelType, + platformId: event.platformId, + threadId: event.threadId, + }; + writeSessionMessage(session.agent_group_id, session.id, { id: messageIdForAgent(event.message.id, agent.agent_group_id), kind: event.message.kind, timestamp: event.message.timestamp, - platformId: event.platformId, - channelType: event.channelType, - threadId: event.threadId, + platformId: deliveryAddr.platformId, + channelType: deliveryAddr.channelType, + threadId: deliveryAddr.threadId, content: event.message.content, trigger: wake ? 1 : 0, }); From 0f6a1ba1ed45da96b76cf7cb75517d966ecf7e39 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Mon, 20 Apr 2026 23:31:42 +0300 Subject: [PATCH 52/95] style: apply prettier formatting to touched files Pre-commit hook reflowed imports on files changed in the previous commit. Unrelated format drift on other files intentionally left unstaged. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/channels/cli.ts | 18 ++++-------------- src/modules/approvals/picks.test.ts | 6 +++++- src/modules/permissions/index.ts | 10 ++-------- src/modules/permissions/permissions.test.ts | 6 +++++- 4 files changed, 16 insertions(+), 24 deletions(-) diff --git a/src/channels/cli.ts b/src/channels/cli.ts index ad5e7e39d..b73818673 100644 --- a/src/channels/cli.ts +++ b/src/channels/cli.ts @@ -39,13 +39,7 @@ import path from 'path'; import { DATA_DIR } from '../config.js'; import { log } from '../log.js'; -import type { - ChannelAdapter, - ChannelSetup, - DeliveryAddress, - InboundEvent, - OutboundMessage, -} from './adapter.js'; +import type { ChannelAdapter, ChannelSetup, DeliveryAddress, InboundEvent, OutboundMessage } from './adapter.js'; import { registerChannelAdapter } from './channel-registry.js'; const PLATFORM_ID = 'local'; @@ -184,11 +178,7 @@ function createAdapter(): ChannelAdapter { }); } - async function handleLine( - line: string, - config: ChannelSetup, - claimChatSlot: () => void, - ): Promise { + async function handleLine(line: string, config: ChannelSetup, claimChatSlot: () => void): Promise { let payload: { text?: unknown; to?: unknown; @@ -260,8 +250,8 @@ function createAdapter(): ChannelAdapter { obj.threadId === null || obj.threadId === undefined ? null : typeof obj.threadId === 'string' - ? obj.threadId - : null; + ? obj.threadId + : null; return { channelType: obj.channelType, platformId: obj.platformId, diff --git a/src/modules/approvals/picks.test.ts b/src/modules/approvals/picks.test.ts index c48f58dda..0d1784aca 100644 --- a/src/modules/approvals/picks.test.ts +++ b/src/modules/approvals/picks.test.ts @@ -6,7 +6,11 @@ import { beforeEach, afterEach, describe, expect, it } from 'vitest'; import type { ChannelAdapter, OutboundMessage } from '../../channels/adapter.js'; -import { initChannelAdapters, registerChannelAdapter, teardownChannelAdapters } from '../../channels/channel-registry.js'; +import { + initChannelAdapters, + registerChannelAdapter, + teardownChannelAdapters, +} from '../../channels/channel-registry.js'; import { closeDb, createAgentGroup, initTestDb, runMigrations } from '../../db/index.js'; import { createUser } from '../permissions/db/users.js'; import { grantRole } from '../permissions/db/user-roles.js'; diff --git a/src/modules/permissions/index.ts b/src/modules/permissions/index.ts index 6913c72bb..83390d837 100644 --- a/src/modules/permissions/index.ts +++ b/src/modules/permissions/index.ts @@ -16,10 +16,7 @@ * access gate is not registered and core defaults to allow-all. */ import { recordDroppedMessage } from '../../db/dropped-messages.js'; -import { - createMessagingGroupAgent, - setMessagingGroupDeniedAt, -} from '../../db/messaging-groups.js'; +import { createMessagingGroupAgent, setMessagingGroupDeniedAt } from '../../db/messaging-groups.js'; import { routeInbound, setAccessGate, @@ -35,10 +32,7 @@ import type { MessagingGroup, MessagingGroupAgent } from '../../types.js'; import { canAccessAgentGroup } from './access.js'; import { requestChannelApproval } from './channel-approval.js'; import { addMember } from './db/agent-group-members.js'; -import { - deletePendingChannelApproval, - getPendingChannelApproval, -} from './db/pending-channel-approvals.js'; +import { deletePendingChannelApproval, getPendingChannelApproval } from './db/pending-channel-approvals.js'; import { deletePendingSenderApproval, getPendingSenderApproval } from './db/pending-sender-approvals.js'; import { hasAdminPrivilege } from './db/user-roles.js'; import { getUser, upsertUser } from './db/users.js'; diff --git a/src/modules/permissions/permissions.test.ts b/src/modules/permissions/permissions.test.ts index c66e082be..505c92686 100644 --- a/src/modules/permissions/permissions.test.ts +++ b/src/modules/permissions/permissions.test.ts @@ -6,7 +6,11 @@ import { beforeEach, afterEach, describe, expect, it } from 'vitest'; import type { ChannelAdapter, OutboundMessage } from '../../channels/adapter.js'; -import { initChannelAdapters, registerChannelAdapter, teardownChannelAdapters } from '../../channels/channel-registry.js'; +import { + initChannelAdapters, + registerChannelAdapter, + teardownChannelAdapters, +} from '../../channels/channel-registry.js'; import { closeDb, createAgentGroup, createMessagingGroup, initTestDb, runMigrations } from '../../db/index.js'; import { canAccessAgentGroup } from './access.js'; import { addMember, isMember } from './db/agent-group-members.js'; From 63b8beb0fb4a51a329971ebdbb260fc00ba7ce56 Mon Sep 17 00:00:00 2001 From: Simeon Simeonov Date: Mon, 20 Apr 2026 23:28:35 -0400 Subject: [PATCH 53/95] fix(container): bump Claude Code to 2.1.116 and Agent SDK to ^0.2.116 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Agent SDK's IPC protocol must match the Claude Code version. Also allowlist @anthropic-ai/claude-code in only-built-dependencies so its postinstall script runs during Docker build — without this, the native binary is never installed and the SDK fails at spawn time. Co-Authored-By: Claude Opus 4.6 (1M context) --- container/Dockerfile | 3 +- container/agent-runner/bun.lock | 52 ++++++++++------------------- container/agent-runner/package.json | 2 +- 3 files changed, 21 insertions(+), 36 deletions(-) diff --git a/container/Dockerfile b/container/Dockerfile index 12d2bf6f4..be3763820 100644 --- a/container/Dockerfile +++ b/container/Dockerfile @@ -15,7 +15,7 @@ ARG INSTALL_CJK_FONTS=false # Pin CLI versions for reproducibility. Bump deliberately — unpinned installs # mean every rebuild silently picks up the latest and can break in lockstep # across all users. -ARG CLAUDE_CODE_VERSION=2.1.112 +ARG CLAUDE_CODE_VERSION=2.1.116 ARG AGENT_BROWSER_VERSION=latest ARG VERCEL_VERSION=latest ARG BUN_VERSION=1.3.12 @@ -76,6 +76,7 @@ RUN corepack enable # package. Pinned versions so every rebuild is reproducible. RUN --mount=type=cache,target=/root/.cache/pnpm \ echo "only-built-dependencies[]=agent-browser" > /root/.npmrc && \ + echo "only-built-dependencies[]=@anthropic-ai/claude-code" >> /root/.npmrc && \ pnpm install -g \ "@anthropic-ai/claude-code@${CLAUDE_CODE_VERSION}" \ "agent-browser@${AGENT_BROWSER_VERSION}" \ diff --git a/container/agent-runner/bun.lock b/container/agent-runner/bun.lock index 99fe8406e..3c0882853 100644 --- a/container/agent-runner/bun.lock +++ b/container/agent-runner/bun.lock @@ -5,7 +5,7 @@ "": { "name": "nanoclaw-agent-runner", "dependencies": { - "@anthropic-ai/claude-agent-sdk": "^0.2.92", + "@anthropic-ai/claude-agent-sdk": "^0.2.116", "@modelcontextprotocol/sdk": "^1.12.1", "cron-parser": "^5.0.0", "zod": "^4.0.0", @@ -18,7 +18,23 @@ }, }, "packages": { - "@anthropic-ai/claude-agent-sdk": ["@anthropic-ai/claude-agent-sdk@0.2.112", "", { "dependencies": { "@anthropic-ai/sdk": "^0.81.0", "@modelcontextprotocol/sdk": "^1.29.0" }, "optionalDependencies": { "@img/sharp-darwin-arm64": "^0.34.2", "@img/sharp-darwin-x64": "^0.34.2", "@img/sharp-linux-arm": "^0.34.2", "@img/sharp-linux-arm64": "^0.34.2", "@img/sharp-linux-x64": "^0.34.2", "@img/sharp-linuxmusl-arm64": "^0.34.2", "@img/sharp-linuxmusl-x64": "^0.34.2", "@img/sharp-win32-arm64": "^0.34.2", "@img/sharp-win32-x64": "^0.34.2" }, "peerDependencies": { "zod": "^4.0.0" } }, "sha512-vMFoiDKlOive8p3tphpV1gQaaytOipwGJ+uw9mvvaLQUODSC2+fCdRDAY25i2Tsv+lOtxzXBKctmaDuWqZY7ig=="], + "@anthropic-ai/claude-agent-sdk": ["@anthropic-ai/claude-agent-sdk@0.2.116", "", { "dependencies": { "@anthropic-ai/sdk": "^0.81.0", "@modelcontextprotocol/sdk": "^1.29.0" }, "optionalDependencies": { "@anthropic-ai/claude-agent-sdk-darwin-arm64": "0.2.116", "@anthropic-ai/claude-agent-sdk-darwin-x64": "0.2.116", "@anthropic-ai/claude-agent-sdk-linux-arm64": "0.2.116", "@anthropic-ai/claude-agent-sdk-linux-arm64-musl": "0.2.116", "@anthropic-ai/claude-agent-sdk-linux-x64": "0.2.116", "@anthropic-ai/claude-agent-sdk-linux-x64-musl": "0.2.116", "@anthropic-ai/claude-agent-sdk-win32-arm64": "0.2.116", "@anthropic-ai/claude-agent-sdk-win32-x64": "0.2.116" }, "peerDependencies": { "zod": "^4.0.0" } }, "sha512-5NKpgaOZkzNCGCvLxJZUVGimf5IcYmpQ2x2XrR9ilK+2UkWrnnwcUfIWo8bBz9e7lSYcUf9XleGigq2eOOF7aw=="], + + "@anthropic-ai/claude-agent-sdk-darwin-arm64": ["@anthropic-ai/claude-agent-sdk-darwin-arm64@0.2.116", "", { "os": "darwin", "cpu": "arm64" }, "sha512-mG19ovtXCpETmd5KmTU1JO2iIHZBG09IP8DmgZjLA3wLmTzpgn9Au9veRaeJeXb1EqiHiFZU+z+mNB79+w5v9g=="], + + "@anthropic-ai/claude-agent-sdk-darwin-x64": ["@anthropic-ai/claude-agent-sdk-darwin-x64@0.2.116", "", { "os": "darwin", "cpu": "x64" }, "sha512-qC25N0HRM8IXbM4Qi4svH9f51Y6DciDvjLV+oNYnxkdPgDG8p/+b7vQirN7qPxytIQb2TPdoFgUeCsSe7lrQyw=="], + + "@anthropic-ai/claude-agent-sdk-linux-arm64": ["@anthropic-ai/claude-agent-sdk-linux-arm64@0.2.116", "", { "os": "linux", "cpu": "arm64" }, "sha512-MQIcJhhPM+RPJ7kMQdOQarkJ2FlJqOiu953c08YyJOoWdHykd3DIiHws3mf1Mwl/dfFeIyshOVpNND3hyIy5Dg=="], + + "@anthropic-ai/claude-agent-sdk-linux-arm64-musl": ["@anthropic-ai/claude-agent-sdk-linux-arm64-musl@0.2.116", "", { "os": "linux", "cpu": "arm64" }, "sha512-Dg/T3NkSp35ODiwdhj0KquvC6Xu+DMbyWFNkfepA3bz4oF2SVSgyOPYwVmfoJerzEUnYDldP4YhOxRrhbt0vXA=="], + + "@anthropic-ai/claude-agent-sdk-linux-x64": ["@anthropic-ai/claude-agent-sdk-linux-x64@0.2.116", "", { "os": "linux", "cpu": "x64" }, "sha512-Bww1fzQB+vcF0tRhmCAlwSsN4wR2HgX7pBT9AWuwzJj6DKsVC23N54Ea80lsnM7dTUtUTrGYMTwVUHTWqfYnfQ=="], + + "@anthropic-ai/claude-agent-sdk-linux-x64-musl": ["@anthropic-ai/claude-agent-sdk-linux-x64-musl@0.2.116", "", { "os": "linux", "cpu": "x64" }, "sha512-LMYxUMa1nK4N9BPRJdcGBAvl9rjTI4ZHo+kfAKrJ3MlfB6VFF1tRIubwsWOaOtkuNazMdAYovsZJg4bdzOBBTQ=="], + + "@anthropic-ai/claude-agent-sdk-win32-arm64": ["@anthropic-ai/claude-agent-sdk-win32-arm64@0.2.116", "", { "os": "win32", "cpu": "arm64" }, "sha512-h0YO1vkTIeUtffQhONrYbNC1pXmk1yjb1xxMEw7bAwucqtFoFpLDWe+q4+RhxaQr8ZOj6LtRE/U3dzPWHOlshA=="], + + "@anthropic-ai/claude-agent-sdk-win32-x64": ["@anthropic-ai/claude-agent-sdk-win32-x64@0.2.116", "", { "os": "win32", "cpu": "x64" }, "sha512-3lllmtDFHgpW0ZM3iNvxsEjblrgRzF9Qm1lxTOtunP3hIn+pA/IkWMtKlN1ixxWiaBguLVQkJ90V6JHsvJJIvw=="], "@anthropic-ai/sdk": ["@anthropic-ai/sdk@0.81.0", "", { "dependencies": { "json-schema-to-ts": "^3.1.1" }, "peerDependencies": { "zod": "^3.25.0 || ^4.0.0" }, "optionalPeers": ["zod"], "bin": { "anthropic-ai-sdk": "bin/cli" } }, "sha512-D4K5PvEV6wPiRtVlVsJHIUhHAmOZ6IT/I9rKlTf84gR7GyyAurPJK7z9BOf/AZqC5d1DhYQGJNKRmV+q8dGhgw=="], @@ -26,38 +42,6 @@ "@hono/node-server": ["@hono/node-server@1.19.14", "", { "peerDependencies": { "hono": "^4" } }, "sha512-GwtvgtXxnWsucXvbQXkRgqksiH2Qed37H9xHZocE5sA3N8O8O8/8FA3uclQXxXVzc9XBZuEOMK7+r02FmSpHtw=="], - "@img/sharp-darwin-arm64": ["@img/sharp-darwin-arm64@0.34.5", "", { "optionalDependencies": { "@img/sharp-libvips-darwin-arm64": "1.2.4" }, "os": "darwin", "cpu": "arm64" }, "sha512-imtQ3WMJXbMY4fxb/Ndp6HBTNVtWCUI0WdobyheGf5+ad6xX8VIDO8u2xE4qc/fr08CKG/7dDseFtn6M6g/r3w=="], - - "@img/sharp-darwin-x64": ["@img/sharp-darwin-x64@0.34.5", "", { "optionalDependencies": { "@img/sharp-libvips-darwin-x64": "1.2.4" }, "os": "darwin", "cpu": "x64" }, "sha512-YNEFAF/4KQ/PeW0N+r+aVVsoIY0/qxxikF2SWdp+NRkmMB7y9LBZAVqQ4yhGCm/H3H270OSykqmQMKLBhBJDEw=="], - - "@img/sharp-libvips-darwin-arm64": ["@img/sharp-libvips-darwin-arm64@1.2.4", "", { "os": "darwin", "cpu": "arm64" }, "sha512-zqjjo7RatFfFoP0MkQ51jfuFZBnVE2pRiaydKJ1G/rHZvnsrHAOcQALIi9sA5co5xenQdTugCvtb1cuf78Vf4g=="], - - "@img/sharp-libvips-darwin-x64": ["@img/sharp-libvips-darwin-x64@1.2.4", "", { "os": "darwin", "cpu": "x64" }, "sha512-1IOd5xfVhlGwX+zXv2N93k0yMONvUlANylbJw1eTah8K/Jtpi15KC+WSiaX/nBmbm2HxRM1gZ0nSdjSsrZbGKg=="], - - "@img/sharp-libvips-linux-arm": ["@img/sharp-libvips-linux-arm@1.2.4", "", { "os": "linux", "cpu": "arm" }, "sha512-bFI7xcKFELdiNCVov8e44Ia4u2byA+l3XtsAj+Q8tfCwO6BQ8iDojYdvoPMqsKDkuoOo+X6HZA0s0q11ANMQ8A=="], - - "@img/sharp-libvips-linux-arm64": ["@img/sharp-libvips-linux-arm64@1.2.4", "", { "os": "linux", "cpu": "arm64" }, "sha512-excjX8DfsIcJ10x1Kzr4RcWe1edC9PquDRRPx3YVCvQv+U5p7Yin2s32ftzikXojb1PIFc/9Mt28/y+iRklkrw=="], - - "@img/sharp-libvips-linux-x64": ["@img/sharp-libvips-linux-x64@1.2.4", "", { "os": "linux", "cpu": "x64" }, "sha512-tJxiiLsmHc9Ax1bz3oaOYBURTXGIRDODBqhveVHonrHJ9/+k89qbLl0bcJns+e4t4rvaNBxaEZsFtSfAdquPrw=="], - - "@img/sharp-libvips-linuxmusl-arm64": ["@img/sharp-libvips-linuxmusl-arm64@1.2.4", "", { "os": "linux", "cpu": "arm64" }, "sha512-FVQHuwx1IIuNow9QAbYUzJ+En8KcVm9Lk5+uGUQJHaZmMECZmOlix9HnH7n1TRkXMS0pGxIJokIVB9SuqZGGXw=="], - - "@img/sharp-libvips-linuxmusl-x64": ["@img/sharp-libvips-linuxmusl-x64@1.2.4", "", { "os": "linux", "cpu": "x64" }, "sha512-+LpyBk7L44ZIXwz/VYfglaX/okxezESc6UxDSoyo2Ks6Jxc4Y7sGjpgU9s4PMgqgjj1gZCylTieNamqA1MF7Dg=="], - - "@img/sharp-linux-arm": ["@img/sharp-linux-arm@0.34.5", "", { "optionalDependencies": { "@img/sharp-libvips-linux-arm": "1.2.4" }, "os": "linux", "cpu": "arm" }, "sha512-9dLqsvwtg1uuXBGZKsxem9595+ujv0sJ6Vi8wcTANSFpwV/GONat5eCkzQo/1O6zRIkh0m/8+5BjrRr7jDUSZw=="], - - "@img/sharp-linux-arm64": ["@img/sharp-linux-arm64@0.34.5", "", { "optionalDependencies": { "@img/sharp-libvips-linux-arm64": "1.2.4" }, "os": "linux", "cpu": "arm64" }, "sha512-bKQzaJRY/bkPOXyKx5EVup7qkaojECG6NLYswgktOZjaXecSAeCWiZwwiFf3/Y+O1HrauiE3FVsGxFg8c24rZg=="], - - "@img/sharp-linux-x64": ["@img/sharp-linux-x64@0.34.5", "", { "optionalDependencies": { "@img/sharp-libvips-linux-x64": "1.2.4" }, "os": "linux", "cpu": "x64" }, "sha512-MEzd8HPKxVxVenwAa+JRPwEC7QFjoPWuS5NZnBt6B3pu7EG2Ge0id1oLHZpPJdn3OQK+BQDiw9zStiHBTJQQQQ=="], - - "@img/sharp-linuxmusl-arm64": ["@img/sharp-linuxmusl-arm64@0.34.5", "", { "optionalDependencies": { "@img/sharp-libvips-linuxmusl-arm64": "1.2.4" }, "os": "linux", "cpu": "arm64" }, "sha512-fprJR6GtRsMt6Kyfq44IsChVZeGN97gTD331weR1ex1c1rypDEABN6Tm2xa1wE6lYb5DdEnk03NZPqA7Id21yg=="], - - "@img/sharp-linuxmusl-x64": ["@img/sharp-linuxmusl-x64@0.34.5", "", { "optionalDependencies": { "@img/sharp-libvips-linuxmusl-x64": "1.2.4" }, "os": "linux", "cpu": "x64" }, "sha512-Jg8wNT1MUzIvhBFxViqrEhWDGzqymo3sV7z7ZsaWbZNDLXRJZoRGrjulp60YYtV4wfY8VIKcWidjojlLcWrd8Q=="], - - "@img/sharp-win32-arm64": ["@img/sharp-win32-arm64@0.34.5", "", { "os": "win32", "cpu": "arm64" }, "sha512-WQ3AgWCWYSb2yt+IG8mnC6Jdk9Whs7O0gxphblsLvdhSpSTtmu69ZG1Gkb6NuvxsNACwiPV6cNSZNzt0KPsw7g=="], - - "@img/sharp-win32-x64": ["@img/sharp-win32-x64@0.34.5", "", { "os": "win32", "cpu": "x64" }, "sha512-+29YMsqY2/9eFEiW93eqWnuLcWcufowXewwSNIT6UwZdUUCrM3oFjMWH/Z6/TMmb4hlFenmfAVbpWeup2jryCw=="], - "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.29.0", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.2.1", "express-rate-limit": "^8.2.1", "hono": "^4.11.4", "jose": "^6.1.3", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.1" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-zo37mZA9hJWpULgkRpowewez1y6ML5GsXJPY8FI0tBBCd77HEvza4jDqRKOXgHNn867PVGCyTdzqpz0izu5ZjQ=="], "@types/bun": ["@types/bun@1.3.12", "", { "dependencies": { "bun-types": "1.3.12" } }, "sha512-DBv81elK+/VSwXHDlnH3Qduw+KxkTIWi7TXkAeh24zpi5l0B2kUg9Ga3tb4nJaPcOFswflgi/yAvMVBPrxMB+A=="], diff --git a/container/agent-runner/package.json b/container/agent-runner/package.json index 06eb39403..e9af0b149 100644 --- a/container/agent-runner/package.json +++ b/container/agent-runner/package.json @@ -9,7 +9,7 @@ "test": "bun test" }, "dependencies": { - "@anthropic-ai/claude-agent-sdk": "^0.2.92", + "@anthropic-ai/claude-agent-sdk": "^0.2.116", "@modelcontextprotocol/sdk": "^1.12.1", "cron-parser": "^5.0.0", "zod": "^4.0.0" From f0090ebbb9670d168ed85e099994698482db91a4 Mon Sep 17 00:00:00 2001 From: Simeon Simeonov Date: Mon, 20 Apr 2026 23:28:54 -0400 Subject: [PATCH 54/95] fix(container): point SDK to pnpm-installed Claude Code binary MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Agent SDK's default binary resolution picks the musl-linked native binary (claude-agent-sdk-linux-arm64-musl), which cannot execute on the Debian-based container image (glibc). Explicitly set pathToClaudeCodeExecutable to /pnpm/claude — the pnpm global symlink that resolves to the correct glibc binary regardless of architecture. Co-Authored-By: Claude Opus 4.6 (1M context) --- container/agent-runner/src/providers/claude.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/container/agent-runner/src/providers/claude.ts b/container/agent-runner/src/providers/claude.ts index a797f06d8..fbb077c47 100644 --- a/container/agent-runner/src/providers/claude.ts +++ b/container/agent-runner/src/providers/claude.ts @@ -271,6 +271,7 @@ export class ClaudeProvider implements AgentProvider { cwd: input.cwd, additionalDirectories: this.additionalDirectories, resume: input.continuation, + pathToClaudeCodeExecutable: '/pnpm/claude', systemPrompt: instructions ? { type: 'preset' as const, preset: 'claude_code' as const, append: instructions } : undefined, allowedTools: TOOL_ALLOWLIST, disallowedTools: SDK_DISALLOWED_TOOLS, From 53c11a2d53a97565e18acffc2eeac90005b7e554 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Fri, 17 Apr 2026 15:10:17 +0300 Subject: [PATCH 55/95] chore(skills): delete 9 irrelevant legacy skills MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These shipped with the old v1 architecture and are no longer needed: - add-reactions, add-voice-transcription, add-image-vision, add-pdf-reader, use-local-whisper — Chat SDK channels handle these natively now; the WhatsApp native (Baileys) adapter on the channels branch covers attachments and reactions out of the box. - add-compact — no longer needed. - add-telegram-swarm — Chat SDK Teams adapter handles multi-bot identity. - channel-formatting — Chat SDK does per-channel formatting natively. - add-gmail — was built on a legacy MCP server; deprecated. add-emacs and use-native-credential-proxy are kept and will be ported to the current architecture in follow-up commits. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/add-compact/SKILL.md | 135 ------ .claude/skills/add-gmail/SKILL.md | 236 ----------- .claude/skills/add-image-vision/SKILL.md | 94 ----- .claude/skills/add-pdf-reader/SKILL.md | 104 ----- .claude/skills/add-reactions/SKILL.md | 117 ------ .claude/skills/add-telegram-swarm/SKILL.md | 384 ------------------ .../skills/add-voice-transcription/SKILL.md | 148 ------- .claude/skills/channel-formatting/SKILL.md | 137 ------- .claude/skills/use-local-whisper/SKILL.md | 152 ------- 9 files changed, 1507 deletions(-) delete mode 100644 .claude/skills/add-compact/SKILL.md delete mode 100644 .claude/skills/add-gmail/SKILL.md delete mode 100644 .claude/skills/add-image-vision/SKILL.md delete mode 100644 .claude/skills/add-pdf-reader/SKILL.md delete mode 100644 .claude/skills/add-reactions/SKILL.md delete mode 100644 .claude/skills/add-telegram-swarm/SKILL.md delete mode 100644 .claude/skills/add-voice-transcription/SKILL.md delete mode 100644 .claude/skills/channel-formatting/SKILL.md delete mode 100644 .claude/skills/use-local-whisper/SKILL.md diff --git a/.claude/skills/add-compact/SKILL.md b/.claude/skills/add-compact/SKILL.md deleted file mode 100644 index ee9674aee..000000000 --- a/.claude/skills/add-compact/SKILL.md +++ /dev/null @@ -1,135 +0,0 @@ ---- -name: add-compact -description: Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only. ---- - -# Add /compact Command - -Adds a `/compact` session command that compacts conversation history to fight context rot in long-running sessions. Uses the Claude Agent SDK's built-in `/compact` slash command — no synthetic system prompts. - -**Session contract:** `/compact` keeps the same logical session alive. The SDK returns a new session ID after compaction (via the `init` system message), which the agent-runner forwards to the orchestrator as `newSessionId`. No destructive reset occurs — the agent retains summarized context. - -## Phase 1: Pre-flight - -Check if `src/session-commands.ts` exists: - -```bash -test -f src/session-commands.ts && echo "Already applied" || echo "Not applied" -``` - -If already applied, skip to Phase 3 (Verify). - -## Phase 2: Apply Code Changes - -Merge the skill branch: - -```bash -git fetch upstream skill/compact -git merge upstream/skill/compact -``` - -> **Note:** `upstream` is the remote pointing to `qwibitai/nanoclaw`. If using a different remote name, substitute accordingly. - -This adds: -- `src/session-commands.ts` (extract and authorize session commands) -- `src/session-commands.test.ts` (unit tests for command parsing and auth) -- Session command interception in `src/index.ts` (both `processGroupMessages` and `startMessageLoop`) -- Slash command handling in `container/agent-runner/src/index.ts` - -### Validate - -```bash -pnpm test -pnpm run build -``` - -### Rebuild container - -```bash -./container/build.sh -``` - -### Restart service - -```bash -launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS -# Linux: systemctl --user restart nanoclaw -``` - -## Phase 3: Verify - -### Integration Test - -1. Start NanoClaw in dev mode: `pnpm run dev` -2. From the **main group** (self-chat), send exactly: `/compact` -3. Verify: - - The agent acknowledges compaction (e.g., "Conversation compacted.") - - The session continues — send a follow-up message and verify the agent responds coherently - - A conversation archive is written to `groups/{folder}/conversations/` (by the PreCompact hook) - - Container logs show `Compact boundary observed` (confirms SDK actually compacted) - - If `compact_boundary` was NOT observed, the response says "compact_boundary was not observed" -4. From a **non-main group** as a non-admin user, send: `@ /compact` -5. Verify: - - The bot responds with "Session commands require admin access." - - No compaction occurs, no container is spawned for the command -6. From a **non-main group** as the admin (device owner / `is_from_me`), send: `@ /compact` -7. Verify: - - Compaction proceeds normally (same behavior as main group) -8. While an **active container** is running for the main group, send `/compact` -9. Verify: - - The active container is signaled to close (authorized senders only — untrusted senders cannot kill in-flight work) - - Compaction proceeds via a new container once the active one exits - - The command is not dropped (no cursor race) -10. Send a normal message, then `/compact`, then another normal message in quick succession (same polling batch): -11. Verify: - - Pre-compact messages are sent to the agent first (check container logs for two `runAgent` calls) - - Compaction proceeds after pre-compact messages are processed - - Messages **after** `/compact` in the batch are preserved (cursor advances to `/compact`'s timestamp only) and processed on the next poll cycle -12. From a **non-main group** as a non-admin user, send `@ /compact`: -13. Verify: - - Denial message is sent ("Session commands require admin access.") - - The `/compact` is consumed (cursor advanced) — it does NOT replay on future polls - - Other messages in the same batch are also consumed (cursor is a high-water mark — this is an accepted tradeoff for the narrow edge case of denied `/compact` + other messages in the same polling interval) - - No container is killed or interrupted -14. From a **non-main group** (with `requiresTrigger` enabled) as a non-admin user, send bare `/compact` (no trigger prefix): -15. Verify: - - No denial message is sent (trigger policy prevents untrusted bot responses) - - The `/compact` is consumed silently - - Note: in groups where `requiresTrigger` is `false`, a denial message IS sent because the sender is considered reachable -16. After compaction, verify **no auto-compaction** behavior — only manual `/compact` triggers it - -### Validation on Fresh Clone - -```bash -git clone /tmp/nanoclaw-test -cd /tmp/nanoclaw-test -claude # then run /add-compact -pnpm run build -pnpm test -./container/build.sh -# Manual: send /compact from main group, verify compaction + continuation -# Manual: send @ /compact from non-main as non-admin, verify denial -# Manual: send @ /compact from non-main as admin, verify allowed -# Manual: verify no auto-compaction behavior -``` - -## Security Constraints - -- **Main-group or trusted/admin sender only.** The main group is the user's private self-chat and is trusted (see `docs/SECURITY.md`). Non-main groups are untrusted — a careless or malicious user could wipe the agent's short-term memory. However, the device owner (`is_from_me`) is always trusted and can compact from any group. -- **No auto-compaction.** This skill implements manual compaction only. Automatic threshold-based compaction is a separate concern and should be a separate skill. -- **No config file.** NanoClaw's philosophy is customization through code changes, not configuration sprawl. -- **Transcript archived before compaction.** The existing `PreCompact` hook in the agent-runner archives the full transcript to `conversations/` before the SDK compacts it. -- **Session continues after compaction.** This is not a destructive reset. The conversation continues with summarized context. - -## What This Does NOT Do - -- No automatic compaction threshold (add separately if desired) -- No `/clear` command (separate skill, separate semantics — `/clear` is a destructive reset) -- No cross-group compaction (each group's session is isolated) -- No changes to the container image, Dockerfile, or build script - -## Troubleshooting - -- **"Session commands require admin access"**: Only the device owner (`is_from_me`) or main-group senders can use `/compact`. Other users are denied. -- **No compact_boundary in logs**: The SDK may not emit this event in all versions. Check the agent-runner logs for the warning message. Compaction may still have succeeded. -- **Pre-compact failure**: If messages before `/compact` fail to process, the error message says "Failed to process messages before /compact." The cursor advances past sent output to prevent duplicates; `/compact` remains pending for the next attempt. diff --git a/.claude/skills/add-gmail/SKILL.md b/.claude/skills/add-gmail/SKILL.md deleted file mode 100644 index 6a1329147..000000000 --- a/.claude/skills/add-gmail/SKILL.md +++ /dev/null @@ -1,236 +0,0 @@ ---- -name: add-gmail -description: Add Gmail integration to NanoClaw. Can be configured as a tool (agent reads/sends emails when triggered from WhatsApp) or as a full channel (emails can trigger the agent, schedule tasks, and receive replies). Guides through GCP OAuth setup and implements the integration. ---- - -# Add Gmail Integration - -This skill adds Gmail support to NanoClaw — either as a tool (read, send, search, draft) or as a full channel that polls the inbox. - -## Phase 1: Pre-flight - -### Check if already applied - -Check if `src/channels/gmail.ts` exists. If it does, skip to Phase 3 (Setup). The code changes are already in place. - -### Ask the user - -Use `AskUserQuestion`: - -AskUserQuestion: Should incoming emails be able to trigger the agent? - -- **Yes** — Full channel mode: the agent listens on Gmail and responds to incoming emails automatically -- **No** — Tool-only: the agent gets full Gmail tools (read, send, search, draft) but won't monitor the inbox. No channel code is added. - -## Phase 2: Apply Code Changes - -### Ensure channel remote - -```bash -git remote -v -``` - -If `gmail` is missing, add it: - -```bash -git remote add gmail https://github.com/qwibitai/nanoclaw-gmail.git -``` - -### Merge the skill branch - -```bash -git fetch gmail main -git merge gmail/main || { - git checkout --theirs pnpm-lock.yaml - git add pnpm-lock.yaml - git merge --continue -} -``` - -This merges in: -- `src/channels/gmail.ts` (GmailChannel class with self-registration via `registerChannel`) -- `src/channels/gmail.test.ts` (unit tests) -- `import './gmail.js'` appended to the channel barrel file `src/channels/index.ts` -- Gmail credentials mount (`~/.gmail-mcp`) in `src/container-runner.ts` -- Gmail MCP server (`@gongrzhe/server-gmail-autoauth-mcp`) and `mcp__gmail__*` allowed tool in `container/agent-runner/src/index.ts` -- `googleapis` npm dependency in `package.json` - -If the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides. - -### Add email handling instructions (Channel mode only) - -If the user chose channel mode, append the following to `groups/main/CLAUDE.md` (before the formatting section): - -```markdown -## Email Notifications - -When you receive an email notification (messages starting with `[Email from ...`), inform the user about it but do NOT reply to the email unless specifically asked. You have Gmail tools available — use them only when the user explicitly asks you to reply, forward, or take action on an email. -``` - -### Validate code changes - -```bash -pnpm install -pnpm run build -pnpm exec vitest run src/channels/gmail.test.ts -``` - -All tests must pass (including the new Gmail tests) and build must be clean before proceeding. - -## Phase 3: Setup - -### Check existing Gmail credentials - -```bash -ls -la ~/.gmail-mcp/ 2>/dev/null || echo "No Gmail config found" -``` - -If `credentials.json` already exists with real tokens (not `onecli-managed` values), skip to "Build and restart" below. - -### GCP Project Setup - -Check if OneCLI is configured: - -```bash -grep -q 'ONECLI_URL=.' .env 2>/dev/null && echo "onecli" || echo "manual" -``` - -**If OneCLI:** Tell the user to open `${ONECLI_URL}/connections?connect=gmail` to set up their Gmail connection. The dashboard walks them through creating a Google Cloud OAuth app and authorizing it. Ask them to let you know when done. - -Once the user confirms, run: - -```bash -onecli apps get --provider gmail -``` - -Check that `config.hasCredentials` is `true` or `connection` is not null. The response `hint` field has instructions and a docs URL for what stub credential files to create under `~/.gmail-mcp/`. Follow the hint — never overwrite existing files that don't contain `onecli-managed` values. - -**If manual:** Tell the user: - -> I need you to set up Google Cloud OAuth credentials: -> -> 1. Open https://console.cloud.google.com — create a new project or select existing -> 2. Go to **APIs & Services > Library**, search "Gmail API", click **Enable** -> 3. Go to **APIs & Services > Credentials**, click **+ CREATE CREDENTIALS > OAuth client ID** -> - If prompted for consent screen: choose "External", fill in app name and email, save -> - Application type: **Desktop app**, name: anything (e.g., "NanoClaw Gmail") -> 4. Click **DOWNLOAD JSON** and save as `gcp-oauth.keys.json` -> -> Where did you save the file? (Give me the full path, or paste the file contents here) - -If user provides a path, copy it: - -```bash -mkdir -p ~/.gmail-mcp -cp "/path/user/provided/gcp-oauth.keys.json" ~/.gmail-mcp/gcp-oauth.keys.json -``` - -If user pastes JSON content, write it to `~/.gmail-mcp/gcp-oauth.keys.json`. - -### OAuth Authorization - -Tell the user: - -> I'm going to run Gmail authorization. A browser window will open — sign in and grant access. If you see an "app isn't verified" warning, click "Advanced" then "Go to [app name] (unsafe)" — this is normal for personal OAuth apps. - -Run the authorization: - -```bash -pnpm dlx @gongrzhe/server-gmail-autoauth-mcp auth -``` - -If that fails (some versions don't have an auth subcommand), try `timeout 60 pnpm dlx @gongrzhe/server-gmail-autoauth-mcp || true`. Verify with `ls ~/.gmail-mcp/credentials.json`. - -### Build and restart - -Clear stale per-group agent-runner copies (they only get re-created if missing, so existing copies won't pick up the new Gmail server): - -```bash -rm -r data/sessions/*/agent-runner-src 2>/dev/null || true -``` - -Rebuild the container (agent-runner changed): - -```bash -cd container && ./build.sh -``` - -Then compile and restart: - -```bash -pnpm run build -launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS -# Linux: systemctl --user restart nanoclaw -``` - -## Phase 4: Verify - -### Test tool access (both modes) - -Tell the user: - -> Gmail is connected! Send this in your main channel: -> -> `@Andy check my recent emails` or `@Andy list my Gmail labels` - -### Test channel mode (Channel mode only) - -Tell the user to send themselves a test email. The agent should pick it up within a minute. Monitor: `tail -f logs/nanoclaw.log | grep -iE "(gmail|email)"`. - -Once verified, offer filter customization via `AskUserQuestion` — by default, only emails in the Primary inbox trigger the agent (Promotions, Social, Updates, and Forums are excluded). The user can keep this default or narrow further by sender, label, or keywords. No code changes needed for filters. - -### Check logs if needed - -```bash -tail -f logs/nanoclaw.log -``` - -## Troubleshooting - -### Gmail connection not responding - -Test directly: - -```bash -pnpm dlx @gongrzhe/server-gmail-autoauth-mcp -``` - -### OAuth token expired - -Re-authorize: - -```bash -rm ~/.gmail-mcp/credentials.json -pnpm dlx @gongrzhe/server-gmail-autoauth-mcp -``` - -### Container can't access Gmail - -- Verify `~/.gmail-mcp` is mounted: check `src/container-runner.ts` for the `.gmail-mcp` mount -- Check container logs: `cat groups/main/logs/container-*.log | tail -50` - -### Emails not being detected (Channel mode only) - -- By default, the channel polls unread Primary inbox emails (`is:unread category:primary`) -- Check logs for Gmail polling errors - -## Removal - -### Tool-only mode - -1. Remove `~/.gmail-mcp` mount from `src/container-runner.ts` -2. Remove `gmail` MCP server and `mcp__gmail__*` from `container/agent-runner/src/index.ts` -3. Rebuild and restart -4. Clear stale agent-runner copies: `rm -r data/sessions/*/agent-runner-src 2>/dev/null || true` -5. Rebuild: `cd container && ./build.sh && cd .. && pnpm run build && launchctl kickstart -k gui/$(id -u)/com.nanoclaw` (macOS) or `systemctl --user restart nanoclaw` (Linux) - -### Channel mode - -1. Delete `src/channels/gmail.ts` and `src/channels/gmail.test.ts` -2. Remove `import './gmail.js'` from `src/channels/index.ts` -3. Remove `~/.gmail-mcp` mount from `src/container-runner.ts` -4. Remove `gmail` MCP server and `mcp__gmail__*` from `container/agent-runner/src/index.ts` -5. Uninstall: `pnpm uninstall googleapis` -6. Rebuild and restart -7. Clear stale agent-runner copies: `rm -r data/sessions/*/agent-runner-src 2>/dev/null || true` -8. Rebuild: `cd container && ./build.sh && cd .. && pnpm run build && launchctl kickstart -k gui/$(id -u)/com.nanoclaw` (macOS) or `systemctl --user restart nanoclaw` (Linux) diff --git a/.claude/skills/add-image-vision/SKILL.md b/.claude/skills/add-image-vision/SKILL.md deleted file mode 100644 index 4a9da26ee..000000000 --- a/.claude/skills/add-image-vision/SKILL.md +++ /dev/null @@ -1,94 +0,0 @@ ---- -name: add-image-vision -description: Add image vision to NanoClaw agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks. ---- - -# Image Vision Skill - -Adds the ability for NanoClaw agents to see and understand images sent via WhatsApp. Images are downloaded, resized with sharp, saved to the group workspace, and passed to the agent as base64-encoded multimodal content blocks. - -## Phase 1: Pre-flight - -1. Check if `src/image.ts` exists — skip to Phase 3 if already applied -2. Confirm `sharp` is installable (native bindings require build tools) - -**Prerequisite:** WhatsApp must be installed first (`skill/whatsapp` merged). This skill modifies WhatsApp channel files. - -## Phase 2: Apply Code Changes - -### Ensure WhatsApp fork remote - -```bash -git remote -v -``` - -If `whatsapp` is missing, add it: - -```bash -git remote add whatsapp https://github.com/qwibitai/nanoclaw-whatsapp.git -``` - -### Merge the skill branch - -```bash -git fetch whatsapp skill/image-vision -git merge whatsapp/skill/image-vision || { - git checkout --theirs pnpm-lock.yaml - git add pnpm-lock.yaml - git merge --continue -} -``` - -This merges in: -- `src/image.ts` (image download, resize via sharp, base64 encoding) -- `src/image.test.ts` (8 unit tests) -- Image attachment handling in `src/channels/whatsapp.ts` -- Image passing to agent in `src/index.ts` and `src/container-runner.ts` -- Image content block support in `container/agent-runner/src/index.ts` -- `sharp` npm dependency in `package.json` - -If the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides. - -### Validate code changes - -```bash -pnpm install -pnpm run build -pnpm exec vitest run src/image.test.ts -``` - -All tests must pass and build must be clean before proceeding. - -## Phase 3: Configure - -1. Rebuild the container (agent-runner changes need a rebuild): - ```bash - ./container/build.sh - ``` - -2. Sync agent-runner source to group caches: - ```bash - for dir in data/sessions/*/agent-runner-src/; do - cp container/agent-runner/src/*.ts "$dir" - done - ``` - -3. Restart the service: - ```bash - launchctl kickstart -k gui/$(id -u)/com.nanoclaw - ``` - -## Phase 4: Verify - -1. Send an image in a registered WhatsApp group -2. Check the agent responds with understanding of the image content -3. Check logs for "Processed image attachment": - ```bash - tail -50 groups/*/logs/container-*.log - ``` - -## Troubleshooting - -- **"Image - download failed"**: Check WhatsApp connection stability. The download may timeout on slow connections. -- **"Image - processing failed"**: Sharp may not be installed correctly. Run `pnpm ls sharp` to verify. -- **Agent doesn't mention image content**: Check container logs for "Loaded image" messages. If missing, ensure agent-runner source was synced to group caches. diff --git a/.claude/skills/add-pdf-reader/SKILL.md b/.claude/skills/add-pdf-reader/SKILL.md deleted file mode 100644 index aecc347b5..000000000 --- a/.claude/skills/add-pdf-reader/SKILL.md +++ /dev/null @@ -1,104 +0,0 @@ ---- -name: add-pdf-reader -description: Add PDF reading to NanoClaw agents. Extracts text from PDFs via pdftotext CLI. Handles WhatsApp attachments, URLs, and local files. ---- - -# Add PDF Reader - -Adds PDF reading capability to all container agents using poppler-utils (pdftotext/pdfinfo). PDFs sent as WhatsApp attachments are auto-downloaded to the group workspace. - -## Phase 1: Pre-flight - -1. Check if `container/skills/pdf-reader/pdf-reader` exists — skip to Phase 3 if already applied -2. Confirm WhatsApp is installed first (`skill/whatsapp` merged). This skill modifies WhatsApp channel files. - -## Phase 2: Apply Code Changes - -### Ensure WhatsApp fork remote - -```bash -git remote -v -``` - -If `whatsapp` is missing, add it: - -```bash -git remote add whatsapp https://github.com/qwibitai/nanoclaw-whatsapp.git -``` - -### Merge the skill branch - -```bash -git fetch whatsapp skill/pdf-reader -git merge whatsapp/skill/pdf-reader || { - git checkout --theirs pnpm-lock.yaml - git add pnpm-lock.yaml - git merge --continue -} -``` - -This merges in: -- `container/skills/pdf-reader/SKILL.md` (agent-facing documentation) -- `container/skills/pdf-reader/pdf-reader` (CLI script) -- `poppler-utils` in `container/Dockerfile` -- PDF attachment download in `src/channels/whatsapp.ts` -- PDF tests in `src/channels/whatsapp.test.ts` - -If the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides. - -### Validate - -```bash -pnpm run build -pnpm exec vitest run src/channels/whatsapp.test.ts -``` - -### Rebuild container - -```bash -./container/build.sh -``` - -### Restart service - -```bash -launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS -# Linux: systemctl --user restart nanoclaw -``` - -## Phase 3: Verify - -### Test PDF extraction - -Send a PDF file in any registered WhatsApp chat. The agent should: -1. Download the PDF to `attachments/` -2. Respond acknowledging the PDF -3. Be able to extract text when asked - -### Test URL fetching - -Ask the agent to read a PDF from a URL. It should use `pdf-reader fetch `. - -### Check logs if needed - -```bash -tail -f logs/nanoclaw.log | grep -i pdf -``` - -Look for: -- `Downloaded PDF attachment` — successful download -- `Failed to download PDF attachment` — media download issue - -## Troubleshooting - -### Agent says pdf-reader command not found - -Container needs rebuilding. Run `./container/build.sh` and restart the service. - -### PDF text extraction is empty - -The PDF may be scanned (image-based). pdftotext only handles text-based PDFs. Consider using the agent-browser to open the PDF visually instead. - -### WhatsApp PDF not detected - -Verify the message has `documentMessage` with `mimetype: application/pdf`. Some file-sharing apps send PDFs as generic files without the correct mimetype. diff --git a/.claude/skills/add-reactions/SKILL.md b/.claude/skills/add-reactions/SKILL.md deleted file mode 100644 index 435bef9c8..000000000 --- a/.claude/skills/add-reactions/SKILL.md +++ /dev/null @@ -1,117 +0,0 @@ ---- -name: add-reactions -description: Add WhatsApp emoji reaction support — receive, send, store, and search reactions. ---- - -# Add Reactions - -This skill adds emoji reaction support to NanoClaw's WhatsApp channel: receive and store reactions, send reactions from the container agent via MCP tool, and query reaction history from SQLite. - -## Phase 1: Pre-flight - -### Check if already applied - -Check if `src/status-tracker.ts` exists: - -```bash -test -f src/status-tracker.ts && echo "Already applied" || echo "Not applied" -``` - -If already applied, skip to Phase 3 (Verify). - -## Phase 2: Apply Code Changes - -### Ensure WhatsApp fork remote - -```bash -git remote -v -``` - -If `whatsapp` is missing, add it: - -```bash -git remote add whatsapp https://github.com/qwibitai/nanoclaw-whatsapp.git -``` - -### Merge the skill branch - -```bash -git fetch whatsapp skill/reactions -git merge whatsapp/skill/reactions || { - git checkout --theirs pnpm-lock.yaml - git add pnpm-lock.yaml - git merge --continue -} -``` - -This adds: -- `scripts/migrate-reactions.ts` (database migration for `reactions` table with composite PK and indexes) -- `src/status-tracker.ts` (forward-only emoji state machine for message lifecycle signaling, with persistence and retry) -- `src/status-tracker.test.ts` (unit tests for StatusTracker) -- `container/skills/reactions/SKILL.md` (agent-facing documentation for the `react_to_message` MCP tool) -- Reaction support in `src/db.ts`, `src/channels/whatsapp.ts`, `src/types.ts`, `src/ipc.ts`, `src/index.ts`, `src/group-queue.ts`, and `container/agent-runner/src/ipc-mcp-stdio.ts` - -### Run database migration - -```bash -pnpm exec tsx scripts/migrate-reactions.ts -``` - -### Validate code changes - -```bash -pnpm test -pnpm run build -``` - -All tests must pass and build must be clean before proceeding. - -## Phase 3: Verify - -### Build and restart - -```bash -pnpm run build -``` - -Linux: -```bash -systemctl --user restart nanoclaw -``` - -macOS: -```bash -launchctl kickstart -k gui/$(id -u)/com.nanoclaw -``` - -### Test receiving reactions - -1. Send a message from your phone -2. React to it with an emoji on WhatsApp -3. Check the database: - -```bash -sqlite3 store/messages.db "SELECT * FROM reactions ORDER BY timestamp DESC LIMIT 5;" -``` - -### Test sending reactions - -Ask the agent to react to a message via the `react_to_message` MCP tool. Check your phone — the reaction should appear on the message. - -## Troubleshooting - -### Reactions not appearing in database - -- Check NanoClaw logs for `Failed to process reaction` errors -- Verify the chat is registered -- Confirm the service is running - -### Migration fails - -- Ensure `store/messages.db` exists and is accessible -- If "table reactions already exists", the migration already ran — skip it - -### Agent can't send reactions - -- Check IPC logs for `Unauthorized IPC reaction attempt blocked` — the agent can only react in its own group's chat -- Verify WhatsApp is connected: check logs for connection status diff --git a/.claude/skills/add-telegram-swarm/SKILL.md b/.claude/skills/add-telegram-swarm/SKILL.md deleted file mode 100644 index 8f6a4fc27..000000000 --- a/.claude/skills/add-telegram-swarm/SKILL.md +++ /dev/null @@ -1,384 +0,0 @@ ---- -name: add-telegram-swarm -description: Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool". ---- - -# Add Agent Swarm to Telegram - -This skill adds Agent Teams (Swarm) support to an existing Telegram channel. Each subagent in a team gets its own bot identity in the Telegram group, so users can visually distinguish which agent is speaking. - -**Prerequisite**: Telegram must already be set up via the `/add-telegram` skill. If `src/telegram.ts` does not exist or `TELEGRAM_BOT_TOKEN` is not configured, tell the user to run `/add-telegram` first. - -## How It Works - -- The **main bot** receives messages and sends lead agent responses (already set up by `/add-telegram`) -- **Pool bots** are send-only — each gets a Grammy `Api` instance (no polling) -- When a subagent calls `send_message` with a `sender` parameter, the host assigns a pool bot and renames it to match the sender's role -- Messages appear in Telegram from different bot identities - -``` -Subagent calls send_message(text: "Found 3 results", sender: "Researcher") - → MCP writes IPC file with sender field - → Host IPC watcher picks it up - → Assigns pool bot #2 to "Researcher" (round-robin, stable per-group) - → Renames pool bot #2 to "Researcher" via setMyName - → Sends message via pool bot #2's Api instance - → Appears in Telegram from "Researcher" bot -``` - -## Prerequisites - -### 1. Create Pool Bots - -Tell the user: - -> I need you to create 3-5 Telegram bots to use as the agent pool. These will be renamed dynamically to match agent roles. -> -> 1. Open Telegram and search for `@BotFather` -> 2. Send `/newbot` for each bot: -> - Give them any placeholder name (e.g., "Bot 1", "Bot 2") -> - Usernames like `myproject_swarm_1_bot`, `myproject_swarm_2_bot`, etc. -> 3. Copy all the tokens -> 4. Add all bots to your Telegram group(s) where you want agent teams - -Wait for user to provide the tokens. - -### 2. Disable Group Privacy for Pool Bots - -Tell the user: - -> **Important**: Each pool bot needs Group Privacy disabled so it can send messages in groups. -> -> For each pool bot in `@BotFather`: -> 1. Send `/mybots` and select the bot -> 2. Go to **Bot Settings** > **Group Privacy** > **Turn off** -> -> Then add all pool bots to your Telegram group(s). - -## Implementation - -### Step 1: Update Configuration - -Read `src/config.ts` and add the bot pool config near the other Telegram exports: - -```typescript -export const TELEGRAM_BOT_POOL = (process.env.TELEGRAM_BOT_POOL || '') - .split(',') - .map((t) => t.trim()) - .filter(Boolean); -``` - -### Step 2: Add Bot Pool to Telegram Module - -Read `src/telegram.ts` and add the following: - -1. **Update imports** — add `Api` to the Grammy import: - -```typescript -import { Api, Bot } from 'grammy'; -``` - -2. **Add pool state** after the existing `let bot` declaration: - -```typescript -// Bot pool for agent teams: send-only Api instances (no polling) -const poolApis: Api[] = []; -// Maps "{groupFolder}:{senderName}" → pool Api index for stable assignment -const senderBotMap = new Map(); -let nextPoolIndex = 0; -``` - -3. **Add pool functions** — place these before the `isTelegramConnected` function: - -```typescript -/** - * Initialize send-only Api instances for the bot pool. - * Each pool bot can send messages but doesn't poll for updates. - */ -export async function initBotPool(tokens: string[]): Promise { - for (const token of tokens) { - try { - const api = new Api(token); - const me = await api.getMe(); - poolApis.push(api); - logger.info( - { username: me.username, id: me.id, poolSize: poolApis.length }, - 'Pool bot initialized', - ); - } catch (err) { - logger.error({ err }, 'Failed to initialize pool bot'); - } - } - if (poolApis.length > 0) { - logger.info({ count: poolApis.length }, 'Telegram bot pool ready'); - } -} - -/** - * Send a message via a pool bot assigned to the given sender name. - * Assigns bots round-robin on first use; subsequent messages from the - * same sender in the same group always use the same bot. - * On first assignment, renames the bot to match the sender's role. - */ -export async function sendPoolMessage( - chatId: string, - text: string, - sender: string, - groupFolder: string, -): Promise { - if (poolApis.length === 0) { - // No pool bots — fall back to main bot - await sendTelegramMessage(chatId, text); - return; - } - - const key = `${groupFolder}:${sender}`; - let idx = senderBotMap.get(key); - if (idx === undefined) { - idx = nextPoolIndex % poolApis.length; - nextPoolIndex++; - senderBotMap.set(key, idx); - // Rename the bot to match the sender's role, then wait for Telegram to propagate - try { - await poolApis[idx].setMyName(sender); - await new Promise((r) => setTimeout(r, 2000)); - logger.info({ sender, groupFolder, poolIndex: idx }, 'Assigned and renamed pool bot'); - } catch (err) { - logger.warn({ sender, err }, 'Failed to rename pool bot (sending anyway)'); - } - } - - const api = poolApis[idx]; - try { - const numericId = chatId.replace(/^tg:/, ''); - const MAX_LENGTH = 4096; - if (text.length <= MAX_LENGTH) { - await api.sendMessage(numericId, text); - } else { - for (let i = 0; i < text.length; i += MAX_LENGTH) { - await api.sendMessage(numericId, text.slice(i, i + MAX_LENGTH)); - } - } - logger.info({ chatId, sender, poolIndex: idx, length: text.length }, 'Pool message sent'); - } catch (err) { - logger.error({ chatId, sender, err }, 'Failed to send pool message'); - } -} -``` - -### Step 3: Add sender Parameter to MCP Tool - -Read `container/agent-runner/src/ipc-mcp-stdio.ts` and update the `send_message` tool to accept an optional `sender` parameter: - -Change the tool's schema from: -```typescript -{ text: z.string().describe('The message text to send') }, -``` - -To: -```typescript -{ - text: z.string().describe('The message text to send'), - sender: z.string().optional().describe('Your role/identity name (e.g. "Researcher"). When set, messages appear from a dedicated bot in Telegram.'), -}, -``` - -And update the handler to include `sender` in the IPC data: - -```typescript -async (args) => { - const data: Record = { - type: 'message', - chatJid, - text: args.text, - sender: args.sender || undefined, - groupFolder, - timestamp: new Date().toISOString(), - }; - - writeIpcFile(MESSAGES_DIR, data); - - return { content: [{ type: 'text' as const, text: 'Message sent.' }] }; - }, -``` - -### Step 4: Update Host IPC Routing - -Read `src/ipc.ts` and make these changes: - -1. **Add imports** — add `sendPoolMessage` and `initBotPool` from the Telegram swarm module, and `TELEGRAM_BOT_POOL` from config. - -2. **Update IPC message routing** — in `src/ipc.ts`, find where the `sendMessage` dependency is called to deliver IPC messages (inside `processIpcFiles`). The `sendMessage` is passed in via the `IpcDeps` parameter. Wrap it to route Telegram swarm messages through the bot pool: - -```typescript -if (data.sender && data.chatJid.startsWith('tg:')) { - await sendPoolMessage( - data.chatJid, - data.text, - data.sender, - sourceGroup, - ); -} else { - await deps.sendMessage(data.chatJid, data.text); -} -``` - -Note: The assistant name prefix is handled by `formatOutbound()` in the router — Telegram channels have `prefixAssistantName = false` so no prefix is added for `tg:` JIDs. - -3. **Initialize pool in `main()` in `src/index.ts`** — after creating the Telegram channel, add: - -```typescript -if (TELEGRAM_BOT_POOL.length > 0) { - await initBotPool(TELEGRAM_BOT_POOL); -} -``` - -### Step 5: Update CLAUDE.md Files - -#### 5a. Add global message formatting rules - -Read `groups/global/CLAUDE.md` and add a Message Formatting section: - -```markdown -## Message Formatting - -NEVER use markdown. Only use WhatsApp/Telegram formatting: -- *single asterisks* for bold (NEVER **double asterisks**) -- _underscores_ for italic -- • bullet points -- ```triple backticks``` for code - -No ## headings. No [links](url). No **double stars**. -``` - -#### 5b. Update existing group CLAUDE.md headings - -In any group CLAUDE.md that has a "WhatsApp Formatting" section (e.g. `groups/main/CLAUDE.md`), rename the heading to reflect multi-channel support: - -``` -## WhatsApp Formatting (and other messaging apps) -``` - -#### 5c. Add Agent Teams instructions to Telegram groups - -For each Telegram group that will use agent teams, create or update its `groups/{folder}/CLAUDE.md` with these instructions. Read the existing CLAUDE.md first (or `groups/global/CLAUDE.md` as a base) and add the Agent Teams section: - -```markdown -## Agent Teams - -When creating a team to tackle a complex task, follow these rules: - -### CRITICAL: Follow the user's prompt exactly - -Create *exactly* the team the user asked for — same number of agents, same roles, same names. Do NOT add extra agents, rename roles, or use generic names like "Researcher 1". If the user says "a marine biologist, a physicist, and Alexander Hamilton", create exactly those three agents with those exact names. - -### Team member instructions - -Each team member MUST be instructed to: - -1. *Share progress in the group* via `mcp__nanoclaw__send_message` with a `sender` parameter matching their exact role/character name (e.g., `sender: "Marine Biologist"` or `sender: "Alexander Hamilton"`). This makes their messages appear from a dedicated bot in the Telegram group. -2. *Also communicate with teammates* via `SendMessage` as normal for coordination. -3. Keep group messages *short* — 2-4 sentences max per message. Break longer content into multiple `send_message` calls. No walls of text. -4. Use the `sender` parameter consistently — always the same name so the bot identity stays stable. -5. NEVER use markdown formatting. Use ONLY WhatsApp/Telegram formatting: single *asterisks* for bold (NOT **double**), _underscores_ for italic, • for bullets, ```backticks``` for code. No ## headings, no [links](url), no **double asterisks**. - -### Example team creation prompt - -When creating a teammate, include instructions like: - -\``` -You are the Marine Biologist. When you have findings or updates for the user, send them to the group using mcp__nanoclaw__send_message with sender set to "Marine Biologist". Keep each message short (2-4 sentences max). Use emojis for strong reactions. ONLY use single *asterisks* for bold (never **double**), _underscores_ for italic, • for bullets. No markdown. Also communicate with teammates via SendMessage. -\``` - -### Lead agent behavior - -As the lead agent who created the team: - -- You do NOT need to react to or relay every teammate message. The user sees those directly from the teammate bots. -- Send your own messages only to comment, share thoughts, synthesize, or direct the team. -- When processing an internal update from a teammate that doesn't need a user-facing response, wrap your *entire* output in `` tags. -- Focus on high-level coordination and the final synthesis. -``` - -### Step 6: Update Environment - -Add pool tokens to `.env`: - -```bash -TELEGRAM_BOT_POOL=TOKEN1,TOKEN2,TOKEN3,... -``` - -**Important**: Sync to all required locations: - -```bash -cp .env data/env/env -``` - -Also add `TELEGRAM_BOT_POOL` to the launchd plist (`~/Library/LaunchAgents/com.nanoclaw.plist`) in the `EnvironmentVariables` dict if using launchd. - -### Step 7: Rebuild and Restart - -```bash -pnpm run build -./container/build.sh # Required — MCP tool changed -# macOS: -launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist -launchctl load ~/Library/LaunchAgents/com.nanoclaw.plist -# Linux: -# systemctl --user restart nanoclaw -``` - -Must use `unload/load` (macOS) or `restart` (Linux) because the service env vars changed. - -### Step 8: Test - -Tell the user: - -> Send a message in your Telegram group asking for a multi-agent task, e.g.: -> "Assemble a team of a researcher and a coder to build me a hello world app" -> -> You should see: -> - The lead agent (main bot) acknowledging and creating the team -> - Each subagent messaging from a different bot, renamed to their role -> - Short, scannable messages from each agent -> -> Check logs: `tail -f logs/nanoclaw.log | grep -i pool` - -## Architecture Notes - -- Pool bots use Grammy's `Api` class — lightweight, no polling, just send -- Bot names are set via `setMyName` — changes are global to the bot, not per-chat -- A 2-second delay after `setMyName` allows Telegram to propagate the name change before the first message -- Sender→bot mapping is stable within a group (keyed as `{groupFolder}:{senderName}`) -- Mapping resets on service restart — pool bots get reassigned fresh -- If pool runs out, bots are reused (round-robin wraps) - -## Troubleshooting - -### Pool bots not sending messages - -1. Verify tokens: `curl -s "https://api.telegram.org/botTOKEN/getMe"` -2. Check pool initialized: `grep "Pool bot" logs/nanoclaw.log` -3. Ensure all pool bots are members of the Telegram group -4. Check Group Privacy is disabled for each pool bot - -### Bot names not updating - -Telegram caches bot names client-side. The 2-second delay after `setMyName` helps, but users may need to restart their Telegram client to see updated names immediately. - -### Subagents not using send_message - -Check the group's `CLAUDE.md` has the Agent Teams instructions. The lead agent reads this when creating teammates and must include the `send_message` + `sender` instructions in each teammate's prompt. - -## Removal - -To remove Agent Swarm support while keeping basic Telegram: - -1. Remove `TELEGRAM_BOT_POOL` from `src/config.ts` -2. Remove pool code from `src/telegram.ts` (`poolApis`, `senderBotMap`, `initBotPool`, `sendPoolMessage`) -3. Remove pool routing from IPC handler in `src/index.ts` (revert to plain `sendMessage`) -4. Remove `initBotPool` call from `main()` -5. Remove `sender` param from MCP tool in `container/agent-runner/src/ipc-mcp-stdio.ts` -6. Remove Agent Teams section from group CLAUDE.md files -7. Remove `TELEGRAM_BOT_POOL` from `.env`, `data/env/env`, and launchd plist/systemd unit -8. Rebuild: `pnpm run build && ./container/build.sh && launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist && launchctl load ~/Library/LaunchAgents/com.nanoclaw.plist` (macOS) or `pnpm run build && ./container/build.sh && systemctl --user restart nanoclaw` (Linux) diff --git a/.claude/skills/add-voice-transcription/SKILL.md b/.claude/skills/add-voice-transcription/SKILL.md deleted file mode 100644 index cae1e4749..000000000 --- a/.claude/skills/add-voice-transcription/SKILL.md +++ /dev/null @@ -1,148 +0,0 @@ ---- -name: add-voice-transcription -description: Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them. ---- - -# Add Voice Transcription - -This skill adds automatic voice message transcription to NanoClaw's WhatsApp channel using OpenAI's Whisper API. When a voice note arrives, it is downloaded, transcribed, and delivered to the agent as `[Voice: ]`. - -## Phase 1: Pre-flight - -### Check if already applied - -Check if `src/transcription.ts` exists. If it does, skip to Phase 3 (Configure). The code changes are already in place. - -### Ask the user - -Use `AskUserQuestion` to collect information: - -AskUserQuestion: Do you have an OpenAI API key for Whisper transcription? - -If yes, collect it now. If no, direct them to create one at https://platform.openai.com/api-keys. - -## Phase 2: Apply Code Changes - -**Prerequisite:** WhatsApp must be installed first (`skill/whatsapp` merged). This skill modifies WhatsApp channel files. - -### Ensure WhatsApp fork remote - -```bash -git remote -v -``` - -If `whatsapp` is missing, add it: - -```bash -git remote add whatsapp https://github.com/qwibitai/nanoclaw-whatsapp.git -``` - -### Merge the skill branch - -```bash -git fetch whatsapp skill/voice-transcription -git merge whatsapp/skill/voice-transcription || { - git checkout --theirs pnpm-lock.yaml - git add pnpm-lock.yaml - git merge --continue -} -``` - -This merges in: -- `src/transcription.ts` (voice transcription module using OpenAI Whisper) -- Voice handling in `src/channels/whatsapp.ts` (isVoiceMessage check, transcribeAudioMessage call) -- Transcription tests in `src/channels/whatsapp.test.ts` -- `openai` npm dependency in `package.json` -- `OPENAI_API_KEY` in `.env.example` - -If the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides. - -### Validate code changes - -```bash -pnpm install -pnpm run build -pnpm exec vitest run src/channels/whatsapp.test.ts -``` - -All tests must pass and build must be clean before proceeding. - -## Phase 3: Configure - -### Get OpenAI API key (if needed) - -If the user doesn't have an API key: - -> I need you to create an OpenAI API key: -> -> 1. Go to https://platform.openai.com/api-keys -> 2. Click "Create new secret key" -> 3. Give it a name (e.g., "NanoClaw Transcription") -> 4. Copy the key (starts with `sk-`) -> -> Cost: ~$0.006 per minute of audio (~$0.003 per typical 30-second voice note) - -Wait for the user to provide the key. - -### Add to environment - -Add to `.env`: - -```bash -OPENAI_API_KEY= -``` - -Sync to container environment: - -```bash -mkdir -p data/env && cp .env data/env/env -``` - -The container reads environment from `data/env/env`, not `.env` directly. - -### Build and restart - -```bash -pnpm run build -launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS -# Linux: systemctl --user restart nanoclaw -``` - -## Phase 4: Verify - -### Test with a voice note - -Tell the user: - -> Send a voice note in any registered WhatsApp chat. The agent should receive it as `[Voice: ]` and respond to its content. - -### Check logs if needed - -```bash -tail -f logs/nanoclaw.log | grep -i voice -``` - -Look for: -- `Transcribed voice message` — successful transcription with character count -- `OPENAI_API_KEY not set` — key missing from `.env` -- `OpenAI transcription failed` — API error (check key validity, billing) -- `Failed to download audio message` — media download issue - -## Troubleshooting - -### Voice notes show "[Voice Message - transcription unavailable]" - -1. Check `OPENAI_API_KEY` is set in `.env` AND synced to `data/env/env` -2. Verify key works: `curl -s https://api.openai.com/v1/models -H "Authorization: Bearer $OPENAI_API_KEY" | head -c 200` -3. Check OpenAI billing — Whisper requires a funded account - -### Voice notes show "[Voice Message - transcription failed]" - -Check logs for the specific error. Common causes: -- Network timeout — transient, will work on next message -- Invalid API key — regenerate at https://platform.openai.com/api-keys -- Rate limiting — wait and retry - -### Agent doesn't respond to voice notes - -Verify the chat is registered and the agent is running. Voice transcription only runs for registered groups. diff --git a/.claude/skills/channel-formatting/SKILL.md b/.claude/skills/channel-formatting/SKILL.md deleted file mode 100644 index 8d27ffceb..000000000 --- a/.claude/skills/channel-formatting/SKILL.md +++ /dev/null @@ -1,137 +0,0 @@ ---- -name: channel-formatting -description: Convert Claude's Markdown output to each channel's native text syntax before delivery. Adds zero-dependency formatting for WhatsApp, Telegram, and Slack (marker substitution). Also ships a Signal rich-text helper (parseSignalStyles) used by the Signal skill. ---- - -# Channel Formatting - -This skill wires channel-aware Markdown conversion into the outbound pipeline so Claude's -responses render natively on each platform — no more literal `**asterisks**` in WhatsApp or -Telegram. - -| Channel | Transformation | -|---------|---------------| -| WhatsApp | `**bold**` → `*bold*`, `*italic*` → `_italic_`, headings → bold, links → `text (url)` | -| Telegram | same as WhatsApp, but `[text](url)` links are preserved (Markdown v1 renders them natively) | -| Slack | same as WhatsApp, but links become `` | -| Discord | passthrough (Discord already renders Markdown) | -| Signal | passthrough for `parseTextStyles`; `parseSignalStyles` in `src/text-styles.ts` produces plain text + native `textStyle` ranges for use by the Signal skill | - -Code blocks (fenced and inline) are always protected — their content is never transformed. - -## Phase 1: Pre-flight - -### Check if already applied - -```bash -test -f src/text-styles.ts && echo "already applied" || echo "not yet applied" -``` - -If `already applied`, skip to Phase 3 (Verify). - -## Phase 2: Apply Code Changes - -### Ensure the upstream remote - -```bash -git remote -v -``` - -If an `upstream` remote pointing to `https://github.com/qwibitai/nanoclaw.git` is missing, -add it: - -```bash -git remote add upstream https://github.com/qwibitai/nanoclaw.git -``` - -### Merge the skill branch - -```bash -git fetch upstream skill/channel-formatting -git merge upstream/skill/channel-formatting -``` - -If there are merge conflicts on `pnpm-lock.yaml`, resolve them by accepting the incoming -version and continuing: - -```bash -git checkout --theirs pnpm-lock.yaml -git add pnpm-lock.yaml -git merge --continue -``` - -For any other conflict, read the conflicted file and reconcile both sides manually. - -This merge adds: - -- `src/text-styles.ts` — `parseTextStyles(text, channel)` for marker substitution and - `parseSignalStyles(text)` for Signal native rich text -- `src/router.ts` — `formatOutbound` gains an optional `channel` parameter; when provided - it calls `parseTextStyles` after stripping `` tags -- `src/index.ts` — both outbound `sendMessage` paths pass `channel.name` to `formatOutbound` -- `src/formatting.test.ts` — test coverage for both functions across all channels - -### Validate - -```bash -pnpm install -pnpm run build -pnpm exec vitest run src/formatting.test.ts -``` - -All 73 tests should pass and the build should be clean before continuing. - -## Phase 3: Verify - -### Rebuild and restart - -```bash -pnpm run build -launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS -# Linux: systemctl --user restart nanoclaw -``` - -### Spot-check formatting - -Send a message through any registered WhatsApp or Telegram chat that will trigger a -response from Claude. Ask something that will produce formatted output, such as: - -> Summarise the three main advantages of TypeScript using bullet points and **bold** headings. - -Confirm that the response arrives with native bold (`*text*`) rather than raw double -asterisks. - -### Check logs if needed - -```bash -tail -f logs/nanoclaw.log -``` - -## Signal Skill Integration - -If you have the Signal skill installed, `src/channels/signal.ts` can import -`parseSignalStyles` from the newly present `src/text-styles.ts`: - -```typescript -import { parseSignalStyles, SignalTextStyle } from '../text-styles.js'; -``` - -`parseSignalStyles` returns `{ text: string, textStyle: SignalTextStyle[] }` where -`textStyle` is an array of `{ style, start, length }` objects suitable for the -`signal-cli` JSON-RPC `textStyles` parameter (format: `"start:length:STYLE"`). - -## Removal - -```bash -# Remove the new file -rm src/text-styles.ts - -# Revert router.ts to remove the channel param -git diff upstream/main src/router.ts # review changes -git checkout upstream/main -- src/router.ts - -# Revert the index.ts sendMessage call sites to plain formatOutbound(rawText) -# (edit manually or: git checkout upstream/main -- src/index.ts) - -pnpm run build -``` \ No newline at end of file diff --git a/.claude/skills/use-local-whisper/SKILL.md b/.claude/skills/use-local-whisper/SKILL.md deleted file mode 100644 index 664cafa51..000000000 --- a/.claude/skills/use-local-whisper/SKILL.md +++ /dev/null @@ -1,152 +0,0 @@ ---- -name: use-local-whisper -description: Use when the user wants local voice transcription instead of OpenAI Whisper API. Switches to whisper.cpp running on Apple Silicon. WhatsApp only for now. Requires voice-transcription skill to be applied first. ---- - -# Use Local Whisper - -Switches voice transcription from OpenAI's Whisper API to local whisper.cpp. Runs entirely on-device — no API key, no network, no cost. - -**Channel support:** Currently WhatsApp only. The transcription module (`src/transcription.ts`) uses Baileys types for audio download. Other channels (Telegram, Discord, etc.) would need their own audio-download logic before this skill can serve them. - -**Note:** The Homebrew package is `whisper-cpp`, but the CLI binary it installs is `whisper-cli`. - -## Prerequisites - -- `voice-transcription` skill must be applied first (WhatsApp channel) -- macOS with Apple Silicon (M1+) recommended -- `whisper-cpp` installed: `brew install whisper-cpp` (provides the `whisper-cli` binary) -- `ffmpeg` installed: `brew install ffmpeg` -- A GGML model file downloaded to `data/models/` - -## Phase 1: Pre-flight - -### Check if already applied - -Check if `src/transcription.ts` already uses `whisper-cli`: - -```bash -grep 'whisper-cli' src/transcription.ts && echo "Already applied" || echo "Not applied" -``` - -If already applied, skip to Phase 3 (Verify). - -### Check dependencies are installed - -```bash -whisper-cli --help >/dev/null 2>&1 && echo "WHISPER_OK" || echo "WHISPER_MISSING" -ffmpeg -version >/dev/null 2>&1 && echo "FFMPEG_OK" || echo "FFMPEG_MISSING" -``` - -If missing, install via Homebrew: -```bash -brew install whisper-cpp ffmpeg -``` - -### Check for model file - -```bash -ls data/models/ggml-*.bin 2>/dev/null || echo "NO_MODEL" -``` - -If no model exists, download the base model (148MB, good balance of speed and accuracy): -```bash -mkdir -p data/models -curl -L -o data/models/ggml-base.bin "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin" -``` - -For better accuracy at the cost of speed, use `ggml-small.bin` (466MB) or `ggml-medium.bin` (1.5GB). - -## Phase 2: Apply Code Changes - -### Ensure WhatsApp fork remote - -```bash -git remote -v -``` - -If `whatsapp` is missing, add it: - -```bash -git remote add whatsapp https://github.com/qwibitai/nanoclaw-whatsapp.git -``` - -### Merge the skill branch - -```bash -git fetch whatsapp skill/local-whisper -git merge whatsapp/skill/local-whisper || { - git checkout --theirs pnpm-lock.yaml - git add pnpm-lock.yaml - git merge --continue -} -``` - -This modifies `src/transcription.ts` to use the `whisper-cli` binary instead of the OpenAI API. - -### Validate - -```bash -pnpm run build -``` - -## Phase 3: Verify - -### Ensure launchd PATH includes Homebrew - -The NanoClaw launchd service runs with a restricted PATH. `whisper-cli` and `ffmpeg` are in `/opt/homebrew/bin/` (Apple Silicon) or `/usr/local/bin/` (Intel), which may not be in the plist's PATH. - -Check the current PATH: -```bash -grep -A1 'PATH' ~/Library/LaunchAgents/com.nanoclaw.plist -``` - -If `/opt/homebrew/bin` is missing, add it to the `` value inside the `PATH` key in the plist. Then reload: -```bash -launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist -launchctl load ~/Library/LaunchAgents/com.nanoclaw.plist -``` - -### Build and restart - -```bash -pnpm run build -launchctl kickstart -k gui/$(id -u)/com.nanoclaw -``` - -### Test - -Send a voice note in any registered group. The agent should receive it as `[Voice: ]`. - -### Check logs - -```bash -tail -f logs/nanoclaw.log | grep -i -E "voice|transcri|whisper" -``` - -Look for: -- `Transcribed voice message` — successful transcription -- `whisper.cpp transcription failed` — check model path, ffmpeg, or PATH - -## Configuration - -Environment variables (optional, set in `.env`): - -| Variable | Default | Description | -|----------|---------|-------------| -| `WHISPER_BIN` | `whisper-cli` | Path to whisper.cpp binary | -| `WHISPER_MODEL` | `data/models/ggml-base.bin` | Path to GGML model file | - -## Troubleshooting - -**"whisper.cpp transcription failed"**: Ensure both `whisper-cli` and `ffmpeg` are in PATH. The launchd service uses a restricted PATH — see Phase 3 above. Test manually: -```bash -ffmpeg -f lavfi -i anullsrc=r=16000:cl=mono -t 1 -f wav /tmp/test.wav -y -whisper-cli -m data/models/ggml-base.bin -f /tmp/test.wav --no-timestamps -nt -``` - -**Transcription works in dev but not as service**: The launchd plist PATH likely doesn't include `/opt/homebrew/bin`. See "Ensure launchd PATH includes Homebrew" in Phase 3. - -**Slow transcription**: The base model processes ~30s of audio in <1s on M1+. If slower, check CPU usage — another process may be competing. - -**Wrong language**: whisper.cpp auto-detects language. To force a language, you can set `WHISPER_LANG` and modify `src/transcription.ts` to pass `-l $WHISPER_LANG`. From 212fc1f1b5c054c95be2ef4dd323a600f822ab37 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Fri, 17 Apr 2026 15:28:44 +0300 Subject: [PATCH 56/95] docs(add-emacs): rewrite skill for copy-from-channels-branch pattern Ports the emacs channel skill to match the other channel skills: copy src/channels/emacs.ts + emacs/nanoclaw.el from the channels branch, append the self-registration import, enable via EMACS_ENABLED, and wire through the register setup step. Documents the v2 entity model (single messaging group, platform_id="default") and drops the v1 auto-register / symlink behavior that the old adapter did. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/add-emacs/SKILL.md | 261 +++++++++++++++--------------- 1 file changed, 134 insertions(+), 127 deletions(-) diff --git a/.claude/skills/add-emacs/SKILL.md b/.claude/skills/add-emacs/SKILL.md index 8a4100e92..82a5098a3 100644 --- a/.claude/skills/add-emacs/SKILL.md +++ b/.claude/skills/add-emacs/SKILL.md @@ -1,12 +1,11 @@ --- name: add-emacs -description: Add Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw from within Emacs (Doom, Spacemacs, or vanilla). Uses a local HTTP bridge — no bot token or external service needed. +description: Add Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw from within Emacs (Doom, Spacemacs, or vanilla). Local HTTP bridge — no bot token or external service needed. --- # Add Emacs Channel -This skill adds Emacs support to NanoClaw, then walks through interactive setup. -Works with Doom Emacs, Spacemacs, and vanilla Emacs 27.1+. +Adds Emacs support via a local HTTP bridge. Works with Doom Emacs, Spacemacs, and vanilla Emacs 27.1+. ## What you can do with this @@ -15,95 +14,99 @@ Works with Doom Emacs, Spacemacs, and vanilla Emacs 27.1+. - **Meeting notes** — send an org agenda entry; get a summary or action item list back as a child node - **Draft writing** — send org prose; receive revisions or continuations in place - **Research capture** — ask a question directly in your org notes; the answer lands exactly where you need it -- **Schedule tasks** — ask Andy to set a reminder or create a scheduled NanoClaw task (e.g. "remind me tomorrow to review the PR") -## Phase 1: Pre-flight +## Install -### Check if already applied +NanoClaw doesn't ship channels in trunk. This skill copies the Emacs adapter and the Lisp client in from the `channels` branch. Native HTTP bridge — no Chat SDK, no adapter package. -Check if `src/channels/emacs.ts` exists: +### Pre-flight (idempotent) + +Skip to **Enable** if all of these are already in place: + +- `src/channels/emacs.ts` exists +- `emacs/nanoclaw.el` exists +- `src/channels/index.ts` contains `import './emacs.js';` + +Otherwise continue. Every step below is safe to re-run. + +### 1. Fetch the channels branch ```bash -test -f src/channels/emacs.ts && echo "already applied" || echo "not applied" +git fetch origin channels ``` -If it exists, skip to Phase 3 (Setup). The code changes are already in place. - -## Phase 2: Apply Code Changes - -### Ensure the upstream remote +### 2. Copy the adapter and Lisp client ```bash -git remote -v +mkdir -p emacs +git show origin/channels:src/channels/emacs.ts > src/channels/emacs.ts +git show origin/channels:src/channels/emacs.test.ts > src/channels/emacs.test.ts +git show origin/channels:emacs/nanoclaw.el > emacs/nanoclaw.el ``` -If an `upstream` remote pointing to `https://github.com/qwibitai/nanoclaw.git` is missing, -add it: +### 3. Append the self-registration import -```bash -git remote add upstream https://github.com/qwibitai/nanoclaw.git +Append to `src/channels/index.ts` (skip if the line is already present): + +```typescript +import './emacs.js'; ``` -### Merge the skill branch - -```bash -git fetch upstream skill/emacs -git merge upstream/skill/emacs -``` - -If there are merge conflicts on `pnpm-lock.yaml`, resolve them by accepting the incoming -version and continuing: - -```bash -git checkout --theirs pnpm-lock.yaml -git add pnpm-lock.yaml -git merge --continue -``` - -For any other conflict, read the conflicted file and reconcile both sides manually. - -This adds: -- `src/channels/emacs.ts` — `EmacsBridgeChannel` HTTP server (port 8766) -- `src/channels/emacs.test.ts` — unit tests -- `emacs/nanoclaw.el` — Emacs Lisp package (`nanoclaw-chat`, `nanoclaw-org-send`) -- `import './emacs.js'` appended to `src/channels/index.ts` - -If the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides. - -### Validate code changes +### 4. Build ```bash pnpm run build -pnpm exec vitest run src/channels/emacs.test.ts ``` -Build must be clean and tests must pass before proceeding. +No npm package to install — the adapter uses only Node builtins (`http`). -## Phase 3: Setup +## Enable -### Configure environment (optional) - -The channel works out of the box with defaults. Add to `.env` only if you need non-defaults: +The adapter is gated by `EMACS_ENABLED` so the HTTP port isn't opened on hosts that aren't running Emacs. Add to `.env`: ```bash -EMACS_CHANNEL_PORT=8766 # default — change if 8766 is already in use -EMACS_AUTH_TOKEN= # optional — locks the endpoint to Emacs only +EMACS_ENABLED=true +EMACS_CHANNEL_PORT=8766 # optional — change only if 8766 is taken +EMACS_AUTH_TOKEN= # optional — set to a random string to lock the endpoint +EMACS_PLATFORM_ID=default # optional — only change if you want a non-default chat id ``` -If you change or add values, sync to the container environment: +Generate an auth token (recommended even on single-user machines — prevents other local processes from poking the endpoint): ```bash -mkdir -p data/env && cp .env data/env/env +node -e "console.log(require('crypto').randomBytes(16).toString('hex'))" ``` -### Configure Emacs +## Wire the channel -The `nanoclaw.el` package requires only Emacs 27.1+ built-in libraries (`url`, `json`, `org`) — no package manager setup needed. +Emacs is a single-user, single-chat channel. One host = one messaging group with `platform_id = "default"`. + +### If this is your first agent group + +Run `/init-first-agent` — pick **Emacs** as the channel, use any short handle as the "user id" (e.g. your OS username), and the skill will create the agent group, wire the channel, and write a welcome message that the agent delivers back to your Emacs buffer. + +### Otherwise — wire to an existing agent group + +Run the `register` step directly. The `EMACS_PLATFORM_ID` (default `default`) becomes the messaging group's platform id: + +```bash +pnpm exec tsx setup/index.ts --step register -- \ + --platform-id "default" --name "Emacs" \ + --folder "" --channel "emacs" \ + --session-mode "agent-shared" \ + --assistant-name "" +``` + +`agent-shared` puts Emacs messages in the same session as any other channel wired to the same agent group — so a conversation you started in Telegram continues in Emacs. Use `shared` to keep an independent Emacs thread with the same workspace, or a new `--folder` for a dedicated Emacs-only agent. + +## Configure Emacs + +`nanoclaw.el` needs only Emacs 27.1+ builtins (`url`, `json`, `org`) — no package manager. AskUserQuestion: Which Emacs distribution are you using? -- **Doom Emacs** - config.el with map! keybindings -- **Spacemacs** - dotspacemacs/user-config in ~/.spacemacs -- **Vanilla Emacs / other** - init.el with global-set-key +- **Doom Emacs** — `config.el` with `map!` keybindings +- **Spacemacs** — `dotspacemacs/user-config` in `~/.spacemacs` +- **Vanilla Emacs / other** — `init.el` with `global-set-key` **Doom Emacs** — add to `~/.config/doom/config.el` (or `~/.doom.d/config.el`): @@ -117,7 +120,7 @@ AskUserQuestion: Which Emacs distribution are you using? :desc "Send org" "o" #'nanoclaw-org-send) ``` -Then reload: `M-x doom/reload` +Reload: `M-x doom/reload` **Spacemacs** — add to `dotspacemacs/user-config` in `~/.spacemacs`: @@ -129,9 +132,9 @@ Then reload: `M-x doom/reload` (spacemacs/set-leader-keys "aNo" #'nanoclaw-org-send) ``` -Then reload: `M-x dotspacemacs/sync-configuration-layers` or restart Emacs. +Reload: `M-x dotspacemacs/sync-configuration-layers` or restart Emacs. -**Vanilla Emacs** — add to `~/.emacs.d/init.el` (or `~/.emacs`): +**Vanilla Emacs** — add to `~/.emacs.d/init.el`: ```elisp ;; NanoClaw — personal AI assistant channel @@ -141,61 +144,75 @@ Then reload: `M-x dotspacemacs/sync-configuration-layers` or restart Emacs. (global-set-key (kbd "C-c n o") #'nanoclaw-org-send) ``` -Then reload: `M-x eval-buffer` or restart Emacs. +Reload: `M-x eval-buffer` or restart Emacs. -If `EMACS_AUTH_TOKEN` was set, also add (any distribution): +Replace `~/src/nanoclaw/emacs/nanoclaw.el` with your actual NanoClaw checkout path. + +If `EMACS_AUTH_TOKEN` is set, also add (any distribution): ```elisp (setq nanoclaw-auth-token "") ``` -If `EMACS_CHANNEL_PORT` was changed from the default, also add: +If you changed `EMACS_CHANNEL_PORT` from the default: ```elisp (setq nanoclaw-port ) ``` -### Restart NanoClaw +## Restart NanoClaw ```bash pnpm run build -launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS -# Linux: systemctl --user restart nanoclaw +launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS +# systemctl --user restart nanoclaw # Linux ``` -## Phase 4: Verify +## Verify -### Test the HTTP endpoint +### HTTP endpoint ```bash -curl -s "http://localhost:8766/api/messages?since=0" +curl -s http://localhost:8766/api/messages?since=0 ``` -Expected: `{"messages":[]}` - -If you set `EMACS_AUTH_TOKEN`: +Expected: `{"messages":[]}`. With an auth token: ```bash -curl -s -H "Authorization: Bearer " "http://localhost:8766/api/messages?since=0" +curl -s -H "Authorization: Bearer " http://localhost:8766/api/messages?since=0 ``` -### Test from Emacs +### From Emacs Tell the user: > 1. Open the chat buffer with your keybinding (`SPC N c`, `SPC a N c`, or `C-c n c`) -> 2. Type a message and press `RET` -> 3. A response from Andy should appear within a few seconds +> 2. Type a message and press `C-c C-c` to send (RET inserts newlines) +> 3. A response should appear within a few seconds > > For org-mode: open any `.org` file, position the cursor on a heading, and use `SPC N o` / `SPC a N o` / `C-c n o` -### Check logs if needed +### Log line -```bash -tail -f logs/nanoclaw.log -``` +`tail -f logs/nanoclaw.log` should show `Emacs channel listening` at startup. -Look for `Emacs channel listening` at startup and `Emacs message received` when a message is sent. +## Channel Info + +- **type**: `emacs` +- **terminology**: Single local buffer. There are no "groups" or separate chats — one host = one chat, addressed by a `platform_id` string (default `default`). +- **how-to-find-id**: The platform id is whatever you set in `EMACS_PLATFORM_ID` (default `default`). User handles are arbitrary; your OS username or first name is fine (e.g. `emacs:`). +- **supports-threads**: no +- **typical-use**: Single developer talking to the assistant from within Emacs, alongside whatever other channel they use (Slack, Telegram, Discord). +- **default-isolation**: Same agent group as the primary DM, with `session-mode = agent-shared` so a conversation started elsewhere continues in Emacs. Pick a separate folder only if you specifically want an Emacs-only persona. + +### Features + +- Interactive chat buffer (`nanoclaw-chat`) with markdown → org-mode rendering +- Org integration (`nanoclaw-org-send`) — sends the current subtree or region; reply lands as a child heading +- Optional bearer-token auth for the local endpoint +- Single-user: the adapter exposes exactly one messaging group per host + +Not applicable (design): multi-user channels, threads, cold DM initiation, typing indicators, attachments. ## Troubleshooting @@ -205,66 +222,53 @@ Look for `Emacs channel listening` at startup and `Emacs message received` when Error: listen EADDRINUSE: address already in use :::8766 ``` -Either a stale NanoClaw process is running, or 8766 is taken by another app. - -Find and kill the stale process: +Either a stale NanoClaw is running or another app has the port. Kill stale process or change port: ```bash lsof -ti :8766 | xargs kill -9 +# or set EMACS_CHANNEL_PORT in .env and mirror in Emacs config (nanoclaw-port) ``` -Or change the port in `.env` (`EMACS_CHANNEL_PORT=8767`) and update `nanoclaw-port` in Emacs config. +### Adapter not starting + +If `grep "Emacs channel listening" logs/nanoclaw.log` returns nothing, check that `EMACS_ENABLED=true` is in `.env` and that the adapter import is present: + +```bash +grep -q '^EMACS_ENABLED=true' .env && echo "enabled" || echo "not enabled" +grep -q "import './emacs.js'" src/channels/index.ts && echo "imported" || echo "not imported" +``` ### No response from agent -Check: -1. NanoClaw is running: `launchctl list | grep nanoclaw` (macOS) or `systemctl --user status nanoclaw` (Linux) -2. Emacs group is registered: `sqlite3 store/messages.db "SELECT * FROM registered_groups WHERE jid = 'emacs:default'"` -3. Logs show activity: `tail -50 logs/nanoclaw.log` +1. NanoClaw running: `launchctl list | grep nanoclaw` (macOS) / `systemctl --user status nanoclaw` (Linux) +2. Messaging group wired: `sqlite3 data/v2.db "SELECT mg.platform_id, ag.folder FROM messaging_groups mg JOIN messaging_group_agents mga ON mg.id = mga.messaging_group_id JOIN agent_groups ag ON ag.id = mga.agent_group_id WHERE mg.channel_type = 'emacs'"` +3. Logs show inbound: `grep 'channel_type=emacs\|Emacs' logs/nanoclaw.log | tail -20` -If the group is not registered, it will be created automatically on the next NanoClaw restart. +If no messaging group row exists, run the `register` command above. ### Auth token mismatch (401 Unauthorized) -Verify the token in Emacs matches `.env`: - ```elisp -;; M-x describe-variable RET nanoclaw-auth-token RET +M-x describe-variable RET nanoclaw-auth-token RET ``` -Must exactly match `EMACS_AUTH_TOKEN` in `.env`. +Must match `EMACS_AUTH_TOKEN` in `.env`. If you didn't set one server-side, clear it in Emacs too: + +```elisp +(setq nanoclaw-auth-token nil) +``` ### nanoclaw.el not loading -Check the path is correct: - ```bash ls ~/src/nanoclaw/emacs/nanoclaw.el ``` If NanoClaw is cloned elsewhere, update the `load`/`load-file` path in your Emacs config. -## After Setup - -If running `pnpm run dev` while the service is active: - -```bash -# macOS: -launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist -pnpm run dev -# When done testing: -launchctl load ~/Library/LaunchAgents/com.nanoclaw.plist - -# Linux: -# systemctl --user stop nanoclaw -# pnpm run dev -# systemctl --user start nanoclaw -``` - ## Agent Formatting -The Emacs bridge converts markdown → org-mode automatically. Agents should -output standard markdown — **not** org-mode syntax. The conversion handles: +The Emacs bridge converts markdown → org-mode automatically. Agents should output standard markdown, **not** org-mode syntax: | Markdown | Org-mode | |----------|----------| @@ -274,16 +278,19 @@ output standard markdown — **not** org-mode syntax. The conversion handles: | `` `code` `` | `~code~` | | ` ```lang ` | `#+begin_src lang` | -If an agent outputs org-mode directly, bold/italic/etc. will be double-converted -and render incorrectly. +If an agent outputs org-mode directly, markers get double-converted and render incorrectly. ## Removal -To remove the Emacs channel: +```bash +rm src/channels/emacs.ts src/channels/emacs.test.ts emacs/nanoclaw.el +# Remove the `import './emacs.js';` line from src/channels/index.ts +# Remove EMACS_* lines from .env +pnpm run build +launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS +# systemctl --user restart nanoclaw # Linux -1. Delete `src/channels/emacs.ts`, `src/channels/emacs.test.ts`, and `emacs/nanoclaw.el` -2. Remove `import './emacs.js'` from `src/channels/index.ts` -3. Remove the NanoClaw block from your Emacs config file -4. Remove Emacs registration from SQLite: `sqlite3 store/messages.db "DELETE FROM registered_groups WHERE jid = 'emacs:default'"` -5. Remove `EMACS_CHANNEL_PORT` and `EMACS_AUTH_TOKEN` from `.env` if set -6. Rebuild: `pnpm run build && launchctl kickstart -k gui/$(id -u)/com.nanoclaw` (macOS) or `pnpm run build && systemctl --user restart nanoclaw` (Linux) \ No newline at end of file +# Remove the NanoClaw block from your Emacs config +# Optionally clean up the messaging group: +sqlite3 data/v2.db "DELETE FROM messaging_group_agents WHERE messaging_group_id IN (SELECT id FROM messaging_groups WHERE channel_type='emacs'); DELETE FROM messaging_groups WHERE channel_type='emacs';" +``` From d8d61d3695196a53969eaaf47a2f6829bc4ed1c3 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 10:16:13 +0300 Subject: [PATCH 57/95] fix: Teams user-id prefix + defer cli:local owner grant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit parseUserId now falls back to user.kind when the id prefix isn't a registered adapter — Teams uses `29:` rather than `teams:`, so the literal prefix wouldn't resolve the channel adapter for cold DMs. init-cli-agent no longer claims the first-owner slot on `cli:local`. The CLI identity is scratch; owner promotion belongs to init-first-agent once the real channel user is wired. --- scripts/init-cli-agent.ts | 15 +++------------ src/modules/permissions/user-dm.ts | 15 +++++++++------ 2 files changed, 12 insertions(+), 18 deletions(-) diff --git a/scripts/init-cli-agent.ts b/scripts/init-cli-agent.ts index ccd9387a9..4a56827bc 100644 --- a/scripts/init-cli-agent.ts +++ b/scripts/init-cli-agent.ts @@ -30,7 +30,6 @@ import { } from '../src/db/messaging-groups.js'; import { runMigrations } from '../src/db/migrations/index.js'; import { normalizeName } from '../src/modules/agent-to-agent/db/agent-destinations.js'; -import { grantRole, hasAnyOwner } from '../src/modules/permissions/db/user-roles.js'; import { upsertUser } from '../src/modules/permissions/db/users.js'; import { initGroupFilesystem } from '../src/group-init.js'; import type { AgentGroup, MessagingGroup } from '../src/types.js'; @@ -91,17 +90,9 @@ async function main(): Promise { created_at: now, }); - let promotedToOwner = false; - if (!hasAnyOwner()) { - grantRole({ - user_id: CLI_SYNTHETIC_USER_ID, - role: 'owner', - agent_group_id: null, - granted_by: null, - granted_at: now, - }); - promotedToOwner = true; - } + // Owner grant deferred to init-first-agent when the real channel user is + // wired — cli:local is a scratch identity, not the operator. + const promotedToOwner = false; // 2. Agent group + filesystem. const folder = `cli-with-${normalizeName(args.displayName)}`; diff --git a/src/modules/permissions/user-dm.ts b/src/modules/permissions/user-dm.ts index ef9566ad8..a5274d19f 100644 --- a/src/modules/permissions/user-dm.ts +++ b/src/modules/permissions/user-dm.ts @@ -136,11 +136,14 @@ async function resolveDmPlatformId(channelType: string, handle: string): Promise function parseUserId(user: User): { channelType: string; handle: string } | { channelType: null; handle: null } { const idx = user.id.indexOf(':'); if (idx < 0) return { channelType: null, handle: null }; - const channelType = user.id.slice(0, idx); + const prefix = user.id.slice(0, idx); const handle = user.id.slice(idx + 1); - if (!channelType || !handle) return { channelType: null, handle: null }; - // The `kind` on users mirrors the channel_type prefix in our current - // scheme. Pull it from `user.kind` if we ever decouple them later, but - // today the id prefix is authoritative. - return { channelType, handle }; + if (!prefix || !handle) return { channelType: null, handle: null }; + // Teams user IDs use a `29:` prefix, not `teams:`. When the id prefix + // isn't a registered adapter, fall back to user.kind and treat the full + // id as the handle. + if (!getChannelAdapter(prefix) && user.kind && getChannelAdapter(user.kind)) { + return { channelType: user.kind, handle: user.id }; + } + return { channelType: prefix, handle }; } From 9fe529984a646eb71c82e29a0a42c0959f65eb39 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Tue, 21 Apr 2026 08:50:59 +0000 Subject: [PATCH 58/95] fix(init-first-agent): seed welcome via inbound.db; drop --no-cli-bonus MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The welcome DM used to be handed to the running service over the CLI admin socket, which stamped `cli:local` as the sender. On a strict messaging group (any fresh DM wired by init-first-agent), that tripped the unknown-sender approval gate — the operator's own bootstrap script ended up requesting its own approval. Fix by writing the welcome directly into the session's inbound.db with a `System` sender; the running service's host-sweep wakes the container on its next pass. Also drop `--no-cli-bonus`. Now that init-cli-agent always wires cli/local to the scratch CLI agent, every caller of init-first-agent had to pass --no-cli-bonus to avoid double-wiring; the flag has become mandatory, so it's just removed. The cli-bonus branch goes with it. Skill docs updated in lockstep. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/init-first-agent/SKILL.md | 4 +- .claude/skills/new-setup-2/SKILL.md | 5 +- scripts/init-first-agent.ts | 157 ++++++----------------- 3 files changed, 45 insertions(+), 121 deletions(-) diff --git a/.claude/skills/init-first-agent/SKILL.md b/.claude/skills/init-first-agent/SKILL.md index 6b110d37f..68eab8760 100644 --- a/.claude/skills/init-first-agent/SKILL.md +++ b/.claude/skills/init-first-agent/SKILL.md @@ -87,13 +87,13 @@ The script: 2. Creates the `agent_groups` row and calls `initGroupFilesystem` at `groups/dm-with-/`. 3. Reuses or creates the DM `messaging_groups` row. 4. Wires them via `messaging_group_agents` (which auto-creates the companion `agent_destinations` row). -5. Hands the welcome message to the running service via its CLI socket (`data/cli.sock`), targeting the DM messaging group. The service routes it into the DM session, which wakes the container synchronously. If the socket isn't reachable (service down), falls back to a direct `inbound.db` write that the next host sweep picks up. +5. Seeds the welcome message directly into the DM session's `inbound.db` (sender tagged `System`). The running service's host-sweep picks it up on the next pass and wakes the container through the normal path — no CLI-socket hand-off, no `cli:local` identity on the new agent's permission surface. Show the script's output to the user. ## 5. Verify -The welcome DM is queued synchronously; the only wait is container cold-start (~60s on first launch) before the agent processes the message and the reply flows through `outbound.db` to the channel. +The welcome is written to `inbound.db` immediately; the wait is host-sweep pickup (≤60s) plus container cold-start (~60s on first launch) before the agent processes the message and the reply flows through `outbound.db` to the channel. Do not tail the log or poll in a sleep loop. Ask the user in plain text: diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md index 1b98443aa..8d75cd3f7 100644 --- a/.claude/skills/new-setup-2/SKILL.md +++ b/.claude/skills/new-setup-2/SKILL.md @@ -92,7 +92,7 @@ When the user picks one: ``` 2. **Capture platform IDs.** After the `/add-` skill finishes (or after inline credentials for Telegram), you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent ` directly and follow its `PAIR_TELEGRAM_ISSUED`/`PAIR_TELEGRAM STATUS=success` blocks — `PLATFORM_ID` and `ADMIN_USER_ID` land in the success block. -3. **Wire the agent.** Run `init-first-agent.ts` in DM mode with `--no-cli-bonus` (this keeps the new agent off the CLI messaging group so the pre-existing throwaway agent still owns CLI routing cleanly): +3. **Wire the agent.** Run `init-first-agent.ts` in DM mode: ``` pnpm exec tsx scripts/init-first-agent.ts \ @@ -100,8 +100,7 @@ When the user picks one: --user-id "" \ --platform-id "" \ --display-name "" \ - --agent-name "" \ - --no-cli-bonus + --agent-name "" ``` 4. **Announce.** On success, emit the encouragement line verbatim: diff --git a/scripts/init-first-agent.ts b/scripts/init-first-agent.ts index 29ca6d444..9dc8b6de4 100644 --- a/scripts/init-first-agent.ts +++ b/scripts/init-first-agent.ts @@ -1,24 +1,25 @@ /** * Init the first (or Nth) NanoClaw v2 agent for a DM channel. * - * Wires a real DM channel (discord, telegram, etc.) to a new agent group - * (and the local CLI channel as a convenience bonus), then hands a welcome - * message to the running service via its CLI socket. The service routes - * that message into the DM session, which wakes the container synchronously — - * the agent processes the welcome and DMs the operator through the normal - * delivery path. + * Wires a real DM channel (discord, telegram, etc.) to a new agent group, + * then seeds a welcome message directly into the session's inbound DB. The + * running service's host-sweep picks it up on its next pass (within + * SWEEP_INTERVAL_MS) and wakes the container through the normal path; the + * agent introduces itself via the channel. * - * For the CLI-only scratch agent used during `/new-setup`, see - * `scripts/init-cli-agent.ts` — that's a distinct flow and doesn't run - * through here. + * CLI channel wiring is NOT touched here — `scripts/init-cli-agent.ts` owns + * the cli/local messaging group and its scratch agent. Keeping the two + * scripts disjoint means no `cli:local` identity ever appears on the new + * agent's permission surface, so the unknown-sender approval card that used + * to fire when the welcome was queued via the CLI admin socket no longer + * happens. * * Creates/reuses: user, owner grant (if none), agent group + filesystem, - * messaging group(s), wiring. + * messaging group, wiring, session, welcome message. * - * Runs alongside the service (WAL-mode sqlite + CLI socket IPC) — does NOT - * initialize channel adapters, so there's no Gateway conflict. Requires - * the service to be running: the welcome hand-off goes over the CLI socket - * and fails loudly if the service isn't up. + * Runs alongside the service (WAL-mode sqlite) — does NOT initialize channel + * adapters, so there's no Gateway conflict. No IPC to the service is needed; + * the sweep is the sole hand-off. * * Usage: * pnpm exec tsx scripts/init-first-agent.ts \ @@ -27,13 +28,11 @@ * --platform-id discord:@me:1491573333382523708 \ * --display-name "Gavriel" \ * [--agent-name "Andy"] \ - * [--welcome "System instruction: ..."] \ - * [--no-cli-bonus] + * [--welcome "System instruction: ..."] * * For direct-addressable channels (telegram, whatsapp, etc.), --platform-id * is typically the same as the handle in --user-id, with the channel prefix. */ -import net from 'net'; import path from 'path'; import { DATA_DIR } from '../src/config.js'; @@ -50,10 +49,10 @@ import { normalizeName } from '../src/modules/agent-to-agent/db/agent-destinatio import { grantRole, hasAnyOwner } from '../src/modules/permissions/db/user-roles.js'; import { upsertUser } from '../src/modules/permissions/db/users.js'; import { initGroupFilesystem } from '../src/group-init.js'; +import { resolveSession, writeSessionMessage } from '../src/session-manager.js'; import type { AgentGroup, MessagingGroup } from '../src/types.js'; interface Args { - noCliBonus: boolean; channel: string; userId: string; platformId: string; @@ -65,18 +64,12 @@ interface Args { const DEFAULT_WELCOME = 'System instruction: run /welcome to introduce yourself to the user on this new channel.'; -const CLI_CHANNEL = 'cli'; -const CLI_PLATFORM_ID = 'local'; - function parseArgs(argv: string[]): Args { - const out: Partial = { noCliBonus: false }; + const out: Partial = {}; for (let i = 0; i < argv.length; i++) { const key = argv[i]; const val = argv[i + 1]; switch (key) { - case '--no-cli-bonus': - out.noCliBonus = true; - break; case '--channel': out.channel = (val ?? '').toLowerCase(); i++; @@ -115,7 +108,6 @@ function parseArgs(argv: string[]): Args { } return { - noCliBonus: out.noCliBonus ?? false, channel: out.channel!, userId: out.userId!, platformId: out.platformId!, @@ -137,24 +129,6 @@ function generateId(prefix: string): string { return `${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; } -function ensureCliMessagingGroup(now: string): MessagingGroup { - let cliMg = getMessagingGroupByPlatform(CLI_CHANNEL, CLI_PLATFORM_ID); - if (cliMg) return cliMg; - - cliMg = { - id: generateId('mg'), - channel_type: CLI_CHANNEL, - platform_id: CLI_PLATFORM_ID, - name: 'Local CLI', - is_group: 0, - unknown_sender_policy: 'public', - created_at: now, - }; - createMessagingGroup(cliMg); - console.log(`Created CLI messaging group: ${cliMg.id}`); - return cliMg; -} - function wireIfMissing(mg: MessagingGroup, ag: AgentGroup, now: string, label: string): void { const existing = getMessagingGroupAgentByPair(mg.id, ag.id); if (existing) { @@ -165,9 +139,8 @@ function wireIfMissing(mg: MessagingGroup, ag: AgentGroup, now: string, label: s id: generateId('mga'), messaging_group_id: mg.id, agent_group_id: ag.id, - // DM / CLI (is_group=0) default to "respond to everything" via a '.' regex. - // Group chats default to mention-only; admins can upgrade to mention-sticky - // via /manage-channels once the agent is in use. + // DMs default to "respond to everything" via a '.' regex. Group chats + // default to mention-only; admins can upgrade via /manage-channels. engage_mode: mg.is_group === 0 ? 'pattern' : 'mention', engage_pattern: mg.is_group === 0 ? '.' : null, sender_scope: 'all', @@ -252,88 +225,40 @@ async function main(): Promise { console.log(`Reusing messaging group: ${dmMg.id} (${platformId})`); } - // 4. Wire DM (auto-creates companion agent_destinations row) and, - // unless suppressed, also wire the CLI channel so `pnpm run chat` works - // against the new agent immediately. `/new-setup-2` sets --no-cli-bonus - // so the scratch CLI agent from `/new-setup` keeps owning CLI routing. + // 4. Wire DM. wireIfMissing(dmMg, ag, now, 'dm'); - if (!args.noCliBonus) { - const cliMg = ensureCliMessagingGroup(now); - wireIfMissing(cliMg, ag, now, 'cli-bonus'); - } - // 5. Welcome delivery over the CLI socket. Router picks up the line, - // writes the message into the DM session's inbound.db, and wakes the - // container synchronously — no sweep wait. - await sendWelcomeViaCliSocket(dmMg, args.welcome); + // 5. Seed the welcome directly into the session's inbound.db. The running + // service's sweep will observe trigger=1 and wake the container on its next + // pass — no IPC, no CLI socket, no `cli:local` sender in the router path. + seedWelcome(ag.id, dmMg, args.welcome); console.log(''); console.log('Init complete.'); console.log(` owner: ${userId}${promotedToOwner ? ' (promoted on first owner)' : ''}`); console.log(` agent: ${ag.name} [${ag.id}] @ groups/${folder}`); console.log(` channel: ${args.channel} ${dmMg.platform_id}`); - if (!args.noCliBonus) { - console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``); - } console.log(''); - console.log('Welcome DM queued — the agent will greet you shortly.'); + console.log('Welcome seeded — the agent will greet you on the next sweep pass.'); } /** - * Hand the welcome to the running service via its CLI Unix socket. The - * service's CLI adapter receives `{text, to}`, builds an InboundEvent - * targeting the DM messaging group, and calls routeInbound(). Router writes - * the message into inbound.db and wakes the container synchronously. - * - * Throws if the socket isn't reachable — this script requires the service - * to be running. + * Write the welcome as a due inbound message on a shared session for the + * new agent group + messaging group pair. Sender is tagged "System" — the + * welcome carries no real user identity and never crosses the router's + * sender-approval gate. */ -async function sendWelcomeViaCliSocket(dmMg: MessagingGroup, welcome: string): Promise { - const sockPath = path.join(DATA_DIR, 'cli.sock'); - - await new Promise((resolve, reject) => { - const socket = net.connect(sockPath); - let settled = false; - - const settle = (err: Error | null) => { - if (settled) return; - settled = true; - try { - socket.end(); - } catch { - /* noop */ - } - if (err) reject(err); - else resolve(); - }; - - socket.once('error', (err) => - settle( - new Error( - `CLI socket at ${sockPath} not reachable: ${err.message}. Is the NanoClaw service running?`, - ), - ), - ); - socket.once('connect', () => { - const payload = - JSON.stringify({ - text: welcome, - to: { - channelType: dmMg.channel_type, - platformId: dmMg.platform_id, - threadId: null, - }, - }) + '\n'; - socket.write(payload, (err) => { - if (err) { - settle(err); - return; - } - // Brief flush delay so the router picks up the line before we close. - // Router handles it synchronously once read, so 50ms is plenty. - setTimeout(() => settle(null), 50); - }); - }); +function seedWelcome(agentGroupId: string, mg: MessagingGroup, welcome: string): void { + const { session } = resolveSession(agentGroupId, mg.id, null, 'shared'); + writeSessionMessage(agentGroupId, session.id, { + id: generateId('welcome'), + kind: 'chat', + timestamp: new Date().toISOString(), + channelType: mg.channel_type, + platformId: mg.platform_id, + threadId: null, + content: JSON.stringify({ text: welcome, sender: 'System' }), + trigger: 1, }); } From 483969a1948469daf3141afe0c6a3bffdc430faa Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Tue, 21 Apr 2026 10:37:06 +0000 Subject: [PATCH 59/95] refactor(skills): merge /new-setup-2 into unified /new-setup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Collapses the two-phase setup into a single linear skill: steps 1-6 (prereqs through end-to-end CLI ping) run straight through, steps 7-13 (naming, timezone, channel wiring, mounts, QoL, done) are skippable. Drops the "chat now vs. continue" branch point — after the ping the flow emits "Test Agent success, proceeding with setup" and continues directly into the naming questions. Also updates stale `/new-setup-2` header comments in setup/install-*.sh. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 154 --------------------------- .claude/skills/new-setup/SKILL.md | 155 +++++++++++++++++++++++----- setup/install-discord.sh | 2 +- setup/install-gchat.sh | 2 +- setup/install-github.sh | 2 +- setup/install-imessage.sh | 2 +- setup/install-linear.sh | 2 +- setup/install-matrix.sh | 2 +- setup/install-resend.sh | 2 +- setup/install-slack.sh | 2 +- setup/install-teams.sh | 2 +- setup/install-telegram.sh | 2 +- setup/install-webex.sh | 2 +- setup/install-whatsapp-cloud.sh | 2 +- setup/install-whatsapp.sh | 2 +- 15 files changed, 145 insertions(+), 190 deletions(-) delete mode 100644 .claude/skills/new-setup-2/SKILL.md diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md deleted file mode 100644 index 8d75cd3f7..000000000 --- a/.claude/skills/new-setup-2/SKILL.md +++ /dev/null @@ -1,154 +0,0 @@ ---- -name: new-setup-2 -description: Follow-on to /new-setup. Captures the operator and agent names, wires a real messaging channel, and adds quality-of-life extras. Linear rollthrough; every step is skippable. Invoked when the user picks "continue setup" at the end of /new-setup. -allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm exec tsx scripts/init-first-agent.ts:*) Bash(tail:*) Bash(head:*) Bash(grep:*) ---- - -# NanoClaw phase-2 setup - -Runs after `/new-setup`. At this point the host is running and a throwaway CLI-only agent exists (used during /new-setup for the end-to-end ping check — inferred name, not user-facing). This flow creates the **real** agent and wires it to a messaging channel. - -**Linear — one step at a time.** Every step is skippable: if the user says "skip", "not now", "later", or similar, move on without complaint. If they say they're done at any point, stop cleanly — don't push the remaining steps. - -Before each step, narrate in your own words what's about to happen — one short, friendly sentence, no jargon. Match the tone of `/new-setup`. - -## Current state - -!`bash setup/probe.sh` - -Parse the probe block above for `INFERRED_DISPLAY_NAME` and `PLATFORM` — referenced below. - -## Steps - -### 1. What should the agent call you? - -Plain-prose ask (do **not** use `AskUserQuestion`): - -> What should your agent call you? (Default: ``) - -Capture the answer into a local variable `OPERATOR_NAME`. **Don't persist yet** — this value is consumed by step 3's channel wiring. If the user skips or confirms the default, set `OPERATOR_NAME = INFERRED_DISPLAY_NAME`. - -### 2. What's your agent's name? - -Plain-prose ask: - -> What would you like to call your agent? (Default: ``) - -Capture as `AGENT_NAME`. If skipped, set `AGENT_NAME = OPERATOR_NAME`. Nothing persisted yet. - -### 3. Timezone - -Run `pnpm exec tsx setup/index.ts --step timezone` and parse the status block. - -- **RESOLVED_TZ is `UTC` or `Etc/UTC`** — before leaving UTC in `.env`, confirm with `AskUserQuestion`: - - - **Question**: "Your system reports UTC as the timezone. Is that right, or are you somewhere else?" - - **Header**: "Timezone" - - **Options**: - 1. `Keep UTC` — "Leave timezone as UTC." - 2. `I'm somewhere else` — "I'll name the IANA zone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`) via Other." - - If they pick "I'm somewhere else" (or type an IANA zone via Other), re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` to overwrite `.env`. If they keep UTC or skip, leave UTC in place. - -- **NEEDS_USER_INPUT=true** — autodetection failed. Use `AskUserQuestion` with the same two options above (reword the question to "Autodetection failed — what timezone are you in?"), then re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` if they supply one. If they skip, move on. - -- Otherwise — timezone is already set; move on. - -### 4. Pick a messaging channel - -Print the list as a numbered plain-prose list (too many options for `AskUserQuestion`, which caps at 4). The user replies with a number or channel name. Preserve the numbering exactly: - -> Which messaging channel should I wire your agent to? -> -> 1. **WhatsApp (native)** — `/add-whatsapp` -> 2. **WhatsApp Cloud (Meta official)** — `/add-whatsapp-cloud` -> 3. **Telegram** — `/add-telegram` -> 4. **Slack** — `/add-slack` -> 5. **Discord** — `/add-discord` -> 6. **iMessage** — `/add-imessage` -> 7. **Teams** — `/add-teams` -> 8. **Matrix** — `/add-matrix` -> 9. **Google Chat** — `/add-gchat` -> 10. **Linear** — `/add-linear` -> 11. **GitHub** — `/add-github` -> 12. **Webex** — `/add-webex` -> 13. **Resend (email)** — `/add-resend` -> 14. **Emacs** — `/add-emacs` -> -> Or say "skip" to leave this for later. - -When the user picks one: - -1. **Install the adapter.** For **Telegram**, run `bash setup/install-telegram.sh` directly — it bundles the preflight + fetch + copy + register + `pnpm install` + build from `/add-telegram` into one idempotent call. Then handle Telegram credentials inline (below) — **do not** invoke `/add-telegram` afterward; its Credentials section would generate an unapprovable `grep && sed && rm` to write `.env`. For every other channel, invoke the matching `/add-` skill via the Skill tool; it copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels also run a pairing step as part of their flow. - - **Telegram credentials (inline):** - - Walk the user through BotFather: `/newbot` → pick name + username ending in `bot` → copy the token. - - Remind them: in `@BotFather` → `/mybots` → their bot → Bot Settings → Group Privacy → **Turn off** (only needed if the bot will live in groups; DM-only can skip). - - Persist the token and sync it to the container mount with the generic setter: - - ``` - pnpm exec tsx setup/index.ts --step set-env -- \ - --key TELEGRAM_BOT_TOKEN --value "" --sync-container - ``` - -2. **Capture platform IDs.** After the `/add-` skill finishes (or after inline credentials for Telegram), you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent ` directly and follow its `PAIR_TELEGRAM_ISSUED`/`PAIR_TELEGRAM STATUS=success` blocks — `PLATFORM_ID` and `ADMIN_USER_ID` land in the success block. -3. **Wire the agent.** Run `init-first-agent.ts` in DM mode: - - ``` - pnpm exec tsx scripts/init-first-agent.ts \ - --channel \ - --user-id "" \ - --platform-id "" \ - --display-name "" \ - --agent-name "" - ``` - -4. **Announce.** On success, emit the encouragement line verbatim: - - > Your agent is now available on {channel-name}, you can already start chatting — But I encourage you to continue and finish this setup, we're almost done! - - Substitute `{channel-name}` with the friendly name (e.g. "Telegram", "WhatsApp", "Slack"). - -If the user skipped, move on to step 5. - -### 5. Host directory access - -By default, agent containers can only touch their own workspace. If the user wants the agent to read or write files in specific host directories, those paths need to go on the mount allowlist. - -Use `AskUserQuestion`: - -- **Question**: "Want your agent to read or write files in any host directories (e.g. a code project, `~/Documents`)?" -- **Header**: "Host mounts" -- **Options**: - 1. `Keep isolated` — "Agent only touches its own workspace (Recommended)." - 2. `Add host paths` — "I'll name the directories to allowlist via Other." - -If they pick "Add host paths" (or name paths via Other), invoke `/manage-mounts` via the Skill tool to add them. If they keep it isolated or skip, move on. - -### 6. Quality of life - -Optional polish. Print the list; the user may pick zero, one, or several — invoke each chosen skill in sequence: - -> Want to add any of these? Pick any that sound useful — or skip: -> -> - `/add-dashboard` — browser dashboard showing agent activity -> - `/add-compact` — `/compact` slash command for managing long sessions -> - `/add-karpathy-llm-wiki` — persistent knowledge-base memory for the agent - -If the probe reports `PLATFORM=darwin`, also offer: - -> - `/add-macos-statusbar` — macOS menu bar indicator with Start/Stop/Restart controls - -Do **not** list `/add-macos-statusbar` on Linux. If the user skips everything, just move on. - -### 7. Done - -Short wrap-up: - -> Setup complete. You can chat with your agent on {channel-name} — or via CLI with `pnpm run chat `. - -Substitute `{channel-name}` with whatever was wired in step 4. If step 4 was skipped, drop the "on {channel-name} — or" clause entirely so the line just mentions the CLI form. - -## If anything fails - -Same rule as `/new-setup`: don't bypass errors to keep moving. Read `logs/setup.log` or `logs/nanoclaw.log`, diagnose, fix the underlying cause, re-run the failed step. diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index 02cef98ec..ef88c7519 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -1,14 +1,17 @@ --- name: new-setup -description: Shortest path from zero to a working two-way agent chat, for any user regardless of technical background — ends at a running NanoClaw instance with at least one CLI-reachable agent. -allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(bash setup/install-node.sh) Bash(bash setup/install-docker.sh) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm run chat) Bash(pnpm run chat:*) Bash(open -a Docker) Bash(sudo systemctl start docker) Bash(node --version) Bash(tail:*) Bash(head:*) Bash(grep:*) +description: End-to-end NanoClaw setup for any user regardless of technical background — from zero to a named agent reachable on a real messaging channel, with sensible defaults and every post-verification step skippable. +allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(bash setup/install-node.sh) Bash(bash setup/install-docker.sh) Bash(bash setup/install-telegram.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm exec tsx scripts/init-first-agent.ts:*) Bash(pnpm run chat) Bash(pnpm run chat:*) Bash(open -a Docker) Bash(sudo systemctl start docker) Bash(node --version) Bash(tail:*) Bash(head:*) Bash(grep:*) --- -# NanoClaw bare-minimum setup +# NanoClaw setup -Purpose of this skill is to take any user — technical or not — from zero to a two-way chat with an agent in the fewest steps possible. Done means a running NanoClaw instance with at least one agent reachable via the CLI channel. +Purpose of this skill is to take any user — technical or not — from zero to a named agent wired to a real messaging channel in the fewest steps possible. -Only run the steps strictly required for the NanoClaw process to start and respond to the user end-to-end. Everything else is deferred to post-setup skills. +The flow has two halves: + +- **Steps 1–6 — required.** Prerequisites, credential, service start, end-to-end ping. These run straight through. +- **Steps 7–12 — skippable.** Naming, channel wiring, QoL. Every step here is skippable: if the user says "skip", "not now", "later", or similar, move on without complaint. If they say they're done at any point, stop cleanly — don't push the remaining steps. Before each step, narrate to the user in your own words what's about to happen — one short, friendly sentence, no jargon. Don't read a scripted line; use the step context below to speak naturally. @@ -109,13 +112,13 @@ Start the NanoClaw background service — it relays messages between the user an `pnpm exec tsx setup/index.ts --step service` -### 6. Wire the CLI agent and verify end-to-end +### 6. Wire a scratch CLI agent and verify end-to-end **Do not narrate this step.** No "creating your first agent…", no "sending a ping…" chatter. The user's experience here is: they finished the last visible step (service), then a single success line appears. Wiring is an implementation detail at this point, not a user-facing milestone. If step 2's container build is still running in the background, join it here before proceeding — the agent needs the image. -Use `INFERRED_DISPLAY_NAME` from the probe silently. **Do not ask the user.** The CLI agent at this stage is a scratch agent whose only purpose is to verify the end-to-end pipeline (host → container → agent → back). The user's real name capture happens in `/new-setup-2` when they wire a messaging channel. +Use `INFERRED_DISPLAY_NAME` from the probe silently. **Do not ask the user.** The CLI agent at this stage is a scratch agent whose only purpose is to verify the end-to-end pipeline (host → container → agent → back). The user's real name capture happens in step 7. Run wiring and ping back-to-back, silently: @@ -126,35 +129,141 @@ pnpm run chat ping First container spin-up takes ~60s. When the agent's reply arrives, emit exactly one line to the user: -> Your agent is up, running and ready to go! +> Test Agent success, proceeding with setup If `pnpm run chat ping` times out or errors, tail `logs/nanoclaw.log`, diagnose, and fix — don't surface a half-success. > **Loose command:** `pnpm run chat ping`. Justification: this is the same command the user will keep using after setup, so verification and the real channel are one and the same. -### 7. Chat now, or keep setting up? +### 7. What should the agent call you? -Ask the user via `AskUserQuestion` which they'd like to do next: +Plain-prose ask (do **not** use `AskUserQuestion`): -1. **Keep chatting with the agent via CLI** — happy with the CLI channel for now. -2. **Continue setup** — name the agent, wire a messaging channel, add quality-of-life extras. +> What should your agent call you? (Default: ``) -**If they pick "keep chatting":** print both options below, then stop. The user is chatting with the agent now, not with you — no further output from you. +Capture the answer into a local variable `OPERATOR_NAME`. **Don't persist yet** — this value is consumed by step 10's channel wiring. If the user skips or confirms the default, set `OPERATOR_NAME = INFERRED_DISPLAY_NAME`. -**Option 1 — from inside this Claude Code session.** Type your message with a leading `!`, which runs it as a bash command in this shell: +### 8. What's your agent's name? -``` -!pnpm run chat your message here -``` +Plain-prose ask: -**Option 2 — from a separate terminal.** Open a new terminal, `cd` into your nanoclaw checkout, then: +> What would you like to call your agent? (Default: ``) -``` -pnpm run chat your message here -``` +Capture as `AGENT_NAME`. If skipped, set `AGENT_NAME = OPERATOR_NAME`. Nothing persisted yet. -**If they pick "continue setup":** hand off directly to `/new-setup-2` via the Skill tool. That follow-on flow is structured like this one (linear, skippable steps) and covers naming, messaging-channel wiring, and QoL. Invoke it immediately — do not offer a menu of individual skills. +### 9. Timezone + +Run `pnpm exec tsx setup/index.ts --step timezone` and parse the status block. + +- **RESOLVED_TZ is `UTC` or `Etc/UTC`** — before leaving UTC in `.env`, confirm with `AskUserQuestion`: + + - **Question**: "Your system reports UTC as the timezone. Is that right, or are you somewhere else?" + - **Header**: "Timezone" + - **Options**: + 1. `Keep UTC` — "Leave timezone as UTC." + 2. `I'm somewhere else` — "I'll name the IANA zone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`) via Other." + + If they pick "I'm somewhere else" (or type an IANA zone via Other), re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` to overwrite `.env`. If they keep UTC or skip, leave UTC in place. + +- **NEEDS_USER_INPUT=true** — autodetection failed. Use `AskUserQuestion` with the same two options above (reword the question to "Autodetection failed — what timezone are you in?"), then re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` if they supply one. If they skip, move on. + +- Otherwise — timezone is already set; move on. + +### 10. Pick a messaging channel + +Print the list as a numbered plain-prose list (too many options for `AskUserQuestion`, which caps at 4). The user replies with a number or channel name. Preserve the numbering exactly: + +> Which messaging channel should I wire your agent to? +> +> 1. **WhatsApp (native)** — `/add-whatsapp` +> 2. **WhatsApp Cloud (Meta official)** — `/add-whatsapp-cloud` +> 3. **Telegram** — `/add-telegram` +> 4. **Slack** — `/add-slack` +> 5. **Discord** — `/add-discord` +> 6. **iMessage** — `/add-imessage` +> 7. **Teams** — `/add-teams` +> 8. **Matrix** — `/add-matrix` +> 9. **Google Chat** — `/add-gchat` +> 10. **Linear** — `/add-linear` +> 11. **GitHub** — `/add-github` +> 12. **Webex** — `/add-webex` +> 13. **Resend (email)** — `/add-resend` +> 14. **Emacs** — `/add-emacs` +> +> Or say "skip" to leave this for later. + +When the user picks one: + +1. **Install the adapter.** For **Telegram**, run `bash setup/install-telegram.sh` directly — it bundles the preflight + fetch + copy + register + `pnpm install` + build from `/add-telegram` into one idempotent call. Then handle Telegram credentials inline (below) — **do not** invoke `/add-telegram` afterward; its Credentials section would generate an unapprovable `grep && sed && rm` to write `.env`. For every other channel, invoke the matching `/add-` skill via the Skill tool; it copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels also run a pairing step as part of their flow. + + **Telegram credentials (inline):** + - Walk the user through BotFather: `/newbot` → pick name + username ending in `bot` → copy the token. + - Remind them: in `@BotFather` → `/mybots` → their bot → Bot Settings → Group Privacy → **Turn off** (only needed if the bot will live in groups; DM-only can skip). + - Persist the token and sync it to the container mount with the generic setter: + + ``` + pnpm exec tsx setup/index.ts --step set-env -- \ + --key TELEGRAM_BOT_TOKEN --value "" --sync-container + ``` + +2. **Capture platform IDs.** After the `/add-` skill finishes (or after inline credentials for Telegram), you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent ` directly and follow its `PAIR_TELEGRAM_ISSUED`/`PAIR_TELEGRAM STATUS=success` blocks — `PLATFORM_ID` and `ADMIN_USER_ID` land in the success block. +3. **Wire the agent.** Run `init-first-agent.ts` in DM mode: + + ``` + pnpm exec tsx scripts/init-first-agent.ts \ + --channel \ + --user-id "" \ + --platform-id "" \ + --display-name "" \ + --agent-name "" + ``` + +4. **Announce.** On success, emit the encouragement line verbatim: + + > Your agent is now available on {channel-name}, you can already start chatting — But I encourage you to continue and finish this setup, we're almost done! + + Substitute `{channel-name}` with the friendly name (e.g. "Telegram", "WhatsApp", "Slack"). + +If the user skipped, move on to step 11. + +### 11. Host directory access + +By default, agent containers can only touch their own workspace. If the user wants the agent to read or write files in specific host directories, those paths need to go on the mount allowlist. + +Use `AskUserQuestion`: + +- **Question**: "Want your agent to read or write files in any host directories (e.g. a code project, `~/Documents`)?" +- **Header**: "Host mounts" +- **Options**: + 1. `Keep isolated` — "Agent only touches its own workspace (Recommended)." + 2. `Add host paths` — "I'll name the directories to allowlist via Other." + +If they pick "Add host paths" (or name paths via Other), invoke `/manage-mounts` via the Skill tool to add them. If they keep it isolated or skip, move on. + +### 12. Quality of life + +Optional polish. Print the list; the user may pick zero, one, or several — invoke each chosen skill in sequence: + +> Want to add any of these? Pick any that sound useful — or skip: +> +> - `/add-dashboard` — browser dashboard showing agent activity +> - `/add-compact` — `/compact` slash command for managing long sessions +> - `/add-karpathy-llm-wiki` — persistent knowledge-base memory for the agent + +If the probe reports `PLATFORM=darwin`, also offer: + +> - `/add-macos-statusbar` — macOS menu bar indicator with Start/Stop/Restart controls + +Do **not** list `/add-macos-statusbar` on Linux. If the user skips everything, just move on. + +### 13. Done + +Short wrap-up: + +> Setup complete. You can chat with your agent on {channel-name} — or via CLI with `pnpm run chat `. + +Substitute `{channel-name}` with whatever was wired in step 10. If step 10 was skipped, drop the "on {channel-name} — or" clause entirely so the line just mentions the CLI form. ## If anything fails -Any step that reports `STATUS: failed` in its status block: read `logs/setup.log`, diagnose, fix the underlying cause, re-run the same `--step`. Don't bypass errors to keep moving. +Any step that reports `STATUS: failed` in its status block: read `logs/setup.log` (or `logs/nanoclaw.log` for runtime failures), diagnose, fix the underlying cause, re-run the same `--step`. Don't bypass errors to keep moving. diff --git a/setup/install-discord.sh b/setup/install-discord.sh index ee221f910..6f5a9c878 100755 --- a/setup/install-discord.sh +++ b/setup/install-discord.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-discord — bundles the preflight + install commands -# from the /add-discord skill into one idempotent script so /new-setup-2 can +# from the /add-discord skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Discord adapter in from the `channels` branch; appends the diff --git a/setup/install-gchat.sh b/setup/install-gchat.sh index f5c210b57..b9166f1a1 100755 --- a/setup/install-gchat.sh +++ b/setup/install-gchat.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-gchat — bundles the preflight + install commands -# from the /add-gchat skill into one idempotent script so /new-setup-2 can +# from the /add-gchat skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Google Chat adapter in from the `channels` branch; appends the diff --git a/setup/install-github.sh b/setup/install-github.sh index 81c2977e8..cb28bfc39 100755 --- a/setup/install-github.sh +++ b/setup/install-github.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-github — bundles the preflight + install commands -# from the /add-github skill into one idempotent script so /new-setup-2 can +# from the /add-github skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the GitHub adapter in from the `channels` branch; appends the diff --git a/setup/install-imessage.sh b/setup/install-imessage.sh index 0b1df3467..864e12796 100755 --- a/setup/install-imessage.sh +++ b/setup/install-imessage.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-imessage — bundles the preflight + install commands -# from the /add-imessage skill into one idempotent script so /new-setup-2 can +# from the /add-imessage skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the iMessage adapter in from the `channels` branch; appends the diff --git a/setup/install-linear.sh b/setup/install-linear.sh index 9f42bec54..f8788be1f 100755 --- a/setup/install-linear.sh +++ b/setup/install-linear.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-linear — bundles the preflight + install commands -# from the /add-linear skill into one idempotent script so /new-setup-2 can +# from the /add-linear skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Linear adapter in from the `channels` branch; appends the diff --git a/setup/install-matrix.sh b/setup/install-matrix.sh index 06d5ccd76..c9854731f 100755 --- a/setup/install-matrix.sh +++ b/setup/install-matrix.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-matrix — bundles the preflight + install commands -# from the /add-matrix skill into one idempotent script so /new-setup-2 can +# from the /add-matrix skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Matrix adapter in from the `channels` branch; appends the diff --git a/setup/install-resend.sh b/setup/install-resend.sh index 4f0bb2eda..9f18a9f96 100755 --- a/setup/install-resend.sh +++ b/setup/install-resend.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-resend — bundles the preflight + install commands -# from the /add-resend skill into one idempotent script so /new-setup-2 can +# from the /add-resend skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Resend adapter in from the `channels` branch; appends the diff --git a/setup/install-slack.sh b/setup/install-slack.sh index 8be6a373d..55d5e8573 100755 --- a/setup/install-slack.sh +++ b/setup/install-slack.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-slack — bundles the preflight + install commands -# from the /add-slack skill into one idempotent script so /new-setup-2 can +# from the /add-slack skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Slack adapter in from the `channels` branch; appends the diff --git a/setup/install-teams.sh b/setup/install-teams.sh index cb66f67e7..4b8c21690 100755 --- a/setup/install-teams.sh +++ b/setup/install-teams.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-teams — bundles the preflight + install commands -# from the /add-teams skill into one idempotent script so /new-setup-2 can +# from the /add-teams skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Teams adapter in from the `channels` branch; appends the diff --git a/setup/install-telegram.sh b/setup/install-telegram.sh index 7eaf9e12d..307dba226 100755 --- a/setup/install-telegram.sh +++ b/setup/install-telegram.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-telegram — bundles the preflight + install commands -# from the /add-telegram skill into one idempotent script so /new-setup-2 can +# from the /add-telegram skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials and pairing. # # Copies the Telegram adapter, helpers, tests, and the pair-telegram setup diff --git a/setup/install-webex.sh b/setup/install-webex.sh index 8bbbc836c..adf52fc4d 100755 --- a/setup/install-webex.sh +++ b/setup/install-webex.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-webex — bundles the preflight + install commands -# from the /add-webex skill into one idempotent script so /new-setup-2 can +# from the /add-webex skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Webex adapter in from the `channels` branch; appends the diff --git a/setup/install-whatsapp-cloud.sh b/setup/install-whatsapp-cloud.sh index 377327809..70e8e0279 100755 --- a/setup/install-whatsapp-cloud.sh +++ b/setup/install-whatsapp-cloud.sh @@ -1,7 +1,7 @@ #!/usr/bin/env bash # Setup helper: install-whatsapp-cloud — bundles the preflight + install # commands from the /add-whatsapp-cloud skill into one idempotent script so -# /new-setup-2 can run them programmatically before continuing to credentials. +# /new-setup can run them programmatically before continuing to credentials. # # Copies the WhatsApp Cloud adapter in from the `channels` branch; appends the # self-registration import; installs the pinned @chat-adapter/whatsapp package; diff --git a/setup/install-whatsapp.sh b/setup/install-whatsapp.sh index 0d307f53c..1c62d65d4 100755 --- a/setup/install-whatsapp.sh +++ b/setup/install-whatsapp.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-whatsapp — bundles the preflight + install commands -# from the /add-whatsapp skill into one idempotent script so /new-setup-2 can +# from the /add-whatsapp skill into one idempotent script so /new-setup can # run them programmatically before continuing to QR/pairing-code auth. # # Copies the native Baileys WhatsApp adapter, its whatsapp-auth and groups From 9776dd4f32f19f07e655b44501e8fc259e3328f3 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Tue, 21 Apr 2026 11:40:12 +0000 Subject: [PATCH 60/95] fix(permissions): welcome new approved channels via /welcome, route to them When the unknown-channel approval flow completes, seed a /welcome task into the newly-wired session so the agent greets the new user on first contact. The replayed /start (Telegram's default first-message) is filtered by the agent-runner's command-command filter, so without an explicit onboarding trigger the first interaction produced nothing. Pin the destination by its local_name from agent_destinations to avoid the agent picking the wrong named destination (previously it greeted the owner, whose DM is in CLAUDE.md). Also guard dispatchResultText against echoing trailing status lines when the agent has already sent messages explicitly via send_message. Otherwise a task-triggered flow that calls send_message then emits "welcome message sent" produces a duplicate chat to the recipient. Co-Authored-By: Claude Opus 4.7 (1M context) --- container/agent-runner/src/poll-loop.ts | 35 ++++++-- .../permissions/channel-approval.test.ts | 81 +++++++++++++++++++ src/modules/permissions/index.ts | 70 ++++++++++++++++ 3 files changed, 181 insertions(+), 5 deletions(-) diff --git a/container/agent-runner/src/poll-loop.ts b/container/agent-runner/src/poll-loop.ts index 3f0e364be..cd7b7e16d 100644 --- a/container/agent-runner/src/poll-loop.ts +++ b/container/agent-runner/src/poll-loop.ts @@ -1,7 +1,7 @@ import { findByName, getAllDestinations, type DestinationEntry } from './destinations.js'; import { getPendingMessages, markProcessing, markCompleted, type MessageInRow } from './db/messages-in.js'; import { writeMessageOut } from './db/messages-out.js'; -import { touchHeartbeat, clearStaleProcessingAcks } from './db/connection.js'; +import { touchHeartbeat, clearStaleProcessingAcks, getOutboundDb } from './db/connection.js'; import { getStoredSessionId, setStoredSessionId, clearStoredSessionId } from './db/session-state.js'; import { formatMessages, extractRouting, categorizeMessage, stripInternalTags, type RoutingContext } from './formatter.js'; import type { AgentProvider, AgentQuery, ProviderEvent } from './providers/types.js'; @@ -280,6 +280,17 @@ async function processQuery(query: AgentQuery, routing: RoutingContext): Promise let queryContinuation: string | undefined; let done = false; + // Track the outbound row count between result events. When the agent uses + // send_message (or any MCP tool that writes to messages_out) during a turn, + // the count grows. We pass that signal to dispatchResultText so it can tell + // the difference between "agent wrote text meant as the reply" (send the + // scratchpad) and "agent did explicit tool sends AND then emitted a trailing + // status line" (don't echo the status line back to the channel). + // + // Reset after each result dispatch so subsequent turns in the same query + // (follow-up messages pushed into the stream) are evaluated independently. + let outboundAtLastResult = getOutboundCount(); + // Concurrent polling: push follow-ups into the active query as they arrive. // We do NOT force-end the stream on silence — keeping the query open is // strictly cheaper than close+reopen (no cold prompt cache, no reconnect). @@ -323,7 +334,9 @@ async function processQuery(query: AgentQuery, routing: RoutingContext): Promise if (event.type === 'init') { queryContinuation = event.continuation; } else if (event.type === 'result' && event.text) { - dispatchResultText(event.text, routing); + const hasExplicitSends = getOutboundCount() > outboundAtLastResult; + dispatchResultText(event.text, routing, hasExplicitSends); + outboundAtLastResult = getOutboundCount(); } } } finally { @@ -363,7 +376,7 @@ function handleEvent(event: ProviderEvent, _routing: RoutingContext): void { * This preserves the simple case of one user on one channel — the agent * doesn't need to know about wrapping syntax at all. */ -function dispatchResultText(text: string, routing: RoutingContext): void { +function dispatchResultText(text: string, routing: RoutingContext, hasExplicitSends: boolean): void { const MESSAGE_RE = /([\s\S]*?)<\/message>/g; let match: RegExpExecArray | null; @@ -397,7 +410,15 @@ function dispatchResultText(text: string, routing: RoutingContext): void { // Single-destination shortcut: the agent wrote plain text — send to // the session's originating channel (from session_routing) if available, // otherwise fall back to the single destination. - if (sent === 0 && scratchpad) { + // + // If the agent already sent messages explicitly this turn (via send_message + // or another MCP tool that writes to outbound), treat trailing plain text as + // a status/summary line and DO NOT echo it back to the channel. Without this + // guard, task-driven flows like the onboarding /welcome cause duplicate + // delivery: the skill uses `send_message` to greet the new user, then the + // model emits "Welcome message sent." which used to be dispatched as a + // second chat message to the same recipient. + if (sent === 0 && scratchpad && !hasExplicitSends) { if (routing.channelType && routing.platformId) { // Reply to the channel/thread the message came from writeMessageOut({ @@ -422,11 +443,15 @@ function dispatchResultText(text: string, routing: RoutingContext): void { log(`[scratchpad] ${scratchpad.slice(0, 500)}${scratchpad.length > 500 ? '…' : ''}`); } - if (sent === 0 && text.trim()) { + if (sent === 0 && text.trim() && !hasExplicitSends) { log(`WARNING: agent output had no blocks — nothing was sent`); } } +function getOutboundCount(): number { + return (getOutboundDb().prepare('SELECT COUNT(*) AS c FROM messages_out').get() as { c: number }).c; +} + function sendToDestination(dest: DestinationEntry, body: string, routing: RoutingContext): void { const platformId = dest.type === 'channel' ? dest.platformId! : dest.agentGroupId!; const channelType = dest.type === 'channel' ? dest.channelType! : 'agent'; diff --git a/src/modules/permissions/channel-approval.test.ts b/src/modules/permissions/channel-approval.test.ts index f3ea7e98c..340a9ed10 100644 --- a/src/modules/permissions/channel-approval.test.ts +++ b/src/modules/permissions/channel-approval.test.ts @@ -247,6 +247,87 @@ describe('unknown-channel registration flow', () => { expect(wakeContainer).toHaveBeenCalled(); }); + it('approve → seeds a /welcome onboarding task into the session', async () => { + const { routeInbound } = await import('../../router.js'); + const { getResponseHandlers } = await import('../../response-registry.js'); + + // `/start` is filtered by the agent-runner (Claude Code slash command), + // so without the seeded onboarding task a Telegram user's first DM would + // produce zero response. The seed ensures the agent runs /welcome regardless. + const startDm = { + channelType: 'telegram', + platformId: 'dm-new-friend', + threadId: null, + message: { + id: 'msg-start', + kind: 'chat' as const, + content: JSON.stringify({ senderId: 'friend', senderName: 'Friend', text: '/start' }), + timestamp: now(), + isMention: true, + }, + }; + await routeInbound(startDm); + await new Promise((r) => setTimeout(r, 10)); + + const { getDb } = await import('../../db/connection.js'); + const pending = getDb() + .prepare('SELECT messaging_group_id, agent_group_id FROM pending_channel_approvals') + .get() as { messaging_group_id: string; agent_group_id: string }; + + for (const handler of getResponseHandlers()) { + const claimed = await handler({ + questionId: pending.messaging_group_id, + value: 'approve', + userId: 'owner', + channelType: 'telegram', + platformId: 'dm-owner', + threadId: null, + }); + if (claimed) break; + } + + // Look up the session that got created, then open its inbound.db and + // confirm an onboarding task with a /welcome prompt landed before the + // replayed chat message. + const session = getDb() + .prepare('SELECT id FROM sessions WHERE agent_group_id = ? AND messaging_group_id = ?') + .get(pending.agent_group_id, pending.messaging_group_id) as { id: string } | undefined; + expect(session).toBeDefined(); + + const Database = (await import('better-sqlite3')).default; + const path = await import('path'); + const inboundPath = path.join(TEST_DIR, 'v2-sessions', pending.agent_group_id, session!.id, 'inbound.db'); + const inbound = new Database(inboundPath, { readonly: true }); + const rows = inbound + .prepare('SELECT kind, content, seq FROM messages_in ORDER BY seq') + .all() as { kind: string; content: string; seq: number }[]; + inbound.close(); + + const taskRow = rows.find((r) => r.kind === 'task'); + expect(taskRow).toBeDefined(); + const prompt: string = JSON.parse(taskRow!.content).prompt; + expect(prompt).toMatch(/\/welcome/); + // Prompt must name the new user — otherwise with multiple destinations + // configured the model may greet the owner instead of the new sender + // (see bug where "Hey Daniel!" landed in the owner's DM). + expect(prompt).toContain('Friend'); + expect(prompt).toContain('dm-new-friend'); + + // Prompt must pin the exact destination by its agent_destinations + // local_name. That name is auto-created by createMessagingGroupAgent + // above; look it up and assert it appears in the prompt verbatim. + const destRow = getDb() + .prepare('SELECT local_name FROM agent_destinations WHERE agent_group_id = ? AND target_id = ?') + .get(pending.agent_group_id, pending.messaging_group_id) as { local_name: string }; + expect(destRow).toBeDefined(); + expect(prompt).toContain(`send_message(to: '${destRow.local_name}'`); + + // Order: task seeded before the replayed /start chat message. + const chatRow = rows.find((r) => r.kind === 'chat'); + expect(chatRow).toBeDefined(); + expect(taskRow!.seq).toBeLessThan(chatRow!.seq); + }); + it('approve on a DM wires with pattern="." defaults', async () => { const { routeInbound } = await import('../../router.js'); const { getResponseHandlers } = await import('../../response-registry.js'); diff --git a/src/modules/permissions/index.ts b/src/modules/permissions/index.ts index 83390d837..a1cd03a7f 100644 --- a/src/modules/permissions/index.ts +++ b/src/modules/permissions/index.ts @@ -28,6 +28,7 @@ import { import type { InboundEvent } from '../../channels/adapter.js'; import { registerResponseHandler, type ResponsePayload } from '../../response-registry.js'; import { log } from '../../log.js'; +import { resolveSession, writeSessionMessage } from '../../session-manager.js'; import type { MessagingGroup, MessagingGroupAgent } from '../../types.js'; import { canAccessAgentGroup } from './access.js'; import { requestChannelApproval } from './channel-approval.js'; @@ -379,6 +380,75 @@ async function handleChannelApprovalResponse(payload: ResponsePayload): Promise< // path normally. deletePendingChannelApproval(row.messaging_group_id); + // Seed a /welcome onboarding task into the session *before* the replayed + // message so the agent greets the new user on first contact. Mirrors the + // owner-setup path (setup/register.ts). Without this, a Telegram user's + // default `/start` greeting gets silently dropped by the agent-runner's + // command filter and the first interaction produces nothing. + // + // The prompt pins the exact destination by name: createMessagingGroupAgent + // above auto-created an `agent_destinations` row pointing at this messaging + // group, and we look it up here. Without that, the agent — which already + // knows about the owner's DM and earlier friends' DMs as named destinations + // — tends to greet the owner (CLAUDE.md anchors on them). Passing the + // specific destination name removes the ambiguity entirely. + try { + const { session } = resolveSession(row.agent_group_id, row.messaging_group_id, event.threadId, 'shared'); + const parsed = safeParseContent(event.message.content); + const author = + parsed && typeof parsed === 'object' && 'author' in parsed && typeof (parsed as { author?: unknown }).author === 'object' + ? ((parsed as { author: Record }).author) + : undefined; + const senderName = + (typeof (parsed as { senderName?: unknown }).senderName === 'string' ? (parsed as { senderName: string }).senderName : undefined) ?? + (typeof (parsed as { sender?: unknown }).sender === 'string' ? (parsed as { sender: string }).sender : undefined) ?? + (typeof author?.fullName === 'string' ? (author.fullName as string) : undefined) ?? + (typeof author?.userName === 'string' ? (author.userName as string) : undefined) ?? + null; + const senderLabel = senderName ? `${senderName} (${event.platformId})` : event.platformId; + + // Pin the destination. Guarded behind hasTable in case the agent-to-agent + // module isn't installed — without it there are no named destinations at + // all, so the agent's send_message call falls through to session default + // routing (which is this new user). Either way, unambiguous. + let destinationClause: string; + const { hasTable, getDb } = await import('../../db/connection.js'); + if (hasTable(getDb(), 'agent_destinations')) { + const { getDestinationByTarget } = await import('../agent-to-agent/db/agent-destinations.js'); + const dest = getDestinationByTarget(row.agent_group_id, 'channel', row.messaging_group_id); + destinationClause = dest + ? `Send your welcome with send_message(to: '${dest.local_name}', text: ...) — that destination resolves to their DM.` + : `Reply using send_message with no \`to\` — the session's default routing points at their DM.`; + } else { + destinationClause = `Reply using send_message — it will land in their DM.`; + } + + writeSessionMessage(row.agent_group_id, session.id, { + id: `onboard-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`, + kind: 'task', + timestamp: new Date().toISOString(), + platformId: event.platformId, + channelType: event.channelType, + content: JSON.stringify({ + prompt: + `A new ${event.channelType} user — ${senderLabel} — just started a conversation. ` + + `Run /welcome to introduce yourself to them. ${destinationClause}`, + }), + }); + log.info('Onboarding message seeded after channel approval', { + sessionId: session.id, + messagingGroupId: row.messaging_group_id, + agentGroupId: row.agent_group_id, + senderName, + }); + } catch (err) { + // Don't block the replay if onboarding write fails. + log.error('Failed to seed onboarding message after channel approval', { + messagingGroupId: row.messaging_group_id, + err, + }); + } + try { await routeInbound(event); } catch (err) { From 01ffce6f74fa7bc3195f207667d39d7b57272180 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 15:20:06 +0300 Subject: [PATCH 61/95] Revert "fix(permissions): welcome new approved channels via /welcome, route to them" This reverts commit 9776dd4f32f19f07e655b44501e8fc259e3328f3. --- container/agent-runner/src/poll-loop.ts | 35 ++------ .../permissions/channel-approval.test.ts | 81 ------------------- src/modules/permissions/index.ts | 70 ---------------- 3 files changed, 5 insertions(+), 181 deletions(-) diff --git a/container/agent-runner/src/poll-loop.ts b/container/agent-runner/src/poll-loop.ts index cd7b7e16d..3f0e364be 100644 --- a/container/agent-runner/src/poll-loop.ts +++ b/container/agent-runner/src/poll-loop.ts @@ -1,7 +1,7 @@ import { findByName, getAllDestinations, type DestinationEntry } from './destinations.js'; import { getPendingMessages, markProcessing, markCompleted, type MessageInRow } from './db/messages-in.js'; import { writeMessageOut } from './db/messages-out.js'; -import { touchHeartbeat, clearStaleProcessingAcks, getOutboundDb } from './db/connection.js'; +import { touchHeartbeat, clearStaleProcessingAcks } from './db/connection.js'; import { getStoredSessionId, setStoredSessionId, clearStoredSessionId } from './db/session-state.js'; import { formatMessages, extractRouting, categorizeMessage, stripInternalTags, type RoutingContext } from './formatter.js'; import type { AgentProvider, AgentQuery, ProviderEvent } from './providers/types.js'; @@ -280,17 +280,6 @@ async function processQuery(query: AgentQuery, routing: RoutingContext): Promise let queryContinuation: string | undefined; let done = false; - // Track the outbound row count between result events. When the agent uses - // send_message (or any MCP tool that writes to messages_out) during a turn, - // the count grows. We pass that signal to dispatchResultText so it can tell - // the difference between "agent wrote text meant as the reply" (send the - // scratchpad) and "agent did explicit tool sends AND then emitted a trailing - // status line" (don't echo the status line back to the channel). - // - // Reset after each result dispatch so subsequent turns in the same query - // (follow-up messages pushed into the stream) are evaluated independently. - let outboundAtLastResult = getOutboundCount(); - // Concurrent polling: push follow-ups into the active query as they arrive. // We do NOT force-end the stream on silence — keeping the query open is // strictly cheaper than close+reopen (no cold prompt cache, no reconnect). @@ -334,9 +323,7 @@ async function processQuery(query: AgentQuery, routing: RoutingContext): Promise if (event.type === 'init') { queryContinuation = event.continuation; } else if (event.type === 'result' && event.text) { - const hasExplicitSends = getOutboundCount() > outboundAtLastResult; - dispatchResultText(event.text, routing, hasExplicitSends); - outboundAtLastResult = getOutboundCount(); + dispatchResultText(event.text, routing); } } } finally { @@ -376,7 +363,7 @@ function handleEvent(event: ProviderEvent, _routing: RoutingContext): void { * This preserves the simple case of one user on one channel — the agent * doesn't need to know about wrapping syntax at all. */ -function dispatchResultText(text: string, routing: RoutingContext, hasExplicitSends: boolean): void { +function dispatchResultText(text: string, routing: RoutingContext): void { const MESSAGE_RE = /([\s\S]*?)<\/message>/g; let match: RegExpExecArray | null; @@ -410,15 +397,7 @@ function dispatchResultText(text: string, routing: RoutingContext, hasExplicitSe // Single-destination shortcut: the agent wrote plain text — send to // the session's originating channel (from session_routing) if available, // otherwise fall back to the single destination. - // - // If the agent already sent messages explicitly this turn (via send_message - // or another MCP tool that writes to outbound), treat trailing plain text as - // a status/summary line and DO NOT echo it back to the channel. Without this - // guard, task-driven flows like the onboarding /welcome cause duplicate - // delivery: the skill uses `send_message` to greet the new user, then the - // model emits "Welcome message sent." which used to be dispatched as a - // second chat message to the same recipient. - if (sent === 0 && scratchpad && !hasExplicitSends) { + if (sent === 0 && scratchpad) { if (routing.channelType && routing.platformId) { // Reply to the channel/thread the message came from writeMessageOut({ @@ -443,15 +422,11 @@ function dispatchResultText(text: string, routing: RoutingContext, hasExplicitSe log(`[scratchpad] ${scratchpad.slice(0, 500)}${scratchpad.length > 500 ? '…' : ''}`); } - if (sent === 0 && text.trim() && !hasExplicitSends) { + if (sent === 0 && text.trim()) { log(`WARNING: agent output had no blocks — nothing was sent`); } } -function getOutboundCount(): number { - return (getOutboundDb().prepare('SELECT COUNT(*) AS c FROM messages_out').get() as { c: number }).c; -} - function sendToDestination(dest: DestinationEntry, body: string, routing: RoutingContext): void { const platformId = dest.type === 'channel' ? dest.platformId! : dest.agentGroupId!; const channelType = dest.type === 'channel' ? dest.channelType! : 'agent'; diff --git a/src/modules/permissions/channel-approval.test.ts b/src/modules/permissions/channel-approval.test.ts index 340a9ed10..f3ea7e98c 100644 --- a/src/modules/permissions/channel-approval.test.ts +++ b/src/modules/permissions/channel-approval.test.ts @@ -247,87 +247,6 @@ describe('unknown-channel registration flow', () => { expect(wakeContainer).toHaveBeenCalled(); }); - it('approve → seeds a /welcome onboarding task into the session', async () => { - const { routeInbound } = await import('../../router.js'); - const { getResponseHandlers } = await import('../../response-registry.js'); - - // `/start` is filtered by the agent-runner (Claude Code slash command), - // so without the seeded onboarding task a Telegram user's first DM would - // produce zero response. The seed ensures the agent runs /welcome regardless. - const startDm = { - channelType: 'telegram', - platformId: 'dm-new-friend', - threadId: null, - message: { - id: 'msg-start', - kind: 'chat' as const, - content: JSON.stringify({ senderId: 'friend', senderName: 'Friend', text: '/start' }), - timestamp: now(), - isMention: true, - }, - }; - await routeInbound(startDm); - await new Promise((r) => setTimeout(r, 10)); - - const { getDb } = await import('../../db/connection.js'); - const pending = getDb() - .prepare('SELECT messaging_group_id, agent_group_id FROM pending_channel_approvals') - .get() as { messaging_group_id: string; agent_group_id: string }; - - for (const handler of getResponseHandlers()) { - const claimed = await handler({ - questionId: pending.messaging_group_id, - value: 'approve', - userId: 'owner', - channelType: 'telegram', - platformId: 'dm-owner', - threadId: null, - }); - if (claimed) break; - } - - // Look up the session that got created, then open its inbound.db and - // confirm an onboarding task with a /welcome prompt landed before the - // replayed chat message. - const session = getDb() - .prepare('SELECT id FROM sessions WHERE agent_group_id = ? AND messaging_group_id = ?') - .get(pending.agent_group_id, pending.messaging_group_id) as { id: string } | undefined; - expect(session).toBeDefined(); - - const Database = (await import('better-sqlite3')).default; - const path = await import('path'); - const inboundPath = path.join(TEST_DIR, 'v2-sessions', pending.agent_group_id, session!.id, 'inbound.db'); - const inbound = new Database(inboundPath, { readonly: true }); - const rows = inbound - .prepare('SELECT kind, content, seq FROM messages_in ORDER BY seq') - .all() as { kind: string; content: string; seq: number }[]; - inbound.close(); - - const taskRow = rows.find((r) => r.kind === 'task'); - expect(taskRow).toBeDefined(); - const prompt: string = JSON.parse(taskRow!.content).prompt; - expect(prompt).toMatch(/\/welcome/); - // Prompt must name the new user — otherwise with multiple destinations - // configured the model may greet the owner instead of the new sender - // (see bug where "Hey Daniel!" landed in the owner's DM). - expect(prompt).toContain('Friend'); - expect(prompt).toContain('dm-new-friend'); - - // Prompt must pin the exact destination by its agent_destinations - // local_name. That name is auto-created by createMessagingGroupAgent - // above; look it up and assert it appears in the prompt verbatim. - const destRow = getDb() - .prepare('SELECT local_name FROM agent_destinations WHERE agent_group_id = ? AND target_id = ?') - .get(pending.agent_group_id, pending.messaging_group_id) as { local_name: string }; - expect(destRow).toBeDefined(); - expect(prompt).toContain(`send_message(to: '${destRow.local_name}'`); - - // Order: task seeded before the replayed /start chat message. - const chatRow = rows.find((r) => r.kind === 'chat'); - expect(chatRow).toBeDefined(); - expect(taskRow!.seq).toBeLessThan(chatRow!.seq); - }); - it('approve on a DM wires with pattern="." defaults', async () => { const { routeInbound } = await import('../../router.js'); const { getResponseHandlers } = await import('../../response-registry.js'); diff --git a/src/modules/permissions/index.ts b/src/modules/permissions/index.ts index a1cd03a7f..83390d837 100644 --- a/src/modules/permissions/index.ts +++ b/src/modules/permissions/index.ts @@ -28,7 +28,6 @@ import { import type { InboundEvent } from '../../channels/adapter.js'; import { registerResponseHandler, type ResponsePayload } from '../../response-registry.js'; import { log } from '../../log.js'; -import { resolveSession, writeSessionMessage } from '../../session-manager.js'; import type { MessagingGroup, MessagingGroupAgent } from '../../types.js'; import { canAccessAgentGroup } from './access.js'; import { requestChannelApproval } from './channel-approval.js'; @@ -380,75 +379,6 @@ async function handleChannelApprovalResponse(payload: ResponsePayload): Promise< // path normally. deletePendingChannelApproval(row.messaging_group_id); - // Seed a /welcome onboarding task into the session *before* the replayed - // message so the agent greets the new user on first contact. Mirrors the - // owner-setup path (setup/register.ts). Without this, a Telegram user's - // default `/start` greeting gets silently dropped by the agent-runner's - // command filter and the first interaction produces nothing. - // - // The prompt pins the exact destination by name: createMessagingGroupAgent - // above auto-created an `agent_destinations` row pointing at this messaging - // group, and we look it up here. Without that, the agent — which already - // knows about the owner's DM and earlier friends' DMs as named destinations - // — tends to greet the owner (CLAUDE.md anchors on them). Passing the - // specific destination name removes the ambiguity entirely. - try { - const { session } = resolveSession(row.agent_group_id, row.messaging_group_id, event.threadId, 'shared'); - const parsed = safeParseContent(event.message.content); - const author = - parsed && typeof parsed === 'object' && 'author' in parsed && typeof (parsed as { author?: unknown }).author === 'object' - ? ((parsed as { author: Record }).author) - : undefined; - const senderName = - (typeof (parsed as { senderName?: unknown }).senderName === 'string' ? (parsed as { senderName: string }).senderName : undefined) ?? - (typeof (parsed as { sender?: unknown }).sender === 'string' ? (parsed as { sender: string }).sender : undefined) ?? - (typeof author?.fullName === 'string' ? (author.fullName as string) : undefined) ?? - (typeof author?.userName === 'string' ? (author.userName as string) : undefined) ?? - null; - const senderLabel = senderName ? `${senderName} (${event.platformId})` : event.platformId; - - // Pin the destination. Guarded behind hasTable in case the agent-to-agent - // module isn't installed — without it there are no named destinations at - // all, so the agent's send_message call falls through to session default - // routing (which is this new user). Either way, unambiguous. - let destinationClause: string; - const { hasTable, getDb } = await import('../../db/connection.js'); - if (hasTable(getDb(), 'agent_destinations')) { - const { getDestinationByTarget } = await import('../agent-to-agent/db/agent-destinations.js'); - const dest = getDestinationByTarget(row.agent_group_id, 'channel', row.messaging_group_id); - destinationClause = dest - ? `Send your welcome with send_message(to: '${dest.local_name}', text: ...) — that destination resolves to their DM.` - : `Reply using send_message with no \`to\` — the session's default routing points at their DM.`; - } else { - destinationClause = `Reply using send_message — it will land in their DM.`; - } - - writeSessionMessage(row.agent_group_id, session.id, { - id: `onboard-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`, - kind: 'task', - timestamp: new Date().toISOString(), - platformId: event.platformId, - channelType: event.channelType, - content: JSON.stringify({ - prompt: - `A new ${event.channelType} user — ${senderLabel} — just started a conversation. ` + - `Run /welcome to introduce yourself to them. ${destinationClause}`, - }), - }); - log.info('Onboarding message seeded after channel approval', { - sessionId: session.id, - messagingGroupId: row.messaging_group_id, - agentGroupId: row.agent_group_id, - senderName, - }); - } catch (err) { - // Don't block the replay if onboarding write fails. - log.error('Failed to seed onboarding message after channel approval', { - messagingGroupId: row.messaging_group_id, - err, - }); - } - try { await routeInbound(event); } catch (err) { From 77e6d3bc66bcd5fc3a3ae21ee7d01b1b82f359f8 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 15:20:06 +0300 Subject: [PATCH 62/95] Revert "refactor(skills): merge /new-setup-2 into unified /new-setup" This reverts commit 483969a1948469daf3141afe0c6a3bffdc430faa. --- .claude/skills/new-setup-2/SKILL.md | 154 +++++++++++++++++++++++++++ .claude/skills/new-setup/SKILL.md | 155 +++++----------------------- setup/install-discord.sh | 2 +- setup/install-gchat.sh | 2 +- setup/install-github.sh | 2 +- setup/install-imessage.sh | 2 +- setup/install-linear.sh | 2 +- setup/install-matrix.sh | 2 +- setup/install-resend.sh | 2 +- setup/install-slack.sh | 2 +- setup/install-teams.sh | 2 +- setup/install-telegram.sh | 2 +- setup/install-webex.sh | 2 +- setup/install-whatsapp-cloud.sh | 2 +- setup/install-whatsapp.sh | 2 +- 15 files changed, 190 insertions(+), 145 deletions(-) create mode 100644 .claude/skills/new-setup-2/SKILL.md diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md new file mode 100644 index 000000000..8d75cd3f7 --- /dev/null +++ b/.claude/skills/new-setup-2/SKILL.md @@ -0,0 +1,154 @@ +--- +name: new-setup-2 +description: Follow-on to /new-setup. Captures the operator and agent names, wires a real messaging channel, and adds quality-of-life extras. Linear rollthrough; every step is skippable. Invoked when the user picks "continue setup" at the end of /new-setup. +allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm exec tsx scripts/init-first-agent.ts:*) Bash(tail:*) Bash(head:*) Bash(grep:*) +--- + +# NanoClaw phase-2 setup + +Runs after `/new-setup`. At this point the host is running and a throwaway CLI-only agent exists (used during /new-setup for the end-to-end ping check — inferred name, not user-facing). This flow creates the **real** agent and wires it to a messaging channel. + +**Linear — one step at a time.** Every step is skippable: if the user says "skip", "not now", "later", or similar, move on without complaint. If they say they're done at any point, stop cleanly — don't push the remaining steps. + +Before each step, narrate in your own words what's about to happen — one short, friendly sentence, no jargon. Match the tone of `/new-setup`. + +## Current state + +!`bash setup/probe.sh` + +Parse the probe block above for `INFERRED_DISPLAY_NAME` and `PLATFORM` — referenced below. + +## Steps + +### 1. What should the agent call you? + +Plain-prose ask (do **not** use `AskUserQuestion`): + +> What should your agent call you? (Default: ``) + +Capture the answer into a local variable `OPERATOR_NAME`. **Don't persist yet** — this value is consumed by step 3's channel wiring. If the user skips or confirms the default, set `OPERATOR_NAME = INFERRED_DISPLAY_NAME`. + +### 2. What's your agent's name? + +Plain-prose ask: + +> What would you like to call your agent? (Default: ``) + +Capture as `AGENT_NAME`. If skipped, set `AGENT_NAME = OPERATOR_NAME`. Nothing persisted yet. + +### 3. Timezone + +Run `pnpm exec tsx setup/index.ts --step timezone` and parse the status block. + +- **RESOLVED_TZ is `UTC` or `Etc/UTC`** — before leaving UTC in `.env`, confirm with `AskUserQuestion`: + + - **Question**: "Your system reports UTC as the timezone. Is that right, or are you somewhere else?" + - **Header**: "Timezone" + - **Options**: + 1. `Keep UTC` — "Leave timezone as UTC." + 2. `I'm somewhere else` — "I'll name the IANA zone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`) via Other." + + If they pick "I'm somewhere else" (or type an IANA zone via Other), re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` to overwrite `.env`. If they keep UTC or skip, leave UTC in place. + +- **NEEDS_USER_INPUT=true** — autodetection failed. Use `AskUserQuestion` with the same two options above (reword the question to "Autodetection failed — what timezone are you in?"), then re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` if they supply one. If they skip, move on. + +- Otherwise — timezone is already set; move on. + +### 4. Pick a messaging channel + +Print the list as a numbered plain-prose list (too many options for `AskUserQuestion`, which caps at 4). The user replies with a number or channel name. Preserve the numbering exactly: + +> Which messaging channel should I wire your agent to? +> +> 1. **WhatsApp (native)** — `/add-whatsapp` +> 2. **WhatsApp Cloud (Meta official)** — `/add-whatsapp-cloud` +> 3. **Telegram** — `/add-telegram` +> 4. **Slack** — `/add-slack` +> 5. **Discord** — `/add-discord` +> 6. **iMessage** — `/add-imessage` +> 7. **Teams** — `/add-teams` +> 8. **Matrix** — `/add-matrix` +> 9. **Google Chat** — `/add-gchat` +> 10. **Linear** — `/add-linear` +> 11. **GitHub** — `/add-github` +> 12. **Webex** — `/add-webex` +> 13. **Resend (email)** — `/add-resend` +> 14. **Emacs** — `/add-emacs` +> +> Or say "skip" to leave this for later. + +When the user picks one: + +1. **Install the adapter.** For **Telegram**, run `bash setup/install-telegram.sh` directly — it bundles the preflight + fetch + copy + register + `pnpm install` + build from `/add-telegram` into one idempotent call. Then handle Telegram credentials inline (below) — **do not** invoke `/add-telegram` afterward; its Credentials section would generate an unapprovable `grep && sed && rm` to write `.env`. For every other channel, invoke the matching `/add-` skill via the Skill tool; it copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels also run a pairing step as part of their flow. + + **Telegram credentials (inline):** + - Walk the user through BotFather: `/newbot` → pick name + username ending in `bot` → copy the token. + - Remind them: in `@BotFather` → `/mybots` → their bot → Bot Settings → Group Privacy → **Turn off** (only needed if the bot will live in groups; DM-only can skip). + - Persist the token and sync it to the container mount with the generic setter: + + ``` + pnpm exec tsx setup/index.ts --step set-env -- \ + --key TELEGRAM_BOT_TOKEN --value "" --sync-container + ``` + +2. **Capture platform IDs.** After the `/add-` skill finishes (or after inline credentials for Telegram), you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent ` directly and follow its `PAIR_TELEGRAM_ISSUED`/`PAIR_TELEGRAM STATUS=success` blocks — `PLATFORM_ID` and `ADMIN_USER_ID` land in the success block. +3. **Wire the agent.** Run `init-first-agent.ts` in DM mode: + + ``` + pnpm exec tsx scripts/init-first-agent.ts \ + --channel \ + --user-id "" \ + --platform-id "" \ + --display-name "" \ + --agent-name "" + ``` + +4. **Announce.** On success, emit the encouragement line verbatim: + + > Your agent is now available on {channel-name}, you can already start chatting — But I encourage you to continue and finish this setup, we're almost done! + + Substitute `{channel-name}` with the friendly name (e.g. "Telegram", "WhatsApp", "Slack"). + +If the user skipped, move on to step 5. + +### 5. Host directory access + +By default, agent containers can only touch their own workspace. If the user wants the agent to read or write files in specific host directories, those paths need to go on the mount allowlist. + +Use `AskUserQuestion`: + +- **Question**: "Want your agent to read or write files in any host directories (e.g. a code project, `~/Documents`)?" +- **Header**: "Host mounts" +- **Options**: + 1. `Keep isolated` — "Agent only touches its own workspace (Recommended)." + 2. `Add host paths` — "I'll name the directories to allowlist via Other." + +If they pick "Add host paths" (or name paths via Other), invoke `/manage-mounts` via the Skill tool to add them. If they keep it isolated or skip, move on. + +### 6. Quality of life + +Optional polish. Print the list; the user may pick zero, one, or several — invoke each chosen skill in sequence: + +> Want to add any of these? Pick any that sound useful — or skip: +> +> - `/add-dashboard` — browser dashboard showing agent activity +> - `/add-compact` — `/compact` slash command for managing long sessions +> - `/add-karpathy-llm-wiki` — persistent knowledge-base memory for the agent + +If the probe reports `PLATFORM=darwin`, also offer: + +> - `/add-macos-statusbar` — macOS menu bar indicator with Start/Stop/Restart controls + +Do **not** list `/add-macos-statusbar` on Linux. If the user skips everything, just move on. + +### 7. Done + +Short wrap-up: + +> Setup complete. You can chat with your agent on {channel-name} — or via CLI with `pnpm run chat `. + +Substitute `{channel-name}` with whatever was wired in step 4. If step 4 was skipped, drop the "on {channel-name} — or" clause entirely so the line just mentions the CLI form. + +## If anything fails + +Same rule as `/new-setup`: don't bypass errors to keep moving. Read `logs/setup.log` or `logs/nanoclaw.log`, diagnose, fix the underlying cause, re-run the failed step. diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index ef88c7519..02cef98ec 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -1,17 +1,14 @@ --- name: new-setup -description: End-to-end NanoClaw setup for any user regardless of technical background — from zero to a named agent reachable on a real messaging channel, with sensible defaults and every post-verification step skippable. -allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(bash setup/install-node.sh) Bash(bash setup/install-docker.sh) Bash(bash setup/install-telegram.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm exec tsx scripts/init-first-agent.ts:*) Bash(pnpm run chat) Bash(pnpm run chat:*) Bash(open -a Docker) Bash(sudo systemctl start docker) Bash(node --version) Bash(tail:*) Bash(head:*) Bash(grep:*) +description: Shortest path from zero to a working two-way agent chat, for any user regardless of technical background — ends at a running NanoClaw instance with at least one CLI-reachable agent. +allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(bash setup/install-node.sh) Bash(bash setup/install-docker.sh) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm run chat) Bash(pnpm run chat:*) Bash(open -a Docker) Bash(sudo systemctl start docker) Bash(node --version) Bash(tail:*) Bash(head:*) Bash(grep:*) --- -# NanoClaw setup +# NanoClaw bare-minimum setup -Purpose of this skill is to take any user — technical or not — from zero to a named agent wired to a real messaging channel in the fewest steps possible. +Purpose of this skill is to take any user — technical or not — from zero to a two-way chat with an agent in the fewest steps possible. Done means a running NanoClaw instance with at least one agent reachable via the CLI channel. -The flow has two halves: - -- **Steps 1–6 — required.** Prerequisites, credential, service start, end-to-end ping. These run straight through. -- **Steps 7–12 — skippable.** Naming, channel wiring, QoL. Every step here is skippable: if the user says "skip", "not now", "later", or similar, move on without complaint. If they say they're done at any point, stop cleanly — don't push the remaining steps. +Only run the steps strictly required for the NanoClaw process to start and respond to the user end-to-end. Everything else is deferred to post-setup skills. Before each step, narrate to the user in your own words what's about to happen — one short, friendly sentence, no jargon. Don't read a scripted line; use the step context below to speak naturally. @@ -112,13 +109,13 @@ Start the NanoClaw background service — it relays messages between the user an `pnpm exec tsx setup/index.ts --step service` -### 6. Wire a scratch CLI agent and verify end-to-end +### 6. Wire the CLI agent and verify end-to-end **Do not narrate this step.** No "creating your first agent…", no "sending a ping…" chatter. The user's experience here is: they finished the last visible step (service), then a single success line appears. Wiring is an implementation detail at this point, not a user-facing milestone. If step 2's container build is still running in the background, join it here before proceeding — the agent needs the image. -Use `INFERRED_DISPLAY_NAME` from the probe silently. **Do not ask the user.** The CLI agent at this stage is a scratch agent whose only purpose is to verify the end-to-end pipeline (host → container → agent → back). The user's real name capture happens in step 7. +Use `INFERRED_DISPLAY_NAME` from the probe silently. **Do not ask the user.** The CLI agent at this stage is a scratch agent whose only purpose is to verify the end-to-end pipeline (host → container → agent → back). The user's real name capture happens in `/new-setup-2` when they wire a messaging channel. Run wiring and ping back-to-back, silently: @@ -129,141 +126,35 @@ pnpm run chat ping First container spin-up takes ~60s. When the agent's reply arrives, emit exactly one line to the user: -> Test Agent success, proceeding with setup +> Your agent is up, running and ready to go! If `pnpm run chat ping` times out or errors, tail `logs/nanoclaw.log`, diagnose, and fix — don't surface a half-success. > **Loose command:** `pnpm run chat ping`. Justification: this is the same command the user will keep using after setup, so verification and the real channel are one and the same. -### 7. What should the agent call you? +### 7. Chat now, or keep setting up? -Plain-prose ask (do **not** use `AskUserQuestion`): +Ask the user via `AskUserQuestion` which they'd like to do next: -> What should your agent call you? (Default: ``) +1. **Keep chatting with the agent via CLI** — happy with the CLI channel for now. +2. **Continue setup** — name the agent, wire a messaging channel, add quality-of-life extras. -Capture the answer into a local variable `OPERATOR_NAME`. **Don't persist yet** — this value is consumed by step 10's channel wiring. If the user skips or confirms the default, set `OPERATOR_NAME = INFERRED_DISPLAY_NAME`. +**If they pick "keep chatting":** print both options below, then stop. The user is chatting with the agent now, not with you — no further output from you. -### 8. What's your agent's name? +**Option 1 — from inside this Claude Code session.** Type your message with a leading `!`, which runs it as a bash command in this shell: -Plain-prose ask: +``` +!pnpm run chat your message here +``` -> What would you like to call your agent? (Default: ``) +**Option 2 — from a separate terminal.** Open a new terminal, `cd` into your nanoclaw checkout, then: -Capture as `AGENT_NAME`. If skipped, set `AGENT_NAME = OPERATOR_NAME`. Nothing persisted yet. +``` +pnpm run chat your message here +``` -### 9. Timezone - -Run `pnpm exec tsx setup/index.ts --step timezone` and parse the status block. - -- **RESOLVED_TZ is `UTC` or `Etc/UTC`** — before leaving UTC in `.env`, confirm with `AskUserQuestion`: - - - **Question**: "Your system reports UTC as the timezone. Is that right, or are you somewhere else?" - - **Header**: "Timezone" - - **Options**: - 1. `Keep UTC` — "Leave timezone as UTC." - 2. `I'm somewhere else` — "I'll name the IANA zone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`) via Other." - - If they pick "I'm somewhere else" (or type an IANA zone via Other), re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` to overwrite `.env`. If they keep UTC or skip, leave UTC in place. - -- **NEEDS_USER_INPUT=true** — autodetection failed. Use `AskUserQuestion` with the same two options above (reword the question to "Autodetection failed — what timezone are you in?"), then re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` if they supply one. If they skip, move on. - -- Otherwise — timezone is already set; move on. - -### 10. Pick a messaging channel - -Print the list as a numbered plain-prose list (too many options for `AskUserQuestion`, which caps at 4). The user replies with a number or channel name. Preserve the numbering exactly: - -> Which messaging channel should I wire your agent to? -> -> 1. **WhatsApp (native)** — `/add-whatsapp` -> 2. **WhatsApp Cloud (Meta official)** — `/add-whatsapp-cloud` -> 3. **Telegram** — `/add-telegram` -> 4. **Slack** — `/add-slack` -> 5. **Discord** — `/add-discord` -> 6. **iMessage** — `/add-imessage` -> 7. **Teams** — `/add-teams` -> 8. **Matrix** — `/add-matrix` -> 9. **Google Chat** — `/add-gchat` -> 10. **Linear** — `/add-linear` -> 11. **GitHub** — `/add-github` -> 12. **Webex** — `/add-webex` -> 13. **Resend (email)** — `/add-resend` -> 14. **Emacs** — `/add-emacs` -> -> Or say "skip" to leave this for later. - -When the user picks one: - -1. **Install the adapter.** For **Telegram**, run `bash setup/install-telegram.sh` directly — it bundles the preflight + fetch + copy + register + `pnpm install` + build from `/add-telegram` into one idempotent call. Then handle Telegram credentials inline (below) — **do not** invoke `/add-telegram` afterward; its Credentials section would generate an unapprovable `grep && sed && rm` to write `.env`. For every other channel, invoke the matching `/add-` skill via the Skill tool; it copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels also run a pairing step as part of their flow. - - **Telegram credentials (inline):** - - Walk the user through BotFather: `/newbot` → pick name + username ending in `bot` → copy the token. - - Remind them: in `@BotFather` → `/mybots` → their bot → Bot Settings → Group Privacy → **Turn off** (only needed if the bot will live in groups; DM-only can skip). - - Persist the token and sync it to the container mount with the generic setter: - - ``` - pnpm exec tsx setup/index.ts --step set-env -- \ - --key TELEGRAM_BOT_TOKEN --value "" --sync-container - ``` - -2. **Capture platform IDs.** After the `/add-` skill finishes (or after inline credentials for Telegram), you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent ` directly and follow its `PAIR_TELEGRAM_ISSUED`/`PAIR_TELEGRAM STATUS=success` blocks — `PLATFORM_ID` and `ADMIN_USER_ID` land in the success block. -3. **Wire the agent.** Run `init-first-agent.ts` in DM mode: - - ``` - pnpm exec tsx scripts/init-first-agent.ts \ - --channel \ - --user-id "" \ - --platform-id "" \ - --display-name "" \ - --agent-name "" - ``` - -4. **Announce.** On success, emit the encouragement line verbatim: - - > Your agent is now available on {channel-name}, you can already start chatting — But I encourage you to continue and finish this setup, we're almost done! - - Substitute `{channel-name}` with the friendly name (e.g. "Telegram", "WhatsApp", "Slack"). - -If the user skipped, move on to step 11. - -### 11. Host directory access - -By default, agent containers can only touch their own workspace. If the user wants the agent to read or write files in specific host directories, those paths need to go on the mount allowlist. - -Use `AskUserQuestion`: - -- **Question**: "Want your agent to read or write files in any host directories (e.g. a code project, `~/Documents`)?" -- **Header**: "Host mounts" -- **Options**: - 1. `Keep isolated` — "Agent only touches its own workspace (Recommended)." - 2. `Add host paths` — "I'll name the directories to allowlist via Other." - -If they pick "Add host paths" (or name paths via Other), invoke `/manage-mounts` via the Skill tool to add them. If they keep it isolated or skip, move on. - -### 12. Quality of life - -Optional polish. Print the list; the user may pick zero, one, or several — invoke each chosen skill in sequence: - -> Want to add any of these? Pick any that sound useful — or skip: -> -> - `/add-dashboard` — browser dashboard showing agent activity -> - `/add-compact` — `/compact` slash command for managing long sessions -> - `/add-karpathy-llm-wiki` — persistent knowledge-base memory for the agent - -If the probe reports `PLATFORM=darwin`, also offer: - -> - `/add-macos-statusbar` — macOS menu bar indicator with Start/Stop/Restart controls - -Do **not** list `/add-macos-statusbar` on Linux. If the user skips everything, just move on. - -### 13. Done - -Short wrap-up: - -> Setup complete. You can chat with your agent on {channel-name} — or via CLI with `pnpm run chat `. - -Substitute `{channel-name}` with whatever was wired in step 10. If step 10 was skipped, drop the "on {channel-name} — or" clause entirely so the line just mentions the CLI form. +**If they pick "continue setup":** hand off directly to `/new-setup-2` via the Skill tool. That follow-on flow is structured like this one (linear, skippable steps) and covers naming, messaging-channel wiring, and QoL. Invoke it immediately — do not offer a menu of individual skills. ## If anything fails -Any step that reports `STATUS: failed` in its status block: read `logs/setup.log` (or `logs/nanoclaw.log` for runtime failures), diagnose, fix the underlying cause, re-run the same `--step`. Don't bypass errors to keep moving. +Any step that reports `STATUS: failed` in its status block: read `logs/setup.log`, diagnose, fix the underlying cause, re-run the same `--step`. Don't bypass errors to keep moving. diff --git a/setup/install-discord.sh b/setup/install-discord.sh index 6f5a9c878..ee221f910 100755 --- a/setup/install-discord.sh +++ b/setup/install-discord.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-discord — bundles the preflight + install commands -# from the /add-discord skill into one idempotent script so /new-setup can +# from the /add-discord skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the Discord adapter in from the `channels` branch; appends the diff --git a/setup/install-gchat.sh b/setup/install-gchat.sh index b9166f1a1..f5c210b57 100755 --- a/setup/install-gchat.sh +++ b/setup/install-gchat.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-gchat — bundles the preflight + install commands -# from the /add-gchat skill into one idempotent script so /new-setup can +# from the /add-gchat skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the Google Chat adapter in from the `channels` branch; appends the diff --git a/setup/install-github.sh b/setup/install-github.sh index cb28bfc39..81c2977e8 100755 --- a/setup/install-github.sh +++ b/setup/install-github.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-github — bundles the preflight + install commands -# from the /add-github skill into one idempotent script so /new-setup can +# from the /add-github skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the GitHub adapter in from the `channels` branch; appends the diff --git a/setup/install-imessage.sh b/setup/install-imessage.sh index 864e12796..0b1df3467 100755 --- a/setup/install-imessage.sh +++ b/setup/install-imessage.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-imessage — bundles the preflight + install commands -# from the /add-imessage skill into one idempotent script so /new-setup can +# from the /add-imessage skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the iMessage adapter in from the `channels` branch; appends the diff --git a/setup/install-linear.sh b/setup/install-linear.sh index f8788be1f..9f42bec54 100755 --- a/setup/install-linear.sh +++ b/setup/install-linear.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-linear — bundles the preflight + install commands -# from the /add-linear skill into one idempotent script so /new-setup can +# from the /add-linear skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the Linear adapter in from the `channels` branch; appends the diff --git a/setup/install-matrix.sh b/setup/install-matrix.sh index c9854731f..06d5ccd76 100755 --- a/setup/install-matrix.sh +++ b/setup/install-matrix.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-matrix — bundles the preflight + install commands -# from the /add-matrix skill into one idempotent script so /new-setup can +# from the /add-matrix skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the Matrix adapter in from the `channels` branch; appends the diff --git a/setup/install-resend.sh b/setup/install-resend.sh index 9f18a9f96..4f0bb2eda 100755 --- a/setup/install-resend.sh +++ b/setup/install-resend.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-resend — bundles the preflight + install commands -# from the /add-resend skill into one idempotent script so /new-setup can +# from the /add-resend skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the Resend adapter in from the `channels` branch; appends the diff --git a/setup/install-slack.sh b/setup/install-slack.sh index 55d5e8573..8be6a373d 100755 --- a/setup/install-slack.sh +++ b/setup/install-slack.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-slack — bundles the preflight + install commands -# from the /add-slack skill into one idempotent script so /new-setup can +# from the /add-slack skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the Slack adapter in from the `channels` branch; appends the diff --git a/setup/install-teams.sh b/setup/install-teams.sh index 4b8c21690..cb66f67e7 100755 --- a/setup/install-teams.sh +++ b/setup/install-teams.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-teams — bundles the preflight + install commands -# from the /add-teams skill into one idempotent script so /new-setup can +# from the /add-teams skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the Teams adapter in from the `channels` branch; appends the diff --git a/setup/install-telegram.sh b/setup/install-telegram.sh index 307dba226..7eaf9e12d 100755 --- a/setup/install-telegram.sh +++ b/setup/install-telegram.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-telegram — bundles the preflight + install commands -# from the /add-telegram skill into one idempotent script so /new-setup can +# from the /add-telegram skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials and pairing. # # Copies the Telegram adapter, helpers, tests, and the pair-telegram setup diff --git a/setup/install-webex.sh b/setup/install-webex.sh index adf52fc4d..8bbbc836c 100755 --- a/setup/install-webex.sh +++ b/setup/install-webex.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-webex — bundles the preflight + install commands -# from the /add-webex skill into one idempotent script so /new-setup can +# from the /add-webex skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to credentials. # # Copies the Webex adapter in from the `channels` branch; appends the diff --git a/setup/install-whatsapp-cloud.sh b/setup/install-whatsapp-cloud.sh index 70e8e0279..377327809 100755 --- a/setup/install-whatsapp-cloud.sh +++ b/setup/install-whatsapp-cloud.sh @@ -1,7 +1,7 @@ #!/usr/bin/env bash # Setup helper: install-whatsapp-cloud — bundles the preflight + install # commands from the /add-whatsapp-cloud skill into one idempotent script so -# /new-setup can run them programmatically before continuing to credentials. +# /new-setup-2 can run them programmatically before continuing to credentials. # # Copies the WhatsApp Cloud adapter in from the `channels` branch; appends the # self-registration import; installs the pinned @chat-adapter/whatsapp package; diff --git a/setup/install-whatsapp.sh b/setup/install-whatsapp.sh index 1c62d65d4..0d307f53c 100755 --- a/setup/install-whatsapp.sh +++ b/setup/install-whatsapp.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-whatsapp — bundles the preflight + install commands -# from the /add-whatsapp skill into one idempotent script so /new-setup can +# from the /add-whatsapp skill into one idempotent script so /new-setup-2 can # run them programmatically before continuing to QR/pairing-code auth. # # Copies the native Baileys WhatsApp adapter, its whatsapp-auth and groups From 40ddc94d0ad0d3c8d3dc7c8a5e3f4179d13ab7ab Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 15:20:06 +0300 Subject: [PATCH 63/95] Revert "fix(init-first-agent): seed welcome via inbound.db; drop --no-cli-bonus" This reverts commit 9fe529984a646eb71c82e29a0a42c0959f65eb39. --- .claude/skills/init-first-agent/SKILL.md | 4 +- .claude/skills/new-setup-2/SKILL.md | 5 +- scripts/init-first-agent.ts | 157 +++++++++++++++++------ 3 files changed, 121 insertions(+), 45 deletions(-) diff --git a/.claude/skills/init-first-agent/SKILL.md b/.claude/skills/init-first-agent/SKILL.md index 68eab8760..6b110d37f 100644 --- a/.claude/skills/init-first-agent/SKILL.md +++ b/.claude/skills/init-first-agent/SKILL.md @@ -87,13 +87,13 @@ The script: 2. Creates the `agent_groups` row and calls `initGroupFilesystem` at `groups/dm-with-/`. 3. Reuses or creates the DM `messaging_groups` row. 4. Wires them via `messaging_group_agents` (which auto-creates the companion `agent_destinations` row). -5. Seeds the welcome message directly into the DM session's `inbound.db` (sender tagged `System`). The running service's host-sweep picks it up on the next pass and wakes the container through the normal path — no CLI-socket hand-off, no `cli:local` identity on the new agent's permission surface. +5. Hands the welcome message to the running service via its CLI socket (`data/cli.sock`), targeting the DM messaging group. The service routes it into the DM session, which wakes the container synchronously. If the socket isn't reachable (service down), falls back to a direct `inbound.db` write that the next host sweep picks up. Show the script's output to the user. ## 5. Verify -The welcome is written to `inbound.db` immediately; the wait is host-sweep pickup (≤60s) plus container cold-start (~60s on first launch) before the agent processes the message and the reply flows through `outbound.db` to the channel. +The welcome DM is queued synchronously; the only wait is container cold-start (~60s on first launch) before the agent processes the message and the reply flows through `outbound.db` to the channel. Do not tail the log or poll in a sleep loop. Ask the user in plain text: diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md index 8d75cd3f7..1b98443aa 100644 --- a/.claude/skills/new-setup-2/SKILL.md +++ b/.claude/skills/new-setup-2/SKILL.md @@ -92,7 +92,7 @@ When the user picks one: ``` 2. **Capture platform IDs.** After the `/add-` skill finishes (or after inline credentials for Telegram), you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent ` directly and follow its `PAIR_TELEGRAM_ISSUED`/`PAIR_TELEGRAM STATUS=success` blocks — `PLATFORM_ID` and `ADMIN_USER_ID` land in the success block. -3. **Wire the agent.** Run `init-first-agent.ts` in DM mode: +3. **Wire the agent.** Run `init-first-agent.ts` in DM mode with `--no-cli-bonus` (this keeps the new agent off the CLI messaging group so the pre-existing throwaway agent still owns CLI routing cleanly): ``` pnpm exec tsx scripts/init-first-agent.ts \ @@ -100,7 +100,8 @@ When the user picks one: --user-id "" \ --platform-id "" \ --display-name "" \ - --agent-name "" + --agent-name "" \ + --no-cli-bonus ``` 4. **Announce.** On success, emit the encouragement line verbatim: diff --git a/scripts/init-first-agent.ts b/scripts/init-first-agent.ts index 9dc8b6de4..29ca6d444 100644 --- a/scripts/init-first-agent.ts +++ b/scripts/init-first-agent.ts @@ -1,25 +1,24 @@ /** * Init the first (or Nth) NanoClaw v2 agent for a DM channel. * - * Wires a real DM channel (discord, telegram, etc.) to a new agent group, - * then seeds a welcome message directly into the session's inbound DB. The - * running service's host-sweep picks it up on its next pass (within - * SWEEP_INTERVAL_MS) and wakes the container through the normal path; the - * agent introduces itself via the channel. + * Wires a real DM channel (discord, telegram, etc.) to a new agent group + * (and the local CLI channel as a convenience bonus), then hands a welcome + * message to the running service via its CLI socket. The service routes + * that message into the DM session, which wakes the container synchronously — + * the agent processes the welcome and DMs the operator through the normal + * delivery path. * - * CLI channel wiring is NOT touched here — `scripts/init-cli-agent.ts` owns - * the cli/local messaging group and its scratch agent. Keeping the two - * scripts disjoint means no `cli:local` identity ever appears on the new - * agent's permission surface, so the unknown-sender approval card that used - * to fire when the welcome was queued via the CLI admin socket no longer - * happens. + * For the CLI-only scratch agent used during `/new-setup`, see + * `scripts/init-cli-agent.ts` — that's a distinct flow and doesn't run + * through here. * * Creates/reuses: user, owner grant (if none), agent group + filesystem, - * messaging group, wiring, session, welcome message. + * messaging group(s), wiring. * - * Runs alongside the service (WAL-mode sqlite) — does NOT initialize channel - * adapters, so there's no Gateway conflict. No IPC to the service is needed; - * the sweep is the sole hand-off. + * Runs alongside the service (WAL-mode sqlite + CLI socket IPC) — does NOT + * initialize channel adapters, so there's no Gateway conflict. Requires + * the service to be running: the welcome hand-off goes over the CLI socket + * and fails loudly if the service isn't up. * * Usage: * pnpm exec tsx scripts/init-first-agent.ts \ @@ -28,11 +27,13 @@ * --platform-id discord:@me:1491573333382523708 \ * --display-name "Gavriel" \ * [--agent-name "Andy"] \ - * [--welcome "System instruction: ..."] + * [--welcome "System instruction: ..."] \ + * [--no-cli-bonus] * * For direct-addressable channels (telegram, whatsapp, etc.), --platform-id * is typically the same as the handle in --user-id, with the channel prefix. */ +import net from 'net'; import path from 'path'; import { DATA_DIR } from '../src/config.js'; @@ -49,10 +50,10 @@ import { normalizeName } from '../src/modules/agent-to-agent/db/agent-destinatio import { grantRole, hasAnyOwner } from '../src/modules/permissions/db/user-roles.js'; import { upsertUser } from '../src/modules/permissions/db/users.js'; import { initGroupFilesystem } from '../src/group-init.js'; -import { resolveSession, writeSessionMessage } from '../src/session-manager.js'; import type { AgentGroup, MessagingGroup } from '../src/types.js'; interface Args { + noCliBonus: boolean; channel: string; userId: string; platformId: string; @@ -64,12 +65,18 @@ interface Args { const DEFAULT_WELCOME = 'System instruction: run /welcome to introduce yourself to the user on this new channel.'; +const CLI_CHANNEL = 'cli'; +const CLI_PLATFORM_ID = 'local'; + function parseArgs(argv: string[]): Args { - const out: Partial = {}; + const out: Partial = { noCliBonus: false }; for (let i = 0; i < argv.length; i++) { const key = argv[i]; const val = argv[i + 1]; switch (key) { + case '--no-cli-bonus': + out.noCliBonus = true; + break; case '--channel': out.channel = (val ?? '').toLowerCase(); i++; @@ -108,6 +115,7 @@ function parseArgs(argv: string[]): Args { } return { + noCliBonus: out.noCliBonus ?? false, channel: out.channel!, userId: out.userId!, platformId: out.platformId!, @@ -129,6 +137,24 @@ function generateId(prefix: string): string { return `${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; } +function ensureCliMessagingGroup(now: string): MessagingGroup { + let cliMg = getMessagingGroupByPlatform(CLI_CHANNEL, CLI_PLATFORM_ID); + if (cliMg) return cliMg; + + cliMg = { + id: generateId('mg'), + channel_type: CLI_CHANNEL, + platform_id: CLI_PLATFORM_ID, + name: 'Local CLI', + is_group: 0, + unknown_sender_policy: 'public', + created_at: now, + }; + createMessagingGroup(cliMg); + console.log(`Created CLI messaging group: ${cliMg.id}`); + return cliMg; +} + function wireIfMissing(mg: MessagingGroup, ag: AgentGroup, now: string, label: string): void { const existing = getMessagingGroupAgentByPair(mg.id, ag.id); if (existing) { @@ -139,8 +165,9 @@ function wireIfMissing(mg: MessagingGroup, ag: AgentGroup, now: string, label: s id: generateId('mga'), messaging_group_id: mg.id, agent_group_id: ag.id, - // DMs default to "respond to everything" via a '.' regex. Group chats - // default to mention-only; admins can upgrade via /manage-channels. + // DM / CLI (is_group=0) default to "respond to everything" via a '.' regex. + // Group chats default to mention-only; admins can upgrade to mention-sticky + // via /manage-channels once the agent is in use. engage_mode: mg.is_group === 0 ? 'pattern' : 'mention', engage_pattern: mg.is_group === 0 ? '.' : null, sender_scope: 'all', @@ -225,40 +252,88 @@ async function main(): Promise { console.log(`Reusing messaging group: ${dmMg.id} (${platformId})`); } - // 4. Wire DM. + // 4. Wire DM (auto-creates companion agent_destinations row) and, + // unless suppressed, also wire the CLI channel so `pnpm run chat` works + // against the new agent immediately. `/new-setup-2` sets --no-cli-bonus + // so the scratch CLI agent from `/new-setup` keeps owning CLI routing. wireIfMissing(dmMg, ag, now, 'dm'); + if (!args.noCliBonus) { + const cliMg = ensureCliMessagingGroup(now); + wireIfMissing(cliMg, ag, now, 'cli-bonus'); + } - // 5. Seed the welcome directly into the session's inbound.db. The running - // service's sweep will observe trigger=1 and wake the container on its next - // pass — no IPC, no CLI socket, no `cli:local` sender in the router path. - seedWelcome(ag.id, dmMg, args.welcome); + // 5. Welcome delivery over the CLI socket. Router picks up the line, + // writes the message into the DM session's inbound.db, and wakes the + // container synchronously — no sweep wait. + await sendWelcomeViaCliSocket(dmMg, args.welcome); console.log(''); console.log('Init complete.'); console.log(` owner: ${userId}${promotedToOwner ? ' (promoted on first owner)' : ''}`); console.log(` agent: ${ag.name} [${ag.id}] @ groups/${folder}`); console.log(` channel: ${args.channel} ${dmMg.platform_id}`); + if (!args.noCliBonus) { + console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``); + } console.log(''); - console.log('Welcome seeded — the agent will greet you on the next sweep pass.'); + console.log('Welcome DM queued — the agent will greet you shortly.'); } /** - * Write the welcome as a due inbound message on a shared session for the - * new agent group + messaging group pair. Sender is tagged "System" — the - * welcome carries no real user identity and never crosses the router's - * sender-approval gate. + * Hand the welcome to the running service via its CLI Unix socket. The + * service's CLI adapter receives `{text, to}`, builds an InboundEvent + * targeting the DM messaging group, and calls routeInbound(). Router writes + * the message into inbound.db and wakes the container synchronously. + * + * Throws if the socket isn't reachable — this script requires the service + * to be running. */ -function seedWelcome(agentGroupId: string, mg: MessagingGroup, welcome: string): void { - const { session } = resolveSession(agentGroupId, mg.id, null, 'shared'); - writeSessionMessage(agentGroupId, session.id, { - id: generateId('welcome'), - kind: 'chat', - timestamp: new Date().toISOString(), - channelType: mg.channel_type, - platformId: mg.platform_id, - threadId: null, - content: JSON.stringify({ text: welcome, sender: 'System' }), - trigger: 1, +async function sendWelcomeViaCliSocket(dmMg: MessagingGroup, welcome: string): Promise { + const sockPath = path.join(DATA_DIR, 'cli.sock'); + + await new Promise((resolve, reject) => { + const socket = net.connect(sockPath); + let settled = false; + + const settle = (err: Error | null) => { + if (settled) return; + settled = true; + try { + socket.end(); + } catch { + /* noop */ + } + if (err) reject(err); + else resolve(); + }; + + socket.once('error', (err) => + settle( + new Error( + `CLI socket at ${sockPath} not reachable: ${err.message}. Is the NanoClaw service running?`, + ), + ), + ); + socket.once('connect', () => { + const payload = + JSON.stringify({ + text: welcome, + to: { + channelType: dmMg.channel_type, + platformId: dmMg.platform_id, + threadId: null, + }, + }) + '\n'; + socket.write(payload, (err) => { + if (err) { + settle(err); + return; + } + // Brief flush delay so the router picks up the line before we close. + // Router handles it synchronously once read, so 50ms is plenty. + setTimeout(() => settle(null), 50); + }); + }); }); } From 1f7508f2aac1f911511287a547089f2148532e80 Mon Sep 17 00:00:00 2001 From: Koshkoshinsk Date: Tue, 21 Apr 2026 10:37:06 +0000 Subject: [PATCH 64/95] refactor(skills): merge /new-setup-2 into unified /new-setup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Collapses the two-phase setup into a single linear skill: steps 1-6 (prereqs through end-to-end CLI ping) run straight through, steps 7-13 (naming, timezone, channel wiring, mounts, QoL, done) are skippable. Drops the "chat now vs. continue" branch point — after the ping the flow emits "Test Agent success, proceeding with setup" and continues directly into the naming questions. Also updates stale `/new-setup-2` header comments in setup/install-*.sh. Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/new-setup-2/SKILL.md | 155 ---------------------------- .claude/skills/new-setup/SKILL.md | 155 +++++++++++++++++++++++----- setup/install-discord.sh | 2 +- setup/install-gchat.sh | 2 +- setup/install-github.sh | 2 +- setup/install-imessage.sh | 2 +- setup/install-linear.sh | 2 +- setup/install-matrix.sh | 2 +- setup/install-resend.sh | 2 +- setup/install-slack.sh | 2 +- setup/install-teams.sh | 2 +- setup/install-telegram.sh | 2 +- setup/install-webex.sh | 2 +- setup/install-whatsapp-cloud.sh | 2 +- setup/install-whatsapp.sh | 2 +- 15 files changed, 145 insertions(+), 191 deletions(-) delete mode 100644 .claude/skills/new-setup-2/SKILL.md diff --git a/.claude/skills/new-setup-2/SKILL.md b/.claude/skills/new-setup-2/SKILL.md deleted file mode 100644 index 1b98443aa..000000000 --- a/.claude/skills/new-setup-2/SKILL.md +++ /dev/null @@ -1,155 +0,0 @@ ---- -name: new-setup-2 -description: Follow-on to /new-setup. Captures the operator and agent names, wires a real messaging channel, and adds quality-of-life extras. Linear rollthrough; every step is skippable. Invoked when the user picks "continue setup" at the end of /new-setup. -allowed-tools: Bash(bash setup/probe.sh) Bash(bash setup/install-telegram.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm exec tsx scripts/init-first-agent.ts:*) Bash(tail:*) Bash(head:*) Bash(grep:*) ---- - -# NanoClaw phase-2 setup - -Runs after `/new-setup`. At this point the host is running and a throwaway CLI-only agent exists (used during /new-setup for the end-to-end ping check — inferred name, not user-facing). This flow creates the **real** agent and wires it to a messaging channel. - -**Linear — one step at a time.** Every step is skippable: if the user says "skip", "not now", "later", or similar, move on without complaint. If they say they're done at any point, stop cleanly — don't push the remaining steps. - -Before each step, narrate in your own words what's about to happen — one short, friendly sentence, no jargon. Match the tone of `/new-setup`. - -## Current state - -!`bash setup/probe.sh` - -Parse the probe block above for `INFERRED_DISPLAY_NAME` and `PLATFORM` — referenced below. - -## Steps - -### 1. What should the agent call you? - -Plain-prose ask (do **not** use `AskUserQuestion`): - -> What should your agent call you? (Default: ``) - -Capture the answer into a local variable `OPERATOR_NAME`. **Don't persist yet** — this value is consumed by step 3's channel wiring. If the user skips or confirms the default, set `OPERATOR_NAME = INFERRED_DISPLAY_NAME`. - -### 2. What's your agent's name? - -Plain-prose ask: - -> What would you like to call your agent? (Default: ``) - -Capture as `AGENT_NAME`. If skipped, set `AGENT_NAME = OPERATOR_NAME`. Nothing persisted yet. - -### 3. Timezone - -Run `pnpm exec tsx setup/index.ts --step timezone` and parse the status block. - -- **RESOLVED_TZ is `UTC` or `Etc/UTC`** — before leaving UTC in `.env`, confirm with `AskUserQuestion`: - - - **Question**: "Your system reports UTC as the timezone. Is that right, or are you somewhere else?" - - **Header**: "Timezone" - - **Options**: - 1. `Keep UTC` — "Leave timezone as UTC." - 2. `I'm somewhere else` — "I'll name the IANA zone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`) via Other." - - If they pick "I'm somewhere else" (or type an IANA zone via Other), re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` to overwrite `.env`. If they keep UTC or skip, leave UTC in place. - -- **NEEDS_USER_INPUT=true** — autodetection failed. Use `AskUserQuestion` with the same two options above (reword the question to "Autodetection failed — what timezone are you in?"), then re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` if they supply one. If they skip, move on. - -- Otherwise — timezone is already set; move on. - -### 4. Pick a messaging channel - -Print the list as a numbered plain-prose list (too many options for `AskUserQuestion`, which caps at 4). The user replies with a number or channel name. Preserve the numbering exactly: - -> Which messaging channel should I wire your agent to? -> -> 1. **WhatsApp (native)** — `/add-whatsapp` -> 2. **WhatsApp Cloud (Meta official)** — `/add-whatsapp-cloud` -> 3. **Telegram** — `/add-telegram` -> 4. **Slack** — `/add-slack` -> 5. **Discord** — `/add-discord` -> 6. **iMessage** — `/add-imessage` -> 7. **Teams** — `/add-teams` -> 8. **Matrix** — `/add-matrix` -> 9. **Google Chat** — `/add-gchat` -> 10. **Linear** — `/add-linear` -> 11. **GitHub** — `/add-github` -> 12. **Webex** — `/add-webex` -> 13. **Resend (email)** — `/add-resend` -> 14. **Emacs** — `/add-emacs` -> -> Or say "skip" to leave this for later. - -When the user picks one: - -1. **Install the adapter.** For **Telegram**, run `bash setup/install-telegram.sh` directly — it bundles the preflight + fetch + copy + register + `pnpm install` + build from `/add-telegram` into one idempotent call. Then handle Telegram credentials inline (below) — **do not** invoke `/add-telegram` afterward; its Credentials section would generate an unapprovable `grep && sed && rm` to write `.env`. For every other channel, invoke the matching `/add-` skill via the Skill tool; it copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels also run a pairing step as part of their flow. - - **Telegram credentials (inline):** - - Walk the user through BotFather: `/newbot` → pick name + username ending in `bot` → copy the token. - - Remind them: in `@BotFather` → `/mybots` → their bot → Bot Settings → Group Privacy → **Turn off** (only needed if the bot will live in groups; DM-only can skip). - - Persist the token and sync it to the container mount with the generic setter: - - ``` - pnpm exec tsx setup/index.ts --step set-env -- \ - --key TELEGRAM_BOT_TOKEN --value "" --sync-container - ``` - -2. **Capture platform IDs.** After the `/add-` skill finishes (or after inline credentials for Telegram), you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent ` directly and follow its `PAIR_TELEGRAM_ISSUED`/`PAIR_TELEGRAM STATUS=success` blocks — `PLATFORM_ID` and `ADMIN_USER_ID` land in the success block. -3. **Wire the agent.** Run `init-first-agent.ts` in DM mode with `--no-cli-bonus` (this keeps the new agent off the CLI messaging group so the pre-existing throwaway agent still owns CLI routing cleanly): - - ``` - pnpm exec tsx scripts/init-first-agent.ts \ - --channel \ - --user-id "" \ - --platform-id "" \ - --display-name "" \ - --agent-name "" \ - --no-cli-bonus - ``` - -4. **Announce.** On success, emit the encouragement line verbatim: - - > Your agent is now available on {channel-name}, you can already start chatting — But I encourage you to continue and finish this setup, we're almost done! - - Substitute `{channel-name}` with the friendly name (e.g. "Telegram", "WhatsApp", "Slack"). - -If the user skipped, move on to step 5. - -### 5. Host directory access - -By default, agent containers can only touch their own workspace. If the user wants the agent to read or write files in specific host directories, those paths need to go on the mount allowlist. - -Use `AskUserQuestion`: - -- **Question**: "Want your agent to read or write files in any host directories (e.g. a code project, `~/Documents`)?" -- **Header**: "Host mounts" -- **Options**: - 1. `Keep isolated` — "Agent only touches its own workspace (Recommended)." - 2. `Add host paths` — "I'll name the directories to allowlist via Other." - -If they pick "Add host paths" (or name paths via Other), invoke `/manage-mounts` via the Skill tool to add them. If they keep it isolated or skip, move on. - -### 6. Quality of life - -Optional polish. Print the list; the user may pick zero, one, or several — invoke each chosen skill in sequence: - -> Want to add any of these? Pick any that sound useful — or skip: -> -> - `/add-dashboard` — browser dashboard showing agent activity -> - `/add-compact` — `/compact` slash command for managing long sessions -> - `/add-karpathy-llm-wiki` — persistent knowledge-base memory for the agent - -If the probe reports `PLATFORM=darwin`, also offer: - -> - `/add-macos-statusbar` — macOS menu bar indicator with Start/Stop/Restart controls - -Do **not** list `/add-macos-statusbar` on Linux. If the user skips everything, just move on. - -### 7. Done - -Short wrap-up: - -> Setup complete. You can chat with your agent on {channel-name} — or via CLI with `pnpm run chat `. - -Substitute `{channel-name}` with whatever was wired in step 4. If step 4 was skipped, drop the "on {channel-name} — or" clause entirely so the line just mentions the CLI form. - -## If anything fails - -Same rule as `/new-setup`: don't bypass errors to keep moving. Read `logs/setup.log` or `logs/nanoclaw.log`, diagnose, fix the underlying cause, re-run the failed step. diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index 02cef98ec..ef88c7519 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -1,14 +1,17 @@ --- name: new-setup -description: Shortest path from zero to a working two-way agent chat, for any user regardless of technical background — ends at a running NanoClaw instance with at least one CLI-reachable agent. -allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(bash setup/install-node.sh) Bash(bash setup/install-docker.sh) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm run chat) Bash(pnpm run chat:*) Bash(open -a Docker) Bash(sudo systemctl start docker) Bash(node --version) Bash(tail:*) Bash(head:*) Bash(grep:*) +description: End-to-end NanoClaw setup for any user regardless of technical background — from zero to a named agent reachable on a real messaging channel, with sensible defaults and every post-verification step skippable. +allowed-tools: Bash(bash setup.sh) Bash(bash setup/probe.sh) Bash(bash setup/install-node.sh) Bash(bash setup/install-docker.sh) Bash(bash setup/install-telegram.sh) Bash(bash setup/install-telegram.sh:*) Bash(pnpm exec tsx setup/index.ts:*) Bash(pnpm exec tsx scripts/init-first-agent.ts:*) Bash(pnpm run chat) Bash(pnpm run chat:*) Bash(open -a Docker) Bash(sudo systemctl start docker) Bash(node --version) Bash(tail:*) Bash(head:*) Bash(grep:*) --- -# NanoClaw bare-minimum setup +# NanoClaw setup -Purpose of this skill is to take any user — technical or not — from zero to a two-way chat with an agent in the fewest steps possible. Done means a running NanoClaw instance with at least one agent reachable via the CLI channel. +Purpose of this skill is to take any user — technical or not — from zero to a named agent wired to a real messaging channel in the fewest steps possible. -Only run the steps strictly required for the NanoClaw process to start and respond to the user end-to-end. Everything else is deferred to post-setup skills. +The flow has two halves: + +- **Steps 1–6 — required.** Prerequisites, credential, service start, end-to-end ping. These run straight through. +- **Steps 7–12 — skippable.** Naming, channel wiring, QoL. Every step here is skippable: if the user says "skip", "not now", "later", or similar, move on without complaint. If they say they're done at any point, stop cleanly — don't push the remaining steps. Before each step, narrate to the user in your own words what's about to happen — one short, friendly sentence, no jargon. Don't read a scripted line; use the step context below to speak naturally. @@ -109,13 +112,13 @@ Start the NanoClaw background service — it relays messages between the user an `pnpm exec tsx setup/index.ts --step service` -### 6. Wire the CLI agent and verify end-to-end +### 6. Wire a scratch CLI agent and verify end-to-end **Do not narrate this step.** No "creating your first agent…", no "sending a ping…" chatter. The user's experience here is: they finished the last visible step (service), then a single success line appears. Wiring is an implementation detail at this point, not a user-facing milestone. If step 2's container build is still running in the background, join it here before proceeding — the agent needs the image. -Use `INFERRED_DISPLAY_NAME` from the probe silently. **Do not ask the user.** The CLI agent at this stage is a scratch agent whose only purpose is to verify the end-to-end pipeline (host → container → agent → back). The user's real name capture happens in `/new-setup-2` when they wire a messaging channel. +Use `INFERRED_DISPLAY_NAME` from the probe silently. **Do not ask the user.** The CLI agent at this stage is a scratch agent whose only purpose is to verify the end-to-end pipeline (host → container → agent → back). The user's real name capture happens in step 7. Run wiring and ping back-to-back, silently: @@ -126,35 +129,141 @@ pnpm run chat ping First container spin-up takes ~60s. When the agent's reply arrives, emit exactly one line to the user: -> Your agent is up, running and ready to go! +> Test Agent success, proceeding with setup If `pnpm run chat ping` times out or errors, tail `logs/nanoclaw.log`, diagnose, and fix — don't surface a half-success. > **Loose command:** `pnpm run chat ping`. Justification: this is the same command the user will keep using after setup, so verification and the real channel are one and the same. -### 7. Chat now, or keep setting up? +### 7. What should the agent call you? -Ask the user via `AskUserQuestion` which they'd like to do next: +Plain-prose ask (do **not** use `AskUserQuestion`): -1. **Keep chatting with the agent via CLI** — happy with the CLI channel for now. -2. **Continue setup** — name the agent, wire a messaging channel, add quality-of-life extras. +> What should your agent call you? (Default: ``) -**If they pick "keep chatting":** print both options below, then stop. The user is chatting with the agent now, not with you — no further output from you. +Capture the answer into a local variable `OPERATOR_NAME`. **Don't persist yet** — this value is consumed by step 10's channel wiring. If the user skips or confirms the default, set `OPERATOR_NAME = INFERRED_DISPLAY_NAME`. -**Option 1 — from inside this Claude Code session.** Type your message with a leading `!`, which runs it as a bash command in this shell: +### 8. What's your agent's name? -``` -!pnpm run chat your message here -``` +Plain-prose ask: -**Option 2 — from a separate terminal.** Open a new terminal, `cd` into your nanoclaw checkout, then: +> What would you like to call your agent? (Default: ``) -``` -pnpm run chat your message here -``` +Capture as `AGENT_NAME`. If skipped, set `AGENT_NAME = OPERATOR_NAME`. Nothing persisted yet. -**If they pick "continue setup":** hand off directly to `/new-setup-2` via the Skill tool. That follow-on flow is structured like this one (linear, skippable steps) and covers naming, messaging-channel wiring, and QoL. Invoke it immediately — do not offer a menu of individual skills. +### 9. Timezone + +Run `pnpm exec tsx setup/index.ts --step timezone` and parse the status block. + +- **RESOLVED_TZ is `UTC` or `Etc/UTC`** — before leaving UTC in `.env`, confirm with `AskUserQuestion`: + + - **Question**: "Your system reports UTC as the timezone. Is that right, or are you somewhere else?" + - **Header**: "Timezone" + - **Options**: + 1. `Keep UTC` — "Leave timezone as UTC." + 2. `I'm somewhere else` — "I'll name the IANA zone (e.g. `America/New_York`, `Europe/London`, `Asia/Tokyo`) via Other." + + If they pick "I'm somewhere else" (or type an IANA zone via Other), re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` to overwrite `.env`. If they keep UTC or skip, leave UTC in place. + +- **NEEDS_USER_INPUT=true** — autodetection failed. Use `AskUserQuestion` with the same two options above (reword the question to "Autodetection failed — what timezone are you in?"), then re-run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` if they supply one. If they skip, move on. + +- Otherwise — timezone is already set; move on. + +### 10. Pick a messaging channel + +Print the list as a numbered plain-prose list (too many options for `AskUserQuestion`, which caps at 4). The user replies with a number or channel name. Preserve the numbering exactly: + +> Which messaging channel should I wire your agent to? +> +> 1. **WhatsApp (native)** — `/add-whatsapp` +> 2. **WhatsApp Cloud (Meta official)** — `/add-whatsapp-cloud` +> 3. **Telegram** — `/add-telegram` +> 4. **Slack** — `/add-slack` +> 5. **Discord** — `/add-discord` +> 6. **iMessage** — `/add-imessage` +> 7. **Teams** — `/add-teams` +> 8. **Matrix** — `/add-matrix` +> 9. **Google Chat** — `/add-gchat` +> 10. **Linear** — `/add-linear` +> 11. **GitHub** — `/add-github` +> 12. **Webex** — `/add-webex` +> 13. **Resend (email)** — `/add-resend` +> 14. **Emacs** — `/add-emacs` +> +> Or say "skip" to leave this for later. + +When the user picks one: + +1. **Install the adapter.** For **Telegram**, run `bash setup/install-telegram.sh` directly — it bundles the preflight + fetch + copy + register + `pnpm install` + build from `/add-telegram` into one idempotent call. Then handle Telegram credentials inline (below) — **do not** invoke `/add-telegram` afterward; its Credentials section would generate an unapprovable `grep && sed && rm` to write `.env`. For every other channel, invoke the matching `/add-` skill via the Skill tool; it copies the adapter source in from the `channels` branch, registers it, installs the pinned npm package, and handles credentials. Some channels also run a pairing step as part of their flow. + + **Telegram credentials (inline):** + - Walk the user through BotFather: `/newbot` → pick name + username ending in `bot` → copy the token. + - Remind them: in `@BotFather` → `/mybots` → their bot → Bot Settings → Group Privacy → **Turn off** (only needed if the bot will live in groups; DM-only can skip). + - Persist the token and sync it to the container mount with the generic setter: + + ``` + pnpm exec tsx setup/index.ts --step set-env -- \ + --key TELEGRAM_BOT_TOKEN --value "" --sync-container + ``` + +2. **Capture platform IDs.** After the `/add-` skill finishes (or after inline credentials for Telegram), you need two values: the operator's user-id on that platform, and the chat/channel platform-id. Each channel surfaces these differently — consult the **Channel Info** section at the bottom of that skill's `SKILL.md` for the exact path. For Telegram, run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent ` directly and follow its `PAIR_TELEGRAM_ISSUED`/`PAIR_TELEGRAM STATUS=success` blocks — `PLATFORM_ID` and `ADMIN_USER_ID` land in the success block. +3. **Wire the agent.** Run `init-first-agent.ts` in DM mode: + + ``` + pnpm exec tsx scripts/init-first-agent.ts \ + --channel \ + --user-id "" \ + --platform-id "" \ + --display-name "" \ + --agent-name "" + ``` + +4. **Announce.** On success, emit the encouragement line verbatim: + + > Your agent is now available on {channel-name}, you can already start chatting — But I encourage you to continue and finish this setup, we're almost done! + + Substitute `{channel-name}` with the friendly name (e.g. "Telegram", "WhatsApp", "Slack"). + +If the user skipped, move on to step 11. + +### 11. Host directory access + +By default, agent containers can only touch their own workspace. If the user wants the agent to read or write files in specific host directories, those paths need to go on the mount allowlist. + +Use `AskUserQuestion`: + +- **Question**: "Want your agent to read or write files in any host directories (e.g. a code project, `~/Documents`)?" +- **Header**: "Host mounts" +- **Options**: + 1. `Keep isolated` — "Agent only touches its own workspace (Recommended)." + 2. `Add host paths` — "I'll name the directories to allowlist via Other." + +If they pick "Add host paths" (or name paths via Other), invoke `/manage-mounts` via the Skill tool to add them. If they keep it isolated or skip, move on. + +### 12. Quality of life + +Optional polish. Print the list; the user may pick zero, one, or several — invoke each chosen skill in sequence: + +> Want to add any of these? Pick any that sound useful — or skip: +> +> - `/add-dashboard` — browser dashboard showing agent activity +> - `/add-compact` — `/compact` slash command for managing long sessions +> - `/add-karpathy-llm-wiki` — persistent knowledge-base memory for the agent + +If the probe reports `PLATFORM=darwin`, also offer: + +> - `/add-macos-statusbar` — macOS menu bar indicator with Start/Stop/Restart controls + +Do **not** list `/add-macos-statusbar` on Linux. If the user skips everything, just move on. + +### 13. Done + +Short wrap-up: + +> Setup complete. You can chat with your agent on {channel-name} — or via CLI with `pnpm run chat `. + +Substitute `{channel-name}` with whatever was wired in step 10. If step 10 was skipped, drop the "on {channel-name} — or" clause entirely so the line just mentions the CLI form. ## If anything fails -Any step that reports `STATUS: failed` in its status block: read `logs/setup.log`, diagnose, fix the underlying cause, re-run the same `--step`. Don't bypass errors to keep moving. +Any step that reports `STATUS: failed` in its status block: read `logs/setup.log` (or `logs/nanoclaw.log` for runtime failures), diagnose, fix the underlying cause, re-run the same `--step`. Don't bypass errors to keep moving. diff --git a/setup/install-discord.sh b/setup/install-discord.sh index ee221f910..6f5a9c878 100755 --- a/setup/install-discord.sh +++ b/setup/install-discord.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-discord — bundles the preflight + install commands -# from the /add-discord skill into one idempotent script so /new-setup-2 can +# from the /add-discord skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Discord adapter in from the `channels` branch; appends the diff --git a/setup/install-gchat.sh b/setup/install-gchat.sh index f5c210b57..b9166f1a1 100755 --- a/setup/install-gchat.sh +++ b/setup/install-gchat.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-gchat — bundles the preflight + install commands -# from the /add-gchat skill into one idempotent script so /new-setup-2 can +# from the /add-gchat skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Google Chat adapter in from the `channels` branch; appends the diff --git a/setup/install-github.sh b/setup/install-github.sh index 81c2977e8..cb28bfc39 100755 --- a/setup/install-github.sh +++ b/setup/install-github.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-github — bundles the preflight + install commands -# from the /add-github skill into one idempotent script so /new-setup-2 can +# from the /add-github skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the GitHub adapter in from the `channels` branch; appends the diff --git a/setup/install-imessage.sh b/setup/install-imessage.sh index 0b1df3467..864e12796 100755 --- a/setup/install-imessage.sh +++ b/setup/install-imessage.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-imessage — bundles the preflight + install commands -# from the /add-imessage skill into one idempotent script so /new-setup-2 can +# from the /add-imessage skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the iMessage adapter in from the `channels` branch; appends the diff --git a/setup/install-linear.sh b/setup/install-linear.sh index 9f42bec54..f8788be1f 100755 --- a/setup/install-linear.sh +++ b/setup/install-linear.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-linear — bundles the preflight + install commands -# from the /add-linear skill into one idempotent script so /new-setup-2 can +# from the /add-linear skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Linear adapter in from the `channels` branch; appends the diff --git a/setup/install-matrix.sh b/setup/install-matrix.sh index 06d5ccd76..c9854731f 100755 --- a/setup/install-matrix.sh +++ b/setup/install-matrix.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-matrix — bundles the preflight + install commands -# from the /add-matrix skill into one idempotent script so /new-setup-2 can +# from the /add-matrix skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Matrix adapter in from the `channels` branch; appends the diff --git a/setup/install-resend.sh b/setup/install-resend.sh index 4f0bb2eda..9f18a9f96 100755 --- a/setup/install-resend.sh +++ b/setup/install-resend.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-resend — bundles the preflight + install commands -# from the /add-resend skill into one idempotent script so /new-setup-2 can +# from the /add-resend skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Resend adapter in from the `channels` branch; appends the diff --git a/setup/install-slack.sh b/setup/install-slack.sh index 8be6a373d..55d5e8573 100755 --- a/setup/install-slack.sh +++ b/setup/install-slack.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-slack — bundles the preflight + install commands -# from the /add-slack skill into one idempotent script so /new-setup-2 can +# from the /add-slack skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Slack adapter in from the `channels` branch; appends the diff --git a/setup/install-teams.sh b/setup/install-teams.sh index cb66f67e7..4b8c21690 100755 --- a/setup/install-teams.sh +++ b/setup/install-teams.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-teams — bundles the preflight + install commands -# from the /add-teams skill into one idempotent script so /new-setup-2 can +# from the /add-teams skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Teams adapter in from the `channels` branch; appends the diff --git a/setup/install-telegram.sh b/setup/install-telegram.sh index 7eaf9e12d..307dba226 100755 --- a/setup/install-telegram.sh +++ b/setup/install-telegram.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-telegram — bundles the preflight + install commands -# from the /add-telegram skill into one idempotent script so /new-setup-2 can +# from the /add-telegram skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials and pairing. # # Copies the Telegram adapter, helpers, tests, and the pair-telegram setup diff --git a/setup/install-webex.sh b/setup/install-webex.sh index 8bbbc836c..adf52fc4d 100755 --- a/setup/install-webex.sh +++ b/setup/install-webex.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-webex — bundles the preflight + install commands -# from the /add-webex skill into one idempotent script so /new-setup-2 can +# from the /add-webex skill into one idempotent script so /new-setup can # run them programmatically before continuing to credentials. # # Copies the Webex adapter in from the `channels` branch; appends the diff --git a/setup/install-whatsapp-cloud.sh b/setup/install-whatsapp-cloud.sh index 377327809..70e8e0279 100755 --- a/setup/install-whatsapp-cloud.sh +++ b/setup/install-whatsapp-cloud.sh @@ -1,7 +1,7 @@ #!/usr/bin/env bash # Setup helper: install-whatsapp-cloud — bundles the preflight + install # commands from the /add-whatsapp-cloud skill into one idempotent script so -# /new-setup-2 can run them programmatically before continuing to credentials. +# /new-setup can run them programmatically before continuing to credentials. # # Copies the WhatsApp Cloud adapter in from the `channels` branch; appends the # self-registration import; installs the pinned @chat-adapter/whatsapp package; diff --git a/setup/install-whatsapp.sh b/setup/install-whatsapp.sh index 0d307f53c..1c62d65d4 100755 --- a/setup/install-whatsapp.sh +++ b/setup/install-whatsapp.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash # Setup helper: install-whatsapp — bundles the preflight + install commands -# from the /add-whatsapp skill into one idempotent script so /new-setup-2 can +# from the /add-whatsapp skill into one idempotent script so /new-setup can # run them programmatically before continuing to QR/pairing-code auth. # # Copies the native Baileys WhatsApp adapter, its whatsapp-auth and groups From c9977d6b696ce2f0ee2b2bab45d301cfdfe626ed Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 15:27:12 +0300 Subject: [PATCH 65/95] chore(settings): drop permissions allowlist from checked-in settings.json Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/settings.json | 36 ------------------------------------ 1 file changed, 36 deletions(-) diff --git a/.claude/settings.json b/.claude/settings.json index 9d9147559..c4beb6f87 100644 --- a/.claude/settings.json +++ b/.claude/settings.json @@ -1,41 +1,5 @@ { "sandbox": { "enabled": false - }, - "permissions": { - "allow": [ - "Bash(bash setup.sh*)", - "Bash(git remote *)", - "Bash(pnpm exec tsx setup/index.ts*)", - "Bash(pnpm exec tsx scripts/init-first-agent.ts*)", - "Bash(pnpm install @chat-adapter/*)", - "Bash(pnpm install chat-adapter-imessage*)", - "Bash(pnpm install @bitbasti/chat-adapter-webex*)", - "Bash(pnpm install @resend/chat-sdk-adapter*)", - "Bash(pnpm install @whiskeysockets/baileys*)", - "Bash(pnpm install @beeper/chat-adapter-matrix*)", - "Bash(pnpm install @nanoco/nanoclaw-dashboard*)", - "Bash(pnpm install --frozen-lockfile*)", - "Bash(pnpm run build*)", - "Bash(curl -fsSL onecli.sh*)", - "Bash(onecli *)", - "Bash(grep -q *)", - "Bash(echo *>> .env)", - "Bash(ls *)", - "Bash(cat ~/.config/nanoclaw/*)", - "Bash(tail *logs/*)", - "Bash(launchctl *nanoclaw*)", - "Bash(sqlite3 data/*)", - "Bash(docker info*)", - "Bash(docker logs *)", - "Bash(mkdir -p *)", - "Bash(cp .env *)", - "Bash(rsync -a .claude/skills/*)", - "Bash(head *)", - "Bash(xattr *)", - "Bash(find ~/.npm *)", - "Bash(which onecli*)", - "Bash(./container/build.sh*)" - ] } } From 91c668e0cc2795fd63351059af7594c363014568 Mon Sep 17 00:00:00 2001 From: Dave Kim Date: Tue, 21 Apr 2026 13:04:57 +0000 Subject: [PATCH 66/95] fix: persist SDK session_id on init + split long messages before adapter truncation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Two related bugs that surfaced together when a Discord response exceeded 2000 chars: 1. **Session id lost on mid-turn container exit.** `runPollLoop` was calling `setStoredSessionId` only after `processQuery` returned. If the container died between the SDK's `init` event (where session_id arrives) and the stream completing, the id was never persisted. The next wake called `getStoredSessionId()` → undefined and started a fresh Claude session, dropping all prior context. Fix: persist immediately in the `init` branch inside `processQuery`. The existing post-query store becomes a harmless no-op. 2. **Silent truncation past adapter limits.** `chat-sdk-bridge.deliver` handed full text straight to `adapter.postMessage`. Discord's adapter hard-truncates at 2000 chars; Telegram's at 4096. Responses longer than that were cut off without any signal to the user or host. Fix: add `maxTextLength` to `ChatSdkBridgeConfig` and a `splitForLimit` helper that breaks on paragraph → line → hard-char boundaries, then posts chunks sequentially. Files ride on the first chunk; the returned id is the first chunk's so edits and reactions still target the reply head. Channel adapter files (Discord, Telegram, …) live on the `channels` branch — a companion PR wires `maxTextLength: 1900` for Discord and `4000` for Telegram so the splitter actually engages in those installs. Without wiring, behavior is unchanged. --- container/agent-runner/src/poll-loop.ts | 7 ++++ src/channels/chat-sdk-bridge.test.ts | 30 +++++++++++++- src/channels/chat-sdk-bridge.ts | 54 ++++++++++++++++++++++--- 3 files changed, 84 insertions(+), 7 deletions(-) diff --git a/container/agent-runner/src/poll-loop.ts b/container/agent-runner/src/poll-loop.ts index 3f0e364be..119b1d499 100644 --- a/container/agent-runner/src/poll-loop.ts +++ b/container/agent-runner/src/poll-loop.ts @@ -322,6 +322,13 @@ async function processQuery(query: AgentQuery, routing: RoutingContext): Promise if (event.type === 'init') { queryContinuation = event.continuation; + // Persist immediately so a mid-turn container crash still lets the + // next wake resume the conversation. Without this, the session id + // was only written after the full stream completed — if the + // container died between `init` and `result`, the SDK session was + // effectively orphaned and the next message started a blank + // Claude session with no prior context. + setStoredSessionId(event.continuation); } else if (event.type === 'result' && event.text) { dispatchResultText(event.text, routing); } diff --git a/src/channels/chat-sdk-bridge.test.ts b/src/channels/chat-sdk-bridge.test.ts index 7ddad4ff0..7e3c4ffd6 100644 --- a/src/channels/chat-sdk-bridge.test.ts +++ b/src/channels/chat-sdk-bridge.test.ts @@ -2,12 +2,40 @@ import { describe, expect, it } from 'vitest'; import type { Adapter } from 'chat'; -import { createChatSdkBridge } from './chat-sdk-bridge.js'; +import { createChatSdkBridge, splitForLimit } from './chat-sdk-bridge.js'; function stubAdapter(partial: Partial): Adapter { return { name: 'stub', ...partial } as unknown as Adapter; } +describe('splitForLimit', () => { + it('returns a single chunk when text fits', () => { + expect(splitForLimit('short text', 100)).toEqual(['short text']); + }); + + it('splits on paragraph boundaries when available', () => { + const text = 'para one line one\npara one line two\n\npara two line one\npara two line two'; + const chunks = splitForLimit(text, 40); + expect(chunks.length).toBeGreaterThan(1); + for (const c of chunks) expect(c.length).toBeLessThanOrEqual(40); + }); + + it('falls back to line boundaries when no paragraph fits', () => { + const text = 'alpha\nbravo\ncharlie\ndelta\necho\nfoxtrot'; + const chunks = splitForLimit(text, 15); + expect(chunks.length).toBeGreaterThan(1); + for (const c of chunks) expect(c.length).toBeLessThanOrEqual(15); + }); + + it('hard-cuts when no whitespace is available', () => { + const text = 'a'.repeat(100); + const chunks = splitForLimit(text, 30); + expect(chunks.length).toBe(Math.ceil(100 / 30)); + for (const c of chunks) expect(c.length).toBeLessThanOrEqual(30); + expect(chunks.join('')).toBe(text); + }); +}); + describe('createChatSdkBridge', () => { // The bridge is now transport-only: forward inbound events, relay outbound // ops. All per-wiring engage / accumulate / drop / subscribe decisions live diff --git a/src/channels/chat-sdk-bridge.ts b/src/channels/chat-sdk-bridge.ts index ef2195e7a..5c120e074 100644 --- a/src/channels/chat-sdk-bridge.ts +++ b/src/channels/chat-sdk-bridge.ts @@ -63,6 +63,38 @@ export interface ChatSdkBridgeConfig { * quirk (e.g. Telegram's legacy Markdown parse mode). */ transformOutboundText?: (text: string) => string; + /** + * Maximum text length the underlying adapter accepts in a single message. + * When set, the bridge splits outbound text longer than this on paragraph + * → line → hard-char boundaries and posts multiple messages. Without this, + * adapters like Discord (2000) and Telegram (4096) silently truncate + * mid-response. The returned id is the first chunk's id so subsequent edits + * and reactions still target the head of the reply. + */ + maxTextLength?: number; +} + +/** + * Split `text` into chunks no larger than `limit`, preferring paragraph + * breaks, then line breaks, then a hard character cut as a last resort. + * Preserves code fences only structurally — a fenced block that straddles a + * chunk boundary will render as two independent blocks on the receiving + * platform, which is the same behavior as manually re-opening a fence. + */ +export function splitForLimit(text: string, limit: number): string[] { + if (text.length <= limit) return [text]; + const chunks: string[] = []; + let remaining = text; + while (remaining.length > limit) { + let cut = remaining.lastIndexOf('\n\n', limit); + if (cut <= 0) cut = remaining.lastIndexOf('\n', limit); + if (cut <= 0) cut = remaining.lastIndexOf(' ', limit); + if (cut <= 0) cut = limit; + chunks.push(remaining.slice(0, cut).trimEnd()); + remaining = remaining.slice(cut).trimStart(); + } + if (remaining.length > 0) chunks.push(remaining); + return chunks; } export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter { @@ -338,13 +370,23 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter data: f.data, filename: f.filename, })); - if (fileUploads && fileUploads.length > 0) { - const result = await adapter.postMessage(tid, { markdown: text, files: fileUploads }); - return result?.id; - } else { - const result = await adapter.postMessage(tid, { markdown: text }); - return result?.id; + // Split if over the adapter's max length. Files ride on the first + // chunk so the head of the reply still carries them. + const chunks = + config.maxTextLength && text.length > config.maxTextLength + ? splitForLimit(text, config.maxTextLength) + : [text]; + let firstId: string | undefined; + for (let i = 0; i < chunks.length; i++) { + const chunk = chunks[i]; + const attachFiles = i === 0 && fileUploads && fileUploads.length > 0; + const result = await adapter.postMessage( + tid, + attachFiles ? { markdown: chunk, files: fileUploads } : { markdown: chunk }, + ); + if (i === 0) firstId = result?.id; } + return firstId; } else if (message.files && message.files.length > 0) { // Files only, no text const fileUploads = message.files.map((f: { data: Buffer; filename: string }) => ({ From 010722803f6523f2f8a89b9c0d2ab503448409cb Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 17:02:22 +0300 Subject: [PATCH 67/95] refactor(setup): drop Apple Container support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Apple Container is no longer supported — the runtime abstraction in src/container-runtime.ts is already Docker-only. Remove the remaining setup-time branches that probed for it: the Apple Container runtime option in the container build step, the APPLE_CONTAINER field emitted by the environment check, and the `command -v container` probe in verify. `--runtime docker` still parses for backwards compatibility with the /setup skill. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/container.ts | 95 ++++++++++++++++---------------------------- setup/environment.ts | 8 ---- setup/verify.ts | 11 ++--- 3 files changed, 37 insertions(+), 77 deletions(-) diff --git a/setup/container.ts b/setup/container.ts index d8105394e..3e48ecfc3 100644 --- a/setup/container.ts +++ b/setup/container.ts @@ -10,7 +10,9 @@ import { commandExists } from './platform.js'; import { emitStatus } from './status.js'; function parseArgs(args: string[]): { runtime: string } { - let runtime = ''; + // `--runtime` is still accepted for backwards compatibility with the /setup + // skill, but `docker` is the only supported value. + let runtime = 'docker'; for (let i = 0; i < args.length; i++) { if (args[i] === '--runtime' && args[i + 1]) { runtime = args[i + 1]; @@ -26,63 +28,7 @@ export async function run(args: string[]): Promise { const image = 'nanoclaw-agent:latest'; const logFile = path.join(projectRoot, 'logs', 'setup.log'); - if (!runtime) { - emitStatus('SETUP_CONTAINER', { - RUNTIME: 'unknown', - IMAGE: image, - BUILD_OK: false, - TEST_OK: false, - STATUS: 'failed', - ERROR: 'missing_runtime_flag', - LOG: 'logs/setup.log', - }); - process.exit(4); - } - - // Validate runtime availability - if (runtime === 'apple-container' && !commandExists('container')) { - emitStatus('SETUP_CONTAINER', { - RUNTIME: runtime, - IMAGE: image, - BUILD_OK: false, - TEST_OK: false, - STATUS: 'failed', - ERROR: 'runtime_not_available', - LOG: 'logs/setup.log', - }); - process.exit(2); - } - - if (runtime === 'docker') { - if (!commandExists('docker')) { - emitStatus('SETUP_CONTAINER', { - RUNTIME: runtime, - IMAGE: image, - BUILD_OK: false, - TEST_OK: false, - STATUS: 'failed', - ERROR: 'runtime_not_available', - LOG: 'logs/setup.log', - }); - process.exit(2); - } - try { - execSync('docker info', { stdio: 'ignore' }); - } catch { - emitStatus('SETUP_CONTAINER', { - RUNTIME: runtime, - IMAGE: image, - BUILD_OK: false, - TEST_OK: false, - STATUS: 'failed', - ERROR: 'runtime_not_available', - LOG: 'logs/setup.log', - }); - process.exit(2); - } - } - - if (!['apple-container', 'docker'].includes(runtime)) { + if (runtime !== 'docker') { emitStatus('SETUP_CONTAINER', { RUNTIME: runtime, IMAGE: image, @@ -95,9 +41,36 @@ export async function run(args: string[]): Promise { process.exit(4); } - const buildCmd = - runtime === 'apple-container' ? 'container build' : 'docker build'; - const runCmd = runtime === 'apple-container' ? 'container' : 'docker'; + if (!commandExists('docker')) { + emitStatus('SETUP_CONTAINER', { + RUNTIME: runtime, + IMAGE: image, + BUILD_OK: false, + TEST_OK: false, + STATUS: 'failed', + ERROR: 'runtime_not_available', + LOG: 'logs/setup.log', + }); + process.exit(2); + } + + try { + execSync('docker info', { stdio: 'ignore' }); + } catch { + emitStatus('SETUP_CONTAINER', { + RUNTIME: runtime, + IMAGE: image, + BUILD_OK: false, + TEST_OK: false, + STATUS: 'failed', + ERROR: 'runtime_not_available', + LOG: 'logs/setup.log', + }); + process.exit(2); + } + + const buildCmd = 'docker build'; + const runCmd = 'docker'; // Build-args from .env. Only INSTALL_CJK_FONTS is passed through today. // Keeps /setup and ./container/build.sh in sync — both read the same source. diff --git a/setup/environment.ts b/setup/environment.ts index 27de9f4d9..4a8366503 100644 --- a/setup/environment.ts +++ b/setup/environment.ts @@ -21,12 +21,6 @@ export async function run(_args: string[]): Promise { const wsl = isWSL(); const headless = isHeadless(); - // Check Apple Container - let appleContainer: 'installed' | 'not_found' = 'not_found'; - if (commandExists('container')) { - appleContainer = 'installed'; - } - // Check Docker let docker: 'running' | 'installed_not_running' | 'not_found' = 'not_found'; if (commandExists('docker')) { @@ -78,7 +72,6 @@ export async function run(_args: string[]): Promise { { platform, wsl, - appleContainer, docker, hasEnv, hasAuth, @@ -91,7 +84,6 @@ export async function run(_args: string[]): Promise { PLATFORM: platform, IS_WSL: wsl, IS_HEADLESS: headless, - APPLE_CONTAINER: appleContainer, DOCKER: docker, HAS_ENV: hasEnv, HAS_AUTH: hasAuth, diff --git a/setup/verify.ts b/setup/verify.ts index 566cc9b82..6dd6a4484 100644 --- a/setup/verify.ts +++ b/setup/verify.ts @@ -85,15 +85,10 @@ export async function run(_args: string[]): Promise { // 2. Check container runtime let containerRuntime = 'none'; try { - execSync('command -v container', { stdio: 'ignore' }); - containerRuntime = 'apple-container'; + execSync('docker info', { stdio: 'ignore' }); + containerRuntime = 'docker'; } catch { - try { - execSync('docker info', { stdio: 'ignore' }); - containerRuntime = 'docker'; - } catch { - // No runtime - } + // Docker not running } // 3. Check credentials From 2311721375bd3e6f880ab688f588c8f2a328a562 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 17:04:48 +0300 Subject: [PATCH 68/95] feat(setup): add scripted setup driver and auto-start Docker MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit `pnpm run setup:auto` chains the deterministic setup steps (environment → timezone → container → mounts → service → verify) by spawning the existing per-step CLI and parsing its status blocks. Config via env: NANOCLAW_TZ, NANOCLAW_SKIP. Credentials + channel install + /manage-channels stay interactive — verify reports what's left and exits 0 rather than failing the driver. Also have the container step try to start Docker when it's installed but not running (open -a Docker on macOS, sudo systemctl start docker on Linux) and poll `docker info` for up to 60s before giving up. Both /setup and setup:auto pick this up automatically. Co-Authored-By: Claude Opus 4.7 (1M context) --- package.json | 1 + setup/auto.ts | 164 +++++++++++++++++++++++++++++++++++++++++++++ setup/container.ts | 72 ++++++++++++++++---- 3 files changed, 223 insertions(+), 14 deletions(-) create mode 100644 setup/auto.ts diff --git a/package.json b/package.json index e2af027fd..a7f8804e9 100644 --- a/package.json +++ b/package.json @@ -15,6 +15,7 @@ "format:check": "prettier --check \"src/**/*.ts\"", "prepare": "husky", "setup": "tsx setup/index.ts", + "setup:auto": "tsx setup/auto.ts", "chat": "tsx scripts/chat.ts", "auth": "tsx src/whatsapp-auth.ts", "lint": "eslint src/", diff --git a/setup/auto.ts b/setup/auto.ts new file mode 100644 index 000000000..0cbac93fa --- /dev/null +++ b/setup/auto.ts @@ -0,0 +1,164 @@ +/** + * Non-interactive setup driver. Chains the deterministic setup steps so a + * scripted install can go from a fresh checkout to a running service without + * the `/setup` skill. + * + * Prerequisite: `bash setup.sh` has run (Node >= 20, pnpm install, native + * module check). This driver picks up from there. + * + * Config via env: + * NANOCLAW_TZ IANA zone override (skip autodetect) + * NANOCLAW_SKIP comma-separated step names to skip + * (environment|timezone|container|mounts|service|verify) + * + * Credential setup (OneCLI + channel auth + `/manage-channels`) is *not* + * scripted — those require interactive platform flows and are handled by + * `/setup`, `/add-`, and `/manage-channels` afterwards. + */ +import { spawn } from 'child_process'; + +type Fields = Record; +type StepResult = { ok: boolean; fields: Fields; exitCode: number }; + +function parseStatus(stdout: string): Fields { + const out: Fields = {}; + let inBlock = false; + for (const line of stdout.split('\n')) { + if (line.startsWith('=== NANOCLAW SETUP:')) { + inBlock = true; + continue; + } + if (line.startsWith('=== END ===')) { + inBlock = false; + continue; + } + if (!inBlock) continue; + const idx = line.indexOf(':'); + if (idx === -1) continue; + const key = line.slice(0, idx).trim(); + const value = line.slice(idx + 1).trim(); + if (key) out[key] = value; + } + return out; +} + +function runStep(name: string, extra: string[] = []): Promise { + return new Promise((resolve) => { + console.log(`\n── ${name} ────────────────────────────────────`); + const args = ['exec', 'tsx', 'setup/index.ts', '--step', name]; + if (extra.length > 0) args.push('--', ...extra); + + const child = spawn('pnpm', args, { stdio: ['inherit', 'pipe', 'inherit'] }); + let buf = ''; + child.stdout.on('data', (chunk: Buffer) => { + const s = chunk.toString('utf-8'); + buf += s; + process.stdout.write(s); + }); + child.on('close', (code) => { + const fields = parseStatus(buf); + resolve({ + ok: code === 0 && fields.STATUS === 'success', + fields, + exitCode: code ?? 1, + }); + }); + }); +} + +function fail(msg: string, hint?: string): never { + console.error(`\n[setup:auto] ${msg}`); + if (hint) console.error(` ${hint}`); + console.error(' Logs: logs/setup.log'); + process.exit(1); +} + +async function main(): Promise { + const skip = new Set( + (process.env.NANOCLAW_SKIP ?? '') + .split(',') + .map((s) => s.trim()) + .filter(Boolean), + ); + const tz = process.env.NANOCLAW_TZ; + + if (!skip.has('environment')) { + const env = await runStep('environment'); + if (!env.ok) fail('environment check failed'); + } + + if (!skip.has('timezone')) { + const res = await runStep('timezone', tz ? ['--tz', tz] : []); + if (res.fields.NEEDS_USER_INPUT === 'true') { + fail( + 'Timezone could not be autodetected.', + 'Set NANOCLAW_TZ to an IANA zone (e.g. NANOCLAW_TZ=America/New_York).', + ); + } + if (!res.ok) fail('timezone step failed'); + } + + if (!skip.has('container')) { + const res = await runStep('container'); + if (!res.ok) { + if (res.fields.ERROR === 'runtime_not_available') { + fail( + 'Docker is not available and could not be started automatically.', + 'Install Docker Desktop or start it manually, then retry.', + ); + } + fail( + 'container build/test failed', + 'For stale build cache: `docker builder prune -f`, then retry `pnpm run setup:auto`.', + ); + } + } + + if (!skip.has('mounts')) { + const res = await runStep('mounts', ['--empty']); + if (!res.ok && res.fields.STATUS !== 'skipped') { + fail('mount allowlist step failed'); + } + } + + if (!skip.has('service')) { + const res = await runStep('service'); + if (!res.ok) { + fail( + 'service install failed', + 'Check logs/nanoclaw.error.log, or run `/setup` to iterate interactively.', + ); + } + if (res.fields.DOCKER_GROUP_STALE === 'true') { + console.warn( + '\n[setup:auto] Docker group stale in systemd session. Run:\n' + + ' sudo setfacl -m u:$(whoami):rw /var/run/docker.sock\n' + + ' systemctl --user restart nanoclaw', + ); + } + } + + if (!skip.has('verify')) { + const res = await runStep('verify'); + if (!res.ok) { + console.log('\n[setup:auto] Scripted steps done. Remaining (interactive):'); + if (res.fields.CREDENTIALS !== 'configured') { + console.log(' • OneCLI + Anthropic secret — see `/setup` §4 or https://onecli.sh'); + } + if (!res.fields.CONFIGURED_CHANNELS) { + console.log(' • Install a channel: `/add-discord`, `/add-slack`, `/add-telegram`, …'); + } + if (res.fields.REGISTERED_GROUPS === '0') { + console.log(' • Wire the channel to an agent group: `/manage-channels`'); + } + return; + } + } + + console.log('\n[setup:auto] Complete.'); +} + +main().catch((err) => { + console.error(err); + process.exit(1); +}); diff --git a/setup/container.ts b/setup/container.ts index 3e48ecfc3..aadd04c9f 100644 --- a/setup/container.ts +++ b/setup/container.ts @@ -4,11 +4,54 @@ */ import { execSync } from 'child_process'; import path from 'path'; +import { setTimeout as sleep } from 'timers/promises'; import { log } from '../src/log.js'; -import { commandExists } from './platform.js'; +import { commandExists, getPlatform } from './platform.js'; import { emitStatus } from './status.js'; +function dockerRunning(): boolean { + try { + execSync('docker info', { stdio: 'ignore' }); + return true; + } catch { + return false; + } +} + +/** + * Try to start Docker if it's installed but idle. Poll for up to 60s. + * Returns true once `docker info` succeeds, false if we gave up. + */ +async function tryStartDocker(): Promise { + const platform = getPlatform(); + log.info('Docker not running — attempting to start', { platform }); + + try { + if (platform === 'macos') { + execSync('open -a Docker', { stdio: 'ignore' }); + } else if (platform === 'linux') { + // Inherit stdio so sudo can prompt for a password if needed. + execSync('sudo systemctl start docker', { stdio: 'inherit' }); + } else { + return false; + } + } catch (err) { + log.warn('Start command failed', { err }); + return false; + } + + for (let i = 0; i < 30; i++) { + await sleep(2000); + if (dockerRunning()) { + log.info('Docker is up'); + return true; + } + } + log.warn('Docker did not become ready within 60s'); + return false; +} + function parseArgs(args: string[]): { runtime: string } { // `--runtime` is still accepted for backwards compatibility with the /setup // skill, but `docker` is the only supported value. @@ -54,19 +97,20 @@ export async function run(args: string[]): Promise { process.exit(2); } - try { - execSync('docker info', { stdio: 'ignore' }); - } catch { - emitStatus('SETUP_CONTAINER', { - RUNTIME: runtime, - IMAGE: image, - BUILD_OK: false, - TEST_OK: false, - STATUS: 'failed', - ERROR: 'runtime_not_available', - LOG: 'logs/setup.log', - }); - process.exit(2); + if (!dockerRunning()) { + const started = await tryStartDocker(); + if (!started) { + emitStatus('SETUP_CONTAINER', { + RUNTIME: runtime, + IMAGE: image, + BUILD_OK: false, + TEST_OK: false, + STATUS: 'failed', + ERROR: 'runtime_not_available', + LOG: 'logs/setup.log', + }); + process.exit(2); + } } const buildCmd = 'docker build'; From 3ce4101cd9ce9770f4f11fce792c4e15aeee564e Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 17:13:39 +0300 Subject: [PATCH 69/95] feat(setup): chain OneCLI install in setup:auto MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The install half of the OneCLI step is fully scriptable (the gateway and CLI install themselves via `curl | sh`, PATH + api-host + .env updates are idempotent). Register the Anthropic secret is still interactive — the auto driver leaves that for `/setup` §4 to handle. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/setup/auto.ts b/setup/auto.ts index 0cbac93fa..84db937a5 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -9,11 +9,12 @@ * Config via env: * NANOCLAW_TZ IANA zone override (skip autodetect) * NANOCLAW_SKIP comma-separated step names to skip - * (environment|timezone|container|mounts|service|verify) + * (environment|timezone|container|onecli|mounts|service|verify) * - * Credential setup (OneCLI + channel auth + `/manage-channels`) is *not* - * scripted — those require interactive platform flows and are handled by - * `/setup`, `/add-`, and `/manage-channels` afterwards. + * OneCLI is installed and configured here, but secret registration (the + * Anthropic token or API key), channel auth, and `/manage-channels` stay + * interactive — they need human input. Finish those with `/setup` §4 + * onwards, `/add-`, and `/manage-channels`. */ import { spawn } from 'child_process'; @@ -114,6 +115,22 @@ async function main(): Promise { } } + if (!skip.has('onecli')) { + const res = await runStep('onecli'); + if (!res.ok) { + if (res.fields.ERROR === 'onecli_not_on_path_after_install') { + fail( + 'OneCLI installed but not on PATH.', + 'Open a new shell or run `export PATH="$HOME/.local/bin:$PATH"`, then retry.', + ); + } + fail( + `OneCLI install failed (${res.fields.ERROR ?? 'unknown'})`, + 'Check that curl + a writable ~/.local/bin are available; re-run `pnpm run setup:auto`.', + ); + } + } + if (!skip.has('mounts')) { const res = await runStep('mounts', ['--empty']); if (!res.ok && res.fields.STATUS !== 'skipped') { @@ -143,7 +160,7 @@ async function main(): Promise { if (!res.ok) { console.log('\n[setup:auto] Scripted steps done. Remaining (interactive):'); if (res.fields.CREDENTIALS !== 'configured') { - console.log(' • OneCLI + Anthropic secret — see `/setup` §4 or https://onecli.sh'); + console.log(' • Register an Anthropic secret in OneCLI — see `/setup` §4'); } if (!res.fields.CONFIGURED_CHANNELS) { console.log(' • Install a channel: `/add-discord`, `/add-slack`, `/add-telegram`, …'); From ee5995ae16a9fa5a7a350c53f07243710bd1d6fe Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 17:38:43 +0300 Subject: [PATCH 70/95] feat(setup): add register-claude-token.sh MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Bash helper that registers an Anthropic credential in OneCLI via three paths: Claude subscription (runs `claude setup-token` under script(1) for PTY capture), paste an existing sk-ant-oat… OAuth token, or paste an sk-ant-api… API key. On bash 4+ the `claude setup-token` command is pre-filled in the readline buffer so Enter submits it. On bash 3.2 (macOS default /bin/bash) we fall back to a plain confirmation prompt. Token extraction strips ANSI + TTY-wrap line breaks and anchors on sk-ant-oat…AA with a length cap (via perl; BSD grep caps {n,m} at 255). Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/register-claude-token.sh | 127 +++++++++++++++++++++++++++++++++ 1 file changed, 127 insertions(+) create mode 100755 setup/register-claude-token.sh diff --git a/setup/register-claude-token.sh b/setup/register-claude-token.sh new file mode 100755 index 000000000..2c0860d2d --- /dev/null +++ b/setup/register-claude-token.sh @@ -0,0 +1,127 @@ +#!/usr/bin/env bash +set -euo pipefail + +# Prefer bash 4+ (for `read -e -i` readline preload). macOS ships 3.2 in +# /bin/bash, but Homebrew users usually have 5.x first on PATH. The readline +# preload is optional — on 3.x we fall back to a plain confirmation prompt. + +# Register an Anthropic credential with OneCLI. Three paths: +# 1) Claude subscription — run `claude setup-token` (browser sign-in) +# and capture the resulting OAuth token. +# 2) Paste an existing sk-ant-oat… OAuth token you already have. +# 3) Paste an Anthropic API key (sk-ant-api…). +# +# Env overrides: +# SECRET_NAME OneCLI secret name (default: Anthropic) +# HOST_PATTERN OneCLI host pattern (default: api.anthropic.com) + +SECRET_NAME="${SECRET_NAME:-Anthropic}" +HOST_PATTERN="${HOST_PATTERN:-api.anthropic.com}" + +command -v onecli >/dev/null \ + || { echo "onecli not found. Install it first (see /setup §4)." >&2; exit 1; } + +TOKEN="" + +capture_via_claude_setup_token() { + command -v claude >/dev/null \ + || { echo "claude CLI not found. Install from https://claude.ai/download" >&2; exit 1; } + command -v script >/dev/null \ + || { echo "script(1) is required for PTY capture." >&2; exit 1; } + + local tmpfile + tmpfile=$(mktemp -t claude-setup-token.XXXXXX) + trap 'rm -f "$tmpfile"' RETURN + + cat <<'EOF' +A browser window will open for sign-in. Token is captured automatically. +Press Enter to run, or edit the command first. + +EOF + + local cmd="claude setup-token" + if [[ ${BASH_VERSINFO[0]:-0} -ge 4 ]]; then + # bash 4+: pre-fill the readline buffer so Enter literally submits. + read -r -e -i "$cmd" -p "$ " cmd /dev/null | grep -q util-linux; then + script -q -c "$cmd" "$tmpfile" + else + # BSD script: command is argv after the file, so let it word-split. + # shellcheck disable=SC2086 + script -q "$tmpfile" $cmd + fi + + # Strip ANSI codes + newlines (TTY wraps the token mid-string), then match + # the sk-ant-oat…AA token. perl because BSD grep caps {n,m} at 255. + TOKEN=$(sed $'s/\x1b\\[[0-9;]*[a-zA-Z]//g' "$tmpfile" \ + | tr -d '\n\r' \ + | perl -ne 'print "$1\n" while /(sk-ant-oat[A-Za-z0-9_-]{80,500}AA)/g' \ + | tail -1 || true) + + if [[ -z "$TOKEN" ]]; then + local keep + keep=$(mktemp -t claude-setup-token-log.XXXXXX) + cp "$tmpfile" "$keep" + echo >&2 + echo "No sk-ant-oat…AA token found. Raw log: $keep" >&2 + exit 1 + fi +} + +prompt_for_pasted() { + local prefix="$1" # "oat" or "api" + local value + echo + echo "Paste your sk-ant-${prefix}… credential and press Enter." + echo "(Input is hidden for safety.)" + read -r -s -p "> " value &2 + exit 1 + fi + if [[ ! "$value" =~ ^sk-ant-${prefix} ]]; then + echo "Value does not start with sk-ant-${prefix}. Aborting." >&2 + exit 1 + fi + TOKEN="$value" +} + +cat <&2; exit 1 ;; +esac + +echo +echo "Got token: ${TOKEN:0:16}…${TOKEN: -4}" +echo "Registering with OneCLI as '$SECRET_NAME' (host pattern: $HOST_PATTERN)…" + +onecli secrets create \ + --name "$SECRET_NAME" \ + --type anthropic \ + --value "$TOKEN" \ + --host-pattern "$HOST_PATTERN" + +echo "Done." From b0cae1ba4cef1fa4a21beae5907f36334184adfc Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 17:41:29 +0300 Subject: [PATCH 71/95] feat(setup): chain register-claude-token.sh into setup:auto Runs after the OneCLI install step and before mounts/service. Skips silently when `onecli secrets list` already reports an Anthropic secret, so re-running setup:auto on a configured install is a no-op. Child process uses stdio:inherit so the menu + browser sign-in flow work normally. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 53 ++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 46 insertions(+), 7 deletions(-) diff --git a/setup/auto.ts b/setup/auto.ts index 84db937a5..66d6880f4 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -9,14 +9,15 @@ * Config via env: * NANOCLAW_TZ IANA zone override (skip autodetect) * NANOCLAW_SKIP comma-separated step names to skip - * (environment|timezone|container|onecli|mounts|service|verify) + * (environment|timezone|container|onecli|auth|mounts|service|verify) * - * OneCLI is installed and configured here, but secret registration (the - * Anthropic token or API key), channel auth, and `/manage-channels` stay - * interactive — they need human input. Finish those with `/setup` §4 - * onwards, `/add-`, and `/manage-channels`. + * Anthropic credential registration runs via setup/register-claude-token.sh + * (the only step that truly requires human input — browser sign-in or a + * pasted token/key). Channel auth and `/manage-channels` remain separate + * because they're platform-specific and typically handled via `/add-` + * and `/manage-channels` after this driver completes. */ -import { spawn } from 'child_process'; +import { spawn, spawnSync } from 'child_process'; type Fields = Record; type StepResult = { ok: boolean; fields: Fields; exitCode: number }; @@ -67,6 +68,26 @@ function runStep(name: string, extra: string[] = []): Promise { }); } +function anthropicSecretExists(): boolean { + try { + const res = spawnSync('onecli', ['secrets', 'list'], { + encoding: 'utf-8', + stdio: ['ignore', 'pipe', 'pipe'], + }); + if (res.status !== 0) return false; + return /anthropic/i.test(res.stdout ?? ''); + } catch { + return false; + } +} + +function runBashScript(relPath: string): Promise { + return new Promise((resolve) => { + const child = spawn('bash', [relPath], { stdio: 'inherit' }); + child.on('close', (code) => resolve(code ?? 1)); + }); +} + function fail(msg: string, hint?: string): never { console.error(`\n[setup:auto] ${msg}`); if (hint) console.error(` ${hint}`); @@ -131,6 +152,24 @@ async function main(): Promise { } } + if (!skip.has('auth')) { + if (anthropicSecretExists()) { + console.log( + '\n── auth ────────────────────────────────────\n' + + '[setup:auto] OneCLI already has an Anthropic secret — skipping.', + ); + } else { + console.log('\n── auth ────────────────────────────────────'); + const code = await runBashScript('setup/register-claude-token.sh'); + if (code !== 0) { + fail( + 'Anthropic credential registration failed or was aborted.', + 'Re-run `bash setup/register-claude-token.sh` or handle via `/setup` §4.', + ); + } + } + } + if (!skip.has('mounts')) { const res = await runStep('mounts', ['--empty']); if (!res.ok && res.fields.STATUS !== 'skipped') { @@ -160,7 +199,7 @@ async function main(): Promise { if (!res.ok) { console.log('\n[setup:auto] Scripted steps done. Remaining (interactive):'); if (res.fields.CREDENTIALS !== 'configured') { - console.log(' • Register an Anthropic secret in OneCLI — see `/setup` §4'); + console.log(' • Anthropic secret not detected — re-run `bash setup/register-claude-token.sh`'); } if (!res.fields.CONFIGURED_CHANNELS) { console.log(' • Install a channel: `/add-discord`, `/add-slack`, `/add-telegram`, …'); From 264849da6c05305d758a338bdd18dd6677f851d2 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 17:45:04 +0300 Subject: [PATCH 72/95] feat(setup): add nanoclaw.sh entry point Single command end-to-end: `bash nanoclaw.sh` runs setup.sh for bootstrap and hands off to `pnpm run setup:auto` on success. Passes through NANOCLAW_TZ, NANOCLAW_SKIP, SECRET_NAME, HOST_PATTERN via env. Co-Authored-By: Claude Opus 4.7 (1M context) --- nanoclaw.sh | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100755 nanoclaw.sh diff --git a/nanoclaw.sh b/nanoclaw.sh new file mode 100755 index 000000000..6a23558a3 --- /dev/null +++ b/nanoclaw.sh @@ -0,0 +1,47 @@ +#!/usr/bin/env bash +# +# NanoClaw — scripted end-to-end install. +# +# Runs `bash setup.sh` (bootstrap: Node check, pnpm install, native module +# verify), then `pnpm run setup:auto` (environment → timezone → container → +# onecli → auth → mounts → service → verify). +# +# Everything that can be scripted runs unattended; the one interactive pause +# is the auth step (browser sign-in or paste token/API key). +# +# Config via env — passed through unchanged: +# NANOCLAW_TZ IANA zone override +# NANOCLAW_SKIP comma-separated setup:auto step names to skip +# SECRET_NAME OneCLI secret name (default: Anthropic) +# HOST_PATTERN OneCLI host pattern (default: api.anthropic.com) + +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" +cd "$PROJECT_ROOT" + +cat <<'EOF' +═══════════════════════════════════════════════════════════════ + NanoClaw scripted setup +═══════════════════════════════════════════════════════════════ + +Phase 1: bootstrap (Node + pnpm + native modules) + +EOF + +if ! bash setup.sh; then + echo + echo "[nanoclaw.sh] Bootstrap failed. Inspect logs/setup.log and retry." >&2 + exit 1 +fi + +cat <<'EOF' + +═══════════════════════════════════════════════════════════════ + Phase 2: setup:auto +═══════════════════════════════════════════════════════════════ + +EOF + +# exec so signals (Ctrl-C) propagate directly to the child. +exec pnpm run setup:auto From fd2e404ba95aec6a478ce55af9bdd7b8280e4402 Mon Sep 17 00:00:00 2001 From: "exe.dev user" Date: Tue, 21 Apr 2026 15:05:52 +0000 Subject: [PATCH 73/95] fix(setup): auto-install Node and bypass corepack prompt Node check now triggers setup/install-node.sh when missing/too old, and COREPACK_ENABLE_DOWNLOAD_PROMPT=0 prevents the first-use prompt from hanging the script when stdout is redirected to the log. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup.sh | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/setup.sh b/setup.sh index af2c5e55b..e163df851 100755 --- a/setup.sh +++ b/setup.sh @@ -72,6 +72,11 @@ install_deps() { cd "$PROJECT_ROOT" + # Corepack's first-use "Do you want to continue? [Y/n]" prompt would hang + # the script since we redirect stdout/stderr to the log file — the prompt + # is invisible but corepack still blocks on stdin. Auto-accept. + export COREPACK_ENABLE_DOWNLOAD_PROMPT=0 + # Enable corepack so `pnpm` shim lands on PATH. log "Enabling corepack" corepack enable >> "$LOG_FILE" 2>&1 || true @@ -131,6 +136,16 @@ log "=== Bootstrap started ===" detect_platform check_node +if [ "$NODE_OK" = "false" ]; then + log "Node missing or too old — running setup/install-node.sh" + echo "Node not found — installing via setup/install-node.sh" + if bash "$PROJECT_ROOT/setup/install-node.sh" 2>&1 | tee -a "$LOG_FILE"; then + hash -r 2>/dev/null || true + check_node + else + log "install-node.sh failed" + fi +fi install_deps check_build_tools From e86d0d93dd50c474015e6aa73fc16e8c08fe7e18 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 18:45:19 +0300 Subject: [PATCH 74/95] feat(setup): wire CLI agent in setup:auto Chains `cli-agent` (wraps scripts/init-cli-agent.ts) between service and verify. Without this wiring, the socket at data/cli.sock accepts the connection but there's no agent group routed to `cli/local`, so `pnpm run chat` hangs waiting for a reply. Defaults: display name from NANOCLAW_DISPLAY_NAME env, falling back to \$USER then "Operator". Agent persona name from NANOCLAW_AGENT_NAME, defaulting to the display name. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) diff --git a/setup/auto.ts b/setup/auto.ts index 66d6880f4..bbe6326e8 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -7,9 +7,12 @@ * module check). This driver picks up from there. * * Config via env: - * NANOCLAW_TZ IANA zone override (skip autodetect) - * NANOCLAW_SKIP comma-separated step names to skip - * (environment|timezone|container|onecli|auth|mounts|service|verify) + * NANOCLAW_TZ IANA zone override (skip autodetect) + * NANOCLAW_DISPLAY_NAME operator name for the CLI agent (default: $USER) + * NANOCLAW_AGENT_NAME agent persona name (default: display name) + * NANOCLAW_SKIP comma-separated step names to skip + * (environment|timezone|container|onecli|auth| + * mounts|service|cli-agent|verify) * * Anthropic credential registration runs via setup/register-claude-token.sh * (the only step that truly requires human input — browser sign-in or a @@ -194,6 +197,24 @@ async function main(): Promise { } } + if (!skip.has('cli-agent')) { + const displayName = + process.env.NANOCLAW_DISPLAY_NAME?.trim() || + process.env.USER?.trim() || + 'Operator'; + const agentName = process.env.NANOCLAW_AGENT_NAME?.trim(); + const args = ['--display-name', displayName]; + if (agentName) args.push('--agent-name', agentName); + + const res = await runStep('cli-agent', args); + if (!res.ok) { + fail( + 'CLI agent wiring failed', + 'Re-run `pnpm exec tsx scripts/init-cli-agent.ts --display-name ""` to fix.', + ); + } + } + if (!skip.has('verify')) { const res = await runStep('verify'); if (!res.ok) { @@ -202,10 +223,10 @@ async function main(): Promise { console.log(' • Anthropic secret not detected — re-run `bash setup/register-claude-token.sh`'); } if (!res.fields.CONFIGURED_CHANNELS) { - console.log(' • Install a channel: `/add-discord`, `/add-slack`, `/add-telegram`, …'); - } - if (res.fields.REGISTERED_GROUPS === '0') { - console.log(' • Wire the channel to an agent group: `/manage-channels`'); + console.log( + ' • Optional: add a messaging channel — `/add-discord`, `/add-slack`, `/add-telegram`, …', + ); + console.log(' (CLI channel is already wired: `pnpm run chat hi`)'); } return; } From be6cec59adc64b8f0d24e8d8710d33ac3fff6b8e Mon Sep 17 00:00:00 2001 From: "exe.dev user" Date: Tue, 21 Apr 2026 15:55:04 +0000 Subject: [PATCH 75/95] fix(setup): auto-recover from stale docker group mid-session - container: install Docker via setup/install-docker.sh when missing, distinguish socket EACCES from daemon-down so we bail fast instead of polling 60s, and re-exec the step under `sg docker` when usermod hasn't reached the current shell. - auto: after the container step, re-exec the whole driver under `sg docker` (with a NANOCLAW_REEXEC_SG guard) so onecli/service/verify also get docker-group access without a re-login. Surface the new docker_group_not_active error from the container step. - service: when the systemd user manager has a stale group list, auto- apply \`sudo setfacl -m u:\$USER:rw /var/run/docker.sock\` so the service can start without waiting for the next login. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 34 +++++++++++++++++++ setup/container.ts | 81 +++++++++++++++++++++++++++++++++++----------- setup/service.ts | 27 ++++++++++++++-- 3 files changed, 121 insertions(+), 21 deletions(-) diff --git a/setup/auto.ts b/setup/auto.ts index bbe6326e8..8ef87d804 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -71,6 +71,33 @@ function runStep(name: string, extra: string[] = []): Promise { }); } +/** + * After installing Docker, this process's supplementary groups are still + * frozen from login — subsequent steps that talk to /var/run/docker.sock + * (onecli install, service start, …) fail with EACCES even though the + * daemon is up. Detect that and re-exec the whole driver under `sg docker` + * so the rest of the run inherits the docker group without a re-login. + */ +function maybeReexecUnderSg(): void { + if (process.env.NANOCLAW_REEXEC_SG === '1') return; // already re-exec'd + if (process.platform !== 'linux') return; + const info = spawnSync('docker', ['info'], { encoding: 'utf-8' }); + if (info.status === 0) return; + const err = `${info.stderr ?? ''}\n${info.stdout ?? ''}`; + if (!/permission denied/i.test(err)) return; + if (spawnSync('which', ['sg'], { stdio: 'ignore' }).status !== 0) return; + + console.log( + '\n[setup:auto] Docker socket not accessible in current group — ' + + 're-executing under `sg docker` to pick up new group membership.', + ); + const res = spawnSync('sg', ['docker', '-c', 'pnpm run setup:auto'], { + stdio: 'inherit', + env: { ...process.env, NANOCLAW_REEXEC_SG: '1' }, + }); + process.exit(res.status ?? 1); +} + function anthropicSecretExists(): boolean { try { const res = spawnSync('onecli', ['secrets', 'list'], { @@ -132,11 +159,18 @@ async function main(): Promise { 'Install Docker Desktop or start it manually, then retry.', ); } + if (res.fields.ERROR === 'docker_group_not_active') { + fail( + 'Docker was just installed but your shell is not yet in the `docker` group.', + 'Log out and back in (or run `newgrp docker` in a new shell), then retry `pnpm run setup:auto`.', + ); + } fail( 'container build/test failed', 'For stale build cache: `docker builder prune -f`, then retry `pnpm run setup:auto`.', ); } + maybeReexecUnderSg(); } if (!skip.has('onecli')) { diff --git a/setup/container.ts b/setup/container.ts index aadd04c9f..a2e64333e 100644 --- a/setup/container.ts +++ b/setup/container.ts @@ -2,7 +2,7 @@ * Step: container — Build container image and verify with test run. * Replaces 03-setup-container.sh */ -import { execSync } from 'child_process'; +import { execSync, spawnSync } from 'child_process'; import path from 'path'; import { setTimeout as sleep } from 'timers/promises'; @@ -10,20 +10,28 @@ import { log } from '../src/log.js'; import { commandExists, getPlatform } from './platform.js'; import { emitStatus } from './status.js'; +type DockerStatus = 'ok' | 'no-permission' | 'no-daemon' | 'other'; + +function dockerStatus(): DockerStatus { + const res = spawnSync('docker', ['info'], { encoding: 'utf-8' }); + if (res.status === 0) return 'ok'; + const err = `${res.stderr ?? ''}\n${res.stdout ?? ''}`; + if (/permission denied/i.test(err)) return 'no-permission'; + if (/cannot connect|is the docker daemon running|no such file/i.test(err)) return 'no-daemon'; + return 'other'; +} + function dockerRunning(): boolean { - try { - execSync('docker info', { stdio: 'ignore' }); - return true; - } catch { - return false; - } + return dockerStatus() === 'ok'; } /** - * Try to start Docker if it's installed but idle. Poll for up to 60s. - * Returns true once `docker info` succeeds, false if we gave up. + * Try to start Docker if it's installed but idle. Poll up to 60s for the + * daemon to come up — but bail immediately if the socket is reachable and + * only blocked by a group-permission error, since that won't resolve by + * waiting (the caller handles the sg re-exec for that case). */ -async function tryStartDocker(): Promise { +async function tryStartDocker(): Promise { const platform = getPlatform(); log.info('Docker not running — attempting to start', { platform }); @@ -34,22 +42,27 @@ async function tryStartDocker(): Promise { // Inherit stdio so sudo can prompt for a password if needed. execSync('sudo systemctl start docker', { stdio: 'inherit' }); } else { - return false; + return 'other'; } } catch (err) { log.warn('Start command failed', { err }); - return false; + return 'other'; } for (let i = 0; i < 30; i++) { await sleep(2000); - if (dockerRunning()) { + const s = dockerStatus(); + if (s === 'ok') { log.info('Docker is up'); - return true; + return 'ok'; + } + if (s === 'no-permission') { + log.info('Docker daemon is up but socket is not accessible (group membership)'); + return 'no-permission'; } } log.warn('Docker did not become ready within 60s'); - return false; + return 'no-daemon'; } function parseArgs(args: string[]): { runtime: string } { @@ -84,6 +97,15 @@ export async function run(args: string[]): Promise { process.exit(4); } + if (!commandExists('docker')) { + log.info('Docker not found — running setup/install-docker.sh'); + try { + execSync('bash setup/install-docker.sh', { cwd: projectRoot, stdio: 'inherit' }); + } catch (err) { + log.warn('install-docker.sh failed', { err }); + } + } + if (!commandExists('docker')) { emitStatus('SETUP_CONTAINER', { RUNTIME: runtime, @@ -97,16 +119,37 @@ export async function run(args: string[]): Promise { process.exit(2); } - if (!dockerRunning()) { - const started = await tryStartDocker(); - if (!started) { + { + let status = dockerStatus(); + if (status !== 'ok') { + status = await tryStartDocker(); + } + + // Socket is unreachable due to group perms — current shell's supplementary + // groups are fixed at login, so `usermod -aG docker` (via install-docker.sh + // or a prior install) doesn't affect us until next login. Re-exec this + // step under `sg docker` so the child picks up docker as its primary + // group and can talk to /var/run/docker.sock without a logout. + if (status === 'no-permission' && getPlatform() === 'linux' && commandExists('sg')) { + log.info('Re-executing container step under `sg docker`'); + const res = spawnSync( + 'sg', + ['docker', '-c', 'pnpm exec tsx setup/index.ts --step container'], + { cwd: projectRoot, stdio: 'inherit' }, + ); + process.exit(res.status ?? 1); + } + + if (status !== 'ok') { + const error = + status === 'no-permission' ? 'docker_group_not_active' : 'runtime_not_available'; emitStatus('SETUP_CONTAINER', { RUNTIME: runtime, IMAGE: image, BUILD_OK: false, TEST_OK: false, STATUS: 'failed', - ERROR: 'runtime_not_available', + ERROR: error, LOG: 'logs/setup.log', }); process.exit(2); diff --git a/setup/service.ts b/setup/service.ts index bc85d1626..56bf3938d 100644 --- a/setup/service.ts +++ b/setup/service.ts @@ -11,6 +11,7 @@ import path from 'path'; import { log } from '../src/log.js'; import { + commandExists, getPlatform, getNodePath, getServiceManager, @@ -255,12 +256,34 @@ WantedBy=${runningAsRoot ? 'multi-user.target' : 'default.target'}`; fs.writeFileSync(unitPath, unit); log.info('Wrote systemd unit', { unitPath }); - // Detect stale docker group before starting (user systemd only) - const dockerGroupStale = !runningAsRoot && checkDockerGroupStale(); + // Detect stale docker group before starting (user systemd only). The user + // systemd manager is a long-running process whose group list is frozen at + // login, so `usermod -aG docker` mid-session doesn't reach it. Rather than + // require the user to log out + back in, punch a POSIX ACL onto the socket + // that grants the current user rw directly. This is temporary — the socket + // is recreated by dockerd on restart (and by then the user has relogged, so + // normal group perms apply again). + let dockerGroupStale = !runningAsRoot && checkDockerGroupStale(); if (dockerGroupStale) { log.warn( 'Docker group not active in systemd session — user was likely added to docker group mid-session', ); + if (commandExists('setfacl')) { + const user = execSync('whoami', { encoding: 'utf-8' }).trim(); + try { + execSync(`sudo setfacl -m u:${user}:rw /var/run/docker.sock`, { + stdio: 'inherit', + }); + log.info( + 'Applied temporary ACL to /var/run/docker.sock (resets on docker restart or reboot)', + ); + dockerGroupStale = false; + } catch (err) { + log.warn('Failed to apply setfacl workaround', { err }); + } + } else { + log.warn('setfacl not installed — cannot apply automatic workaround'); + } } // Kill orphaned nanoclaw processes to avoid channel connection conflicts From 52a9ab517943b43c7dd3f21f71c8a1c878c20d8a Mon Sep 17 00:00:00 2001 From: Gabi Simons Date: Tue, 21 Apr 2026 17:21:50 +0000 Subject: [PATCH 76/95] feat(add-wechat): personal WeChat channel via Tencent iLink Bot API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit New channel skill for personal WeChat, using Tencent's official iLink Bot API (the same protocol @tencent-weixin/openclaw-weixin uses). Region-restricted to mainland 微信 accounts — international WeChat clients can't complete the QR flow. Skill contents: - Install steps copy the adapter from the `channels` branch (same pattern as other /add- skills) and register it in src/channels/index.ts. - Post-login wiring helper at scripts/wire-dm.ts — lists unwired WeChat messaging groups, prompts for an agent group, and inserts the messaging_group_agents row with sender policy `request_approval` by default (matches the router auto-create default so the admin gets an approval card on the next unknown-sender DM). - Channel Info documents how /new-setup Claude captures the operator's user_id (from data/wechat/auth.json.operatorUserId) and the first DM's platform_id (from the adapter's "WeChat inbound" log). Also adds WeChat as option 15 in /new-setup's channel list so setup wires into the existing /add- flow automatically. Addresses https://github.com/qwibitai/nanoclaw/issues/1901. Co-Authored-By: ythx-101 <226337373+ythx-101@users.noreply.github.com> Co-Authored-By: Claude Opus 4.6 (1M context) --- .claude/skills/add-wechat/REMOVE.md | 49 ++++++ .claude/skills/add-wechat/SKILL.md | 170 ++++++++++++++++++ .claude/skills/add-wechat/scripts/wire-dm.ts | 172 +++++++++++++++++++ .claude/skills/new-setup/SKILL.md | 1 + 4 files changed, 392 insertions(+) create mode 100644 .claude/skills/add-wechat/REMOVE.md create mode 100644 .claude/skills/add-wechat/SKILL.md create mode 100644 .claude/skills/add-wechat/scripts/wire-dm.ts diff --git a/.claude/skills/add-wechat/REMOVE.md b/.claude/skills/add-wechat/REMOVE.md new file mode 100644 index 000000000..366739e32 --- /dev/null +++ b/.claude/skills/add-wechat/REMOVE.md @@ -0,0 +1,49 @@ +# Remove WeChat Channel + +Undo `/add-wechat`. + +### 1. Remove credentials + +Delete WeChat lines from `.env`: + +```bash +sed -i.bak '/^WECHAT_ENABLED=/d' .env && rm -f .env.bak +cp .env data/env/env +``` + +### 2. Remove adapter and import + +```bash +rm -f src/channels/wechat.ts +sed -i.bak "/import '\.\/wechat\.js';/d" src/channels/index.ts && rm -f src/channels/index.ts.bak +``` + +### 3. Uninstall the package + +```bash +pnpm remove wechat-ilink-client +``` + +### 4. Remove saved auth + sync state + +```bash +rm -rf data/wechat +``` + +### 5. Remove DB wiring + +```sql +-- Remove any sessions first (foreign key) +DELETE FROM sessions WHERE messaging_group_id IN (SELECT id FROM messaging_groups WHERE channel_type = 'wechat'); +DELETE FROM messaging_group_agents WHERE messaging_group_id IN (SELECT id FROM messaging_groups WHERE channel_type = 'wechat'); +DELETE FROM messaging_groups WHERE channel_type = 'wechat'; +``` + +### 6. Rebuild and restart + +```bash +pnpm run build +systemctl --user restart nanoclaw # Linux +# or +launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS +``` diff --git a/.claude/skills/add-wechat/SKILL.md b/.claude/skills/add-wechat/SKILL.md new file mode 100644 index 000000000..ba0294ad5 --- /dev/null +++ b/.claude/skills/add-wechat/SKILL.md @@ -0,0 +1,170 @@ +--- +name: add-wechat +description: Add WeChat (personal) channel integration via Tencent's official iLink Bot API. Uses long-polling and QR scan — no webhook, no ToS risk, no paid token. +--- + +# Add WeChat Channel + +Adds WeChat support via **iLink Bot API** — the first-party Tencent API for personal WeChat bots (different from WeCom / Official Account). + +**Why this is different from wechaty/PadLocal:** + +- Official Tencent API — no ToS violation, no ban risk +- Free — no PadLocal token required +- No public webhook URL needed — uses long-poll +- Works with any personal WeChat account + +## Prerequisites + +- A **personal WeChat account** with the mobile app installed +- A phone to scan the QR code for login +- Node.js >= 20 (already required by NanoClaw) + +## Install + +NanoClaw doesn't ship channels in trunk. This skill copies the WeChat adapter in from the `channels` branch. + +### Pre-flight (idempotent) + +Skip to **Credentials** if all of these are already in place: + +- `src/channels/wechat.ts` exists +- `src/channels/index.ts` contains `import './wechat.js';` +- `wechat-ilink-client` is listed in `package.json` dependencies + +Otherwise continue. Every step below is safe to re-run. + +### 1. Fetch the channels branch + +```bash +git fetch origin channels +``` + +### 2. Copy the adapter + +```bash +git show origin/channels:src/channels/wechat.ts > src/channels/wechat.ts +``` + +### 3. Append the self-registration import + +Append to `src/channels/index.ts` (skip if the line is already present): + +```typescript +import './wechat.js'; +``` + +### 4. Install the library (pinned) + +```bash +pnpm install wechat-ilink-client@0.1.0 +``` + +### 5. Build + +```bash +pnpm run build +``` + +## Credentials + +Unlike most channels, WeChat requires **no pre-configured API keys**. Auth happens via QR code scan from your phone. + +### 1. Enable the channel + +Add to `.env`: + +```bash +WECHAT_ENABLED=true +``` + +Sync to container: `mkdir -p data/env && cp .env data/env/env` + +### 2. Start the service and scan the QR + +Restart NanoClaw: + +```bash +systemctl --user restart nanoclaw # Linux +# or +launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS +``` + +The adapter will print a **QR URL** to the logs and save it to `data/wechat/qr.txt`: + +```bash +tail -f logs/nanoclaw.log | grep WeChat +# or +cat data/wechat/qr.txt +``` + +Open the URL in a browser (it renders a QR code), then: + +1. Open WeChat on your phone +2. Use its built-in QR scanner (top-right "+" → Scan) +3. Approve the authorization on your phone +4. Auth credentials are saved to `data/wechat/auth.json` — do not commit this file + +The bot is now connected as your WeChat account. + +## Wire your first DM + +A successful QR login alone isn't enough — the adapter still needs to be wired to an agent group before it can respond. + +### 1. Trigger the first inbound message + +Have a different WeChat account send a message to the bot account. This auto-creates a `messaging_groups` row with the sender's `platform_id`. + +### 2. Run the wire script + +```bash +pnpm exec tsx .claude/skills/add-wechat/scripts/wire-dm.ts +``` + +Interactive flow: the script lists all unwired WeChat messaging groups, asks which agent group to wire it to, and creates the `messaging_group_agents` row with sensible defaults (sender policy `request_approval`, session mode `shared`). + +With `request_approval`, the next DM from the stranger fires an approval card to the admin — admin taps Approve/Deny, approved users are added as members and their queued message replays through the agent. + +Non-interactive: + +```bash +pnpm exec tsx .claude/skills/add-wechat/scripts/wire-dm.ts \ + --platform-id wechat:wxid_xxxxx \ + --agent-group ag-xxxxx \ + --non-interactive +``` + +Flags: + +- `--platform-id ` — wire a specific messaging group (default: most recent unwired) +- `--agent-group ` — target agent group (default: prompt; or solo admin group in non-interactive) +- `--sender-policy public|strict|request_approval` — default `request_approval` (fires an admin approval card on unknown-sender DMs) +- `--session-mode shared|per-thread` — default `shared` + +### 3. Test + +Have the sender message the bot again — the agent should respond. + +## Operational notes + +- **Only one instance can use a given token at a time.** Don't run multiple NanoClaw instances pointing to the same `data/wechat/auth.json`. +- **Re-login on session expiry:** if you see `WeChat: session expired` in logs, delete `data/wechat/auth.json` and restart — you'll be asked to re-scan. +- **Sync cursor persistence:** `data/wechat/sync-buf.txt` holds the long-poll cursor. Deleting it replays recent history on next start; don't delete it in normal operation. +- **Account safety:** this uses the official Tencent API, so account bans for bot automation aren't a risk. That said, don't spam — normal rate limits still apply. + +## Next Steps + +If you're in the middle of `/setup`, return to the setup flow now. + +Otherwise, restart the service to pick up the new channel and wiring. + +## Channel Info + +- **type**: `wechat` +- **terminology**: WeChat has "contacts" (DMs) and "group chats" (rooms). Each DM or group is a separate messaging group. +- **how-to-find-id**: Send a message to the bot from the target account; the adapter auto-creates a messaging group and logs `WeChat inbound platformId=wechat:`. Use `wechat:` for DMs, `wechat:` for rooms. +- **admin-user-id**: The operator's WeChat user_id (for `init-first-agent.ts --admin-user-id`) is saved to `data/wechat/auth.json` as `operatorUserId` after the QR scan. Read it with `cat data/wechat/auth.json | jq -r .operatorUserId` and prefix with `wechat:` (i.e. `wechat:`). +- **supports-threads**: no (WeChat has no reply threads) +- **typical-use**: Long-poll — the adapter holds a persistent connection to Tencent's iLink API and receives messages in real time. No webhook URL needed. +- **default-isolation**: `shared` session mode per messaging group (DM or room). Use `strict` sender policy if you want only specific users to reach the agent; `public` opens it to anyone who messages the bot. +- **post-install-wiring**: Use the `wire-dm.ts` helper (see the "Wire your first DM" section above) if running this skill standalone. If running inside `/new-setup`, `init-first-agent.ts` handles wiring — just pass the `platform-id` and `admin-user-id` captured above. diff --git a/.claude/skills/add-wechat/scripts/wire-dm.ts b/.claude/skills/add-wechat/scripts/wire-dm.ts new file mode 100644 index 000000000..f94c88d98 --- /dev/null +++ b/.claude/skills/add-wechat/scripts/wire-dm.ts @@ -0,0 +1,172 @@ +#!/usr/bin/env pnpm exec tsx +/** + * Wire a WeChat DM (or group) to an agent group. + * + * After /add-wechat installs the adapter and the user scans the QR login, + * the first inbound message from another WeChat account auto-creates a + * `messaging_groups` row. This script finds that row, asks the operator + * which agent group to wire it to, and inserts the `messaging_group_agents` + * join row with sensible defaults — the "post-login wiring" step /add-wechat + * otherwise requires manual SQL for. + * + * Usage: + * pnpm exec tsx .claude/skills/add-wechat/scripts/wire-dm.ts + * + * Flags: + * --platform-id Wire a specific messaging group (default: most recent unwired) + * --agent-group Target agent group (default: interactive pick; or solo admin group) + * --sender-policy

public | strict (default: public) + * --session-mode shared | per-thread (default: shared) + * --non-interactive Fail instead of prompting + */ +import Database from 'better-sqlite3'; +import path from 'node:path'; +import readline from 'node:readline'; + +const DB_PATH = process.env.NANOCLAW_DB_PATH ?? path.join(process.cwd(), 'data', 'v2.db'); + +type SenderPolicy = 'public' | 'strict' | 'request_approval'; + +interface Args { + platformId?: string; + agentGroupId?: string; + senderPolicy: SenderPolicy; + sessionMode: 'shared' | 'per-thread'; + interactive: boolean; +} + +function parseArgs(argv: string[]): Args { + const args: Args = { + // Default matches the router's auto-create (`request_approval`) so the + // admin gets an approval card on the next unknown-sender DM rather than + // a silent allow. Pass `--sender-policy public` to open the channel to + // anyone, or `strict` to require explicit membership. + senderPolicy: 'request_approval', + sessionMode: 'shared', + interactive: true, + }; + for (let i = 0; i < argv.length; i++) { + const flag = argv[i]; + const val = argv[i + 1]; + switch (flag) { + case '--platform-id': args.platformId = val; i++; break; + case '--agent-group': args.agentGroupId = val; i++; break; + case '--sender-policy': + if (val !== 'public' && val !== 'strict' && val !== 'request_approval') { + throw new Error(`bad --sender-policy: ${val} (use public | strict | request_approval)`); + } + args.senderPolicy = val; i++; break; + case '--session-mode': + if (val !== 'shared' && val !== 'per-thread') throw new Error(`bad --session-mode: ${val}`); + args.sessionMode = val; i++; break; + case '--non-interactive': args.interactive = false; break; + case '--help': case '-h': + console.log('See .claude/skills/add-wechat/scripts/wire-dm.ts header for usage.'); + process.exit(0); + } + } + return args; +} + +async function prompt(q: string): Promise { + const rl = readline.createInterface({ input: process.stdin, output: process.stdout }); + return new Promise((resolve) => rl.question(q, (a) => { rl.close(); resolve(a.trim()); })); +} + +function generateId(prefix: string): string { + return `${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; +} + +async function main(): Promise { + const args = parseArgs(process.argv.slice(2)); + const db = new Database(DB_PATH); + db.pragma('journal_mode = WAL'); + + // 1. Pick the messaging group + let platformId = args.platformId; + if (!platformId) { + const rows = db.prepare(` + SELECT mg.id, mg.platform_id, mg.name, mg.is_group, mg.created_at + FROM messaging_groups mg + LEFT JOIN messaging_group_agents mga ON mga.messaging_group_id = mg.id + WHERE mg.channel_type = 'wechat' AND mga.id IS NULL + ORDER BY mg.created_at DESC + `).all() as Array<{ id: string; platform_id: string; name: string | null; is_group: number; created_at: string }>; + + if (rows.length === 0) { + console.error('No unwired WeChat messaging groups found.'); + console.error('Send a message to the bot first (from another WeChat account), then re-run.'); + process.exit(1); + } + + if (rows.length === 1 || !args.interactive) { + platformId = rows[0].platform_id; + console.log(`Using most recent unwired group: ${platformId} (${rows[0].is_group ? 'group' : 'DM'})`); + } else { + console.log('Unwired WeChat messaging groups:'); + rows.forEach((r, i) => { + console.log(` ${i + 1}. ${r.platform_id} (${r.is_group ? 'group' : 'DM'}, ${r.created_at})`); + }); + const pick = await prompt('Pick one [1]: '); + const idx = pick === '' ? 0 : parseInt(pick, 10) - 1; + if (Number.isNaN(idx) || idx < 0 || idx >= rows.length) throw new Error('invalid choice'); + platformId = rows[idx].platform_id; + } + } + + const mg = db.prepare( + 'SELECT id, platform_id, is_group FROM messaging_groups WHERE channel_type = ? AND platform_id = ?' + ).get('wechat', platformId) as { id: string; platform_id: string; is_group: number } | undefined; + if (!mg) throw new Error(`no wechat messaging_group with platform_id = ${platformId}`); + + // 2. Pick the agent group + let agentGroupId = args.agentGroupId; + if (!agentGroupId) { + const agents = db.prepare('SELECT id, name, is_admin FROM agent_groups ORDER BY is_admin DESC, created_at ASC') + .all() as Array<{ id: string; name: string; is_admin: number }>; + if (agents.length === 0) throw new Error('no agent groups exist — create one first'); + + const adminAgents = agents.filter((a) => a.is_admin === 1); + if (adminAgents.length === 1 && !args.interactive) { + agentGroupId = adminAgents[0].id; + console.log(`Auto-selected sole admin agent group: ${adminAgents[0].name} (${agentGroupId})`); + } else if (args.interactive) { + console.log('Agent groups:'); + agents.forEach((a, i) => { + console.log(` ${i + 1}. ${a.name} (${a.id})${a.is_admin ? ' [admin]' : ''}`); + }); + const pick = await prompt('Pick one [1]: '); + const idx = pick === '' ? 0 : parseInt(pick, 10) - 1; + if (Number.isNaN(idx) || idx < 0 || idx >= agents.length) throw new Error('invalid choice'); + agentGroupId = agents[idx].id; + } else { + throw new Error('multiple agent groups exist; pass --agent-group '); + } + } + + const ag = db.prepare('SELECT id, name FROM agent_groups WHERE id = ?').get(agentGroupId) as + { id: string; name: string } | undefined; + if (!ag) throw new Error(`no agent_group with id = ${agentGroupId}`); + + // 3. Update sender policy + wire + const tx = db.transaction(() => { + db.prepare('UPDATE messaging_groups SET unknown_sender_policy = ? WHERE id = ?') + .run(args.senderPolicy, mg.id); + + db.prepare(` + INSERT INTO messaging_group_agents + (id, messaging_group_id, agent_group_id, trigger_rules, response_scope, session_mode, priority, created_at) + VALUES (?, ?, ?, '', 'all', ?, 10, datetime('now')) + `).run(generateId('mga'), mg.id, ag.id, args.sessionMode); + }); + tx(); + + console.log(''); + console.log(`WIRED platform_id=${mg.platform_id} agent_group=${ag.name} policy=${args.senderPolicy} mode=${args.sessionMode}`); + db.close(); +} + +main().catch((err) => { + console.error('FAILED:', err.message); + process.exit(1); +}); diff --git a/.claude/skills/new-setup/SKILL.md b/.claude/skills/new-setup/SKILL.md index ef88c7519..4a3f1b865 100644 --- a/.claude/skills/new-setup/SKILL.md +++ b/.claude/skills/new-setup/SKILL.md @@ -189,6 +189,7 @@ Print the list as a numbered plain-prose list (too many options for `AskUserQues > 12. **Webex** — `/add-webex` > 13. **Resend (email)** — `/add-resend` > 14. **Emacs** — `/add-emacs` +> 15. **WeChat** — `/add-wechat` > > Or say "skip" to leave this for later. From 1c748f1f2b16396ffd5fa60831f1d787dd5da228 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 22:18:08 +0300 Subject: [PATCH 77/95] refactor(setup): drop timezone step from setup:auto chain MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The timezone step blocked the scripted flow on headless servers where the resolved TZ was UTC (interactive /setup confirms, setup:auto had to bail). Drop it from the chain — host TZ defaults to whatever the OS reports. Users who need an explicit override run the step on demand: `pnpm exec tsx setup/index.ts --step timezone -- --tz `. Co-Authored-By: Claude Opus 4.7 (1M context) --- nanoclaw.sh | 5 ++--- setup/auto.ts | 19 +++++-------------- 2 files changed, 7 insertions(+), 17 deletions(-) diff --git a/nanoclaw.sh b/nanoclaw.sh index 6a23558a3..2a98f9853 100755 --- a/nanoclaw.sh +++ b/nanoclaw.sh @@ -3,14 +3,13 @@ # NanoClaw — scripted end-to-end install. # # Runs `bash setup.sh` (bootstrap: Node check, pnpm install, native module -# verify), then `pnpm run setup:auto` (environment → timezone → container → -# onecli → auth → mounts → service → verify). +# verify), then `pnpm run setup:auto` (environment → container → onecli → +# auth → mounts → service → cli-agent → verify). # # Everything that can be scripted runs unattended; the one interactive pause # is the auth step (browser sign-in or paste token/API key). # # Config via env — passed through unchanged: -# NANOCLAW_TZ IANA zone override # NANOCLAW_SKIP comma-separated setup:auto step names to skip # SECRET_NAME OneCLI secret name (default: Anthropic) # HOST_PATTERN OneCLI host pattern (default: api.anthropic.com) diff --git a/setup/auto.ts b/setup/auto.ts index 8ef87d804..3945d8274 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -7,13 +7,16 @@ * module check). This driver picks up from there. * * Config via env: - * NANOCLAW_TZ IANA zone override (skip autodetect) * NANOCLAW_DISPLAY_NAME operator name for the CLI agent (default: $USER) * NANOCLAW_AGENT_NAME agent persona name (default: display name) * NANOCLAW_SKIP comma-separated step names to skip - * (environment|timezone|container|onecli|auth| + * (environment|container|onecli|auth| * mounts|service|cli-agent|verify) * + * Timezone is not configured here — it defaults to the host system's TZ. + * Run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` later + * if autodetect is wrong (e.g. headless server with TZ=UTC). + * * Anthropic credential registration runs via setup/register-claude-token.sh * (the only step that truly requires human input — browser sign-in or a * pasted token/key). Channel auth and `/manage-channels` remain separate @@ -132,24 +135,12 @@ async function main(): Promise { .map((s) => s.trim()) .filter(Boolean), ); - const tz = process.env.NANOCLAW_TZ; if (!skip.has('environment')) { const env = await runStep('environment'); if (!env.ok) fail('environment check failed'); } - if (!skip.has('timezone')) { - const res = await runStep('timezone', tz ? ['--tz', tz] : []); - if (res.fields.NEEDS_USER_INPUT === 'true') { - fail( - 'Timezone could not be autodetected.', - 'Set NANOCLAW_TZ to an IANA zone (e.g. NANOCLAW_TZ=America/New_York).', - ); - } - if (!res.ok) fail('timezone step failed'); - } - if (!skip.has('container')) { const res = await runStep('container'); if (!res.ok) { From 81838bbb345555e2f3896916773ecc4d2c02ec54 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 23:43:43 +0300 Subject: [PATCH 78/95] fix(setup): clarify silent-paste prompt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Explicitly tell the user that nothing appears on screen as they paste and that a single Enter submits. "(Input is hidden for safety.)" was ambiguous — users kept waiting for a visible confirmation. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/register-claude-token.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/setup/register-claude-token.sh b/setup/register-claude-token.sh index 2c0860d2d..9c042d9bc 100755 --- a/setup/register-claude-token.sh +++ b/setup/register-claude-token.sh @@ -80,7 +80,8 @@ prompt_for_pasted() { local value echo echo "Paste your sk-ant-${prefix}… credential and press Enter." - echo "(Input is hidden for safety.)" + echo "Nothing will appear on the screen as you paste — that's intentional." + echo "Paste once, then just press Enter to submit." read -r -s -p "> " value Date: Tue, 21 Apr 2026 23:46:49 +0300 Subject: [PATCH 79/95] feat(setup): prompt for display name, hardcode agent persona MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Before the cli-agent step, ask the operator what the agent should call them (defaults to \$USER). The agent's own persona name is hardcoded to "Terminal Agent" — this is the scratch CLI agent, not one of the operator's real personas. NANOCLAW_DISPLAY_NAME still skips the prompt. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 39 ++++++++++++++++++++++++++++----------- 1 file changed, 28 insertions(+), 11 deletions(-) diff --git a/setup/auto.ts b/setup/auto.ts index 3945d8274..9a37a4504 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -7,8 +7,9 @@ * module check). This driver picks up from there. * * Config via env: - * NANOCLAW_DISPLAY_NAME operator name for the CLI agent (default: $USER) - * NANOCLAW_AGENT_NAME agent persona name (default: display name) + * NANOCLAW_DISPLAY_NAME operator name for the CLI agent — skips the + * interactive prompt before cli-agent. If unset, + * the driver asks, defaulting to $USER. * NANOCLAW_SKIP comma-separated step names to skip * (environment|container|onecli|auth| * mounts|service|cli-agent|verify) @@ -24,6 +25,9 @@ * and `/manage-channels` after this driver completes. */ import { spawn, spawnSync } from 'child_process'; +import { createInterface } from 'readline/promises'; + +const CLI_AGENT_NAME = 'Terminal Agent'; type Fields = Record; type StepResult = { ok: boolean; fields: Fields; exitCode: number }; @@ -114,6 +118,18 @@ function anthropicSecretExists(): boolean { } } +async function askDisplayName(fallback: string): Promise { + const rl = createInterface({ input: process.stdin, output: process.stdout }); + try { + const answer = await rl.question( + `\nWhat should the agent call you? [${fallback}]: `, + ); + return answer.trim() || fallback; + } finally { + rl.close(); + } +} + function runBashScript(relPath: string): Promise { return new Promise((resolve) => { const child = spawn('bash', [relPath], { stdio: 'inherit' }); @@ -223,19 +239,20 @@ async function main(): Promise { } if (!skip.has('cli-agent')) { - const displayName = - process.env.NANOCLAW_DISPLAY_NAME?.trim() || - process.env.USER?.trim() || - 'Operator'; - const agentName = process.env.NANOCLAW_AGENT_NAME?.trim(); - const args = ['--display-name', displayName]; - if (agentName) args.push('--agent-name', agentName); + const fallback = process.env.USER?.trim() || 'Operator'; + const preset = process.env.NANOCLAW_DISPLAY_NAME?.trim(); + const displayName = preset || (await askDisplayName(fallback)); - const res = await runStep('cli-agent', args); + const res = await runStep('cli-agent', [ + '--display-name', + displayName, + '--agent-name', + CLI_AGENT_NAME, + ]); if (!res.ok) { fail( 'CLI agent wiring failed', - 'Re-run `pnpm exec tsx scripts/init-cli-agent.ts --display-name ""` to fix.', + `Re-run \`pnpm exec tsx scripts/init-cli-agent.ts --display-name "${displayName}" --agent-name "${CLI_AGENT_NAME}"\` to fix.`, ); } } From 85faa3eab08171c815673cbbe72f177264abf519 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 23:49:28 +0300 Subject: [PATCH 80/95] fix(setup): rephrase display-name prompt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit "Your agents" — the name is stored on the operator's user row and applies to every future agent they wire up, not just this scratch CLI one. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup/auto.ts b/setup/auto.ts index 9a37a4504..dbe873390 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -122,7 +122,7 @@ async function askDisplayName(fallback: string): Promise { const rl = createInterface({ input: process.stdin, output: process.stdout }); try { const answer = await rl.question( - `\nWhat should the agent call you? [${fallback}]: `, + `\nWhat should your agents call you? [${fallback}]: `, ); return answer.trim() || fallback; } finally { From c87cd250b2989072e5fd12770cc65325b2d50797 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Tue, 21 Apr 2026 23:52:51 +0300 Subject: [PATCH 81/95] feat(verify): end-to-end agent ping via CLI channel Verify now runs \`pnpm run chat ping\` silently and checks for a reply. Emits AGENT_PING=ok|no_reply|socket_error|skipped; skipped when the service isn't running or no groups are wired (those already fail the verify via other checks). Kills the child after 90s so a wedged container can't hang setup (chat.ts's own 120s timeout is too long here). setup:auto surfaces AGENT_PING!=ok in its failure summary. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 6 +++++ setup/verify.ts | 60 +++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 64 insertions(+), 2 deletions(-) diff --git a/setup/auto.ts b/setup/auto.ts index dbe873390..d3b811397 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -264,6 +264,12 @@ async function main(): Promise { if (res.fields.CREDENTIALS !== 'configured') { console.log(' • Anthropic secret not detected — re-run `bash setup/register-claude-token.sh`'); } + if (res.fields.AGENT_PING && res.fields.AGENT_PING !== 'ok' && res.fields.AGENT_PING !== 'skipped') { + console.log( + ` • CLI agent did not reply (status: ${res.fields.AGENT_PING}). ` + + 'Check `logs/nanoclaw.log` and `groups/*/logs/container-*.log`, then try `pnpm run chat hi`.', + ); + } if (!res.fields.CONFIGURED_CHANNELS) { console.log( ' • Optional: add a messaging channel — `/add-discord`, `/add-slack`, `/add-telegram`, …', diff --git a/setup/verify.ts b/setup/verify.ts index 6dd6a4484..4be9c3f15 100644 --- a/setup/verify.ts +++ b/setup/verify.ts @@ -4,7 +4,7 @@ * * Uses better-sqlite3 directly (no sqlite3 CLI), platform-aware service checks. */ -import { execSync } from 'child_process'; +import { execSync, spawn } from 'child_process'; import fs from 'fs'; import os from 'os'; import path from 'path'; @@ -175,12 +175,22 @@ export async function run(_args: string[]): Promise { mountAllowlist = 'configured'; } + // 7. End-to-end: ping the CLI agent and confirm it replies. Only run if + // everything upstream looks healthy, since a broken socket would just hang. + let agentPing: 'ok' | 'no_reply' | 'socket_error' | 'skipped' = 'skipped'; + if (service === 'running' && registeredGroups > 0) { + log.info('Pinging CLI agent'); + agentPing = await pingCliAgent(); + log.info('Agent ping result', { agentPing }); + } + // Determine overall status const status = service === 'running' && credentials !== 'missing' && anyChannelConfigured && - registeredGroups > 0 + registeredGroups > 0 && + (agentPing === 'ok' || agentPing === 'skipped') ? 'success' : 'failed'; @@ -194,9 +204,55 @@ export async function run(_args: string[]): Promise { CHANNEL_AUTH: JSON.stringify(channelAuth), REGISTERED_GROUPS: registeredGroups, MOUNT_ALLOWLIST: mountAllowlist, + AGENT_PING: agentPing, STATUS: status, LOG: 'logs/setup.log', }); if (status === 'failed') process.exit(1); } + +/** + * Send a one-word message through the CLI channel and check for a reply. + * Silent by default — stdout/stderr of the child are captured but not + * forwarded. Kills the child after 90s so verify can't hang on a wedged + * agent (chat.ts's own timeout is 120s, which is too long for setup). + */ +function pingCliAgent(): Promise<'ok' | 'no_reply' | 'socket_error'> { + return new Promise((resolve) => { + const child = spawn('pnpm', ['run', 'chat', 'ping'], { + stdio: ['ignore', 'pipe', 'pipe'], + }); + let stdout = ''; + let settled = false; + const timer = setTimeout(() => { + if (settled) return; + settled = true; + child.kill('SIGKILL'); + resolve('no_reply'); + }, 90_000); + + child.stdout.on('data', (chunk: Buffer) => { + stdout += chunk.toString('utf-8'); + }); + child.on('close', (code) => { + if (settled) return; + settled = true; + clearTimeout(timer); + // chat.ts: exit 0 on reply, 2 on socket error, 3 on no reply. + if (code === 2) { + resolve('socket_error'); + } else if (code === 0 && stdout.trim().length > 0) { + resolve('ok'); + } else { + resolve('no_reply'); + } + }); + child.on('error', () => { + if (settled) return; + settled = true; + clearTimeout(timer); + resolve('socket_error'); + }); + }); +} From 9c7e1d02af92a0b7ef3b5f6079a1dfb2883edd2e Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 00:04:14 +0300 Subject: [PATCH 82/95] feat(setup): optional Telegram wiring in setup:auto After cli-agent, prompt the user to connect a messaging app. For now only Telegram is offered; "skip" falls through to the existing CLI flow. setup/add-telegram.sh runs the scriptable half of /add-telegram: fetch the channels branch, copy the adapter + pair-telegram files, append the self-registration import, install @chat-adapter/telegram@4.26.0 (pinned to match the skill), rebuild, collect TELEGRAM_BOT_TOKEN via silent paste, write .env + data/env/env, and kick the service so the new adapter is live. Idempotent throughout. setup:auto then runs the existing `pair-telegram` step with --intent main. The step emits the 4-digit code in its status stream, which is already forwarded to stdout by runStep. Co-Authored-By: Claude Opus 4.7 (1M context) --- nanoclaw.sh | 2 +- setup/add-telegram.sh | 134 ++++++++++++++++++++++++++++++++++++++++++ setup/auto.ts | 45 +++++++++++++- 3 files changed, 178 insertions(+), 3 deletions(-) create mode 100755 setup/add-telegram.sh diff --git a/nanoclaw.sh b/nanoclaw.sh index 2a98f9853..2dc0f048e 100755 --- a/nanoclaw.sh +++ b/nanoclaw.sh @@ -4,7 +4,7 @@ # # Runs `bash setup.sh` (bootstrap: Node check, pnpm install, native module # verify), then `pnpm run setup:auto` (environment → container → onecli → -# auth → mounts → service → cli-agent → verify). +# auth → mounts → service → cli-agent → channel → verify). # # Everything that can be scripted runs unattended; the one interactive pause # is the auth step (browser sign-in or paste token/API key). diff --git a/setup/add-telegram.sh b/setup/add-telegram.sh new file mode 100755 index 000000000..c822994c5 --- /dev/null +++ b/setup/add-telegram.sh @@ -0,0 +1,134 @@ +#!/usr/bin/env bash +set -euo pipefail + +# Install the Telegram adapter (Phase A of the /add-telegram skill), collect +# the bot token, write .env + data/env/env, and restart the service so the +# new adapter is live. Idempotent. +# +# Pair-telegram (the interactive code-sending step) is run separately by the +# caller (setup/auto.ts) so it can stream status blocks to the user. + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +# Keep in sync with .claude/skills/add-telegram/SKILL.md. +ADAPTER_VERSION="@chat-adapter/telegram@4.26.0" +CHANNELS_BRANCH="origin/channels" + +need_install() { + [[ ! -f src/channels/telegram.ts ]] && return 0 + [[ ! -f setup/pair-telegram.ts ]] && return 0 + ! grep -q "^import './telegram.js';" src/channels/index.ts 2>/dev/null && return 0 + return 1 +} + +if need_install; then + echo "[add-telegram] Fetching channels branch…" + git fetch origin channels >/dev/null 2>&1 + + echo "[add-telegram] Copying adapter files from $CHANNELS_BRANCH…" + for f in \ + src/channels/telegram.ts \ + src/channels/telegram-pairing.ts \ + src/channels/telegram-pairing.test.ts \ + src/channels/telegram-markdown-sanitize.ts \ + src/channels/telegram-markdown-sanitize.test.ts \ + setup/pair-telegram.ts + do + git show "$CHANNELS_BRANCH:$f" > "$f" + done + + # Append self-registration import if missing. + if ! grep -q "^import './telegram.js';" src/channels/index.ts; then + echo "import './telegram.js';" >> src/channels/index.ts + fi + + # Register pair-telegram step if not already in the STEPS map. + # Uses node (not sed) since sed's in-place + escape semantics differ + # between BSD (macOS) and GNU. + node -e ' + const fs = require("fs"); + const p = "setup/index.ts"; + let s = fs.readFileSync(p, "utf-8"); + if (!s.includes("\047pair-telegram\047")) { + s = s.replace( + /(register: \(\) => import\(\x27\.\/register\.js\x27\),)/, + "$1\n \x27pair-telegram\x27: () => import(\x27./pair-telegram.js\x27)," + ); + fs.writeFileSync(p, s); + } + ' + + echo "[add-telegram] Installing $ADAPTER_VERSION…" + pnpm install "$ADAPTER_VERSION" + + echo "[add-telegram] Building…" + pnpm run build >/dev/null +else + echo "[add-telegram] Adapter files already installed — skipping install phase." +fi + +# Token collection. +if grep -q '^TELEGRAM_BOT_TOKEN=.' .env 2>/dev/null; then + echo "[add-telegram] TELEGRAM_BOT_TOKEN already set in .env — skipping token prompt." +else + cat <<'EOF' + +── Create a Telegram bot ────────────────────────────────────── + + 1. Open Telegram and message @BotFather + 2. Send: /newbot + 3. Follow the prompts (bot name, username ending in "bot") + 4. Copy the token it gives you (format: :) + +Optional but recommended for groups: + 5. @BotFather → /mybots → your bot → Bot Settings → Group Privacy → OFF + +EOF + echo "Paste your TELEGRAM_BOT_TOKEN and press Enter." + echo "Nothing will appear on the screen as you paste — that's intentional." + echo "Paste once, then just press Enter to submit." + read -r -s -p "> " TOKEN &2 + exit 1 + fi + + # Telegram bot tokens: :<35+ base64url-ish chars>. + if [[ ! "$TOKEN" =~ ^[0-9]+:[A-Za-z0-9_-]{35,}$ ]]; then + echo "[add-telegram] Token format looks wrong (expected :). Aborting." >&2 + exit 1 + fi + + touch .env + if grep -q '^TELEGRAM_BOT_TOKEN=' .env; then + awk -v tok="$TOKEN" '/^TELEGRAM_BOT_TOKEN=/{print "TELEGRAM_BOT_TOKEN=" tok; next} {print}' \ + .env > .env.tmp && mv .env.tmp .env + else + echo "TELEGRAM_BOT_TOKEN=$TOKEN" >> .env + fi +fi + +# Container reads from data/env/env (the host mounts it). +mkdir -p data/env +cp .env data/env/env + +echo "[add-telegram] Restarting service so the new adapter picks up the token…" +case "$(uname -s)" in + Darwin) + launchctl kickstart -k "gui/$(id -u)/com.nanoclaw" >/dev/null 2>&1 || true + ;; + Linux) + systemctl --user restart nanoclaw >/dev/null 2>&1 \ + || sudo systemctl restart nanoclaw >/dev/null 2>&1 \ + || true + ;; +esac + +# Give the Telegram adapter a moment to finish starting before pair-telegram +# begins polling for the user's code message. +sleep 5 + +echo "[add-telegram] Install + credentials complete." diff --git a/setup/auto.ts b/setup/auto.ts index d3b811397..12a30706d 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -11,8 +11,8 @@ * interactive prompt before cli-agent. If unset, * the driver asks, defaulting to $USER. * NANOCLAW_SKIP comma-separated step names to skip - * (environment|container|onecli|auth| - * mounts|service|cli-agent|verify) + * (environment|container|onecli|auth|mounts| + * service|cli-agent|channel|verify) * * Timezone is not configured here — it defaults to the host system's TZ. * Run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` later @@ -130,6 +130,19 @@ async function askDisplayName(fallback: string): Promise { } } +async function askChannelChoice(): Promise<'telegram' | 'skip'> { + const rl = createInterface({ input: process.stdin, output: process.stdout }); + try { + console.log('\nConnect a messaging app so you can chat from your phone?'); + console.log(' 1) Telegram'); + console.log(' 2) Skip — just use the CLI for now'); + const answer = (await rl.question('Choose [1/2]: ')).trim(); + return answer === '1' ? 'telegram' : 'skip'; + } finally { + rl.close(); + } +} + function runBashScript(relPath: string): Promise { return new Promise((resolve) => { const child = spawn('bash', [relPath], { stdio: 'inherit' }); @@ -257,6 +270,34 @@ async function main(): Promise { } } + if (!skip.has('channel')) { + const choice = await askChannelChoice(); + if (choice === 'telegram') { + const installCode = await runBashScript('setup/add-telegram.sh'); + if (installCode !== 0) { + fail( + 'Telegram install failed.', + 'Re-run `bash setup/add-telegram.sh`, then `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main`.', + ); + } + + console.log( + '\n[setup:auto] Pairing Telegram. A 4-digit code will appear below.\n' + + ' From Telegram, send just those 4 digits to your bot\n' + + ' (DM the bot for a personal chat, or prefix with your\n' + + ' bot handle in a group with privacy on).\n', + ); + + const pair = await runStep('pair-telegram', ['--intent', 'main']); + if (!pair.ok) { + fail( + 'Telegram pairing failed.', + 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main`.', + ); + } + } + } + if (!skip.has('verify')) { const res = await runStep('verify'); if (!res.ok) { From 92c28a956de32c631612c5550a0f1677f07bdd77 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 00:11:35 +0300 Subject: [PATCH 83/95] feat(setup): run init-first-agent after Telegram pairing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit pair-telegram only identifies the chat and operator — it returns PLATFORM_ID and ADMIN_USER_ID but doesn't create the agent group, grant owner, or send the welcome. scripts/init-first-agent.ts does that, matching the pattern the /new-setup skill already uses for channel wiring. Also prompts for the agent's own name (default: Nano), overridable via NANOCLAW_AGENT_NAME. displayName is hoisted out of the cli-agent block so both cli-agent and channel wiring share the value. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 75 ++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 68 insertions(+), 7 deletions(-) diff --git a/setup/auto.ts b/setup/auto.ts index 12a30706d..e76d9cfc5 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -7,9 +7,11 @@ * module check). This driver picks up from there. * * Config via env: - * NANOCLAW_DISPLAY_NAME operator name for the CLI agent — skips the - * interactive prompt before cli-agent. If unset, - * the driver asks, defaulting to $USER. + * NANOCLAW_DISPLAY_NAME how the agents address the operator — skips the + * prompt. Defaults to $USER. + * NANOCLAW_AGENT_NAME name for the messaging-channel agent (Telegram, + * etc.) — skips the prompt. Defaults to "Nano". + * (The CLI scratch agent is always "Terminal Agent".) * NANOCLAW_SKIP comma-separated step names to skip * (environment|container|onecli|auth|mounts| * service|cli-agent|channel|verify) @@ -28,6 +30,7 @@ import { spawn, spawnSync } from 'child_process'; import { createInterface } from 'readline/promises'; const CLI_AGENT_NAME = 'Terminal Agent'; +const DEFAULT_AGENT_NAME = 'Nano'; type Fields = Record; type StepResult = { ok: boolean; fields: Fields; exitCode: number }; @@ -130,6 +133,18 @@ async function askDisplayName(fallback: string): Promise { } } +async function askAgentName(fallback: string): Promise { + const rl = createInterface({ input: process.stdin, output: process.stdout }); + try { + const answer = await rl.question( + `\nWhat should your agent be called? [${fallback}]: `, + ); + return answer.trim() || fallback; + } finally { + rl.close(); + } +} + async function askChannelChoice(): Promise<'telegram' | 'skip'> { const rl = createInterface({ input: process.stdin, output: process.stdout }); try { @@ -150,6 +165,15 @@ function runBashScript(relPath: string): Promise { }); } +function runTsxScript(relPath: string, args: string[] = []): Promise { + return new Promise((resolve) => { + const child = spawn('pnpm', ['exec', 'tsx', relPath, ...args], { + stdio: 'inherit', + }); + child.on('close', (code) => resolve(code ?? 1)); + }); +} + function fail(msg: string, hint?: string): never { console.error(`\n[setup:auto] ${msg}`); if (hint) console.error(` ${hint}`); @@ -251,21 +275,26 @@ async function main(): Promise { } } - if (!skip.has('cli-agent')) { + // Resolved once, reused by cli-agent + channel wiring. + let displayName: string | undefined; + const needsDisplayName = !skip.has('cli-agent') || !skip.has('channel'); + if (needsDisplayName) { const fallback = process.env.USER?.trim() || 'Operator'; const preset = process.env.NANOCLAW_DISPLAY_NAME?.trim(); - const displayName = preset || (await askDisplayName(fallback)); + displayName = preset || (await askDisplayName(fallback)); + } + if (!skip.has('cli-agent')) { const res = await runStep('cli-agent', [ '--display-name', - displayName, + displayName!, '--agent-name', CLI_AGENT_NAME, ]); if (!res.ok) { fail( 'CLI agent wiring failed', - `Re-run \`pnpm exec tsx scripts/init-cli-agent.ts --display-name "${displayName}" --agent-name "${CLI_AGENT_NAME}"\` to fix.`, + `Re-run \`pnpm exec tsx scripts/init-cli-agent.ts --display-name "${displayName!}" --agent-name "${CLI_AGENT_NAME}"\` to fix.`, ); } } @@ -295,6 +324,38 @@ async function main(): Promise { 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main`.', ); } + + const platformId = pair.fields.PLATFORM_ID; + const adminUserId = pair.fields.ADMIN_USER_ID; + if (!platformId || !adminUserId) { + fail( + 'pair-telegram succeeded but did not return PLATFORM_ID and ADMIN_USER_ID.', + 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main` and capture the success block.', + ); + } + + const agentName = + process.env.NANOCLAW_AGENT_NAME?.trim() || + (await askAgentName(DEFAULT_AGENT_NAME)); + + console.log('\n── wiring first agent ──────────────────────────'); + const initCode = await runTsxScript('scripts/init-first-agent.ts', [ + '--channel', 'telegram', + '--user-id', adminUserId, + '--platform-id', platformId, + '--display-name', displayName!, + '--agent-name', agentName, + ]); + if (initCode !== 0) { + fail( + 'Wiring the Telegram agent failed.', + `Re-run \`pnpm exec tsx scripts/init-first-agent.ts --channel telegram --user-id "${adminUserId}" --platform-id "${platformId}" --display-name "${displayName!}" --agent-name "${agentName}"\`.`, + ); + } + + console.log( + `\n[setup:auto] Telegram is wired. ${agentName} will DM you a welcome shortly.`, + ); } } From e7d798b00da16f2925ed50402b232d76935780f7 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 00:17:42 +0300 Subject: [PATCH 84/95] feat(setup): validate Telegram token via getMe and deep-link to bot MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After the token is in .env, call https://api.telegram.org/bot/getMe — if ok, extract the bot's username and \`open tg://resolve?domain=\` so the Telegram desktop app lands on the bot chat. When pair-telegram prints the 4-digit code a moment later, the user just types it into the already- open chat instead of hunting for their bot. Falls back to https://t.me/ if the tg:// scheme isn't registered, and just warns-and-continues if getMe fails (network hiccup shouldn't block setup). Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/add-telegram.sh | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/setup/add-telegram.sh b/setup/add-telegram.sh index c822994c5..8183c333f 100755 --- a/setup/add-telegram.sh +++ b/setup/add-telegram.sh @@ -111,10 +111,46 @@ EOF fi fi +# Validate the token via getMe so a typo surfaces before we restart the +# service, and capture the bot's username for the deep link. +TELEGRAM_BOT_TOKEN_VALUE="$(grep '^TELEGRAM_BOT_TOKEN=' .env | head -1 | cut -d= -f2-)" +BOT_USERNAME="" +if [[ -n "$TELEGRAM_BOT_TOKEN_VALUE" ]]; then + INFO=$(curl -fsS --max-time 8 \ + "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN_VALUE}/getMe" 2>/dev/null || true) + if echo "$INFO" | grep -q '"ok":true'; then + # Crude JSON parse — the response is always a flat object here. + BOT_USERNAME=$(echo "$INFO" | sed -nE 's/.*"username":"([^"]+)".*/\1/p') + if [[ -n "$BOT_USERNAME" ]]; then + echo "[add-telegram] Token validated — bot is @${BOT_USERNAME}." + fi + else + echo "[add-telegram] Warning: getMe did not return ok. Continuing, but the token may be wrong." + fi +fi + # Container reads from data/env/env (the host mounts it). mkdir -p data/env cp .env data/env/env +# Deep-link into the bot's chat in the installed Telegram app so the user +# is already on the right screen when pair-telegram prints the code. +if [[ -n "$BOT_USERNAME" ]]; then + case "$(uname -s)" in + Darwin) + open "tg://resolve?domain=${BOT_USERNAME}" >/dev/null 2>&1 \ + || open "https://t.me/${BOT_USERNAME}" >/dev/null 2>&1 \ + || true + ;; + Linux) + xdg-open "tg://resolve?domain=${BOT_USERNAME}" >/dev/null 2>&1 \ + || xdg-open "https://t.me/${BOT_USERNAME}" >/dev/null 2>&1 \ + || true + ;; + esac + echo "[add-telegram] Opened Telegram → @${BOT_USERNAME}. Keep it open for the pairing code." +fi + echo "[add-telegram] Restarting service so the new adapter picks up the token…" case "$(uname -s)" in Darwin) From 5a472c4155ec81424b8ee8ebbecdcc9468e43090 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 00:19:23 +0300 Subject: [PATCH 85/95] fix(setup): print bot URL alongside the deep-link attempt Headless / SSH / WSL users won't have \`open\` or \`xdg-open\` wired up, so the deep-link fails silently and they have no clue where to go. Always print https://t.me/ so the URL is at least clickable or copy-pasteable from the terminal. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/add-telegram.sh | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/setup/add-telegram.sh b/setup/add-telegram.sh index 8183c333f..13ffaa933 100755 --- a/setup/add-telegram.sh +++ b/setup/add-telegram.sh @@ -134,21 +134,24 @@ mkdir -p data/env cp .env data/env/env # Deep-link into the bot's chat in the installed Telegram app so the user -# is already on the right screen when pair-telegram prints the code. +# is already on the right screen when pair-telegram prints the code. Also +# always print the URL so headless / remote-SSH users can open it manually. if [[ -n "$BOT_USERNAME" ]]; then + BOT_URL="https://t.me/${BOT_USERNAME}" case "$(uname -s)" in Darwin) open "tg://resolve?domain=${BOT_USERNAME}" >/dev/null 2>&1 \ - || open "https://t.me/${BOT_USERNAME}" >/dev/null 2>&1 \ + || open "$BOT_URL" >/dev/null 2>&1 \ || true ;; Linux) xdg-open "tg://resolve?domain=${BOT_USERNAME}" >/dev/null 2>&1 \ - || xdg-open "https://t.me/${BOT_USERNAME}" >/dev/null 2>&1 \ + || xdg-open "$BOT_URL" >/dev/null 2>&1 \ || true ;; esac - echo "[add-telegram] Opened Telegram → @${BOT_USERNAME}. Keep it open for the pairing code." + echo "[add-telegram] Bot chat: ${BOT_URL}" + echo "[add-telegram] (If Telegram didn't open automatically, click the link above.)" fi echo "[add-telegram] Restarting service so the new adapter picks up the token…" From 356a4d0a9fd3fe7da7444065a56a603131f016cf Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 00:22:53 +0300 Subject: [PATCH 86/95] feat(setup): render Telegram pairing code in a focused banner MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The pair-telegram step emits PAIR_TELEGRAM_ISSUED / _NEW_CODE / _ATTEMPT blocks meant for /setup skill parsing — dumping them raw in setup:auto left the operator squinting at key/value clutter. Intercept the stream line-by-line, suppress the block framing, and print just the 4-digit code inside a box with a short instruction. Wrong-code attempts and the final success block also get short human lines. parseStatus still runs on the full buffered output at close so PLATFORM_ID / ADMIN_USER_ID flow through unchanged to init-first-agent. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 122 ++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 114 insertions(+), 8 deletions(-) diff --git a/setup/auto.ts b/setup/auto.ts index e76d9cfc5..096368c27 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -81,6 +81,119 @@ function runStep(name: string, extra: string[] = []): Promise { }); } +/** + * Variant of runStep for `pair-telegram`. The step emits machine-readable + * status blocks (PAIR_TELEGRAM_ISSUED, PAIR_TELEGRAM_ATTEMPT, etc.) meant + * for the /setup skill to parse and relay. Running it directly leaves the + * operator staring at noisy blocks — this filters them and renders a + * focused banner around the 4-digit code instead. + */ +function runPairTelegram(intent: string): Promise { + return new Promise((resolve) => { + console.log('\n── pair-telegram ───────────────────────────────'); + const args = [ + 'exec', 'tsx', 'setup/index.ts', + '--step', 'pair-telegram', + '--', '--intent', intent, + ]; + const child = spawn('pnpm', args, { stdio: ['inherit', 'pipe', 'inherit'] }); + + let buf = ''; + let partial = ''; + let inBlock = false; + let blockType = ''; + let blockFields: Record = {}; + + function handleLine(line: string): void { + if (line.startsWith('=== NANOCLAW SETUP:')) { + inBlock = true; + blockType = line.replace('=== NANOCLAW SETUP:', '').replace('===', '').trim(); + blockFields = {}; + return; + } + if (line.startsWith('=== END ===')) { + inBlock = false; + renderBlock(blockType, blockFields); + return; + } + if (inBlock) { + const idx = line.indexOf(':'); + if (idx > -1) { + blockFields[line.slice(0, idx).trim()] = line.slice(idx + 1).trim(); + } + return; + } + process.stdout.write(line + '\n'); + } + + function renderBlock(type: string, fields: Record): void { + switch (type) { + case 'PAIR_TELEGRAM_ISSUED': + printCodeBanner(fields.CODE ?? '????'); + break; + case 'PAIR_TELEGRAM_NEW_CODE': + console.log('\n Previous code invalidated. New code:'); + printCodeBanner(fields.CODE ?? '????'); + break; + case 'PAIR_TELEGRAM_ATTEMPT': + console.log( + ` Got "${fields.RECEIVED_CODE ?? '?'}" — doesn't match. A new code is on its way.`, + ); + break; + case 'PAIR_TELEGRAM': + if (fields.STATUS === 'success') { + console.log('\n ✓ Telegram paired.'); + } else if (fields.STATUS === 'failed') { + console.log(`\n ✗ Pairing failed: ${fields.ERROR ?? 'unknown'}`); + } + break; + default: { + // Forward unknown blocks verbatim (forward-compat). + const lines = [`=== NANOCLAW SETUP: ${type} ===`]; + for (const [k, v] of Object.entries(fields)) lines.push(`${k}: ${v}`); + lines.push('=== END ==='); + process.stdout.write(lines.join('\n') + '\n'); + } + } + } + + child.stdout.on('data', (chunk: Buffer) => { + const s = chunk.toString('utf-8'); + buf += s; + partial += s; + const lines = partial.split('\n'); + partial = lines.pop() ?? ''; + for (const line of lines) handleLine(line); + }); + child.on('close', (code) => { + if (partial) handleLine(partial); + const fields = parseStatus(buf); + resolve({ + ok: code === 0 && fields.STATUS === 'success', + fields, + exitCode: code ?? 1, + }); + }); + }); +} + +function printCodeBanner(code: string): void { + // Double-space between digits for readability in a 4-digit code. + const digits = code.trim().split('').join(' '); + const content = [ + '', + ` PAIRING CODE: ${digits}`, + '', + ' Send these digits from Telegram to your bot.', + '', + ]; + const width = Math.max(...content.map((l) => l.length)); + const top = ' ╔' + '═'.repeat(width + 2) + '╗'; + const bot = ' ╚' + '═'.repeat(width + 2) + '╝'; + const mid = content.map((l) => ' ║ ' + l.padEnd(width) + ' ║'); + console.log(['', top, ...mid, bot, ''].join('\n')); +} + /** * After installing Docker, this process's supplementary groups are still * frozen from login — subsequent steps that talk to /var/run/docker.sock @@ -310,14 +423,7 @@ async function main(): Promise { ); } - console.log( - '\n[setup:auto] Pairing Telegram. A 4-digit code will appear below.\n' + - ' From Telegram, send just those 4 digits to your bot\n' + - ' (DM the bot for a personal chat, or prefix with your\n' + - ' bot handle in a group with privacy on).\n', - ); - - const pair = await runStep('pair-telegram', ['--intent', 'main']); + const pair = await runPairTelegram('main'); if (!pair.ok) { fail( 'Telegram pairing failed.', From e24ecbf8b083be9ecf5cacd8e460c64ae7e0b9c7 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 00:27:43 +0300 Subject: [PATCH 87/95] refactor(setup): own pair-telegram.ts in this branch with clean output MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously setup:auto parsed pair-telegram's machine-readable status blocks and rendered a banner on top. Fork the script instead: check in setup/pair-telegram.ts with a focused 4-digit banner, a short wrong-attempt line, and a single final PAIR_TELEGRAM status block (kept so the parent driver still picks up PLATFORM_ID and PAIRED_USER_ID via parseStatus). Drop pair-telegram.ts from add-telegram.sh's copy list so the local version isn't overwritten on re-runs. The other adapter files (telegram.ts, telegram-pairing.ts, etc.) still come from the channels branch. Also fix a latent bug: auto.ts was reading ADMIN_USER_ID from the success block, but the actual field name is PAIRED_USER_ID — init-first-agent would have been called with --user-id "". Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/add-telegram.sh | 6 +- setup/auto.ts | 125 ++--------------------------------------- setup/pair-telegram.ts | 124 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 133 insertions(+), 122 deletions(-) create mode 100644 setup/pair-telegram.ts diff --git a/setup/add-telegram.sh b/setup/add-telegram.sh index 13ffaa933..262502de5 100755 --- a/setup/add-telegram.sh +++ b/setup/add-telegram.sh @@ -17,7 +17,6 @@ CHANNELS_BRANCH="origin/channels" need_install() { [[ ! -f src/channels/telegram.ts ]] && return 0 - [[ ! -f setup/pair-telegram.ts ]] && return 0 ! grep -q "^import './telegram.js';" src/channels/index.ts 2>/dev/null && return 0 return 1 } @@ -26,14 +25,15 @@ if need_install; then echo "[add-telegram] Fetching channels branch…" git fetch origin channels >/dev/null 2>&1 + # pair-telegram.ts is maintained in this branch (setup-auto), so it's NOT + # in this list — do not overwrite the local version with the channels copy. echo "[add-telegram] Copying adapter files from $CHANNELS_BRANCH…" for f in \ src/channels/telegram.ts \ src/channels/telegram-pairing.ts \ src/channels/telegram-pairing.test.ts \ src/channels/telegram-markdown-sanitize.ts \ - src/channels/telegram-markdown-sanitize.test.ts \ - setup/pair-telegram.ts + src/channels/telegram-markdown-sanitize.test.ts do git show "$CHANNELS_BRANCH:$f" > "$f" done diff --git a/setup/auto.ts b/setup/auto.ts index 096368c27..d1358ca15 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -81,119 +81,6 @@ function runStep(name: string, extra: string[] = []): Promise { }); } -/** - * Variant of runStep for `pair-telegram`. The step emits machine-readable - * status blocks (PAIR_TELEGRAM_ISSUED, PAIR_TELEGRAM_ATTEMPT, etc.) meant - * for the /setup skill to parse and relay. Running it directly leaves the - * operator staring at noisy blocks — this filters them and renders a - * focused banner around the 4-digit code instead. - */ -function runPairTelegram(intent: string): Promise { - return new Promise((resolve) => { - console.log('\n── pair-telegram ───────────────────────────────'); - const args = [ - 'exec', 'tsx', 'setup/index.ts', - '--step', 'pair-telegram', - '--', '--intent', intent, - ]; - const child = spawn('pnpm', args, { stdio: ['inherit', 'pipe', 'inherit'] }); - - let buf = ''; - let partial = ''; - let inBlock = false; - let blockType = ''; - let blockFields: Record = {}; - - function handleLine(line: string): void { - if (line.startsWith('=== NANOCLAW SETUP:')) { - inBlock = true; - blockType = line.replace('=== NANOCLAW SETUP:', '').replace('===', '').trim(); - blockFields = {}; - return; - } - if (line.startsWith('=== END ===')) { - inBlock = false; - renderBlock(blockType, blockFields); - return; - } - if (inBlock) { - const idx = line.indexOf(':'); - if (idx > -1) { - blockFields[line.slice(0, idx).trim()] = line.slice(idx + 1).trim(); - } - return; - } - process.stdout.write(line + '\n'); - } - - function renderBlock(type: string, fields: Record): void { - switch (type) { - case 'PAIR_TELEGRAM_ISSUED': - printCodeBanner(fields.CODE ?? '????'); - break; - case 'PAIR_TELEGRAM_NEW_CODE': - console.log('\n Previous code invalidated. New code:'); - printCodeBanner(fields.CODE ?? '????'); - break; - case 'PAIR_TELEGRAM_ATTEMPT': - console.log( - ` Got "${fields.RECEIVED_CODE ?? '?'}" — doesn't match. A new code is on its way.`, - ); - break; - case 'PAIR_TELEGRAM': - if (fields.STATUS === 'success') { - console.log('\n ✓ Telegram paired.'); - } else if (fields.STATUS === 'failed') { - console.log(`\n ✗ Pairing failed: ${fields.ERROR ?? 'unknown'}`); - } - break; - default: { - // Forward unknown blocks verbatim (forward-compat). - const lines = [`=== NANOCLAW SETUP: ${type} ===`]; - for (const [k, v] of Object.entries(fields)) lines.push(`${k}: ${v}`); - lines.push('=== END ==='); - process.stdout.write(lines.join('\n') + '\n'); - } - } - } - - child.stdout.on('data', (chunk: Buffer) => { - const s = chunk.toString('utf-8'); - buf += s; - partial += s; - const lines = partial.split('\n'); - partial = lines.pop() ?? ''; - for (const line of lines) handleLine(line); - }); - child.on('close', (code) => { - if (partial) handleLine(partial); - const fields = parseStatus(buf); - resolve({ - ok: code === 0 && fields.STATUS === 'success', - fields, - exitCode: code ?? 1, - }); - }); - }); -} - -function printCodeBanner(code: string): void { - // Double-space between digits for readability in a 4-digit code. - const digits = code.trim().split('').join(' '); - const content = [ - '', - ` PAIRING CODE: ${digits}`, - '', - ' Send these digits from Telegram to your bot.', - '', - ]; - const width = Math.max(...content.map((l) => l.length)); - const top = ' ╔' + '═'.repeat(width + 2) + '╗'; - const bot = ' ╚' + '═'.repeat(width + 2) + '╝'; - const mid = content.map((l) => ' ║ ' + l.padEnd(width) + ' ║'); - console.log(['', top, ...mid, bot, ''].join('\n')); -} - /** * After installing Docker, this process's supplementary groups are still * frozen from login — subsequent steps that talk to /var/run/docker.sock @@ -423,7 +310,7 @@ async function main(): Promise { ); } - const pair = await runPairTelegram('main'); + const pair = await runStep('pair-telegram', ['--intent', 'main']); if (!pair.ok) { fail( 'Telegram pairing failed.', @@ -432,10 +319,10 @@ async function main(): Promise { } const platformId = pair.fields.PLATFORM_ID; - const adminUserId = pair.fields.ADMIN_USER_ID; - if (!platformId || !adminUserId) { + const pairedUserId = pair.fields.PAIRED_USER_ID; + if (!platformId || !pairedUserId) { fail( - 'pair-telegram succeeded but did not return PLATFORM_ID and ADMIN_USER_ID.', + 'pair-telegram succeeded but did not return PLATFORM_ID and PAIRED_USER_ID.', 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main` and capture the success block.', ); } @@ -447,7 +334,7 @@ async function main(): Promise { console.log('\n── wiring first agent ──────────────────────────'); const initCode = await runTsxScript('scripts/init-first-agent.ts', [ '--channel', 'telegram', - '--user-id', adminUserId, + '--user-id', pairedUserId, '--platform-id', platformId, '--display-name', displayName!, '--agent-name', agentName, @@ -455,7 +342,7 @@ async function main(): Promise { if (initCode !== 0) { fail( 'Wiring the Telegram agent failed.', - `Re-run \`pnpm exec tsx scripts/init-first-agent.ts --channel telegram --user-id "${adminUserId}" --platform-id "${platformId}" --display-name "${displayName!}" --agent-name "${agentName}"\`.`, + `Re-run \`pnpm exec tsx scripts/init-first-agent.ts --channel telegram --user-id "${pairedUserId}" --platform-id "${platformId}" --display-name "${displayName!}" --agent-name "${agentName}"\`.`, ); } diff --git a/setup/pair-telegram.ts b/setup/pair-telegram.ts new file mode 100644 index 000000000..cf7259bca --- /dev/null +++ b/setup/pair-telegram.ts @@ -0,0 +1,124 @@ +/** + * Step: pair-telegram — issue a one-time pairing code and wait for the + * operator to send the code from the chat they want to register. + * + * Used exclusively by `setup:auto` / `bash nanoclaw.sh` on this branch. Human- + * facing output is a focused banner for the code (no parseable block), plus a + * short line for wrong attempts / regenerations. A single machine-readable + * PAIR_TELEGRAM status block is still emitted at the end so the parent driver + * can pick up PLATFORM_ID / PAIRED_USER_ID / IS_GROUP. + * + * Depends on src/channels/telegram-pairing.js, which setup/add-telegram.sh + * copies in from the `channels` branch before this step runs. setup/ is + * excluded from the host tsconfig, so this file's import resolves only at + * runtime — tsc won't complain on branches that haven't run add-telegram yet. + */ +import path from 'path'; + +import { + createPairing, + waitForPairing, + type PairingIntent, +} from '../src/channels/telegram-pairing.js'; +import { DATA_DIR } from '../src/config.js'; +import { initDb } from '../src/db/connection.js'; +import { runMigrations } from '../src/db/migrations/index.js'; + +import { emitStatus } from './status.js'; + +function parseArgs(args: string[]): PairingIntent { + let intent: PairingIntent = 'main'; + for (let i = 0; i < args.length; i++) { + if (args[i] === '--intent') { + const raw = args[++i] || 'main'; + if (raw === 'main') { + intent = 'main'; + } else if (raw.startsWith('wire-to:')) { + intent = { kind: 'wire-to', folder: raw.slice('wire-to:'.length) }; + } else if (raw.startsWith('new-agent:')) { + intent = { kind: 'new-agent', folder: raw.slice('new-agent:'.length) }; + } else { + throw new Error(`Unknown intent: ${raw}`); + } + } + } + return intent; +} + +function intentToString(intent: PairingIntent): string { + if (intent === 'main') return 'main'; + return `${intent.kind}:${intent.folder}`; +} + +function printCodeBanner(code: string): void { + const digits = code.split('').join(' '); + const content = [ + '', + ` PAIRING CODE: ${digits}`, + '', + ' Send these digits from Telegram to your bot.', + '', + ]; + const width = Math.max(...content.map((l) => l.length)); + const top = ' ╔' + '═'.repeat(width + 2) + '╗'; + const bot = ' ╚' + '═'.repeat(width + 2) + '╝'; + const mid = content.map((l) => ' ║ ' + l.padEnd(width) + ' ║'); + console.log(['', top, ...mid, bot, ''].join('\n')); +} + +export async function run(args: string[]): Promise { + const intent = parseArgs(args); + + // Pairing stores state under DATA_DIR; the DB isn't strictly needed for the + // pairing primitive itself, but the inbound interceptor running inside the + // live service needs migrations applied. Touch it here so a fresh install + // doesn't fail on the first code match. + const db = initDb(path.join(DATA_DIR, 'v2.db')); + runMigrations(db); + + const MAX_REGENERATIONS = 5; + let record = await createPairing(intent); + printCodeBanner(record.code); + + for (let regen = 0; regen <= MAX_REGENERATIONS; regen++) { + try { + const consumed = await waitForPairing(record.code, { + onAttempt: (a) => { + console.log( + ` Got "${a.candidate}" — doesn't match. A new code is on its way.`, + ); + }, + }); + + console.log('\n ✓ Telegram paired.\n'); + emitStatus('PAIR_TELEGRAM', { + STATUS: 'success', + CODE: record.code, + INTENT: intentToString(consumed.intent), + PLATFORM_ID: consumed.consumed!.platformId, + IS_GROUP: consumed.consumed!.isGroup, + PAIRED_USER_ID: consumed.consumed!.adminUserId + ? `telegram:${consumed.consumed!.adminUserId}` + : '', + }); + return; + } catch (err) { + const message = err instanceof Error ? err.message : String(err); + const invalidated = /invalidated by wrong code/.test(message); + if (invalidated && regen < MAX_REGENERATIONS) { + record = await createPairing(intent); + console.log('\n Previous code invalidated. New code:'); + printCodeBanner(record.code); + continue; + } + const reason = invalidated ? 'max-regenerations-exceeded' : message; + console.error(`\n ✗ Pairing failed: ${reason}`); + emitStatus('PAIR_TELEGRAM', { + STATUS: 'failed', + CODE: record.code, + ERROR: reason, + }); + process.exit(2); + } + } +} From 6e0d742a7fdc0335d3ced3c2951bcda4e7ffd473 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 01:09:26 +0300 Subject: [PATCH 88/95] feat(setup): brand setup:auto with @clack/prompts + brand palette MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Wraps the scripted setup flow in a branded, friendly UI. Each step runs under a clack spinner with elapsed time; child stdout/stderr is captured quietly and dumped only on failure. Interactive children (token paste, Anthropic OAuth) bypass the spinner and inherit the TTY. - intro: NanoClaw wordmark + brand-cyan accent chip, truecolor with kleur fallback and NO_COLOR / non-TTY awareness - pair-telegram: emits PAIR_TELEGRAM_CODE / _ATTEMPT status blocks only; auto.ts renders clack notes + "received X — doesn't match" checkpoints - streaming status-block parser handles mid-step events without waiting for the child to exit - terminal-block detection now finds any block with a STATUS field (handles MOUNTS emitting CONFIGURE_MOUNTS, etc.) and treats 'skipped' as a success variant with an optional friendlier label Also fixes a latent bash bug where `$VAR…` (unbraced followed by a multi-byte Unicode character) pulled ellipsis bytes into the variable name lookup and tripped `set -u`. Braced `${VAR}` in add-telegram.sh and register-claude-token.sh. Co-Authored-By: Claude Opus 4.7 (1M context) --- package.json | 5 +- pnpm-lock.yaml | 76 +++++ setup/add-telegram.sh | 4 +- setup/auto.ts | 596 ++++++++++++++++++++++++--------- setup/pair-telegram.ts | 50 ++- setup/register-claude-token.sh | 2 +- 6 files changed, 541 insertions(+), 192 deletions(-) diff --git a/package.json b/package.json index a7f8804e9..536714f1a 100644 --- a/package.json +++ b/package.json @@ -24,10 +24,13 @@ "test:watch": "vitest" }, "dependencies": { + "@chat-adapter/telegram": "4.26.0", + "@clack/prompts": "^1.2.0", "@onecli-sh/sdk": "^0.3.1", "better-sqlite3": "11.10.0", "chat": "^4.24.0", - "cron-parser": "5.5.0" + "cron-parser": "5.5.0", + "kleur": "^4.1.5" }, "devDependencies": { "@eslint/js": "^9.35.0", diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index c1aa19738..4f284a425 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -8,6 +8,12 @@ importers: .: dependencies: + '@chat-adapter/telegram': + specifier: 4.26.0 + version: 4.26.0 + '@clack/prompts': + specifier: ^1.2.0 + version: 1.2.0 '@onecli-sh/sdk': specifier: ^0.3.1 version: 0.3.1 @@ -20,6 +26,9 @@ importers: cron-parser: specifier: 5.5.0 version: 5.5.0 + kleur: + specifier: ^4.1.5 + version: 4.1.5 devDependencies: '@eslint/js': specifier: ^9.35.0 @@ -60,6 +69,18 @@ importers: packages: + '@chat-adapter/shared@4.26.0': + resolution: {integrity: sha512-YD0MGktFXrArUqTBsyPfL5vkdD1WBS58PAWO0oVrMQAMmPxpAXfWGjBtZCkf3y8R8Svb0uVuVXiMZSForaEnMQ==} + + '@chat-adapter/telegram@4.26.0': + resolution: {integrity: sha512-PE2HoCQ4648VNKZTuHFanQNoYzM/niNoSbDyYlPq6VOoB5qsoo1ctR8TERyl1EfPBNexWZpSWYrrnQPr15LUfA==} + + '@clack/core@1.2.0': + resolution: {integrity: sha512-qfxof/3T3t9DPU/Rj3OmcFyZInceqj/NVtO9rwIuJqCUgh32gwPjpFQQp/ben07qKlhpwq7GzfWpST4qdJ5Drg==} + + '@clack/prompts@1.2.0': + resolution: {integrity: sha512-4jmztR9fMqPMjz6H/UZXj0zEmE43ha1euENwkckKKel4XpSfokExPo5AiVStdHSAlHekz4d0CA/r45Ok1E4D3w==} + '@emnapi/core@1.9.2': resolution: {integrity: sha512-UC+ZhH3XtczQYfOlu3lNEkdW/p4dsJ1r/bP7H8+rhao3TTTMO1ATq/4DdIi23XuGoFY+Cz0JmCbdVl0hz9jZcA==} @@ -748,6 +769,15 @@ packages: fast-levenshtein@2.0.6: resolution: {integrity: sha512-DCXu6Ifhqcks7TZKY3Hxp3y6qphY5SJZmrWMDrKcERSOXWQdMhU9Ig/PYrzyw/ul9jOIyh0N4M0tbC5hodg8dw==} + fast-string-truncated-width@1.2.1: + resolution: {integrity: sha512-Q9acT/+Uu3GwGj+5w/zsGuQjh9O1TyywhIwAxHudtWrgF09nHOPrvTLhQevPbttcxjr/SNN7mJmfOw/B1bXgow==} + + fast-string-width@1.1.0: + resolution: {integrity: sha512-O3fwIVIH5gKB38QNbdg+3760ZmGz0SZMgvwJbA1b2TGXceKE6A2cOlfogh1iw8lr049zPyd7YADHy+B7U4W9bQ==} + + fast-wrap-ansi@0.1.6: + resolution: {integrity: sha512-HlUwET7a5gqjURj70D5jl7aC3Zmy4weA1SHUfM0JFI0Ptq987NH2TwbBFLoERhfwk+E+eaq4EK3jXoT+R3yp3w==} + fdir@6.5.0: resolution: {integrity: sha512-tIbYtZbucOs0BRGqPJkshJUYdL+SDH7dVM8gjy+ERp3WAUjLEFJE+02kanyHtwjWOnwrKYBiwAmM0p4kLJAnXg==} engines: {node: '>=12.0.0'} @@ -866,6 +896,10 @@ packages: keyv@4.5.4: resolution: {integrity: sha512-oxVHkHR/EJf2CNXnWxRLW6mg7JyCCUcG0DtEGmL2ctUo1PNTin1PUil+r/+4r5MpVgC/fn1kjsx7mjSujKqIpw==} + kleur@4.1.5: + resolution: {integrity: sha512-o+NO+8WrRiQEE4/7nwRJhN1HWpVmJm511pBHUxPLtp0BUISzlBplORYSmTclCnJvQq2tKu/sgl3xVpkc7ZWuQQ==} + engines: {node: '>=6'} + levn@0.4.1: resolution: {integrity: sha512-+bT2uH4E5LGE7h/n3evcS/sQlJXCpIp6ym8OWJ5eV6+67Dsql/LaaT7qJBAt2rzfoa/5QBGBhxDix1dMt2kQKQ==} engines: {node: '>= 0.8.0'} @@ -1239,6 +1273,9 @@ packages: simple-get@4.0.1: resolution: {integrity: sha512-brv7p5WgH0jmQJr1ZDDfKDOSeWWg+OVypG99A/5vYGPqJ6pxiaHLy8nxtFjBA7oMa01ebA9gfh1uMCFqOuXxvA==} + sisteransi@1.0.5: + resolution: {integrity: sha512-bLGGlR1QxBcynn2d5YmDX4MGjlZvy2MRBDRNHLJ8VI6l6+9FUiyTFNJ0IveOSP0bcXgVDPRcfGqA0pjaqUpfVg==} + source-map-js@1.2.1: resolution: {integrity: sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==} engines: {node: '>=0.10.0'} @@ -1462,6 +1499,31 @@ packages: snapshots: + '@chat-adapter/shared@4.26.0': + dependencies: + chat: 4.26.0 + transitivePeerDependencies: + - supports-color + + '@chat-adapter/telegram@4.26.0': + dependencies: + '@chat-adapter/shared': 4.26.0 + chat: 4.26.0 + transitivePeerDependencies: + - supports-color + + '@clack/core@1.2.0': + dependencies: + fast-wrap-ansi: 0.1.6 + sisteransi: 1.0.5 + + '@clack/prompts@1.2.0': + dependencies: + '@clack/core': 1.2.0 + fast-string-width: 1.1.0 + fast-wrap-ansi: 0.1.6 + sisteransi: 1.0.5 + '@emnapi/core@1.9.2': dependencies: '@emnapi/wasi-threads': 1.2.1 @@ -2105,6 +2167,16 @@ snapshots: fast-levenshtein@2.0.6: {} + fast-string-truncated-width@1.2.1: {} + + fast-string-width@1.1.0: + dependencies: + fast-string-truncated-width: 1.2.1 + + fast-wrap-ansi@0.1.6: + dependencies: + fast-string-width: 1.1.0 + fdir@6.5.0(picomatch@4.0.4): optionalDependencies: picomatch: 4.0.4 @@ -2191,6 +2263,8 @@ snapshots: dependencies: json-buffer: 3.0.1 + kleur@4.1.5: {} + levn@0.4.1: dependencies: prelude-ls: 1.2.1 @@ -2735,6 +2809,8 @@ snapshots: once: 1.4.0 simple-concat: 1.0.1 + sisteransi@1.0.5: {} + source-map-js@1.2.1: {} stackback@0.0.2: {} diff --git a/setup/add-telegram.sh b/setup/add-telegram.sh index 262502de5..4d540af5d 100755 --- a/setup/add-telegram.sh +++ b/setup/add-telegram.sh @@ -27,7 +27,7 @@ if need_install; then # pair-telegram.ts is maintained in this branch (setup-auto), so it's NOT # in this list — do not overwrite the local version with the channels copy. - echo "[add-telegram] Copying adapter files from $CHANNELS_BRANCH…" + echo "[add-telegram] Copying adapter files from ${CHANNELS_BRANCH}…" for f in \ src/channels/telegram.ts \ src/channels/telegram-pairing.ts \ @@ -59,7 +59,7 @@ if need_install; then } ' - echo "[add-telegram] Installing $ADAPTER_VERSION…" + echo "[add-telegram] Installing ${ADAPTER_VERSION}…" pnpm install "$ADAPTER_VERSION" echo "[add-telegram] Building…" diff --git a/setup/auto.ts b/setup/auto.ts index d1358ca15..482fcea0d 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -20,67 +20,249 @@ * Run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` later * if autodetect is wrong (e.g. headless server with TZ=UTC). * - * Anthropic credential registration runs via setup/register-claude-token.sh - * (the only step that truly requires human input — browser sign-in or a - * pasted token/key). Channel auth and `/manage-channels` remain separate - * because they're platform-specific and typically handled via `/add-` - * and `/manage-channels` after this driver completes. + * UI is rendered with @clack/prompts: spinners wrap each step, child output + * is captured quietly and only dumped on failure. Interactive children + * (register-claude-token.sh, add-telegram.sh) bypass the spinner and run + * with inherited stdio — clack resumes cleanly on the next step. */ import { spawn, spawnSync } from 'child_process'; -import { createInterface } from 'readline/promises'; + +import * as p from '@clack/prompts'; +import k from 'kleur'; const CLI_AGENT_NAME = 'Terminal Agent'; const DEFAULT_AGENT_NAME = 'Nano'; -type Fields = Record; -type StepResult = { ok: boolean; fields: Fields; exitCode: number }; +/** + * Brand palette, pulled from assets/nanoclaw-logo.png: + * brand cyan ≈ #2BB7CE — the "Claw" wordmark + mascot body + * brand navy ≈ #171B3B — the dark logo background + outlines + * Gated on TTY + NO_COLOR so piped / CI output stays plain. Falls back to + * kleur's 16-color cyan when the terminal isn't truecolor. + */ +const USE_ANSI = Boolean(process.stdout.isTTY) && !process.env.NO_COLOR; +const TRUECOLOR = + USE_ANSI && + (process.env.COLORTERM === 'truecolor' || process.env.COLORTERM === '24bit'); -function parseStatus(stdout: string): Fields { - const out: Fields = {}; - let inBlock = false; - for (const line of stdout.split('\n')) { - if (line.startsWith('=== NANOCLAW SETUP:')) { - inBlock = true; - continue; +const brand = (s: string): string => { + if (!USE_ANSI) return s; + if (TRUECOLOR) return `\x1b[38;2;43;183;206m${s}\x1b[0m`; + return k.cyan(s); +}; +const brandBold = (s: string): string => { + if (!USE_ANSI) return s; + if (TRUECOLOR) return `\x1b[1;38;2;43;183;206m${s}\x1b[0m`; + return k.bold(k.cyan(s)); +}; +const brandChip = (s: string): string => { + if (!USE_ANSI) return s; + if (TRUECOLOR) { + return `\x1b[48;2;43;183;206m\x1b[38;2;23;27;59m\x1b[1m${s}\x1b[0m`; + } + return k.bgCyan(k.black(k.bold(s))); +}; + +type Fields = Record; +type Block = { type: string; fields: Fields }; +type StepResult = { + ok: boolean; + exitCode: number; + blocks: Block[]; + transcript: string; + /** The last block matching `stepName.toUpperCase()` if any. */ + terminal: Block | null; +}; + +/** + * Streaming parser for `=== NANOCLAW SETUP: TYPE ===` blocks. Emits each + * block as it closes so the UI can react mid-stream (e.g. render a pairing + * code card as soon as pair-telegram emits it, rather than after the step + * has finished). + */ +class StatusStream { + private lineBuf = ''; + private current: Block | null = null; + readonly blocks: Block[] = []; + transcript = ''; + + constructor(private readonly onBlock: (block: Block) => void) {} + + write(chunk: string): void { + this.transcript += chunk; + this.lineBuf += chunk; + let idx: number; + while ((idx = this.lineBuf.indexOf('\n')) !== -1) { + const line = this.lineBuf.slice(0, idx); + this.lineBuf = this.lineBuf.slice(idx + 1); + this.processLine(line); + } + } + + private processLine(line: string): void { + const start = line.match(/^=== NANOCLAW SETUP: (\S+) ===/); + if (start) { + this.current = { type: start[1], fields: {} }; + return; } if (line.startsWith('=== END ===')) { - inBlock = false; - continue; + if (this.current) { + this.blocks.push(this.current); + this.onBlock(this.current); + this.current = null; + } + return; } - if (!inBlock) continue; - const idx = line.indexOf(':'); - if (idx === -1) continue; - const key = line.slice(0, idx).trim(); - const value = line.slice(idx + 1).trim(); - if (key) out[key] = value; + if (!this.current) return; + const colon = line.indexOf(':'); + if (colon === -1) return; + const key = line.slice(0, colon).trim(); + const value = line.slice(colon + 1).trim(); + if (key) this.current.fields[key] = value; } - return out; } -function runStep(name: string, extra: string[] = []): Promise { +/** + * Spawn a setup step as a child process, swallowing stdout/stderr into a + * buffer. The provided onBlock callback fires per status block as they + * parse. Returns when the child exits. + */ +function spawnStep( + stepName: string, + extra: string[], + onBlock: (block: Block) => void, +): Promise { return new Promise((resolve) => { - console.log(`\n── ${name} ────────────────────────────────────`); - const args = ['exec', 'tsx', 'setup/index.ts', '--step', name]; + const args = ['exec', 'tsx', 'setup/index.ts', '--step', stepName]; if (extra.length > 0) args.push('--', ...extra); - const child = spawn('pnpm', args, { stdio: ['inherit', 'pipe', 'inherit'] }); - let buf = ''; - child.stdout.on('data', (chunk: Buffer) => { - const s = chunk.toString('utf-8'); - buf += s; - process.stdout.write(s); + const child = spawn('pnpm', args, { stdio: ['ignore', 'pipe', 'pipe'] }); + const stream = new StatusStream(onBlock); + + child.stdout.on('data', (chunk: Buffer) => stream.write(chunk.toString('utf-8'))); + child.stderr.on('data', (chunk: Buffer) => { + stream.transcript += chunk.toString('utf-8'); }); + child.on('close', (code) => { - const fields = parseStatus(buf); + // Step block types don't always mirror step names (e.g. `mounts` emits + // CONFIGURE_MOUNTS, `container` emits SETUP_CONTAINER). Any block with + // a STATUS field is a terminal block; the last one wins. + const terminal = + [...stream.blocks].reverse().find((b) => b.fields.STATUS) ?? null; + const status = terminal?.fields.STATUS; + const ok = code === 0 && (status === 'success' || status === 'skipped'); resolve({ - ok: code === 0 && fields.STATUS === 'success', - fields, + ok, exitCode: code ?? 1, + blocks: stream.blocks, + transcript: stream.transcript, + terminal, }); }); }); } +type SpinnerLabels = { + running: string; + done: string; + skipped?: string; + failed?: string; +}; + +/** Run a step under a clack spinner. Child output is captured; shown only on failure. */ +async function runQuietStep( + stepName: string, + labels: SpinnerLabels, + extra: string[] = [], +): Promise { + return runUnderSpinner(labels, () => spawnStep(stepName, extra, () => {})); +} + +/** Run an arbitrary child under a spinner, capturing its stdout/stderr. */ +async function runQuietChild( + cmd: string, + args: string[], + labels: SpinnerLabels, +): Promise<{ ok: boolean; exitCode: number; transcript: string }> { + return runUnderSpinner(labels, () => spawnQuiet(cmd, args)); +} + +async function runUnderSpinner< + T extends { ok: boolean; transcript: string; terminal?: Block | null }, +>( + labels: SpinnerLabels, + work: () => Promise, +): Promise { + const s = p.spinner(); + const start = Date.now(); + s.start(labels.running); + const tick = setInterval(() => { + const elapsed = Math.round((Date.now() - start) / 1000); + s.message(`${labels.running} ${k.dim(`(${elapsed}s)`)}`); + }, 1000); + + const result = await work(); + + clearInterval(tick); + const elapsed = Math.round((Date.now() - start) / 1000); + if (result.ok) { + const isSkipped = result.terminal?.fields.STATUS === 'skipped'; + const msg = isSkipped && labels.skipped ? labels.skipped : labels.done; + s.stop(`${msg} ${k.dim(`(${elapsed}s)`)}`); + } else { + const failMsg = labels.failed ?? labels.running.replace(/…$/, ' failed'); + s.stop(`${failMsg} ${k.dim(`(${elapsed}s)`)}`, 1); + dumpTranscriptOnFailure(result.transcript); + } + return result; +} + +function spawnQuiet( + cmd: string, + args: string[], +): Promise<{ ok: boolean; exitCode: number; transcript: string }> { + return new Promise((resolve) => { + const child = spawn(cmd, args, { stdio: ['ignore', 'pipe', 'pipe'] }); + let transcript = ''; + child.stdout.on('data', (c: Buffer) => { transcript += c.toString('utf-8'); }); + child.stderr.on('data', (c: Buffer) => { transcript += c.toString('utf-8'); }); + child.on('close', (code) => { + resolve({ ok: code === 0, exitCode: code ?? 1, transcript }); + }); + }); +} + +function dumpTranscriptOnFailure(transcript: string): void { + const lines = transcript.split('\n').filter((l) => { + if (l.startsWith('=== NANOCLAW SETUP:')) return false; + if (l.startsWith('=== END ===')) return false; + return true; + }); + const tail = lines.slice(-40).join('\n').trimEnd(); + if (tail) { + console.log(); + console.log(k.dim(tail)); + console.log(); + } +} + +function fail(msg: string, hint?: string): never { + p.log.error(msg); + if (hint) p.log.message(k.dim(hint)); + p.log.message(k.dim('Logs: logs/setup.log')); + p.cancel('Setup aborted.'); + process.exit(1); +} + +function ensureAnswer(value: T | symbol): T { + if (p.isCancel(value)) { + p.cancel('Setup cancelled.'); + process.exit(0); + } + return value as T; +} + /** * After installing Docker, this process's supplementary groups are still * frozen from login — subsequent steps that talk to /var/run/docker.sock @@ -89,7 +271,7 @@ function runStep(name: string, extra: string[] = []): Promise { * so the rest of the run inherits the docker group without a re-login. */ function maybeReexecUnderSg(): void { - if (process.env.NANOCLAW_REEXEC_SG === '1') return; // already re-exec'd + if (process.env.NANOCLAW_REEXEC_SG === '1') return; if (process.platform !== 'linux') return; const info = spawnSync('docker', ['info'], { encoding: 'utf-8' }); if (info.status === 0) return; @@ -97,10 +279,7 @@ function maybeReexecUnderSg(): void { if (!/permission denied/i.test(err)) return; if (spawnSync('which', ['sg'], { stdio: 'ignore' }).status !== 0) return; - console.log( - '\n[setup:auto] Docker socket not accessible in current group — ' + - 're-executing under `sg docker` to pick up new group membership.', - ); + p.log.warn('Docker socket not accessible in current group — re-executing under `sg docker`.'); const res = spawnSync('sg', ['docker', '-c', 'pnpm run setup:auto'], { stdio: 'inherit', env: { ...process.env, NANOCLAW_REEXEC_SG: '1' }, @@ -121,67 +300,121 @@ function anthropicSecretExists(): boolean { } } -async function askDisplayName(fallback: string): Promise { - const rl = createInterface({ input: process.stdin, output: process.stdout }); - try { - const answer = await rl.question( - `\nWhat should your agents call you? [${fallback}]: `, - ); - return answer.trim() || fallback; - } finally { - rl.close(); +function runInheritScript(cmd: string, args: string[]): Promise { + return new Promise((resolve) => { + const child = spawn(cmd, args, { stdio: 'inherit' }); + child.on('close', (code) => resolve(code ?? 1)); + }); +} + +function formatCodeCard(code: string): string { + const spaced = code.split('').join(' '); + return [ + '', + ` ${brandBold(spaced)}`, + '', + k.dim(' Send these digits from Telegram to your bot.'), + ].join('\n'); +} + +async function runPairTelegram(): Promise { + const s = p.spinner(); + s.start('Creating pairing code…'); + let spinnerActive = true; + + const stopSpinner = (msg: string, code?: number) => { + if (spinnerActive) { + s.stop(msg, code); + spinnerActive = false; + } + }; + + const result = await spawnStep('pair-telegram', ['--intent', 'main'], (block) => { + if (block.type === 'PAIR_TELEGRAM_CODE') { + const reason = block.fields.REASON ?? 'initial'; + if (reason === 'initial') { + stopSpinner('Pairing code ready.'); + } else { + stopSpinner('Previous code invalidated. New code below.'); + } + p.note(formatCodeCard(block.fields.CODE ?? '????'), 'Pairing code'); + s.start('Waiting for the code from Telegram…'); + spinnerActive = true; + } else if (block.type === 'PAIR_TELEGRAM_ATTEMPT') { + stopSpinner(`Received "${block.fields.CANDIDATE ?? '?'}" — doesn't match.`); + s.start('Waiting for the correct code…'); + spinnerActive = true; + } else if (block.type === 'PAIR_TELEGRAM') { + if (block.fields.STATUS === 'success') { + stopSpinner('Telegram paired.'); + } else { + stopSpinner(`Pairing failed: ${block.fields.ERROR ?? 'unknown'}`, 1); + } + } + }); + + // Safety net: if the child died without emitting a terminal block, make + // sure we don't leave the spinner running. + if (spinnerActive) { + stopSpinner(result.ok ? 'Done.' : 'Pairing exited unexpectedly.', result.ok ? 0 : 1); + if (!result.ok) dumpTranscriptOnFailure(result.transcript); } + return result; +} + +async function askDisplayName(fallback: string): Promise { + const answer = ensureAnswer( + await p.text({ + message: 'What should your agents call you?', + placeholder: fallback, + defaultValue: fallback, + }), + ); + return (answer as string).trim() || fallback; } async function askAgentName(fallback: string): Promise { - const rl = createInterface({ input: process.stdin, output: process.stdout }); - try { - const answer = await rl.question( - `\nWhat should your agent be called? [${fallback}]: `, - ); - return answer.trim() || fallback; - } finally { - rl.close(); - } + const answer = ensureAnswer( + await p.text({ + message: 'What should your messaging agent be called?', + placeholder: fallback, + defaultValue: fallback, + }), + ); + return (answer as string).trim() || fallback; } async function askChannelChoice(): Promise<'telegram' | 'skip'> { - const rl = createInterface({ input: process.stdin, output: process.stdout }); - try { - console.log('\nConnect a messaging app so you can chat from your phone?'); - console.log(' 1) Telegram'); - console.log(' 2) Skip — just use the CLI for now'); - const answer = (await rl.question('Choose [1/2]: ')).trim(); - return answer === '1' ? 'telegram' : 'skip'; - } finally { - rl.close(); + const choice = ensureAnswer( + await p.select({ + message: 'Connect a messaging app so you can chat from your phone?', + options: [ + { value: 'telegram', label: 'Telegram', hint: 'recommended' }, + { value: 'skip', label: 'Skip — use the CLI only' }, + ], + }), + ); + return choice as 'telegram' | 'skip'; +} + +function printIntro(): void { + const isReexec = process.env.NANOCLAW_REEXEC_SG === '1'; + const wordmark = `${k.bold('Nano')}${brandBold('Claw')}`; + + if (isReexec) { + p.intro(`${brandChip(' setup:auto ')} ${wordmark} ${k.dim('· resuming under docker group')}`); + return; } -} -function runBashScript(relPath: string): Promise { - return new Promise((resolve) => { - const child = spawn('bash', [relPath], { stdio: 'inherit' }); - child.on('close', (code) => resolve(code ?? 1)); - }); -} - -function runTsxScript(relPath: string, args: string[] = []): Promise { - return new Promise((resolve) => { - const child = spawn('pnpm', ['exec', 'tsx', relPath, ...args], { - stdio: 'inherit', - }); - child.on('close', (code) => resolve(code ?? 1)); - }); -} - -function fail(msg: string, hint?: string): never { - console.error(`\n[setup:auto] ${msg}`); - if (hint) console.error(` ${hint}`); - console.error(' Logs: logs/setup.log'); - process.exit(1); + console.log(); + console.log(` ${wordmark}`); + console.log(` ${k.dim('end-to-end scripted setup of your personal assistant')}`); + p.intro(`${brandChip(' setup:auto ')}`); } async function main(): Promise { + printIntro(); + const skip = new Set( (process.env.NANOCLAW_SKIP ?? '') .split(',') @@ -190,92 +423,113 @@ async function main(): Promise { ); if (!skip.has('environment')) { - const env = await runStep('environment'); - if (!env.ok) fail('environment check failed'); + const res = await runQuietStep( + 'environment', + { running: 'Checking environment…', done: 'Environment OK.' }, + ); + if (!res.ok) fail('Environment check failed.'); } if (!skip.has('container')) { - const res = await runStep('container'); + const res = await runQuietStep('container', { + running: 'Building the agent container image…', + done: 'Container image ready.', + failed: 'Container build failed.', + }); if (!res.ok) { - if (res.fields.ERROR === 'runtime_not_available') { + const err = res.terminal?.fields.ERROR; + if (err === 'runtime_not_available') { fail( 'Docker is not available and could not be started automatically.', 'Install Docker Desktop or start it manually, then retry.', ); } - if (res.fields.ERROR === 'docker_group_not_active') { + if (err === 'docker_group_not_active') { fail( 'Docker was just installed but your shell is not yet in the `docker` group.', - 'Log out and back in (or run `newgrp docker` in a new shell), then retry `pnpm run setup:auto`.', + 'Log out and back in (or run `newgrp docker` in a new shell), then retry.', ); } fail( - 'container build/test failed', - 'For stale build cache: `docker builder prune -f`, then retry `pnpm run setup:auto`.', + 'Container build/test failed.', + 'For stale cache: `docker builder prune -f`, then retry `pnpm run setup:auto`.', ); } maybeReexecUnderSg(); } if (!skip.has('onecli')) { - const res = await runStep('onecli'); + const res = await runQuietStep('onecli', { + running: 'Installing OneCLI credential vault…', + done: 'OneCLI installed.', + }); if (!res.ok) { - if (res.fields.ERROR === 'onecli_not_on_path_after_install') { + const err = res.terminal?.fields.ERROR; + if (err === 'onecli_not_on_path_after_install') { fail( 'OneCLI installed but not on PATH.', 'Open a new shell or run `export PATH="$HOME/.local/bin:$PATH"`, then retry.', ); } fail( - `OneCLI install failed (${res.fields.ERROR ?? 'unknown'})`, - 'Check that curl + a writable ~/.local/bin are available; re-run `pnpm run setup:auto`.', + `OneCLI install failed (${err ?? 'unknown'}).`, + 'Check that curl + a writable ~/.local/bin are available, then retry.', ); } } if (!skip.has('auth')) { if (anthropicSecretExists()) { - console.log( - '\n── auth ────────────────────────────────────\n' + - '[setup:auto] OneCLI already has an Anthropic secret — skipping.', - ); + p.log.success('OneCLI already has an Anthropic secret — skipping.'); } else { - console.log('\n── auth ────────────────────────────────────'); - const code = await runBashScript('setup/register-claude-token.sh'); + p.log.step('Registering your Anthropic credential…'); + console.log( + k.dim(' (browser sign-in or paste a token/key — this part is interactive)'), + ); + console.log(); + const code = await runInheritScript('bash', ['setup/register-claude-token.sh']); + console.log(); if (code !== 0) { fail( 'Anthropic credential registration failed or was aborted.', 'Re-run `bash setup/register-claude-token.sh` or handle via `/setup` §4.', ); } + p.log.success('Anthropic credential registered with OneCLI.'); } } if (!skip.has('mounts')) { - const res = await runStep('mounts', ['--empty']); - if (!res.ok && res.fields.STATUS !== 'skipped') { - fail('mount allowlist step failed'); - } + const res = await runQuietStep('mounts', { + running: 'Writing mount allowlist…', + done: 'Mount allowlist in place.', + skipped: 'Mount allowlist already configured.', + }, ['--empty']); + if (!res.ok) fail('Mount allowlist step failed.'); } if (!skip.has('service')) { - const res = await runStep('service'); + const res = await runQuietStep('service', { + running: 'Installing the background service…', + done: 'Service installed and running.', + }); if (!res.ok) { fail( - 'service install failed', + 'Service install failed.', 'Check logs/nanoclaw.error.log, or run `/setup` to iterate interactively.', ); } - if (res.fields.DOCKER_GROUP_STALE === 'true') { - console.warn( - '\n[setup:auto] Docker group stale in systemd session. Run:\n' + - ' sudo setfacl -m u:$(whoami):rw /var/run/docker.sock\n' + - ' systemctl --user restart nanoclaw', + if (res.terminal?.fields.DOCKER_GROUP_STALE === 'true') { + p.log.warn('Docker group stale in systemd session.'); + p.log.message( + k.dim( + ' sudo setfacl -m u:$(whoami):rw /var/run/docker.sock\n' + + ' systemctl --user restart nanoclaw', + ), ); } } - // Resolved once, reused by cli-agent + channel wiring. let displayName: string | undefined; const needsDisplayName = !skip.has('cli-agent') || !skip.has('channel'); if (needsDisplayName) { @@ -285,15 +539,17 @@ async function main(): Promise { } if (!skip.has('cli-agent')) { - const res = await runStep('cli-agent', [ - '--display-name', - displayName!, - '--agent-name', - CLI_AGENT_NAME, - ]); + const res = await runQuietStep( + 'cli-agent', + { + running: 'Wiring the terminal agent…', + done: 'Terminal agent wired (try `pnpm run chat hi`).', + }, + ['--display-name', displayName!, '--agent-name', CLI_AGENT_NAME], + ); if (!res.ok) { fail( - 'CLI agent wiring failed', + 'CLI agent wiring failed.', `Re-run \`pnpm exec tsx scripts/init-cli-agent.ts --display-name "${displayName!}" --agent-name "${CLI_AGENT_NAME}"\` to fix.`, ); } @@ -302,15 +558,19 @@ async function main(): Promise { if (!skip.has('channel')) { const choice = await askChannelChoice(); if (choice === 'telegram') { - const installCode = await runBashScript('setup/add-telegram.sh'); + p.log.step('Installing the Telegram adapter and collecting your bot token…'); + console.log(); + const installCode = await runInheritScript('bash', ['setup/add-telegram.sh']); + console.log(); if (installCode !== 0) { fail( 'Telegram install failed.', - 'Re-run `bash setup/add-telegram.sh`, then `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main`.', + 'Re-run `bash setup/add-telegram.sh`, then retry `pnpm run setup:auto`.', ); } + p.log.success('Telegram adapter installed.'); - const pair = await runStep('pair-telegram', ['--intent', 'main']); + const pair = await runPairTelegram(); if (!pair.ok) { fail( 'Telegram pairing failed.', @@ -318,8 +578,8 @@ async function main(): Promise { ); } - const platformId = pair.fields.PLATFORM_ID; - const pairedUserId = pair.fields.PAIRED_USER_ID; + const platformId = pair.terminal?.fields.PLATFORM_ID; + const pairedUserId = pair.terminal?.fields.PAIRED_USER_ID; if (!platformId || !pairedUserId) { fail( 'pair-telegram succeeded but did not return PLATFORM_ID and PAIRED_USER_ID.', @@ -331,54 +591,72 @@ async function main(): Promise { process.env.NANOCLAW_AGENT_NAME?.trim() || (await askAgentName(DEFAULT_AGENT_NAME)); - console.log('\n── wiring first agent ──────────────────────────'); - const initCode = await runTsxScript('scripts/init-first-agent.ts', [ - '--channel', 'telegram', - '--user-id', pairedUserId, - '--platform-id', platformId, - '--display-name', displayName!, - '--agent-name', agentName, - ]); - if (initCode !== 0) { + const init = await runQuietChild( + 'pnpm', + [ + 'exec', 'tsx', 'scripts/init-first-agent.ts', + '--channel', 'telegram', + '--user-id', pairedUserId, + '--platform-id', platformId, + '--display-name', displayName!, + '--agent-name', agentName, + ], + { + running: `Wiring ${agentName} to your Telegram chat…`, + done: `${agentName} is wired — welcome DM incoming.`, + }, + ); + if (!init.ok) { fail( 'Wiring the Telegram agent failed.', `Re-run \`pnpm exec tsx scripts/init-first-agent.ts --channel telegram --user-id "${pairedUserId}" --platform-id "${platformId}" --display-name "${displayName!}" --agent-name "${agentName}"\`.`, ); } - - console.log( - `\n[setup:auto] Telegram is wired. ${agentName} will DM you a welcome shortly.`, - ); + } else { + p.log.info('No messaging channel wired — you can add one later with `/add-`.'); } } if (!skip.has('verify')) { - const res = await runStep('verify'); + const res = await runQuietStep('verify', { + running: 'Verifying the install…', + done: 'Install verified.', + failed: 'Verification found issues.', + }); if (!res.ok) { - console.log('\n[setup:auto] Scripted steps done. Remaining (interactive):'); - if (res.fields.CREDENTIALS !== 'configured') { - console.log(' • Anthropic secret not detected — re-run `bash setup/register-claude-token.sh`'); + const notes: string[] = []; + if (res.terminal?.fields.CREDENTIALS !== 'configured') { + notes.push('• Anthropic secret not detected — re-run `bash setup/register-claude-token.sh`.'); } - if (res.fields.AGENT_PING && res.fields.AGENT_PING !== 'ok' && res.fields.AGENT_PING !== 'skipped') { - console.log( - ` • CLI agent did not reply (status: ${res.fields.AGENT_PING}). ` + + const agentPing = res.terminal?.fields.AGENT_PING; + if (agentPing && agentPing !== 'ok' && agentPing !== 'skipped') { + notes.push( + `• CLI agent did not reply (status: ${agentPing}). ` + 'Check `logs/nanoclaw.log` and `groups/*/logs/container-*.log`, then try `pnpm run chat hi`.', ); } - if (!res.fields.CONFIGURED_CHANNELS) { - console.log( - ' • Optional: add a messaging channel — `/add-discord`, `/add-slack`, `/add-telegram`, …', - ); - console.log(' (CLI channel is already wired: `pnpm run chat hi`)'); + if (!res.terminal?.fields.CONFIGURED_CHANNELS) { + notes.push('• Optional: add a messaging channel — `/add-discord`, `/add-slack`, `/add-telegram`, …'); } + if (notes.length > 0) { + p.note(notes.join('\n'), 'What’s left'); + } + p.outro(k.yellow('Scripted steps done — some pieces still need you.')); return; } } - console.log('\n[setup:auto] Complete.'); + const nextSteps = [ + `${k.cyan('Chat from the CLI:')} pnpm run chat hi`, + `${k.cyan('Tail host logs:')} tail -f logs/nanoclaw.log`, + `${k.cyan('Open Claude Code:')} claude`, + ].join('\n'); + p.note(nextSteps, 'Next steps'); + p.outro(k.green('Setup complete.')); } main().catch((err) => { - console.error(err); + p.log.error(err instanceof Error ? err.message : String(err)); + p.cancel('Setup aborted.'); process.exit(1); }); diff --git a/setup/pair-telegram.ts b/setup/pair-telegram.ts index cf7259bca..f3f9bf8cf 100644 --- a/setup/pair-telegram.ts +++ b/setup/pair-telegram.ts @@ -2,11 +2,16 @@ * Step: pair-telegram — issue a one-time pairing code and wait for the * operator to send the code from the chat they want to register. * - * Used exclusively by `setup:auto` / `bash nanoclaw.sh` on this branch. Human- - * facing output is a focused banner for the code (no parseable block), plus a - * short line for wrong attempts / regenerations. A single machine-readable - * PAIR_TELEGRAM status block is still emitted at the end so the parent driver - * can pick up PLATFORM_ID / PAIRED_USER_ID / IS_GROUP. + * Emits machine-readable status blocks only. The parent driver + * (`setup:auto`) renders the code / attempt / success UI with clack. Running + * this step directly will look sparse — that's intentional. + * + * Blocks emitted: + * PAIR_TELEGRAM_CODE { CODE, REASON=initial|regenerated } + * PAIR_TELEGRAM_ATTEMPT { CANDIDATE } + * PAIR_TELEGRAM (final) { STATUS=success, CODE, INTENT, PLATFORM_ID, + * IS_GROUP, PAIRED_USER_ID } + * or { STATUS=failed, CODE, ERROR } * * Depends on src/channels/telegram-pairing.js, which setup/add-telegram.sh * copies in from the `channels` branch before this step runs. setup/ is @@ -50,22 +55,6 @@ function intentToString(intent: PairingIntent): string { return `${intent.kind}:${intent.folder}`; } -function printCodeBanner(code: string): void { - const digits = code.split('').join(' '); - const content = [ - '', - ` PAIRING CODE: ${digits}`, - '', - ' Send these digits from Telegram to your bot.', - '', - ]; - const width = Math.max(...content.map((l) => l.length)); - const top = ' ╔' + '═'.repeat(width + 2) + '╗'; - const bot = ' ╚' + '═'.repeat(width + 2) + '╝'; - const mid = content.map((l) => ' ║ ' + l.padEnd(width) + ' ║'); - console.log(['', top, ...mid, bot, ''].join('\n')); -} - export async function run(args: string[]): Promise { const intent = parseArgs(args); @@ -78,19 +67,21 @@ export async function run(args: string[]): Promise { const MAX_REGENERATIONS = 5; let record = await createPairing(intent); - printCodeBanner(record.code); + emitStatus('PAIR_TELEGRAM_CODE', { + CODE: record.code, + REASON: 'initial', + }); for (let regen = 0; regen <= MAX_REGENERATIONS; regen++) { try { const consumed = await waitForPairing(record.code, { onAttempt: (a) => { - console.log( - ` Got "${a.candidate}" — doesn't match. A new code is on its way.`, - ); + emitStatus('PAIR_TELEGRAM_ATTEMPT', { + CANDIDATE: a.candidate, + }); }, }); - console.log('\n ✓ Telegram paired.\n'); emitStatus('PAIR_TELEGRAM', { STATUS: 'success', CODE: record.code, @@ -107,12 +98,13 @@ export async function run(args: string[]): Promise { const invalidated = /invalidated by wrong code/.test(message); if (invalidated && regen < MAX_REGENERATIONS) { record = await createPairing(intent); - console.log('\n Previous code invalidated. New code:'); - printCodeBanner(record.code); + emitStatus('PAIR_TELEGRAM_CODE', { + CODE: record.code, + REASON: 'regenerated', + }); continue; } const reason = invalidated ? 'max-regenerations-exceeded' : message; - console.error(`\n ✗ Pairing failed: ${reason}`); emitStatus('PAIR_TELEGRAM', { STATUS: 'failed', CODE: record.code, diff --git a/setup/register-claude-token.sh b/setup/register-claude-token.sh index 9c042d9bc..8bcab734a 100755 --- a/setup/register-claude-token.sh +++ b/setup/register-claude-token.sh @@ -117,7 +117,7 @@ esac echo echo "Got token: ${TOKEN:0:16}…${TOKEN: -4}" -echo "Registering with OneCLI as '$SECRET_NAME' (host pattern: $HOST_PATTERN)…" +echo "Registering with OneCLI as '${SECRET_NAME}' (host pattern: ${HOST_PATTERN})…" onecli secrets create \ --name "$SECRET_NAME" \ From 5269edada4ddcb23c27ac201c7b5eb2c8a60fdc5 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 02:02:13 +0300 Subject: [PATCH 89/95] feat(setup): three-level output (clack UI / progression log / raw per-step) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Documents and implements the output contract from docs/setup-flow.md: Level 1: clack UI — branded, concise, product content Level 2: logs/setup.log — append-only, linear, structured entries for humans + AI agents reviewing a run Level 3: logs/setup-steps/NN-name.log — full raw stdout+stderr per step Every scripted sub-step, including bootstrap, emits at all three levels. Bootstrap now runs under a bash-side clack-alike spinner with live elapsed time; its apt/pnpm output is captured to 01-bootstrap.log and summarised as a progression entry. setup.sh's legacy log() routes to the raw log instead of contaminating the progression log. Telegram install becomes fully branded: setup/auto.ts owns the BotFather instructions (clack note), token paste (clack password with format validation), and getMe check (clack spinner). add-telegram.sh drops to a non-interactive installer that reads TELEGRAM_BOT_TOKEN from env, logs to stderr, and emits a single ADD_TELEGRAM status block on stdout. The Anthropic credential flow is the one intentional break — register- claude-token.sh still inherits the TTY for claude setup-token's browser dance; it logs as an 'interactive' progression entry with the method. setup/logs.ts centralises the level 2/3 formatting: reset, header, step, userInput, complete, abort, stepRawLog. User answers (display name, agent name, channel choice, telegram_token preview) log as their own entries so the setup path is reconstructable from the progression log alone. Co-Authored-By: Claude Opus 4.7 (1M context) --- docs/setup-flow.md | 226 ++++++++++++++++++++++++++ nanoclaw.sh | 162 +++++++++++++++++-- setup.sh | 12 +- setup/add-telegram.sh | 171 ++++++++++---------- setup/auto.ts | 359 ++++++++++++++++++++++++++++++++++++------ setup/logs.ts | 130 +++++++++++++++ 6 files changed, 909 insertions(+), 151 deletions(-) create mode 100644 docs/setup-flow.md create mode 100644 setup/logs.ts diff --git a/docs/setup-flow.md b/docs/setup-flow.md new file mode 100644 index 000000000..800411cf3 --- /dev/null +++ b/docs/setup-flow.md @@ -0,0 +1,226 @@ +# Setup flow + +This document is the contract for NanoClaw's end-to-end scripted setup +(`bash nanoclaw.sh` → `pnpm run setup:auto`). Read it before adding a new +step, fixing a regression, or changing how output is rendered. + +## The three output levels + +Every setup step produces output at **three distinct levels**. They have +different audiences, go to different places, and are formatted differently. +Don't conflate them. + +| Level | Audience | Destination | Format | +|---|---|---|---| +| 1. User-facing | The operator running setup | Terminal (via clack) | Branded, concise, informational — "product content" | +| 2. Progression | Future debuggers, AI agents reviewing a failed run, release support | `logs/setup.log` (one file, append-only) | Structured per-step blocks, linear chronology, human + machine readable | +| 3. Raw | Whoever is deep-debugging a specific step | `logs/setup-steps/NN-step-name.log` (one file per step) | Full raw child stdout + stderr, verbatim | + +Think of it as: the user sees a **summary**, the progression log is an +**index with key facts**, the raw logs are the **evidence**. + +### Level 1: user-facing (clack) + +Rendered by `setup/auto.ts` via `@clack/prompts`. This is our *product +surface* for setup — every line should read as if we designed it for a +stranger on day one. + +- Clack spinners for in-progress work. Show elapsed time. +- `p.log.success` / `p.log.step` / `p.log.warn` for permanent status + markers. +- `p.note` for multi-line information (pairing code, next steps). +- `p.text` / `p.select` / `p.password` for prompts. +- Brand palette: `brand()` / `brandBold()` / `brandChip()` helpers in + `setup/auto.ts`. Truecolor when the terminal supports it, 16-color + cyan fallback otherwise, plain text when piped / `NO_COLOR`. + +Rules: +- **No discontinuity.** Every sub-step belongs to the same visual flow. + The only exception is Anthropic credential registration (see below). +- **No raw child output.** Never `stdio: 'inherit'` a child whose output + wasn't written by us. Capture it and show it on failure only. +- **No debug-style prefixes** (`[add-telegram] …`, `INFO …`, timestamps). + Those belong in levels 2 and 3. +- **No emoji** unless the clack glyph requires it. + +### Level 2: progression log + +`logs/setup.log` — one file per setup run, append-only, cumulative across +a multi-run install (if a run fails midway and is re-attempted, the new +entries append). It's the thing you'd ask an operator to paste when they +report a setup bug, and the thing an AI agent would read to understand +what happened. + +Entry format: + +``` +=== [2026-04-22T22:14:12Z] bootstrap [45.1s] → success === + platform: linux + is_wsl: false + node_version: 22.22.2 + deps_ok: true + native_ok: true + raw: logs/setup-steps/01-bootstrap.log + +=== [2026-04-22T22:14:57Z] environment [2.3s] → success === + docker: running + apple_container: not_found + raw: logs/setup-steps/02-environment.log + +=== [2026-04-22T22:15:00Z] container [92.4s] → success === + runtime: docker + image: nanoclaw-agent:latest + build_ok: true + raw: logs/setup-steps/03-container.log +``` + +Design constraints: +- Start-time timestamp (UTC, ISO-8601) on the opening line so a `grep` + gives you the sequence. +- Duration in seconds with one decimal — fast steps read as "0.5s", not + "0ms". +- Status is one of: `success`, `skipped`, `failed`, `aborted`. +- Fields are step-specific but **must** be short scalar values. No JSON, + no multi-line. If a value is long, put it in the raw log and reference + it. +- Always emit a `raw:` pointer, even on success — makes debugging the + second failure easier. +- **User choices** are their own entries, not nested inside a step: + + ``` + === [2026-04-22T22:17:44Z] user-input → display_name === + value: gav + + === [2026-04-22T22:17:51Z] user-input → channel_choice === + value: telegram + ``` + + These matter because the path through the setup flow depends on them. + +The log opens with a header block identifying the run, and closes with +a completion block: + +``` +## 2026-04-22T22:14:12Z · setup:auto started + user: exedev + cwd: /home/exedev/nanoclaw + branch: branded-setup + commit: 6e0d742 + +… (step entries) … + +## 2026-04-22T22:18:54Z · completed (total 4m42s) +``` + +On failure the completion block names the failing step and its error: + +``` +## 2026-04-22T22:16:40Z · aborted at container (err=cache_miss) +``` + +### Level 3: raw per-step logs + +`logs/setup-steps/NN-step-name.log` — one file per step, numbered in +execution order (zero-padded 2-digit prefix for natural sorting). Full +verbatim stdout + stderr from the child process. Truncated and rewritten +on each run (not appended). + +Contents are whatever the step emits: apt output, docker build layers, +pnpm install spam, `curl` bodies, etc. This is the evidence plane — +"what did the shell actually see?" Nothing is filtered. + +## Contract for a new step + +When you add a step (either a TS step in `setup/.ts` or a bash +installer invoked from `auto.ts`), it must: + +1. **Receive a raw-log path** from the caller. Write all stdout + stderr + there. Don't write to the terminal directly. +2. **Emit a single terminal status block** at the end, containing + `STATUS: success|skipped|failed` and any step-specific fields: + + ``` + === NANOCLAW SETUP: STEP_NAME === + STATUS: success + KEY: value + KEY: value + === END === + ``` + + Field names are `UPPER_SNAKE_CASE`. Values are short scalars. + +3. If it's a long-running step, optionally emit **sub-status blocks** + mid-stream. `auto.ts` parses them live and can render intermediate + UI (as `pair-telegram` does with `PAIR_TELEGRAM_CODE` / + `PAIR_TELEGRAM_ATTEMPT`). + +4. **Exit non-zero** on hard failure so `auto.ts` can distinguish + "step ran to completion and reported failed" from "step crashed". + +The driver handles the rest: spinner in level 1, structured append to +level 2, raw capture to level 3. + +## The Anthropic exception + +Anthropic credential registration (`setup/register-claude-token.sh`) is +the **one** permitted break in the visual flow. Why: + +- `claude setup-token` opens a browser, runs its own OAuth prompt, and + prints the token. It owns the TTY via `script(1)`. +- We don't want to re-implement the OAuth device flow ourselves. +- We don't want to intercept / mirror the token (it appears in the + user's terminal already — mirroring it adds attack surface). + +So during this step: +- The clack flow explicitly pauses (a `p.log.step` marker says "this + part is interactive, you're handing off to Anthropic"). +- The child inherits stdio fully. +- When control returns, clack resumes on the next line with a success + marker. + +The level-2 log still gets an entry (`auth [interactive] → success` +with the method — subscription / oauth-token / api-key). Level-3 captures +are optional here; mirroring `script -q` output is tricky and the risk of +leaking the token to disk outweighs the debugging value. + +## File reference + +| File | Role | +|---|---| +| `nanoclaw.sh` | Top-level wrapper. Phase 1 (bootstrap) and phase 2 (setup:auto) orchestration. Writes bootstrap's raw log + progression entry. | +| `setup.sh` | Phase 1 bootstrap: Node, pnpm, native-module verify. Emits its own `BOOTSTRAP` status block (historically printed to stdout; now goes to the bootstrap raw log). | +| `setup/auto.ts` | Phase 2 driver. Orchestrates the clack UI, step execution, user prompts, and writes to all three log levels for every step it spawns. | +| `setup/logs.ts` | The logging primitives (`logStep`, `logUserInput`, `logComplete`, `stepRawLog`, `initSetupLog`). Single source of truth for level 2/3 formatting and file paths. | +| `setup/.ts` | Individual step implementations. Must emit one terminal status block; must not write directly to the terminal. | +| `setup/register-claude-token.sh` | The Anthropic exception. Inherits stdio, prints its own UI, returns a status to the driver. | +| `setup/add-telegram.sh` | Non-interactive adapter installer. Reads `TELEGRAM_BOT_TOKEN` from env; never prompts. User-facing bits live in `auto.ts`. | +| `setup/pair-telegram.ts` | Emits `PAIR_TELEGRAM_CODE` / `PAIR_TELEGRAM_ATTEMPT` / `PAIR_TELEGRAM` status blocks. Never prints UI. The driver renders it via clack notes. | + +## Common pitfalls + +- **Printing debug output from inside a step.** Tempting during + development; forbidden in checked-in code. All runtime messaging goes + through status blocks (level 2) or raw log writes (level 3). +- **Adding a `console.log` that "just this once" goes to the terminal.** + It breaks the clack flow — the spinner line gets torn. Use + `log.info` / `log.error` from `src/log.ts` (writes to the raw log) + instead. +- **`stdio: 'inherit'` for a non-exception child.** See Anthropic above. + Anything else needs `pipe` + explicit capture. +- **Tee-ing to stderr.** Clack's spinner owns the terminal during a step. + Even stderr writes tear the frame. Pipe everything, then choose what + to surface. +- **UTF-8 in bash `$VAR…` positions.** Bash's lexer can pull the first + byte of a multi-byte character into the variable name and trip + `set -u`. Always brace: `${VAR}…`. + +## Future work (not yet implemented) + +- **Progression log rotation.** Today's implementation truncates on each + run. Future: roll prior runs to `logs/setup.log.1`, `.2`, etc. +- **Raw log rotation for multi-run installs.** Currently each run + overwrites. Fine for now; revisit if support needs to compare + successive attempts. +- **Structured output from `register-claude-token.sh`.** The interactive + step emits no machine-readable status today. Future could add a + post-interaction status block with the method used. diff --git a/nanoclaw.sh b/nanoclaw.sh index 2dc0f048e..17df82ce1 100755 --- a/nanoclaw.sh +++ b/nanoclaw.sh @@ -2,12 +2,15 @@ # # NanoClaw — scripted end-to-end install. # -# Runs `bash setup.sh` (bootstrap: Node check, pnpm install, native module -# verify), then `pnpm run setup:auto` (environment → container → onecli → -# auth → mounts → service → cli-agent → channel → verify). +# Phase 1: bootstrap (Node + pnpm + native module verify). Runs bash-side +# since tsx isn't available until pnpm install completes. +# Phase 2: setup:auto (all remaining steps under clack). # -# Everything that can be scripted runs unattended; the one interactive pause -# is the auth step (browser sign-in or paste token/API key). +# Both phases obey the same three-level output contract (see +# docs/setup-flow.md): +# 1. User-facing — concise status line with elapsed time +# 2. Progression log — logs/setup.log (header + one entry per phase/step) +# 3. Raw per-step log — logs/setup-steps/NN-name.log (full verbatim output) # # Config via env — passed through unchanged: # NANOCLAW_SKIP comma-separated setup:auto step names to skip @@ -19,28 +22,163 @@ set -euo pipefail PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" cd "$PROJECT_ROOT" +LOGS_DIR="$PROJECT_ROOT/logs" +STEPS_DIR="$LOGS_DIR/setup-steps" +PROGRESS_LOG="$LOGS_DIR/setup.log" + +# ─── log helpers ──────────────────────────────────────────────────────── + +ts_utc() { date -u +%Y-%m-%dT%H:%M:%SZ; } + +write_header() { + local ts + ts=$(ts_utc) + local branch commit + branch=$(git branch --show-current 2>/dev/null || echo unknown) + commit=$(git rev-parse --short HEAD 2>/dev/null || echo unknown) + { + echo "## ${ts} · setup:auto started" + echo " invocation: nanoclaw.sh" + echo " user: $(whoami)" + echo " cwd: ${PROJECT_ROOT}" + echo " branch: ${branch}" + echo " commit: ${commit}" + echo "" + } > "$PROGRESS_LOG" +} + +# grep_field FIELD FILE — first value of FIELD: from a status block. +grep_field() { + grep "^$1:" "$2" 2>/dev/null | head -1 | sed "s/^$1: *//" || true +} + +write_bootstrap_entry() { + local status=$1 dur=$2 raw=$3 + local ts + ts=$(ts_utc) + local platform is_wsl node_version deps_ok native_ok has_build_tools + platform=$(grep_field PLATFORM "$raw") + is_wsl=$(grep_field IS_WSL "$raw") + node_version=$(grep_field NODE_VERSION "$raw" | head -1) + deps_ok=$(grep_field DEPS_OK "$raw") + native_ok=$(grep_field NATIVE_OK "$raw") + has_build_tools=$(grep_field HAS_BUILD_TOOLS "$raw") + { + echo "=== [${ts}] bootstrap [${dur}s] → ${status} ===" + [ -n "$platform" ] && echo " platform: ${platform}" + [ -n "$is_wsl" ] && echo " is_wsl: ${is_wsl}" + [ -n "$node_version" ] && echo " node_version: ${node_version}" + [ -n "$deps_ok" ] && echo " deps_ok: ${deps_ok}" + [ -n "$native_ok" ] && echo " native_ok: ${native_ok}" + [ -n "$has_build_tools" ] && echo " has_build_tools: ${has_build_tools}" + # Emit the raw path relative to PROJECT_ROOT so the progression log + # is portable and matches the TS-side format (logs/setup-steps/NN-…). + echo " raw: ${raw#${PROJECT_ROOT}/}" + echo "" + } >> "$PROGRESS_LOG" +} + +write_abort_entry() { + local step=$1 error=$2 + local ts + ts=$(ts_utc) + echo "## ${ts} · aborted at ${step} (${error})" >> "$PROGRESS_LOG" +} + +# ─── bash-side "clack-alike" status line ──────────────────────────────── + +use_ansi() { [ -t 1 ] && [ -z "${NO_COLOR:-}" ]; } +dim() { use_ansi && printf '\033[2m%s\033[0m' "$1" || printf '%s' "$1"; } +gray() { use_ansi && printf '\033[90m%s\033[0m' "$1" || printf '%s' "$1"; } +red() { use_ansi && printf '\033[31m%s\033[0m' "$1" || printf '%s' "$1"; } +clear_line() { use_ansi && printf '\r\033[2K' || printf '\n'; } + +spinner_start() { printf '%s %s…' "$(gray '◒')" "$1"; } +spinner_update() { clear_line; printf '%s %s… %s' "$(gray '◒')" "$1" "$(dim "(${2}s)")"; } +spinner_success() { clear_line; printf '%s %s %s\n' "$(gray '◇')" "$1" "$(dim "(${2}s)")"; } +spinner_failure() { clear_line; printf '%s %s %s\n' "$(red '✗')" "$1" "$(dim "(${2}s)")"; } + +# ─── fresh-run setup ──────────────────────────────────────────────────── + +rm -rf "$STEPS_DIR" +rm -f "$PROGRESS_LOG" +mkdir -p "$STEPS_DIR" "$LOGS_DIR" +write_header + cat <<'EOF' ═══════════════════════════════════════════════════════════════ NanoClaw scripted setup ═══════════════════════════════════════════════════════════════ -Phase 1: bootstrap (Node + pnpm + native modules) +Phase 1 · bootstrap EOF -if ! bash setup.sh; then +# ─── phase 1: bootstrap ───────────────────────────────────────────────── + +BOOTSTRAP_RAW="${STEPS_DIR}/01-bootstrap.log" +BOOTSTRAP_LABEL="Bootstrapping Node, pnpm, native modules" +BOOTSTRAP_START=$(date +%s) + +spinner_start "$BOOTSTRAP_LABEL" + +# Run in the background so we can tick elapsed time. Capture exit code via +# a tmpfile (subshell $? is lost after the while loop finishes). +BOOTSTRAP_EXIT_FILE=$(mktemp -t nanoclaw-bootstrap-exit.XXXXXX) +( + # setup.sh's legacy `log()` writes to a file; point it at the raw log + # so its verbose entries land alongside the stdout we're capturing. + export NANOCLAW_BOOTSTRAP_LOG="$BOOTSTRAP_RAW" + if bash setup.sh > "$BOOTSTRAP_RAW" 2>&1; then + echo 0 > "$BOOTSTRAP_EXIT_FILE" + else + echo $? > "$BOOTSTRAP_EXIT_FILE" + fi +) & +BOOTSTRAP_PID=$! + +while kill -0 "$BOOTSTRAP_PID" 2>/dev/null; do + sleep 1 + if kill -0 "$BOOTSTRAP_PID" 2>/dev/null; then + spinner_update "$BOOTSTRAP_LABEL" "$(( $(date +%s) - BOOTSTRAP_START ))" + fi +done +# `wait` surfaces the child's exit code; we've already captured it. +wait "$BOOTSTRAP_PID" 2>/dev/null || true + +BOOTSTRAP_RC=$(cat "$BOOTSTRAP_EXIT_FILE") +rm -f "$BOOTSTRAP_EXIT_FILE" +BOOTSTRAP_DUR=$(( $(date +%s) - BOOTSTRAP_START )) + +if [ "$BOOTSTRAP_RC" -eq 0 ]; then + spinner_success "Bootstrap complete" "$BOOTSTRAP_DUR" + write_bootstrap_entry success "$BOOTSTRAP_DUR" "$BOOTSTRAP_RAW" +else + spinner_failure "Bootstrap failed" "$BOOTSTRAP_DUR" + write_bootstrap_entry failed "$BOOTSTRAP_DUR" "$BOOTSTRAP_RAW" + write_abort_entry bootstrap "exit-${BOOTSTRAP_RC}" + echo - echo "[nanoclaw.sh] Bootstrap failed. Inspect logs/setup.log and retry." >&2 + echo "$(dim '── last 40 lines of ')$(dim "$BOOTSTRAP_RAW")$(dim ' ──')" + tail -40 "$BOOTSTRAP_RAW" + echo + echo "Full raw log: $BOOTSTRAP_RAW" + echo "Progression: $PROGRESS_LOG" exit 1 fi +echo cat <<'EOF' - -═══════════════════════════════════════════════════════════════ - Phase 2: setup:auto -═══════════════════════════════════════════════════════════════ +Phase 2 · setup:auto EOF +# ─── phase 2: clack driver ────────────────────────────────────────────── + +# NANOCLAW_BOOTSTRAPPED=1 tells setup/auto.ts that the progression log has +# already been initialized (header + bootstrap entry), so it should append +# rather than wipe. +export NANOCLAW_BOOTSTRAPPED=1 + # exec so signals (Ctrl-C) propagate directly to the child. exec pnpm run setup:auto diff --git a/setup.sh b/setup.sh index e163df851..ae5da2789 100755 --- a/setup.sh +++ b/setup.sh @@ -6,9 +6,17 @@ set -euo pipefail # This is the only bash script in the setup flow. PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" -LOG_FILE="$PROJECT_ROOT/logs/setup.log" -mkdir -p "$PROJECT_ROOT/logs" +# Where verbose bootstrap logs go. nanoclaw.sh captures setup.sh's stdout to +# the per-step raw log, but legacy code in this script + install-node.sh +# also calls `log` which writes to a file. Route those to the raw log so +# they don't contaminate the progression log (logs/setup.log). +# Default: write to the raw bootstrap log if nanoclaw.sh pointed us there, +# else fall back to a dedicated bootstrap log (keeps standalone `bash +# setup.sh` invocations working). +LOG_FILE="${NANOCLAW_BOOTSTRAP_LOG:-${PROJECT_ROOT}/logs/bootstrap.log}" + +mkdir -p "$(dirname "$LOG_FILE")" log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] [bootstrap] $*" >> "$LOG_FILE"; } diff --git a/setup/add-telegram.sh b/setup/add-telegram.sh index 4d540af5d..5036bd4da 100755 --- a/setup/add-telegram.sh +++ b/setup/add-telegram.sh @@ -1,12 +1,15 @@ #!/usr/bin/env bash -set -euo pipefail - -# Install the Telegram adapter (Phase A of the /add-telegram skill), collect -# the bot token, write .env + data/env/env, and restart the service so the -# new adapter is live. Idempotent. # -# Pair-telegram (the interactive code-sending step) is run separately by the -# caller (setup/auto.ts) so it can stream status blocks to the user. +# Install the Telegram adapter, persist the bot token to .env + data/env/env, +# restart the service, and open the bot's chat page in the local Telegram +# client. Non-interactive — the operator-facing "Create a bot" instructions +# and token paste live in setup/auto.ts. The token comes in via the +# TELEGRAM_BOT_TOKEN env var. +# +# Emits exactly one status block on stdout (ADD_TELEGRAM) at the end. All +# chatty progress messages go to stderr so setup:auto's raw-log capture +# sees the full story without cluttering the final block for the parser. +set -euo pipefail PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" cd "$PROJECT_ROOT" @@ -15,19 +18,49 @@ cd "$PROJECT_ROOT" ADAPTER_VERSION="@chat-adapter/telegram@4.26.0" CHANNELS_BRANCH="origin/channels" +emit_status() { + local status=$1 error=${2:-} + local already=${ADAPTER_ALREADY_INSTALLED:-false} + local username=${BOT_USERNAME:-} + echo "=== NANOCLAW SETUP: ADD_TELEGRAM ===" + echo "STATUS: ${status}" + echo "ADAPTER_VERSION: ${ADAPTER_VERSION}" + echo "ADAPTER_ALREADY_INSTALLED: ${already}" + [ -n "$username" ] && echo "BOT_USERNAME: ${username}" + [ -n "$error" ] && echo "ERROR: ${error}" + echo "=== END ===" +} + +log() { echo "[add-telegram] $*" >&2; } + +if [ -z "${TELEGRAM_BOT_TOKEN:-}" ]; then + emit_status failed "TELEGRAM_BOT_TOKEN env var not set" + exit 1 +fi + +if ! [[ "$TELEGRAM_BOT_TOKEN" =~ ^[0-9]+:[A-Za-z0-9_-]{35,}$ ]]; then + emit_status failed "token format invalid (expected :)" + exit 1 +fi + need_install() { - [[ ! -f src/channels/telegram.ts ]] && return 0 + [ ! -f src/channels/telegram.ts ] && return 0 ! grep -q "^import './telegram.js';" src/channels/index.ts 2>/dev/null && return 0 return 1 } +ADAPTER_ALREADY_INSTALLED=true if need_install; then - echo "[add-telegram] Fetching channels branch…" - git fetch origin channels >/dev/null 2>&1 + ADAPTER_ALREADY_INSTALLED=false + log "Fetching channels branch…" + git fetch origin channels >&2 2>/dev/null || { + emit_status failed "git fetch origin channels failed" + exit 1 + } # pair-telegram.ts is maintained in this branch (setup-auto), so it's NOT # in this list — do not overwrite the local version with the channels copy. - echo "[add-telegram] Copying adapter files from ${CHANNELS_BRANCH}…" + log "Copying adapter files from ${CHANNELS_BRANCH}…" for f in \ src/channels/telegram.ts \ src/channels/telegram-pairing.ts \ @@ -35,7 +68,7 @@ if need_install; then src/channels/telegram-markdown-sanitize.ts \ src/channels/telegram-markdown-sanitize.test.ts do - git show "$CHANNELS_BRANCH:$f" > "$f" + git show "${CHANNELS_BRANCH}:$f" > "$f" done # Append self-registration import if missing. @@ -59,109 +92,71 @@ if need_install; then } ' - echo "[add-telegram] Installing ${ADAPTER_VERSION}…" - pnpm install "$ADAPTER_VERSION" + log "Installing ${ADAPTER_VERSION}…" + pnpm install "${ADAPTER_VERSION}" >&2 2>/dev/null || { + emit_status failed "pnpm install ${ADAPTER_VERSION} failed" + exit 1 + } - echo "[add-telegram] Building…" - pnpm run build >/dev/null + log "Building…" + pnpm run build >&2 2>/dev/null || { + emit_status failed "pnpm run build failed" + exit 1 + } else - echo "[add-telegram] Adapter files already installed — skipping install phase." + log "Adapter files already installed — skipping install phase." fi -# Token collection. -if grep -q '^TELEGRAM_BOT_TOKEN=.' .env 2>/dev/null; then - echo "[add-telegram] TELEGRAM_BOT_TOKEN already set in .env — skipping token prompt." +# Persist token. auto.ts validates before this point, so a bad token here +# would be an internal bug rather than operator input. +touch .env +if grep -q '^TELEGRAM_BOT_TOKEN=' .env; then + awk -v tok="$TELEGRAM_BOT_TOKEN" \ + '/^TELEGRAM_BOT_TOKEN=/{print "TELEGRAM_BOT_TOKEN=" tok; next} {print}' \ + .env > .env.tmp && mv .env.tmp .env else - cat <<'EOF' - -── Create a Telegram bot ────────────────────────────────────── - - 1. Open Telegram and message @BotFather - 2. Send: /newbot - 3. Follow the prompts (bot name, username ending in "bot") - 4. Copy the token it gives you (format: :) - -Optional but recommended for groups: - 5. @BotFather → /mybots → your bot → Bot Settings → Group Privacy → OFF - -EOF - echo "Paste your TELEGRAM_BOT_TOKEN and press Enter." - echo "Nothing will appear on the screen as you paste — that's intentional." - echo "Paste once, then just press Enter to submit." - read -r -s -p "> " TOKEN &2 - exit 1 - fi - - # Telegram bot tokens: :<35+ base64url-ish chars>. - if [[ ! "$TOKEN" =~ ^[0-9]+:[A-Za-z0-9_-]{35,}$ ]]; then - echo "[add-telegram] Token format looks wrong (expected :). Aborting." >&2 - exit 1 - fi - - touch .env - if grep -q '^TELEGRAM_BOT_TOKEN=' .env; then - awk -v tok="$TOKEN" '/^TELEGRAM_BOT_TOKEN=/{print "TELEGRAM_BOT_TOKEN=" tok; next} {print}' \ - .env > .env.tmp && mv .env.tmp .env - else - echo "TELEGRAM_BOT_TOKEN=$TOKEN" >> .env - fi + echo "TELEGRAM_BOT_TOKEN=${TELEGRAM_BOT_TOKEN}" >> .env fi -# Validate the token via getMe so a typo surfaces before we restart the -# service, and capture the bot's username for the deep link. -TELEGRAM_BOT_TOKEN_VALUE="$(grep '^TELEGRAM_BOT_TOKEN=' .env | head -1 | cut -d= -f2-)" +# Look up the bot username (auto.ts already validated; we re-query here so +# standalone invocations still work). +INFO=$(curl -fsS --max-time 8 \ + "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getMe" 2>/dev/null || true) BOT_USERNAME="" -if [[ -n "$TELEGRAM_BOT_TOKEN_VALUE" ]]; then - INFO=$(curl -fsS --max-time 8 \ - "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN_VALUE}/getMe" 2>/dev/null || true) - if echo "$INFO" | grep -q '"ok":true'; then - # Crude JSON parse — the response is always a flat object here. - BOT_USERNAME=$(echo "$INFO" | sed -nE 's/.*"username":"([^"]+)".*/\1/p') - if [[ -n "$BOT_USERNAME" ]]; then - echo "[add-telegram] Token validated — bot is @${BOT_USERNAME}." - fi - else - echo "[add-telegram] Warning: getMe did not return ok. Continuing, but the token may be wrong." - fi +if echo "$INFO" | grep -q '"ok":true'; then + BOT_USERNAME=$(echo "$INFO" | sed -nE 's/.*"username":"([^"]+)".*/\1/p') fi # Container reads from data/env/env (the host mounts it). mkdir -p data/env cp .env data/env/env -# Deep-link into the bot's chat in the installed Telegram app so the user -# is already on the right screen when pair-telegram prints the code. Also -# always print the URL so headless / remote-SSH users can open it manually. -if [[ -n "$BOT_USERNAME" ]]; then - BOT_URL="https://t.me/${BOT_USERNAME}" +# Deep-link into the bot's chat so the user is already on the right screen +# when pair-telegram prints the code. Silent best-effort — runs under a +# spinner, any output (from `open` / `xdg-open`) goes to the raw log. +if [ -n "$BOT_USERNAME" ]; then case "$(uname -s)" in Darwin) - open "tg://resolve?domain=${BOT_USERNAME}" >/dev/null 2>&1 \ - || open "$BOT_URL" >/dev/null 2>&1 \ + open "tg://resolve?domain=${BOT_USERNAME}" >&2 2>/dev/null \ + || open "https://t.me/${BOT_USERNAME}" >&2 2>/dev/null \ || true ;; Linux) - xdg-open "tg://resolve?domain=${BOT_USERNAME}" >/dev/null 2>&1 \ - || xdg-open "$BOT_URL" >/dev/null 2>&1 \ + xdg-open "tg://resolve?domain=${BOT_USERNAME}" >&2 2>/dev/null \ + || xdg-open "https://t.me/${BOT_USERNAME}" >&2 2>/dev/null \ || true ;; esac - echo "[add-telegram] Bot chat: ${BOT_URL}" - echo "[add-telegram] (If Telegram didn't open automatically, click the link above.)" fi -echo "[add-telegram] Restarting service so the new adapter picks up the token…" +log "Restarting service so the new adapter picks up the token…" case "$(uname -s)" in Darwin) - launchctl kickstart -k "gui/$(id -u)/com.nanoclaw" >/dev/null 2>&1 || true + launchctl kickstart -k "gui/$(id -u)/com.nanoclaw" >&2 2>/dev/null || true ;; Linux) - systemctl --user restart nanoclaw >/dev/null 2>&1 \ - || sudo systemctl restart nanoclaw >/dev/null 2>&1 \ + systemctl --user restart nanoclaw >&2 2>/dev/null \ + || sudo systemctl restart nanoclaw >&2 2>/dev/null \ || true ;; esac @@ -170,4 +165,4 @@ esac # begins polling for the user's code message. sleep 5 -echo "[add-telegram] Install + credentials complete." +emit_status success diff --git a/setup/auto.ts b/setup/auto.ts index 482fcea0d..c16b6e50e 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -26,13 +26,19 @@ * with inherited stdio — clack resumes cleanly on the next step. */ import { spawn, spawnSync } from 'child_process'; +import fs from 'fs'; import * as p from '@clack/prompts'; import k from 'kleur'; +import * as setupLog from './logs.js'; + const CLI_AGENT_NAME = 'Terminal Agent'; const DEFAULT_AGENT_NAME = 'Nano'; +const RUN_START = Date.now(); +let failingStep = 'setup'; + /** * Brand palette, pulled from assets/nanoclaw-logo.png: * brand cyan ≈ #2BB7CE — the "Claw" wordmark + mascot body @@ -123,14 +129,16 @@ class StatusStream { } /** - * Spawn a setup step as a child process, swallowing stdout/stderr into a - * buffer. The provided onBlock callback fires per status block as they - * parse. Returns when the child exits. + * Spawn a setup step as a child process. Output is tee'd to the provided + * raw log file (level 3) and parsed for status blocks (level 2 summary). + * The onBlock callback fires per status block as they close so the UI can + * react mid-stream. */ function spawnStep( stepName: string, extra: string[], onBlock: (block: Block) => void, + rawLogPath: string, ): Promise { return new Promise((resolve) => { const args = ['exec', 'tsx', 'setup/index.ts', '--step', stepName]; @@ -138,13 +146,20 @@ function spawnStep( const child = spawn('pnpm', args, { stdio: ['ignore', 'pipe', 'pipe'] }); const stream = new StatusStream(onBlock); + const raw = fs.createWriteStream(rawLogPath, { flags: 'w' }); + raw.write(`# ${stepName} — ${new Date().toISOString()}\n\n`); - child.stdout.on('data', (chunk: Buffer) => stream.write(chunk.toString('utf-8'))); + child.stdout.on('data', (chunk: Buffer) => { + stream.write(chunk.toString('utf-8')); + raw.write(chunk); + }); child.stderr.on('data', (chunk: Buffer) => { stream.transcript += chunk.toString('utf-8'); + raw.write(chunk); }); child.on('close', (code) => { + raw.end(); // Step block types don't always mirror step names (e.g. `mounts` emits // CONFIGURE_MOUNTS, `container` emits SETUP_CONTAINER). Any block with // a STATUS field is a terminal block; the last one wins. @@ -170,22 +185,90 @@ type SpinnerLabels = { failed?: string; }; -/** Run a step under a clack spinner. Child output is captured; shown only on failure. */ +/** Run a step under a clack spinner. Teed to a per-step raw log + progression entry at the end. */ async function runQuietStep( stepName: string, labels: SpinnerLabels, extra: string[] = [], -): Promise { - return runUnderSpinner(labels, () => spawnStep(stepName, extra, () => {})); +): Promise { + failingStep = stepName; + const rawLog = setupLog.stepRawLog(stepName); + const start = Date.now(); + const result = await runUnderSpinner(labels, () => + spawnStep(stepName, extra, () => {}, rawLog), + ); + const durationMs = Date.now() - start; + writeStepEntry(stepName, result, durationMs, rawLog); + return { ...result, rawLog, durationMs }; } -/** Run an arbitrary child under a spinner, capturing its stdout/stderr. */ +/** Run an arbitrary child under a spinner. Same raw-log + progression treatment as runQuietStep. */ async function runQuietChild( + logName: string, cmd: string, args: string[], labels: SpinnerLabels, -): Promise<{ ok: boolean; exitCode: number; transcript: string }> { - return runUnderSpinner(labels, () => spawnQuiet(cmd, args)); + opts?: { + /** Extra fields to merge into the progression entry (on top of any status-block fields). */ + extraFields?: Record; + /** Environment overrides to pass to the child process. */ + env?: NodeJS.ProcessEnv; + }, +): Promise<{ + ok: boolean; + exitCode: number; + transcript: string; + terminal: Block | null; + rawLog: string; + durationMs: number; +}> { + failingStep = logName; + const rawLog = setupLog.stepRawLog(logName); + const start = Date.now(); + const result = await runUnderSpinner(labels, () => + spawnQuiet(cmd, args, rawLog, opts?.env), + ); + const durationMs = Date.now() - start; + + const blockFields = summariseTerminalFields(result.terminal); + const fields = { ...blockFields, ...(opts?.extraFields ?? {}) }; + const rawStatus = result.terminal?.fields.STATUS; + const status: 'success' | 'skipped' | 'failed' = !result.ok + ? 'failed' + : rawStatus === 'skipped' + ? 'skipped' + : 'success'; + setupLog.step(logName, status, durationMs, fields, rawLog); + return { ...result, rawLog, durationMs }; +} + +/** Turn a step's terminal-block fields into a concise progression-log entry. */ +function writeStepEntry( + stepName: string, + result: StepResult, + durationMs: number, + rawLog: string, +): void { + const rawStatus = result.terminal?.fields.STATUS; + const logStatus: 'success' | 'skipped' | 'failed' = !result.ok + ? 'failed' + : rawStatus === 'skipped' + ? 'skipped' + : 'success'; + const fields = summariseTerminalFields(result.terminal); + setupLog.step(stepName, logStatus, durationMs, fields, rawLog); +} + +/** Strip STATUS + LOG (redundant) and any oversize values from the terminal block's fields. */ +function summariseTerminalFields(block: Block | null): Record { + if (!block) return {}; + const out: Record = {}; + for (const [k, v] of Object.entries(block.fields)) { + if (k === 'STATUS' || k === 'LOG') continue; + if (v.length > 120) continue; // keep it skimmable; full value lives in the raw log + out[k] = v; + } + return out; } async function runUnderSpinner< @@ -221,14 +304,34 @@ async function runUnderSpinner< function spawnQuiet( cmd: string, args: string[], -): Promise<{ ok: boolean; exitCode: number; transcript: string }> { + rawLogPath: string, + envOverride?: NodeJS.ProcessEnv, +): Promise<{ ok: boolean; exitCode: number; transcript: string; terminal: Block | null; blocks: Block[] }> { return new Promise((resolve) => { - const child = spawn(cmd, args, { stdio: ['ignore', 'pipe', 'pipe'] }); + const child = spawn(cmd, args, { + stdio: ['ignore', 'pipe', 'pipe'], + env: envOverride ? { ...process.env, ...envOverride } : process.env, + }); let transcript = ''; - child.stdout.on('data', (c: Buffer) => { transcript += c.toString('utf-8'); }); - child.stderr.on('data', (c: Buffer) => { transcript += c.toString('utf-8'); }); + const raw = fs.createWriteStream(rawLogPath, { flags: 'w' }); + raw.write(`# ${[cmd, ...args].join(' ')} — ${new Date().toISOString()}\n\n`); + const blocks: Block[] = []; + const stream = new StatusStream((b) => blocks.push(b)); + child.stdout.on('data', (c: Buffer) => { + const s = c.toString('utf-8'); + transcript += s; + stream.write(s); + raw.write(c); + }); + child.stderr.on('data', (c: Buffer) => { + transcript += c.toString('utf-8'); + raw.write(c); + }); child.on('close', (code) => { - resolve({ ok: code === 0, exitCode: code ?? 1, transcript }); + raw.end(); + const terminal = + [...blocks].reverse().find((b) => b.fields.STATUS) ?? null; + resolve({ ok: code === 0, exitCode: code ?? 1, transcript, terminal, blocks }); }); }); } @@ -248,15 +351,17 @@ function dumpTranscriptOnFailure(transcript: string): void { } function fail(msg: string, hint?: string): never { + setupLog.abort(failingStep, msg); p.log.error(msg); if (hint) p.log.message(k.dim(hint)); - p.log.message(k.dim('Logs: logs/setup.log')); + p.log.message(k.dim('Logs: logs/setup.log · Raw: logs/setup-steps/')); p.cancel('Setup aborted.'); process.exit(1); } function ensureAnswer(value: T | symbol): T { if (p.isCancel(value)) { + setupLog.abort(failingStep, 'user-cancelled'); p.cancel('Setup cancelled.'); process.exit(0); } @@ -317,7 +422,10 @@ function formatCodeCard(code: string): string { ].join('\n'); } -async function runPairTelegram(): Promise { +async function runPairTelegram(): Promise { + failingStep = 'pair-telegram'; + const rawLog = setupLog.stepRawLog('pair-telegram'); + const start = Date.now(); const s = p.spinner(); s.start('Creating pairing code…'); let spinnerActive = true; @@ -329,29 +437,35 @@ async function runPairTelegram(): Promise { } }; - const result = await spawnStep('pair-telegram', ['--intent', 'main'], (block) => { - if (block.type === 'PAIR_TELEGRAM_CODE') { - const reason = block.fields.REASON ?? 'initial'; - if (reason === 'initial') { - stopSpinner('Pairing code ready.'); - } else { - stopSpinner('Previous code invalidated. New code below.'); + const result = await spawnStep( + 'pair-telegram', + ['--intent', 'main'], + (block) => { + if (block.type === 'PAIR_TELEGRAM_CODE') { + const reason = block.fields.REASON ?? 'initial'; + if (reason === 'initial') { + stopSpinner('Pairing code ready.'); + } else { + stopSpinner('Previous code invalidated. New code below.'); + } + p.note(formatCodeCard(block.fields.CODE ?? '????'), 'Pairing code'); + s.start('Waiting for the code from Telegram…'); + spinnerActive = true; + } else if (block.type === 'PAIR_TELEGRAM_ATTEMPT') { + stopSpinner(`Received "${block.fields.CANDIDATE ?? '?'}" — doesn't match.`); + s.start('Waiting for the correct code…'); + spinnerActive = true; + } else if (block.type === 'PAIR_TELEGRAM') { + if (block.fields.STATUS === 'success') { + stopSpinner('Telegram paired.'); + } else { + stopSpinner(`Pairing failed: ${block.fields.ERROR ?? 'unknown'}`, 1); + } } - p.note(formatCodeCard(block.fields.CODE ?? '????'), 'Pairing code'); - s.start('Waiting for the code from Telegram…'); - spinnerActive = true; - } else if (block.type === 'PAIR_TELEGRAM_ATTEMPT') { - stopSpinner(`Received "${block.fields.CANDIDATE ?? '?'}" — doesn't match.`); - s.start('Waiting for the correct code…'); - spinnerActive = true; - } else if (block.type === 'PAIR_TELEGRAM') { - if (block.fields.STATUS === 'success') { - stopSpinner('Telegram paired.'); - } else { - stopSpinner(`Pairing failed: ${block.fields.ERROR ?? 'unknown'}`, 1); - } - } - }); + }, + rawLog, + ); + const durationMs = Date.now() - start; // Safety net: if the child died without emitting a terminal block, make // sure we don't leave the spinner running. @@ -359,7 +473,9 @@ async function runPairTelegram(): Promise { stopSpinner(result.ok ? 'Done.' : 'Pairing exited unexpectedly.', result.ok ? 0 : 1); if (!result.ok) dumpTranscriptOnFailure(result.transcript); } - return result; + + writeStepEntry('pair-telegram', result, durationMs, rawLog); + return { ...result, rawLog, durationMs }; } async function askDisplayName(fallback: string): Promise { @@ -370,7 +486,9 @@ async function askDisplayName(fallback: string): Promise { defaultValue: fallback, }), ); - return (answer as string).trim() || fallback; + const value = (answer as string).trim() || fallback; + setupLog.userInput('display_name', value); + return value; } async function askAgentName(fallback: string): Promise { @@ -381,7 +499,9 @@ async function askAgentName(fallback: string): Promise { defaultValue: fallback, }), ); - return (answer as string).trim() || fallback; + const value = (answer as string).trim() || fallback; + setupLog.userInput('agent_name', value); + return value; } async function askChannelChoice(): Promise<'telegram' | 'skip'> { @@ -394,9 +514,94 @@ async function askChannelChoice(): Promise<'telegram' | 'skip'> { ], }), ); + setupLog.userInput('channel_choice', String(choice)); return choice as 'telegram' | 'skip'; } +async function collectTelegramToken(): Promise { + p.note( + [ + '1. Open Telegram and message @BotFather', + '2. Send: /newbot', + '3. Follow the prompts (name + username ending in "bot")', + '4. Copy the token it gives you (format: :)', + '', + k.dim('Optional, but recommended for groups:'), + k.dim(' @BotFather → /mybots → Bot Settings → Group Privacy → OFF'), + ].join('\n'), + 'Create a Telegram bot', + ); + + const answer = ensureAnswer( + await p.password({ + message: 'Paste your bot token', + validate: (v) => { + if (!v || !v.trim()) return 'Token is required'; + if (!/^[0-9]+:[A-Za-z0-9_-]{35,}$/.test(v.trim())) { + return 'Format looks wrong — expected :'; + } + return undefined; + }, + }), + ); + const token = (answer as string).trim(); + setupLog.userInput( + 'telegram_token', + `${token.slice(0, 12)}…${token.slice(-4)}`, + ); + return token; +} + +async function validateTelegramToken(token: string): Promise { + failingStep = 'telegram-validate'; + const s = p.spinner(); + const start = Date.now(); + s.start('Validating token with Telegram…'); + try { + const res = await fetch(`https://api.telegram.org/bot${token}/getMe`); + const data = (await res.json()) as { + ok?: boolean; + result?: { username?: string; id?: number }; + description?: string; + }; + const elapsed = Math.round((Date.now() - start) / 1000); + if (data.ok && data.result?.username) { + const username = data.result.username; + s.stop(`Bot is @${username}. ${k.dim(`(${elapsed}s)`)}`); + setupLog.step( + 'telegram-validate', + 'success', + Date.now() - start, + { BOT_USERNAME: username, BOT_ID: data.result.id ?? '' }, + ); + return username; + } + const reason = data.description ?? 'token rejected by Telegram'; + s.stop(`Telegram rejected the token: ${reason}`, 1); + setupLog.step( + 'telegram-validate', + 'failed', + Date.now() - start, + { ERROR: reason }, + ); + fail( + 'Telegram rejected the token.', + 'Double-check the token (copy it again from @BotFather) and retry.', + ); + } catch (err) { + const elapsed = Math.round((Date.now() - start) / 1000); + s.stop(`Could not reach Telegram. ${k.dim(`(${elapsed}s)`)}`, 1); + const message = err instanceof Error ? err.message : String(err); + setupLog.step('telegram-validate', 'failed', Date.now() - start, { + ERROR: message, + }); + fail( + 'Telegram API unreachable.', + 'Check your network connection and retry.', + ); + } +} + function printIntro(): void { const isReexec = process.env.NANOCLAW_REEXEC_SG === '1'; const wordmark = `${k.bold('Nano')}${brandBold('Claw')}`; @@ -414,6 +619,7 @@ function printIntro(): void { async function main(): Promise { printIntro(); + initProgressionLog(); const skip = new Set( (process.env.NANOCLAW_SKIP ?? '') @@ -479,22 +685,28 @@ async function main(): Promise { } if (!skip.has('auth')) { + failingStep = 'auth'; if (anthropicSecretExists()) { p.log.success('OneCLI already has an Anthropic secret — skipping.'); + setupLog.step('auth', 'skipped', 0, { REASON: 'secret-already-present' }); } else { p.log.step('Registering your Anthropic credential…'); console.log( k.dim(' (browser sign-in or paste a token/key — this part is interactive)'), ); console.log(); + const start = Date.now(); const code = await runInheritScript('bash', ['setup/register-claude-token.sh']); + const durationMs = Date.now() - start; console.log(); if (code !== 0) { + setupLog.step('auth', 'failed', durationMs, { EXIT_CODE: code }); fail( 'Anthropic credential registration failed or was aborted.', 'Re-run `bash setup/register-claude-token.sh` or handle via `/setup` §4.', ); } + setupLog.step('auth', 'interactive', durationMs, { METHOD: 'register-claude-token.sh' }); p.log.success('Anthropic credential registered with OneCLI.'); } } @@ -558,17 +770,28 @@ async function main(): Promise { if (!skip.has('channel')) { const choice = await askChannelChoice(); if (choice === 'telegram') { - p.log.step('Installing the Telegram adapter and collecting your bot token…'); - console.log(); - const installCode = await runInheritScript('bash', ['setup/add-telegram.sh']); - console.log(); - if (installCode !== 0) { + const token = await collectTelegramToken(); + const botUsername = await validateTelegramToken(token); + + const install = await runQuietChild( + 'telegram-install', + 'bash', + ['setup/add-telegram.sh'], + { + running: `Installing Telegram adapter and wiring @${botUsername}…`, + done: `Telegram adapter ready.`, + }, + { + env: { TELEGRAM_BOT_TOKEN: token }, + extraFields: { BOT_USERNAME: botUsername }, + }, + ); + if (!install.ok) { fail( 'Telegram install failed.', - 'Re-run `bash setup/add-telegram.sh`, then retry `pnpm run setup:auto`.', + 'Check the raw log under logs/setup-steps/, then retry `pnpm run setup:auto`.', ); } - p.log.success('Telegram adapter installed.'); const pair = await runPairTelegram(); if (!pair.ok) { @@ -592,6 +815,7 @@ async function main(): Promise { (await askAgentName(DEFAULT_AGENT_NAME)); const init = await runQuietChild( + 'init-first-agent', 'pnpm', [ 'exec', 'tsx', 'scripts/init-first-agent.ts', @@ -605,6 +829,9 @@ async function main(): Promise { running: `Wiring ${agentName} to your Telegram chat…`, done: `${agentName} is wired — welcome DM incoming.`, }, + { + extraFields: { CHANNEL: 'telegram', AGENT_NAME: agentName, PLATFORM_ID: platformId }, + }, ); if (!init.ok) { fail( @@ -652,9 +879,43 @@ async function main(): Promise { `${k.cyan('Open Claude Code:')} claude`, ].join('\n'); p.note(nextSteps, 'Next steps'); + setupLog.complete(Date.now() - RUN_START); p.outro(k.green('Setup complete.')); } +/** + * Bootstrap (nanoclaw.sh) normally initializes logs/setup.log and writes + * the bootstrap entry before we even boot. If someone runs `pnpm run + * setup:auto` directly, start a fresh progression log here so we don't + * append to a stale one from a previous run. + */ +function initProgressionLog(): void { + if (process.env.NANOCLAW_BOOTSTRAPPED === '1') return; + let commit = ''; + try { + commit = spawnSync('git', ['rev-parse', '--short', 'HEAD'], { + encoding: 'utf-8', + }).stdout.trim(); + } catch { + // git not available or not a repo — skip + } + let branch = ''; + try { + branch = spawnSync('git', ['branch', '--show-current'], { + encoding: 'utf-8', + }).stdout.trim(); + } catch { + // skip + } + setupLog.reset({ + invocation: 'setup:auto (standalone)', + user: process.env.USER ?? 'unknown', + cwd: process.cwd(), + branch: branch || 'unknown', + commit: commit || 'unknown', + }); +} + main().catch((err) => { p.log.error(err instanceof Error ? err.message : String(err)); p.cancel('Setup aborted.'); diff --git a/setup/logs.ts b/setup/logs.ts new file mode 100644 index 000000000..127f9692b --- /dev/null +++ b/setup/logs.ts @@ -0,0 +1,130 @@ +/** + * Three-level setup logging primitives. See docs/setup-flow.md for the + * contract and design rationale. + * + * Level 1: clack UI in setup/auto.ts (not here) + * Level 2: logs/setup.log — structured, append-only progression log + * Level 3: logs/setup-steps/NN-name.log — raw stdout+stderr per step + * + * Usage from auto.ts: + * + * import * as setupLog from './logs.js'; + * + * const rawLog = setupLog.stepRawLog('container'); + * const { ok, durationMs, terminal } = + * await spawnIntoRawLog('...', rawLog); + * setupLog.step('container', ok ? 'success' : 'failed', durationMs, + * { RUNTIME: 'docker', BUILD_OK: terminal.fields.BUILD_OK }, + * rawLog); + * + * nanoclaw.sh emits the bootstrap entry directly via a bash helper so + * the format stays consistent without needing IPC between bash and tsx. + */ +import fs from 'fs'; +import path from 'path'; + +const LOGS_DIR = 'logs'; +const STEPS_DIR = path.join(LOGS_DIR, 'setup-steps'); +const PROGRESS_LOG = path.join(LOGS_DIR, 'setup.log'); + +export const progressLogPath = PROGRESS_LOG; +export const stepsDir = STEPS_DIR; + +/** Wipe prior logs and write a header. Called once per fresh run (by nanoclaw.sh or as a fallback by auto.ts if invoked standalone). */ +export function reset(meta: Record): void { + if (fs.existsSync(STEPS_DIR)) { + fs.rmSync(STEPS_DIR, { recursive: true, force: true }); + } + fs.mkdirSync(STEPS_DIR, { recursive: true }); + if (fs.existsSync(PROGRESS_LOG)) fs.unlinkSync(PROGRESS_LOG); + header(meta); +} + +/** Append a run-start header to the progression log. Idempotent: creates the file if missing. */ +export function header(meta: Record): void { + fs.mkdirSync(LOGS_DIR, { recursive: true }); + const ts = new Date().toISOString(); + const lines = [`## ${ts} · setup:auto started`]; + for (const [k, v] of Object.entries(meta)) { + lines.push(` ${k}: ${v}`); + } + lines.push(''); + fs.appendFileSync(PROGRESS_LOG, lines.join('\n') + '\n'); +} + +/** Append one step entry to the progression log. */ +export function step( + name: string, + status: 'success' | 'skipped' | 'failed' | 'aborted' | 'interactive', + durationMs: number, + fields: Record, + rawRel?: string, +): void { + fs.mkdirSync(LOGS_DIR, { recursive: true }); + const ts = new Date().toISOString(); + const dur = formatDuration(durationMs); + const lines = [`=== [${ts}] ${name} [${dur}] → ${status} ===`]; + for (const [k, v] of Object.entries(fields)) { + if (v === undefined || v === null || v === '') continue; + lines.push(` ${k.toLowerCase()}: ${String(v)}`); + } + if (rawRel) lines.push(` raw: ${rawRel}`); + lines.push(''); + fs.appendFileSync(PROGRESS_LOG, lines.join('\n') + '\n'); +} + +/** A user answered a prompt. Logs as its own entry because the setup path depends on it. */ +export function userInput(key: string, value: string): void { + fs.mkdirSync(LOGS_DIR, { recursive: true }); + const ts = new Date().toISOString(); + fs.appendFileSync( + PROGRESS_LOG, + `=== [${ts}] user-input → ${key} ===\n value: ${value}\n\n`, + ); +} + +/** Append the success footer. */ +export function complete(totalMs: number): void { + const ts = new Date().toISOString(); + fs.appendFileSync( + PROGRESS_LOG, + `## ${ts} · completed (total ${formatDurationTotal(totalMs)})\n`, + ); +} + +/** Append the failure footer. Keep error short — full context lives in the failing step's raw log. */ +export function abort(stepName: string, error: string): void { + const ts = new Date().toISOString(); + fs.appendFileSync( + PROGRESS_LOG, + `## ${ts} · aborted at ${stepName} (${error})\n`, + ); +} + +/** + * Return the next raw-log path for a given step name. Numbering is derived + * from the count of existing NN-*.log files in STEPS_DIR, so bootstrap's + * pre-existing 01-bootstrap.log (written by nanoclaw.sh before this module + * is loaded) counts toward the sequence. + */ +export function stepRawLog(name: string): string { + fs.mkdirSync(STEPS_DIR, { recursive: true }); + const existing = fs + .readdirSync(STEPS_DIR) + .filter((n) => /^\d+-.+\.log$/.test(n)); + const nextIdx = existing.length + 1; + const num = String(nextIdx).padStart(2, '0'); + const safeName = name.replace(/[^a-z0-9-]/gi, '-').toLowerCase(); + return path.join(STEPS_DIR, `${num}-${safeName}.log`); +} + +function formatDuration(ms: number): string { + if (ms < 1000) return `${Math.round(ms)}ms`; + return `${(ms / 1000).toFixed(1)}s`; +} + +function formatDurationTotal(ms: number): string { + const mins = Math.floor(ms / 60000); + const secs = Math.round((ms % 60000) / 1000); + return mins > 0 ? `${mins}m${secs}s` : `${secs}s`; +} From 416fe018550cbb3f83826cc1a3d67dc165920720 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 02:13:22 +0300 Subject: [PATCH 90/95] refactor(setup): drop CLI-bonus wiring from init-first-agent MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit init-first-agent used to double-wire the CLI channel to every new DM agent as a convenience for `pnpm run chat`, gated by --no-cli-bonus. With the /new-setup-2 flow gone and a dedicated scratch CLI agent created earlier in setup:auto, that bonus just stomps on CLI routing the user already set up. Remove the CLI_CHANNEL/CLI_PLATFORM_ID constants, ensureCliMessagingGroup, the --no-cli-bonus flag, and the cli-bonus wiring block. Pass the paired user's identity through to the welcome delivery so the sender resolver sees the real owner (e.g. telegram:) instead of cli:local. Extend the CLI channel's admin-transport payload to accept optional sender/senderId overrides — falls back to the old cli/cli:local defaults when omitted, so existing callers are unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) --- scripts/init-first-agent.ts | 74 +++++++++++-------------------------- src/channels/cli.ts | 6 ++- 2 files changed, 26 insertions(+), 54 deletions(-) diff --git a/scripts/init-first-agent.ts b/scripts/init-first-agent.ts index 29ca6d444..c634851d8 100644 --- a/scripts/init-first-agent.ts +++ b/scripts/init-first-agent.ts @@ -1,16 +1,13 @@ /** * Init the first (or Nth) NanoClaw v2 agent for a DM channel. * - * Wires a real DM channel (discord, telegram, etc.) to a new agent group - * (and the local CLI channel as a convenience bonus), then hands a welcome - * message to the running service via its CLI socket. The service routes - * that message into the DM session, which wakes the container synchronously — - * the agent processes the welcome and DMs the operator through the normal - * delivery path. + * Wires a real DM channel (discord, telegram, etc.) to a new agent group, + * then hands a welcome message to the running service via the CLI socket + * (admin transport). The service routes that message into the DM session, + * which wakes the container synchronously — the agent processes the welcome + * and DMs the operator through the normal delivery path. * - * For the CLI-only scratch agent used during `/new-setup`, see - * `scripts/init-cli-agent.ts` — that's a distinct flow and doesn't run - * through here. + * CLI channel wiring is handled separately by `scripts/init-cli-agent.ts`. * * Creates/reuses: user, owner grant (if none), agent group + filesystem, * messaging group(s), wiring. @@ -27,8 +24,7 @@ * --platform-id discord:@me:1491573333382523708 \ * --display-name "Gavriel" \ * [--agent-name "Andy"] \ - * [--welcome "System instruction: ..."] \ - * [--no-cli-bonus] + * [--welcome "System instruction: ..."] * * For direct-addressable channels (telegram, whatsapp, etc.), --platform-id * is typically the same as the handle in --user-id, with the channel prefix. @@ -53,7 +49,6 @@ import { initGroupFilesystem } from '../src/group-init.js'; import type { AgentGroup, MessagingGroup } from '../src/types.js'; interface Args { - noCliBonus: boolean; channel: string; userId: string; platformId: string; @@ -65,18 +60,12 @@ interface Args { const DEFAULT_WELCOME = 'System instruction: run /welcome to introduce yourself to the user on this new channel.'; -const CLI_CHANNEL = 'cli'; -const CLI_PLATFORM_ID = 'local'; - function parseArgs(argv: string[]): Args { - const out: Partial = { noCliBonus: false }; + const out: Partial = {}; for (let i = 0; i < argv.length; i++) { const key = argv[i]; const val = argv[i + 1]; switch (key) { - case '--no-cli-bonus': - out.noCliBonus = true; - break; case '--channel': out.channel = (val ?? '').toLowerCase(); i++; @@ -115,7 +104,6 @@ function parseArgs(argv: string[]): Args { } return { - noCliBonus: out.noCliBonus ?? false, channel: out.channel!, userId: out.userId!, platformId: out.platformId!, @@ -137,24 +125,6 @@ function generateId(prefix: string): string { return `${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`; } -function ensureCliMessagingGroup(now: string): MessagingGroup { - let cliMg = getMessagingGroupByPlatform(CLI_CHANNEL, CLI_PLATFORM_ID); - if (cliMg) return cliMg; - - cliMg = { - id: generateId('mg'), - channel_type: CLI_CHANNEL, - platform_id: CLI_PLATFORM_ID, - name: 'Local CLI', - is_group: 0, - unknown_sender_policy: 'public', - created_at: now, - }; - createMessagingGroup(cliMg); - console.log(`Created CLI messaging group: ${cliMg.id}`); - return cliMg; -} - function wireIfMissing(mg: MessagingGroup, ag: AgentGroup, now: string, label: string): void { const existing = getMessagingGroupAgentByPair(mg.id, ag.id); if (existing) { @@ -252,29 +222,23 @@ async function main(): Promise { console.log(`Reusing messaging group: ${dmMg.id} (${platformId})`); } - // 4. Wire DM (auto-creates companion agent_destinations row) and, - // unless suppressed, also wire the CLI channel so `pnpm run chat` works - // against the new agent immediately. `/new-setup-2` sets --no-cli-bonus - // so the scratch CLI agent from `/new-setup` keeps owning CLI routing. + // 4. Wire DM messaging group to the agent. wireIfMissing(dmMg, ag, now, 'dm'); - if (!args.noCliBonus) { - const cliMg = ensureCliMessagingGroup(now); - wireIfMissing(cliMg, ag, now, 'cli-bonus'); - } // 5. Welcome delivery over the CLI socket. Router picks up the line, // writes the message into the DM session's inbound.db, and wakes the - // container synchronously — no sweep wait. - await sendWelcomeViaCliSocket(dmMg, args.welcome); + // container synchronously — no sweep wait. The paired user's identity is + // passed so the sender resolver sees the real owner, not cli:local. + await sendWelcomeViaCliSocket(dmMg, args.welcome, { + senderId: userId, + sender: args.displayName, + }); console.log(''); console.log('Init complete.'); console.log(` owner: ${userId}${promotedToOwner ? ' (promoted on first owner)' : ''}`); console.log(` agent: ${ag.name} [${ag.id}] @ groups/${folder}`); console.log(` channel: ${args.channel} ${dmMg.platform_id}`); - if (!args.noCliBonus) { - console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``); - } console.log(''); console.log('Welcome DM queued — the agent will greet you shortly.'); } @@ -288,7 +252,11 @@ async function main(): Promise { * Throws if the socket isn't reachable — this script requires the service * to be running. */ -async function sendWelcomeViaCliSocket(dmMg: MessagingGroup, welcome: string): Promise { +async function sendWelcomeViaCliSocket( + dmMg: MessagingGroup, + welcome: string, + identity: { senderId: string; sender: string }, +): Promise { const sockPath = path.join(DATA_DIR, 'cli.sock'); await new Promise((resolve, reject) => { @@ -318,6 +286,8 @@ async function sendWelcomeViaCliSocket(dmMg: MessagingGroup, welcome: string): P const payload = JSON.stringify({ text: welcome, + senderId: identity.senderId, + sender: identity.sender, to: { channelType: dmMg.channel_type, platformId: dmMg.platform_id, diff --git a/src/channels/cli.ts b/src/channels/cli.ts index b73818673..ad78bea8a 100644 --- a/src/channels/cli.ts +++ b/src/channels/cli.ts @@ -183,6 +183,8 @@ function createAdapter(): ChannelAdapter { text?: unknown; to?: unknown; reply_to?: unknown; + sender?: unknown; + senderId?: unknown; }; try { payload = JSON.parse(line); @@ -209,8 +211,8 @@ function createAdapter(): ChannelAdapter { timestamp: new Date().toISOString(), content: JSON.stringify({ text: payload.text, - sender: 'cli', - senderId: `cli:${PLATFORM_ID}`, + sender: typeof payload.sender === 'string' ? payload.sender : 'cli', + senderId: typeof payload.senderId === 'string' ? payload.senderId : `cli:${PLATFORM_ID}`, }), }, replyTo: replyTo ?? undefined, From 9b7d4d50e409fb240f6a1a80c2bfe5d43330ae9e Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 02:26:50 +0300 Subject: [PATCH 91/95] refactor(setup): split auto.ts into runner + theme + telegram channel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit auto.ts had grown to 923 lines with ~10 interleaved responsibilities. Split into three focused modules, keeping auto.ts as a pure step sequencer: - setup/lib/runner.ts (325 lines) — spawn + stream-parse + spinner-wrap primitives. Exports: spawnStep, spawnQuiet, runQuietStep, runQuietChild, runUnderSpinner (internal), StatusStream, types (Fields, Block, StepResult, SpinnerLabels, QuietChildResult), writeStepEntry, summariseTerminalFields, dumpTranscriptOnFailure, fail(), ensureAnswer(). - setup/lib/theme.ts (39 lines) — brand palette (brand, brandBold, brandChip) with USE_ANSI / TRUECOLOR gating, so both auto.ts and channel flows can render the NanoClaw cyan without duplicating the detection. - setup/channels/telegram.ts (277 lines) — runTelegramChannel(displayName) owns the full flow: BotFather instructions, token paste + validation (via getMe), install script, pair-telegram streaming UI (code card + attempt checkpoints), agent-name prompt, init-first-agent wiring. auto.ts drops to 376 lines. main() reads as a clean sequence of `if (!skip.has(X)) await Xstep(...)` blocks. fail() now takes the step name explicitly — no module-level failingStep state. Every call site is grep-friendly and self-contained (fail('container', msg, hint)). Typechecks clean. Smoke-tested end-to-end: intro, mounts step, progression log, and outro all render the same as before the split. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 813 ++++++------------------------------- setup/channels/telegram.ts | 277 +++++++++++++ setup/lib/runner.ts | 325 +++++++++++++++ setup/lib/theme.ts | 39 ++ 4 files changed, 774 insertions(+), 680 deletions(-) create mode 100644 setup/channels/telegram.ts create mode 100644 setup/lib/runner.ts create mode 100644 setup/lib/theme.ts diff --git a/setup/auto.ts b/setup/auto.ts index c16b6e50e..bb23650cc 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -1,621 +1,37 @@ /** - * Non-interactive setup driver. Chains the deterministic setup steps so a - * scripted install can go from a fresh checkout to a running service without - * the `/setup` skill. + * Non-interactive setup driver — the step sequencer for `pnpm run setup:auto`. * - * Prerequisite: `bash setup.sh` has run (Node >= 20, pnpm install, native - * module check). This driver picks up from there. + * Responsibility: orchestrate the sequence of steps end-to-end and route + * between them. The runner, spawning, status parsing, spinner, abort, and + * prompt primitives live in `setup/lib/runner.ts`; theming in + * `setup/lib/theme.ts`; Telegram's full flow in `setup/channels/telegram.ts`. * * Config via env: * NANOCLAW_DISPLAY_NAME how the agents address the operator — skips the * prompt. Defaults to $USER. - * NANOCLAW_AGENT_NAME name for the messaging-channel agent (Telegram, - * etc.) — skips the prompt. Defaults to "Nano". - * (The CLI scratch agent is always "Terminal Agent".) + * NANOCLAW_AGENT_NAME messaging-channel agent name (consumed by the + * channel flow). The CLI scratch agent is always + * "Terminal Agent". * NANOCLAW_SKIP comma-separated step names to skip * (environment|container|onecli|auth|mounts| * service|cli-agent|channel|verify) * - * Timezone is not configured here — it defaults to the host system's TZ. - * Run `pnpm exec tsx setup/index.ts --step timezone -- --tz ` later - * if autodetect is wrong (e.g. headless server with TZ=UTC). - * - * UI is rendered with @clack/prompts: spinners wrap each step, child output - * is captured quietly and only dumped on failure. Interactive children - * (register-claude-token.sh, add-telegram.sh) bypass the spinner and run - * with inherited stdio — clack resumes cleanly on the next step. + * Timezone defaults to the host system's TZ. Run + * pnpm exec tsx setup/index.ts --step timezone -- --tz + * later if autodetect is wrong. */ import { spawn, spawnSync } from 'child_process'; -import fs from 'fs'; import * as p from '@clack/prompts'; import k from 'kleur'; +import { runTelegramChannel } from './channels/telegram.js'; import * as setupLog from './logs.js'; +import { ensureAnswer, fail, runQuietStep } from './lib/runner.js'; +import { brandBold, brandChip } from './lib/theme.js'; const CLI_AGENT_NAME = 'Terminal Agent'; -const DEFAULT_AGENT_NAME = 'Nano'; - const RUN_START = Date.now(); -let failingStep = 'setup'; - -/** - * Brand palette, pulled from assets/nanoclaw-logo.png: - * brand cyan ≈ #2BB7CE — the "Claw" wordmark + mascot body - * brand navy ≈ #171B3B — the dark logo background + outlines - * Gated on TTY + NO_COLOR so piped / CI output stays plain. Falls back to - * kleur's 16-color cyan when the terminal isn't truecolor. - */ -const USE_ANSI = Boolean(process.stdout.isTTY) && !process.env.NO_COLOR; -const TRUECOLOR = - USE_ANSI && - (process.env.COLORTERM === 'truecolor' || process.env.COLORTERM === '24bit'); - -const brand = (s: string): string => { - if (!USE_ANSI) return s; - if (TRUECOLOR) return `\x1b[38;2;43;183;206m${s}\x1b[0m`; - return k.cyan(s); -}; -const brandBold = (s: string): string => { - if (!USE_ANSI) return s; - if (TRUECOLOR) return `\x1b[1;38;2;43;183;206m${s}\x1b[0m`; - return k.bold(k.cyan(s)); -}; -const brandChip = (s: string): string => { - if (!USE_ANSI) return s; - if (TRUECOLOR) { - return `\x1b[48;2;43;183;206m\x1b[38;2;23;27;59m\x1b[1m${s}\x1b[0m`; - } - return k.bgCyan(k.black(k.bold(s))); -}; - -type Fields = Record; -type Block = { type: string; fields: Fields }; -type StepResult = { - ok: boolean; - exitCode: number; - blocks: Block[]; - transcript: string; - /** The last block matching `stepName.toUpperCase()` if any. */ - terminal: Block | null; -}; - -/** - * Streaming parser for `=== NANOCLAW SETUP: TYPE ===` blocks. Emits each - * block as it closes so the UI can react mid-stream (e.g. render a pairing - * code card as soon as pair-telegram emits it, rather than after the step - * has finished). - */ -class StatusStream { - private lineBuf = ''; - private current: Block | null = null; - readonly blocks: Block[] = []; - transcript = ''; - - constructor(private readonly onBlock: (block: Block) => void) {} - - write(chunk: string): void { - this.transcript += chunk; - this.lineBuf += chunk; - let idx: number; - while ((idx = this.lineBuf.indexOf('\n')) !== -1) { - const line = this.lineBuf.slice(0, idx); - this.lineBuf = this.lineBuf.slice(idx + 1); - this.processLine(line); - } - } - - private processLine(line: string): void { - const start = line.match(/^=== NANOCLAW SETUP: (\S+) ===/); - if (start) { - this.current = { type: start[1], fields: {} }; - return; - } - if (line.startsWith('=== END ===')) { - if (this.current) { - this.blocks.push(this.current); - this.onBlock(this.current); - this.current = null; - } - return; - } - if (!this.current) return; - const colon = line.indexOf(':'); - if (colon === -1) return; - const key = line.slice(0, colon).trim(); - const value = line.slice(colon + 1).trim(); - if (key) this.current.fields[key] = value; - } -} - -/** - * Spawn a setup step as a child process. Output is tee'd to the provided - * raw log file (level 3) and parsed for status blocks (level 2 summary). - * The onBlock callback fires per status block as they close so the UI can - * react mid-stream. - */ -function spawnStep( - stepName: string, - extra: string[], - onBlock: (block: Block) => void, - rawLogPath: string, -): Promise { - return new Promise((resolve) => { - const args = ['exec', 'tsx', 'setup/index.ts', '--step', stepName]; - if (extra.length > 0) args.push('--', ...extra); - - const child = spawn('pnpm', args, { stdio: ['ignore', 'pipe', 'pipe'] }); - const stream = new StatusStream(onBlock); - const raw = fs.createWriteStream(rawLogPath, { flags: 'w' }); - raw.write(`# ${stepName} — ${new Date().toISOString()}\n\n`); - - child.stdout.on('data', (chunk: Buffer) => { - stream.write(chunk.toString('utf-8')); - raw.write(chunk); - }); - child.stderr.on('data', (chunk: Buffer) => { - stream.transcript += chunk.toString('utf-8'); - raw.write(chunk); - }); - - child.on('close', (code) => { - raw.end(); - // Step block types don't always mirror step names (e.g. `mounts` emits - // CONFIGURE_MOUNTS, `container` emits SETUP_CONTAINER). Any block with - // a STATUS field is a terminal block; the last one wins. - const terminal = - [...stream.blocks].reverse().find((b) => b.fields.STATUS) ?? null; - const status = terminal?.fields.STATUS; - const ok = code === 0 && (status === 'success' || status === 'skipped'); - resolve({ - ok, - exitCode: code ?? 1, - blocks: stream.blocks, - transcript: stream.transcript, - terminal, - }); - }); - }); -} - -type SpinnerLabels = { - running: string; - done: string; - skipped?: string; - failed?: string; -}; - -/** Run a step under a clack spinner. Teed to a per-step raw log + progression entry at the end. */ -async function runQuietStep( - stepName: string, - labels: SpinnerLabels, - extra: string[] = [], -): Promise { - failingStep = stepName; - const rawLog = setupLog.stepRawLog(stepName); - const start = Date.now(); - const result = await runUnderSpinner(labels, () => - spawnStep(stepName, extra, () => {}, rawLog), - ); - const durationMs = Date.now() - start; - writeStepEntry(stepName, result, durationMs, rawLog); - return { ...result, rawLog, durationMs }; -} - -/** Run an arbitrary child under a spinner. Same raw-log + progression treatment as runQuietStep. */ -async function runQuietChild( - logName: string, - cmd: string, - args: string[], - labels: SpinnerLabels, - opts?: { - /** Extra fields to merge into the progression entry (on top of any status-block fields). */ - extraFields?: Record; - /** Environment overrides to pass to the child process. */ - env?: NodeJS.ProcessEnv; - }, -): Promise<{ - ok: boolean; - exitCode: number; - transcript: string; - terminal: Block | null; - rawLog: string; - durationMs: number; -}> { - failingStep = logName; - const rawLog = setupLog.stepRawLog(logName); - const start = Date.now(); - const result = await runUnderSpinner(labels, () => - spawnQuiet(cmd, args, rawLog, opts?.env), - ); - const durationMs = Date.now() - start; - - const blockFields = summariseTerminalFields(result.terminal); - const fields = { ...blockFields, ...(opts?.extraFields ?? {}) }; - const rawStatus = result.terminal?.fields.STATUS; - const status: 'success' | 'skipped' | 'failed' = !result.ok - ? 'failed' - : rawStatus === 'skipped' - ? 'skipped' - : 'success'; - setupLog.step(logName, status, durationMs, fields, rawLog); - return { ...result, rawLog, durationMs }; -} - -/** Turn a step's terminal-block fields into a concise progression-log entry. */ -function writeStepEntry( - stepName: string, - result: StepResult, - durationMs: number, - rawLog: string, -): void { - const rawStatus = result.terminal?.fields.STATUS; - const logStatus: 'success' | 'skipped' | 'failed' = !result.ok - ? 'failed' - : rawStatus === 'skipped' - ? 'skipped' - : 'success'; - const fields = summariseTerminalFields(result.terminal); - setupLog.step(stepName, logStatus, durationMs, fields, rawLog); -} - -/** Strip STATUS + LOG (redundant) and any oversize values from the terminal block's fields. */ -function summariseTerminalFields(block: Block | null): Record { - if (!block) return {}; - const out: Record = {}; - for (const [k, v] of Object.entries(block.fields)) { - if (k === 'STATUS' || k === 'LOG') continue; - if (v.length > 120) continue; // keep it skimmable; full value lives in the raw log - out[k] = v; - } - return out; -} - -async function runUnderSpinner< - T extends { ok: boolean; transcript: string; terminal?: Block | null }, ->( - labels: SpinnerLabels, - work: () => Promise, -): Promise { - const s = p.spinner(); - const start = Date.now(); - s.start(labels.running); - const tick = setInterval(() => { - const elapsed = Math.round((Date.now() - start) / 1000); - s.message(`${labels.running} ${k.dim(`(${elapsed}s)`)}`); - }, 1000); - - const result = await work(); - - clearInterval(tick); - const elapsed = Math.round((Date.now() - start) / 1000); - if (result.ok) { - const isSkipped = result.terminal?.fields.STATUS === 'skipped'; - const msg = isSkipped && labels.skipped ? labels.skipped : labels.done; - s.stop(`${msg} ${k.dim(`(${elapsed}s)`)}`); - } else { - const failMsg = labels.failed ?? labels.running.replace(/…$/, ' failed'); - s.stop(`${failMsg} ${k.dim(`(${elapsed}s)`)}`, 1); - dumpTranscriptOnFailure(result.transcript); - } - return result; -} - -function spawnQuiet( - cmd: string, - args: string[], - rawLogPath: string, - envOverride?: NodeJS.ProcessEnv, -): Promise<{ ok: boolean; exitCode: number; transcript: string; terminal: Block | null; blocks: Block[] }> { - return new Promise((resolve) => { - const child = spawn(cmd, args, { - stdio: ['ignore', 'pipe', 'pipe'], - env: envOverride ? { ...process.env, ...envOverride } : process.env, - }); - let transcript = ''; - const raw = fs.createWriteStream(rawLogPath, { flags: 'w' }); - raw.write(`# ${[cmd, ...args].join(' ')} — ${new Date().toISOString()}\n\n`); - const blocks: Block[] = []; - const stream = new StatusStream((b) => blocks.push(b)); - child.stdout.on('data', (c: Buffer) => { - const s = c.toString('utf-8'); - transcript += s; - stream.write(s); - raw.write(c); - }); - child.stderr.on('data', (c: Buffer) => { - transcript += c.toString('utf-8'); - raw.write(c); - }); - child.on('close', (code) => { - raw.end(); - const terminal = - [...blocks].reverse().find((b) => b.fields.STATUS) ?? null; - resolve({ ok: code === 0, exitCode: code ?? 1, transcript, terminal, blocks }); - }); - }); -} - -function dumpTranscriptOnFailure(transcript: string): void { - const lines = transcript.split('\n').filter((l) => { - if (l.startsWith('=== NANOCLAW SETUP:')) return false; - if (l.startsWith('=== END ===')) return false; - return true; - }); - const tail = lines.slice(-40).join('\n').trimEnd(); - if (tail) { - console.log(); - console.log(k.dim(tail)); - console.log(); - } -} - -function fail(msg: string, hint?: string): never { - setupLog.abort(failingStep, msg); - p.log.error(msg); - if (hint) p.log.message(k.dim(hint)); - p.log.message(k.dim('Logs: logs/setup.log · Raw: logs/setup-steps/')); - p.cancel('Setup aborted.'); - process.exit(1); -} - -function ensureAnswer(value: T | symbol): T { - if (p.isCancel(value)) { - setupLog.abort(failingStep, 'user-cancelled'); - p.cancel('Setup cancelled.'); - process.exit(0); - } - return value as T; -} - -/** - * After installing Docker, this process's supplementary groups are still - * frozen from login — subsequent steps that talk to /var/run/docker.sock - * (onecli install, service start, …) fail with EACCES even though the - * daemon is up. Detect that and re-exec the whole driver under `sg docker` - * so the rest of the run inherits the docker group without a re-login. - */ -function maybeReexecUnderSg(): void { - if (process.env.NANOCLAW_REEXEC_SG === '1') return; - if (process.platform !== 'linux') return; - const info = spawnSync('docker', ['info'], { encoding: 'utf-8' }); - if (info.status === 0) return; - const err = `${info.stderr ?? ''}\n${info.stdout ?? ''}`; - if (!/permission denied/i.test(err)) return; - if (spawnSync('which', ['sg'], { stdio: 'ignore' }).status !== 0) return; - - p.log.warn('Docker socket not accessible in current group — re-executing under `sg docker`.'); - const res = spawnSync('sg', ['docker', '-c', 'pnpm run setup:auto'], { - stdio: 'inherit', - env: { ...process.env, NANOCLAW_REEXEC_SG: '1' }, - }); - process.exit(res.status ?? 1); -} - -function anthropicSecretExists(): boolean { - try { - const res = spawnSync('onecli', ['secrets', 'list'], { - encoding: 'utf-8', - stdio: ['ignore', 'pipe', 'pipe'], - }); - if (res.status !== 0) return false; - return /anthropic/i.test(res.stdout ?? ''); - } catch { - return false; - } -} - -function runInheritScript(cmd: string, args: string[]): Promise { - return new Promise((resolve) => { - const child = spawn(cmd, args, { stdio: 'inherit' }); - child.on('close', (code) => resolve(code ?? 1)); - }); -} - -function formatCodeCard(code: string): string { - const spaced = code.split('').join(' '); - return [ - '', - ` ${brandBold(spaced)}`, - '', - k.dim(' Send these digits from Telegram to your bot.'), - ].join('\n'); -} - -async function runPairTelegram(): Promise { - failingStep = 'pair-telegram'; - const rawLog = setupLog.stepRawLog('pair-telegram'); - const start = Date.now(); - const s = p.spinner(); - s.start('Creating pairing code…'); - let spinnerActive = true; - - const stopSpinner = (msg: string, code?: number) => { - if (spinnerActive) { - s.stop(msg, code); - spinnerActive = false; - } - }; - - const result = await spawnStep( - 'pair-telegram', - ['--intent', 'main'], - (block) => { - if (block.type === 'PAIR_TELEGRAM_CODE') { - const reason = block.fields.REASON ?? 'initial'; - if (reason === 'initial') { - stopSpinner('Pairing code ready.'); - } else { - stopSpinner('Previous code invalidated. New code below.'); - } - p.note(formatCodeCard(block.fields.CODE ?? '????'), 'Pairing code'); - s.start('Waiting for the code from Telegram…'); - spinnerActive = true; - } else if (block.type === 'PAIR_TELEGRAM_ATTEMPT') { - stopSpinner(`Received "${block.fields.CANDIDATE ?? '?'}" — doesn't match.`); - s.start('Waiting for the correct code…'); - spinnerActive = true; - } else if (block.type === 'PAIR_TELEGRAM') { - if (block.fields.STATUS === 'success') { - stopSpinner('Telegram paired.'); - } else { - stopSpinner(`Pairing failed: ${block.fields.ERROR ?? 'unknown'}`, 1); - } - } - }, - rawLog, - ); - const durationMs = Date.now() - start; - - // Safety net: if the child died without emitting a terminal block, make - // sure we don't leave the spinner running. - if (spinnerActive) { - stopSpinner(result.ok ? 'Done.' : 'Pairing exited unexpectedly.', result.ok ? 0 : 1); - if (!result.ok) dumpTranscriptOnFailure(result.transcript); - } - - writeStepEntry('pair-telegram', result, durationMs, rawLog); - return { ...result, rawLog, durationMs }; -} - -async function askDisplayName(fallback: string): Promise { - const answer = ensureAnswer( - await p.text({ - message: 'What should your agents call you?', - placeholder: fallback, - defaultValue: fallback, - }), - ); - const value = (answer as string).trim() || fallback; - setupLog.userInput('display_name', value); - return value; -} - -async function askAgentName(fallback: string): Promise { - const answer = ensureAnswer( - await p.text({ - message: 'What should your messaging agent be called?', - placeholder: fallback, - defaultValue: fallback, - }), - ); - const value = (answer as string).trim() || fallback; - setupLog.userInput('agent_name', value); - return value; -} - -async function askChannelChoice(): Promise<'telegram' | 'skip'> { - const choice = ensureAnswer( - await p.select({ - message: 'Connect a messaging app so you can chat from your phone?', - options: [ - { value: 'telegram', label: 'Telegram', hint: 'recommended' }, - { value: 'skip', label: 'Skip — use the CLI only' }, - ], - }), - ); - setupLog.userInput('channel_choice', String(choice)); - return choice as 'telegram' | 'skip'; -} - -async function collectTelegramToken(): Promise { - p.note( - [ - '1. Open Telegram and message @BotFather', - '2. Send: /newbot', - '3. Follow the prompts (name + username ending in "bot")', - '4. Copy the token it gives you (format: :)', - '', - k.dim('Optional, but recommended for groups:'), - k.dim(' @BotFather → /mybots → Bot Settings → Group Privacy → OFF'), - ].join('\n'), - 'Create a Telegram bot', - ); - - const answer = ensureAnswer( - await p.password({ - message: 'Paste your bot token', - validate: (v) => { - if (!v || !v.trim()) return 'Token is required'; - if (!/^[0-9]+:[A-Za-z0-9_-]{35,}$/.test(v.trim())) { - return 'Format looks wrong — expected :'; - } - return undefined; - }, - }), - ); - const token = (answer as string).trim(); - setupLog.userInput( - 'telegram_token', - `${token.slice(0, 12)}…${token.slice(-4)}`, - ); - return token; -} - -async function validateTelegramToken(token: string): Promise { - failingStep = 'telegram-validate'; - const s = p.spinner(); - const start = Date.now(); - s.start('Validating token with Telegram…'); - try { - const res = await fetch(`https://api.telegram.org/bot${token}/getMe`); - const data = (await res.json()) as { - ok?: boolean; - result?: { username?: string; id?: number }; - description?: string; - }; - const elapsed = Math.round((Date.now() - start) / 1000); - if (data.ok && data.result?.username) { - const username = data.result.username; - s.stop(`Bot is @${username}. ${k.dim(`(${elapsed}s)`)}`); - setupLog.step( - 'telegram-validate', - 'success', - Date.now() - start, - { BOT_USERNAME: username, BOT_ID: data.result.id ?? '' }, - ); - return username; - } - const reason = data.description ?? 'token rejected by Telegram'; - s.stop(`Telegram rejected the token: ${reason}`, 1); - setupLog.step( - 'telegram-validate', - 'failed', - Date.now() - start, - { ERROR: reason }, - ); - fail( - 'Telegram rejected the token.', - 'Double-check the token (copy it again from @BotFather) and retry.', - ); - } catch (err) { - const elapsed = Math.round((Date.now() - start) / 1000); - s.stop(`Could not reach Telegram. ${k.dim(`(${elapsed}s)`)}`, 1); - const message = err instanceof Error ? err.message : String(err); - setupLog.step('telegram-validate', 'failed', Date.now() - start, { - ERROR: message, - }); - fail( - 'Telegram API unreachable.', - 'Check your network connection and retry.', - ); - } -} - -function printIntro(): void { - const isReexec = process.env.NANOCLAW_REEXEC_SG === '1'; - const wordmark = `${k.bold('Nano')}${brandBold('Claw')}`; - - if (isReexec) { - p.intro(`${brandChip(' setup:auto ')} ${wordmark} ${k.dim('· resuming under docker group')}`); - return; - } - - console.log(); - console.log(` ${wordmark}`); - console.log(` ${k.dim('end-to-end scripted setup of your personal assistant')}`); - p.intro(`${brandChip(' setup:auto ')}`); -} async function main(): Promise { printIntro(); @@ -629,11 +45,11 @@ async function main(): Promise { ); if (!skip.has('environment')) { - const res = await runQuietStep( - 'environment', - { running: 'Checking environment…', done: 'Environment OK.' }, - ); - if (!res.ok) fail('Environment check failed.'); + const res = await runQuietStep('environment', { + running: 'Checking environment…', + done: 'Environment OK.', + }); + if (!res.ok) fail('environment', 'Environment check failed.'); } if (!skip.has('container')) { @@ -646,17 +62,20 @@ async function main(): Promise { const err = res.terminal?.fields.ERROR; if (err === 'runtime_not_available') { fail( + 'container', 'Docker is not available and could not be started automatically.', 'Install Docker Desktop or start it manually, then retry.', ); } if (err === 'docker_group_not_active') { fail( + 'container', 'Docker was just installed but your shell is not yet in the `docker` group.', 'Log out and back in (or run `newgrp docker` in a new shell), then retry.', ); } fail( + 'container', 'Container build/test failed.', 'For stale cache: `docker builder prune -f`, then retry `pnpm run setup:auto`.', ); @@ -673,11 +92,13 @@ async function main(): Promise { const err = res.terminal?.fields.ERROR; if (err === 'onecli_not_on_path_after_install') { fail( + 'onecli', 'OneCLI installed but not on PATH.', 'Open a new shell or run `export PATH="$HOME/.local/bin:$PATH"`, then retry.', ); } fail( + 'onecli', `OneCLI install failed (${err ?? 'unknown'}).`, 'Check that curl + a writable ~/.local/bin are available, then retry.', ); @@ -685,7 +106,6 @@ async function main(): Promise { } if (!skip.has('auth')) { - failingStep = 'auth'; if (anthropicSecretExists()) { p.log.success('OneCLI already has an Anthropic secret — skipping.'); setupLog.step('auth', 'skipped', 0, { REASON: 'secret-already-present' }); @@ -702,22 +122,29 @@ async function main(): Promise { if (code !== 0) { setupLog.step('auth', 'failed', durationMs, { EXIT_CODE: code }); fail( + 'auth', 'Anthropic credential registration failed or was aborted.', 'Re-run `bash setup/register-claude-token.sh` or handle via `/setup` §4.', ); } - setupLog.step('auth', 'interactive', durationMs, { METHOD: 'register-claude-token.sh' }); + setupLog.step('auth', 'interactive', durationMs, { + METHOD: 'register-claude-token.sh', + }); p.log.success('Anthropic credential registered with OneCLI.'); } } if (!skip.has('mounts')) { - const res = await runQuietStep('mounts', { - running: 'Writing mount allowlist…', - done: 'Mount allowlist in place.', - skipped: 'Mount allowlist already configured.', - }, ['--empty']); - if (!res.ok) fail('Mount allowlist step failed.'); + const res = await runQuietStep( + 'mounts', + { + running: 'Writing mount allowlist…', + done: 'Mount allowlist in place.', + skipped: 'Mount allowlist already configured.', + }, + ['--empty'], + ); + if (!res.ok) fail('mounts', 'Mount allowlist step failed.'); } if (!skip.has('service')) { @@ -727,6 +154,7 @@ async function main(): Promise { }); if (!res.ok) { fail( + 'service', 'Service install failed.', 'Check logs/nanoclaw.error.log, or run `/setup` to iterate interactively.', ); @@ -761,6 +189,7 @@ async function main(): Promise { ); if (!res.ok) { fail( + 'cli-agent', 'CLI agent wiring failed.', `Re-run \`pnpm exec tsx scripts/init-cli-agent.ts --display-name "${displayName!}" --agent-name "${CLI_AGENT_NAME}"\` to fix.`, ); @@ -770,75 +199,7 @@ async function main(): Promise { if (!skip.has('channel')) { const choice = await askChannelChoice(); if (choice === 'telegram') { - const token = await collectTelegramToken(); - const botUsername = await validateTelegramToken(token); - - const install = await runQuietChild( - 'telegram-install', - 'bash', - ['setup/add-telegram.sh'], - { - running: `Installing Telegram adapter and wiring @${botUsername}…`, - done: `Telegram adapter ready.`, - }, - { - env: { TELEGRAM_BOT_TOKEN: token }, - extraFields: { BOT_USERNAME: botUsername }, - }, - ); - if (!install.ok) { - fail( - 'Telegram install failed.', - 'Check the raw log under logs/setup-steps/, then retry `pnpm run setup:auto`.', - ); - } - - const pair = await runPairTelegram(); - if (!pair.ok) { - fail( - 'Telegram pairing failed.', - 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main`.', - ); - } - - const platformId = pair.terminal?.fields.PLATFORM_ID; - const pairedUserId = pair.terminal?.fields.PAIRED_USER_ID; - if (!platformId || !pairedUserId) { - fail( - 'pair-telegram succeeded but did not return PLATFORM_ID and PAIRED_USER_ID.', - 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main` and capture the success block.', - ); - } - - const agentName = - process.env.NANOCLAW_AGENT_NAME?.trim() || - (await askAgentName(DEFAULT_AGENT_NAME)); - - const init = await runQuietChild( - 'init-first-agent', - 'pnpm', - [ - 'exec', 'tsx', 'scripts/init-first-agent.ts', - '--channel', 'telegram', - '--user-id', pairedUserId, - '--platform-id', platformId, - '--display-name', displayName!, - '--agent-name', agentName, - ], - { - running: `Wiring ${agentName} to your Telegram chat…`, - done: `${agentName} is wired — welcome DM incoming.`, - }, - { - extraFields: { CHANNEL: 'telegram', AGENT_NAME: agentName, PLATFORM_ID: platformId }, - }, - ); - if (!init.ok) { - fail( - 'Wiring the Telegram agent failed.', - `Re-run \`pnpm exec tsx scripts/init-first-agent.ts --channel telegram --user-id "${pairedUserId}" --platform-id "${platformId}" --display-name "${displayName!}" --agent-name "${agentName}"\`.`, - ); - } + await runTelegramChannel(displayName!); } else { p.log.info('No messaging channel wired — you can add one later with `/add-`.'); } @@ -883,6 +244,98 @@ async function main(): Promise { p.outro(k.green('Setup complete.')); } +// ─── prompts owned by the sequencer ──────────────────────────────────── + +async function askDisplayName(fallback: string): Promise { + const answer = ensureAnswer( + await p.text({ + message: 'What should your agents call you?', + placeholder: fallback, + defaultValue: fallback, + }), + ); + const value = (answer as string).trim() || fallback; + setupLog.userInput('display_name', value); + return value; +} + +async function askChannelChoice(): Promise<'telegram' | 'skip'> { + const choice = ensureAnswer( + await p.select({ + message: 'Connect a messaging app so you can chat from your phone?', + options: [ + { value: 'telegram', label: 'Telegram', hint: 'recommended' }, + { value: 'skip', label: 'Skip — use the CLI only' }, + ], + }), + ); + setupLog.userInput('channel_choice', String(choice)); + return choice as 'telegram' | 'skip'; +} + +// ─── interactive / env helpers ───────────────────────────────────────── + +function anthropicSecretExists(): boolean { + try { + const res = spawnSync('onecli', ['secrets', 'list'], { + encoding: 'utf-8', + stdio: ['ignore', 'pipe', 'pipe'], + }); + if (res.status !== 0) return false; + return /anthropic/i.test(res.stdout ?? ''); + } catch { + return false; + } +} + +function runInheritScript(cmd: string, args: string[]): Promise { + return new Promise((resolve) => { + const child = spawn(cmd, args, { stdio: 'inherit' }); + child.on('close', (code) => resolve(code ?? 1)); + }); +} + +/** + * After installing Docker, this process's supplementary groups are still + * frozen from login — subsequent steps that talk to /var/run/docker.sock + * (onecli install, service start, …) fail with EACCES even though the + * daemon is up. Detect that and re-exec the whole driver under `sg docker` + * so the rest of the run inherits the docker group without a re-login. + */ +function maybeReexecUnderSg(): void { + if (process.env.NANOCLAW_REEXEC_SG === '1') return; + if (process.platform !== 'linux') return; + const info = spawnSync('docker', ['info'], { encoding: 'utf-8' }); + if (info.status === 0) return; + const err = `${info.stderr ?? ''}\n${info.stdout ?? ''}`; + if (!/permission denied/i.test(err)) return; + if (spawnSync('which', ['sg'], { stdio: 'ignore' }).status !== 0) return; + + p.log.warn('Docker socket not accessible in current group — re-executing under `sg docker`.'); + const res = spawnSync('sg', ['docker', '-c', 'pnpm run setup:auto'], { + stdio: 'inherit', + env: { ...process.env, NANOCLAW_REEXEC_SG: '1' }, + }); + process.exit(res.status ?? 1); +} + +// ─── intro + progression-log init ────────────────────────────────────── + +function printIntro(): void { + const isReexec = process.env.NANOCLAW_REEXEC_SG === '1'; + const wordmark = `${k.bold('Nano')}${brandBold('Claw')}`; + + if (isReexec) { + p.intro(`${brandChip(' setup:auto ')} ${wordmark} ${k.dim('· resuming under docker group')}`); + return; + } + + console.log(); + console.log(` ${wordmark}`); + console.log(` ${k.dim('end-to-end scripted setup of your personal assistant')}`); + p.intro(`${brandChip(' setup:auto ')}`); +} + /** * Bootstrap (nanoclaw.sh) normally initializes logs/setup.log and writes * the bootstrap entry before we even boot. If someone runs `pnpm run diff --git a/setup/channels/telegram.ts b/setup/channels/telegram.ts new file mode 100644 index 000000000..d3e3f89e5 --- /dev/null +++ b/setup/channels/telegram.ts @@ -0,0 +1,277 @@ +/** + * Telegram channel flow for setup:auto. + * + * `runTelegramChannel(displayName)` owns the full branch from the + * BotFather instructions through the welcome DM: + * + * 1. BotFather instructions (clack note) + * 2. Paste the bot token (clack password) — format-validated + * 3. getMe via the Bot API to resolve the bot's username + * 4. Install the adapter (setup/add-telegram.sh, non-interactive) + * 5. Run the pair-telegram step, rendering code events as clack notes + * 6. Ask for the messaging-agent name (defaulting to "Nano") + * 7. Wire the agent via scripts/init-first-agent.ts + * + * All output obeys the three-level contract: clack UI for the user, + * structured entries in logs/setup.log, full raw output in per-step files + * under logs/setup-steps/. See docs/setup-flow.md. + */ +import * as p from '@clack/prompts'; +import k from 'kleur'; + +import * as setupLog from '../logs.js'; +import { + type Block, + type StepResult, + dumpTranscriptOnFailure, + ensureAnswer, + fail, + runQuietChild, + spawnStep, + writeStepEntry, +} from '../lib/runner.js'; +import { brandBold } from '../lib/theme.js'; + +const DEFAULT_AGENT_NAME = 'Nano'; + +export async function runTelegramChannel(displayName: string): Promise { + const token = await collectTelegramToken(); + const botUsername = await validateTelegramToken(token); + + const install = await runQuietChild( + 'telegram-install', + 'bash', + ['setup/add-telegram.sh'], + { + running: `Installing Telegram adapter and wiring @${botUsername}…`, + done: 'Telegram adapter ready.', + }, + { + env: { TELEGRAM_BOT_TOKEN: token }, + extraFields: { BOT_USERNAME: botUsername }, + }, + ); + if (!install.ok) { + fail( + 'telegram-install', + 'Telegram install failed.', + 'Check the raw log under logs/setup-steps/, then retry `pnpm run setup:auto`.', + ); + } + + const pair = await runPairTelegram(); + if (!pair.ok) { + fail( + 'pair-telegram', + 'Telegram pairing failed.', + 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main`.', + ); + } + + const platformId = pair.terminal?.fields.PLATFORM_ID; + const pairedUserId = pair.terminal?.fields.PAIRED_USER_ID; + if (!platformId || !pairedUserId) { + fail( + 'pair-telegram', + 'pair-telegram succeeded but did not return PLATFORM_ID and PAIRED_USER_ID.', + 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main` and capture the success block.', + ); + } + + const agentName = await resolveAgentName(); + + const init = await runQuietChild( + 'init-first-agent', + 'pnpm', + [ + 'exec', 'tsx', 'scripts/init-first-agent.ts', + '--channel', 'telegram', + '--user-id', pairedUserId, + '--platform-id', platformId, + '--display-name', displayName, + '--agent-name', agentName, + ], + { + running: `Wiring ${agentName} to your Telegram chat…`, + done: `${agentName} is wired — welcome DM incoming.`, + }, + { + extraFields: { CHANNEL: 'telegram', AGENT_NAME: agentName, PLATFORM_ID: platformId }, + }, + ); + if (!init.ok) { + fail( + 'init-first-agent', + 'Wiring the Telegram agent failed.', + `Re-run \`pnpm exec tsx scripts/init-first-agent.ts --channel telegram --user-id "${pairedUserId}" --platform-id "${platformId}" --display-name "${displayName}" --agent-name "${agentName}"\`.`, + ); + } +} + +async function collectTelegramToken(): Promise { + p.note( + [ + '1. Open Telegram and message @BotFather', + '2. Send: /newbot', + '3. Follow the prompts (name + username ending in "bot")', + '4. Copy the token it gives you (format: :)', + '', + k.dim('Optional, but recommended for groups:'), + k.dim(' @BotFather → /mybots → Bot Settings → Group Privacy → OFF'), + ].join('\n'), + 'Create a Telegram bot', + ); + + const answer = ensureAnswer( + await p.password({ + message: 'Paste your bot token', + validate: (v) => { + if (!v || !v.trim()) return 'Token is required'; + if (!/^[0-9]+:[A-Za-z0-9_-]{35,}$/.test(v.trim())) { + return 'Format looks wrong — expected :'; + } + return undefined; + }, + }), + ); + const token = (answer as string).trim(); + setupLog.userInput( + 'telegram_token', + `${token.slice(0, 12)}…${token.slice(-4)}`, + ); + return token; +} + +async function validateTelegramToken(token: string): Promise { + const s = p.spinner(); + const start = Date.now(); + s.start('Validating token with Telegram…'); + try { + const res = await fetch(`https://api.telegram.org/bot${token}/getMe`); + const data = (await res.json()) as { + ok?: boolean; + result?: { username?: string; id?: number }; + description?: string; + }; + const elapsedS = Math.round((Date.now() - start) / 1000); + if (data.ok && data.result?.username) { + const username = data.result.username; + s.stop(`Bot is @${username}. ${k.dim(`(${elapsedS}s)`)}`); + setupLog.step('telegram-validate', 'success', Date.now() - start, { + BOT_USERNAME: username, + BOT_ID: data.result.id ?? '', + }); + return username; + } + const reason = data.description ?? 'token rejected by Telegram'; + s.stop(`Telegram rejected the token: ${reason}`, 1); + setupLog.step('telegram-validate', 'failed', Date.now() - start, { + ERROR: reason, + }); + fail( + 'telegram-validate', + 'Telegram rejected the token.', + 'Double-check the token (copy it again from @BotFather) and retry.', + ); + } catch (err) { + const elapsedS = Math.round((Date.now() - start) / 1000); + s.stop(`Could not reach Telegram. ${k.dim(`(${elapsedS}s)`)}`, 1); + const message = err instanceof Error ? err.message : String(err); + setupLog.step('telegram-validate', 'failed', Date.now() - start, { + ERROR: message, + }); + fail( + 'telegram-validate', + 'Telegram API unreachable.', + 'Check your network connection and retry.', + ); + } +} + +async function runPairTelegram(): Promise< + StepResult & { rawLog: string; durationMs: number } +> { + const rawLog = setupLog.stepRawLog('pair-telegram'); + const start = Date.now(); + const s = p.spinner(); + s.start('Creating pairing code…'); + let spinnerActive = true; + + const stopSpinner = (msg: string, code?: number) => { + if (spinnerActive) { + s.stop(msg, code); + spinnerActive = false; + } + }; + + const result = await spawnStep( + 'pair-telegram', + ['--intent', 'main'], + (block: Block) => { + if (block.type === 'PAIR_TELEGRAM_CODE') { + const reason = block.fields.REASON ?? 'initial'; + if (reason === 'initial') { + stopSpinner('Pairing code ready.'); + } else { + stopSpinner('Previous code invalidated. New code below.'); + } + p.note(formatCodeCard(block.fields.CODE ?? '????'), 'Pairing code'); + s.start('Waiting for the code from Telegram…'); + spinnerActive = true; + } else if (block.type === 'PAIR_TELEGRAM_ATTEMPT') { + stopSpinner(`Received "${block.fields.CANDIDATE ?? '?'}" — doesn't match.`); + s.start('Waiting for the correct code…'); + spinnerActive = true; + } else if (block.type === 'PAIR_TELEGRAM') { + if (block.fields.STATUS === 'success') { + stopSpinner('Telegram paired.'); + } else { + stopSpinner(`Pairing failed: ${block.fields.ERROR ?? 'unknown'}`, 1); + } + } + }, + rawLog, + ); + const durationMs = Date.now() - start; + + // Safety net: if the child died without emitting a terminal block, make + // sure we don't leave the spinner running. + if (spinnerActive) { + stopSpinner( + result.ok ? 'Done.' : 'Pairing exited unexpectedly.', + result.ok ? 0 : 1, + ); + if (!result.ok) dumpTranscriptOnFailure(result.transcript); + } + + writeStepEntry('pair-telegram', result, durationMs, rawLog); + return { ...result, rawLog, durationMs }; +} + +function formatCodeCard(code: string): string { + const spaced = code.split('').join(' '); + return [ + '', + ` ${brandBold(spaced)}`, + '', + k.dim(' Send these digits from Telegram to your bot.'), + ].join('\n'); +} + +async function resolveAgentName(): Promise { + const preset = process.env.NANOCLAW_AGENT_NAME?.trim(); + if (preset) { + setupLog.userInput('agent_name', preset); + return preset; + } + const answer = ensureAnswer( + await p.text({ + message: 'What should your messaging agent be called?', + placeholder: DEFAULT_AGENT_NAME, + defaultValue: DEFAULT_AGENT_NAME, + }), + ); + const value = (answer as string).trim() || DEFAULT_AGENT_NAME; + setupLog.userInput('agent_name', value); + return value; +} diff --git a/setup/lib/runner.ts b/setup/lib/runner.ts new file mode 100644 index 000000000..59b3da6bc --- /dev/null +++ b/setup/lib/runner.ts @@ -0,0 +1,325 @@ +/** + * Step runner + abort helpers for setup:auto. + * + * Responsibilities: + * - Stream-parse setup-step status blocks (`=== NANOCLAW SETUP: … ===`) + * - Spawn children with output tee'd to a per-step raw log (level 3) + * - Wrap each run in a clack spinner with live elapsed time (level 1) + * - Append a structured entry to the progression log (level 2) via + * `setup/logs.ts` when the run ends + * - Abort helpers (`fail`, `ensureAnswer`) used by step orchestrators + * + * See docs/setup-flow.md for the three-level output contract. + */ +import { spawn } from 'child_process'; +import fs from 'fs'; + +import * as p from '@clack/prompts'; +import k from 'kleur'; + +import * as setupLog from '../logs.js'; + +export type Fields = Record; +export type Block = { type: string; fields: Fields }; + +export type StepResult = { + ok: boolean; + exitCode: number; + blocks: Block[]; + transcript: string; + /** The last block with a STATUS field (the terminal/result block). */ + terminal: Block | null; +}; + +export type QuietChildResult = { + ok: boolean; + exitCode: number; + transcript: string; + terminal: Block | null; + blocks: Block[]; +}; + +export type SpinnerLabels = { + running: string; + done: string; + skipped?: string; + failed?: string; +}; + +/** + * Streaming parser for `=== NANOCLAW SETUP: TYPE ===` blocks. Emits each + * block as it closes so the UI can react mid-stream (e.g. render a pairing + * code card as soon as pair-telegram emits it, rather than after the step + * has finished). + */ +export class StatusStream { + private lineBuf = ''; + private current: Block | null = null; + readonly blocks: Block[] = []; + transcript = ''; + + constructor(private readonly onBlock: (block: Block) => void) {} + + write(chunk: string): void { + this.transcript += chunk; + this.lineBuf += chunk; + let idx: number; + while ((idx = this.lineBuf.indexOf('\n')) !== -1) { + const line = this.lineBuf.slice(0, idx); + this.lineBuf = this.lineBuf.slice(idx + 1); + this.processLine(line); + } + } + + private processLine(line: string): void { + const start = line.match(/^=== NANOCLAW SETUP: (\S+) ===/); + if (start) { + this.current = { type: start[1], fields: {} }; + return; + } + if (line.startsWith('=== END ===')) { + if (this.current) { + this.blocks.push(this.current); + this.onBlock(this.current); + this.current = null; + } + return; + } + if (!this.current) return; + const colon = line.indexOf(':'); + if (colon === -1) return; + const key = line.slice(0, colon).trim(); + const value = line.slice(colon + 1).trim(); + if (key) this.current.fields[key] = value; + } +} + +/** + * Spawn a setup step as a child process. Output is tee'd to the provided + * raw log file (level 3) and parsed for status blocks (level 2 summary). + * The onBlock callback fires per status block as they close so the UI can + * react mid-stream. + */ +export function spawnStep( + stepName: string, + extra: string[], + onBlock: (block: Block) => void, + rawLogPath: string, +): Promise { + return new Promise((resolve) => { + const args = ['exec', 'tsx', 'setup/index.ts', '--step', stepName]; + if (extra.length > 0) args.push('--', ...extra); + + const child = spawn('pnpm', args, { stdio: ['ignore', 'pipe', 'pipe'] }); + const stream = new StatusStream(onBlock); + const raw = fs.createWriteStream(rawLogPath, { flags: 'w' }); + raw.write(`# ${stepName} — ${new Date().toISOString()}\n\n`); + + child.stdout.on('data', (chunk: Buffer) => { + stream.write(chunk.toString('utf-8')); + raw.write(chunk); + }); + child.stderr.on('data', (chunk: Buffer) => { + stream.transcript += chunk.toString('utf-8'); + raw.write(chunk); + }); + + child.on('close', (code) => { + raw.end(); + const terminal = + [...stream.blocks].reverse().find((b) => b.fields.STATUS) ?? null; + const status = terminal?.fields.STATUS; + const ok = code === 0 && (status === 'success' || status === 'skipped'); + resolve({ + ok, + exitCode: code ?? 1, + blocks: stream.blocks, + transcript: stream.transcript, + terminal, + }); + }); + }); +} + +export function spawnQuiet( + cmd: string, + args: string[], + rawLogPath: string, + envOverride?: NodeJS.ProcessEnv, +): Promise { + return new Promise((resolve) => { + const child = spawn(cmd, args, { + stdio: ['ignore', 'pipe', 'pipe'], + env: envOverride ? { ...process.env, ...envOverride } : process.env, + }); + let transcript = ''; + const raw = fs.createWriteStream(rawLogPath, { flags: 'w' }); + raw.write(`# ${[cmd, ...args].join(' ')} — ${new Date().toISOString()}\n\n`); + const blocks: Block[] = []; + const stream = new StatusStream((b) => blocks.push(b)); + child.stdout.on('data', (c: Buffer) => { + const s = c.toString('utf-8'); + transcript += s; + stream.write(s); + raw.write(c); + }); + child.stderr.on('data', (c: Buffer) => { + transcript += c.toString('utf-8'); + raw.write(c); + }); + child.on('close', (code) => { + raw.end(); + const terminal = + [...blocks].reverse().find((b) => b.fields.STATUS) ?? null; + resolve({ ok: code === 0, exitCode: code ?? 1, transcript, terminal, blocks }); + }); + }); +} + +/** Run a step under a clack spinner. Teed to a per-step raw log + progression entry at the end. */ +export async function runQuietStep( + stepName: string, + labels: SpinnerLabels, + extra: string[] = [], +): Promise { + const rawLog = setupLog.stepRawLog(stepName); + const start = Date.now(); + const result = await runUnderSpinner(labels, () => + spawnStep(stepName, extra, () => {}, rawLog), + ); + const durationMs = Date.now() - start; + writeStepEntry(stepName, result, durationMs, rawLog); + return { ...result, rawLog, durationMs }; +} + +/** Run an arbitrary child under a spinner. Same raw-log + progression treatment as runQuietStep. */ +export async function runQuietChild( + logName: string, + cmd: string, + args: string[], + labels: SpinnerLabels, + opts?: { + /** Extra fields to merge into the progression entry (on top of any status-block fields). */ + extraFields?: Record; + /** Environment overrides to pass to the child process. */ + env?: NodeJS.ProcessEnv; + }, +): Promise { + const rawLog = setupLog.stepRawLog(logName); + const start = Date.now(); + const result = await runUnderSpinner(labels, () => + spawnQuiet(cmd, args, rawLog, opts?.env), + ); + const durationMs = Date.now() - start; + + const blockFields = summariseTerminalFields(result.terminal); + const fields = { ...blockFields, ...(opts?.extraFields ?? {}) }; + const rawStatus = result.terminal?.fields.STATUS; + const status: 'success' | 'skipped' | 'failed' = !result.ok + ? 'failed' + : rawStatus === 'skipped' + ? 'skipped' + : 'success'; + setupLog.step(logName, status, durationMs, fields, rawLog); + return { ...result, rawLog, durationMs }; +} + +/** Turn a step's terminal-block fields into a concise progression-log entry. */ +export function writeStepEntry( + stepName: string, + result: StepResult, + durationMs: number, + rawLog: string, +): void { + const rawStatus = result.terminal?.fields.STATUS; + const logStatus: 'success' | 'skipped' | 'failed' = !result.ok + ? 'failed' + : rawStatus === 'skipped' + ? 'skipped' + : 'success'; + const fields = summariseTerminalFields(result.terminal); + setupLog.step(stepName, logStatus, durationMs, fields, rawLog); +} + +/** Strip STATUS + LOG (redundant) and any oversize values from the terminal block's fields. */ +export function summariseTerminalFields(block: Block | null): Record { + if (!block) return {}; + const out: Record = {}; + for (const [k, v] of Object.entries(block.fields)) { + if (k === 'STATUS' || k === 'LOG') continue; + if (v.length > 120) continue; // keep it skimmable; full value lives in the raw log + out[k] = v; + } + return out; +} + +async function runUnderSpinner< + T extends { ok: boolean; transcript: string; terminal?: Block | null }, +>( + labels: SpinnerLabels, + work: () => Promise, +): Promise { + const s = p.spinner(); + const start = Date.now(); + s.start(labels.running); + const tick = setInterval(() => { + const elapsed = Math.round((Date.now() - start) / 1000); + s.message(`${labels.running} ${k.dim(`(${elapsed}s)`)}`); + }, 1000); + + const result = await work(); + + clearInterval(tick); + const elapsed = Math.round((Date.now() - start) / 1000); + if (result.ok) { + const isSkipped = result.terminal?.fields.STATUS === 'skipped'; + const msg = isSkipped && labels.skipped ? labels.skipped : labels.done; + s.stop(`${msg} ${k.dim(`(${elapsed}s)`)}`); + } else { + const failMsg = labels.failed ?? labels.running.replace(/…$/, ' failed'); + s.stop(`${failMsg} ${k.dim(`(${elapsed}s)`)}`, 1); + dumpTranscriptOnFailure(result.transcript); + } + return result; +} + +export function dumpTranscriptOnFailure(transcript: string): void { + const lines = transcript.split('\n').filter((l) => { + if (l.startsWith('=== NANOCLAW SETUP:')) return false; + if (l.startsWith('=== END ===')) return false; + return true; + }); + const tail = lines.slice(-40).join('\n').trimEnd(); + if (tail) { + console.log(); + console.log(k.dim(tail)); + console.log(); + } +} + +/** + * Abort the setup run with a user-facing error, logging the abort to the + * progression log. Takes the step name explicitly so callers are clear + * about which step they're failing from — no hidden module state. + */ +export function fail(stepName: string, msg: string, hint?: string): never { + setupLog.abort(stepName, msg); + p.log.error(msg); + if (hint) p.log.message(k.dim(hint)); + p.log.message(k.dim('Logs: logs/setup.log · Raw: logs/setup-steps/')); + p.cancel('Setup aborted.'); + process.exit(1); +} + +/** + * Unwrap a clack prompt result. If the user cancelled (Ctrl-C / Esc), exit + * gracefully. Cancel is exit 0 — it's not an abort worth logging to the + * progression log, since the operator initiated it deliberately. + */ +export function ensureAnswer(value: T | symbol): T { + if (p.isCancel(value)) { + p.cancel('Setup cancelled.'); + process.exit(0); + } + return value as T; +} diff --git a/setup/lib/theme.ts b/setup/lib/theme.ts new file mode 100644 index 000000000..9bd18a560 --- /dev/null +++ b/setup/lib/theme.ts @@ -0,0 +1,39 @@ +/** + * NanoClaw brand palette for the terminal. + * + * Colors pulled from assets/nanoclaw-logo.png: + * brand cyan ≈ #2BB7CE — the "Claw" wordmark + mascot body + * brand navy ≈ #171B3B — the dark logo background + outlines + * + * Rendering gates: + * - No TTY (piped / redirected) → plain text, no ANSI + * - NO_COLOR set → plain text, no ANSI + * - COLORTERM truecolor/24bit → 24-bit ANSI (exact brand cyan) + * - Otherwise → kleur's 16-color cyan (closest fallback) + */ +import k from 'kleur'; + +const USE_ANSI = Boolean(process.stdout.isTTY) && !process.env.NO_COLOR; +const TRUECOLOR = + USE_ANSI && + (process.env.COLORTERM === 'truecolor' || process.env.COLORTERM === '24bit'); + +export function brand(s: string): string { + if (!USE_ANSI) return s; + if (TRUECOLOR) return `\x1b[38;2;43;183;206m${s}\x1b[0m`; + return k.cyan(s); +} + +export function brandBold(s: string): string { + if (!USE_ANSI) return s; + if (TRUECOLOR) return `\x1b[1;38;2;43;183;206m${s}\x1b[0m`; + return k.bold(k.cyan(s)); +} + +export function brandChip(s: string): string { + if (!USE_ANSI) return s; + if (TRUECOLOR) { + return `\x1b[48;2;43;183;206m\x1b[38;2;23;27;59m\x1b[1m${s}\x1b[0m`; + } + return k.bgCyan(k.black(k.bold(s))); +} From 7d2081660bec24db1e2c0bf577c2028b6c03ad73 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 02:57:20 +0300 Subject: [PATCH 92/95] feat(setup): rewrite copy for first-time users + split auth flow MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Content pass: every user-facing line is rewritten from the perspective of someone trying NanoClaw for the first time. Phase labels and devops framing are gone. Examples: "Environment OK" → "Your system looks good." "Container image ready" → "Sandbox ready." "OneCLI installed" → "OneCLI vault ready." "Anthropic credential" → "Claude account" "Mount allowlist in place" → "Access rules set." "Service installed/running" → "NanoClaw is running." "Wiring the terminal agent" → "Setting up your terminal chat…" "Setup complete" → "You're ready! Enjoy NanoClaw." Long-running steps get a one-sentence "why" that teaches a NanoClaw differentiator while the user waits: bootstrap → "NanoClaw is small and runs entirely on your machine. Yours to modify." container → "Your assistant lives in its own sandbox. It can only see what you explicitly share." onecli → "Your assistant never gets your API keys directly. The vault adds them to approved requests as they leave the sandbox." OneCLI is now named explicitly and framed as "your agent's vault" in the install step, the paste-auth save step, the subscription-auth banner, and their associated failure hints. Auth split (option b: explicit step name on fail): the auth-method choice moves from the bash menu in register-claude-token.sh into a clack select. Only the subscription path still breaks out to the interactive TTY for `claude setup-token`; paste-based OAuth tokens and API keys stay in clack via p.password() and register directly via `onecli secrets create`. register-claude-token.sh is scoped down to the subscription flow only. nanoclaw.sh: dropped the "Phase 1 / Phase 2" labels. The wordmark and subtitle now print bash-side so setup:auto skips repeating them and the flow reads as one continuous sequence. Bootstrap label is "Installing the basics" with a dim gutter-line "why" preamble. pnpm's `> nanoclaw@X setup:auto` preamble is suppressed via --silent. Em-dash pass on user-facing copy: every em-dash that functions as an em-dash in a user-visible string is replaced with period, semicolon, comma, or parens. Code comments and JSDoc are untouched. Co-Authored-By: Claude Opus 4.7 (1M context) --- nanoclaw.sh | 77 +++++---- setup/auto.ts | 286 +++++++++++++++++++++++---------- setup/channels/telegram.ts | 78 ++++----- setup/register-claude-token.sh | 154 +++++++----------- 4 files changed, 346 insertions(+), 249 deletions(-) diff --git a/nanoclaw.sh b/nanoclaw.sh index 17df82ce1..e94e383fe 100755 --- a/nanoclaw.sh +++ b/nanoclaw.sh @@ -1,15 +1,18 @@ #!/usr/bin/env bash # -# NanoClaw — scripted end-to-end install. +# NanoClaw — end-to-end setup entry point. # -# Phase 1: bootstrap (Node + pnpm + native module verify). Runs bash-side -# since tsx isn't available until pnpm install completes. -# Phase 2: setup:auto (all remaining steps under clack). +# Runs two parts from the user's perspective as one continuous flow: +# - bash-side: install the basics (Node + pnpm + native modules) under a +# bash-rendered clack-alike spinner. Can't use setup/auto.ts here since +# tsx isn't available until pnpm install completes. +# - hand off to `pnpm run setup:auto`, which renders the rest with +# @clack/prompts. The wordmark is printed once here so setup:auto can +# skip it and the flow reads as a single sequence. # -# Both phases obey the same three-level output contract (see -# docs/setup-flow.md): +# Obeys the three-level output contract (see docs/setup-flow.md): # 1. User-facing — concise status line with elapsed time -# 2. Progression log — logs/setup.log (header + one entry per phase/step) +# 2. Progression log — logs/setup.log (header + one entry per step) # 3. Raw per-step log — logs/setup-steps/NN-name.log (full verbatim output) # # Config via env — passed through unchanged: @@ -91,6 +94,19 @@ use_ansi() { [ -t 1 ] && [ -z "${NO_COLOR:-}" ]; } dim() { use_ansi && printf '\033[2m%s\033[0m' "$1" || printf '%s' "$1"; } gray() { use_ansi && printf '\033[90m%s\033[0m' "$1" || printf '%s' "$1"; } red() { use_ansi && printf '\033[31m%s\033[0m' "$1" || printf '%s' "$1"; } +bold() { use_ansi && printf '\033[1m%s\033[0m' "$1" || printf '%s' "$1"; } +# brand cyan (≈ #2BB7CE) — truecolor when supported, 16-color cyan fallback. +brand_bold() { + if use_ansi; then + if [ "${COLORTERM:-}" = "truecolor" ] || [ "${COLORTERM:-}" = "24bit" ]; then + printf '\033[1;38;2;43;183;206m%s\033[0m' "$1" + else + printf '\033[1;36m%s\033[0m' "$1" + fi + else + printf '%s' "$1" + fi +} clear_line() { use_ansi && printf '\r\033[2K' || printf '\n'; } spinner_start() { printf '%s %s…' "$(gray '◒')" "$1"; } @@ -105,21 +121,20 @@ rm -f "$PROGRESS_LOG" mkdir -p "$STEPS_DIR" "$LOGS_DIR" write_header -cat <<'EOF' -═══════════════════════════════════════════════════════════════ - NanoClaw scripted setup -═══════════════════════════════════════════════════════════════ +# NanoClaw wordmark + subtitle — setup:auto will see NANOCLAW_BOOTSTRAPPED=1 +# and skip printing these again, so the flow stays visually continuous. +printf '\n %s%s\n' "$(bold 'Nano')" "$(brand_bold 'Claw')" +printf ' %s\n\n' "$(dim 'Setting up your personal AI assistant')" -Phase 1 · bootstrap - -EOF - -# ─── phase 1: bootstrap ───────────────────────────────────────────────── +# ─── first step: install the basics (Node + pnpm + native modules) ───── BOOTSTRAP_RAW="${STEPS_DIR}/01-bootstrap.log" -BOOTSTRAP_LABEL="Bootstrapping Node, pnpm, native modules" +BOOTSTRAP_LABEL="Installing the basics" BOOTSTRAP_START=$(date +%s) +# One-line "why" that teaches a differentiator while the user waits. +printf '%s %s\n' "$(gray '│')" \ + "$(dim "NanoClaw is small and runs entirely on your machine. Yours to modify.")" spinner_start "$BOOTSTRAP_LABEL" # Run in the background so we can tick elapsed time. Capture exit code via @@ -151,10 +166,10 @@ rm -f "$BOOTSTRAP_EXIT_FILE" BOOTSTRAP_DUR=$(( $(date +%s) - BOOTSTRAP_START )) if [ "$BOOTSTRAP_RC" -eq 0 ]; then - spinner_success "Bootstrap complete" "$BOOTSTRAP_DUR" + spinner_success "Basics installed" "$BOOTSTRAP_DUR" write_bootstrap_entry success "$BOOTSTRAP_DUR" "$BOOTSTRAP_RAW" else - spinner_failure "Bootstrap failed" "$BOOTSTRAP_DUR" + spinner_failure "Couldn't install the basics" "$BOOTSTRAP_DUR" write_bootstrap_entry failed "$BOOTSTRAP_DUR" "$BOOTSTRAP_RAW" write_abort_entry bootstrap "exit-${BOOTSTRAP_RC}" @@ -162,23 +177,19 @@ else echo "$(dim '── last 40 lines of ')$(dim "$BOOTSTRAP_RAW")$(dim ' ──')" tail -40 "$BOOTSTRAP_RAW" echo - echo "Full raw log: $BOOTSTRAP_RAW" - echo "Progression: $PROGRESS_LOG" + echo "$(dim "Full raw log: $BOOTSTRAP_RAW")" + echo "$(dim "Progression: $PROGRESS_LOG")" exit 1 fi -echo -cat <<'EOF' -Phase 2 · setup:auto +# ─── hand off to setup:auto ──────────────────────────────────────────── -EOF - -# ─── phase 2: clack driver ────────────────────────────────────────────── - -# NANOCLAW_BOOTSTRAPPED=1 tells setup/auto.ts that the progression log has -# already been initialized (header + bootstrap entry), so it should append -# rather than wipe. +# NANOCLAW_BOOTSTRAPPED=1 tells setup/auto.ts to skip the wordmark (we +# already printed it) and to append to the progression log rather than +# wipe it. export NANOCLAW_BOOTSTRAPPED=1 -# exec so signals (Ctrl-C) propagate directly to the child. -exec pnpm run setup:auto +# --silent suppresses pnpm's `> nanoclaw@1.2.52 setup:auto / > tsx setup/auto.ts` +# preamble so the flow continues visually from "Basics installed" straight +# into setup:auto's spinner. exec so signals (Ctrl-C) propagate directly. +exec pnpm --silent run setup:auto diff --git a/setup/auto.ts b/setup/auto.ts index bb23650cc..a0068bbbd 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -27,7 +27,7 @@ import k from 'kleur'; import { runTelegramChannel } from './channels/telegram.js'; import * as setupLog from './logs.js'; -import { ensureAnswer, fail, runQuietStep } from './lib/runner.js'; +import { ensureAnswer, fail, runQuietChild, runQuietStep } from './lib/runner.js'; import { brandBold, brandChip } from './lib/theme.js'; const CLI_AGENT_NAME = 'Terminal Agent'; @@ -46,121 +46,116 @@ async function main(): Promise { if (!skip.has('environment')) { const res = await runQuietStep('environment', { - running: 'Checking environment…', - done: 'Environment OK.', + running: 'Checking your system…', + done: 'Your system looks good.', }); - if (!res.ok) fail('environment', 'Environment check failed.'); + if (!res.ok) { + fail( + 'environment', + "Your system doesn't look quite right.", + 'See logs/setup-steps/ for details, then retry.', + ); + } } if (!skip.has('container')) { + p.log.message( + k.dim( + 'Your assistant lives in its own sandbox. It can only see what you explicitly share.', + ), + ); const res = await runQuietStep('container', { - running: 'Building the agent container image…', - done: 'Container image ready.', - failed: 'Container build failed.', + running: 'Preparing the sandbox your assistant runs in…', + done: 'Sandbox ready.', + failed: "Couldn't prepare the sandbox.", }); if (!res.ok) { const err = res.terminal?.fields.ERROR; if (err === 'runtime_not_available') { fail( 'container', - 'Docker is not available and could not be started automatically.', - 'Install Docker Desktop or start it manually, then retry.', + "Docker isn't available.", + 'Install Docker Desktop (or start it if already installed), then retry.', ); } if (err === 'docker_group_not_active') { fail( 'container', - 'Docker was just installed but your shell is not yet in the `docker` group.', + "Docker was just installed but your shell doesn't know yet.", 'Log out and back in (or run `newgrp docker` in a new shell), then retry.', ); } fail( 'container', - 'Container build/test failed.', - 'For stale cache: `docker builder prune -f`, then retry `pnpm run setup:auto`.', + "Couldn't build the sandbox.", + 'If Docker has a stale cache, try: `docker builder prune -f`, then retry.', ); } maybeReexecUnderSg(); } if (!skip.has('onecli')) { + p.log.message( + k.dim( + 'Your assistant never gets your API keys directly. The vault adds them to approved requests as they leave the sandbox.', + ), + ); const res = await runQuietStep('onecli', { - running: 'Installing OneCLI credential vault…', - done: 'OneCLI installed.', + running: "Setting up OneCLI, your agent's vault…", + done: 'OneCLI vault ready.', }); if (!res.ok) { const err = res.terminal?.fields.ERROR; if (err === 'onecli_not_on_path_after_install') { fail( 'onecli', - 'OneCLI installed but not on PATH.', + 'OneCLI was installed but your shell needs to refresh to see it.', 'Open a new shell or run `export PATH="$HOME/.local/bin:$PATH"`, then retry.', ); } fail( 'onecli', - `OneCLI install failed (${err ?? 'unknown'}).`, - 'Check that curl + a writable ~/.local/bin are available, then retry.', + `Couldn't set up OneCLI (${err ?? 'unknown error'}).`, + 'Make sure curl is installed and ~/.local/bin is writable, then retry.', ); } } if (!skip.has('auth')) { - if (anthropicSecretExists()) { - p.log.success('OneCLI already has an Anthropic secret — skipping.'); - setupLog.step('auth', 'skipped', 0, { REASON: 'secret-already-present' }); - } else { - p.log.step('Registering your Anthropic credential…'); - console.log( - k.dim(' (browser sign-in or paste a token/key — this part is interactive)'), - ); - console.log(); - const start = Date.now(); - const code = await runInheritScript('bash', ['setup/register-claude-token.sh']); - const durationMs = Date.now() - start; - console.log(); - if (code !== 0) { - setupLog.step('auth', 'failed', durationMs, { EXIT_CODE: code }); - fail( - 'auth', - 'Anthropic credential registration failed or was aborted.', - 'Re-run `bash setup/register-claude-token.sh` or handle via `/setup` §4.', - ); - } - setupLog.step('auth', 'interactive', durationMs, { - METHOD: 'register-claude-token.sh', - }); - p.log.success('Anthropic credential registered with OneCLI.'); - } + await runAuthStep(); } if (!skip.has('mounts')) { const res = await runQuietStep( 'mounts', { - running: 'Writing mount allowlist…', - done: 'Mount allowlist in place.', - skipped: 'Mount allowlist already configured.', + running: "Setting your assistant's access rules…", + done: 'Access rules set.', + skipped: 'Access rules already set.', }, ['--empty'], ); - if (!res.ok) fail('mounts', 'Mount allowlist step failed.'); + if (!res.ok) { + fail('mounts', "Couldn't write access rules."); + } } if (!skip.has('service')) { const res = await runQuietStep('service', { - running: 'Installing the background service…', - done: 'Service installed and running.', + running: 'Starting NanoClaw in the background…', + done: 'NanoClaw is running.', }); if (!res.ok) { fail( 'service', - 'Service install failed.', - 'Check logs/nanoclaw.error.log, or run `/setup` to iterate interactively.', + "Couldn't start NanoClaw.", + 'See logs/nanoclaw.error.log for details.', ); } if (res.terminal?.fields.DOCKER_GROUP_STALE === 'true') { - p.log.warn('Docker group stale in systemd session.'); + p.log.warn( + "NanoClaw's permissions need a tweak before it can reach Docker.", + ); p.log.message( k.dim( ' sudo setfacl -m u:$(whoami):rw /var/run/docker.sock\n' + @@ -182,16 +177,16 @@ async function main(): Promise { const res = await runQuietStep( 'cli-agent', { - running: 'Wiring the terminal agent…', - done: 'Terminal agent wired (try `pnpm run chat hi`).', + running: 'Setting up your terminal chat…', + done: 'Terminal chat ready. Try `pnpm run chat hi`.', }, ['--display-name', displayName!, '--agent-name', CLI_AGENT_NAME], ); if (!res.ok) { fail( 'cli-agent', - 'CLI agent wiring failed.', - `Re-run \`pnpm exec tsx scripts/init-cli-agent.ts --display-name "${displayName!}" --agent-name "${CLI_AGENT_NAME}"\` to fix.`, + "Couldn't set up the terminal chat.", + `You can retry later with \`pnpm exec tsx scripts/init-cli-agent.ts --display-name "${displayName!}" --agent-name "${CLI_AGENT_NAME}"\`.`, ); } } @@ -201,47 +196,165 @@ async function main(): Promise { if (choice === 'telegram') { await runTelegramChannel(displayName!); } else { - p.log.info('No messaging channel wired — you can add one later with `/add-`.'); + p.log.info( + "No messaging app for now. You can add one later (like Telegram, Slack, or Discord).", + ); } } if (!skip.has('verify')) { const res = await runQuietStep('verify', { - running: 'Verifying the install…', - done: 'Install verified.', - failed: 'Verification found issues.', + running: 'Making sure everything works together…', + done: "Everything's connected.", + failed: 'A few things still need your attention.', }); if (!res.ok) { const notes: string[] = []; if (res.terminal?.fields.CREDENTIALS !== 'configured') { - notes.push('• Anthropic secret not detected — re-run `bash setup/register-claude-token.sh`.'); + notes.push('• Your Claude account isn\'t connected. Re-run setup and try again.'); } const agentPing = res.terminal?.fields.AGENT_PING; if (agentPing && agentPing !== 'ok' && agentPing !== 'skipped') { notes.push( - `• CLI agent did not reply (status: ${agentPing}). ` + - 'Check `logs/nanoclaw.log` and `groups/*/logs/container-*.log`, then try `pnpm run chat hi`.', + "• Your assistant didn't reply to a test message. " + + 'Check `logs/nanoclaw.log` for clues, then try `pnpm run chat hi`.', ); } if (!res.terminal?.fields.CONFIGURED_CHANNELS) { - notes.push('• Optional: add a messaging channel — `/add-discord`, `/add-slack`, `/add-telegram`, …'); + notes.push('• Want to chat from your phone? Add a messaging app with `/add-telegram`, `/add-slack`, or `/add-discord`.'); } if (notes.length > 0) { - p.note(notes.join('\n'), 'What’s left'); + p.note(notes.join('\n'), "What's left"); } - p.outro(k.yellow('Scripted steps done — some pieces still need you.')); + p.outro(k.yellow('Almost there. A few things still need your attention.')); return; } } - const nextSteps = [ - `${k.cyan('Chat from the CLI:')} pnpm run chat hi`, - `${k.cyan('Tail host logs:')} tail -f logs/nanoclaw.log`, - `${k.cyan('Open Claude Code:')} claude`, - ].join('\n'); - p.note(nextSteps, 'Next steps'); + const rows: [string, string][] = [ + ['Chat in the terminal:', 'pnpm run chat hi'], + ["See what's happening:", 'tail -f logs/nanoclaw.log'], + ['Open Claude Code:', 'claude'], + ]; + const labelWidth = Math.max(...rows.map(([l]) => l.length)); + const nextSteps = rows + .map(([l, c]) => `${k.cyan(l.padEnd(labelWidth))} ${c}`) + .join('\n'); + p.note(nextSteps, 'Try these'); setupLog.complete(Date.now() - RUN_START); - p.outro(k.green('Setup complete.')); + p.outro(k.green("You're ready! Enjoy NanoClaw.")); +} + +// ─── auth step (select → branch) ──────────────────────────────────────── + +async function runAuthStep(): Promise { + if (anthropicSecretExists()) { + p.log.success('Your Claude account is already connected.'); + setupLog.step('auth', 'skipped', 0, { REASON: 'secret-already-present' }); + return; + } + + const method = ensureAnswer( + await p.select({ + message: 'How would you like to connect to Claude?', + options: [ + { + value: 'subscription', + label: 'Sign in with my Claude subscription', + hint: 'recommended if you have Pro or Max', + }, + { + value: 'oauth', + label: 'Paste an OAuth token I already have', + hint: 'sk-ant-oat…', + }, + { + value: 'api', + label: 'Paste an Anthropic API key', + hint: 'pay-per-use via console.anthropic.com', + }, + ], + }), + ) as 'subscription' | 'oauth' | 'api'; + setupLog.userInput('auth_method', method); + + if (method === 'subscription') { + await runSubscriptionAuth(); + } else { + await runPasteAuth(method); + } +} + +async function runSubscriptionAuth(): Promise { + p.log.step("Opening the Claude sign-in flow…"); + console.log( + k.dim(' (a browser will open for sign-in; this part is interactive)'), + ); + console.log(); + const start = Date.now(); + const code = await runInheritScript('bash', [ + 'setup/register-claude-token.sh', + ]); + const durationMs = Date.now() - start; + console.log(); + if (code !== 0) { + setupLog.step('auth', 'failed', durationMs, { + EXIT_CODE: code, + METHOD: 'subscription', + }); + fail( + 'auth', + "Couldn't complete the Claude sign-in.", + 'Re-run setup and try again, or choose a paste option instead.', + ); + } + setupLog.step('auth', 'interactive', durationMs, { METHOD: 'subscription' }); + p.log.success('Claude account connected.'); +} + +async function runPasteAuth(method: 'oauth' | 'api'): Promise { + const label = method === 'oauth' ? 'OAuth token' : 'API key'; + const prefix = method === 'oauth' ? 'sk-ant-oat' : 'sk-ant-api'; + + const answer = ensureAnswer( + await p.password({ + message: `Paste your ${label}`, + validate: (v) => { + if (!v || !v.trim()) return 'Required'; + if (!v.trim().startsWith(prefix)) { + return `Should start with ${prefix}…`; + } + return undefined; + }, + }), + ); + const token = (answer as string).trim(); + + const res = await runQuietChild( + 'auth', + 'onecli', + [ + 'secrets', 'create', + '--name', 'Anthropic', + '--type', 'anthropic', + '--value', token, + '--host-pattern', 'api.anthropic.com', + ], + { + running: `Saving your ${label} to your OneCLI vault…`, + done: 'Claude account connected.', + }, + { + extraFields: { METHOD: method }, + }, + ); + if (!res.ok) { + fail( + 'auth', + `Couldn't save your ${label} to the vault.`, + 'Make sure OneCLI is running (`onecli version`), then retry.', + ); + } } // ─── prompts owned by the sequencer ──────────────────────────────────── @@ -249,7 +362,7 @@ async function main(): Promise { async function askDisplayName(fallback: string): Promise { const answer = ensureAnswer( await p.text({ - message: 'What should your agents call you?', + message: 'What should your assistant call you?', placeholder: fallback, defaultValue: fallback, }), @@ -262,10 +375,10 @@ async function askDisplayName(fallback: string): Promise { async function askChannelChoice(): Promise<'telegram' | 'skip'> { const choice = ensureAnswer( await p.select({ - message: 'Connect a messaging app so you can chat from your phone?', + message: 'Want to chat with your assistant from your phone?', options: [ - { value: 'telegram', label: 'Telegram', hint: 'recommended' }, - { value: 'skip', label: 'Skip — use the CLI only' }, + { value: 'telegram', label: 'Yes, connect Telegram', hint: 'recommended' }, + { value: 'skip', label: 'Skip for now', hint: "I'll just use the terminal" }, ], }), ); @@ -311,7 +424,7 @@ function maybeReexecUnderSg(): void { if (!/permission denied/i.test(err)) return; if (spawnSync('which', ['sg'], { stdio: 'ignore' }).status !== 0) return; - p.log.warn('Docker socket not accessible in current group — re-executing under `sg docker`.'); + p.log.warn('Docker socket not accessible in current group. Re-executing under `sg docker`.'); const res = spawnSync('sg', ['docker', '-c', 'pnpm run setup:auto'], { stdio: 'inherit', env: { ...process.env, NANOCLAW_REEXEC_SG: '1' }, @@ -323,17 +436,28 @@ function maybeReexecUnderSg(): void { function printIntro(): void { const isReexec = process.env.NANOCLAW_REEXEC_SG === '1'; + const isBootstrapped = process.env.NANOCLAW_BOOTSTRAPPED === '1'; const wordmark = `${k.bold('Nano')}${brandBold('Claw')}`; if (isReexec) { - p.intro(`${brandChip(' setup:auto ')} ${wordmark} ${k.dim('· resuming under docker group')}`); + p.intro( + `${brandChip(' Welcome ')} ${wordmark} ${k.dim('· picking up where we left off')}`, + ); + return; + } + + // When we were called via nanoclaw.sh, the wordmark + subtitle were + // already printed in bash. Just open the clack gutter with a short, + // neutral intro so the flow continues without duplication. + if (isBootstrapped) { + p.intro(k.dim("Let's get you set up.")); return; } console.log(); console.log(` ${wordmark}`); - console.log(` ${k.dim('end-to-end scripted setup of your personal assistant')}`); - p.intro(`${brandChip(' setup:auto ')}`); + console.log(` ${k.dim('Setting up your personal AI assistant')}`); + p.intro(k.dim("Let's get you set up.")); } /** diff --git a/setup/channels/telegram.ts b/setup/channels/telegram.ts index d3e3f89e5..348cd0502 100644 --- a/setup/channels/telegram.ts +++ b/setup/channels/telegram.ts @@ -43,8 +43,8 @@ export async function runTelegramChannel(displayName: string): Promise { 'bash', ['setup/add-telegram.sh'], { - running: `Installing Telegram adapter and wiring @${botUsername}…`, - done: 'Telegram adapter ready.', + running: `Connecting Telegram to @${botUsername}…`, + done: 'Telegram connected.', }, { env: { TELEGRAM_BOT_TOKEN: token }, @@ -54,8 +54,8 @@ export async function runTelegramChannel(displayName: string): Promise { if (!install.ok) { fail( 'telegram-install', - 'Telegram install failed.', - 'Check the raw log under logs/setup-steps/, then retry `pnpm run setup:auto`.', + "Couldn't connect Telegram.", + 'See logs/setup-steps/ for details, then retry setup.', ); } @@ -63,8 +63,8 @@ export async function runTelegramChannel(displayName: string): Promise { if (!pair.ok) { fail( 'pair-telegram', - 'Telegram pairing failed.', - 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main`.', + "Couldn't pair with Telegram.", + 'Re-run setup to try again.', ); } @@ -73,8 +73,8 @@ export async function runTelegramChannel(displayName: string): Promise { if (!platformId || !pairedUserId) { fail( 'pair-telegram', - 'pair-telegram succeeded but did not return PLATFORM_ID and PAIRED_USER_ID.', - 'Re-run `pnpm exec tsx setup/index.ts --step pair-telegram -- --intent main` and capture the success block.', + 'Pairing completed but came back incomplete.', + 'Re-run setup to try again.', ); } @@ -92,8 +92,8 @@ export async function runTelegramChannel(displayName: string): Promise { '--agent-name', agentName, ], { - running: `Wiring ${agentName} to your Telegram chat…`, - done: `${agentName} is wired — welcome DM incoming.`, + running: `Connecting ${agentName} to your Telegram chat…`, + done: `${agentName} is ready. Check Telegram for a welcome message.`, }, { extraFields: { CHANNEL: 'telegram', AGENT_NAME: agentName, PLATFORM_ID: platformId }, @@ -102,8 +102,8 @@ export async function runTelegramChannel(displayName: string): Promise { if (!init.ok) { fail( 'init-first-agent', - 'Wiring the Telegram agent failed.', - `Re-run \`pnpm exec tsx scripts/init-first-agent.ts --channel telegram --user-id "${pairedUserId}" --platform-id "${platformId}" --display-name "${displayName}" --agent-name "${agentName}"\`.`, + `Couldn't finish connecting ${agentName}.`, + 'You can retry later with `/manage-channels`.', ); } } @@ -111,24 +111,26 @@ export async function runTelegramChannel(displayName: string): Promise { async function collectTelegramToken(): Promise { p.note( [ - '1. Open Telegram and message @BotFather', - '2. Send: /newbot', - '3. Follow the prompts (name + username ending in "bot")', - '4. Copy the token it gives you (format: :)', + "Your assistant talks to you through a Telegram bot you create.", + "Here's how:", '', - k.dim('Optional, but recommended for groups:'), - k.dim(' @BotFather → /mybots → Bot Settings → Group Privacy → OFF'), + ' 1. Open Telegram and message @BotFather', + ' 2. Send /newbot and follow the prompts', + ' 3. Copy the token it gives you (it looks like :)', + '', + k.dim('Planning to add your assistant to group chats? In @BotFather:'), + k.dim(' /mybots → your bot → Bot Settings → Group Privacy → OFF'), ].join('\n'), - 'Create a Telegram bot', + 'Set up your Telegram bot', ); const answer = ensureAnswer( await p.password({ message: 'Paste your bot token', validate: (v) => { - if (!v || !v.trim()) return 'Token is required'; + if (!v || !v.trim()) return "Token is required"; if (!/^[0-9]+:[A-Za-z0-9_-]{35,}$/.test(v.trim())) { - return 'Format looks wrong — expected :'; + return "That doesn't look right. It should be :"; } return undefined; }, @@ -145,7 +147,7 @@ async function collectTelegramToken(): Promise { async function validateTelegramToken(token: string): Promise { const s = p.spinner(); const start = Date.now(); - s.start('Validating token with Telegram…'); + s.start('Checking your bot token…'); try { const res = await fetch(`https://api.telegram.org/bot${token}/getMe`); const data = (await res.json()) as { @@ -156,7 +158,7 @@ async function validateTelegramToken(token: string): Promise { const elapsedS = Math.round((Date.now() - start) / 1000); if (data.ok && data.result?.username) { const username = data.result.username; - s.stop(`Bot is @${username}. ${k.dim(`(${elapsedS}s)`)}`); + s.stop(`Found your bot: @${username}. ${k.dim(`(${elapsedS}s)`)}`); setupLog.step('telegram-validate', 'success', Date.now() - start, { BOT_USERNAME: username, BOT_ID: data.result.id ?? '', @@ -164,26 +166,26 @@ async function validateTelegramToken(token: string): Promise { return username; } const reason = data.description ?? 'token rejected by Telegram'; - s.stop(`Telegram rejected the token: ${reason}`, 1); + s.stop(`Telegram didn't accept that token: ${reason}`, 1); setupLog.step('telegram-validate', 'failed', Date.now() - start, { ERROR: reason, }); fail( 'telegram-validate', - 'Telegram rejected the token.', - 'Double-check the token (copy it again from @BotFather) and retry.', + "Telegram didn't accept that token.", + 'Copy the token again from @BotFather and try setup once more.', ); } catch (err) { const elapsedS = Math.round((Date.now() - start) / 1000); - s.stop(`Could not reach Telegram. ${k.dim(`(${elapsedS}s)`)}`, 1); + s.stop(`Couldn't reach Telegram. ${k.dim(`(${elapsedS}s)`)}`, 1); const message = err instanceof Error ? err.message : String(err); setupLog.step('telegram-validate', 'failed', Date.now() - start, { ERROR: message, }); fail( 'telegram-validate', - 'Telegram API unreachable.', - 'Check your network connection and retry.', + "Couldn't reach Telegram.", + 'Check your internet connection and retry setup.', ); } } @@ -194,7 +196,7 @@ async function runPairTelegram(): Promise< const rawLog = setupLog.stepRawLog('pair-telegram'); const start = Date.now(); const s = p.spinner(); - s.start('Creating pairing code…'); + s.start('Generating a secret code for your bot…'); let spinnerActive = true; const stopSpinner = (msg: string, code?: number) => { @@ -211,15 +213,15 @@ async function runPairTelegram(): Promise< if (block.type === 'PAIR_TELEGRAM_CODE') { const reason = block.fields.REASON ?? 'initial'; if (reason === 'initial') { - stopSpinner('Pairing code ready.'); + stopSpinner('Your secret code is ready.'); } else { - stopSpinner('Previous code invalidated. New code below.'); + stopSpinner("Old code expired. Here's a fresh one."); } - p.note(formatCodeCard(block.fields.CODE ?? '????'), 'Pairing code'); - s.start('Waiting for the code from Telegram…'); + p.note(formatCodeCard(block.fields.CODE ?? '????'), 'Secret code'); + s.start('Waiting for you to send the code from Telegram…'); spinnerActive = true; } else if (block.type === 'PAIR_TELEGRAM_ATTEMPT') { - stopSpinner(`Received "${block.fields.CANDIDATE ?? '?'}" — doesn't match.`); + stopSpinner(`Got "${block.fields.CANDIDATE ?? '?'}", not a match.`); s.start('Waiting for the correct code…'); spinnerActive = true; } else if (block.type === 'PAIR_TELEGRAM') { @@ -238,7 +240,7 @@ async function runPairTelegram(): Promise< // sure we don't leave the spinner running. if (spinnerActive) { stopSpinner( - result.ok ? 'Done.' : 'Pairing exited unexpectedly.', + result.ok ? 'Done.' : 'Pairing ended unexpectedly.', result.ok ? 0 : 1, ); if (!result.ok) dumpTranscriptOnFailure(result.transcript); @@ -254,7 +256,7 @@ function formatCodeCard(code: string): string { '', ` ${brandBold(spaced)}`, '', - k.dim(' Send these digits from Telegram to your bot.'), + k.dim(' Send this code to your bot from Telegram.'), ].join('\n'); } @@ -266,7 +268,7 @@ async function resolveAgentName(): Promise { } const answer = ensureAnswer( await p.text({ - message: 'What should your messaging agent be called?', + message: 'What should your assistant be called?', placeholder: DEFAULT_AGENT_NAME, defaultValue: DEFAULT_AGENT_NAME, }), diff --git a/setup/register-claude-token.sh b/setup/register-claude-token.sh index 8bcab734a..e0707bf07 100755 --- a/setup/register-claude-token.sh +++ b/setup/register-claude-token.sh @@ -1,128 +1,88 @@ #!/usr/bin/env bash set -euo pipefail -# Prefer bash 4+ (for `read -e -i` readline preload). macOS ships 3.2 in -# /bin/bash, but Homebrew users usually have 5.x first on PATH. The readline -# preload is optional — on 3.x we fall back to a plain confirmation prompt. - -# Register an Anthropic credential with OneCLI. Three paths: -# 1) Claude subscription — run `claude setup-token` (browser sign-in) -# and capture the resulting OAuth token. -# 2) Paste an existing sk-ant-oat… OAuth token you already have. -# 3) Paste an Anthropic API key (sk-ant-api…). +# Register a Claude subscription OAuth token with OneCLI — the *only* auth +# path that needs a TTY break in the flow. Paste-based paths (existing +# OAuth token / API key) are handled in-process by setup/auto.ts using +# clack prompts, then onecli secrets create is invoked directly from TS. +# +# Flow: +# 1. Run `claude setup-token` under a PTY (via script(1)) so the browser +# OAuth dance works and its token is captured into a tempfile. +# 2. Regex the sk-ant-oat…AA token out of the ANSI-stripped capture. +# 3. Register it with OneCLI. # # Env overrides: # SECRET_NAME OneCLI secret name (default: Anthropic) # HOST_PATTERN OneCLI host pattern (default: api.anthropic.com) +# Prefer bash 4+ (for `read -e -i` readline preload). macOS ships 3.2 in +# /bin/bash, but Homebrew users usually have 5.x first on PATH. The +# readline preload is optional — on 3.x we fall back to a plain prompt. + SECRET_NAME="${SECRET_NAME:-Anthropic}" HOST_PATTERN="${HOST_PATTERN:-api.anthropic.com}" command -v onecli >/dev/null \ || { echo "onecli not found. Install it first (see /setup §4)." >&2; exit 1; } +command -v claude >/dev/null \ + || { echo "claude CLI not found. Install from https://claude.ai/download" >&2; exit 1; } +command -v script >/dev/null \ + || { echo "script(1) is required for PTY capture." >&2; exit 1; } -TOKEN="" +tmpfile=$(mktemp -t claude-setup-token.XXXXXX) +trap 'rm -f "$tmpfile"' EXIT -capture_via_claude_setup_token() { - command -v claude >/dev/null \ - || { echo "claude CLI not found. Install from https://claude.ai/download" >&2; exit 1; } - command -v script >/dev/null \ - || { echo "script(1) is required for PTY capture." >&2; exit 1; } +cat <<'EOF' +A browser window will open for you to sign in with your Claude account. +When you finish, we'll save the token to your OneCLI vault automatically. - local tmpfile - tmpfile=$(mktemp -t claude-setup-token.XXXXXX) - trap 'rm -f "$tmpfile"' RETURN - - cat <<'EOF' -A browser window will open for sign-in. Token is captured automatically. -Press Enter to run, or edit the command first. +Press Enter to continue, or edit the command first. EOF - local cmd="claude setup-token" - if [[ ${BASH_VERSINFO[0]:-0} -ge 4 ]]; then - # bash 4+: pre-fill the readline buffer so Enter literally submits. - read -r -e -i "$cmd" -p "$ " cmd /dev/null | grep -q util-linux; then - script -q -c "$cmd" "$tmpfile" - else - # BSD script: command is argv after the file, so let it word-split. - # shellcheck disable=SC2086 - script -q "$tmpfile" $cmd - fi +# `script` arg order differs between BSD (macOS) and util-linux. +if script --version 2>/dev/null | grep -q util-linux; then + script -q -c "$cmd" "$tmpfile" +else + # BSD script: command is argv after the file, so let it word-split. + # shellcheck disable=SC2086 + script -q "$tmpfile" $cmd +fi - # Strip ANSI codes + newlines (TTY wraps the token mid-string), then match - # the sk-ant-oat…AA token. perl because BSD grep caps {n,m} at 255. - TOKEN=$(sed $'s/\x1b\\[[0-9;]*[a-zA-Z]//g' "$tmpfile" \ - | tr -d '\n\r' \ - | perl -ne 'print "$1\n" while /(sk-ant-oat[A-Za-z0-9_-]{80,500}AA)/g' \ - | tail -1 || true) +# Strip ANSI codes + newlines (TTY wraps the token mid-string), then match +# the sk-ant-oat…AA token. perl because BSD grep caps {n,m} at 255. +token=$(sed $'s/\x1b\\[[0-9;]*[a-zA-Z]//g' "$tmpfile" \ + | tr -d '\n\r' \ + | perl -ne 'print "$1\n" while /(sk-ant-oat[A-Za-z0-9_-]{80,500}AA)/g' \ + | tail -1 || true) - if [[ -z "$TOKEN" ]]; then - local keep - keep=$(mktemp -t claude-setup-token-log.XXXXXX) - cp "$tmpfile" "$keep" - echo >&2 - echo "No sk-ant-oat…AA token found. Raw log: $keep" >&2 - exit 1 - fi -} - -prompt_for_pasted() { - local prefix="$1" # "oat" or "api" - local value - echo - echo "Paste your sk-ant-${prefix}… credential and press Enter." - echo "Nothing will appear on the screen as you paste — that's intentional." - echo "Paste once, then just press Enter to submit." - read -r -s -p "> " value &2 - exit 1 - fi - if [[ ! "$value" =~ ^sk-ant-${prefix} ]]; then - echo "Value does not start with sk-ant-${prefix}. Aborting." >&2 - exit 1 - fi - TOKEN="$value" -} - -cat <&2; exit 1 ;; -esac +if [ -z "$token" ]; then + keep=$(mktemp -t claude-setup-token-log.XXXXXX) + cp "$tmpfile" "$keep" + echo >&2 + echo "No sk-ant-oat…AA token found. Raw log: $keep" >&2 + exit 1 +fi echo -echo "Got token: ${TOKEN:0:16}…${TOKEN: -4}" -echo "Registering with OneCLI as '${SECRET_NAME}' (host pattern: ${HOST_PATTERN})…" +echo "Got token: ${token:0:16}…${token: -4}" +echo "Saving it to your OneCLI vault as '${SECRET_NAME}' (host: ${HOST_PATTERN})…" onecli secrets create \ --name "$SECRET_NAME" \ --type anthropic \ - --value "$TOKEN" \ + --value "$token" \ --host-pattern "$HOST_PATTERN" echo "Done." From a263da3e538008005951eaa0193f9e2b15de49ec Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 09:17:19 +0300 Subject: [PATCH 93/95] feat(setup): prompt to install Homebrew on factory macOS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit install-node.sh and install-docker.sh both require brew on macOS. On a fresh Mac there's no brew, so the bootstrap spinner would bail with a cryptic "Homebrew not installed" error. Move the prompt to nanoclaw.sh as a pre-flight, so the user sees a clear ask — including the heads-up that Xcode Command Line Tools come along for the ride (~5-10 min) — before the spinner starts and brew's own sudo/CLT prompts appear. Co-Authored-By: Claude Opus 4.7 (1M context) --- nanoclaw.sh | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/nanoclaw.sh b/nanoclaw.sh index e94e383fe..a1a22af73 100755 --- a/nanoclaw.sh +++ b/nanoclaw.sh @@ -126,6 +126,54 @@ write_header printf '\n %s%s\n' "$(bold 'Nano')" "$(brand_bold 'Claw')" printf ' %s\n\n' "$(dim 'Setting up your personal AI assistant')" +# ─── pre-flight: Homebrew on macOS ───────────────────────────────────── +# setup/install-node.sh and setup/install-docker.sh both require `brew` on +# macOS. On a factory Mac there's no brew, and those helpers would fail +# later inside the bootstrap spinner with a cryptic error. Prompt here, +# before the spinner starts, so the user knows what's about to happen and +# brew's own interactive sudo/CLT prompts stay readable. +if [ "$(uname -s)" = "Darwin" ] && ! command -v brew >/dev/null 2>&1; then + printf ' %s\n' \ + "$(dim "Homebrew isn't installed. NanoClaw uses it to install Node and Docker on your Mac.")" + printf ' %s\n\n' \ + "$(dim "This also installs Apple's Command Line Tools, which can take 5-10 minutes.")" + read -r -p " $(bold 'Install Homebrew now?') [Y/n] " BREW_ANS /dev/null 2>&1; then + printf '\n %s %s\n' "$(red '✗')" "Homebrew install didn't complete." + printf ' %s\n\n' \ + "$(dim 'Install manually from https://brew.sh and re-run: bash nanoclaw.sh')" + exit 1 + fi + printf '\n' + ;; + *) + printf '\n %s\n\n' \ + "$(dim 'NanoClaw needs Homebrew. Install it from https://brew.sh and re-run.')" + exit 1 + ;; + esac +fi + # ─── first step: install the basics (Node + pnpm + native modules) ───── BOOTSTRAP_RAW="${STEPS_DIR}/01-bootstrap.log" From 9b6e5b24a1ba80ce9bb0d4993cd530bf7f761e12 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 10:45:05 +0300 Subject: [PATCH 94/95] feat(setup): optional Discord wiring in setup:auto MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mirror of the Telegram flow but without a pairing step — Discord exposes enough via the bot token that we only need one paste from the operator, with every other identity field derived: GET /users/@me → bot username (sanity check) GET /oauth2/applications/@me → application id, verify_key (public key), owner {id, username} POST /users/@me/channels → DM channel id After confirming "Is @ your Discord account?" the flow invites the bot to a server (OAuth URL + open + confirm, gating so the welcome DM can actually reach the operator), installs the adapter, opens the DM channel, and hands off to init-first-agent with --channel discord --platform-id discord:@me:. The existing init-first-agent welcome-over-CLI-socket path delivers the greeting through the normal adapter pipeline — no Discord-specific code in the welcome logic. Fallbacks: if the app is team-owned (no owner object) or the operator declines the confirmation, a Dev Mode walkthrough + user-id paste prompt takes over. Adds: - setup/add-discord.sh (non-interactive installer, mirror of add-telegram.sh minus pair-step registration) - setup/channels/discord.ts (operator-facing flow) - setup/auto.ts: Discord option in askChannelChoice + dispatch Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/add-discord.sh | 122 ++++++++++ setup/auto.ts | 10 +- setup/channels/discord.ts | 455 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 584 insertions(+), 3 deletions(-) create mode 100755 setup/add-discord.sh create mode 100644 setup/channels/discord.ts diff --git a/setup/add-discord.sh b/setup/add-discord.sh new file mode 100755 index 000000000..1cd247a28 --- /dev/null +++ b/setup/add-discord.sh @@ -0,0 +1,122 @@ +#!/usr/bin/env bash +# +# Install the Discord adapter, persist DISCORD_BOT_TOKEN / APPLICATION_ID / +# PUBLIC_KEY to .env + data/env/env, and restart the service. Non-interactive — +# the operator-facing "Create a bot" walkthrough, owner confirmation, and +# server-invite step live in setup/channels/discord.ts. Credentials come in via +# env vars: DISCORD_BOT_TOKEN, DISCORD_APPLICATION_ID, DISCORD_PUBLIC_KEY. +# +# Emits exactly one status block on stdout (ADD_DISCORD) at the end. All chatty +# progress messages go to stderr so setup:auto's raw-log capture sees the full +# story without cluttering the final block for the parser. +set -euo pipefail + +PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" +cd "$PROJECT_ROOT" + +# Keep in sync with .claude/skills/add-discord/SKILL.md. +ADAPTER_VERSION="@chat-adapter/discord@4.26.0" +CHANNELS_BRANCH="origin/channels" + +emit_status() { + local status=$1 error=${2:-} + local already=${ADAPTER_ALREADY_INSTALLED:-false} + echo "=== NANOCLAW SETUP: ADD_DISCORD ===" + echo "STATUS: ${status}" + echo "ADAPTER_VERSION: ${ADAPTER_VERSION}" + echo "ADAPTER_ALREADY_INSTALLED: ${already}" + [ -n "$error" ] && echo "ERROR: ${error}" + echo "=== END ===" +} + +log() { echo "[add-discord] $*" >&2; } + +if [ -z "${DISCORD_BOT_TOKEN:-}" ]; then + emit_status failed "DISCORD_BOT_TOKEN env var not set" + exit 1 +fi +if [ -z "${DISCORD_APPLICATION_ID:-}" ]; then + emit_status failed "DISCORD_APPLICATION_ID env var not set" + exit 1 +fi +if [ -z "${DISCORD_PUBLIC_KEY:-}" ]; then + emit_status failed "DISCORD_PUBLIC_KEY env var not set" + exit 1 +fi + +need_install() { + [ ! -f src/channels/discord.ts ] && return 0 + ! grep -q "^import './discord.js';" src/channels/index.ts 2>/dev/null && return 0 + return 1 +} + +ADAPTER_ALREADY_INSTALLED=true +if need_install; then + ADAPTER_ALREADY_INSTALLED=false + log "Fetching channels branch…" + git fetch origin channels >&2 2>/dev/null || { + emit_status failed "git fetch origin channels failed" + exit 1 + } + + log "Copying adapter from ${CHANNELS_BRANCH}…" + git show "${CHANNELS_BRANCH}:src/channels/discord.ts" > src/channels/discord.ts + + # Append self-registration import if missing. + if ! grep -q "^import './discord.js';" src/channels/index.ts; then + echo "import './discord.js';" >> src/channels/index.ts + fi + + log "Installing ${ADAPTER_VERSION}…" + pnpm install "${ADAPTER_VERSION}" >&2 2>/dev/null || { + emit_status failed "pnpm install ${ADAPTER_VERSION} failed" + exit 1 + } + + log "Building…" + pnpm run build >&2 2>/dev/null || { + emit_status failed "pnpm run build failed" + exit 1 + } +else + log "Adapter files already installed — skipping install phase." +fi + +# Persist credentials. auto.ts validates before this point, so bad values here +# would be an internal bug rather than operator input. +touch .env +upsert_env() { + local key=$1 value=$2 + if grep -q "^${key}=" .env; then + awk -v k="$key" -v v="$value" \ + 'BEGIN{FS=OFS="="} $1==k {print k "=" v; next} {print}' \ + .env > .env.tmp && mv .env.tmp .env + else + echo "${key}=${value}" >> .env + fi +} +upsert_env DISCORD_BOT_TOKEN "$DISCORD_BOT_TOKEN" +upsert_env DISCORD_APPLICATION_ID "$DISCORD_APPLICATION_ID" +upsert_env DISCORD_PUBLIC_KEY "$DISCORD_PUBLIC_KEY" + +# Container reads from data/env/env (the host mounts it). +mkdir -p data/env +cp .env data/env/env + +log "Restarting service so the new adapter picks up the credentials…" +case "$(uname -s)" in + Darwin) + launchctl kickstart -k "gui/$(id -u)/com.nanoclaw" >&2 2>/dev/null || true + ;; + Linux) + systemctl --user restart nanoclaw >&2 2>/dev/null \ + || sudo systemctl restart nanoclaw >&2 2>/dev/null \ + || true + ;; +esac + +# Give the Discord adapter a moment to finish gateway handshake before +# init-first-agent attempts delivery. +sleep 5 + +emit_status success diff --git a/setup/auto.ts b/setup/auto.ts index a0068bbbd..97f38ac40 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -25,6 +25,7 @@ import { spawn, spawnSync } from 'child_process'; import * as p from '@clack/prompts'; import k from 'kleur'; +import { runDiscordChannel } from './channels/discord.js'; import { runTelegramChannel } from './channels/telegram.js'; import * as setupLog from './logs.js'; import { ensureAnswer, fail, runQuietChild, runQuietStep } from './lib/runner.js'; @@ -195,9 +196,11 @@ async function main(): Promise { const choice = await askChannelChoice(); if (choice === 'telegram') { await runTelegramChannel(displayName!); + } else if (choice === 'discord') { + await runDiscordChannel(displayName!); } else { p.log.info( - "No messaging app for now. You can add one later (like Telegram, Slack, or Discord).", + "No messaging app for now. You can add one later (like Telegram, Discord, or Slack).", ); } } @@ -372,18 +375,19 @@ async function askDisplayName(fallback: string): Promise { return value; } -async function askChannelChoice(): Promise<'telegram' | 'skip'> { +async function askChannelChoice(): Promise<'telegram' | 'discord' | 'skip'> { const choice = ensureAnswer( await p.select({ message: 'Want to chat with your assistant from your phone?', options: [ { value: 'telegram', label: 'Yes, connect Telegram', hint: 'recommended' }, + { value: 'discord', label: 'Yes, connect Discord' }, { value: 'skip', label: 'Skip for now', hint: "I'll just use the terminal" }, ], }), ); setupLog.userInput('channel_choice', String(choice)); - return choice as 'telegram' | 'skip'; + return choice as 'telegram' | 'discord' | 'skip'; } // ─── interactive / env helpers ───────────────────────────────────────── diff --git a/setup/channels/discord.ts b/setup/channels/discord.ts new file mode 100644 index 000000000..cfc8155e5 --- /dev/null +++ b/setup/channels/discord.ts @@ -0,0 +1,455 @@ +/** + * Discord channel flow for setup:auto. + * + * `runDiscordChannel(displayName)` owns the full branch from "do you have a + * bot?" through the welcome DM: + * + * 1. Ask if they have a bot already; walk them through Dev Portal creation + * if not + * 2. Paste the bot token (clack password) — format-validated + * 3. GET /users/@me to confirm the token and resolve bot username + * 4. GET /oauth2/applications/@me to derive application_id, verify_key + * (public key), and owner — no separate paste needed in the common case + * 5. Confirm owner identity (falls back to a manual user-id prompt with + * Developer Mode instructions if declined or if the app is team-owned) + * 6. Print the OAuth invite URL, open it, wait for "I've added the bot" + * 7. Install the adapter via setup/add-discord.sh (non-interactive) + * 8. POST /users/@me/channels to open the DM channel (yields dm channel id) + * 9. Ask for the messaging-agent name (defaulting to "Nano") + * 10. Wire the agent via scripts/init-first-agent.ts, which sends the welcome + * DM through the normal delivery path + * + * All output obeys the three-level contract: clack UI for the user, structured + * entries in logs/setup.log, full raw output in per-step files under + * logs/setup-steps/. See docs/setup-flow.md. + */ +import { spawn } from 'child_process'; + +import * as p from '@clack/prompts'; +import k from 'kleur'; + +import * as setupLog from '../logs.js'; +import { ensureAnswer, fail, runQuietChild } from '../lib/runner.js'; + +const DEFAULT_AGENT_NAME = 'Nano'; +const DISCORD_API = 'https://discord.com/api/v10'; + +// Send Messages (0x800) + Add Reactions (0x40) + Attach Files (0x8000) +// + Read Message History (0x10000) = 100416. +// Matches the permissions set documented in .claude/skills/add-discord/SKILL.md. +const INVITE_PERMISSIONS = '100416'; + +interface AppInfo { + applicationId: string; + publicKey: string; + owner: { id: string; username: string } | null; +} + +export async function runDiscordChannel(displayName: string): Promise { + if (!(await askHasBotToken())) { + await walkThroughBotCreation(); + } + + const token = await collectDiscordToken(); + const botUsername = await validateDiscordToken(token); + const app = await fetchApplicationInfo(token); + + const ownerUserId = await resolveOwnerUserId(app.owner); + + await promptInviteBot(app.applicationId, botUsername); + + const install = await runQuietChild( + 'discord-install', + 'bash', + ['setup/add-discord.sh'], + { + running: `Connecting Discord to @${botUsername}…`, + done: 'Discord connected.', + }, + { + env: { + DISCORD_BOT_TOKEN: token, + DISCORD_APPLICATION_ID: app.applicationId, + DISCORD_PUBLIC_KEY: app.publicKey, + }, + extraFields: { + BOT_USERNAME: botUsername, + APPLICATION_ID: app.applicationId, + }, + }, + ); + if (!install.ok) { + fail( + 'discord-install', + "Couldn't connect Discord.", + 'See logs/setup-steps/ for details, then retry setup.', + ); + } + + const dmChannelId = await openDmChannel(token, ownerUserId); + const platformId = `discord:@me:${dmChannelId}`; + + const agentName = await resolveAgentName(); + + const init = await runQuietChild( + 'init-first-agent', + 'pnpm', + [ + 'exec', 'tsx', 'scripts/init-first-agent.ts', + '--channel', 'discord', + '--user-id', `discord:${ownerUserId}`, + '--platform-id', platformId, + '--display-name', displayName, + '--agent-name', agentName, + ], + { + running: `Connecting ${agentName} to your Discord DMs…`, + done: `${agentName} is ready. Check Discord for a welcome message.`, + }, + { + extraFields: { + CHANNEL: 'discord', + AGENT_NAME: agentName, + PLATFORM_ID: platformId, + }, + }, + ); + if (!init.ok) { + fail( + 'init-first-agent', + `Couldn't finish connecting ${agentName}.`, + 'Most likely the bot and you don\'t share a server yet — invite the bot, then retry later with `/manage-channels`.', + ); + } +} + +async function askHasBotToken(): Promise { + const answer = ensureAnswer( + await p.select({ + message: 'Do you already have a Discord bot?', + options: [ + { value: 'yes', label: 'Yes, I have a bot token ready' }, + { value: 'no', label: "No, walk me through creating one" }, + ], + }), + ); + return answer === 'yes'; +} + +async function walkThroughBotCreation(): Promise { + const url = 'https://discord.com/developers/applications'; + p.note( + [ + "You'll create a Discord bot in the Developer Portal. It's free and takes about a minute.", + '', + ' 1. Click "New Application", give it a name (e.g. "NanoClaw")', + ' 2. In the "Bot" tab, click "Reset Token" and copy the token', + ' 3. On the same tab, enable "Message Content Intent"', + ' (under Privileged Gateway Intents)', + '', + k.dim(`Opening ${url} …`), + ].join('\n'), + 'Create a Discord bot', + ); + openUrl(url); + + ensureAnswer( + await p.confirm({ + message: "Got your bot token?", + initialValue: true, + }), + ); +} + +async function collectDiscordToken(): Promise { + const answer = ensureAnswer( + await p.password({ + message: 'Paste your bot token', + validate: (v) => { + const t = (v ?? '').trim(); + if (!t) return 'Token is required'; + // Discord bot tokens are base64url segments separated by dots. + // Be lenient on length; the real check is /users/@me. + if (!/^[A-Za-z0-9._-]{50,}$/.test(t)) { + return "That doesn't look like a Discord bot token"; + } + return undefined; + }, + }), + ); + const token = (answer as string).trim(); + setupLog.userInput( + 'discord_token', + `${token.slice(0, 10)}…${token.slice(-4)}`, + ); + return token; +} + +async function validateDiscordToken(token: string): Promise { + const s = p.spinner(); + const start = Date.now(); + s.start('Checking your bot token…'); + try { + const res = await fetch(`${DISCORD_API}/users/@me`, { + headers: { Authorization: `Bot ${token}` }, + }); + const data = (await res.json()) as { + id?: string; + username?: string; + message?: string; + }; + const elapsedS = Math.round((Date.now() - start) / 1000); + if (res.ok && data.username) { + s.stop(`Found your bot: @${data.username}. ${k.dim(`(${elapsedS}s)`)}`); + setupLog.step('discord-validate', 'success', Date.now() - start, { + BOT_USERNAME: data.username, + BOT_ID: data.id ?? '', + }); + return data.username; + } + const reason = data.message ?? `HTTP ${res.status}`; + s.stop(`Discord didn't accept that token: ${reason}`, 1); + setupLog.step('discord-validate', 'failed', Date.now() - start, { + ERROR: reason, + }); + fail( + 'discord-validate', + "Discord didn't accept that token.", + 'Copy the token again from the Developer Portal and retry setup.', + ); + } catch (err) { + const elapsedS = Math.round((Date.now() - start) / 1000); + s.stop(`Couldn't reach Discord. ${k.dim(`(${elapsedS}s)`)}`, 1); + const message = err instanceof Error ? err.message : String(err); + setupLog.step('discord-validate', 'failed', Date.now() - start, { + ERROR: message, + }); + fail( + 'discord-validate', + "Couldn't reach Discord.", + 'Check your internet connection and retry setup.', + ); + } +} + +async function fetchApplicationInfo(token: string): Promise { + const s = p.spinner(); + const start = Date.now(); + s.start('Looking up your bot application…'); + try { + const res = await fetch(`${DISCORD_API}/oauth2/applications/@me`, { + headers: { Authorization: `Bot ${token}` }, + }); + const data = (await res.json()) as { + id?: string; + verify_key?: string; + owner?: { id: string; username: string } | null; + team?: unknown; + message?: string; + }; + const elapsedS = Math.round((Date.now() - start) / 1000); + if (!res.ok || !data.id || !data.verify_key) { + const reason = data.message ?? `HTTP ${res.status}`; + s.stop(`Couldn't read application info: ${reason}`, 1); + setupLog.step('discord-app-info', 'failed', Date.now() - start, { + ERROR: reason, + }); + fail( + 'discord-app-info', + "Couldn't read your Discord application details.", + 'Re-run setup. If it keeps failing, check the bot token has the right scopes.', + ); + } + s.stop(`Got your application details. ${k.dim(`(${elapsedS}s)`)}`); + // owner is populated for solo applications; team-owned apps return a + // team object instead and we'll fall back to a manual user-id prompt. + const owner = + data.owner && data.owner.id && data.owner.username + ? { id: data.owner.id, username: data.owner.username } + : null; + setupLog.step('discord-app-info', 'success', Date.now() - start, { + APPLICATION_ID: data.id, + OWNER_USERNAME: owner?.username ?? '', + TEAM_OWNED: data.team ? 'true' : 'false', + }); + return { + applicationId: data.id, + publicKey: data.verify_key, + owner, + }; + } catch (err) { + const elapsedS = Math.round((Date.now() - start) / 1000); + s.stop(`Couldn't reach Discord. ${k.dim(`(${elapsedS}s)`)}`, 1); + const message = err instanceof Error ? err.message : String(err); + setupLog.step('discord-app-info', 'failed', Date.now() - start, { + ERROR: message, + }); + fail( + 'discord-app-info', + "Couldn't reach Discord.", + 'Check your internet connection and retry setup.', + ); + } +} + +async function resolveOwnerUserId( + owner: { id: string; username: string } | null, +): Promise { + if (owner) { + const confirmed = ensureAnswer( + await p.confirm({ + message: `Is @${owner.username} your Discord account?`, + initialValue: true, + }), + ); + if (confirmed === true) { + setupLog.userInput('discord_owner_confirmed', owner.username); + return owner.id; + } + } else { + p.log.info( + "Your bot is owned by a Developer Team, so we need your Discord user ID directly.", + ); + } + return await promptForUserIdWithDevMode(); +} + +async function promptForUserIdWithDevMode(): Promise { + p.note( + [ + "To get your Discord user ID:", + '', + ' 1. Open Discord → Settings (⚙️) → Advanced', + ' 2. Turn on "Developer Mode"', + ' 3. Right-click your own name/avatar → "Copy User ID"', + ].join('\n'), + 'Find your Discord user ID', + ); + const answer = ensureAnswer( + await p.text({ + message: 'Paste your Discord user ID', + validate: (v) => { + const t = (v ?? '').trim(); + if (!t) return 'User ID is required'; + if (!/^\d{17,20}$/.test(t)) { + return "That doesn't look like a Discord user ID (17-20 digits)"; + } + return undefined; + }, + }), + ); + const id = (answer as string).trim(); + setupLog.userInput('discord_user_id', id); + return id; +} + +async function promptInviteBot( + applicationId: string, + botUsername: string, +): Promise { + const url = + `https://discord.com/api/oauth2/authorize` + + `?client_id=${applicationId}` + + `&scope=bot` + + `&permissions=${INVITE_PERMISSIONS}`; + + p.note( + [ + `@${botUsername} needs to share a server with you before it can DM you.`, + '', + ' 1. Pick any server you\'re in (a personal one is fine)', + ' 2. Click "Authorize"', + '', + k.dim(`Opening ${url}`), + ].join('\n'), + 'Add bot to a server', + ); + openUrl(url); + + ensureAnswer( + await p.confirm({ + message: "I've added the bot to a server", + initialValue: true, + }), + ); +} + +async function openDmChannel(token: string, userId: string): Promise { + const s = p.spinner(); + const start = Date.now(); + s.start('Opening a DM channel…'); + try { + const res = await fetch(`${DISCORD_API}/users/@me/channels`, { + method: 'POST', + headers: { + Authorization: `Bot ${token}`, + 'Content-Type': 'application/json', + }, + body: JSON.stringify({ recipient_id: userId }), + }); + const data = (await res.json()) as { id?: string; message?: string }; + const elapsedS = Math.round((Date.now() - start) / 1000); + if (!res.ok || !data.id) { + const reason = data.message ?? `HTTP ${res.status}`; + s.stop(`Couldn't open a DM channel: ${reason}`, 1); + setupLog.step('discord-open-dm', 'failed', Date.now() - start, { + ERROR: reason, + }); + fail( + 'discord-open-dm', + "Couldn't open a DM channel with you.", + 'Make sure the bot is in a server you\'re also in, then retry setup.', + ); + } + s.stop(`DM channel ready. ${k.dim(`(${elapsedS}s)`)}`); + setupLog.step('discord-open-dm', 'success', Date.now() - start, { + DM_CHANNEL_ID: data.id, + }); + return data.id; + } catch (err) { + const elapsedS = Math.round((Date.now() - start) / 1000); + s.stop(`Couldn't reach Discord. ${k.dim(`(${elapsedS}s)`)}`, 1); + const message = err instanceof Error ? err.message : String(err); + setupLog.step('discord-open-dm', 'failed', Date.now() - start, { + ERROR: message, + }); + fail( + 'discord-open-dm', + "Couldn't reach Discord.", + 'Check your internet connection and retry setup.', + ); + } +} + +async function resolveAgentName(): Promise { + const preset = process.env.NANOCLAW_AGENT_NAME?.trim(); + if (preset) { + setupLog.userInput('agent_name', preset); + return preset; + } + const answer = ensureAnswer( + await p.text({ + message: 'What should your assistant be called?', + placeholder: DEFAULT_AGENT_NAME, + defaultValue: DEFAULT_AGENT_NAME, + }), + ); + const value = (answer as string).trim() || DEFAULT_AGENT_NAME; + setupLog.userInput('agent_name', value); + return value; +} + +/** Best-effort open of a URL in the user's default browser. Silent on failure. */ +function openUrl(url: string): void { + try { + const cmd = process.platform === 'darwin' ? 'open' : 'xdg-open'; + const child = spawn(cmd, [url], { stdio: 'ignore', detached: true }); + child.on('error', () => { + // Headless / no browser / unknown command — the URL is already + // printed in the note above, so the user can copy-paste. + }); + child.unref(); + } catch { + // swallow — URL is visible in the note. + } +} From 72b7a72cbbe55489d6c5813a701e9777fef9ea54 Mon Sep 17 00:00:00 2001 From: gavrielc Date: Wed, 22 Apr 2026 11:06:15 +0300 Subject: [PATCH 95/95] feat(setup): ping agent before chat, detect stale service, auto-install Claude MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Round-trip confirmation before first chat. After cli-agent wires up the Terminal Agent, send `chat ping` through the CLI socket under a spinner with 30s timeout (shared helper in setup/lib/agent-ping.ts, also used by verify). Only after a real reply do we show "Your assistant is ready." and enter the chat loop. Ping failures surface a targeted note (socket_error vs no_reply) and skip the prompt — so users never type into the void. Checkout-mismatch detection. verify resolves the running service PID's script path via `ps -p -o command=` and compares to projectRoot. If the service is running from a sibling clone (common for developers with multiple checkouts), SERVICE comes back as running_other_checkout instead of running, AGENT_PING is skipped, and the failure note tells the user exactly which bootout + bootstrap pair to run. Native Claude Code install on demand. Only the subscription auth path needs `claude`; the paste-token and paste-API-key paths don't. So register-claude-token.sh now runs setup/install-claude.sh when `claude` is missing (curl -fsSL https://claude.ai/install.sh | bash), then prepends ~/.local/bin to PATH in-process so the rest of the script can see the fresh binary. Gutter-safe wrapping. wrapForGutter + dimWrap in lib/theme.ts hard-wrap text to `process.stdout.columns - gutter` on word boundaries, measuring visible length (ANSI-stripped). dimWrap applies the dim envelope per line because clack resets styling at each line break when rendering multi-line log content — a single outer dim() only colors the first line. Applied to the long "why" notes before container + onecli, the channel-skip info, the ping-failure note, and the checkout-mismatch remediation. Wordmark anchoring. printIntro always includes the NanoClaw wordmark in the clack intro line, whether or not nanoclaw.sh already printed one in bash. Worth ~1 line of redundancy so the brand stays visible at the top of the clack session after bootstrap output scrolls out. Co-Authored-By: Claude Opus 4.7 (1M context) --- setup/auto.ts | 160 +++++++++++++++++++++++++++------ setup/install-claude.sh | 50 +++++++++++ setup/lib/agent-ping.ts | 50 +++++++++++ setup/lib/theme.ts | 63 +++++++++++++ setup/register-claude-token.sh | 22 ++++- setup/verify.ts | 122 ++++++++++++++----------- 6 files changed, 389 insertions(+), 78 deletions(-) create mode 100755 setup/install-claude.sh create mode 100644 setup/lib/agent-ping.ts diff --git a/setup/auto.ts b/setup/auto.ts index 97f38ac40..49be3f333 100644 --- a/setup/auto.ts +++ b/setup/auto.ts @@ -14,7 +14,7 @@ * "Terminal Agent". * NANOCLAW_SKIP comma-separated step names to skip * (environment|container|onecli|auth|mounts| - * service|cli-agent|channel|verify) + * service|cli-agent|channel|verify|first-chat) * * Timezone defaults to the host system's TZ. Run * pnpm exec tsx setup/index.ts --step timezone -- --tz @@ -27,9 +27,10 @@ import k from 'kleur'; import { runDiscordChannel } from './channels/discord.js'; import { runTelegramChannel } from './channels/telegram.js'; +import { pingCliAgent, type PingResult } from './lib/agent-ping.js'; import * as setupLog from './logs.js'; import { ensureAnswer, fail, runQuietChild, runQuietStep } from './lib/runner.js'; -import { brandBold, brandChip } from './lib/theme.js'; +import { brandBold, brandChip, dimWrap, wrapForGutter } from './lib/theme.js'; const CLI_AGENT_NAME = 'Terminal Agent'; const RUN_START = Date.now(); @@ -61,8 +62,9 @@ async function main(): Promise { if (!skip.has('container')) { p.log.message( - k.dim( + dimWrap( 'Your assistant lives in its own sandbox. It can only see what you explicitly share.', + 4, ), ); const res = await runQuietStep('container', { @@ -97,8 +99,9 @@ async function main(): Promise { if (!skip.has('onecli')) { p.log.message( - k.dim( + dimWrap( 'Your assistant never gets your API keys directly. The vault adds them to approved requests as they leave the sandbox.', + 4, ), ); const res = await runQuietStep('onecli', { @@ -178,18 +181,26 @@ async function main(): Promise { const res = await runQuietStep( 'cli-agent', { - running: 'Setting up your terminal chat…', - done: 'Terminal chat ready. Try `pnpm run chat hi`.', + running: 'Bringing your assistant online…', + done: 'Assistant wired up.', }, ['--display-name', displayName!, '--agent-name', CLI_AGENT_NAME], ); if (!res.ok) { fail( 'cli-agent', - "Couldn't set up the terminal chat.", + "Couldn't bring your assistant online.", `You can retry later with \`pnpm exec tsx scripts/init-cli-agent.ts --display-name "${displayName!}" --agent-name "${CLI_AGENT_NAME}"\`.`, ); } + if (!skip.has('first-chat')) { + const ping = await confirmAssistantResponds(); + if (ping === 'ok') { + await runFirstChat(); + } else { + renderPingFailureNote(ping); + } + } } if (!skip.has('channel')) { @@ -200,7 +211,10 @@ async function main(): Promise { await runDiscordChannel(displayName!); } else { p.log.info( - "No messaging app for now. You can add one later (like Telegram, Discord, or Slack).", + wrapForGutter( + 'No messaging app for now. You can add one later (like Telegram, Discord, or Slack).', + 4, + ), ); } } @@ -216,12 +230,27 @@ async function main(): Promise { if (res.terminal?.fields.CREDENTIALS !== 'configured') { notes.push('• Your Claude account isn\'t connected. Re-run setup and try again.'); } - const agentPing = res.terminal?.fields.AGENT_PING; - if (agentPing && agentPing !== 'ok' && agentPing !== 'skipped') { + const service = res.terminal?.fields.SERVICE; + if (service === 'running_other_checkout') { notes.push( - "• Your assistant didn't reply to a test message. " + - 'Check `logs/nanoclaw.log` for clues, then try `pnpm run chat hi`.', + wrapForGutter( + [ + '• Your NanoClaw service is running from a different folder on this machine.', + ' Point it at this checkout with:', + ' launchctl bootout gui/$(id -u)/com.nanoclaw', + ' launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/com.nanoclaw.plist', + ].join('\n'), + 6, + ), ); + } else { + const agentPing = res.terminal?.fields.AGENT_PING; + if (agentPing && agentPing !== 'ok' && agentPing !== 'skipped') { + notes.push( + "• Your assistant didn't reply to a test message. " + + 'Check `logs/nanoclaw.log` for clues, then try `pnpm run chat hi`.', + ); + } } if (!res.terminal?.fields.CONFIGURED_CHANNELS) { notes.push('• Want to chat from your phone? Add a messaging app with `/add-telegram`, `/add-slack`, or `/add-discord`.'); @@ -248,6 +277,95 @@ async function main(): Promise { p.outro(k.green("You're ready! Enjoy NanoClaw.")); } +// ─── first-chat step ─────────────────────────────────────────────────── + +/** + * Round-trip ping against the CLI socket before we ask the user to chat. + * Renders its own spinner with elapsed time because a cold-start container + * boot can take 30–60s — the elapsed counter is the difference between + * "patient" and "is this hung?". Returns the raw result so the caller can + * branch between the chat loop (ok) and a diagnostic note (anything else). + */ +async function confirmAssistantResponds(): Promise { + const s = p.spinner(); + const start = Date.now(); + const label = 'Waking your assistant…'; + s.start(label); + const tick = setInterval(() => { + const elapsed = Math.round((Date.now() - start) / 1000); + s.message(`${label} ${k.dim(`(${elapsed}s)`)}`); + }, 1000); + + const result = await pingCliAgent(); + + clearInterval(tick); + const elapsed = Math.round((Date.now() - start) / 1000); + if (result === 'ok') { + s.stop(`Your assistant is ready. ${k.dim(`(${elapsed}s)`)}`); + } else { + const msg = + result === 'socket_error' + ? "Couldn't reach the NanoClaw service." + : "Your assistant didn't reply in time."; + s.stop(`${msg} ${k.dim(`(${elapsed}s)`)}`, 1); + } + return result; +} + +function renderPingFailureNote(result: PingResult): void { + const body = + result === 'socket_error' + ? [ + wrapForGutter( + "The NanoClaw service isn't listening on its local socket. Try restarting it, then chat with `pnpm run chat hi`:", + 6, + ), + '', + k.dim(' macOS: launchctl kickstart -k gui/$(id -u)/com.nanoclaw'), + k.dim(' Linux: systemctl --user restart nanoclaw'), + ].join('\n') + : wrapForGutter( + 'No reply from your assistant within 30 seconds. Check `logs/nanoclaw.log` for clues, then try `pnpm run chat hi`.', + 6, + ); + p.note(body, 'Skipping the first chat'); +} + +/** + * Chat loop. Each message is piped through `pnpm run chat`, which uses + * the same Unix-socket path the ping just exercised, so output streams + * back inline as the agent replies. An empty input ends the loop. + */ +async function runFirstChat(): Promise { + while (true) { + const answer = ensureAnswer( + await p.text({ + message: 'Say something to your assistant', + placeholder: 'press Enter with nothing to continue', + }), + ); + const text = ((answer as string | undefined) ?? '').trim(); + if (!text) return; + await sendChatMessage(text); + } +} + +function sendChatMessage(message: string): Promise { + return new Promise((resolve) => { + // `pnpm --silent` suppresses the `> nanoclaw@… chat` preamble so the + // agent's reply reads as a clean block under the prompt. Splitting on + // whitespace mirrors `pnpm run chat hello world` — chat.ts joins argv + // with spaces on the far side. + const child = spawn( + 'pnpm', + ['--silent', 'run', 'chat', ...message.split(/\s+/)], + { stdio: ['ignore', 'inherit', 'inherit'] }, + ); + child.on('close', () => resolve()); + child.on('error', () => resolve()); + }); +} + // ─── auth step (select → branch) ──────────────────────────────────────── async function runAuthStep(): Promise { @@ -440,7 +558,6 @@ function maybeReexecUnderSg(): void { function printIntro(): void { const isReexec = process.env.NANOCLAW_REEXEC_SG === '1'; - const isBootstrapped = process.env.NANOCLAW_BOOTSTRAPPED === '1'; const wordmark = `${k.bold('Nano')}${brandBold('Claw')}`; if (isReexec) { @@ -450,18 +567,11 @@ function printIntro(): void { return; } - // When we were called via nanoclaw.sh, the wordmark + subtitle were - // already printed in bash. Just open the clack gutter with a short, - // neutral intro so the flow continues without duplication. - if (isBootstrapped) { - p.intro(k.dim("Let's get you set up.")); - return; - } - - console.log(); - console.log(` ${wordmark}`); - console.log(` ${k.dim('Setting up your personal AI assistant')}`); - p.intro(k.dim("Let's get you set up.")); + // Always include the wordmark inside the clack intro line. When bash ran + // first (NANOCLAW_BOOTSTRAPPED=1) it already printed its own wordmark + // above us; the small repeat is worth it to keep the brand anchored at + // the visible top of the clack session once the bash output scrolls away. + p.intro(`${wordmark} ${k.dim("Let's get you set up.")}`); } /** diff --git a/setup/install-claude.sh b/setup/install-claude.sh new file mode 100755 index 000000000..485f0b47f --- /dev/null +++ b/setup/install-claude.sh @@ -0,0 +1,50 @@ +#!/usr/bin/env bash +# Install the Claude Code CLI on the host via the official native installer. +# Invoked from setup/register-claude-token.sh when the user picks the +# subscription auth path and `claude` is missing. The other two auth paths +# (paste OAuth token, paste API key) don't need the CLI, so this runs on +# demand rather than up front. +# +# The native installer is Node-independent (downloads a prebuilt binary to +# ~/.local/bin) and is the path Anthropic documents. This matches the +# pattern used by install-docker.sh / install-node.sh: the script itself is +# the allowlisted unit; the curl | bash pipe lives inside it. + +set -euo pipefail + +echo "=== NANOCLAW SETUP: INSTALL_CLAUDE ===" + +if command -v claude >/dev/null 2>&1; then + echo "STATUS: already-installed" + echo "CLAUDE_VERSION: $(claude --version 2>/dev/null || echo unknown)" + echo "=== END ===" + exit 0 +fi + +if ! command -v curl >/dev/null 2>&1; then + echo "STATUS: failed" + echo "ERROR: curl not available." + echo "=== END ===" + exit 1 +fi + +echo "STEP: claude-native-install" +curl -fsSL https://claude.ai/install.sh | bash + +# Native installer writes to ~/.local/bin and appends a PATH line to the +# user's rc file; that doesn't help this session, so put it on PATH now. +if [ -d "$HOME/.local/bin" ] && [[ ":$PATH:" != *":$HOME/.local/bin:"* ]]; then + export PATH="$HOME/.local/bin:$PATH" +fi +hash -r 2>/dev/null || true + +if ! command -v claude >/dev/null 2>&1; then + echo "STATUS: failed" + echo "ERROR: claude not found on PATH after install." + echo "=== END ===" + exit 1 +fi + +echo "STATUS: installed" +echo "CLAUDE_VERSION: $(claude --version 2>/dev/null || echo unknown)" +echo "=== END ===" diff --git a/setup/lib/agent-ping.ts b/setup/lib/agent-ping.ts new file mode 100644 index 000000000..8c5127f00 --- /dev/null +++ b/setup/lib/agent-ping.ts @@ -0,0 +1,50 @@ +/** + * Round-trip check against the CLI Unix socket. + * + * Shared by `setup/verify.ts` (end-of-run health check) and `setup/auto.ts` + * (confirm the freshly-wired agent actually responds before prompting the + * user to chat with it). + * + * Exit-code contract follows `scripts/chat.ts`: + * 0 → got a reply on stdout + * 2 → socket unreachable (service not running or wrong checkout) + * 3 → no reply before chat.ts's own 120s hard stop + * This wrapper also guards with its own timeout in case chat.ts hangs. + */ +import { spawn } from 'child_process'; + +export type PingResult = 'ok' | 'no_reply' | 'socket_error'; + +export function pingCliAgent(timeoutMs = 30_000): Promise { + return new Promise((resolve) => { + const child = spawn('pnpm', ['run', 'chat', 'ping'], { + stdio: ['ignore', 'pipe', 'pipe'], + }); + let stdout = ''; + let settled = false; + const timer = setTimeout(() => { + if (settled) return; + settled = true; + child.kill('SIGKILL'); + resolve('no_reply'); + }, timeoutMs); + + child.stdout.on('data', (chunk: Buffer) => { + stdout += chunk.toString('utf-8'); + }); + child.on('close', (code) => { + if (settled) return; + settled = true; + clearTimeout(timer); + if (code === 2) resolve('socket_error'); + else if (code === 0 && stdout.trim().length > 0) resolve('ok'); + else resolve('no_reply'); + }); + child.on('error', () => { + if (settled) return; + settled = true; + clearTimeout(timer); + resolve('socket_error'); + }); + }); +} diff --git a/setup/lib/theme.ts b/setup/lib/theme.ts index 9bd18a560..0a08eae37 100644 --- a/setup/lib/theme.ts +++ b/setup/lib/theme.ts @@ -37,3 +37,66 @@ export function brandChip(s: string): string { } return k.bgCyan(k.black(k.bold(s))); } + +/** + * Wrap text so it fits inside clack's gutter without the terminal's soft + * wrap breaking the `│ …` bar on long lines. Works on a single string with + * embedded `\n`s; each logical line is wrapped independently. + * + * The `gutter` argument is the total horizontal overhead clack adds for + * the component the text lives in (e.g. 4 for `p.log.*`'s `│ ` prefix; + * 6-ish for `p.note`'s box). Caller picks it; we just subtract from + * `process.stdout.columns` and hard-wrap at word boundaries. + */ +export function wrapForGutter(text: string, gutter: number): string { + const cols = process.stdout.columns ?? 80; + const width = Math.max(30, cols - gutter); + return text + .split('\n') + .map((line) => wrapLine(line, width)) + .join('\n'); +} + +/** + * Wrap + dim together. Needed instead of `k.dim(wrapForGutter(...))` + * because clack resets styling at each line break when rendering + * multi-line log content — a single outer dim envelope only colors the + * first line. Applying dim per-line gives each wrapped row its own + * `\x1b[2m…\x1b[0m` envelope so the whole block reads as one block. + */ +export function dimWrap(text: string, gutter: number): string { + return wrapForGutter(text, gutter) + .split('\n') + .map((line) => k.dim(line)) + .join('\n'); +} + +const ANSI_RE = /\x1b\[[0-9;]*m/g; + +function visibleLength(s: string): number { + return s.replace(ANSI_RE, '').length; +} + +function wrapLine(line: string, width: number): string { + if (visibleLength(line) <= width) return line; + const words = line.split(' '); + const rows: string[] = []; + let cur = ''; + let curLen = 0; + for (const word of words) { + const wLen = visibleLength(word); + if (curLen === 0) { + cur = word; + curLen = wLen; + } else if (curLen + 1 + wLen <= width) { + cur += ' ' + word; + curLen += 1 + wLen; + } else { + rows.push(cur); + cur = word; + curLen = wLen; + } + } + if (cur) rows.push(cur); + return rows.join('\n'); +} diff --git a/setup/register-claude-token.sh b/setup/register-claude-token.sh index e0707bf07..e0adfc628 100755 --- a/setup/register-claude-token.sh +++ b/setup/register-claude-token.sh @@ -25,8 +25,26 @@ HOST_PATTERN="${HOST_PATTERN:-api.anthropic.com}" command -v onecli >/dev/null \ || { echo "onecli not found. Install it first (see /setup §4)." >&2; exit 1; } -command -v claude >/dev/null \ - || { echo "claude CLI not found. Install from https://claude.ai/download" >&2; exit 1; } + +if ! command -v claude >/dev/null 2>&1; then + echo "Claude Code CLI not found — installing it now (needed for subscription sign-in)…" + SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" + if ! bash "$SCRIPT_DIR/install-claude.sh"; then + echo >&2 + echo "Couldn't install the Claude Code CLI automatically." >&2 + echo "Install it manually with" >&2 + echo " curl -fsSL https://claude.ai/install.sh | bash" >&2 + echo "and re-run setup." >&2 + exit 1 + fi + # install-claude.sh PATH additions are scoped to its own subshell; redo + # them here so the rest of this script can see the fresh `claude` binary. + if [ -d "$HOME/.local/bin" ] && [[ ":$PATH:" != *":$HOME/.local/bin:"* ]]; then + export PATH="$HOME/.local/bin:$PATH" + fi + hash -r 2>/dev/null || true +fi + command -v script >/dev/null \ || { echo "script(1) is required for PTY capture." >&2; exit 1; } diff --git a/setup/verify.ts b/setup/verify.ts index 4be9c3f15..ab0b80e0f 100644 --- a/setup/verify.ts +++ b/setup/verify.ts @@ -4,7 +4,7 @@ * * Uses better-sqlite3 directly (no sqlite3 CLI), platform-aware service checks. */ -import { execSync, spawn } from 'child_process'; +import { execSync } from 'child_process'; import fs from 'fs'; import os from 'os'; import path from 'path'; @@ -14,6 +14,7 @@ import Database from 'better-sqlite3'; import { DATA_DIR } from '../src/config.js'; import { readEnvFile } from '../src/env.js'; import { log } from '../src/log.js'; +import { pingCliAgent } from './lib/agent-ping.js'; import { getPlatform, getServiceManager, @@ -29,19 +30,35 @@ export async function run(_args: string[]): Promise { log.info('Starting verification'); - // 1. Check service status - let service = 'not_found'; + // 1. Check service status + detect checkout mismatch. + // + // Why the mismatch matters: the host binds `/cli.sock` relative + // to the project root it was started from. If the running service is from + // a sibling checkout (common for developers with multiple clones), this + // repo's `data/cli.sock` won't exist — AGENT_PING would return a + // misleading `socket_error`. Surface the mismatch directly instead. + let service: + | 'not_found' + | 'stopped' + | 'running' + | 'running_other_checkout' = 'not_found'; + let runningFromPath: string | null = null; const mgr = getServiceManager(); if (mgr === 'launchd') { try { const output = execSync('launchctl list', { encoding: 'utf-8' }); - if (output.includes('com.nanoclaw')) { - // Check if it has a PID (actually running) - const line = output.split('\n').find((l) => l.includes('com.nanoclaw')); - if (line) { - const pidField = line.trim().split(/\s+/)[0]; - service = pidField !== '-' && pidField ? 'running' : 'stopped'; + const line = output.split('\n').find((l) => l.includes('com.nanoclaw')); + if (line) { + const pidField = line.trim().split(/\s+/)[0]; + if (pidField !== '-' && pidField) { + service = 'running'; + const pid = Number(pidField); + if (Number.isInteger(pid) && pid > 0) { + runningFromPath = resolveBinaryScript(pid); + } + } else { + service = 'stopped'; } } } catch { @@ -52,6 +69,18 @@ export async function run(_args: string[]): Promise { try { execSync(`${prefix} is-active nanoclaw`, { stdio: 'ignore' }); service = 'running'; + try { + const pidStr = execSync( + `${prefix} show nanoclaw -p MainPID --value`, + { encoding: 'utf-8' }, + ).trim(); + const pid = Number(pidStr); + if (Number.isInteger(pid) && pid > 0) { + runningFromPath = resolveBinaryScript(pid); + } + } catch { + // couldn't read MainPID; leave runningFromPath null + } } catch { try { const output = execSync(`${prefix} list-unit-files`, { @@ -74,13 +103,23 @@ export async function run(_args: string[]): Promise { if (raw && Number.isInteger(pid) && pid > 0) { process.kill(pid, 0); service = 'running'; + runningFromPath = resolveBinaryScript(pid); } } catch { service = 'stopped'; } } } - log.info('Service status', { service }); + + if ( + service === 'running' && + runningFromPath && + !isPathInside(runningFromPath, projectRoot) + ) { + service = 'running_other_checkout'; + } + + log.info('Service status', { service, runningFromPath }); // 2. Check container runtime let containerRuntime = 'none'; @@ -213,46 +252,27 @@ export async function run(_args: string[]): Promise { } /** - * Send a one-word message through the CLI channel and check for a reply. - * Silent by default — stdout/stderr of the child are captured but not - * forwarded. Kills the child after 90s so verify can't hang on a wedged - * agent (chat.ts's own timeout is 120s, which is too long for setup). + * Given a PID, resolve the script path the process is executing (i.e. the + * first `.js` / `.ts` / `.mjs` arg after `node`). Returns null on any + * error — callers should treat null as "couldn't tell" and skip the + * mismatch check rather than flag a false positive. */ -function pingCliAgent(): Promise<'ok' | 'no_reply' | 'socket_error'> { - return new Promise((resolve) => { - const child = spawn('pnpm', ['run', 'chat', 'ping'], { - stdio: ['ignore', 'pipe', 'pipe'], - }); - let stdout = ''; - let settled = false; - const timer = setTimeout(() => { - if (settled) return; - settled = true; - child.kill('SIGKILL'); - resolve('no_reply'); - }, 90_000); - - child.stdout.on('data', (chunk: Buffer) => { - stdout += chunk.toString('utf-8'); - }); - child.on('close', (code) => { - if (settled) return; - settled = true; - clearTimeout(timer); - // chat.ts: exit 0 on reply, 2 on socket error, 3 on no reply. - if (code === 2) { - resolve('socket_error'); - } else if (code === 0 && stdout.trim().length > 0) { - resolve('ok'); - } else { - resolve('no_reply'); - } - }); - child.on('error', () => { - if (settled) return; - settled = true; - clearTimeout(timer); - resolve('socket_error'); - }); - }); +function resolveBinaryScript(pid: number): string | null { + try { + // BSD ps (macOS) and util-linux both honour `-o command=` (full argv, + // no header). Node argv: "node /path/to/dist/index.js ...". + const out = execSync(`ps -p ${pid} -o command=`, { + encoding: 'utf-8', + }).trim(); + const tokens = out.split(/\s+/); + const script = tokens.find((t) => /\.(js|mjs|cjs|ts)$/.test(t)); + return script ?? null; + } catch { + return null; + } +} + +function isPathInside(candidate: string, parent: string): boolean { + const rel = path.relative(parent, candidate); + return rel !== '' && !rel.startsWith('..') && !path.isAbsolute(rel); }