Slipped through during the #2035 rebase resolution — both #2030's import
and ours landed in the merge. TypeScript dedups by symbol so it didn't
fail the typecheck, but it's noise and would've eventually tripped a
linter rule.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Matches the OneCLI CLI's own format expectation ("oc_... format" per
`onecli auth login --help`) so a malformed token gets caught at setup
time rather than at first vault call.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaces the example.internal placeholder with the hosted gateway URL
so the advanced screen and --help suggest the canonical destination
out of the box.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Without `onecli auth login`, setup-time CLI calls (e.g. `secrets list`
inside anthropicSecretExists, `secrets create` in runPasteAuth) hit a
secured remote vault unauthenticated and fail silently — the auth step
sees no existing Anthropic credential and prompts the user to add one
even when it's already in the remote vault.
Two auth surfaces matter here: the CLI's persistent store via
`onecli auth login --api-key`, and ONECLI_API_KEY in .env that the
runtime SDK reads at request time. We need both.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a single config registry that drives both CLI flags and an opt-in
advanced-settings screen, so power users can override defaults like
remote OneCLI host/token or alt Anthropic endpoints without burdening
the standard linear flow with extra prompts.
Why: advanced configurations didn't fit cleanly into the existing
sequenced setup. PR #2030 took the "add another prompt step" route for
remote OneCLI; this approach instead routes those overrides through a
single source of truth so adding the next knob (alt endpoint, custom
host pattern, …) doesn't mean another prompt-or-skip decision.
setup/lib/setup-config.ts — schema (typed entry list with surface
'flag' | 'flag+ui'), name derivation (camelCase → NANOCLAW_UPPER_SNAKE
+ --kebab-case), seeded with --onecli-api-host, --onecli-api-token,
--anthropic-base-url, plus existing NANOCLAW_SKIP / NANOCLAW_DISPLAY_NAME
as flag-only entries.
setup/lib/setup-config-parse.ts — argv parser (--key value, --key=value,
--no-bool, -- terminator), env reader, applyToEnv() bridge that writes
resolved values back to process.env so existing step code keeps reading
env vars unchanged. Also --help printer.
setup/lib/setup-config-screen.ts — interactive menu loop. Entries
render with current value as hint; selecting one opens the right prompt
type (text / password for secrets / confirm / brightSelect for enums);
"Done" returns to the main flow.
setup/auto.ts — parses argv first (--help short-circuits before any
render), folds env+flags into process.env, then offers a welcome menu:
"Standard setup" (default) vs "Advanced". The onecli step branches on
NANOCLAW_ONECLI_API_HOST: if set, skips the local-vs-fresh prompt
entirely, runs pollHealth pre-flight, then calls runQuietStep with
--remote-url. Token, when provided, writes through to ONECLI_API_KEY in
.env. Welcome copy tightened (drops the duplicate wordmark/tagline) so
the bash → clack handoff reads as one flow.
setup/onecli.ts — cherries the --remote-url implementation from PR
run()) and generalizes writeEnvOnecliUrl into a writeEnvVar helper so
ONECLI_API_KEY follows the same upsert path.
nanoclaw.sh — forwards "$@" to setup:auto so flags reach the parser;
trims the redundant "Setting up your personal AI assistant" subtitle
and the bootstrap teach line so the pre-clack section isn't competing
with the clack intro for the same role.
Token plumbing only fires in --remote-url mode; local installs are
unauthenticated against localhost and don't need it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Allow connecting to an OneCLI gateway running on another host instead
of installing one locally. Adds a third choice ('Connect to a remote
OneCLI') alongside reuse/fresh in the setup wizard, prompts for the
remote URL, validates reachability before proceeding, and passes
--remote-url to the onecli step.
In onecli.ts: extracts installOnecliCliOnly() for the remote path
(installs the CLI binary but skips the gateway), exports pollHealth
for use by auto.ts, and handles --remote-url to configure api-host
and write ONECLI_URL to .env without running the full gateway install.
Absorbs battle-tested knowledge from the v2 skill into the upstream
add-signal: registration paths (new number + linked device), CAPTCHA
flow, VoIP SMS-first timing, Java prereq, config-lock warning, wiring
SQL for groups, not_member silent-drop fix, GroupV2 groupId extraction
note, and UUID-based platform ID format.
Corrects a factual error in the upstream: DM platform IDs are
signal:{UUID} (ACI), not phone numbers.
Removes the now-redundant add-signal-v2 skill.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
setup/register.ts had two bugs that prevented new channels from being
registered via `/manage-channels`:
1. createMessagingGroupAgent was called with the legacy field names
`trigger_rules` and `response_scope`. The SQL INSERT expects
`engage_mode` / `engage_pattern` / `sender_scope` / `ignored_message_policy`
(migration 010). Every register call failed with
`RangeError: Missing named parameter "engage_mode"` after the agent
and messaging group were partially created — leaving an orphaned pair.
Now mirrors scripts/init-first-agent.ts:wireIfMissing:
- Groups (is_group=1) default to engage_mode='mention' (bot only
responds when addressed).
- DMs (is_group=0) default to engage_mode='pattern' with '.' (respond
to every message).
- An explicit --trigger overrides the pattern regex.
2. The "normalize platform_id" block unconditionally prefixed
"<channel>:" even for native IDs like WhatsApp JIDs
("120363408974444974@g.us"), iMessage emails ("user@example.com"),
or Signal phones ("+15551234567") / Signal groups ("group:abc"). But
the router (src/router.ts:158) looks up messaging_groups by the raw
event.platformId from the adapter, which for these native adapters
never has a prefix. So the prefixed row was never matched — the
message was silently dropped with no "Message routed" log.
Extracted scripts/init-first-agent.ts:namespacedPlatformId into
src/platform-id.ts so both setup paths use the same heuristic (skip
the prefix for IDs containing '@', starting with '+', or starting
with 'group:'). Prevents future drift between the two paths.
Tested by: re-running `setup/index.ts --step register` for a WhatsApp
group JID, confirming the row is created with correct engage fields
and matching platform_id, then sending a test message and observing
"Message routed" with the right agent group.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds /add-gcal-tool — a sibling of /add-gmail-tool that installs
@cocal/google-calendar-mcp with the same OneCLI stub-file pattern. Skill
applies the Dockerfile + TOOL_ALLOWLIST changes at install time; trunk
stays clean so users who never run the skill don't carry the calendar
MCP in their image.
Dropped the Phase 5 dry-run section since it hardcoded a per-install
image tag slug and duplicated Phase 4's live agent test.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The upstream precedence fix (5845a5a) made agent_groups.agent_provider and
sessions.agent_provider authoritative for host-side provider contribution
(per-session mount, env passthrough), but those DB values don't propagate
into the group's container.json — and the in-container runner reads
`provider` from container.json, not from the DB. That caused a confusing
failure mode: flipping the DB column to 'codex', rebuilding, and
restarting still spawned a Claude runner because container.json had no
provider field. The old skill wording ("container receives AGENT_PROVIDER
from the resolved value") overstated the integration.
Update add-codex and add-opencode "Per group / per session" sections to
say: set `"provider": "<name>"` in the group's container.json — that's
the source the runner reads. Keep the DB columns documented for the
host-side contribution they actually drive, and spell out the
session → group → container.json → 'claude' fallback so the precedence
is still discoverable.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Phase 2 of the SKILL.md already contains the Dockerfile + TOOL_ALLOWLIST
edit instructions with an "ALREADY APPLIED" short-circuit. Keeping those
edits out of trunk means users who never run /add-gmail-tool don't carry
the Gmail MCP package in their image.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
On a fork PR, GITHUB_TOKEN is demoted to read-only regardless of the
workflow's permissions: block, so issues.addLabels() returns 403. The
label workflow silently works for PRs that skip the template (no
checkboxes ticked → no API call) and fails for PRs that actually
follow it — a hostile incentive against contributors who do the right
thing.
pull_request_target runs in the context of the base branch with full
declared permissions, which is the documented fix for this case. Safe
here because the workflow is metadata-only: it reads
context.payload.pull_request.body and calls addLabels. No checkout,
no PR-supplied code executes. A SECURITY comment is added above the
trigger to keep it that way.
Refs:
- https://docs.github.com/en/actions/reference/events-that-trigger-workflows#pull_request_target
- https://securitylab.github.com/resources/github-actions-preventing-pwn-requests/
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two long-line violations introduced in d121cd1 (isGroup plumbing)
exceed the printWidth limit. CI format:check fails on every PR
opened against main until this is fixed; the fix is isolated here
so no behavior change is mixed in.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Filenames in forwardAttachedFiles arrived from the source agent's
messages_out content and were used directly in path.join on both
source outbox read and target inbox write. A value like `../evil.sh`
could escape `inbox/<a2a-id>/` on the target session (and similarly
the source outbox on read), breaking session isolation — an
adversarial or hallucinating sub-agent could overwrite files in
a sibling session.
Adds isSafeAttachmentName(name) — exported so it's unit-testable —
which rejects empty, `.`, `..`, anything containing `/`, `\`, or
NUL, and anything path.basename would strip. Guard runs before any
I/O. Unsafe names are dropped with a warning log, same pattern as
missing-source-file handling; a bad filename in one attachment
doesn't kill the whole route's text delivery.
Addresses Codex Review P1 on qwibitai/nanoclaw#1967.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Before: `send_file(to='parent')` from a sub-agent wrote the bytes to
the sub-agent's own session outbox, but agent-to-agent routing copied
only the content JSON — the target's inbound message referenced
`files: ['x.png']` but the bytes lived in a session directory the
target couldn't mount. Parent agents orchestrating sub-agents (e.g.
Design Team delegating illustration work to an Illustrator sub-agent
on Codex) received file-reference messages with nothing to forward.
Fix: on route, if the source's content has `files`, copy each referenced
file from `<source>/outbox/<src-msg-id>/` to
`<target>/inbox/<a2a-msg-id>/`, and emit `attachments` (the existing
formatter convention — see formatter.ts:223) with `localPath` relative
to `/workspace/`. The target formatter already renders these as
`[file: <name> — saved to /workspace/inbox/<a2a-id>/<name>]`, so the
target agent sees the path and can call `send_file(path=…, to=…)` to
forward onward.
Convention matches what session-manager.ts:256 already does for
base64-encoded channel-inbound attachments — same inbox layout, same
content shape. Nothing on the formatter/agent side needed to change.
## Scope
- `forwardAttachedFiles(source, target)` — pure-ish helper that copies
files and returns the attachments array.
- `forwardFileAttachments(msg, …)` — wraps the helper for the route
path: parses content, copies files if present, merges into any
existing `attachments`, re-serialises.
- `routeAgentMessage` — uses the rewritten content when writing the
target's inbound row.
- Log line now includes `forwardedFileCount` for observability.
Missing source files are skipped with a warning rather than killing
the route — a bad filename in a batch shouldn't drop the
accompanying text.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Before, every provider stored its opaque continuation id under the
single outbound.db key `sdk_session_id`. Flipping a session's
agent_provider (e.g. Codex → Claude) meant the new provider read the
old provider's id at wake, handed it to its own SDK, and got a
"No conversation found" error that cost the user one sacrificed
message before the stale-session recovery path cleared the id.
This reshapes session_state so continuations are keyed
`continuation:<provider>` instead. Consequences:
- Per-provider continuations coexist. Flipping Claude → Codex → Claude
resumes the Claude thread exactly where it left off, with the
intervening Codex thread also still on file.
- No provider ever reads another provider's id. Switching costs no
sacrificed message and emits no transient error.
- Legacy installs are migrated forward on first startup:
migrateLegacyContinuation() adopts any pre-existing `sdk_session_id`
row into the current provider's slot (best guess — it was whichever
provider ran last), then deletes the legacy row unconditionally so
it can't poison a future provider's read.
runPollLoop now takes providerName alongside the provider instance,
and threads it through processQuery to setContinuation on init.
Tests: 9 new tests covering set/get isolation across providers,
clear-specificity, legacy-adoption, legacy-always-deleted,
prefer-existing-slot-over-legacy, and idempotency of a second
migration call.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds /add-gmail-tool — a Utility skill that installs Gmail as an MCP tool
in NanoClaw v2 using OneCLI for credential injection. No raw OAuth tokens
ever reach the container; the gateway swaps the "onecli-managed" stub
bearer for the real token at request time.
Scope (3 files):
- container/Dockerfile: pnpm global-install of
@gongrzhe/server-gmail-autoauth-mcp@1.1.11, pinned behind GMAIL_MCP_VERSION.
Also pins zod-to-json-schema@3.22.5 to avoid an ERR_PACKAGE_PATH_NOT_EXPORTED
crash: the MCP server's loose zod range resolves zod@3.24.x while
zod-to-json-schema@3.25.x imports the zod/v3 subpath that only exists in
zod>=3.25.
- container/agent-runner/src/providers/claude.ts: adds 'mcp__gmail__*' to
TOOL_ALLOWLIST so the agent can invoke the server's tools.
- .claude/skills/add-gmail-tool/SKILL.md: pre-flight checks (OneCLI Gmail app
connected, stubs present, mount allowlist covers ~/.gmail-mcp, agent
secret-mode), per-group wiring in container.json (mount + mcpServers),
verification steps, troubleshooting, removal instructions. Credits to
gongrzhe for the MCP server and the add-atomic-chat-tool / add-vercel
skill patterns.
Addresses #1500 (proxy Gmail OAuth through credential proxy) on the Gmail
side. Overlaps in intent with #1810 but stays surgical — no bundled
unrelated changes.
Tested end-to-end on Linux/Docker: CLI and WhatsApp self-chat agents can
list labels, search/read/send mail via OneCLI-injected tokens.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Migration 010-engage-modes (replace trigger_rules + response_scope with
engage_mode/engage_pattern/sender_scope/ignored_message_policy) updated
the schema and the production code paths, but missed setup/register.ts.
The step still constructed a payload with the dropped columns. On any
fresh v2 install, attempting to register a channel via:
pnpm exec tsx setup/index.ts --step register -- --platform-id ...
fails with: `Missing named parameter "engage_mode"`. This affects every
flow that calls the register step — the /add-<channel> skills,
/manage-channels, and the setup auto driver.
Map old → new:
- trigger_rules.pattern (string) → engage_mode='pattern',
engage_pattern=<pattern>
- requiresTrigger=false (no pattern) → engage_mode='pattern',
engage_pattern='.' (the "always" sentinel from migration 010)
- requiresTrigger=true (no pattern) → engage_mode='mention'
- response_scope='all' → sender_scope='all',
ignored_message_policy='drop' (conservative default matching the
migration backfill rule)
Tested by registering three Telegram channels (one DM, two groups) on a
fresh v2 install — all succeeded.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
resolveProviderContribution read only containerConfig.provider (from each
group's container.json) and ignored both agent_groups.agent_provider and
sessions.agent_provider. The provider-install skills (opencode, codex)
and CLAUDE.md document those DB columns as the source of truth with
session-overrides-group precedence, but the code never consulted them —
so setting `agent_provider = 'codex'` on a group had no effect, and the
only way to route to a non-default provider was to edit the per-group
JSON directly. Discovered while wiring up Codex: DB update landed but
the spawned container kept running Claude.
Extract a pure `resolveProviderName(session, group, containerConfig)`
with the documented precedence:
sessions.agent_provider
→ agent_groups.agent_provider
→ container.json `provider`
→ 'claude'
`resolveProviderContribution` now calls it. The container.json fallback
stays so existing installs that only set provider in JSON keep working.
Empty strings treated as unset to avoid footguns when a DB-backed form
writes '' for "no override."
Added unit tests covering precedence, null-fallthrough, empty-string
fallthrough, and case normalization.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
gavrielc