mirror of
https://github.com/qwibitai/nanoclaw.git
synced 2026-06-18 18:29:35 +08:00
Compare commits
331 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 8137440698 | |||
| 7ceb06cc8a | |||
| d011752c67 | |||
| 2e6f10cdd7 | |||
| 8906105825 | |||
| ef9e7d5f99 | |||
| 051b895b3c | |||
| 43adb1998a | |||
| 5ba4735fe9 | |||
| 3986ce0e11 | |||
| 3777a9b614 | |||
| 36fb78092c | |||
| c52591f68f | |||
| e372f05d2e | |||
| 8e91d37bc9 | |||
| bba8213cbd | |||
| 5f069221b2 | |||
| 151091f384 | |||
| 5ada950982 | |||
| 6c455330e4 | |||
| 27af41d9b0 | |||
| ea68aa810b | |||
| 5987fdc189 | |||
| 0ef8757f50 | |||
| 878d3706b4 | |||
| b52ab850b2 | |||
| 7b4dfd28c3 | |||
| 106c21a567 | |||
| 221c4948cd | |||
| c6b21e7493 | |||
| 4a8887636c | |||
| 7789fcc67a | |||
| 6ec5f06d51 | |||
| 8f4c79dcaa | |||
| 7e37b13aab | |||
| b672e8271e | |||
| f8c3d02348 | |||
| b808ab4fd2 | |||
| b9b186c9cf | |||
| b44bcf5dcf | |||
| be86bd3c2d | |||
| 6591062fbb | |||
| 26fc3ff322 | |||
| 4ebf56e2a3 | |||
| 7693a20970 | |||
| e706dcac00 | |||
| f048447ec5 | |||
| efdd05a7ef | |||
| 7de1fc1b3c | |||
| 6b431c195d | |||
| 0bc082a17c | |||
| b6be3b9bf4 | |||
| 7e99d0eaf7 | |||
| 8d8522202a | |||
| 0df647be74 | |||
| 2825f657ca | |||
| 15a6950b5b | |||
| 226fc93795 | |||
| 15e2ac7649 | |||
| f804ebf2e9 | |||
| fc375ca72b | |||
| 88d3da76c3 | |||
| 6d35c85129 | |||
| f0ebc8d6e1 | |||
| c7f8e98471 | |||
| 52f8661f0c | |||
| f37e775358 | |||
| de448ef22f | |||
| 41162517d9 | |||
| 2afcee3a4f | |||
| 9bb416c157 | |||
| beb73d792a | |||
| 8b783daa67 | |||
| 5cbfccec05 | |||
| 8637143216 | |||
| 44067e73cb | |||
| 72d0134d0a | |||
| 2b51a4e707 | |||
| 3d6837c411 | |||
| 9fd694c763 | |||
| 4fc2c4275c | |||
| 1de5a0356b | |||
| f41c162009 | |||
| fd03b89333 | |||
| 672e228876 | |||
| 81ef193e69 | |||
| 53513db5bc | |||
| 9e33274e2a | |||
| d0c608c751 | |||
| a4346f566c | |||
| 1df8dec9bd | |||
| 82baa39f20 | |||
| 5845a5a980 | |||
| ce28e7f558 | |||
| 9e480a0624 | |||
| 3fa001409e | |||
| 78b0ad68f6 | |||
| e3f4a8b0d8 | |||
| c1d0395d11 | |||
| 0eeeecf75e | |||
| 7a628bfb3c | |||
| 2fd2bf3bde | |||
| f0a0939860 | |||
| f351e46008 | |||
| 5f3bd9c880 | |||
| 5d32efbce4 | |||
| 7eda2628fa | |||
| ffd38f660a | |||
| 57eeed6cb6 | |||
| 2861009d95 | |||
| bd032c2b83 | |||
| 0e0794ca10 | |||
| 83254b12b4 | |||
| cf2b1c9755 | |||
| f3524a33bb | |||
| c6d2f45f93 | |||
| e5a7a33084 | |||
| 0ec56b732d | |||
| 97868af5a7 | |||
| ff277c0d49 | |||
| a67b4abd79 | |||
| 500353c182 | |||
| a8eb82d529 | |||
| 237876c2c6 | |||
| 209061f54f | |||
| bee80b0072 | |||
| 539af750d4 | |||
| 438dedad77 | |||
| 6475e0f0b5 | |||
| dd5bc85b02 | |||
| 97e356d243 | |||
| 94d33bcc1d | |||
| cca22e9270 | |||
| 3a9b98f1a4 | |||
| 677cc47bd1 | |||
| 40f5683c36 | |||
| 15f30682d7 | |||
| d121cd1cd6 | |||
| 61ca43d193 | |||
| 3101f65a72 | |||
| d8b1f52f2b | |||
| c84a6ba80e | |||
| 73c931594a | |||
| 2383bde80f | |||
| dee7e0be32 | |||
| 990d243dbd | |||
| 910342fd80 | |||
| 7f4583d0fe | |||
| 092f16dfaa | |||
| 4ff4cc75b9 | |||
| 56ef5b4461 | |||
| 8a19ad019a | |||
| 5f1b3e5cad | |||
| 72aba8c7ba | |||
| 3d44001633 | |||
| 7a9401ddf2 | |||
| 4f6d62a65e | |||
| 564000dcae | |||
| 601fc7c396 | |||
| cdb9442796 | |||
| c91168bd74 | |||
| 68352351e4 | |||
| 8326b4c0be | |||
| 22c2beff3c | |||
| 6cd261a26d | |||
| d97a0e1484 | |||
| 16421cc022 | |||
| 469dd9af7e | |||
| dbb859bfec | |||
| dbb82440bd | |||
| c16052ed4d | |||
| e9d056dc6c | |||
| 25687dca8f | |||
| 5df8d9d2e5 | |||
| 8412b899fa | |||
| 39ae04df98 | |||
| d2f53048f2 | |||
| 52ebdce9c9 | |||
| e2b1df876b | |||
| 3b8240a91b | |||
| e64bdb3016 | |||
| 95e74d8383 | |||
| 202ee71311 | |||
| 0ed00b3358 | |||
| 3db66c0ced | |||
| 5371c76c14 | |||
| fe942dd3dd | |||
| 8e1c8f8f61 | |||
| 8662f21e8f | |||
| 390e09597a | |||
| a70e41856b | |||
| a541e7542c | |||
| fb82c1babb | |||
| 7da24b166d | |||
| c8fc1da719 | |||
| 8a12fa61ac | |||
| 596035be09 | |||
| 4859d8fb2d | |||
| dfcbab5364 | |||
| 22ed951f05 | |||
| 4dfc2e3a24 | |||
| 3a29674b46 | |||
| e8b01bdb07 | |||
| 6ed228f9a8 | |||
| 72b7a72cbb | |||
| 9b6e5b24a1 | |||
| 1e0f7d631d | |||
| a263da3e53 | |||
| 1858ef35f0 | |||
| 7d2081660b | |||
| 9b7d4d50e4 | |||
| 416fe01855 | |||
| 5269edada4 | |||
| 6e0d742a7f | |||
| e24ecbf8b0 | |||
| 356a4d0a9f | |||
| 5a472c4155 | |||
| e7d798b00d | |||
| 92c28a956d | |||
| 9c7e1d02af | |||
| c87cd250b2 | |||
| 85faa3eab0 | |||
| d02001e144 | |||
| 81838bbb34 | |||
| 1c748f1f2b | |||
| e49cbce429 | |||
| a9a488eb27 | |||
| fb2790a5d5 | |||
| 52a9ab5179 | |||
| be6cec59ad | |||
| e86d0d93dd | |||
| fd2e404ba9 | |||
| 264849da6c | |||
| b0cae1ba4c | |||
| ee5995ae16 | |||
| 3ce4101cd9 | |||
| 2311721375 | |||
| 010722803f | |||
| 91c668e0cc | |||
| c9977d6b69 | |||
| 1f7508f2aa | |||
| 40ddc94d0a | |||
| 77e6d3bc66 | |||
| 01ffce6f74 | |||
| 9776dd4f32 | |||
| 483969a194 | |||
| 9fe529984a | |||
| d8d61d3695 | |||
| 212fc1f1b5 | |||
| 53c11a2d53 | |||
| f0090ebbb9 | |||
| 63b8beb0fb | |||
| 9ecee27b82 | |||
| 8d8126a3d7 | |||
| c778242fad | |||
| 0f6a1ba1ed | |||
| 6c26c0413a | |||
| dadf258136 | |||
| bd5e074acf | |||
| 866b7915b5 | |||
| 712a0e1e01 | |||
| ccb676ae91 | |||
| 0d145ad938 | |||
| 9870deb5dd | |||
| 97d9cf1a63 | |||
| cdefc97c37 | |||
| a29f3e5cf4 | |||
| 719f97e483 | |||
| 74c9c9e27a | |||
| 5f8a138868 | |||
| a4061a0012 | |||
| 4e1cee0e5b | |||
| 2eb6907f09 | |||
| b15972284b | |||
| ad97829151 | |||
| bc0b559461 | |||
| 68058cbc4a | |||
| f74df3b0d3 | |||
| 0105de0257 | |||
| 06918f35e0 | |||
| f894b5b1d0 | |||
| 31f2da9585 | |||
| c38e5b11a8 | |||
| ce25e1e97c | |||
| 52c6223292 | |||
| 57e0cda9e5 | |||
| 73b20880ff | |||
| fca3d8de70 | |||
| 9882c94530 | |||
| a1079da877 | |||
| aa2c77b5c7 | |||
| e9b7265874 | |||
| 5d5f72e117 | |||
| 622a370815 | |||
| 16b9499532 | |||
| 6a815190c0 | |||
| dcfa12ea06 | |||
| 0283391e0a | |||
| 47950671fa | |||
| 0dae3498c3 | |||
| 91400f9f66 | |||
| 0d09c6ea21 | |||
| 57ad3591a1 | |||
| 46c8829f2f | |||
| 96d7656112 | |||
| 5542107b9e | |||
| 0992979c5a | |||
| f553c8126c | |||
| 77fec6c7c3 | |||
| 77624d7854 | |||
| b3e8b2e047 | |||
| f6ddd20636 | |||
| 6db81554bf | |||
| 01389ff8fc | |||
| 47e3203809 | |||
| 12f50281c2 | |||
| 100e556ee9 | |||
| 2444ab171f | |||
| 09a3b48dae | |||
| cec6768f4b | |||
| 303a5c7100 | |||
| 5454bae426 | |||
| a81e1651b5 | |||
| caf23208f0 | |||
| 0d75ca26f4 | |||
| fbd8af618d | |||
| eba94b721a | |||
| da9a73b50a | |||
| dbb1b26f2a | |||
| 38163bc5c4 | |||
| 8b5b5818e0 |
@@ -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*)"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,243 @@
|
||||
---
|
||||
name: add-atomic-chat-tool
|
||||
description: Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.
|
||||
---
|
||||
|
||||
# Add Atomic Chat Integration
|
||||
|
||||
This skill adds a stdio-based MCP server that exposes models running in the local [Atomic Chat](https://github.com/AtomicBot-ai/Atomic-Chat) desktop app as tools for the container agent. Claude remains the orchestrator but can offload work to local models served by Atomic Chat on `http://127.0.0.1:1337/v1` (OpenAI-compatible).
|
||||
|
||||
Tools exposed:
|
||||
- `atomic_chat_list_models` — list models currently available in Atomic Chat (`GET /v1/models`)
|
||||
- `atomic_chat_generate` — send a prompt to a specified model and return the response (`POST /v1/chat/completions`)
|
||||
|
||||
Model management (download, delete) is done through the **Atomic Chat desktop UI** — the app is a fork of Jan and manages its own model library.
|
||||
|
||||
The skill ships the MCP server source in this folder and copies it into the agent-runner tree at install time, then wires it up with small edits to `index.ts`, `providers/claude.ts`, and `container-runner.ts`. No branch merge — all edits are additive and idempotent.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
### Check if already applied
|
||||
|
||||
Check if `container/agent-runner/src/atomic-chat-mcp-stdio.ts` exists. If it does, skip to Phase 3 (Configure).
|
||||
|
||||
### Check prerequisites
|
||||
|
||||
Verify Atomic Chat is installed and its local API server is running. On the host:
|
||||
|
||||
```bash
|
||||
curl -s http://127.0.0.1:1337/v1/models | head
|
||||
```
|
||||
|
||||
If the request fails:
|
||||
|
||||
1. Install Atomic Chat from the [latest release](https://github.com/AtomicBot-ai/Atomic-Chat/releases) (macOS only for now — `atomic-chat.dmg`).
|
||||
2. Open the app.
|
||||
3. Open **Settings → Local API Server** and make sure it's enabled on port `1337`.
|
||||
4. Go to the **Hub** (or **Models**) tab and download at least one model (e.g. Llama 3.2 3B, Qwen 2.5 Coder 7B).
|
||||
5. Load the model once by sending any message in Atomic Chat's UI to warm it up.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Copy the MCP server source
|
||||
|
||||
```bash
|
||||
cp .claude/skills/add-atomic-chat-tool/atomic-chat-mcp-stdio.ts container/agent-runner/src/atomic-chat-mcp-stdio.ts
|
||||
```
|
||||
|
||||
### Register the MCP server in the agent-runner
|
||||
|
||||
Edit `container/agent-runner/src/index.ts`. Find the `mcpServers` object that currently looks like this:
|
||||
|
||||
```ts
|
||||
const mcpServers: Record<string, { command: string; args: string[]; env: Record<string, string> }> = {
|
||||
nanoclaw: {
|
||||
command: 'bun',
|
||||
args: ['run', mcpServerPath],
|
||||
env: {},
|
||||
},
|
||||
};
|
||||
```
|
||||
|
||||
Add an `atomic_chat` entry alongside `nanoclaw`:
|
||||
|
||||
```ts
|
||||
const mcpServers: Record<string, { command: string; args: string[]; env: Record<string, string> }> = {
|
||||
nanoclaw: {
|
||||
command: 'bun',
|
||||
args: ['run', mcpServerPath],
|
||||
env: {},
|
||||
},
|
||||
atomic_chat: {
|
||||
command: 'bun',
|
||||
args: ['run', path.join(__dirname, 'atomic-chat-mcp-stdio.ts')],
|
||||
env: {
|
||||
...(process.env.ATOMIC_CHAT_HOST ? { ATOMIC_CHAT_HOST: process.env.ATOMIC_CHAT_HOST } : {}),
|
||||
...(process.env.ATOMIC_CHAT_API_KEY ? { ATOMIC_CHAT_API_KEY: process.env.ATOMIC_CHAT_API_KEY } : {}),
|
||||
},
|
||||
},
|
||||
};
|
||||
```
|
||||
|
||||
### Add the tool glob to the allowlist
|
||||
|
||||
Edit `container/agent-runner/src/providers/claude.ts`. Find `'mcp__nanoclaw__*',` in the `TOOL_ALLOWLIST` array and add `'mcp__atomic_chat__*',` on the following line:
|
||||
|
||||
```ts
|
||||
'mcp__nanoclaw__*',
|
||||
'mcp__atomic_chat__*',
|
||||
];
|
||||
```
|
||||
|
||||
### Forward host env vars into the container
|
||||
|
||||
Edit `src/container-runner.ts` in `buildContainerArgs`. Find the `TZ` env line:
|
||||
|
||||
```ts
|
||||
args.push('-e', `TZ=${TIMEZONE}`);
|
||||
```
|
||||
|
||||
Add ATOMIC_CHAT forwarding right after it:
|
||||
|
||||
```ts
|
||||
args.push('-e', `TZ=${TIMEZONE}`);
|
||||
|
||||
// Atomic Chat MCP tool: forward host overrides if set (default is host.docker.internal:1337).
|
||||
if (process.env.ATOMIC_CHAT_HOST) {
|
||||
args.push('-e', `ATOMIC_CHAT_HOST=${process.env.ATOMIC_CHAT_HOST}`);
|
||||
}
|
||||
if (process.env.ATOMIC_CHAT_API_KEY) {
|
||||
args.push('-e', `ATOMIC_CHAT_API_KEY=${process.env.ATOMIC_CHAT_API_KEY}`);
|
||||
}
|
||||
```
|
||||
|
||||
### Surface `[ATOMIC]` log lines at info level
|
||||
|
||||
In the same file, find the stderr logger:
|
||||
|
||||
```ts
|
||||
container.stderr?.on('data', (data) => {
|
||||
for (const line of data.toString().trim().split('\n')) {
|
||||
if (line) log.debug(line, { container: agentGroup.folder });
|
||||
}
|
||||
});
|
||||
```
|
||||
|
||||
Replace it with:
|
||||
|
||||
```ts
|
||||
container.stderr?.on('data', (data) => {
|
||||
for (const line of data.toString().trim().split('\n')) {
|
||||
if (!line) continue;
|
||||
if (line.includes('[ATOMIC]')) {
|
||||
log.info(line, { container: agentGroup.folder });
|
||||
} else {
|
||||
log.debug(line, { container: agentGroup.folder });
|
||||
}
|
||||
}
|
||||
});
|
||||
```
|
||||
|
||||
### Add env-var stubs to `.env.example`
|
||||
|
||||
Append to `.env.example`:
|
||||
|
||||
```bash
|
||||
# Atomic Chat MCP tool (.claude/skills/add-atomic-chat-tool)
|
||||
# Override the host where Atomic Chat exposes its OpenAI-compatible API.
|
||||
# Default: http://host.docker.internal:1337 (with fallback to localhost)
|
||||
# ATOMIC_CHAT_HOST=http://host.docker.internal:1337
|
||||
|
||||
# Optional API key. Leave unset for a local Atomic Chat install — it does not require auth.
|
||||
# ATOMIC_CHAT_API_KEY=
|
||||
```
|
||||
|
||||
### Validate code changes
|
||||
|
||||
```bash
|
||||
pnpm run build
|
||||
pnpm exec tsc -p container/agent-runner/tsconfig.json --noEmit
|
||||
./container/build.sh
|
||||
```
|
||||
|
||||
All three must be clean before proceeding.
|
||||
|
||||
## Phase 3: Configure
|
||||
|
||||
### Set Atomic Chat host (optional)
|
||||
|
||||
By default, the MCP server connects to `http://host.docker.internal:1337` (Docker Desktop) with a fallback to `localhost`. To use a custom host, add to `.env`:
|
||||
|
||||
```bash
|
||||
ATOMIC_CHAT_HOST=http://your-atomic-chat-host:1337
|
||||
```
|
||||
|
||||
### Set API key (optional)
|
||||
|
||||
Atomic Chat does **not require authentication** when running locally — leave this unset. Only set it if you've put Atomic Chat behind a reverse proxy that enforces auth:
|
||||
|
||||
```bash
|
||||
ATOMIC_CHAT_API_KEY=sk-...
|
||||
```
|
||||
|
||||
### Restart the service
|
||||
|
||||
```bash
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# Linux: systemctl --user restart nanoclaw
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
### Test inference
|
||||
|
||||
Tell the user:
|
||||
|
||||
> Send a message like: "use atomic chat to tell me the capital of France"
|
||||
>
|
||||
> The agent should use `atomic_chat_list_models` to find available models, then `atomic_chat_generate` to get a response.
|
||||
|
||||
### Check logs if needed
|
||||
|
||||
```bash
|
||||
tail -f logs/nanoclaw.log | grep -i atomic
|
||||
```
|
||||
|
||||
Look for:
|
||||
- `[ATOMIC] Listing models...` — list request started
|
||||
- `[ATOMIC] Found N models` — models discovered
|
||||
- `[ATOMIC] >>> Generating with <model>` — generation started
|
||||
- `[ATOMIC] <<< Done: <model> | Xs | N tokens | M chars` — generation completed
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Agent says "Atomic Chat is not installed" or tries to run a CLI
|
||||
|
||||
The agent is looking for a CLI that doesn't exist instead of using the MCP tools. This means:
|
||||
1. The MCP server wasn't copied — check `container/agent-runner/src/atomic-chat-mcp-stdio.ts` exists
|
||||
2. The MCP server wasn't registered — check `container/agent-runner/src/index.ts` has the `atomic_chat` entry in `mcpServers`
|
||||
3. The allowlist wasn't updated — check `container/agent-runner/src/providers/claude.ts` includes `mcp__atomic_chat__*` in `TOOL_ALLOWLIST`
|
||||
4. The container wasn't rebuilt — run `./container/build.sh`
|
||||
|
||||
### "Failed to connect to Atomic Chat"
|
||||
|
||||
1. Verify the host API is reachable: `curl http://127.0.0.1:1337/v1/models`
|
||||
2. Confirm the Local API Server is enabled in Atomic Chat's settings
|
||||
3. Check Docker can reach the host: `docker run --rm curlimages/curl curl -s http://host.docker.internal:1337/v1/models`
|
||||
4. If using a custom host, check `ATOMIC_CHAT_HOST` in `.env`
|
||||
|
||||
### `model not found` / 404 on generate
|
||||
|
||||
The model ID passed to `atomic_chat_generate` must exactly match one of the IDs returned by `atomic_chat_list_models`. Ask the agent to list models first, then pick one from that list.
|
||||
|
||||
### Slow first response
|
||||
|
||||
Atomic Chat lazy-loads models into memory on first use. The initial call may take longer while the model warms up. Subsequent calls against the same model are fast.
|
||||
|
||||
### Agent doesn't use Atomic Chat tools
|
||||
|
||||
The agent may not know about the tools. Try being explicit: "use the atomic_chat_generate tool with llama3.2-3b-instruct to answer: ..."
|
||||
|
||||
### Context window or output size issues
|
||||
|
||||
Atomic Chat respects each model's native context length. If you hit limits, pass `max_tokens` explicitly when calling `atomic_chat_generate`, or switch to a model with a larger context window in the Atomic Chat UI.
|
||||
@@ -0,0 +1,229 @@
|
||||
/**
|
||||
* Atomic Chat MCP Server for NanoClaw
|
||||
* Exposes local Atomic Chat models (OpenAI-compatible, /v1) as tools for the container agent.
|
||||
* Uses host.docker.internal to reach the host's Atomic Chat desktop app from Docker.
|
||||
*/
|
||||
|
||||
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
|
||||
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
|
||||
import { z } from 'zod';
|
||||
|
||||
import fs from 'fs';
|
||||
import path from 'path';
|
||||
|
||||
const ATOMIC_CHAT_HOST =
|
||||
process.env.ATOMIC_CHAT_HOST || 'http://host.docker.internal:1337';
|
||||
const ATOMIC_CHAT_API_KEY = process.env.ATOMIC_CHAT_API_KEY || '';
|
||||
const ATOMIC_CHAT_STATUS_FILE = '/workspace/ipc/atomic_chat_status.json';
|
||||
|
||||
function log(msg: string): void {
|
||||
console.error(`[ATOMIC] ${msg}`);
|
||||
}
|
||||
|
||||
function writeStatus(status: string, detail?: string): void {
|
||||
try {
|
||||
const data = { status, detail, timestamp: new Date().toISOString() };
|
||||
const tmpPath = `${ATOMIC_CHAT_STATUS_FILE}.tmp`;
|
||||
fs.mkdirSync(path.dirname(ATOMIC_CHAT_STATUS_FILE), { recursive: true });
|
||||
fs.writeFileSync(tmpPath, JSON.stringify(data));
|
||||
fs.renameSync(tmpPath, ATOMIC_CHAT_STATUS_FILE);
|
||||
} catch {
|
||||
/* best-effort */
|
||||
}
|
||||
}
|
||||
|
||||
async function atomicFetch(
|
||||
apiPath: string,
|
||||
options?: RequestInit,
|
||||
): Promise<Response> {
|
||||
const url = `${ATOMIC_CHAT_HOST}${apiPath}`;
|
||||
const headers: Record<string, string> = {
|
||||
...((options?.headers as Record<string, string>) || {}),
|
||||
};
|
||||
if (ATOMIC_CHAT_API_KEY) {
|
||||
headers.Authorization = `Bearer ${ATOMIC_CHAT_API_KEY}`;
|
||||
}
|
||||
const finalOptions: RequestInit = { ...options, headers };
|
||||
try {
|
||||
return await fetch(url, finalOptions);
|
||||
} catch (err) {
|
||||
// Fallback to localhost if host.docker.internal fails
|
||||
if (ATOMIC_CHAT_HOST.includes('host.docker.internal')) {
|
||||
const fallbackUrl = url.replace('host.docker.internal', 'localhost');
|
||||
return await fetch(fallbackUrl, finalOptions);
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
}
|
||||
|
||||
const server = new McpServer({
|
||||
name: 'atomic_chat',
|
||||
version: '1.0.0',
|
||||
});
|
||||
|
||||
server.tool(
|
||||
'atomic_chat_list_models',
|
||||
'List all models available in the local Atomic Chat desktop app. Use this to see which models are loaded before calling atomic_chat_generate.',
|
||||
{},
|
||||
async () => {
|
||||
log('Listing models...');
|
||||
writeStatus('listing', 'Listing available models');
|
||||
try {
|
||||
const res = await atomicFetch('/v1/models');
|
||||
if (!res.ok) {
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text' as const,
|
||||
text: `Atomic Chat API error: ${res.status} ${res.statusText}`,
|
||||
},
|
||||
],
|
||||
isError: true,
|
||||
};
|
||||
}
|
||||
|
||||
const data = (await res.json()) as {
|
||||
data?: Array<{ id: string; owned_by?: string }>;
|
||||
};
|
||||
const models = data.data || [];
|
||||
|
||||
if (models.length === 0) {
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text' as const,
|
||||
text: 'No models available. Open Atomic Chat on the host and download a model from the Hub.',
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
|
||||
const list = models
|
||||
.map((m) => `- ${m.id}${m.owned_by ? ` (${m.owned_by})` : ''}`)
|
||||
.join('\n');
|
||||
|
||||
log(`Found ${models.length} models`);
|
||||
return {
|
||||
content: [
|
||||
{ type: 'text' as const, text: `Available models:\n${list}` },
|
||||
],
|
||||
};
|
||||
} catch (err) {
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text' as const,
|
||||
text: `Failed to connect to Atomic Chat at ${ATOMIC_CHAT_HOST}: ${err instanceof Error ? err.message : String(err)}`,
|
||||
},
|
||||
],
|
||||
isError: true,
|
||||
};
|
||||
}
|
||||
},
|
||||
);
|
||||
|
||||
server.tool(
|
||||
'atomic_chat_generate',
|
||||
'Send a prompt to a local Atomic Chat model and get a response. Good for cheaper/faster tasks like summarization, translation, or general queries. Use atomic_chat_list_models first to see available models.',
|
||||
{
|
||||
model: z
|
||||
.string()
|
||||
.describe(
|
||||
'The model ID as returned by atomic_chat_list_models (e.g. "llama3.2-3b-instruct")',
|
||||
),
|
||||
prompt: z.string().describe('The prompt to send to the model'),
|
||||
system: z
|
||||
.string()
|
||||
.optional()
|
||||
.describe('Optional system prompt to set model behavior'),
|
||||
temperature: z
|
||||
.number()
|
||||
.optional()
|
||||
.describe('Sampling temperature (0.0–2.0). Defaults to model default.'),
|
||||
max_tokens: z
|
||||
.number()
|
||||
.optional()
|
||||
.describe('Maximum number of tokens to generate in the response.'),
|
||||
},
|
||||
async (args) => {
|
||||
log(`>>> Generating with ${args.model} (${args.prompt.length} chars)...`);
|
||||
writeStatus('generating', `Generating with ${args.model}`);
|
||||
try {
|
||||
const messages: Array<{ role: string; content: string }> = [];
|
||||
if (args.system) {
|
||||
messages.push({ role: 'system', content: args.system });
|
||||
}
|
||||
messages.push({ role: 'user', content: args.prompt });
|
||||
|
||||
const body: Record<string, unknown> = {
|
||||
model: args.model,
|
||||
messages,
|
||||
stream: false,
|
||||
};
|
||||
if (args.temperature !== undefined) body.temperature = args.temperature;
|
||||
if (args.max_tokens !== undefined) body.max_tokens = args.max_tokens;
|
||||
|
||||
const startedAt = Date.now();
|
||||
const res = await atomicFetch('/v1/chat/completions', {
|
||||
method: 'POST',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify(body),
|
||||
});
|
||||
|
||||
if (!res.ok) {
|
||||
const errorText = await res.text();
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text' as const,
|
||||
text: `Atomic Chat error (${res.status}): ${errorText}`,
|
||||
},
|
||||
],
|
||||
isError: true,
|
||||
};
|
||||
}
|
||||
|
||||
const data = (await res.json()) as {
|
||||
choices?: Array<{ message?: { content?: string } }>;
|
||||
usage?: {
|
||||
prompt_tokens?: number;
|
||||
completion_tokens?: number;
|
||||
total_tokens?: number;
|
||||
};
|
||||
};
|
||||
|
||||
const response = data.choices?.[0]?.message?.content ?? '';
|
||||
const elapsedSec = ((Date.now() - startedAt) / 1000).toFixed(1);
|
||||
const completionTokens = data.usage?.completion_tokens;
|
||||
|
||||
const meta = `\n\n[${args.model} | ${elapsedSec}s${
|
||||
completionTokens !== undefined ? ` | ${completionTokens} tokens` : ''
|
||||
}]`;
|
||||
|
||||
log(
|
||||
`<<< Done: ${args.model} | ${elapsedSec}s | ${
|
||||
completionTokens ?? '?'
|
||||
} tokens | ${response.length} chars`,
|
||||
);
|
||||
writeStatus(
|
||||
'done',
|
||||
`${args.model} | ${elapsedSec}s | ${completionTokens ?? '?'} tokens`,
|
||||
);
|
||||
|
||||
return { content: [{ type: 'text' as const, text: response + meta }] };
|
||||
} catch (err) {
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text' as const,
|
||||
text: `Failed to call Atomic Chat: ${err instanceof Error ? err.message : String(err)}`,
|
||||
},
|
||||
],
|
||||
isError: true,
|
||||
};
|
||||
}
|
||||
},
|
||||
);
|
||||
|
||||
const transport = new StdioServerTransport();
|
||||
await server.connect(transport);
|
||||
@@ -0,0 +1,161 @@
|
||||
---
|
||||
name: add-codex
|
||||
description: Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).
|
||||
---
|
||||
|
||||
# Codex agent provider
|
||||
|
||||
NanoClaw runs agents in a long-lived **poll loop** inside the container. The backend is selected with **`AGENT_PROVIDER`** (`claude` | `opencode` | `codex` | `mock`).
|
||||
|
||||
Trunk ships with only the `claude` provider baked in. This skill copies the Codex provider files in from the `providers` branch, wires them into the host and container barrels, updates the Dockerfile to install the Codex CLI, and rebuilds the image.
|
||||
|
||||
The Codex provider runs `codex app-server` as a child process and speaks JSON-RPC over stdio. That gives it native session resume, streaming events, MCP tool access, and `thread/compact/start` compaction — same feature bar as the Claude Agent SDK, without the Anthropic-only lock-in.
|
||||
|
||||
## Install
|
||||
|
||||
### Pre-flight
|
||||
|
||||
If all of the following are already present, skip to **Configuration**:
|
||||
|
||||
- `src/providers/codex.ts`
|
||||
- `container/agent-runner/src/providers/codex.ts`
|
||||
- `container/agent-runner/src/providers/codex-app-server.ts`
|
||||
- `container/agent-runner/src/providers/codex.factory.test.ts`
|
||||
- `import './codex.js';` line in `src/providers/index.ts`
|
||||
- `import './codex.js';` line in `container/agent-runner/src/providers/index.ts`
|
||||
- `ARG CODEX_VERSION` and `"@openai/codex@${CODEX_VERSION}"` in the pnpm global-install block in `container/Dockerfile`
|
||||
|
||||
Missing pieces — continue below. All steps are idempotent; re-running is safe.
|
||||
|
||||
### 1. Fetch the providers branch
|
||||
|
||||
```bash
|
||||
git fetch origin providers
|
||||
```
|
||||
|
||||
### 2. Copy the Codex source files
|
||||
|
||||
Wholesale copies (owned entirely by this skill — user edits to these files won't survive a re-run, as designed):
|
||||
|
||||
```bash
|
||||
git show origin/providers:src/providers/codex.ts > src/providers/codex.ts
|
||||
git show origin/providers:container/agent-runner/src/providers/codex.ts > container/agent-runner/src/providers/codex.ts
|
||||
git show origin/providers:container/agent-runner/src/providers/codex-app-server.ts > container/agent-runner/src/providers/codex-app-server.ts
|
||||
git show origin/providers:container/agent-runner/src/providers/codex.factory.test.ts > container/agent-runner/src/providers/codex.factory.test.ts
|
||||
```
|
||||
|
||||
### 3. Append the self-registration imports
|
||||
|
||||
Each barrel gets one line — alphabetical placement keeps diffs small.
|
||||
|
||||
`src/providers/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './codex.js';
|
||||
```
|
||||
|
||||
`container/agent-runner/src/providers/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './codex.js';
|
||||
```
|
||||
|
||||
### 4. Add the Codex CLI to the container Dockerfile
|
||||
|
||||
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 CLAUDE_CODE_VERSION=...`:
|
||||
|
||||
```dockerfile
|
||||
ARG CODEX_VERSION=0.124.0
|
||||
```
|
||||
|
||||
**(b)** Add a new standalone `RUN` block for the Codex CLI, after the existing per-CLI install blocks (around line 106, right after the `@anthropic-ai/claude-code` block). The Dockerfile splits each global CLI into its own layer for cache granularity — keep that pattern; do not collapse them into a single combined `pnpm install -g` call:
|
||||
|
||||
```dockerfile
|
||||
RUN --mount=type=cache,target=/root/.cache/pnpm \
|
||||
pnpm install -g "@openai/codex@${CODEX_VERSION}"
|
||||
```
|
||||
|
||||
Note: **no agent-runner package dependency** — Codex is a CLI binary, not a library. Unlike OpenCode, there's nothing to add to `container/agent-runner/package.json`.
|
||||
|
||||
### 5. Build
|
||||
|
||||
```bash
|
||||
pnpm run build # host
|
||||
pnpm exec tsc -p container/agent-runner/tsconfig.json --noEmit # container typecheck
|
||||
./container/build.sh # agent image
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
Codex supports two primary auth paths and one experimental BYO-endpoint path. Pick the one that matches your setup.
|
||||
|
||||
### Option A — ChatGPT subscription (recommended for individuals)
|
||||
|
||||
On the host (not inside the container), run Codex's OAuth login:
|
||||
|
||||
```bash
|
||||
codex login
|
||||
```
|
||||
|
||||
This writes `~/.codex/auth.json` with a subscription token. The host-side Codex provider ([src/providers/codex.ts](../../../src/providers/codex.ts)) copies `auth.json` into a per-session `~/.codex` directory mounted into the container — your host's own Codex CLI is never touched.
|
||||
|
||||
No `.env` variables required for this mode.
|
||||
|
||||
### Option B — API key (recommended for CI or API billing)
|
||||
|
||||
```env
|
||||
OPENAI_API_KEY=sk-...
|
||||
CODEX_MODEL=gpt-5.4-mini
|
||||
```
|
||||
|
||||
The host forwards both variables into the container. If both subscription (`auth.json`) and `OPENAI_API_KEY` are present, Codex prefers the subscription.
|
||||
|
||||
### Option C — BYO OpenAI-compatible endpoint (experimental)
|
||||
|
||||
Codex's built-in `openai` provider honors the `OPENAI_BASE_URL` env var directly. Point it at any OpenAI-compatible endpoint — Groq, Together, self-hosted vLLM, an OpenAI proxy, etc.
|
||||
|
||||
```env
|
||||
OPENAI_API_KEY=...
|
||||
OPENAI_BASE_URL=https://api.groq.com/openai/v1
|
||||
CODEX_MODEL=llama-3.3-70b-versatile
|
||||
```
|
||||
|
||||
Codex also ships first-class local-runner flags — `codex --oss --local-provider ollama` or `--local-provider lmstudio` — that auto-detect a local server. To use those inside NanoClaw, set `CODEX_MODEL` to a model your local runner serves and add the corresponding base URL; see the Codex CLI docs for the full `model_provider = oss` configuration.
|
||||
|
||||
**Experimental caveat:** tool-calling quality depends on the model and endpoint. Not every OpenAI-compat provider implements the full function-calling spec, and smaller models (< 30B) often struggle with multi-step tool orchestration. Test before committing.
|
||||
|
||||
### Per group / per session
|
||||
|
||||
Set `"provider": "codex"` in the group's **`container.json`** (`groups/<folder>/container.json`) — the in-container runner reads `provider` from there, not from the DB. The DB columns **`agent_groups.agent_provider`** and **`sessions.agent_provider`** (session overrides group) only drive host-side provider contribution — per-session `~/.codex` mount, `OPENAI_*` / `CODEX_MODEL` env passthrough — and do not propagate into `container.json` at spawn time. Set both, or just edit `container.json`; if they disagree, the runner uses `container.json` and the host-side resolver falls back through session → group → `container.json` → `'claude'`.
|
||||
|
||||
`CODEX_MODEL` applies process-wide via `.env`; if you need different models for different groups, set them via `container_config.env` on the group.
|
||||
|
||||
Extra MCP servers still come from **`NANOCLAW_MCP_SERVERS`** / `container_config.mcpServers` on the host. The runner merges them into the same `mcpServers` object passed to all providers.
|
||||
|
||||
## Operational notes
|
||||
|
||||
- **Spawn-per-query:** Codex's app-server is spawned fresh per query invocation, matching the OpenCode pattern. No long-lived daemon to keep healthy across sessions.
|
||||
- **Per-session `~/.codex` isolation:** each group gets its own copy of the host's `auth.json`. The container can rewrite `config.toml` freely on every wake without touching the host's Codex config.
|
||||
- **Native compaction:** kicks in automatically at 40K cumulative input tokens between turns, via `thread/compact/start`. If compaction fails, the provider logs and continues uncompacted — no fatal error.
|
||||
- **Approvals:** auto-accepted inside the container (the container is the sandbox; same posture as Claude/OpenCode).
|
||||
- **Mid-turn input:** Codex turns don't accept mid-turn messages. Follow-up `push()` calls queue and drain between turns, matching the OpenCode pattern. The poll-loop only pushes between turns anyway, so no messages are dropped.
|
||||
- **Stale thread recovery:** `isSessionInvalid` matches on stale-thread-ID errors (`thread not found`, `unknown thread`, etc.) so a cold-started app-server can recover cleanly when it sees a stored continuation it no longer has.
|
||||
|
||||
## Verify
|
||||
|
||||
```bash
|
||||
grep -q "./codex.js" container/agent-runner/src/providers/index.ts && echo "container barrel: OK"
|
||||
grep -q "./codex.js" src/providers/index.ts && echo "host barrel: OK"
|
||||
grep -q "@openai/codex@" container/Dockerfile && echo "Dockerfile install: OK"
|
||||
cd container/agent-runner && bun test src/providers/codex.factory.test.ts && cd -
|
||||
```
|
||||
|
||||
After the image rebuild, set `agent_provider = 'codex'` on a test group and send a message. Successful round-trip looks like:
|
||||
|
||||
- `init` event with a stable thread ID as continuation
|
||||
- One or more `activity` / `progress` events during the turn
|
||||
- `result` event with the model's reply
|
||||
|
||||
If the agent hangs or errors, check `~/.codex/auth.json` exists on the host (Option A) or that `OPENAI_API_KEY` is forwarding correctly (Option B) — `docker exec` into a running container and `env | grep -i openai` to confirm.
|
||||
@@ -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: `@<assistant> /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: `@<assistant> /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 `@<assistant> /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 <your-fork> /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 @<assistant> /compact from non-main as non-admin, verify denial
|
||||
# Manual: send @<assistant> /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.
|
||||
@@ -0,0 +1,62 @@
|
||||
# Remove DeltaChat
|
||||
|
||||
## 1. Disable the adapter
|
||||
|
||||
Comment out the import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
// import './deltachat.js';
|
||||
```
|
||||
|
||||
## 2. Remove credentials
|
||||
|
||||
Remove the `DC_*` lines from `.env`:
|
||||
|
||||
```bash
|
||||
DC_EMAIL
|
||||
DC_PASSWORD
|
||||
DC_IMAP_HOST
|
||||
DC_IMAP_PORT
|
||||
DC_SMTP_HOST
|
||||
DC_SMTP_PORT
|
||||
```
|
||||
|
||||
## 3. Rebuild and restart
|
||||
|
||||
```bash
|
||||
pnpm run build
|
||||
|
||||
# Linux
|
||||
systemctl --user restart nanoclaw
|
||||
|
||||
# macOS
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw
|
||||
```
|
||||
|
||||
## 4. Remove account data (optional)
|
||||
|
||||
To fully remove all account data including DeltaChat encryption keys:
|
||||
|
||||
```bash
|
||||
rm -rf dc-account/
|
||||
```
|
||||
|
||||
> **Warning:** This deletes the Autocrypt keys. Contacts who have verified your bot's key will need to re-verify if the same email address is re-used with a new account.
|
||||
|
||||
To keep the account for later reinstall, leave `dc-account/` intact.
|
||||
|
||||
## 5. Remove the package (optional)
|
||||
|
||||
```bash
|
||||
pnpm remove @deltachat/stdio-rpc-server
|
||||
```
|
||||
|
||||
## Verification
|
||||
|
||||
After removal, confirm the adapter is no longer starting:
|
||||
|
||||
```bash
|
||||
grep "deltachat" logs/nanoclaw.log | tail -5
|
||||
```
|
||||
|
||||
Expected: no `Channel adapter started` entry after the last restart.
|
||||
@@ -0,0 +1,254 @@
|
||||
---
|
||||
name: add-deltachat
|
||||
description: Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.
|
||||
---
|
||||
|
||||
# Add DeltaChat Channel
|
||||
|
||||
The adapter drives the `@deltachat/stdio-rpc-server` JSON-RPC subprocess directly — pure Node.js against the DeltaChat core library. Messages are delivered over email with Autocrypt/OpenPGP encryption.
|
||||
|
||||
## Install
|
||||
|
||||
### Pre-flight (idempotent)
|
||||
|
||||
Skip to **Credentials** if all of these are already in place:
|
||||
|
||||
- `src/channels/deltachat.ts` exists
|
||||
- `src/channels/index.ts` contains `import './deltachat.js';`
|
||||
- `@deltachat/stdio-rpc-server` 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/deltachat.ts > src/channels/deltachat.ts
|
||||
```
|
||||
|
||||
### 3. Append the self-registration import
|
||||
|
||||
Append to `src/channels/index.ts` (skip if already present):
|
||||
|
||||
```typescript
|
||||
import './deltachat.js';
|
||||
```
|
||||
|
||||
### 4. Install the adapter package (pinned)
|
||||
|
||||
```bash
|
||||
pnpm install @deltachat/stdio-rpc-server@2.49.0
|
||||
```
|
||||
|
||||
### 5. Build
|
||||
|
||||
```bash
|
||||
pnpm run build
|
||||
```
|
||||
|
||||
## Account Setup
|
||||
|
||||
A dedicated email account is strongly recommended — it will accumulate DeltaChat-formatted messages and store encryption keys. Not all providers work well with DeltaChat; check https://providers.delta.chat/ before picking one.
|
||||
|
||||
**Default security modes:** IMAP uses SSL/TLS (port 993), SMTP uses STARTTLS (port 587). Both are configurable via `.env` — see Credentials below.
|
||||
|
||||
To find the correct hostnames for a domain:
|
||||
|
||||
```bash
|
||||
node -e "require('dns').resolveMx('example.com', (e,r) => console.log(r))"
|
||||
```
|
||||
|
||||
Most providers publish their IMAP/SMTP hostnames in their help docs under "manual setup" or "IMAP access."
|
||||
|
||||
## Credentials
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
DC_EMAIL=bot@example.com
|
||||
DC_PASSWORD=your-app-password
|
||||
DC_IMAP_HOST=imap.example.com
|
||||
DC_IMAP_PORT=993
|
||||
DC_IMAP_SECURITY=1 # 1=SSL/TLS (default), 2=STARTTLS, 3=plain
|
||||
DC_SMTP_HOST=smtp.example.com
|
||||
DC_SMTP_PORT=587
|
||||
DC_SMTP_SECURITY=2 # 2=STARTTLS (default), 1=SSL/TLS, 3=plain
|
||||
```
|
||||
|
||||
Security settings are applied on every startup, so changing them in `.env` and restarting takes effect without wiping the account.
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Optional settings
|
||||
|
||||
The following are read from the process environment (not `.env`). To override them, add `Environment=` lines to the systemd service unit or your launchd plist:
|
||||
|
||||
| Variable | Default | Description |
|
||||
|----------|---------|-------------|
|
||||
| `DC_ACCOUNT_DIR` | `dc-account` | Directory for DeltaChat account data (IMAP state, keys, blobs) |
|
||||
| `DC_DISPLAY_NAME` | `NanoClaw` | Bot display name shown in DeltaChat |
|
||||
| `DC_AVATAR_PATH` | _(none)_ | Absolute path to avatar image; set at startup only |
|
||||
|
||||
The `/set-avatar` command (send an image with that caption) is the easiest way to set the avatar at runtime without modifying the service file. Only users with `owner` or global `admin` role can use it.
|
||||
|
||||
### Restart
|
||||
|
||||
```bash
|
||||
# Linux
|
||||
systemctl --user restart nanoclaw
|
||||
|
||||
# macOS
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw
|
||||
```
|
||||
|
||||
On first start the adapter configures the email account (IMAP/SMTP credentials, calls `configure()`). Subsequent starts skip straight to `startIo()`. Account data is stored in `dc-account/` in the project root (or your `DC_ACCOUNT_DIR`).
|
||||
|
||||
## Wiring
|
||||
|
||||
### DMs
|
||||
|
||||
**DeltaChat contacts cannot be added by email alone** — to start a chat, the user must open the bot's invite link in their DeltaChat app or scan its QR code. This triggers the SecureJoin handshake.
|
||||
|
||||
#### Step 1 — Get the invite link
|
||||
|
||||
After the service starts, the adapter logs the invite URL and writes a QR SVG:
|
||||
|
||||
```bash
|
||||
grep "invite link" logs/nanoclaw.log | tail -1
|
||||
# url field contains the https://i.delta.chat/... invite link
|
||||
# also written to dc-account/invite-qr.svg (or $DC_ACCOUNT_DIR/invite-qr.svg)
|
||||
```
|
||||
|
||||
The invite URL is stable (tied to the bot's email and encryption keys) so it stays valid across restarts.
|
||||
|
||||
#### Step 2 — Add the bot in DeltaChat
|
||||
|
||||
Two options for the user to connect:
|
||||
|
||||
- **Link**: Copy the `https://i.delta.chat/...` URL and open it on the device running DeltaChat. The app recognises it and shows a "Start chat" prompt.
|
||||
- **QR code**: Open `dc-account/invite-qr.svg` in a browser or image viewer, display it on screen, and scan it from the DeltaChat app using the QR-scan button on the new-chat screen.
|
||||
|
||||
After accepting, DeltaChat exchanges keys and creates the chat automatically.
|
||||
|
||||
#### Step 3 — Wire the chat to an agent
|
||||
|
||||
Once the first message arrives the router auto-creates a `messaging_groups` row. Look up the chat ID:
|
||||
|
||||
```bash
|
||||
sqlite3 data/v2.db \
|
||||
"SELECT platform_id, name FROM messaging_groups WHERE channel_type='deltachat' AND is_group=0 ORDER BY created_at DESC LIMIT 5"
|
||||
```
|
||||
|
||||
Then run `/init-first-agent` — it creates the agent group, grants the user owner access, and wires the messaging group in one step:
|
||||
|
||||
```bash
|
||||
pnpm exec tsx scripts/init-first-agent.ts \
|
||||
--channel deltachat \
|
||||
--user-id deltachat:user@example.com \
|
||||
--platform-id <platform_id from above> \
|
||||
--display-name "Your Name"
|
||||
```
|
||||
|
||||
### Groups
|
||||
|
||||
Add the bot email to a DeltaChat group. When any member sends a message, the router creates a `messaging_groups` row with `is_group = 1`. Run `/manage-channels` to wire it to an agent group.
|
||||
|
||||
## Next Steps
|
||||
|
||||
If you're in the middle of `/setup`, return to the setup flow now.
|
||||
|
||||
Otherwise, run `/init-first-agent` to create an agent and wire it to your DeltaChat DM (see Wiring above), or `/manage-channels` to wire this channel to an existing agent group.
|
||||
|
||||
## Channel Info
|
||||
|
||||
- **type**: `deltachat`
|
||||
- **terminology**: DeltaChat calls them "chats" (1:1 DMs) and "groups"
|
||||
- **supports-threads**: no — DeltaChat has no thread model
|
||||
- **platform-id-format**: numeric chat ID as a string (e.g. `"12"`) — the DeltaChat core's internal chat identifier
|
||||
- **user-id-format**: `deltachat:{email}` — the contact's email address
|
||||
- **how-to-find-id**: Send a message from DeltaChat to the bot email, then query `messaging_groups` as shown above
|
||||
- **typical-use**: Personal assistant over DeltaChat DMs; small groups where participants use DeltaChat
|
||||
- **default-isolation**: One agent per bot identity. Multiple chats with the same operator can share an agent group; groups with other people should typically use `isolated` session mode
|
||||
|
||||
### Features
|
||||
|
||||
- File attachments — inbound and outbound; inbound waits up to 30 seconds for large-message download to complete
|
||||
- Invite link logged on every startup — URL + QR SVG written to `dc-account/invite-qr.svg`; see Wiring for the bootstrap flow
|
||||
- `/set-avatar` — send an image with this caption to change the bot's DeltaChat avatar (admin/owner only)
|
||||
- Connectivity watchdog — restarts IO if IMAP goes quiet for 20 minutes or connectivity drops below threshold for two consecutive 5-minute checks
|
||||
- Network nudge — `maybeNetwork()` called every 10 minutes to recover from prolonged idle
|
||||
|
||||
Not supported: DeltaChat reactions, message editing/deletion, read receipts.
|
||||
|
||||
### Connectivity model
|
||||
|
||||
`isConnected()` returns `true` when the internal connectivity value is ≥ 3000:
|
||||
|
||||
| Range | Meaning |
|
||||
|-------|---------|
|
||||
| 1000–1999 | Not connected |
|
||||
| 2000–2999 | Connecting |
|
||||
| 3000–3999 | Working (IMAP fetching) |
|
||||
| ≥ 4000 | Fully connected (IMAP IDLE) |
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Adapter not starting — credentials missing
|
||||
|
||||
```bash
|
||||
grep "Channel credentials missing" logs/nanoclaw.log | grep deltachat
|
||||
```
|
||||
|
||||
All six required vars (`DC_EMAIL`, `DC_PASSWORD`, `DC_IMAP_HOST`, `DC_IMAP_PORT`, `DC_SMTP_HOST`, `DC_SMTP_PORT`) must be present in `.env`.
|
||||
|
||||
### Account configure fails
|
||||
|
||||
```bash
|
||||
grep "DeltaChat" logs/nanoclaw.log | tail -20
|
||||
```
|
||||
|
||||
Common causes:
|
||||
- Wrong IMAP/SMTP hostnames — double-check provider docs
|
||||
- App password not generated — Gmail and some others require this when 2FA is enabled
|
||||
- Port/security mismatch — defaults are port 993 + SSL/TLS for IMAP and port 587 + STARTTLS for SMTP; override with `DC_IMAP_PORT`/`DC_IMAP_SECURITY` or `DC_SMTP_PORT`/`DC_SMTP_SECURITY` in `.env`
|
||||
|
||||
### Provider uses SMTP port 465 (SSL/TLS) instead of 587
|
||||
|
||||
Set `DC_SMTP_SECURITY=1` and `DC_SMTP_PORT=465` in `.env`, then restart.
|
||||
|
||||
### Messages not arriving
|
||||
|
||||
1. Check the service is running and the adapter started: `grep "Channel adapter started.*deltachat" logs/nanoclaw.log`
|
||||
2. Check connectivity: `grep "DeltaChat: IO started" logs/nanoclaw.log`
|
||||
3. Check the sender has been granted access — run `/init-first-agent` to create their user record and wire the chat
|
||||
4. Verify the messaging group is wired: `sqlite3 data/v2.db "SELECT mg.platform_id, mga.agent_group_id FROM messaging_groups mg JOIN messaging_group_agents mga ON mg.id = mga.messaging_group_id WHERE mg.channel_type='deltachat'"`
|
||||
|
||||
### Stale lock file after crash
|
||||
|
||||
```bash
|
||||
rm -f dc-account/accounts.lock
|
||||
systemctl --user restart nanoclaw
|
||||
```
|
||||
|
||||
### Bot not responding after restart
|
||||
|
||||
The account is already configured — IO restarts automatically on service start. If the RPC subprocess is stuck, restart the service. Check for errors:
|
||||
|
||||
```bash
|
||||
grep "DeltaChat" logs/nanoclaw.error.log | tail -20
|
||||
```
|
||||
|
||||
### Messages received but agent not responding
|
||||
|
||||
The messaging group exists but may not be wired to an agent group. Run:
|
||||
|
||||
```bash
|
||||
sqlite3 data/v2.db "SELECT id, platform_id, name FROM messaging_groups WHERE channel_type='deltachat'"
|
||||
```
|
||||
|
||||
If the group has no entry in `messaging_group_agents`, wire it with `/manage-channels`.
|
||||
@@ -0,0 +1,54 @@
|
||||
# Verify DeltaChat
|
||||
|
||||
## 1. Check the adapter started
|
||||
|
||||
```bash
|
||||
grep "Channel adapter started.*deltachat" logs/nanoclaw.log | tail -1
|
||||
```
|
||||
|
||||
Expected: `Channel adapter started { channel: 'deltachat', type: 'deltachat' }`
|
||||
|
||||
## 2. Check IMAP/SMTP connectivity
|
||||
|
||||
Replace with your provider's hostnames from `.env`:
|
||||
|
||||
```bash
|
||||
DC_IMAP=$(grep '^DC_IMAP_HOST=' .env | cut -d= -f2)
|
||||
DC_SMTP=$(grep '^DC_SMTP_HOST=' .env | cut -d= -f2)
|
||||
|
||||
bash -c "echo >/dev/tcp/$DC_IMAP/993" && echo "IMAP open" || echo "IMAP blocked"
|
||||
bash -c "echo >/dev/tcp/$DC_SMTP/587" && echo "SMTP open" || echo "SMTP blocked"
|
||||
```
|
||||
|
||||
## 3. End-to-end message test
|
||||
|
||||
1. Open DeltaChat on your device
|
||||
2. Add the bot email address as a contact
|
||||
3. Send a message
|
||||
4. The bot should respond within a few seconds
|
||||
|
||||
If nothing arrives, check:
|
||||
|
||||
```bash
|
||||
grep "DeltaChat" logs/nanoclaw.log | tail -20
|
||||
grep "DeltaChat" logs/nanoclaw.error.log | tail -10
|
||||
```
|
||||
|
||||
## 4. Check messaging group was created
|
||||
|
||||
```bash
|
||||
sqlite3 data/v2.db \
|
||||
"SELECT id, platform_id, name FROM messaging_groups WHERE channel_type='deltachat' ORDER BY created_at DESC LIMIT 5"
|
||||
```
|
||||
|
||||
If a row appears, the inbound routing is working. If not, the adapter isn't receiving the message — check logs for `DeltaChat: error handling incoming message`.
|
||||
|
||||
## 5. Verify user access
|
||||
|
||||
If the message arrived but the agent didn't respond, the sender may not have access:
|
||||
|
||||
```bash
|
||||
sqlite3 data/v2.db "SELECT id, display_name FROM users WHERE id LIKE 'deltachat:%'"
|
||||
```
|
||||
|
||||
Grant access as shown in the SKILL.md "Grant user access" section.
|
||||
+134
-127
@@ -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=<random> # 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 "<existing-folder>" --channel "emacs" \
|
||||
--session-mode "agent-shared" \
|
||||
--assistant-name "<existing-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 "<your-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 <your-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 <token>" "http://localhost:8766/api/messages?since=0"
|
||||
curl -s -H "Authorization: Bearer <token>" 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:<username>`).
|
||||
- **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)
|
||||
# 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';"
|
||||
```
|
||||
|
||||
@@ -0,0 +1,210 @@
|
||||
---
|
||||
name: add-gcal-tool
|
||||
description: Add Google Calendar as an MCP tool (list calendars, list/search/create events, free/busy queries) using OneCLI-managed OAuth. Multi-calendar and multi-account supported. Mirrors /add-gmail-tool's stub pattern — no raw credentials ever reach the container; OneCLI injects real tokens at request time.
|
||||
---
|
||||
|
||||
# Add Google Calendar Tool (OneCLI-native)
|
||||
|
||||
This skill wires [`@cocal/google-calendar-mcp`](https://github.com/cocal-com/google-calendar-mcp) into selected agent groups. The MCP server reads stub credentials containing the `onecli-managed` placeholder; the OneCLI gateway intercepts outbound calls to `calendar.googleapis.com` / `oauth2.googleapis.com` and swaps the bearer for the real OAuth token from its vault.
|
||||
|
||||
**Why this package (and not gongrzhe's):** `@gongrzhe/server-calendar-autoauth-mcp` only supports the `primary` calendar and exposes 5 tools (no `list_calendars`). `@cocal/google-calendar-mcp` explicitly supports multi-calendar and multi-account, and is actively maintained.
|
||||
|
||||
Tools exposed (surfaced as `mcp__calendar__<name>`, exact set depends on version — run `tools/list` against the MCP server to enumerate): `list-calendars`, `list-events`, `search-events`, `create-event`, `update-event`, `delete-event`, `get-event`, `list-colors`, `get-freebusy`, `get-current-time`, plus multi-account management tools.
|
||||
|
||||
**Why this pattern:** v2's invariant is that containers never receive raw API keys (CHANGELOG 2.0.0). Same stub pattern `/add-gmail-tool` uses. This skill is deliberately a sibling, not a combined "Google Workspace" skill — installs independently and removes cleanly.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
### Verify OneCLI has Google Calendar connected
|
||||
|
||||
```bash
|
||||
onecli apps get --provider google-calendar
|
||||
```
|
||||
|
||||
Expected: `"connection": { "status": "connected" }` with scopes including `calendar.readonly` and `calendar.events`.
|
||||
|
||||
If not connected, tell the user:
|
||||
|
||||
> Open the OneCLI web UI at http://127.0.0.1:10254, go to Apps → Google Calendar, and click Connect. Sign in with the Google account the agent should act as. `calendar.readonly` + `calendar.events` are the minimum useful scopes.
|
||||
|
||||
### Verify stub credentials exist
|
||||
|
||||
The stub lives at `~/.calendar-mcp/` by convention (shared with `/add-gmail-tool`'s sibling). cocal doesn't default to this path (it uses `~/.config/google-calendar-mcp/tokens.json`) — we override via env vars below so it reads our stubs instead.
|
||||
|
||||
```bash
|
||||
ls -la ~/.calendar-mcp/gcp-oauth.keys.json ~/.calendar-mcp/credentials.json 2>&1
|
||||
```
|
||||
|
||||
If both exist with `onecli-managed`:
|
||||
|
||||
```bash
|
||||
grep -l onecli-managed ~/.calendar-mcp/gcp-oauth.keys.json ~/.calendar-mcp/credentials.json
|
||||
```
|
||||
|
||||
...skip to Phase 2. If either file has real credentials (no `onecli-managed`), **STOP** — back up and delete before proceeding.
|
||||
|
||||
If absent, write them:
|
||||
|
||||
```bash
|
||||
mkdir -p ~/.calendar-mcp
|
||||
cat > ~/.calendar-mcp/gcp-oauth.keys.json <<'EOF'
|
||||
{
|
||||
"installed": {
|
||||
"client_id": "onecli-managed.apps.googleusercontent.com",
|
||||
"client_secret": "onecli-managed",
|
||||
"redirect_uris": ["http://localhost:3000/oauth2callback"]
|
||||
}
|
||||
}
|
||||
EOF
|
||||
cat > ~/.calendar-mcp/credentials.json <<'EOF'
|
||||
{
|
||||
"access_token": "onecli-managed",
|
||||
"refresh_token": "onecli-managed",
|
||||
"token_type": "Bearer",
|
||||
"expiry_date": 99999999999999,
|
||||
"scope": "https://www.googleapis.com/auth/calendar.readonly https://www.googleapis.com/auth/calendar.events"
|
||||
}
|
||||
EOF
|
||||
chmod 600 ~/.calendar-mcp/*.json
|
||||
```
|
||||
|
||||
### Verify mount allowlist covers the path
|
||||
|
||||
```bash
|
||||
cat ~/.config/nanoclaw/mount-allowlist.json
|
||||
```
|
||||
|
||||
`~/.calendar-mcp` must sit under an `allowedRoots` entry.
|
||||
|
||||
### Check agent secret-mode
|
||||
|
||||
For each target agent group, confirm OneCLI will inject the Google Calendar token:
|
||||
|
||||
```bash
|
||||
onecli agents list
|
||||
```
|
||||
|
||||
`secretMode: all` is sufficient. If `selective`, explicitly assign the Calendar secret.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Check if already applied
|
||||
|
||||
```bash
|
||||
grep -q 'CALENDAR_MCP_VERSION' container/Dockerfile && \
|
||||
grep -q "mcp__calendar__\*" container/agent-runner/src/providers/claude.ts && \
|
||||
echo "ALREADY APPLIED — skip to Phase 3"
|
||||
```
|
||||
|
||||
### Add MCP server to Dockerfile
|
||||
|
||||
Edit `container/Dockerfile`. Find the pinned-version ARG block and add:
|
||||
|
||||
```dockerfile
|
||||
ARG CALENDAR_MCP_VERSION=2.6.1
|
||||
```
|
||||
|
||||
If `/add-gmail-tool` has already been applied, the pnpm global-install block already exists with its `zod-to-json-schema@3.22.5` pin. Just append the calendar package — **the calendar-mcp uses `zod@4.x` and does NOT need that pin**, but it's harmless to share the block:
|
||||
|
||||
```dockerfile
|
||||
RUN --mount=type=cache,target=/root/.cache/pnpm \
|
||||
pnpm install -g \
|
||||
"@gongrzhe/server-gmail-autoauth-mcp@${GMAIL_MCP_VERSION}" \
|
||||
"@cocal/google-calendar-mcp@${CALENDAR_MCP_VERSION}" \
|
||||
"zod-to-json-schema@3.22.5"
|
||||
```
|
||||
|
||||
If `/add-gmail-tool` hasn't been applied, install Calendar standalone:
|
||||
|
||||
```dockerfile
|
||||
RUN --mount=type=cache,target=/root/.cache/pnpm \
|
||||
pnpm install -g "@cocal/google-calendar-mcp@${CALENDAR_MCP_VERSION}"
|
||||
```
|
||||
|
||||
### Add tools to allowlist
|
||||
|
||||
Edit `container/agent-runner/src/providers/claude.ts`. Add `'mcp__calendar__*'` to `TOOL_ALLOWLIST` after `'mcp__nanoclaw__*'` (or after `'mcp__gmail__*'` if present).
|
||||
|
||||
### Rebuild the container image
|
||||
|
||||
```bash
|
||||
./container/build.sh
|
||||
```
|
||||
|
||||
## Phase 3: Wire Per-Agent-Group
|
||||
|
||||
For each agent group, merge into `groups/<folder>/container.json`:
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"mcpServers": {
|
||||
"calendar": {
|
||||
"command": "google-calendar-mcp",
|
||||
"args": [],
|
||||
"env": {
|
||||
"GOOGLE_OAUTH_CREDENTIALS": "/workspace/extra/.calendar-mcp/gcp-oauth.keys.json",
|
||||
"GOOGLE_CALENDAR_MCP_TOKEN_PATH": "/workspace/extra/.calendar-mcp/credentials.json"
|
||||
}
|
||||
}
|
||||
},
|
||||
"additionalMounts": [
|
||||
{
|
||||
"hostPath": "/home/<user>/.calendar-mcp",
|
||||
"containerPath": ".calendar-mcp",
|
||||
"readonly": false
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Substitute `<user>` with `echo $HOME`. `containerPath` is relative (mount-security rejects absolute paths — additional mounts land at `/workspace/extra/<relative>`).
|
||||
|
||||
**Same-group-as-gmail tip:** if this group already has the gmail MCP + `.gmail-mcp` mount, **merge, don't replace** — both entries coexist in `mcpServers` and `additionalMounts`.
|
||||
|
||||
## Phase 4: Build and Restart
|
||||
|
||||
```bash
|
||||
pnpm run build
|
||||
systemctl --user restart nanoclaw # Linux
|
||||
# launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
```
|
||||
|
||||
Kill any existing agent containers so they respawn with the new mcpServers config:
|
||||
|
||||
```bash
|
||||
docker ps -q --filter 'name=nanoclaw-v2-' | xargs -r docker kill
|
||||
```
|
||||
|
||||
## Phase 5: Verify
|
||||
|
||||
### Test from a wired agent
|
||||
|
||||
> Send: **"list my calendars"** or **"what's on my work calendar next Monday?"**.
|
||||
>
|
||||
> First call takes 2–3s while the MCP server starts and OneCLI does the token exchange.
|
||||
|
||||
### Check logs if the tool isn't working
|
||||
|
||||
```bash
|
||||
tail -100 logs/nanoclaw.log | grep -iE 'calendar|mcp'
|
||||
```
|
||||
|
||||
Common signals:
|
||||
- `command not found: google-calendar-mcp` → image not rebuilt.
|
||||
- `ENOENT ...credentials.json` → mount missing. Check the mount allowlist.
|
||||
- `401 Unauthorized` from `*.googleapis.com` → OneCLI isn't injecting; verify agent's secret mode and that Google Calendar is connected.
|
||||
- Agent says "I don't have calendar tools" → `mcp__calendar__*` missing from `TOOL_ALLOWLIST`, or image cache stale (`./container/build.sh` again).
|
||||
|
||||
## Removal
|
||||
|
||||
1. Delete `"calendar"` from `mcpServers` and the `.calendar-mcp` mount from `additionalMounts` in each group's `container.json`.
|
||||
2. Remove `'mcp__calendar__*'` from `TOOL_ALLOWLIST`.
|
||||
3. Remove `CALENDAR_MCP_VERSION` ARG and the calendar package from the Dockerfile install block.
|
||||
4. `pnpm run build && ./container/build.sh && systemctl --user restart nanoclaw`.
|
||||
5. Optional: `rm -rf ~/.calendar-mcp/` and `onecli apps disconnect --provider google-calendar`.
|
||||
|
||||
## Credits & references
|
||||
|
||||
- **MCP server:** [`@cocal/google-calendar-mcp`](https://github.com/cocal-com/google-calendar-mcp) — MIT-licensed, actively maintained, multi-account and multi-calendar.
|
||||
- **Why not gongrzhe:** earlier versions of this skill used `@gongrzhe/server-calendar-autoauth-mcp@1.0.2` which only supports the primary calendar with 5 event-level tools. The cocal server supersedes it.
|
||||
- **Skill pattern:** direct sibling of [`/add-gmail-tool`](../add-gmail-tool/SKILL.md); same OneCLI stub mechanism.
|
||||
@@ -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, '<policy>', 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', '<your-agent-group-id>', '', 'all', 'per-thread', 10, datetime('now'));
|
||||
```
|
||||
|
||||
Replace `<policy>` 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:<numeric-user-id>')
|
||||
INSERT OR IGNORE INTO users (id, kind, display_name, created_at)
|
||||
VALUES ('github:<user-id>', 'github', '<username>', datetime('now'));
|
||||
|
||||
-- Grant membership to the agent group
|
||||
INSERT OR IGNORE INTO agent_group_members (user_id, agent_group_id)
|
||||
VALUES ('github:<user-id>', '<agent-group-id>');
|
||||
```
|
||||
|
||||
To find a GitHub user's numeric ID: `gh api users/<username> --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.
|
||||
|
||||
@@ -0,0 +1,229 @@
|
||||
---
|
||||
name: add-gmail-tool
|
||||
description: Add Gmail as an MCP tool (read, search, send, label, draft) using OneCLI-managed OAuth. The agent gets Gmail tools in every enabled group; OneCLI injects real tokens at request time so no raw credentials are ever in the container or on disk in usable form.
|
||||
---
|
||||
|
||||
# Add Gmail Tool (OneCLI-native)
|
||||
|
||||
This skill wires the [`@gongrzhe/server-gmail-autoauth-mcp`](https://www.npmjs.com/package/@gongrzhe/server-gmail-autoauth-mcp) stdio MCP server into selected agent groups. The MCP server reads stub credentials containing the `onecli-managed` placeholder; the OneCLI gateway intercepts outbound calls to `gmail.googleapis.com` and injects the real OAuth bearer from its vault.
|
||||
|
||||
Tools exposed (from `gmail-mcp@1.1.11`, surfaced to the agent as `mcp__gmail__<name>`): `search_emails`, `read_email`, `send_email`, `draft_email`, `delete_email`, `modify_email`, `batch_modify_emails`, `batch_delete_emails`, `download_attachment`, `list_email_labels`, `create_label`, `update_label`, `delete_label`, `get_or_create_label`, `list_filters`, `get_filter`, `create_filter`, `create_filter_from_template`, `delete_filter`.
|
||||
|
||||
**Why this pattern:** v2's invariant is that containers never receive raw API keys — OneCLI is the sole credential path (see CHANGELOG v2.0.0). The stub-file pattern satisfies this: the container sees `"onecli-managed"` placeholders, the gateway swaps them in flight.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
### Verify OneCLI has Gmail connected
|
||||
|
||||
```bash
|
||||
onecli apps get --provider gmail
|
||||
```
|
||||
|
||||
Expected: `"connection": { "status": "connected" }` with scopes including `gmail.readonly`, `gmail.modify`, `gmail.send`.
|
||||
|
||||
If not connected, tell the user:
|
||||
|
||||
> Open the OneCLI web UI at http://127.0.0.1:10254, go to Apps → Gmail, and click Connect. Sign in with the Google account you want the agent to act as.
|
||||
|
||||
### Verify stub credentials exist
|
||||
|
||||
```bash
|
||||
ls -la ~/.gmail-mcp/gcp-oauth.keys.json ~/.gmail-mcp/credentials.json 2>&1
|
||||
```
|
||||
|
||||
If both exist and contain `"onecli-managed"`:
|
||||
|
||||
```bash
|
||||
grep -l onecli-managed ~/.gmail-mcp/gcp-oauth.keys.json ~/.gmail-mcp/credentials.json
|
||||
```
|
||||
|
||||
...skip to Phase 2.
|
||||
|
||||
If either file exists but does **not** contain `onecli-managed`, **STOP** and tell the user — these are real OAuth credentials from a previous non-OneCLI install. Back them up, then delete before proceeding. The OneCLI migration normally handles this; if it didn't, something is wrong.
|
||||
|
||||
If both files are absent, write them now:
|
||||
|
||||
```bash
|
||||
mkdir -p ~/.gmail-mcp
|
||||
cat > ~/.gmail-mcp/gcp-oauth.keys.json <<'EOF'
|
||||
{
|
||||
"installed": {
|
||||
"client_id": "onecli-managed.apps.googleusercontent.com",
|
||||
"client_secret": "onecli-managed",
|
||||
"redirect_uris": ["http://localhost:3000/oauth2callback"]
|
||||
}
|
||||
}
|
||||
EOF
|
||||
cat > ~/.gmail-mcp/credentials.json <<'EOF'
|
||||
{
|
||||
"access_token": "onecli-managed",
|
||||
"refresh_token": "onecli-managed",
|
||||
"token_type": "Bearer",
|
||||
"expiry_date": 99999999999999,
|
||||
"scope": "https://www.googleapis.com/auth/gmail.readonly https://www.googleapis.com/auth/gmail.modify https://www.googleapis.com/auth/gmail.send"
|
||||
}
|
||||
EOF
|
||||
chmod 600 ~/.gmail-mcp/gcp-oauth.keys.json ~/.gmail-mcp/credentials.json
|
||||
```
|
||||
|
||||
### Verify mount allowlist covers the path
|
||||
|
||||
```bash
|
||||
cat ~/.config/nanoclaw/mount-allowlist.json
|
||||
```
|
||||
|
||||
`~/.gmail-mcp` must sit under an `allowedRoots` entry (e.g. `/home/<user>`). If it doesn't, tell the user to run `/manage-mounts` first or add their home directory.
|
||||
|
||||
### Check agent secret-mode
|
||||
|
||||
For each target agent group, confirm OneCLI will inject Gmail secrets into its container. Find the OneCLI agent ID that matches the group's `agentGroupId`:
|
||||
|
||||
```bash
|
||||
onecli agents list
|
||||
```
|
||||
|
||||
If that agent's `secretMode` is `all`, you're done — Gmail secrets (identified by OneCLI's Gmail hostPattern) will auto-inject. If it's `selective`, explicitly assign the Gmail secrets:
|
||||
|
||||
```bash
|
||||
onecli secrets list # find Gmail secret IDs (OneCLI creates one per connected app)
|
||||
onecli agents set-secrets --id <agent-id> --secret-ids <gmail-secret-id>
|
||||
```
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Check if already applied
|
||||
|
||||
```bash
|
||||
grep -q 'GMAIL_MCP_VERSION' container/Dockerfile && \
|
||||
grep -q "mcp__gmail__\*" container/agent-runner/src/providers/claude.ts && \
|
||||
echo "ALREADY APPLIED — skip to Phase 3"
|
||||
```
|
||||
|
||||
### Add MCP server to Dockerfile
|
||||
|
||||
Edit `container/Dockerfile`. Find the pinned-version ARG block:
|
||||
|
||||
```dockerfile
|
||||
ARG CLAUDE_CODE_VERSION=2.1.116
|
||||
ARG AGENT_BROWSER_VERSION=latest
|
||||
ARG VERCEL_VERSION=latest
|
||||
ARG BUN_VERSION=1.3.12
|
||||
```
|
||||
|
||||
Add a new line:
|
||||
|
||||
```dockerfile
|
||||
ARG GMAIL_MCP_VERSION=1.1.11
|
||||
```
|
||||
|
||||
Then find the last pnpm global-install `RUN` block (the one that installs `@anthropic-ai/claude-code`) and add a new block after it, before `# ---- Entrypoint`:
|
||||
|
||||
```dockerfile
|
||||
RUN --mount=type=cache,target=/root/.cache/pnpm \
|
||||
pnpm install -g \
|
||||
"@gongrzhe/server-gmail-autoauth-mcp@${GMAIL_MCP_VERSION}" \
|
||||
"zod-to-json-schema@3.22.5"
|
||||
```
|
||||
|
||||
Pinned version matters — `minimumReleaseAge` in `pnpm-workspace.yaml` gates trunk installs, and CLAUDE.md requires a fixed ARG version for all Node CLIs installed into the image.
|
||||
|
||||
**Why the `zod-to-json-schema` pin:** `@gongrzhe/server-gmail-autoauth-mcp@1.1.11` has loose deps (`zod-to-json-schema: ^3.22.1`, `zod: ^3.22.4`). pnpm resolves `zod-to-json-schema` to the latest 3.25.x, which imports `zod/v3` — a subpath that only exists in `zod>=3.25`. But `zod` resolves to `3.24.x` (highest satisfying `^3.22.4` without breaking peer ranges). Result: `ERR_PACKAGE_PATH_NOT_EXPORTED` at import time. Pinning `zod-to-json-schema` to a pre-v3-subpath version avoids it. Re-check if you bump `GMAIL_MCP_VERSION`.
|
||||
|
||||
### Add tools to allowlist
|
||||
|
||||
Edit `container/agent-runner/src/providers/claude.ts`. Find `'mcp__nanoclaw__*',` in `TOOL_ALLOWLIST` and add `'mcp__gmail__*',` after it.
|
||||
|
||||
### Rebuild the container image
|
||||
|
||||
```bash
|
||||
./container/build.sh
|
||||
```
|
||||
|
||||
Must complete cleanly. The new `pnpm install -g` layer is ~60s first time (cached on rebuild).
|
||||
|
||||
## Phase 3: Wire Per-Agent-Group
|
||||
|
||||
For each agent group that should have Gmail (ask the user — typically their personal DM and CLI agents, sometimes shared household agents), edit `groups/<folder>/container.json` to add the mount and MCP server.
|
||||
|
||||
Merge these into the group's `container.json`:
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"mcpServers": {
|
||||
"gmail": {
|
||||
"command": "gmail-mcp",
|
||||
"args": [],
|
||||
"env": {
|
||||
"GMAIL_OAUTH_PATH": "/workspace/extra/.gmail-mcp/gcp-oauth.keys.json",
|
||||
"GMAIL_CREDENTIALS_PATH": "/workspace/extra/.gmail-mcp/credentials.json"
|
||||
}
|
||||
}
|
||||
},
|
||||
"additionalMounts": [
|
||||
{
|
||||
"hostPath": "/home/<user>/.gmail-mcp",
|
||||
"containerPath": ".gmail-mcp",
|
||||
"readonly": false
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Substitute `<user>` with the host user's home (use `echo $HOME`, don't assume `~` will expand — `container-runner.ts` does expand `~` via `expandPath`, but an explicit absolute path is clearer and matches what `/manage-mounts` writes).
|
||||
|
||||
**Why the container path is relative:** `mount-security` rejects absolute `containerPath` values. Additional mounts are prefixed with `/workspace/extra/`, so `containerPath: ".gmail-mcp"` lands at `/workspace/extra/.gmail-mcp`. The MCP server's `GMAIL_OAUTH_PATH` / `GMAIL_CREDENTIALS_PATH` env vars point at that absolute location inside the container.
|
||||
|
||||
## Phase 4: Build and Restart
|
||||
|
||||
```bash
|
||||
pnpm run build
|
||||
systemctl --user restart nanoclaw # Linux
|
||||
# launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
```
|
||||
|
||||
## Phase 5: Verify
|
||||
|
||||
### Test from the wired agent
|
||||
|
||||
Tell the user:
|
||||
|
||||
> In your `<agent-name>` chat, send: **"list my gmail labels"** or **"search my inbox for invoices from last month"**.
|
||||
>
|
||||
> The agent should use `mcp__gmail__list_labels` / `mcp__gmail__search`. The first call may take a second or two while the MCP server starts and OneCLI does the token exchange.
|
||||
|
||||
### Check logs if the tool isn't working
|
||||
|
||||
```bash
|
||||
tail -100 logs/nanoclaw.log logs/nanoclaw.error.log | grep -iE 'gmail|mcp'
|
||||
# Per-container logs — session-scoped:
|
||||
ls data/v2-sessions/*/stderr.log | head
|
||||
```
|
||||
|
||||
Common signals:
|
||||
- `command not found: gmail-mcp` → image wasn't rebuilt or PATH doesn't include `/pnpm` (should — `ENV PATH="$PNPM_HOME:$PATH"` in Dockerfile).
|
||||
- `ENOENT: no such file or directory, open '/workspace/extra/.gmail-mcp/credentials.json'` → mount is missing. Check `~/.config/nanoclaw/mount-allowlist.json` includes a parent of `~/.gmail-mcp`.
|
||||
- `401 Unauthorized` from `gmail.googleapis.com` → OneCLI isn't injecting. Check the agent's secret mode (`onecli agents secrets --id <agent-id>`) and that the Gmail app is connected (`onecli apps get --provider gmail`).
|
||||
- Agent says "I don't have Gmail tools" → `mcp__gmail__*` wasn't added to `TOOL_ALLOWLIST`, or the agent-runner wasn't rebuilt (image cache — run `./container/build.sh` again with `--no-cache` if suspicious).
|
||||
|
||||
## Removal
|
||||
|
||||
1. Delete the `"gmail"` entry from `mcpServers` and the `.gmail-mcp` entry from `additionalMounts` in each group's `container.json`.
|
||||
2. Remove `'mcp__gmail__*'` from `TOOL_ALLOWLIST` in `container/agent-runner/src/providers/claude.ts`.
|
||||
3. Remove the `GMAIL_MCP_VERSION` ARG and the `pnpm install -g @gongrzhe/server-gmail-autoauth-mcp` block from `container/Dockerfile`.
|
||||
4. `pnpm run build && ./container/build.sh && systemctl --user restart nanoclaw`.
|
||||
5. (Optional) `rm -rf ~/.gmail-mcp/` if no other host-side tool needs the stubs.
|
||||
6. (Optional) Disconnect Gmail in OneCLI: `onecli apps disconnect --provider gmail`.
|
||||
|
||||
## Notes
|
||||
|
||||
- **Stub format is OneCLI-prescribed.** The `access_token: "onecli-managed"` pattern with `expiry_date: 99999999999999` tells the Google auth client the token is valid; OneCLI intercepts the outgoing Gmail API call and rewrites `Authorization: Bearer onecli-managed` to the real token. `expiry_date: 0` (refresh-interception) is an alternative the OneCLI docs describe — both work but OneCLI's own `migrate` command writes the far-future variant, which is what this skill assumes.
|
||||
- **Scopes are set at OAuth connect time.** If the agent needs scopes beyond what's currently connected (e.g. the user later wants `calendar.readonly` for combined email/calendar workflows), disconnect and reconnect Gmail in the OneCLI web UI with the expanded scope set.
|
||||
- **This is tool-only.** Inbound email as a channel (emails trigger the agent) is a separate piece of work — it needs a `src/channels/gmail.ts` adapter that polls the inbox and routes to a messaging group. The pre-v2 qwibitai skill had this; it has not been ported to v2's channel architecture as of v2.0.0.
|
||||
|
||||
## Credits & references
|
||||
|
||||
- **MCP server:** [`@gongrzhe/server-gmail-autoauth-mcp`](https://github.com/GongRzhe/Gmail-MCP-Server) by GongRzhe — MIT-licensed.
|
||||
- **OneCLI credential stubs:** pattern documented at `https://onecli.sh/docs/guides/credential-stubs/gmail.md`.
|
||||
- **Skill pattern:** modeled on [`add-atomic-chat-tool`](../add-atomic-chat-tool/SKILL.md) and [`add-vercel`](../add-vercel/SKILL.md).
|
||||
- **Addresses:** [issue #1500](https://github.com/qwibitai/nanoclaw/issues/1500) (proxy Gmail/Calendar OAuth tokens through credential proxy) for the Gmail side.
|
||||
- **Related PRs:** [#1810](https://github.com/qwibitai/nanoclaw/pull/1810) (pre-install Gmail/Notion MCP) overlaps on the "install the MCP server in the image" idea but bundles many unrelated changes; this skill is the focused OneCLI-native version.
|
||||
@@ -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)
|
||||
@@ -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.
|
||||
@@ -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', '<your-agent-group-id>', '', 'all', 'per-thread', 10, datetime('now'));
|
||||
```
|
||||
|
||||
The `platform_id` must be `linear:<TEAM_KEY>` 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:<TEAM_KEY>` (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.
|
||||
|
||||
@@ -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\/[^"]+?)(?<!\.js)"/g, "from \"$1.js\""
|
||||
));
|
||||
console.log("Patched", f);
|
||||
'
|
||||
```
|
||||
|
||||
Re-run this after every `pnpm install` that touches the adapter.
|
||||
|
||||
### 6. Build
|
||||
|
||||
```bash
|
||||
pnpm run build
|
||||
@@ -55,25 +77,60 @@ pnpm run build
|
||||
|
||||
## Credentials
|
||||
|
||||
1. Register a bot account on your Matrix homeserver (e.g., via Element)
|
||||
2. Get the homeserver URL (e.g., `https://matrix.org` or your self-hosted URL)
|
||||
3. Get an access token:
|
||||
- In Element: **Settings** > **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.
|
||||
|
||||
@@ -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<string, string>;
|
||||
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/<FOLDER>/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=$(sqlite3 data/v2.db "SELECT id FROM agent_groups WHERE folder='<FOLDER>';")
|
||||
SETTINGS=data/v2-sessions/$AG_ID/.claude-shared/settings.json
|
||||
```
|
||||
|
||||
Add `"model": "<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-<FOLDER>" --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/<FOLDER>/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/<FOLDER>/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.
|
||||
@@ -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@${OPENCODE_VERSION}"` to the list:
|
||||
|
||||
```dockerfile
|
||||
@@ -94,6 +96,25 @@ pnpm exec tsc -p container/agent-runner/tsconfig.json --noEmit # container typ
|
||||
./container/build.sh # agent image
|
||||
```
|
||||
|
||||
> **Build cache gotcha:** The container buildkit caches COPY steps aggressively. If provider files were already present in the build context before, the new files may not be picked up. If you see "Unknown provider: opencode" after the build, prune the builder and rebuild:
|
||||
> ```bash
|
||||
> docker builder prune -f && ./container/build.sh
|
||||
> ```
|
||||
|
||||
### 7. Propagate to existing per-group overlays
|
||||
|
||||
Each agent group has a live source overlay at `data/v2-sessions/<group-id>/agent-runner-src/providers/` that **overrides the image at runtime**. This overlay is created when the group is first wired and never auto-updated by image rebuilds. Any group that already existed before this skill ran needs the new files copied in manually.
|
||||
|
||||
```bash
|
||||
for overlay in data/v2-sessions/*/agent-runner-src/providers/; do
|
||||
[ -d "$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 <agent-id> --secret-ids <existing-ids>,<new-secret-id>
|
||||
```
|
||||
|
||||
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
|
||||
```
|
||||
|
||||
@@ -162,18 +206,16 @@ 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).
|
||||
Set `"provider": "opencode"` in the group's **`container.json`** (`groups/<folder>/container.json`) — the in-container runner reads `provider` from there, not from the DB. The DB columns **`agent_groups.agent_provider`** and **`sessions.agent_provider`** (session overrides group) only drive host-side provider contribution — per-session XDG mount, `OPENCODE_*` env passthrough — and do not propagate into `container.json` at spawn time. Set both, or just edit `container.json`; if they disagree, the runner uses `container.json` and the host-side resolver falls back through session → group → `container.json` → `'claude'`.
|
||||
|
||||
Extra MCP servers still come from **`NANOCLAW_MCP_SERVERS`** / `container_config.mcpServers` on the host; the runner merges them into the same `mcpServers` object passed to **both** Claude and OpenCode providers.
|
||||
|
||||
## 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
|
||||
|
||||
@@ -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 <url>`.
|
||||
|
||||
### 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.
|
||||
@@ -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
|
||||
@@ -0,0 +1,13 @@
|
||||
# Remove Signal
|
||||
|
||||
1. Comment out `import './signal.js'` in `src/channels/index.ts`
|
||||
2. Remove `SIGNAL_ACCOUNT` (and any other `SIGNAL_*` vars) from `.env`
|
||||
3. Rebuild and restart
|
||||
|
||||
If you also want to unlink the Signal account from `signal-cli`:
|
||||
|
||||
```bash
|
||||
signal-cli -a +1YOURNUMBER removeDevice --deviceId <id>
|
||||
```
|
||||
|
||||
(Find the device id with `signal-cli -a +1YOURNUMBER listDevices`.)
|
||||
@@ -0,0 +1,318 @@
|
||||
---
|
||||
name: add-signal
|
||||
description: Add Signal channel integration via signal-cli TCP daemon. Native adapter — no Chat SDK bridge.
|
||||
---
|
||||
|
||||
# Add Signal Channel
|
||||
|
||||
Adds Signal messaging support via a native adapter that speaks JSON-RPC to a [signal-cli](https://github.com/AsamK/signal-cli) TCP daemon. No Chat SDK bridge — only Node.js builtins (`node:net`, `node:child_process`, `node:fs`).
|
||||
|
||||
Unlike Telegram or Discord, Signal has no bot API. NanoClaw registers as a full Signal account on a dedicated phone number (recommended) or links as a secondary device on your existing number.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
### Java
|
||||
|
||||
signal-cli requires Java 17+:
|
||||
|
||||
```bash
|
||||
java -version
|
||||
```
|
||||
|
||||
If missing:
|
||||
- **macOS:** `brew install --cask temurin@17`
|
||||
- **Debian/Ubuntu:** `sudo apt-get install -y default-jre`
|
||||
- **RHEL/Fedora:** `sudo dnf install -y java-17-openjdk`
|
||||
|
||||
Java 17–25 all work.
|
||||
|
||||
### signal-cli
|
||||
|
||||
- **macOS:** `brew install signal-cli`
|
||||
- **Linux:** download the native binary from [GitHub releases](https://github.com/AsamK/signal-cli/releases):
|
||||
|
||||
```bash
|
||||
SIGNAL_CLI_VERSION=$(curl -fsSL https://api.github.com/repos/AsamK/signal-cli/releases/latest | python3 -c "import sys,json; print(json.load(sys.stdin)['tag_name'][1:])")
|
||||
curl -fsSL "https://github.com/AsamK/signal-cli/releases/download/v${SIGNAL_CLI_VERSION}/signal-cli-${SIGNAL_CLI_VERSION}-Linux-native.tar.gz" \
|
||||
| tar -xz -C ~/.local
|
||||
ln -sf ~/.local/signal-cli ~/.local/bin/signal-cli
|
||||
signal-cli --version
|
||||
```
|
||||
|
||||
> The Linux native tarball extracts a single binary directly to `~/.local/signal-cli` (not into a subdirectory). The symlink above puts it on PATH.
|
||||
|
||||
## Registration
|
||||
|
||||
Two paths. The new-number path is recommended and battle-tested.
|
||||
|
||||
### Path A: Register a new number (recommended)
|
||||
|
||||
Use a dedicated SIM or VoIP number. NanoClaw owns it entirely.
|
||||
|
||||
> **VoIP numbers:** Signal requires SMS verification before voice. Some VoIP providers are blocked even for voice calls. If registration fails with an auth error, try a different provider or a physical SIM.
|
||||
|
||||
**Step 1: Solve the CAPTCHA**
|
||||
|
||||
Signal requires a CAPTCHA on first registration:
|
||||
|
||||
1. Open `https://signalcaptchas.org/registration/generate.html` in a browser
|
||||
2. Solve the captcha
|
||||
3. Right-click the **"Open Signal"** button → **Copy Link**
|
||||
4. The link starts with `signalcaptcha://` — the token is everything after that prefix
|
||||
|
||||
**Step 2: Request SMS verification**
|
||||
|
||||
```bash
|
||||
signal-cli -a +1YOURNUMBER register --captcha "PASTE_TOKEN_HERE"
|
||||
```
|
||||
|
||||
**Step 3: Voice call fallback (if your number can't receive SMS)**
|
||||
|
||||
Wait ~60 seconds after the SMS request, then:
|
||||
|
||||
```bash
|
||||
signal-cli -a +1YOURNUMBER register --voice --captcha "SAME_TOKEN"
|
||||
```
|
||||
|
||||
Signal calls your number and reads a 6-digit code. The same captcha token is reusable — no need to solve a new one.
|
||||
|
||||
> You must request SMS first. Requesting voice immediately fails with `Invalid verification method: Before requesting voice verification…`
|
||||
|
||||
**Step 4: Verify**
|
||||
|
||||
```bash
|
||||
signal-cli -a +1YOURNUMBER verify CODE
|
||||
```
|
||||
|
||||
No output = success.
|
||||
|
||||
**Step 5: Set profile name (optional)**
|
||||
|
||||
> ⚠ Stop NanoClaw before running signal-cli commands — the daemon holds an exclusive lock on its data directory while running.
|
||||
|
||||
```bash
|
||||
# macOS
|
||||
launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist
|
||||
signal-cli -a +1YOURNUMBER updateProfile --name "YourBotName"
|
||||
# optionally: --avatar /path/to/avatar.jpg
|
||||
launchctl load ~/Library/LaunchAgents/com.nanoclaw.plist
|
||||
|
||||
# Linux
|
||||
systemctl --user stop nanoclaw
|
||||
signal-cli -a +1YOURNUMBER updateProfile --name "YourBotName"
|
||||
systemctl --user start nanoclaw
|
||||
```
|
||||
|
||||
### Path B: Link as secondary device
|
||||
|
||||
Joins an existing Signal account as a secondary device. Simpler, but NanoClaw shares your personal number.
|
||||
|
||||
```bash
|
||||
signal-cli -a +1YOURNUMBER link --name "NanoClaw"
|
||||
```
|
||||
|
||||
This prints a `tsdevice:` URI. Scan it as a QR code on your phone: **Settings → Linked Devices → Link New Device**. QR codes expire in ~30 seconds — re-run if it expires.
|
||||
|
||||
## Install
|
||||
|
||||
### Pre-flight (idempotent)
|
||||
|
||||
Skip to **Credentials** if all of these are already in place:
|
||||
|
||||
- `src/channels/signal.ts` and `src/channels/signal.test.ts` both exist
|
||||
- `src/channels/index.ts` contains `import './signal.js';`
|
||||
|
||||
Otherwise continue. Every step below is safe to re-run.
|
||||
|
||||
### 1. Fetch the channels branch
|
||||
|
||||
```bash
|
||||
git fetch origin channels
|
||||
```
|
||||
|
||||
### 2. Copy the adapter and tests
|
||||
|
||||
```bash
|
||||
git show origin/channels:src/channels/signal.ts > src/channels/signal.ts
|
||||
git show origin/channels:src/channels/signal.test.ts > src/channels/signal.test.ts
|
||||
```
|
||||
|
||||
### 3. Append the self-registration import
|
||||
|
||||
Append to `src/channels/index.ts` (skip if the line is already present):
|
||||
|
||||
```typescript
|
||||
import './signal.js';
|
||||
```
|
||||
|
||||
### 4. Build
|
||||
|
||||
```bash
|
||||
pnpm run build
|
||||
```
|
||||
|
||||
No npm packages to install — the adapter uses only Node.js builtins.
|
||||
|
||||
## Credentials
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
SIGNAL_ACCOUNT=+1YOURNUMBER
|
||||
```
|
||||
|
||||
### Optional settings
|
||||
|
||||
```bash
|
||||
# TCP daemon host and port (default: 127.0.0.1:7583)
|
||||
SIGNAL_TCP_HOST=127.0.0.1
|
||||
SIGNAL_TCP_PORT=7583
|
||||
|
||||
# Path to the signal-cli binary (default: resolved on PATH)
|
||||
SIGNAL_CLI_PATH=/usr/local/bin/signal-cli
|
||||
|
||||
# Whether NanoClaw manages the daemon lifecycle (default: true).
|
||||
# Set to false if you run signal-cli daemon externally.
|
||||
SIGNAL_MANAGE_DAEMON=true
|
||||
|
||||
# signal-cli data directory (default: ~/.local/share/signal-cli)
|
||||
SIGNAL_DATA_DIR=~/.local/share/signal-cli
|
||||
```
|
||||
|
||||
**Security note:** keep the TCP host on `127.0.0.1`. The daemon has no auth — binding it to a public interface would expose your full Signal account to the network.
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Restart
|
||||
|
||||
```bash
|
||||
# macOS
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw
|
||||
|
||||
# Linux
|
||||
systemctl --user restart nanoclaw
|
||||
```
|
||||
|
||||
## Wiring
|
||||
|
||||
### DMs
|
||||
|
||||
After the service starts, send any message to the Signal number from your personal Signal app. The router auto-creates a `messaging_groups` row. Then:
|
||||
|
||||
```bash
|
||||
sqlite3 data/v2.db \
|
||||
"SELECT id, platform_id FROM messaging_groups WHERE channel_type='signal' ORDER BY created_at DESC LIMIT 5"
|
||||
```
|
||||
|
||||
Pass the `id` to `/init-first-agent` or `/manage-channels` to wire it to an agent group.
|
||||
|
||||
### Groups
|
||||
|
||||
Add the Signal number to a group from your phone, send any message, then wire the resulting row the same way. For isolated per-group sessions:
|
||||
|
||||
```bash
|
||||
NOW=$(date -u +"%Y-%m-%dT%H:%M:%S.000Z")
|
||||
sqlite3 data/v2.db "
|
||||
INSERT OR IGNORE INTO messaging_group_agents
|
||||
(id, messaging_group_id, agent_group_id, session_mode, priority, created_at)
|
||||
VALUES
|
||||
('mga-'||hex(randomblob(8)), 'mg-GROUPID', 'ag-AGENTID', 'isolated', 0, '$NOW');
|
||||
"
|
||||
```
|
||||
|
||||
### Grant user access
|
||||
|
||||
New Signal users (including the owner's Signal identity) are silently dropped with `not_member` until granted access. After the user's first message appears in `messaging_groups`:
|
||||
|
||||
```bash
|
||||
NOW=$(date -u +"%Y-%m-%dT%H:%M:%S.000Z")
|
||||
sqlite3 data/v2.db "
|
||||
INSERT OR REPLACE INTO user_roles (user_id, role, agent_group_id, granted_by, granted_at)
|
||||
VALUES ('signal:UUID', 'owner', NULL, 'system', '$NOW');
|
||||
INSERT OR IGNORE INTO agent_group_members (user_id, agent_group_id, added_by, added_at)
|
||||
VALUES ('signal:UUID', 'ag-AGENTID', 'system', '$NOW');
|
||||
"
|
||||
```
|
||||
|
||||
Find the UUID from `messaging_groups.platform_id` or the `users` table.
|
||||
|
||||
## Next Steps
|
||||
|
||||
If you're in the middle of `/setup`, return to the setup flow now.
|
||||
|
||||
Otherwise, run `/init-first-agent` to create an agent and wire it to your Signal DM, or `/manage-channels` to wire this channel to an existing agent group.
|
||||
|
||||
## Channel Info
|
||||
|
||||
- **type**: `signal`
|
||||
- **terminology**: Signal has "chats" (1:1 DMs) and "groups"
|
||||
- **supports-threads**: no
|
||||
- **platform-id-format**:
|
||||
- DM: `signal:{UUID}` — sender's Signal UUID (ACI), **not** their phone number
|
||||
- Group: `signal:{base64GroupId}` — base64-encoded GroupV2 ID
|
||||
- **how-to-find-id**: Send a message to the bot, then query `messaging_groups` as shown above
|
||||
- **typical-use**: Personal assistant via Signal DMs or small group chats
|
||||
- **default-isolation**: One agent per Signal account. Multiple chats with the same operator can share an agent group; groups with other people should typically use `isolated` session mode
|
||||
|
||||
### Features
|
||||
|
||||
- Markdown formatting — `**bold**`, `*italic*` / `_italic_`, `` `code` ``, ` ```code fence``` `, `~~strike~~`, `||spoiler||` (converted to Signal's offset-based text styles)
|
||||
- Quoted replies — `replyTo*` fields populated from Signal quotes
|
||||
- Typing indicators — DMs only (Signal doesn't support group typing)
|
||||
- Echo suppression — outbound messages matched on `(platformId, text)` within a 10 s TTL to avoid syncMessage loops
|
||||
- Note to Self — messages you send to your own account from another device route to the agent as inbound with `isFromMe: true`
|
||||
- Voice attachments — detected but not transcribed by default; the agent receives `[Voice Message]` placeholder text. Run `/add-voice-transcription` for local transcription via parakeet-mlx
|
||||
|
||||
Not supported yet: outbound file attachments (logged and dropped), edit/delete messages, reactions.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Daemon not reachable
|
||||
|
||||
```bash
|
||||
grep "Signal" logs/nanoclaw.log | tail
|
||||
```
|
||||
|
||||
If you see `Signal daemon failed to start. Is signal-cli installed and your account linked?`:
|
||||
- Confirm `signal-cli` is on PATH (or set `SIGNAL_CLI_PATH`)
|
||||
- Confirm the account is linked: `signal-cli -a +1YOURNUMBER listIdentities` should succeed without prompting
|
||||
|
||||
If you see `Signal daemon not reachable at 127.0.0.1:7583` and `SIGNAL_MANAGE_DAEMON=false`, start the daemon yourself: `signal-cli -a +1YOURNUMBER daemon --tcp 127.0.0.1:7583`.
|
||||
|
||||
### Bot not responding
|
||||
|
||||
1. Channel initialized: `grep "Signal channel connected" logs/nanoclaw.log | tail -1`
|
||||
2. Channel wired: `sqlite3 data/v2.db "SELECT mg.platform_id, mg.name FROM messaging_groups mg JOIN messaging_group_agents mga ON mg.id = mga.messaging_group_id WHERE mg.channel_type='signal'"`
|
||||
3. Service running: `launchctl print gui/$(id -u)/com.nanoclaw` (macOS) / `systemctl --user status nanoclaw` (Linux)
|
||||
|
||||
### Lost connection mid-session
|
||||
|
||||
If you see `Signal channel lost TCP connection to signal-cli daemon` in the logs, the daemon dropped the connection. Restart the service to re-establish.
|
||||
|
||||
### Messages dropped with `not_member`
|
||||
|
||||
The Signal user hasn't been granted membership. See "Grant user access" above. This affects every new Signal user, including the owner's Signal identity — which is a separate user record from their identity on other channels even if it's the same person.
|
||||
|
||||
### Captcha required
|
||||
|
||||
Signal requires a captcha for new registrations. Go to `https://signalcaptchas.org/registration/generate.html`, solve it, right-click "Open Signal", copy the link, extract the token after `signalcaptcha://`.
|
||||
|
||||
### `Invalid verification method: Before requesting voice verification…`
|
||||
|
||||
You must request SMS first, wait ~60 seconds, then request voice. Both steps can use the same captcha token.
|
||||
|
||||
### Config file in use / daemon lock
|
||||
|
||||
signal-cli holds an exclusive lock on its data directory while the daemon is running. Stop NanoClaw before running any `signal-cli` commands directly, then restart afterward.
|
||||
|
||||
### Group replies going to DM instead of group
|
||||
|
||||
Modern Signal groups use GroupV2. The adapter must extract the group ID from `envelope?.dataMessage?.groupV2?.id` — not `groupInfo?.groupId`, which is GroupV1/legacy. If group messages are routing as DMs, check `src/channels/signal.ts` and confirm the groupId extraction falls through to `groupV2.id`.
|
||||
|
||||
### Java not found
|
||||
|
||||
Install Java 17+ — see the Prerequisites section above.
|
||||
|
||||
### QR code expired (Path B)
|
||||
|
||||
QR codes expire in ~30 seconds. Re-run the link command to generate a new one.
|
||||
@@ -0,0 +1,5 @@
|
||||
# Verify Signal
|
||||
|
||||
Send a message to your own Signal number (Note to Self) from another device, or have someone send your linked number a DM. The bot should respond within a few seconds.
|
||||
|
||||
If nothing happens, tail `logs/nanoclaw.log` for `Signal channel connected` and `Signal message received`.
|
||||
@@ -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<string, number>();
|
||||
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<void> {
|
||||
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<void> {
|
||||
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<string, string | undefined> = {
|
||||
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 `<internal>` 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)
|
||||
@@ -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: <transcript>]`.
|
||||
|
||||
## 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 (~$0.003 per typical 30-second voice note)
|
||||
|
||||
Wait for the user to provide the key.
|
||||
|
||||
### Add to environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
OPENAI_API_KEY=<their-key>
|
||||
```
|
||||
|
||||
Sync to container environment:
|
||||
|
||||
```bash
|
||||
mkdir -p data/env && cp .env data/env/env
|
||||
```
|
||||
|
||||
The container reads environment from `data/env/env`, not `.env` directly.
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
pnpm run build
|
||||
launchctl kickstart -k gui/$(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: <transcript>]` 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 $OPENAI_API_KEY" | head -c 200`
|
||||
3. Check OpenAI billing — Whisper requires a funded account
|
||||
|
||||
### Voice notes show "[Voice Message - transcription failed]"
|
||||
|
||||
Check logs for the specific error. Common causes:
|
||||
- Network timeout — transient, will work on next message
|
||||
- Invalid API key — regenerate at https://platform.openai.com/api-keys
|
||||
- Rate limiting — wait and retry
|
||||
|
||||
### Agent doesn't respond to voice notes
|
||||
|
||||
Verify the chat is registered and the agent is running. Voice transcription only runs for registered groups.
|
||||
@@ -0,0 +1,49 @@
|
||||
# Remove WeChat Channel
|
||||
|
||||
Undo `/add-wechat`.
|
||||
|
||||
### 1. Remove credentials
|
||||
|
||||
Delete WeChat lines from `.env`:
|
||||
|
||||
```bash
|
||||
sed -i.bak '/^WECHAT_ENABLED=/d' .env && rm -f .env.bak
|
||||
cp .env data/env/env
|
||||
```
|
||||
|
||||
### 2. Remove adapter and import
|
||||
|
||||
```bash
|
||||
rm -f src/channels/wechat.ts
|
||||
sed -i.bak "/import '\.\/wechat\.js';/d" src/channels/index.ts && rm -f src/channels/index.ts.bak
|
||||
```
|
||||
|
||||
### 3. Uninstall the package
|
||||
|
||||
```bash
|
||||
pnpm remove wechat-ilink-client
|
||||
```
|
||||
|
||||
### 4. Remove saved auth + sync state
|
||||
|
||||
```bash
|
||||
rm -rf data/wechat
|
||||
```
|
||||
|
||||
### 5. Remove DB wiring
|
||||
|
||||
```sql
|
||||
-- Remove any sessions first (foreign key)
|
||||
DELETE FROM sessions WHERE messaging_group_id IN (SELECT id FROM messaging_groups WHERE channel_type = 'wechat');
|
||||
DELETE FROM messaging_group_agents WHERE messaging_group_id IN (SELECT id FROM messaging_groups WHERE channel_type = 'wechat');
|
||||
DELETE FROM messaging_groups WHERE channel_type = 'wechat';
|
||||
```
|
||||
|
||||
### 6. Rebuild and restart
|
||||
|
||||
```bash
|
||||
pnpm run build
|
||||
systemctl --user restart nanoclaw # Linux
|
||||
# or
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
```
|
||||
@@ -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 <id>` — wire a specific messaging group (default: most recent unwired)
|
||||
- `--agent-group <id>` — 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:<id>`. Use `wechat:<user_id>` for DMs, `wechat:<group_id>` 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:<operatorUserId>`).
|
||||
- **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 as part of `bash nanoclaw.sh`, `init-first-agent.ts` handles wiring — just pass the `platform-id` and `admin-user-id` captured above.
|
||||
@@ -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 <id> Wire a specific messaging group (default: most recent unwired)
|
||||
* --agent-group <id> Target agent group (default: interactive pick; or solo admin group)
|
||||
* --sender-policy <p> public | strict (default: public)
|
||||
* --session-mode <m> 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: ${val}`);
|
||||
args.sessionMode = val; i++; break;
|
||||
case '--non-interactive': args.interactive = false; break;
|
||||
case '--help': case '-h':
|
||||
console.log('See .claude/skills/add-wechat/scripts/wire-dm.ts header for usage.');
|
||||
process.exit(0);
|
||||
}
|
||||
}
|
||||
return args;
|
||||
}
|
||||
|
||||
async function prompt(q: string): Promise<string> {
|
||||
const rl = readline.createInterface({ input: process.stdin, output: process.stdout });
|
||||
return new Promise((resolve) => rl.question(q, (a) => { rl.close(); resolve(a.trim()); }));
|
||||
}
|
||||
|
||||
function generateId(prefix: string): string {
|
||||
return `${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`;
|
||||
}
|
||||
|
||||
async function main(): Promise<void> {
|
||||
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 <id>');
|
||||
}
|
||||
}
|
||||
|
||||
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);
|
||||
});
|
||||
@@ -57,7 +57,7 @@ groups: () => import('./groups.js'),
|
||||
### 5. Install the adapter packages (pinned)
|
||||
|
||||
```bash
|
||||
pnpm install @whiskeysockets/baileys@6.17.16 qrcode@1.5.4 @types/qrcode@1.5.6 pino@9.6.0
|
||||
pnpm install @whiskeysockets/baileys@7.0.0-rc.9 qrcode@1.5.4 @types/qrcode@1.5.6 pino@9.6.0
|
||||
```
|
||||
|
||||
### 6. Build
|
||||
|
||||
@@ -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 `<url\|text>` |
|
||||
| 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 `<internal>` 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
|
||||
```
|
||||
@@ -87,18 +87,17 @@ The script:
|
||||
2. Creates the `agent_groups` row and calls `initGroupFilesystem` at `groups/dm-with-<name>/`.
|
||||
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.
|
||||
|
||||
|
||||
@@ -45,8 +45,7 @@ rm /tmp/nanoclaw-diagnostics.json
|
||||
**No**: `rm /tmp/nanoclaw-diagnostics.json`
|
||||
|
||||
**Never ask again**:
|
||||
1. Replace contents of `.claude/skills/setup/diagnostics.md` with `# Diagnostics — opted out`
|
||||
2. Replace contents of `.claude/skills/update-nanoclaw/diagnostics.md` with `# Diagnostics — opted out`
|
||||
3. Replace contents of `.claude/skills/migrate-nanoclaw/diagnostics.md` with `# Diagnostics — opted out`
|
||||
4. Remove the diagnostics sections from each corresponding SKILL.md
|
||||
5. `rm /tmp/nanoclaw-diagnostics.json`
|
||||
1. Replace contents of `.claude/skills/update-nanoclaw/diagnostics.md` with `# Diagnostics — opted out`
|
||||
2. Replace contents of `.claude/skills/migrate-nanoclaw/diagnostics.md` with `# Diagnostics — opted out`
|
||||
3. Remove the diagnostics sections from each corresponding SKILL.md
|
||||
4. `rm /tmp/nanoclaw-diagnostics.json`
|
||||
|
||||
@@ -1,350 +1,10 @@
|
||||
---
|
||||
name: setup
|
||||
description: Run initial NanoClaw setup. Use when user wants to install dependencies, authenticate messaging channels, register their main channel, or start the background services. Triggers on "setup", "install", "configure nanoclaw", or first-time setup requests.
|
||||
allowed-tools: Bash(git remote*), Bash(bash setup.sh), Bash(pnpm exec tsx setup/index.ts*)
|
||||
description: Run initial NanoClaw setup. Use when user wants to install NanoClaw, configure it, or go through first-time setup. Triggers on "setup", "install", "configure nanoclaw", or first-time setup requests.
|
||||
---
|
||||
|
||||
# NanoClaw Setup
|
||||
|
||||
Welcome the user to NanoClaw. Introduce yourself — you'll be walking them through the entire setup process step by step, from installing dependencies to getting their first message through. Keep it warm and brief (2-3 sentences).
|
||||
Tell the user to run `bash nanoclaw.sh` in their terminal. That script handles the full end-to-end setup — dependencies, container image, OneCLI vault, Anthropic credential, service, first agent, and optional channel wiring.
|
||||
|
||||
Then explain that setup involves running many shell commands (installing packages, building containers, starting services), and recommend pre-approving the standard setup commands so they don't have to confirm each one individually.
|
||||
|
||||
Use `AskUserQuestion` with these options:
|
||||
|
||||
1. **Pre-approve (recommended)** — description: "Pre-approve standard setup commands so you don't have to confirm each one. You can review the list first if you'd like."
|
||||
2. **No thanks** — description: "I'll approve each command individually as it comes up."
|
||||
3. **Show me the list first** — description: "Show me exactly which commands will be pre-approved before I decide."
|
||||
|
||||
If they pick option 1: read `.claude/skills/setup/setup-permissions.json`, then read the project settings file at `.claude/settings.json` (create it if it doesn't exist with `{}`), and directly edit it to add/merge the permissions into the `permissions.allow` array. Do NOT use the `update-config` skill.
|
||||
|
||||
If they pick option 3: read and display `.claude/skills/setup/setup-permissions.json`, then re-ask with just options 1 and 2.
|
||||
|
||||
If they decline, continue — they'll approve commands individually.
|
||||
|
||||
---
|
||||
|
||||
**Internal guidance (do not show to user):**
|
||||
|
||||
- Run setup steps automatically. Only pause when user action is required (channel authentication, configuration choices).
|
||||
- Setup uses `bash setup.sh` for bootstrap, then `npx tsx setup/index.ts --step <name>` for all other steps. Steps emit structured status blocks to stdout. Verbose logs go to `logs/setup.log`.
|
||||
- **Principle:** When something is broken or missing, fix it. Don't tell the user to go fix it themselves unless it genuinely requires their manual action (e.g. authenticating a channel, pasting a secret token). If a dependency is missing, install it. If a service won't start, diagnose and repair.
|
||||
- **UX Note:** Use `AskUserQuestion` for multiple-choice questions only (e.g. "which credential method?"). Do NOT use it when free-text input is needed (e.g. phone numbers, tokens, paths) — just ask the question in plain text and wait for the user's reply.
|
||||
- **Timeouts:** Use 5m timeouts for install and build steps.
|
||||
- **Waiting on user:** When the user needs to do something (change a setting, get a token, open a browser, etc.), stop and wait. Give clear instructions, then say "Let me know when done or if you need help." Do NOT continue to the next step. If they ask for help, give more detail, ask where they got stuck, and try to assist.
|
||||
|
||||
## 0. Git Upstream
|
||||
|
||||
Ensure `upstream` remote points to `qwibitai/nanoclaw`. If missing, add it silently.
|
||||
|
||||
```!
|
||||
git remote add upstream https://github.com/qwibitai/nanoclaw.git 2>/dev/null || true
|
||||
git remote -v
|
||||
```
|
||||
|
||||
## 1. Bootstrap (Node.js + Dependencies)
|
||||
|
||||
Output from !`bash setup.sh` — parse the status block.
|
||||
|
||||
- If NODE_OK=false → Node.js is missing or too old. Use `AskUserQuestion: Would you like me to install Node.js 22?` If confirmed:
|
||||
- macOS: `brew install node@22` (if brew available) or install nvm then `nvm install 22`
|
||||
- Linux: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs`, or nvm
|
||||
- After installing Node, re-run `bash setup.sh`
|
||||
- If DEPS_OK=false → Read `logs/setup.log`. Try: delete `node_modules`, re-run `bash setup.sh`. If native module build fails, install build tools (`xcode-select --install` on macOS, `build-essential` on Linux), then retry.
|
||||
- If NATIVE_OK=false → better-sqlite3 failed to load. Install build tools and re-run.
|
||||
- Record PLATFORM and IS_WSL for later steps.
|
||||
|
||||
## 2. Check Environment
|
||||
|
||||
Output from !`pnpm exec tsx setup/index.ts --step environment` — parse the status block.
|
||||
|
||||
- If HAS_AUTH=true → WhatsApp is already configured, note for step 5
|
||||
- If HAS_REGISTERED_GROUPS=true → note existing config, offer to skip or reconfigure
|
||||
- Record DOCKER value for step 3
|
||||
|
||||
### OpenClaw Migration Detection
|
||||
|
||||
If OPENCLAW_PATH is not `none` from the environment check above, AskUserQuestion:
|
||||
|
||||
1. **Migrate now** — "Import identity, credentials, and settings from OpenClaw before continuing setup."
|
||||
2. **Fresh start** — "Skip migration and set up NanoClaw from scratch."
|
||||
3. **Migrate later** — "Continue setup now, run `/migrate-from-openclaw` anytime later."
|
||||
|
||||
If "Migrate now": invoke `/migrate-from-openclaw`, then return here and continue at step 2a (Timezone).
|
||||
|
||||
## 2a. Timezone
|
||||
|
||||
Output from !`pnpm exec tsx setup/index.ts --step timezone` — parse the status block.
|
||||
|
||||
- If NEEDS_USER_INPUT=true → The system timezone could not be autodetected (e.g. POSIX-style TZ like `IST-2`). AskUserQuestion: "What is your timezone?" with common options (America/New_York, Europe/London, Asia/Jerusalem, Asia/Tokyo) and an "Other" escape. Then re-run: `pnpm exec tsx setup/index.ts --step timezone -- --tz <their-answer>`.
|
||||
- If STATUS=success and RESOLVED_TZ is `UTC` or `Etc/UTC` → confirm with the user: "Your system timezone is UTC — is that correct, or are you on a remote server?" If wrong, ask for their actual timezone and re-run with `--tz`.
|
||||
- If STATUS=success → Timezone is configured. Note RESOLVED_TZ for reference.
|
||||
|
||||
## 3. Container Runtime (Docker)
|
||||
|
||||
### 3a. Install Docker
|
||||
|
||||
- DOCKER=running → continue to step 4
|
||||
- DOCKER=installed_not_running → start Docker: `open -a Docker` (macOS) or `sudo systemctl start docker` (Linux). Wait 15s, re-check with `docker info`.
|
||||
- DOCKER=not_found → Use `AskUserQuestion: Docker is required for running agents. Would you like me to install it?` If confirmed:
|
||||
- macOS: install via `brew install --cask docker`, then `open -a Docker` and wait for it to start. If brew not available, direct to Docker Desktop download at https://docker.com/products/docker-desktop
|
||||
- Linux: install with `curl -fsSL https://get.docker.com | sh && sudo usermod -aG docker $USER`. Note: user may need to log out/in for group membership.
|
||||
|
||||
### 3b. CJK fonts
|
||||
|
||||
Agent containers skip CJK fonts by default (~200MB saved). Without them, Chromium-rendered screenshots and PDFs show tofu for Chinese/Japanese/Korean.
|
||||
|
||||
- **User writing to you in Chinese, Japanese, or Korean** → enable without asking. Mention it briefly.
|
||||
- **Resolved timezone from step 2a is a CJK region** (`Asia/Tokyo`, `Asia/Shanghai`, `Asia/Hong_Kong`, `Asia/Taipei`, `Asia/Seoul`) or other signal short of active CJK use → ask: "Enable CJK fonts? Adds ~200MB, lets the agent render CJK in screenshots and PDFs."
|
||||
- **Otherwise** → skip.
|
||||
|
||||
To enable, write `INSTALL_CJK_FONTS=true` to `.env`:
|
||||
|
||||
```bash
|
||||
grep -q '^INSTALL_CJK_FONTS=' .env && sed -i.bak 's/^INSTALL_CJK_FONTS=.*/INSTALL_CJK_FONTS=true/' .env && rm -f .env.bak || echo 'INSTALL_CJK_FONTS=true' >> .env
|
||||
```
|
||||
|
||||
The next step's build picks it up automatically.
|
||||
|
||||
### 3c. Build and test
|
||||
|
||||
Run `pnpm exec tsx setup/index.ts --step container -- --runtime docker` and parse the status block.
|
||||
|
||||
**If BUILD_OK=false:** Read `logs/setup.log` tail for the build error.
|
||||
- Cache issue (stale layers): `docker builder prune -f`. Retry.
|
||||
- Dockerfile syntax or missing files: diagnose from the log and fix, then retry.
|
||||
|
||||
**If TEST_OK=false but BUILD_OK=true:** The image built but won't run. Check logs — common cause is runtime not fully started. Wait a moment and retry the test.
|
||||
|
||||
## 4. Credential System
|
||||
|
||||
### 4a. OneCLI
|
||||
|
||||
Install OneCLI and its CLI tool:
|
||||
|
||||
```bash
|
||||
curl -fsSL onecli.sh/install | sh
|
||||
curl -fsSL onecli.sh/cli/install | sh
|
||||
```
|
||||
|
||||
Verify both installed: `onecli version`. If the command is not found, the CLI was likely installed to `~/.local/bin/`. Add it to PATH for the current session and persist it:
|
||||
|
||||
```bash
|
||||
export PATH="$HOME/.local/bin:$PATH"
|
||||
# Persist for future sessions (append to shell profile if not already present)
|
||||
grep -q '.local/bin' ~/.bashrc 2>/dev/null || echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
|
||||
grep -q '.local/bin' ~/.zshrc 2>/dev/null || echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc
|
||||
```
|
||||
|
||||
Then re-verify with `onecli version`.
|
||||
|
||||
Point the CLI at the local OneCLI instance, the ONECLI_URL was output from the install script above:
|
||||
```bash
|
||||
onecli config set api-host ${ONECLI_URL}
|
||||
```
|
||||
|
||||
Ensure `.env` has the OneCLI URL (create the file if it doesn't exist):
|
||||
```bash
|
||||
grep -q 'ONECLI_URL' .env 2>/dev/null || echo 'ONECLI_URL=${ONECLI_URL}' >> .env
|
||||
```
|
||||
|
||||
Check if a secret already exists:
|
||||
```bash
|
||||
onecli secrets list
|
||||
```
|
||||
|
||||
If an Anthropic secret is listed, confirm with user: keep or reconfigure? If keeping, skip to step 5.
|
||||
|
||||
AskUserQuestion: Do you want to use your **Claude subscription** (Pro/Max) or an **Anthropic API key**?
|
||||
|
||||
1. **Claude subscription (Pro/Max)** — description: "Uses your existing Claude Pro or Max subscription. You'll run `claude setup-token` in another terminal to get your token."
|
||||
2. **Anthropic API key** — description: "Pay-per-use API key from console.anthropic.com."
|
||||
|
||||
#### Subscription path
|
||||
|
||||
Tell the user:
|
||||
|
||||
> Run `claude setup-token` in another terminal. It will output a token — copy it but don't paste it here.
|
||||
|
||||
Then stop and wait for the user to confirm they have the token. Do NOT proceed until they respond.
|
||||
|
||||
Once they confirm, they register it with OneCLI. AskUserQuestion with two options:
|
||||
|
||||
1. **Dashboard** — description: "Best if you have a browser on this machine. Open ${ONECLI_URL} and add the secret in the UI. Use type 'anthropic' and paste your token as the value."
|
||||
2. **CLI** — description: "Best for remote/headless servers. Run: `onecli secrets create --name Anthropic --type anthropic --value YOUR_TOKEN --host-pattern api.anthropic.com`"
|
||||
|
||||
#### API key path
|
||||
|
||||
Tell the user to get an API key from https://console.anthropic.com/settings/keys if they don't have one.
|
||||
|
||||
Then AskUserQuestion with two options:
|
||||
|
||||
1. **Dashboard** — description: "Best if you have a browser on this machine. Open ${ONECLI_URL} and add the secret in the UI."
|
||||
2. **CLI** — description: "Best for remote/headless servers. Run: `onecli secrets create --name Anthropic --type anthropic --value YOUR_KEY --host-pattern api.anthropic.com`"
|
||||
|
||||
#### After either path
|
||||
|
||||
Ask them to let you know when done.
|
||||
|
||||
**If the user's response happens to contain a token or key** (starts with `sk-ant-`): handle it gracefully — run the `onecli secrets create` command with that value on their behalf.
|
||||
|
||||
**After user confirms:** verify with `onecli secrets list` that an Anthropic secret exists. If not, ask again.
|
||||
|
||||
## 5. Set Up Channels
|
||||
|
||||
Show the full list of available channels in plain text (do NOT use AskUserQuestion — it limits to 4 options). Ask which one they want to start with. They can add more later with `/customize`.
|
||||
|
||||
Channels where the agent gets its own identity (name and avatar) are marked as recommended.
|
||||
|
||||
1. Discord *(recommended — agent gets own identity)*
|
||||
2. Slack *(recommended — agent gets own identity)*
|
||||
3. Telegram *(recommended — agent gets own identity)*
|
||||
4. Microsoft Teams *(recommended — agent gets own identity)*
|
||||
5. Webex *(recommended — agent gets own identity)*
|
||||
6. WhatsApp
|
||||
7. WhatsApp Cloud API
|
||||
8. iMessage
|
||||
9. GitHub
|
||||
10. Linear
|
||||
11. Google Chat
|
||||
12. Resend (email)
|
||||
13. Matrix
|
||||
|
||||
**Delegate to the selected channel's skill.** Each channel skill handles its own package installation, authentication, registration, and configuration.
|
||||
|
||||
Invoke the matching skill:
|
||||
|
||||
- **Discord:** Invoke `/add-discord`
|
||||
- **Slack:** Invoke `/add-slack`
|
||||
- **Telegram:** Invoke `/add-telegram`
|
||||
- **GitHub:** Invoke `/add-github`
|
||||
- **Linear:** Invoke `/add-linear`
|
||||
- **Microsoft Teams:** Invoke `/add-teams`
|
||||
- **Google Chat:** Invoke `/add-gchat`
|
||||
- **WhatsApp Cloud API:** Invoke `/add-whatsapp-cloud`
|
||||
- **WhatsApp Baileys:** Invoke `/add-whatsapp`
|
||||
- **Resend:** Invoke `/add-resend`
|
||||
- **Matrix:** Invoke `/add-matrix`
|
||||
- **Webex:** Invoke `/add-webex`
|
||||
- **iMessage:** Invoke `/add-imessage`
|
||||
|
||||
The skill will:
|
||||
1. Install the Chat SDK adapter package
|
||||
2. Uncomment the channel import in `src/channels/index.ts`
|
||||
3. Collect credentials/tokens and write to `.env`
|
||||
4. Build and verify
|
||||
|
||||
**After the channel skill completes**, install dependencies and rebuild — channel merges may introduce new packages:
|
||||
|
||||
```bash
|
||||
pnpm install && pnpm run build
|
||||
```
|
||||
|
||||
If the build fails, read the error output and fix it (usually a missing dependency). Then continue to step 5a.
|
||||
|
||||
## 6. Mount Allowlist
|
||||
|
||||
Set empty mount allowlist (agents only access their own workspace). Users can configure mounts later with `/manage-mounts`.
|
||||
|
||||
```bash
|
||||
pnpm exec tsx setup/index.ts --step mounts -- --empty
|
||||
```
|
||||
|
||||
## 7. Start Service
|
||||
|
||||
If service already running: unload first.
|
||||
- macOS: `launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist`
|
||||
- Linux: `systemctl --user stop nanoclaw` (or `systemctl stop nanoclaw` if root)
|
||||
|
||||
Run `pnpm exec tsx setup/index.ts --step service` and parse the status block.
|
||||
|
||||
**If FALLBACK=wsl_no_systemd:** WSL without systemd detected. Tell user they can either enable systemd in WSL (`echo -e "[boot]\nsystemd=true" | sudo tee /etc/wsl.conf` then restart WSL) or use the generated `start-nanoclaw.sh` wrapper.
|
||||
|
||||
**If DOCKER_GROUP_STALE=true:** The user was added to the docker group after their session started — the systemd service can't reach the Docker socket. Ask user to run these two commands:
|
||||
|
||||
1. Immediate fix: `sudo setfacl -m u:$(whoami):rw /var/run/docker.sock`
|
||||
2. Persistent fix (re-applies after every Docker restart):
|
||||
```bash
|
||||
sudo mkdir -p /etc/systemd/system/docker.service.d
|
||||
sudo tee /etc/systemd/system/docker.service.d/socket-acl.conf << 'EOF'
|
||||
[Service]
|
||||
ExecStartPost=/usr/bin/setfacl -m u:USERNAME:rw /var/run/docker.sock
|
||||
EOF
|
||||
sudo systemctl daemon-reload
|
||||
```
|
||||
Replace `USERNAME` with the actual username (from `whoami`). Run the two `sudo` commands separately — the `tee` heredoc first, then `daemon-reload`. After user confirms setfacl ran, re-run the service step.
|
||||
|
||||
**If SERVICE_LOADED=false:**
|
||||
- Read `logs/setup.log` for the error.
|
||||
- macOS: check `launchctl list | grep nanoclaw`. If PID=`-` and status non-zero, read `logs/nanoclaw.error.log`.
|
||||
- Linux: check `systemctl --user status nanoclaw`.
|
||||
- Re-run the service step after fixing.
|
||||
|
||||
## 7a. Wire Channels to Agent Groups
|
||||
|
||||
The service is now running, so polling-based adapters (Telegram) can observe inbound messages — required for pairing.
|
||||
|
||||
Invoke `/manage-channels` to wire the installed channels to agent groups. This step:
|
||||
1. Creates the agent group(s) and assigns a name to the assistant
|
||||
2. Resolves each channel's platform-specific ID (Telegram via pairing code; other channels via the platform's own ID lookup)
|
||||
3. Decides the isolation level — whether channels share an agent, session, or are fully separate
|
||||
|
||||
The `/manage-channels` skill reads each channel's `## Channel Info` section from its SKILL.md for platform-specific guidance (terminology, how to find IDs, recommended isolation).
|
||||
|
||||
**This step is required.** Without it, channels are installed but not wired — messages will be silently dropped because the router has no agent group to route to.
|
||||
|
||||
## 7b. Dashboard & Web Applications
|
||||
|
||||
AskUserQuestion: Do you want to create a dashboard and build web applications?
|
||||
|
||||
1. **Yes (recommended)** — description: "Get a NanoClaw dashboard to monitor your agents and build custom websites however you want. Deploys to Vercel."
|
||||
2. **Not now** — description: "You can add this later with `/add-vercel`."
|
||||
|
||||
If yes: invoke `/add-vercel`.
|
||||
|
||||
## 8. Verify
|
||||
|
||||
Run `pnpm exec tsx setup/index.ts --step verify` and parse the status block.
|
||||
|
||||
**If STATUS=failed, fix each:**
|
||||
- SERVICE=stopped → `pnpm run build`, then restart: `launchctl kickstart -k gui/$(id -u)/com.nanoclaw` (macOS) or `systemctl --user restart nanoclaw` (Linux) or `bash start-nanoclaw.sh` (WSL nohup)
|
||||
- SERVICE=not_found → re-run step 7
|
||||
- CREDENTIALS=missing → re-run step 4 (check `onecli secrets list`)
|
||||
- CHANNEL_AUTH shows `not_found` for any channel → re-invoke that channel's skill (e.g. `/add-telegram`)
|
||||
- REGISTERED_GROUPS=0 → re-invoke `/manage-channels` from step 7a
|
||||
Tell user to test: send a message in their registered chat. Show: `tail -f logs/nanoclaw.log`
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
**Service not starting:** Check `logs/nanoclaw.error.log`. Common: wrong Node path (re-run step 7), credential system not running (check `curl ${ONECLI_URL}/api/health`), missing channel credentials (re-invoke channel skill).
|
||||
|
||||
**Container agent fails ("Claude Code process exited with code 1"):** Ensure Docker is running — `open -a Docker` (macOS) or `sudo systemctl start docker` (Linux). Check container logs in `groups/main/logs/container-*.log`.
|
||||
|
||||
**No response to messages:** Check trigger pattern. Main channel doesn't need prefix. Check DB: `pnpm exec tsx setup/index.ts --step verify`. Check `logs/nanoclaw.log`.
|
||||
|
||||
**Channel not connecting:** Verify the channel's credentials are set in `.env`. Channels auto-enable when their credentials are present. For WhatsApp: check `store/auth/creds.json` exists. For token-based channels: check token values in `.env`. Restart the service after any `.env` change.
|
||||
|
||||
**Unload service:** macOS: `launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist` | Linux: `systemctl --user stop nanoclaw`
|
||||
|
||||
|
||||
## 9. Diagnostics
|
||||
|
||||
1. Use the Read tool to read `.claude/skills/setup/diagnostics.md`.
|
||||
2. Follow every step in that file before completing setup.
|
||||
|
||||
## 10. Fork Setup
|
||||
|
||||
Only run this after the user has confirmed 2-way messaging works.
|
||||
|
||||
Check `git remote -v`. If `origin` points to `qwibitai/nanoclaw` (not a fork), ask in plain text:
|
||||
|
||||
> We recommend forking NanoClaw so you can push your customizations and pull updates easily. Would you like to set up a fork now?
|
||||
|
||||
If yes: instruct the user to fork `qwibitai/nanoclaw` on GitHub (they need to do this in their browser), then ask for their GitHub username. Run:
|
||||
```bash
|
||||
git remote rename origin upstream
|
||||
git remote add origin https://github.com/<their-username>/nanoclaw.git
|
||||
git push --force origin main
|
||||
```
|
||||
|
||||
If no: skip — upstream is already configured from step 0.
|
||||
If they hit an error partway through, it will offer Claude-assisted recovery inline — no need to come back here.
|
||||
|
||||
@@ -1,49 +0,0 @@
|
||||
# Diagnostics
|
||||
|
||||
Gather system info:
|
||||
|
||||
```bash
|
||||
node -p "require('./package.json').version"
|
||||
uname -s
|
||||
uname -m
|
||||
node -p "process.versions.node.split('.')[0]"
|
||||
```
|
||||
|
||||
Check if the user migrated from OpenClaw during this setup session (i.e. `/migrate-from-openclaw` was invoked). If you're unsure (e.g. after context compaction), check for `migration-state.md` in the project root — it exists during and sometimes after migration.
|
||||
|
||||
Write `/tmp/nanoclaw-diagnostics.json`. No paths, usernames, hostnames, or IP addresses.
|
||||
|
||||
```json
|
||||
{
|
||||
"api_key": "phc_fx1Hhx9ucz8GuaJC8LVZWO8u03yXZZJJ6ObS4yplnaP",
|
||||
"event": "setup_complete",
|
||||
"distinct_id": "<uuid>",
|
||||
"properties": {
|
||||
"success": true,
|
||||
"nanoclaw_version": "1.2.21",
|
||||
"os_platform": "darwin",
|
||||
"arch": "arm64",
|
||||
"node_major_version": 22,
|
||||
"channels_selected": ["telegram", "whatsapp"],
|
||||
"migrated_from_openclaw": false,
|
||||
"error_count": 0,
|
||||
"failed_step": null
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Show the entire JSON to the user and ask via AskUserQuestion: **Yes** / **No** / **Never ask again**
|
||||
|
||||
**Yes**:
|
||||
```bash
|
||||
curl -s -X POST https://us.i.posthog.com/capture/ -H 'Content-Type: application/json' -d @/tmp/nanoclaw-diagnostics.json
|
||||
rm /tmp/nanoclaw-diagnostics.json
|
||||
```
|
||||
|
||||
**No**: `rm /tmp/nanoclaw-diagnostics.json`
|
||||
|
||||
**Never ask again**:
|
||||
1. Replace contents of `.claude/skills/setup/diagnostics.md` with `# Diagnostics — opted out`
|
||||
2. Replace contents of `.claude/skills/update-nanoclaw/diagnostics.md` with `# Diagnostics — opted out`
|
||||
3. Remove the `## 9. Diagnostics` section from `.claude/skills/setup/SKILL.md` and the `## Diagnostics` section from `.claude/skills/update-nanoclaw/SKILL.md`
|
||||
4. `rm /tmp/nanoclaw-diagnostics.json`
|
||||
@@ -1,34 +0,0 @@
|
||||
[
|
||||
"Bash(bash setup.sh*)",
|
||||
"Bash(git remote *)",
|
||||
"Bash(npx tsx setup/index.ts*)",
|
||||
"Bash(npx tsx scripts/init-first-agent.ts*)",
|
||||
"Bash(npm install @chat-adapter/*)",
|
||||
"Bash(npm install chat-adapter-imessage*)",
|
||||
"Bash(npm install @bitbasti/chat-adapter-webex*)",
|
||||
"Bash(npm install @resend/chat-sdk-adapter*)",
|
||||
"Bash(npm install @whiskeysockets/baileys*)",
|
||||
"Bash(npm install @beeper/chat-adapter-matrix*)",
|
||||
"Bash(npm install @nanoco/nanoclaw-dashboard*)",
|
||||
"Bash(npm ci*)",
|
||||
"Bash(npm 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*)"
|
||||
]
|
||||
@@ -43,7 +43,6 @@ rm /tmp/nanoclaw-diagnostics.json
|
||||
**No**: `rm /tmp/nanoclaw-diagnostics.json`
|
||||
|
||||
**Never ask again**:
|
||||
1. Replace contents of `.claude/skills/setup/diagnostics.md` with `# Diagnostics — opted out`
|
||||
2. Replace contents of `.claude/skills/update-nanoclaw/diagnostics.md` with `# Diagnostics — opted out`
|
||||
3. Remove the `## 9. Diagnostics` section from `.claude/skills/setup/SKILL.md` and the `## Diagnostics` section from `.claude/skills/update-nanoclaw/SKILL.md`
|
||||
4. `rm /tmp/nanoclaw-diagnostics.json`
|
||||
1. Replace contents of `.claude/skills/update-nanoclaw/diagnostics.md` with `# Diagnostics — opted out`
|
||||
2. Remove the `## Diagnostics` section from `.claude/skills/update-nanoclaw/SKILL.md`
|
||||
3. `rm /tmp/nanoclaw-diagnostics.json`
|
||||
|
||||
@@ -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 `<string>` 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: <transcript>]`.
|
||||
|
||||
### 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`.
|
||||
@@ -1,7 +1,12 @@
|
||||
name: Label PR
|
||||
|
||||
# SECURITY: this workflow runs with write access to the base repo on fork PRs,
|
||||
# because `pull_request_target` executes in the context of the base branch.
|
||||
# Keep it metadata-only — do NOT add actions/checkout or any step that
|
||||
# executes PR-supplied content (install scripts, build commands, etc.).
|
||||
# See https://securitylab.github.com/resources/github-actions-preventing-pwn-requests/
|
||||
on:
|
||||
pull_request:
|
||||
pull_request_target:
|
||||
types: [opened, edited]
|
||||
|
||||
jobs:
|
||||
|
||||
+8
-7
@@ -11,18 +11,19 @@ store/
|
||||
data/
|
||||
logs/
|
||||
|
||||
# Groups - only track base structure and specific CLAUDE.md files
|
||||
# Groups - per-installation state, not tracked
|
||||
groups/*
|
||||
!groups/main/
|
||||
!groups/global/
|
||||
groups/main/*
|
||||
groups/global/*
|
||||
!groups/main/CLAUDE.md
|
||||
!groups/global/CLAUDE.md
|
||||
|
||||
# Composer-managed CLAUDE.md artifacts (regenerated every spawn) and
|
||||
# per-group memory (CLAUDE.local.md) must never be committed.
|
||||
**/CLAUDE.local.md
|
||||
**/.claude-shared.md
|
||||
**/.claude-fragments/
|
||||
|
||||
# Secrets
|
||||
*.keys.json
|
||||
.env
|
||||
.env*
|
||||
|
||||
# Temp files
|
||||
.tmp-*
|
||||
|
||||
@@ -4,6 +4,21 @@ All notable changes to NanoClaw will be documented in this file.
|
||||
|
||||
For detailed release notes, see the [full changelog on the documentation site](https://docs.nanoclaw.dev/changelog).
|
||||
|
||||
## [2.0.0] - 2026-04-22
|
||||
|
||||
Major version. NanoClaw v2 is a substantial architectural rewrite. Existing forks should run `/migrate-nanoclaw` (clean-base replay of customizations) or `/update-nanoclaw` (selective cherry-pick) before resuming work.
|
||||
|
||||
- [BREAKING] **New entity model.** Users, roles (owner/admin), messaging groups, and agent groups are now tracked as separate entities, wired via `messaging_group_agents`. Privilege is user-level instead of channel-level, so the old "main channel = admin" concept is retired. See [docs/architecture.md](docs/architecture.md) and [docs/isolation-model.md](docs/isolation-model.md).
|
||||
- [BREAKING] **Two-DB session split.** Each session now has `inbound.db` (host writes, container reads) and `outbound.db` (container writes, host reads) with exactly one writer each. Replaces the single shared session DB and eliminates cross-mount SQLite contention. See [docs/db-session.md](docs/db-session.md).
|
||||
- [BREAKING] **Install flow replaced.** `bash nanoclaw.sh` is the new default: a scripted installer that hands off to Claude Code for error recovery and guided decisions. The `/setup` Claude-guided skill still works as an alternative.
|
||||
- [BREAKING] **Channels moved to the `channels` branch.** Trunk no longer ships Discord, Slack, Telegram, WhatsApp, iMessage, Teams, Linear, GitHub, WeChat, Matrix, Google Chat, Webex, Resend, or WhatsApp Cloud. Install them per fork via `/add-<channel>` skills, which copy from the `channels` branch. `/update-nanoclaw` will re-install the channels your fork had.
|
||||
- [BREAKING] **Alternative providers moved to the `providers` branch.** OpenCode, Codex, and Ollama install via `/add-opencode`, `/add-codex`, `/add-ollama-provider`. Claude remains the default provider baked into trunk.
|
||||
- [BREAKING] **Three-level channel isolation.** Wire channels to their own agent (separate agent groups), share an agent with independent conversations (`session_mode: 'shared'`), or merge channels into one shared session (`session_mode: 'agent-shared'`). Chosen per channel via `/manage-channels`.
|
||||
- [BREAKING] **Apple Container removed from default setup.** Still available as an opt-in via `/convert-to-apple-container`.
|
||||
- **Shared-source agent-runner.** Per-group `agent-runner-src/` overlays are gone; all groups mount the same agent-runner read-only. Per-group customization flows through composed `CLAUDE.md` (shared base + per-group fragments).
|
||||
- **Agent-runner runtime moved from Node to Bun.** Container image is self-contained; no host-side impact. Host remains on Node + pnpm.
|
||||
- **OneCLI Agent Vault is the sole credential path.** Containers never receive raw API keys; credentials are injected at request time.
|
||||
|
||||
## [1.2.36] - 2026-03-26
|
||||
|
||||
- [BREAKING] Replaced pino logger with built-in logger. WhatsApp users must re-merge the WhatsApp fork to pick up the Baileys logger compatibility fix: `git fetch whatsapp main && git merge whatsapp/main`. If the `whatsapp` remote is not configured: `git remote add whatsapp https://github.com/qwibitai/nanoclaw-whatsapp.git`.
|
||||
|
||||
@@ -1,3 +1,18 @@
|
||||
# ⚠️ STOP — READ THIS FIRST IF YOU ARE CLAUDE ⚠️
|
||||
|
||||
**If you are reading this because you just ran `git pull`, `git merge`, `git fetch && git merge`, or any equivalent to bring in upstream changes — and you see merge conflicts or a large diff involving this file — HALT IMMEDIATELY.**
|
||||
|
||||
This is NanoClaw v2, a ground-up rewrite with breaking changes throughout. It cannot be merged into an existing v1 install. Attempting to resolve the conflicts by hand, run builds, or "fix" anything will corrupt the user's install and burn tokens for no result.
|
||||
|
||||
**Do this instead:**
|
||||
1. Abort the merge: `git merge --abort` (or `git reset --hard ORIG_HEAD` if the merge already completed).
|
||||
2. Tell the user, verbatim: *"This is the v2 rewrite — it can't be merged into your existing install. Run `bash migrate-v2.sh` to migrate instead."*
|
||||
3. Wait for the user to confirm before doing anything else. Do not attempt the migration yourself.
|
||||
|
||||
If you are a fresh install (you ran `git clone`, not `git pull`) and there are no conflicts, ignore this banner and continue below.
|
||||
|
||||
---
|
||||
|
||||
# NanoClaw
|
||||
|
||||
Personal Claude assistant. See [README.md](README.md) for philosophy and setup. Architecture lives in `docs/`.
|
||||
@@ -49,7 +64,9 @@ Exactly one writer per file — no cross-mount lock contention. Heartbeat is a f
|
||||
| `src/session-manager.ts` | Resolves sessions; opens `inbound.db` / `outbound.db`; manages heartbeat path |
|
||||
| `src/container-runner.ts` | Spawns per-agent-group Docker containers with session DB + outbox mounts, OneCLI `ensureAgent` |
|
||||
| `src/container-runtime.ts` | Runtime selection (Docker vs Apple containers), orphan cleanup |
|
||||
| `src/access.ts` | `pickApprover`, `pickApprovalDelivery`, admin resolution for `NANOCLAW_ADMIN_USER_IDS` |
|
||||
| `src/modules/permissions/access.ts` | `canAccessAgentGroup` — owner / global admin / scoped admin / member resolution against `user_roles` + `agent_group_members` |
|
||||
| `src/modules/approvals/primitive.ts` | `pickApprover`, `pickApprovalDelivery`, `requestApproval`, approval-handler registry |
|
||||
| `src/command-gate.ts` | Router-side admin command gate — queries `user_roles` directly (no env var, no container-side check) |
|
||||
| `src/onecli-approvals.ts` | OneCLI credentialed-action approval bridge |
|
||||
| `src/user-dm.ts` | Cold-DM resolution + `user_dms` cache |
|
||||
| `src/group-init.ts` | Per-agent-group filesystem scaffold (CLAUDE.md, skills, agent-runner-src overlay) |
|
||||
@@ -74,7 +91,7 @@ Each `/add-<name>` skill is idempotent: `git fetch origin <branch>` → copy mod
|
||||
|
||||
One tier of agent self-modification today:
|
||||
|
||||
1. **`install_packages` / `add_mcp_server` / `request_rebuild`** — changes to the per-agent-group container config only (apt/npm deps, wire an existing MCP server). Admin approval, rebuild, container restart. `container/agent-runner/src/mcp-tools/self-mod.ts`.
|
||||
1. **`install_packages` / `add_mcp_server`** — changes to the per-agent-group container config only (apt/npm deps, wire an existing MCP server). Single admin approval per request; on approve, the handler in `src/modules/self-mod/apply.ts` rebuilds the image when needed (`install_packages` only) and restarts the container. `container/agent-runner/src/mcp-tools/self-mod.ts`.
|
||||
|
||||
A second tier (direct source-level self-edits via a draft/activate flow) is planned but not yet implemented.
|
||||
|
||||
@@ -82,6 +99,41 @@ A second tier (direct source-level self-edits via a draft/activate flow) is plan
|
||||
|
||||
API keys, OAuth tokens, and auth credentials are managed by the OneCLI gateway. Secrets are injected into per-agent containers at request time — none are passed in env vars or through chat context. `src/onecli-approvals.ts`, `ensureAgent()` in `container-runner.ts`. Run `onecli --help`.
|
||||
|
||||
### Gotcha: auto-created agents start in `selective` secret mode
|
||||
|
||||
When the host first spawns a session for a new agent group, `container-runner.ts:385` calls `onecli.ensureAgent({ name, identifier })`. The OneCLI `POST /api/agents` endpoint creates the agent in **`selective`** secret mode — meaning **no secrets are assigned to it by default**, even if the secrets exist in the vault and have host patterns that would otherwise match.
|
||||
|
||||
Symptom: container starts, the proxy + CA cert are wired correctly, but the agent gets `401 Unauthorized` (or similar) from APIs whose credentials *are* in the vault. The credential just isn't in this agent's allow-list.
|
||||
|
||||
The SDK does not expose `setSecretMode` — the only fix is the CLI (or the web UI at `http://127.0.0.1:10254`).
|
||||
|
||||
```bash
|
||||
# Find the agent (identifier is the agent group id)
|
||||
onecli agents list
|
||||
|
||||
# Flip to "all" so every vault secret with a matching host pattern gets injected
|
||||
onecli agents set-secret-mode --id <agent-id> --mode all
|
||||
|
||||
# Or, stay selective and assign specific secrets
|
||||
onecli secrets list # find secret ids
|
||||
onecli agents set-secrets --id <agent-id> --secret-ids <id1>,<id2>
|
||||
|
||||
# Inspect what an agent currently has
|
||||
onecli agents secrets --id <agent-id> # secrets assigned to this agent
|
||||
onecli secrets list # all vault secrets (with host patterns)
|
||||
```
|
||||
|
||||
If you've just enabled `mode all`, no container restart is needed — the gateway looks up secrets per request, so the next API call from the running container will see the new credentials.
|
||||
|
||||
### Requiring approval for credential use
|
||||
|
||||
Approval-gating credentialed actions is a **two-sided** flow:
|
||||
|
||||
- **Server-side** (OneCLI gateway): decides *when* to hold a request and emit a pending approval. As of `onecli@1.3.0`, the CLI does **not** expose this — `rules create --action` only accepts `block` or `rate_limit`, and `secrets create` has no approval flag. Approval policies must be configured via the OneCLI web UI at `http://127.0.0.1:10254`. If/when the CLI grows an `approve` action, this section needs updating.
|
||||
- **Host-side** (nanoclaw): receives pending approvals and routes them to a human. `src/modules/approvals/onecli-approvals.ts` registers a callback via `onecli.configureManualApproval(cb)` (long-polls `GET /api/approvals/pending`). The callback uses `pickApprover` + `pickApprovalDelivery` from `src/modules/approvals/primitive.ts` to DM an approver. Approvers are resolved from the `user_roles` table — preference order: scoped admins for the agent group → global admins → owners. There is no env var like `NANOCLAW_ADMIN_USER_IDS`; roles are persisted in the central DB only.
|
||||
|
||||
If approvals are configured server-side but the host callback isn't running (or throws), every credentialed call hangs until the gateway times out. Conversely, if the gateway has no rule asking for approval, the host callback never fires regardless of how it's wired.
|
||||
|
||||
## Skills
|
||||
|
||||
Four types of skills. See [CONTRIBUTING.md](CONTRIBUTING.md) for the full taxonomy.
|
||||
@@ -157,7 +209,6 @@ This project uses pnpm with `minimumReleaseAge: 4320` (3 days) in `pnpm-workspac
|
||||
| [docs/agent-runner-details.md](docs/agent-runner-details.md) | Agent-runner internals + MCP tool interface |
|
||||
| [docs/isolation-model.md](docs/isolation-model.md) | Three-level channel isolation model |
|
||||
| [docs/setup-wiring.md](docs/setup-wiring.md) | What's wired, what's open in the setup flow |
|
||||
| [docs/checklist.md](docs/checklist.md) | Rolling status checklist across all subsystems |
|
||||
| [docs/architecture-diagram.md](docs/architecture-diagram.md) | Diagram version of the architecture |
|
||||
| [docs/build-and-runtime.md](docs/build-and-runtime.md) | Runtime split (Node host + Bun container), lockfiles, image build surface, CI, key invariants |
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@
|
||||
<a href="README_zh.md">中文</a> •
|
||||
<a href="README_ja.md">日本語</a> •
|
||||
<a href="https://discord.gg/VDdww8qS42"><img src="https://img.shields.io/discord/1470188214710046894?label=Discord&logo=discord&v=2" alt="Discord" valign="middle"></a> •
|
||||
<a href="repo-tokens"><img src="repo-tokens/badge.svg" alt="34.9k tokens, 17% of context window" valign="middle"></a>
|
||||
<a href="repo-tokens"><img src="repo-tokens/badge.svg" alt="repo tokens" valign="middle"></a>
|
||||
</p>
|
||||
|
||||
---
|
||||
@@ -26,55 +26,38 @@ NanoClaw provides that same core functionality, but in a codebase small enough t
|
||||
## Quick Start
|
||||
|
||||
```bash
|
||||
gh repo fork qwibitai/nanoclaw --clone
|
||||
cd nanoclaw
|
||||
claude
|
||||
git clone https://github.com/qwibitai/nanoclaw.git nanoclaw-v2
|
||||
cd nanoclaw-v2
|
||||
bash nanoclaw.sh
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>Without GitHub CLI</summary>
|
||||
|
||||
1. Fork [qwibitai/nanoclaw](https://github.com/qwibitai/nanoclaw) on GitHub (click the Fork button)
|
||||
2. `git clone https://github.com/<your-username>/nanoclaw.git`
|
||||
3. `cd nanoclaw`
|
||||
4. `claude`
|
||||
|
||||
</details>
|
||||
|
||||
Then run `/setup`. Claude Code handles everything: dependencies, authentication, container setup and service configuration.
|
||||
|
||||
> **Note:** Commands prefixed with `/` (like `/setup`, `/add-whatsapp`) are [Claude Code skills](https://code.claude.com/docs/en/skills). Type them inside the `claude` CLI prompt, not in your regular terminal. If you don't have Claude Code installed, get it at [claude.com/product/claude-code](https://claude.com/product/claude-code).
|
||||
`nanoclaw.sh` walks you from a fresh machine to a named agent you can message. It installs Node, pnpm, and Docker if missing, registers your Anthropic credential with OneCLI, builds the agent container, and pairs your first channel (Telegram, Discord, WhatsApp, or a local CLI). If a step fails, Claude Code is invoked automatically to diagnose and resume from where it broke.
|
||||
|
||||
## Philosophy
|
||||
|
||||
**Small enough to understand.** One process, a few source files and no microservices. If you want to understand the full NanoClaw codebase, just ask Claude Code to walk you through it.
|
||||
|
||||
**Secure by isolation.** Agents run in Linux containers (Apple Container on macOS, or Docker) and they can only see what's explicitly mounted. Bash access is safe because commands run inside the container, not on your host.
|
||||
**Secure by isolation.** Agents run in Linux containers and they can only see what's explicitly mounted. Bash access is safe because commands run inside the container, not on your host.
|
||||
|
||||
**Built for the individual user.** NanoClaw isn't a monolithic framework; it's software that fits each user's exact needs. Instead of becoming bloatware, NanoClaw is designed to be bespoke. You make your own fork and have Claude Code modify it to match your needs.
|
||||
|
||||
**Customization = code changes.** No configuration sprawl. Want different behavior? Modify the code. The codebase is small enough that it's safe to make changes.
|
||||
|
||||
**AI-native.**
|
||||
- No installation wizard; Claude Code guides setup.
|
||||
- No monitoring dashboard; ask Claude what's happening.
|
||||
- No debugging tools; describe the problem and Claude fixes it.
|
||||
**AI-native, hybrid by design.** The install and onboarding flow is an optimized scripted path, fast and deterministic. When a step needs judgment, whether a failed install, a guided decision, or a customization, control hands off to Claude Code seamlessly. Beyond setup there's no monitoring dashboard or debugging UI either: describe the problem in chat and Claude Code handles it.
|
||||
|
||||
**Skills over features.** Instead of adding features (e.g. support for Telegram) to the codebase, contributors submit [claude code skills](https://code.claude.com/docs/en/skills) like `/add-telegram` that transform your fork. You end up with clean code that does exactly what you need.
|
||||
**Skills over features.** Trunk ships the registry and infrastructure, not specific channel adapters or alternative agent providers. Channels (Discord, Slack, Telegram, WhatsApp, …) live on a long-lived `channels` branch; alternative providers (OpenCode, Ollama) live on `providers`. You run `/add-telegram`, `/add-opencode`, etc. and the skill copies exactly the module(s) you need into your fork. No feature you didn't ask for.
|
||||
|
||||
**Best harness, best model.** NanoClaw runs on the Claude Agent SDK, which means you're running Claude Code directly. Claude Code is highly capable and its coding and problem-solving capabilities allow it to modify and expand NanoClaw and tailor it to each user.
|
||||
**Best harness, best model.** NanoClaw natively uses Claude Code via Anthropic's official Claude Agent SDK, so you get the latest Claude models and Claude Code's full toolset, including the ability to modify and expand your own NanoClaw fork. Other providers are drop-in options: `/add-codex` for OpenAI's Codex (ChatGPT subscription or API key), `/add-opencode` for OpenRouter, Google, DeepSeek and more via OpenCode, and `/add-ollama-provider` for local open-weight models. Provider is configurable per agent group.
|
||||
|
||||
## What It Supports
|
||||
|
||||
- **Multi-channel messaging** - Talk to your assistant from WhatsApp, Telegram, Discord, Slack, or Gmail. Add channels with skills like `/add-whatsapp` or `/add-telegram`. Run one or many at the same time.
|
||||
- **Isolated group context** - Each group has its own `CLAUDE.md` memory, isolated filesystem, and runs in its own container sandbox with only that filesystem mounted to it.
|
||||
- **Main channel** - Your private channel (self-chat) for admin control; every group is completely isolated
|
||||
- **Scheduled tasks** - Recurring jobs that run Claude and can message you back
|
||||
- **Web access** - Search and fetch content from the Web
|
||||
- **Container isolation** - Agents are sandboxed in Docker (macOS/Linux), [Docker Sandboxes](docs/docker-sandboxes.md) (micro VM isolation), or Apple Container (macOS)
|
||||
- **Credential security** - Agents never hold raw API keys. Outbound requests route through [OneCLI's Agent Vault](https://github.com/onecli/onecli), which injects credentials at request time and enforces per-agent policies and rate limits.
|
||||
- **Agent Swarms** - Spin up teams of specialized agents that collaborate on complex tasks
|
||||
- **Optional integrations** - Add Gmail (`/add-gmail`) and more via skills
|
||||
- **Multi-channel messaging** — WhatsApp, Telegram, Discord, Slack, Microsoft Teams, iMessage, Matrix, Google Chat, Webex, Linear, GitHub, WeChat, and email via Resend. Installed on demand with `/add-<channel>` skills. Run one or many at the same time.
|
||||
- **Flexible isolation** — connect each channel to its own agent for full privacy, share one agent across many channels for unified memory with separate conversations, or fold multiple channels into a single shared session so one conversation spans many surfaces. Pick per channel via `/manage-channels`. See [docs/isolation-model.md](docs/isolation-model.md).
|
||||
- **Per-agent workspace** — each agent group has its own `CLAUDE.md`, its own memory, its own container, and only the mounts you allow. Nothing crosses the boundary unless you wire it to.
|
||||
- **Scheduled tasks** — recurring jobs that run Claude and can message you back
|
||||
- **Web access** — search and fetch content from the web
|
||||
- **Container isolation** — agents are sandboxed in Docker (macOS/Linux/WSL2), with optional [Docker Sandboxes](docs/docker-sandboxes.md) micro-VM isolation or Apple Container as a macOS-native opt-in
|
||||
- **Credential security** — agents never hold raw API keys. Outbound requests route through [OneCLI's Agent Vault](https://github.com/onecli/onecli), which injects credentials at request time and enforces per-agent policies and rate limits.
|
||||
|
||||
## Usage
|
||||
|
||||
@@ -86,7 +69,7 @@ Talk to your assistant with the trigger word (default: `@Andy`):
|
||||
@Andy every Monday at 8am, compile news on AI developments from Hacker News and TechCrunch and message me a briefing
|
||||
```
|
||||
|
||||
From the main channel (your self-chat), you can manage groups and tasks:
|
||||
From a channel you own or administer, you can manage groups and tasks:
|
||||
```
|
||||
@Andy list all scheduled tasks across groups
|
||||
@Andy pause the Monday briefing task
|
||||
@@ -110,54 +93,58 @@ The codebase is small enough that Claude can safely modify it.
|
||||
|
||||
**Don't add features. Add skills.**
|
||||
|
||||
If you want to add Telegram support, don't create a PR that adds Telegram to the core codebase. Instead, fork NanoClaw, make the code changes on a branch, and open a PR. We'll create a `skill/telegram` branch from your PR that other users can merge into their fork.
|
||||
If you want to add a new channel or agent provider, don't add it to trunk. New channel adapters land on the `channels` branch; new agent providers land on `providers`. Users install them in their own fork with `/add-<name>` skills, which copy the relevant module(s) into the standard paths, wire the registration, and pin dependencies.
|
||||
|
||||
Users then run `/add-telegram` on their fork and get clean code that does exactly what they need, not a bloated system trying to support every use case.
|
||||
This keeps trunk as pure registry and infra, and every fork stays lean — users get the channels and providers they asked for and nothing else.
|
||||
|
||||
### RFS (Request for Skills)
|
||||
|
||||
Skills we'd like to see:
|
||||
|
||||
**Communication Channels**
|
||||
- `/add-signal` - Add Signal as a channel
|
||||
- `/add-signal` — Add Signal as a channel
|
||||
|
||||
## Requirements
|
||||
|
||||
- macOS, Linux, or Windows (via WSL2)
|
||||
- Node.js 20+
|
||||
- [Claude Code](https://claude.ai/download)
|
||||
- [Apple Container](https://github.com/apple/container) (macOS) or [Docker](https://docker.com/products/docker-desktop) (macOS/Linux)
|
||||
- macOS or Linux (Windows via WSL2)
|
||||
- Node.js 20+ and pnpm 10+ (the installer will install both if missing)
|
||||
- [Docker Desktop](https://docker.com/products/docker-desktop) (macOS/Windows) or Docker Engine (Linux)
|
||||
- [Claude Code](https://claude.ai/download) for `/customize`, `/debug`, error recovery during setup, and all `/add-<channel>` skills
|
||||
|
||||
## Architecture
|
||||
|
||||
```
|
||||
Channels --> SQLite --> Polling loop --> Container (Claude Agent SDK) --> Response
|
||||
messaging apps → host process (router) → inbound.db → container (Bun, Claude Agent SDK) → outbound.db → host process (delivery) → messaging apps
|
||||
```
|
||||
|
||||
Single Node.js process. Channels are added via skills and self-register at startup — the orchestrator connects whichever ones have credentials present. Agents execute in isolated Linux containers with filesystem isolation. Only mounted directories are accessible. Per-group message queue with concurrency control. IPC via filesystem.
|
||||
A single Node host orchestrates per-session agent containers. When a message arrives, the host routes it via the entity model (user → messaging group → agent group → session), writes it to the session's `inbound.db`, and wakes the container. The agent-runner inside the container polls `inbound.db`, runs Claude, and writes responses to `outbound.db`. The host polls `outbound.db` and delivers back through the channel adapter.
|
||||
|
||||
For the full architecture details, see the [documentation site](https://docs.nanoclaw.dev/concepts/architecture).
|
||||
Two SQLite files per session, each with exactly one writer — no cross-mount contention, no IPC, no stdin piping. Channels and alternative providers self-register at startup; trunk ships the registry and the Chat SDK bridge, while the adapters themselves are skill-installed per fork.
|
||||
|
||||
For the full architecture writeup see [docs/architecture.md](docs/architecture.md); for the three-level isolation model see [docs/isolation-model.md](docs/isolation-model.md).
|
||||
|
||||
Key files:
|
||||
- `src/index.ts` - Orchestrator: state, message loop, agent invocation
|
||||
- `src/channels/registry.ts` - Channel registry (self-registration at startup)
|
||||
- `src/ipc.ts` - IPC watcher and task processing
|
||||
- `src/router.ts` - Message formatting and outbound routing
|
||||
- `src/group-queue.ts` - Per-group queue with global concurrency limit
|
||||
- `src/container-runner.ts` - Spawns streaming agent containers
|
||||
- `src/task-scheduler.ts` - Runs scheduled tasks
|
||||
- `src/db.ts` - SQLite operations (messages, groups, sessions, state)
|
||||
- `groups/*/CLAUDE.md` - Per-group memory
|
||||
- `src/index.ts` — entry point: DB init, channel adapters, delivery polls, sweep
|
||||
- `src/router.ts` — inbound routing: messaging group → agent group → session → `inbound.db`
|
||||
- `src/delivery.ts` — polls `outbound.db`, delivers via adapter, handles system actions
|
||||
- `src/host-sweep.ts` — 60s sweep: stale detection, due-message wake, recurrence
|
||||
- `src/session-manager.ts` — resolves sessions, opens `inbound.db` / `outbound.db`
|
||||
- `src/container-runner.ts` — spawns per-agent-group containers, OneCLI credential injection
|
||||
- `src/db/` — central DB (users, roles, agent groups, messaging groups, wiring, migrations)
|
||||
- `src/channels/` — channel adapter infra (adapters installed via `/add-<channel>` skills)
|
||||
- `src/providers/` — host-side provider config (`claude` baked in; others via skills)
|
||||
- `container/agent-runner/` — Bun agent-runner: poll loop, MCP tools, provider abstraction
|
||||
- `groups/<folder>/` — per-agent-group filesystem (`CLAUDE.md`, skills, container config)
|
||||
|
||||
## FAQ
|
||||
|
||||
**Why Docker?**
|
||||
|
||||
Docker provides cross-platform support (macOS, Linux and even Windows via WSL2) and a mature ecosystem. On macOS, you can optionally switch to Apple Container via `/convert-to-apple-container` for a lighter-weight native runtime. For additional isolation, [Docker Sandboxes](docs/docker-sandboxes.md) run each container inside a micro VM.
|
||||
Docker provides cross-platform support (macOS, Linux and Windows via WSL2) and a mature ecosystem. On macOS, you can optionally switch to Apple Container via `/convert-to-apple-container` for a lighter-weight native runtime. For additional isolation, [Docker Sandboxes](docs/docker-sandboxes.md) run each container inside a micro VM.
|
||||
|
||||
**Can I run this on Linux or Windows?**
|
||||
|
||||
Yes. Docker is the default runtime and works on macOS, Linux, and Windows (via WSL2). Just run `/setup`.
|
||||
Yes. Docker is the default runtime and works on macOS, Linux, and Windows (via WSL2). Just run `bash nanoclaw.sh`.
|
||||
|
||||
**Is this secure?**
|
||||
|
||||
@@ -169,33 +156,28 @@ We don't want configuration sprawl. Every user should customize NanoClaw so that
|
||||
|
||||
**Can I use third-party or open-source models?**
|
||||
|
||||
Yes. NanoClaw supports any Claude API-compatible model endpoint. Set these environment variables in your `.env` file:
|
||||
Yes. The supported path is `/add-opencode` (OpenRouter, OpenAI, Google, DeepSeek, and more via OpenCode config) or `/add-ollama-provider` (local open-weight models via Ollama). Both are configurable per agent group, so different agents can run on different backends in the same install.
|
||||
|
||||
For one-off experiments, any Claude API-compatible endpoint also works via `.env`:
|
||||
|
||||
```bash
|
||||
ANTHROPIC_BASE_URL=https://your-api-endpoint.com
|
||||
ANTHROPIC_AUTH_TOKEN=your-token-here
|
||||
```
|
||||
|
||||
This allows you to use:
|
||||
- Local models via [Ollama](https://ollama.ai) with an API proxy
|
||||
- Open-source models hosted on [Together AI](https://together.ai), [Fireworks](https://fireworks.ai), etc.
|
||||
- Custom model deployments with Anthropic-compatible APIs
|
||||
|
||||
Note: The model must support the Anthropic API format for best compatibility.
|
||||
|
||||
**How do I debug issues?**
|
||||
|
||||
Ask Claude Code. "Why isn't the scheduler running?" "What's in the recent logs?" "Why did this message not get a response?" That's the AI-native approach that underlies NanoClaw.
|
||||
|
||||
**Why isn't the setup working for me?**
|
||||
|
||||
If you have issues, during setup, Claude will try to dynamically fix them. If that doesn't work, run `claude`, then run `/debug`. If Claude finds an issue that is likely affecting other users, open a PR to modify the setup SKILL.md.
|
||||
If a step fails, `nanoclaw.sh` hands off to Claude Code to diagnose and resume. If that doesn't resolve it, run `claude`, then `/debug`. If Claude identifies an issue likely to affect other users, open a PR against the relevant setup step or skill.
|
||||
|
||||
**What changes will be accepted into the codebase?**
|
||||
|
||||
Only security fixes, bug fixes, and clear improvements will be accepted to the base configuration. That's all.
|
||||
|
||||
Everything else (new capabilities, OS compatibility, hardware support, enhancements) should be contributed as skills.
|
||||
Everything else (new capabilities, OS compatibility, hardware support, enhancements) should be contributed as skills on the `channels` or `providers` branch.
|
||||
|
||||
This keeps the base system minimal and lets every user customize their installation without inheriting features they don't want.
|
||||
|
||||
|
||||
+63
-101
@@ -8,90 +8,56 @@
|
||||
|
||||
<p align="center">
|
||||
<a href="https://nanoclaw.dev">nanoclaw.dev</a> •
|
||||
<a href="https://docs.nanoclaw.dev">ドキュメント</a> •
|
||||
<a href="README.md">English</a> •
|
||||
<a href="README_zh.md">中文</a> •
|
||||
<a href="https://discord.gg/VDdww8qS42"><img src="https://img.shields.io/discord/1470188214710046894?label=Discord&logo=discord&v=2" alt="Discord" valign="middle"></a> •
|
||||
<a href="repo-tokens"><img src="repo-tokens/badge.svg" alt="34.9k tokens, 17% of context window" valign="middle"></a>
|
||||
<a href="repo-tokens"><img src="repo-tokens/badge.svg" alt="repo tokens" valign="middle"></a>
|
||||
</p>
|
||||
|
||||
---
|
||||
|
||||
<h2 align="center">🐳 Dockerサンドボックスで動作</h2>
|
||||
<p align="center">各エージェントはマイクロVM内の独立したコンテナで実行されます。<br>ハイパーバイザーレベルの分離。ミリ秒で起動。複雑なセットアップ不要。</p>
|
||||
|
||||
**macOS (Apple Silicon)**
|
||||
```bash
|
||||
curl -fsSL https://nanoclaw.dev/install-docker-sandboxes.sh | bash
|
||||
```
|
||||
|
||||
**Windows (WSL)**
|
||||
```bash
|
||||
curl -fsSL https://nanoclaw.dev/install-docker-sandboxes-windows.sh | bash
|
||||
```
|
||||
|
||||
> 現在、macOS(Apple Silicon)とWindows(x86)に対応しています。Linux対応は近日公開予定。
|
||||
|
||||
<p align="center"><a href="https://nanoclaw.dev/blog/nanoclaw-docker-sandboxes">発表記事を読む →</a> · <a href="docs/docker-sandboxes.md">手動セットアップガイド →</a></p>
|
||||
|
||||
---
|
||||
|
||||
## NanoClawを作った理由
|
||||
|
||||
[OpenClaw](https://github.com/openclaw/openclaw)は素晴らしいプロジェクトですが、理解しきれない複雑なソフトウェアに自分の生活へのフルアクセスを与えたまま安心して眠れるとは思えませんでした。OpenClawは約50万行のコード、53の設定ファイル、70以上の依存関係を持っています。セキュリティはアプリケーションレベル(許可リスト、ペアリングコード)であり、真のOS レベルの分離ではありません。すべてが共有メモリを持つ1つのNodeプロセスで動作します。
|
||||
[OpenClaw](https://github.com/openclaw/openclaw)は素晴らしいプロジェクトですが、自分が理解しきれない複雑なソフトウェアに生活へのフルアクセスを与えたまま安心して眠れるとは思えませんでした。OpenClawは約50万行のコード、53の設定ファイル、70以上の依存関係を持っています。セキュリティはアプリケーションレベル(許可リスト、ペアリングコード)であり、真のOSレベルの分離ではありません。すべてが共有メモリを持つ1つのNodeプロセスで動作します。
|
||||
|
||||
NanoClawは同じコア機能を提供しますが、理解できる規模のコードベースで実現しています:1つのプロセスと少数のファイル。Claudeエージェントは単なるパーミッションチェックの背後ではなく、ファイルシステム分離された独自のLinuxコンテナで実行されます。
|
||||
NanoClawは同じコア機能を提供しますが、理解できる規模のコードベースで実現しています。1つのプロセスと少数のファイル。Claudeエージェントは単なるパーミッションチェックの背後ではなく、ファイルシステム分離された独自のLinuxコンテナで実行されます。
|
||||
|
||||
## クイックスタート
|
||||
|
||||
```bash
|
||||
gh repo fork qwibitai/nanoclaw --clone
|
||||
cd nanoclaw
|
||||
claude
|
||||
git clone https://github.com/qwibitai/nanoclaw.git nanoclaw-v2
|
||||
cd nanoclaw-v2
|
||||
bash nanoclaw.sh
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>GitHub CLIなしの場合</summary>
|
||||
|
||||
1. GitHub上で[qwibitai/nanoclaw](https://github.com/qwibitai/nanoclaw)をフォーク(Forkボタンをクリック)
|
||||
2. `git clone https://github.com/<あなたのユーザー名>/nanoclaw.git`
|
||||
3. `cd nanoclaw`
|
||||
4. `claude`
|
||||
|
||||
</details>
|
||||
|
||||
その後、`/setup`を実行します。Claude Codeがすべてを処理します:依存関係、認証、コンテナセットアップ、サービス設定。
|
||||
|
||||
> **注意:** `/`で始まるコマンド(`/setup`、`/add-whatsapp`など)は[Claude Codeスキル](https://code.claude.com/docs/en/skills)です。通常のターミナルではなく、`claude` CLIプロンプト内で入力してください。Claude Codeをインストールしていない場合は、[claude.com/product/claude-code](https://claude.com/product/claude-code)から入手してください。
|
||||
`nanoclaw.sh`は、まっさらなマシンから、メッセージを送れる名前付きエージェントが動く状態までを一気通貫で案内します。NodeやpnpmやDockerが無ければインストールし、AnthropicクレデンシャルをOneCLIに登録し、エージェントコンテナをビルドし、最初のチャネル(Telegram、Discord、WhatsApp、またはローカルCLI)とペアリングします。途中でステップが失敗すれば自動的にClaude Codeが呼び出され、原因を診断して中断箇所から再開します。
|
||||
|
||||
## 設計思想
|
||||
|
||||
**理解できる規模。** 1つのプロセス、少数のソースファイル、マイクロサービスなし。NanoClawのコードベース全体を理解したい場合は、Claude Codeに説明を求めるだけです。
|
||||
**理解できる規模。** 1つのプロセス、少数のソースファイル、マイクロサービスなし。NanoClawのコードベース全体を把握したいなら、Claude Codeに説明を求めれば十分です。
|
||||
|
||||
**分離によるセキュリティ。** エージェントはLinuxコンテナ(macOSではApple Container、またはDocker)で実行され、明示的にマウントされたものだけが見えます。コマンドはホストではなくコンテナ内で実行されるため、Bashアクセスは安全です。
|
||||
**分離によるセキュリティ。** エージェントはLinuxコンテナで実行され、明示的にマウントされたものだけが見えます。コマンドはホストではなくコンテナ内で実行されるため、Bashアクセスも安全です。
|
||||
|
||||
**個人ユーザー向け。** NanoClawはモノリシックなフレームワークではなく、各ユーザーのニーズに正確にフィットするソフトウェアです。肥大化するのではなく、オーダーメイドになるよう設計されています。自分のフォークを作成し、Claude Codeにニーズに合わせて変更させます。
|
||||
**個人ユーザー向け。** NanoClawはモノリシックなフレームワークではなく、各ユーザーのニーズに正確にフィットするソフトウェアです。肥大化するのではなく、オーダーメイドであるよう設計されています。自分のフォークを作り、Claude Codeにニーズに合わせて変更させます。
|
||||
|
||||
**カスタマイズ=コード変更。** 設定ファイルの肥大化なし。動作を変えたい?コードを変更するだけ。コードベースは変更しても安全な規模です。
|
||||
**カスタマイズ=コード変更。** 設定の肥大化はありません。動作を変えたいならコードを変える。コードベースは変更しても安全な規模です。
|
||||
|
||||
**AIネイティブ。**
|
||||
- インストールウィザードなし — Claude Codeがセットアップを案内。
|
||||
- モニタリングダッシュボードなし — Claudeに状況を聞くだけ。
|
||||
- デバッグツールなし — 問題を説明すればClaudeが修正。
|
||||
**AIネイティブ、設計としてハイブリッド。** インストールとオンボーディングは最適化されたスクリプトのパスで、速く決定的です。判断が必要なところ(インストール失敗、対話的な決定、カスタマイズ)では、制御はシームレスにClaude Codeへ渡されます。セットアップ以降も、監視ダッシュボードやデバッグUIは用意しません。問題をチャットで説明すれば、Claude Codeが処理します。
|
||||
|
||||
**機能追加ではなくスキル。** コードベースに機能(例:Telegram対応)を追加する代わりに、コントリビューターは`/add-telegram`のような[Claude Codeスキル](https://code.claude.com/docs/en/skills)を提出し、あなたのフォークを変換します。あなたが必要なものだけを正確に実行するクリーンなコードが手に入ります。
|
||||
**機能ではなくスキル。** トランクにはレジストリとインフラのみを同梱し、個別のチャネルアダプターや代替プロバイダーは含めません。チャネル(Discord、Slack、Telegram、WhatsAppなど)は長期運用される`channels`ブランチに、代替プロバイダー(OpenCode、Ollama)は`providers`ブランチに置かれます。`/add-telegram`や`/add-opencode`などを実行すると、スキルが必要なモジュールだけを正確にフォークへコピーします。要求していない機能は一切入りません。
|
||||
|
||||
**最高のハーネス、最高のモデル。** NanoClawはClaude Agent SDK上で動作します。つまり、Claude Codeを直接実行しているということです。Claude Codeは高い能力を持ち、そのコーディングと問題解決能力によってNanoClawを変更・拡張し、各ユーザーに合わせてカスタマイズできます。
|
||||
**最高のハーネス、最高のモデル。** NanoClawはAnthropic公式のClaude Agent SDK経由でネイティブにClaude Codeを使用します。最新のClaudeモデルとClaude Codeの全ツールセット(自分のNanoClawフォークを変更・拡張する能力を含む)が手に入ります。他プロバイダーはドロップイン・オプションです。OpenAIのCodex(ChatGPTサブスクリプションまたはAPIキー)向けには`/add-codex`、OpenCode経由のOpenRouter、Google、DeepSeekなどには`/add-opencode`、ローカルのオープンウェイトモデルには`/add-ollama-provider`。プロバイダーはエージェントグループごとに設定可能です。
|
||||
|
||||
## サポート機能
|
||||
|
||||
- **マルチチャネルメッセージング** - WhatsApp、Telegram、Discord、Slack、Gmailからアシスタントと会話。`/add-whatsapp`や`/add-telegram`などのスキルでチャネルを追加。1つでも複数でも同時に実行可能。
|
||||
- **グループごとの分離コンテキスト** - 各グループは独自の`CLAUDE.md`メモリ、分離されたファイルシステムを持ち、そのファイルシステムのみがマウントされた専用コンテナサンドボックスで実行。
|
||||
- **メインチャネル** - 管理制御用のプライベートチャネル(セルフチャット)。各グループは完全に分離。
|
||||
- **スケジュールタスク** - Claudeを実行し、メッセージを返せる定期ジョブ。
|
||||
- **Webアクセス** - Webからのコンテンツ検索・取得。
|
||||
- **コンテナ分離** - エージェントは[Dockerサンドボックス](https://nanoclaw.dev/blog/nanoclaw-docker-sandboxes)(マイクロVM分離)、Apple Container(macOS)、またはDocker(macOS/Linux)でサンドボックス化。
|
||||
- **エージェントスウォーム** - 複雑なタスクで協力する専門エージェントチームを起動。
|
||||
- **オプション連携** - Gmail(`/add-gmail`)などをスキルで追加。
|
||||
- **マルチチャネルメッセージング** — WhatsApp、Telegram、Discord、Slack、Microsoft Teams、iMessage、Matrix、Google Chat、Webex、Linear、GitHub、WeChat、Resend経由のメール。`/add-<channel>`スキルでオンデマンドにインストール。1つでも複数でも同時に実行可能。
|
||||
- **柔軟な分離モデル** — チャネルごとに専用エージェントを割り当てて完全プライバシーを確保することも、複数チャネルで1つのエージェントを共有して会話は分離しつつメモリを統一することも、複数チャネルを1つの共有セッションにまとめて会話を横断させることもできます。`/manage-channels`でチャネル単位に選択。[docs/isolation-model.md](docs/isolation-model.md)参照。
|
||||
- **エージェントごとのワークスペース** — 各エージェントグループは独自の`CLAUDE.md`、独自のメモリ、独自のコンテナ、そしてあなたが許可したマウントのみを持ちます。明示的に配線しない限り、境界を越えるものはありません。
|
||||
- **スケジュールタスク** — Claudeを実行し、結果を返信できる定期ジョブ。
|
||||
- **Webアクセス** — Webからの検索とコンテンツ取得。
|
||||
- **コンテナ分離** — エージェントはDockerでサンドボックス化されます(macOS/Linux/WSL2)。[Docker Sandboxes](docs/docker-sandboxes.md)によるマイクロVM分離や、macOSネイティブのオプトインとしてApple Containerも選択可能です。
|
||||
- **クレデンシャルのセキュリティ** — エージェントは生のAPIキーを保持しません。アウトバウンドリクエストは[OneCLI Agent Vault](https://github.com/onecli/onecli)を経由し、リクエスト時に認証情報を注入して、エージェントごとのポリシーとレート制限を適用します。
|
||||
|
||||
## 使い方
|
||||
|
||||
@@ -103,7 +69,7 @@ claude
|
||||
@Andy 毎週月曜の朝8時に、Hacker NewsとTechCrunchからAI関連のニュースをまとめてブリーフィングを送って
|
||||
```
|
||||
|
||||
メインチャネル(セルフチャット)から、グループやタスクを管理できます:
|
||||
所有または管理しているチャネルからは、グループやタスクを管理できます:
|
||||
```
|
||||
@Andy 全グループのスケジュールタスクを一覧表示して
|
||||
@Andy 月曜のブリーフィングタスクを一時停止して
|
||||
@@ -112,14 +78,14 @@ claude
|
||||
|
||||
## カスタマイズ
|
||||
|
||||
NanoClawは設定ファイルを使いません。変更するには、Claude Codeに伝えるだけです:
|
||||
NanoClawは設定ファイルを使いません。変更したいときは、Claude Codeにやりたいことを伝えるだけです:
|
||||
|
||||
- 「トリガーワードを@Bobに変更して」
|
||||
- 「今後はレスポンスをもっと短く直接的にして」
|
||||
- 「おはようと言ったらカスタム挨拶を追加して」
|
||||
- 「会話の要約を毎週保存して」
|
||||
|
||||
または`/customize`を実行してガイド付きの変更を行えます。
|
||||
または`/customize`を実行すればガイド付きで変更できます。
|
||||
|
||||
コードベースは十分に小さいため、Claudeが安全に変更できます。
|
||||
|
||||
@@ -127,105 +93,101 @@ NanoClawは設定ファイルを使いません。変更するには、Claude Co
|
||||
|
||||
**機能を追加するのではなく、スキルを追加してください。**
|
||||
|
||||
Telegram対応を追加したい場合、コアコードベースにTelegramを追加するPRを作成しないでください。代わりに、NanoClawをフォークし、ブランチでコード変更を行い、PRを開いてください。あなたのPRから`skill/telegram`ブランチを作成し、他のユーザーが自分のフォークにマージできるようにします。
|
||||
新しいチャネルやエージェントプロバイダーを追加したい場合、トランクには追加しないでください。新しいチャネルアダプターは`channels`ブランチに、新しいエージェントプロバイダーは`providers`ブランチに追加します。ユーザーはそれぞれのフォークで`/add-<name>`スキルを実行し、スキルが必要なモジュールを標準パスへコピーし、登録を配線し、依存関係をピン留めします。
|
||||
|
||||
ユーザーは自分のフォークで`/add-telegram`を実行するだけで、あらゆるユースケースに対応しようとする肥大化したシステムではなく、必要なものだけを正確に実行するクリーンなコードが手に入ります。
|
||||
こうすることでトランクは純粋なレジストリ/インフラのまま保たれ、どのフォークもスリムなままです。ユーザーは求めたチャネルとプロバイダーだけを受け取り、それ以外は入りません。
|
||||
|
||||
### RFS(スキル募集)
|
||||
|
||||
私たちが求めているスキル:
|
||||
私たちが見たいスキル:
|
||||
|
||||
**コミュニケーションチャネル**
|
||||
- `/add-signal` - Signalをチャネルとして追加
|
||||
|
||||
**セッション管理**
|
||||
- `/clear` - 会話をコンパクト化する`/clear`コマンドの追加(同一セッション内で重要な情報を保持しながらコンテキストを要約)。Claude Agent SDKを通じてプログラム的にコンパクト化をトリガーする方法の解明が必要。
|
||||
- `/add-signal` — Signalをチャネルとして追加
|
||||
|
||||
## 必要条件
|
||||
|
||||
- macOSまたはLinux
|
||||
- Node.js 20以上
|
||||
- [Claude Code](https://claude.ai/download)
|
||||
- [Apple Container](https://github.com/apple/container)(macOS)または[Docker](https://docker.com/products/docker-desktop)(macOS/Linux)
|
||||
- macOSまたはLinux(WindowsはWSL2経由)
|
||||
- Node.js 20以上とpnpm 10以上(インストーラーが未インストールなら両方をインストールします)
|
||||
- [Docker Desktop](https://docker.com/products/docker-desktop)(macOS/Windows)または Docker Engine(Linux)
|
||||
- [Claude Code](https://claude.ai/download)(`/customize`、`/debug`、セットアップ時のエラー復旧、全ての`/add-<channel>`スキルで使用)
|
||||
|
||||
## アーキテクチャ
|
||||
|
||||
```
|
||||
チャネル --> SQLite --> ポーリングループ --> コンテナ(Claude Agent SDK) --> レスポンス
|
||||
メッセージングアプリ → ホストプロセス(ルーター) → inbound.db → コンテナ(Bun、Claude Agent SDK) → outbound.db → ホストプロセス(配信) → メッセージングアプリ
|
||||
```
|
||||
|
||||
単一のNode.jsプロセス。チャネルはスキルで追加され、起動時に自己登録します — オーケストレーターは認証情報が存在するチャネルを接続します。エージェントはファイルシステム分離された独立したLinuxコンテナで実行されます。マウントされたディレクトリのみアクセス可能。グループごとのメッセージキューと同時実行制御。ファイルシステム経由のIPC。
|
||||
単一のNodeホストがセッションごとのエージェントコンテナをオーケストレーションします。メッセージが到着すると、ホストはエンティティモデル(ユーザー → メッセージンググループ → エージェントグループ → セッション)に沿ってルーティングし、セッションの`inbound.db`に書き込み、コンテナを起こします。コンテナ内部のagent-runnerは`inbound.db`をポーリングしてClaudeを実行し、レスポンスを`outbound.db`に書き込みます。ホストは`outbound.db`をポーリングし、チャネルアダプターを通じて配信します。
|
||||
|
||||
詳細なアーキテクチャについては、[docs/SPEC.md](docs/SPEC.md)を参照してください。
|
||||
セッションごとに2つのSQLiteファイル、各ファイルにライターは1つだけ — クロスマウントの競合なし、IPCなし、stdinパイプなし。チャネルと代替プロバイダーは起動時に自己登録します。トランクはレジストリとChat SDKブリッジを同梱し、アダプター本体はフォークごとにスキルでインストールされます。
|
||||
|
||||
詳しいアーキテクチャ説明は[docs/architecture.md](docs/architecture.md)を、3階層の分離モデルについては[docs/isolation-model.md](docs/isolation-model.md)を参照してください。
|
||||
|
||||
主要ファイル:
|
||||
- `src/index.ts` - オーケストレーター:状態、メッセージループ、エージェント呼び出し
|
||||
- `src/channels/registry.ts` - チャネルレジストリ(起動時の自己登録)
|
||||
- `src/ipc.ts` - IPCウォッチャーとタスク処理
|
||||
- `src/router.ts` - メッセージフォーマットとアウトバウンドルーティング
|
||||
- `src/group-queue.ts` - グローバル同時実行制限付きのグループごとのキュー
|
||||
- `src/container-runner.ts` - ストリーミングエージェントコンテナの起動
|
||||
- `src/task-scheduler.ts` - スケジュールタスクの実行
|
||||
- `src/db.ts` - SQLite操作(メッセージ、グループ、セッション、状態)
|
||||
- `groups/*/CLAUDE.md` - グループごとのメモリ
|
||||
- `src/index.ts` — エントリーポイント:DB初期化、チャネルアダプター、配信ポーリング、sweep
|
||||
- `src/router.ts` — インバウンドルーティング:メッセージンググループ → エージェントグループ → セッション → `inbound.db`
|
||||
- `src/delivery.ts` — `outbound.db`をポーリングし、アダプター経由で配信、システムアクションを処理
|
||||
- `src/host-sweep.ts` — 60秒ごとのsweep:ストール検出、期限到来メッセージの起動、繰り返し
|
||||
- `src/session-manager.ts` — セッションの解決、`inbound.db`と`outbound.db`のオープン
|
||||
- `src/container-runner.ts` — エージェントグループごとのコンテナ起動、OneCLIによるクレデンシャル注入
|
||||
- `src/db/` — セントラルDB(ユーザー、ロール、エージェントグループ、メッセージンググループ、配線、マイグレーション)
|
||||
- `src/channels/` — チャネルアダプターのインフラ(アダプターは`/add-<channel>`スキルでインストール)
|
||||
- `src/providers/` — ホスト側プロバイダー設定(`claude`はバンドル、その他はスキル経由)
|
||||
- `container/agent-runner/` — Bun製agent-runner:ポーリングループ、MCPツール、プロバイダー抽象化
|
||||
- `groups/<folder>/` — エージェントグループごとのファイルシステム(`CLAUDE.md`、スキル、コンテナ設定)
|
||||
|
||||
## FAQ
|
||||
|
||||
**なぜDockerなのか?**
|
||||
|
||||
Dockerはクロスプラットフォーム対応(macOS、Linux、さらにWSL2経由のWindows)と成熟したエコシステムを提供します。macOSでは、`/convert-to-apple-container`でオプションとしてApple Containerに切り替え、より軽量なネイティブランタイムを使用できます。
|
||||
Dockerはクロスプラットフォーム対応(macOS、Linux、WSL2経由のWindows)と成熟したエコシステムを提供します。macOSでは、`/convert-to-apple-container`でオプションとしてApple Containerに切り替え、より軽量なネイティブランタイムを使えます。さらに強い分離が必要なら、[Docker Sandboxes](docs/docker-sandboxes.md)が各コンテナをマイクロVM内で動作させます。
|
||||
|
||||
**Linuxで実行できますか?**
|
||||
**LinuxやWindowsで実行できますか?**
|
||||
|
||||
はい。DockerがデフォルトのランタイムでmacOSとLinuxの両方で動作します。`/setup`を実行するだけです。
|
||||
はい。Dockerがデフォルトのランタイムで、macOS、Linux、Windows(WSL2経由)で動作します。`bash nanoclaw.sh`を実行するだけです。
|
||||
|
||||
**セキュリティは大丈夫ですか?**
|
||||
|
||||
エージェントはアプリケーションレベルのパーミッションチェックの背後ではなく、コンテナで実行されます。明示的にマウントされたディレクトリのみアクセスできます。実行するものをレビューすべきですが、コードベースは十分に小さいため実際にレビュー可能です。完全なセキュリティモデルについては[docs/SECURITY.md](docs/SECURITY.md)を参照してください。
|
||||
エージェントはアプリケーションレベルのパーミッションチェックではなく、コンテナ内で実行されます。明示的にマウントされたディレクトリのみアクセス可能です。クレデンシャルはコンテナに渡されず、アウトバウンドAPIリクエストは[OneCLI Agent Vault](https://github.com/onecli/onecli)を経由し、プロキシレベルで認証を注入し、レートリミットやアクセスポリシーをサポートします。実行するものはレビューすべきですが、コードベースは実際にレビュー可能な規模です。完全なセキュリティモデルについては[セキュリティドキュメント](https://docs.nanoclaw.dev/concepts/security)を参照してください。
|
||||
|
||||
**なぜ設定ファイルがないのか?**
|
||||
|
||||
設定の肥大化を避けたいからです。すべてのユーザーがNanoClawをカスタマイズし、汎用的なシステムを設定するのではなく、コードが必要なことを正確に実行するようにすべきです。設定ファイルが欲しい場合は、Claudeに追加するよう伝えることができます。
|
||||
設定の肥大化を避けたいからです。すべてのユーザーがNanoClawをカスタマイズし、汎用的なシステムを設定するのではなくコードが自分の望み通りに動くようにすべきです。設定ファイルが欲しければClaudeに追加するよう伝えれば実現できます。
|
||||
|
||||
**サードパーティやオープンソースモデルを使えますか?**
|
||||
|
||||
はい。NanoClawはClaude API互換のモデルエンドポイントに対応しています。`.env`ファイルで以下の環境変数を設定してください:
|
||||
はい。推奨される方法は`/add-opencode`(OpenCode設定経由でOpenRouter、OpenAI、Google、DeepSeekなど)か`/add-ollama-provider`(Ollama経由でローカルのオープンウェイトモデル)です。どちらもエージェントグループごとに設定可能なので、同じインストール内で異なるエージェントが異なるバックエンドで動作できます。
|
||||
|
||||
一時的な実験用には、Claude API互換のエンドポイントも`.env`で利用できます:
|
||||
|
||||
```bash
|
||||
ANTHROPIC_BASE_URL=https://your-api-endpoint.com
|
||||
ANTHROPIC_AUTH_TOKEN=your-token-here
|
||||
```
|
||||
|
||||
以下が使用可能です:
|
||||
- [Ollama](https://ollama.ai)とAPIプロキシ経由のローカルモデル
|
||||
- [Together AI](https://together.ai)、[Fireworks](https://fireworks.ai)等でホストされたオープンソースモデル
|
||||
- Anthropic互換APIのカスタムモデルデプロイメント
|
||||
|
||||
注意:最高の互換性のため、モデルはAnthropic APIフォーマットに対応している必要があります。
|
||||
|
||||
**問題のデバッグ方法は?**
|
||||
|
||||
Claude Codeに聞いてください。「スケジューラーが動いていないのはなぜ?」「最近のログには何がある?」「このメッセージに返信がなかったのはなぜ?」これがNanoClawの基盤となるAIネイティブなアプローチです。
|
||||
|
||||
**セットアップがうまくいかない場合は?**
|
||||
|
||||
問題がある場合、セットアップ中にClaudeが動的に修正を試みます。それでもうまくいかない場合は、`claude`を実行してから`/debug`を実行してください。Claudeが他のユーザーにも影響する可能性のある問題を見つけた場合は、セットアップのSKILL.mdを修正するPRを開いてください。
|
||||
ステップが失敗した場合、`nanoclaw.sh`は診断と再開のためにClaude Codeへ制御を渡します。それでも解決しなければ、`claude`を実行して`/debug`を呼び出してください。他のユーザーにも影響しそうな問題をClaudeが特定した場合は、該当のセットアップステップまたはスキルにPRを送ってください。
|
||||
|
||||
**どのような変更がコードベースに受け入れられますか?**
|
||||
|
||||
セキュリティ修正、バグ修正、明確な改善のみが基本設定に受け入れられます。それだけです。
|
||||
ベース設定に受け入れられるのは、セキュリティ修正、バグ修正、明確な改善のみです。それだけです。
|
||||
|
||||
それ以外のすべて(新機能、OS互換性、ハードウェアサポート、機能拡張)はスキルとしてコントリビューションすべきです。
|
||||
それ以外(新機能、OS互換性、ハードウェアサポート、拡張など)は、`channels`または`providers`ブランチのスキルとしてコントリビュートしてください。
|
||||
|
||||
これにより、基本システムを最小限に保ち、すべてのユーザーが不要な機能を継承することなく、自分のインストールをカスタマイズできます。
|
||||
これにより、ベースシステムを最小限に保ち、全ユーザーが不要な機能を継承することなく自分のインストールをカスタマイズできます。
|
||||
|
||||
## コミュニティ
|
||||
|
||||
質問やアイデアは?[Discordに参加](https://discord.gg/VDdww8qS42)してください。
|
||||
質問やアイデアがありますか?[Discordに参加](https://discord.gg/VDdww8qS42)してください。
|
||||
|
||||
## 変更履歴
|
||||
|
||||
破壊的変更と移行ノートについては[CHANGELOG.md](CHANGELOG.md)を参照してください。
|
||||
破壊的変更については[CHANGELOG.md](CHANGELOG.md)を、完全なリリース履歴はドキュメントサイトの[full release history](https://docs.nanoclaw.dev/changelog)を参照してください。
|
||||
|
||||
## ライセンス
|
||||
|
||||
|
||||
+78
-85
@@ -3,90 +3,87 @@
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
NanoClaw —— 您的专属 Claude 助手,在容器中安全运行。它轻巧易懂,并能根据您的个人需求灵活定制。
|
||||
一个将智能体安全运行在独立容器中的 AI 助手。轻量、易于理解,并可根据您的需求完全定制。
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://nanoclaw.dev">nanoclaw.dev</a> •
|
||||
<a href="https://docs.nanoclaw.dev">文档</a> •
|
||||
<a href="README.md">English</a> •
|
||||
<a href="README_ja.md">日本語</a> •
|
||||
<a href="https://discord.gg/VDdww8qS42"><img src="https://img.shields.io/discord/1470188214710046894?label=Discord&logo=discord&v=2" alt="Discord" valign="middle"></a> •
|
||||
<a href="repo-tokens"><img src="repo-tokens/badge.svg" alt="34.9k tokens, 17% of context window" valign="middle"></a>
|
||||
<a href="repo-tokens"><img src="repo-tokens/badge.svg" alt="repo tokens" valign="middle"></a>
|
||||
</p>
|
||||
通过 Claude Code,NanoClaw 可以动态重写自身代码,根据您的需求定制功能。
|
||||
|
||||
**新功能:** 首个支持 [Agent Swarms(智能体集群)](https://code.claude.com/docs/en/agent-teams) 的 AI 助手。可轻松组建智能体团队,在您的聊天中高效协作。
|
||||
---
|
||||
|
||||
## 我为什么创建这个项目
|
||||
## 我为什么创建 NanoClaw
|
||||
|
||||
[OpenClaw](https://github.com/openclaw/openclaw) 是一个令人印象深刻的项目,但我无法安心使用一个我不了解却能访问我个人隐私的软件。OpenClaw 有近 50 万行代码、53 个配置文件和 70+ 个依赖项。其安全性是应用级别的(通过白名单、配对码实现),而非操作系统级别的隔离。所有东西都在一个共享内存的 Node 进程中运行。
|
||||
[OpenClaw](https://github.com/openclaw/openclaw) 是一个令人印象深刻的项目,但我无法安心使用一个我不了解、却能访问我个人隐私的复杂软件。OpenClaw 有近 50 万行代码、53 个配置文件和 70+ 个依赖项。其安全性是应用级别的(白名单、配对码),而非真正的操作系统级隔离。所有东西都在一个共享内存的 Node 进程中运行。
|
||||
|
||||
NanoClaw 用一个您能快速理解的代码库,为您提供了同样的核心功能。只有一个进程,少数几个文件。智能体(Agent)运行在具有文件系统隔离的真实 Linux 容器中,而不是依赖于权限检查。
|
||||
NanoClaw 用一个您能轻松理解的代码库提供了同样的核心功能:一个进程,少数几个文件。Claude 智能体运行在具有文件系统隔离的独立 Linux 容器中,而不是仅靠权限检查。
|
||||
|
||||
## 快速开始
|
||||
|
||||
```bash
|
||||
git clone https://github.com/qwibitai/nanoclaw.git
|
||||
cd nanoclaw
|
||||
claude
|
||||
git clone https://github.com/qwibitai/nanoclaw.git nanoclaw-v2
|
||||
cd nanoclaw-v2
|
||||
bash nanoclaw.sh
|
||||
```
|
||||
|
||||
然后运行 `/setup`。Claude Code 会处理一切:依赖安装、身份验证、容器设置、服务配置。
|
||||
|
||||
> **注意:** 以 `/` 开头的命令(如 `/setup`、`/add-whatsapp`)是 [Claude Code 技能](https://code.claude.com/docs/en/skills)。请在 `claude` CLI 提示符中输入,而非在普通终端中。
|
||||
`nanoclaw.sh` 会把您从一台全新机器一直带到一个可以直接发消息的命名智能体。它会在缺失时安装 Node、pnpm 和 Docker,向 OneCLI 注册您的 Anthropic 凭据,构建智能体容器,并配对您的第一个渠道(Telegram、Discord、WhatsApp 或本地 CLI)。如果某一步失败,会自动调用 Claude Code 进行诊断并从中断处继续。
|
||||
|
||||
## 设计哲学
|
||||
|
||||
**小巧易懂:** 单一进程,少量源文件。无微服务、无消息队列、无复杂抽象层。让 Claude Code 引导您轻松上手。
|
||||
**小到可以理解。** 单一进程,少量源文件,无微服务。如果您想了解完整的 NanoClaw 代码库,直接让 Claude Code 给您讲一遍就行。
|
||||
|
||||
**通过隔离保障安全:** 智能体运行在 Linux 容器(在 macOS 上是 Apple Container,或 Docker)中。它们只能看到被明确挂载的内容。即便通过 Bash 访问也十分安全,因为所有命令都在容器内执行,不会直接操作您的宿主机。
|
||||
**通过隔离实现安全。** 智能体运行在 Linux 容器中,只能看到明确挂载的内容。Bash 访问是安全的,因为命令在容器内执行,而不是在您的宿主机上。
|
||||
|
||||
**为单一用户打造:** 这不是一个框架,是一个完全符合您个人需求的、可工作的软件。您可以 Fork 本项目,然后让 Claude Code 根据您的精确需求进行修改和适配。
|
||||
**为个人用户打造。** NanoClaw 不是一个单体框架,而是能精确匹配每个用户需求的软件。它被设计成量身定制的,而不是臃肿膨胀。您创建自己的 fork,让 Claude Code 按您的需求修改它。
|
||||
|
||||
**定制即代码修改:** 没有繁杂的配置文件。想要不同的行为?直接修改代码。代码库足够小,这样做是安全的。
|
||||
**定制 = 修改代码。** 没有配置膨胀。想要不同的行为?改代码。代码库小到改动是安全的。
|
||||
|
||||
**AI 原生:** 无安装向导(由 Claude Code 指导安装)。无需监控仪表盘,直接询问 Claude 即可了解系统状况。无调试工具(描述问题,Claude 会修复它)。
|
||||
**AI 原生,混合式设计。** 安装与上手流程走的是经过优化的脚本路径,快速且确定。当某一步需要判断(安装失败、引导决策、定制化)时,控制权会无缝地交给 Claude Code。安装之后也不提供监控仪表盘或调试 UI:您在聊天中描述问题,Claude Code 来处理。
|
||||
|
||||
**技能(Skills)优于功能(Features):** 贡献者不应该向代码库添加新功能(例如支持 Telegram)。相反,他们应该贡献像 `/add-telegram` 这样的 [Claude Code 技能](https://code.claude.com/docs/en/skills),这些技能可以改造您的 fork。最终,您得到的是只做您需要事情的整洁代码。
|
||||
**技能优于功能。** 主干只发布注册表和基础设施,不包含具体的渠道适配器或替代智能体提供者。各个渠道(Discord、Slack、Telegram、WhatsApp……)放在长期存在的 `channels` 分支上;替代提供者(OpenCode、Ollama)放在 `providers` 分支上。您运行 `/add-telegram`、`/add-opencode` 等,技能会把您所需要的模块精确地复制到您的 fork 里。不会出现您没要求的功能。
|
||||
|
||||
**最好的工具套件,最好的模型:** 本项目运行在 Claude Agent SDK 之上,这意味着您直接运行的就是 Claude Code。Claude Code 高度强大,其编码和问题解决能力使其能够修改和扩展 NanoClaw,为每个用户量身定制。
|
||||
**最强的 harness,最强的模型。** NanoClaw 通过 Anthropic 官方的 Claude Agent SDK 原生使用 Claude Code,所以您能用上最新的 Claude 模型以及 Claude Code 的完整工具集——包括修改和扩展自己的 NanoClaw fork 的能力。其他提供者是可插拔选项:`/add-codex` 对应 OpenAI 的 Codex(ChatGPT 订阅或 API key),`/add-opencode` 通过 OpenCode 接入 OpenRouter、Google、DeepSeek 等,`/add-ollama-provider` 用于本地开源权重模型。提供者可按智能体组单独配置。
|
||||
|
||||
## 功能支持
|
||||
|
||||
- **多渠道消息** - 通过 WhatsApp、Telegram、Discord、Slack 或 Gmail 与您的助手对话。使用 `/add-whatsapp` 或 `/add-telegram` 等技能添加渠道,可同时运行一个或多个。
|
||||
- **隔离的群组上下文** - 每个群组都拥有独立的 `CLAUDE.md` 记忆和隔离的文件系统。它们在各自的容器沙箱中运行,且仅挂载所需的文件系统。
|
||||
- **主频道** - 您的私有频道(self-chat),用于管理控制;其他所有群组都完全隔离
|
||||
- **计划任务** - 运行 Claude 的周期性作业,并可以给您回发消息
|
||||
- **网络访问** - 搜索和抓取网页内容
|
||||
- **容器隔离** - 智能体在 Apple Container (macOS) 或 Docker (macOS/Linux) 的沙箱中运行
|
||||
- **智能体集群(Agent Swarms)** - 启动多个专业智能体团队,协作完成复杂任务(首个支持此功能的个人 AI 助手)
|
||||
- **可选集成** - 通过技能添加 Gmail (`/add-gmail`) 等更多功能
|
||||
- **多渠道消息** — WhatsApp、Telegram、Discord、Slack、Microsoft Teams、iMessage、Matrix、Google Chat、Webex、Linear、GitHub、WeChat,以及通过 Resend 的邮件。按需通过 `/add-<channel>` 技能安装。可同时运行一个或多个。
|
||||
- **灵活的隔离模式** — 可为每个渠道配一个独立智能体以获得完全隐私,也可让一个智能体在多个渠道上共享、统一记忆但会话独立,或者把多个渠道合并到一个共享会话里,让一场对话横跨多个入口。通过 `/manage-channels` 按渠道选择。详见 [docs/isolation-model.md](docs/isolation-model.md)。
|
||||
- **每个智能体的独立工作区** — 每个智能体组都有自己的 `CLAUDE.md`、自己的记忆、自己的容器,以及您允许的挂载点。除非您明确接线,否则不会有东西越过边界。
|
||||
- **计划任务** — 运行 Claude 的周期性作业,可以给您回发消息。
|
||||
- **网络访问** — 搜索和抓取网页内容。
|
||||
- **容器隔离** — 智能体在 Docker(macOS/Linux/WSL2)中沙箱化运行,可选 [Docker Sandboxes](docs/docker-sandboxes.md) 的微虚拟机隔离,或在 macOS 上选用 Apple Container 作为原生运行时。
|
||||
- **凭据安全** — 智能体不持有原始 API key。出站请求经由 [OneCLI 的 Agent Vault](https://github.com/onecli/onecli),在请求时注入凭据,并按每个智能体执行策略和速率限制。
|
||||
|
||||
## 使用方法
|
||||
|
||||
使用触发词(默认为 `@Andy`)与您的助手对话:
|
||||
用触发词(默认为 `@Andy`)与您的助手对话:
|
||||
|
||||
```
|
||||
@Andy 每周一到周五早上9点,给我发一份销售渠道的概览(需要访问我的 Obsidian vault 文件夹)
|
||||
@Andy 每周五回顾过去一周的 git 历史,如果与 README 有出入,就更新它
|
||||
@Andy 每周一早上8点,从 Hacker News 和 TechCrunch 收集关于 AI 发展的资讯,然后发给我一份简报
|
||||
@Andy 每个工作日早上 9 点给我发一份销售渠道概览(可以访问我的 Obsidian vault 文件夹)
|
||||
@Andy 每周五回顾过去一周的 git 历史,如果与 README 有出入就更新它
|
||||
@Andy 每周一早上 8 点,从 Hacker News 和 TechCrunch 收集 AI 相关资讯,给我发一份简报
|
||||
```
|
||||
|
||||
在主频道(您的self-chat)中,可以管理群组和任务:
|
||||
在您拥有或管理的渠道里,还可以管理群组和任务:
|
||||
```
|
||||
@Andy 列出所有群组的计划任务
|
||||
@Andy 列出所有群组里的计划任务
|
||||
@Andy 暂停周一简报任务
|
||||
@Andy 加入"家庭聊天"群组
|
||||
```
|
||||
|
||||
## 定制
|
||||
|
||||
没有需要学习的配置文件。直接告诉 Claude Code 您想要什么:
|
||||
NanoClaw 不用配置文件。想改就直接告诉 Claude Code:
|
||||
|
||||
- "把触发词改成 @Bob"
|
||||
- "记住以后回答要更简短直接"
|
||||
- "当我说早上好的时候,加一个自定义的问候"
|
||||
- "每周存储一次对话摘要"
|
||||
- "以后回答请更简短、更直接"
|
||||
- "我说早上好的时候加一个自定义问候"
|
||||
- "每周保存一次会话摘要"
|
||||
|
||||
或者运行 `/customize` 进行引导式修改。
|
||||
|
||||
@@ -94,107 +91,103 @@ claude
|
||||
|
||||
## 贡献
|
||||
|
||||
**不要添加功能,而是添加技能。**
|
||||
**不要加功能,要加技能。**
|
||||
|
||||
如果您想添加 Telegram 支持,不要创建一个 PR 同时添加 Telegram 和 WhatsApp。而是贡献一个技能文件 (`.claude/skills/add-telegram/SKILL.md`),教 Claude Code 如何改造一个 NanoClaw 安装以使用 Telegram。
|
||||
如果您想添加新的渠道或智能体提供者,不要把它加到主干上。新的渠道适配器进入 `channels` 分支;新的智能体提供者进入 `providers` 分支。用户在自己的 fork 上运行 `/add-<name>` 技能,由技能把相关模块复制到标准路径、接好注册、固定依赖版本。
|
||||
|
||||
然后用户在自己的 fork 上运行 `/add-telegram`,就能得到只做他们需要事情的整洁代码,而不是一个试图支持所有用例的臃肿系统。
|
||||
这样主干始终保持为纯粹的注册表和基础设施,每个 fork 也都保持精简——用户只获得他们要求的渠道和提供者,其它什么也不会混进来。
|
||||
|
||||
### RFS (技能征集)
|
||||
### RFS(技能征集)
|
||||
|
||||
我们希望看到的技能:
|
||||
|
||||
**通信渠道**
|
||||
- `/add-signal` - 添加 Signal 作为渠道
|
||||
|
||||
**会话管理**
|
||||
- `/clear` - 添加一个 `/clear` 命令,用于压缩会话(在同一会话中总结上下文,同时保留关键信息)。这需要研究如何通过 Claude Agent SDK 以编程方式触发压缩。
|
||||
- `/add-signal` — 添加 Signal 作为渠道
|
||||
|
||||
## 系统要求
|
||||
|
||||
- macOS 或 Linux
|
||||
- Node.js 20+
|
||||
- [Claude Code](https://claude.ai/download)
|
||||
- [Apple Container](https://github.com/apple/container) (macOS) 或 [Docker](https://docker.com/products/docker-desktop) (macOS/Linux)
|
||||
- macOS 或 Linux(Windows 通过 WSL2)
|
||||
- Node.js 20+ 和 pnpm 10+(安装脚本会在缺失时自动安装)
|
||||
- [Docker Desktop](https://docker.com/products/docker-desktop)(macOS/Windows)或 Docker Engine(Linux)
|
||||
- [Claude Code](https://claude.ai/download),用于 `/customize`、`/debug`、安装过程中的错误恢复以及所有 `/add-<channel>` 技能
|
||||
|
||||
## 架构
|
||||
|
||||
```
|
||||
渠道 --> SQLite --> 轮询循环 --> 容器 (Claude Agent SDK) --> 响应
|
||||
消息应用 → 主机进程(路由器) → inbound.db → 容器(Bun、Claude Agent SDK) → outbound.db → 主机进程(投递) → 消息应用
|
||||
```
|
||||
|
||||
单一 Node.js 进程。渠道通过技能添加,启动时自注册 — 编排器连接具有凭据的渠道。智能体在具有文件系统隔离的 Linux 容器中执行。每个群组的消息队列带有并发控制。通过文件系统进行 IPC。
|
||||
单一 Node 主机编排每个会话的智能体容器。当一条消息到来时,主机按实体模型(用户 → 消息组 → 智能体组 → 会话)进行路由,写入该会话的 `inbound.db`,并唤醒容器。容器内部的 agent-runner 轮询 `inbound.db`,调用 Claude,并把响应写入 `outbound.db`。主机轮询 `outbound.db`,通过渠道适配器投递回去。
|
||||
|
||||
完整架构详情请见 [docs/SPEC.md](docs/SPEC.md)。
|
||||
每个会话两个 SQLite 文件,每个文件只有一个写入者——没有跨挂载的锁争用,没有 IPC,没有 stdin 管道。渠道和替代提供者在启动时自注册;主干提供注册表和 Chat SDK 桥接,而适配器本身在每个 fork 里通过技能安装。
|
||||
|
||||
完整架构说明见 [docs/architecture.md](docs/architecture.md);三级隔离模型见 [docs/isolation-model.md](docs/isolation-model.md)。
|
||||
|
||||
关键文件:
|
||||
- `src/index.ts` - 编排器:状态管理、消息循环、智能体调用
|
||||
- `src/channels/registry.ts` - 渠道注册表(启动时自注册)
|
||||
- `src/ipc.ts` - IPC 监听与任务处理
|
||||
- `src/router.ts` - 消息格式化与出站路由
|
||||
- `src/group-queue.ts` - 带全局并发限制的群组队列
|
||||
- `src/container-runner.ts` - 生成流式智能体容器
|
||||
- `src/task-scheduler.ts` - 运行计划任务
|
||||
- `src/db.ts` - SQLite 操作(消息、群组、会话、状态)
|
||||
- `groups/*/CLAUDE.md` - 各群组的记忆
|
||||
- `src/index.ts` — 入口:数据库初始化、渠道适配器、投递轮询、sweep
|
||||
- `src/router.ts` — 入站路由:消息组 → 智能体组 → 会话 → `inbound.db`
|
||||
- `src/delivery.ts` — 轮询 `outbound.db`,通过适配器投递,处理系统动作
|
||||
- `src/host-sweep.ts` — 60 秒 sweep:失效检测、到期消息唤醒、循环任务
|
||||
- `src/session-manager.ts` — 解析会话,打开 `inbound.db` / `outbound.db`
|
||||
- `src/container-runner.ts` — 为每个智能体组启动容器,OneCLI 凭据注入
|
||||
- `src/db/` — 中心数据库(用户、角色、智能体组、消息组、接线、迁移)
|
||||
- `src/channels/` — 渠道适配器基础设施(适配器通过 `/add-<channel>` 技能安装)
|
||||
- `src/providers/` — 主机侧提供者配置(`claude` 内置,其他通过技能安装)
|
||||
- `container/agent-runner/` — Bun 版 agent-runner:轮询循环、MCP 工具、提供者抽象
|
||||
- `groups/<folder>/` — 每个智能体组的文件系统(`CLAUDE.md`、技能、容器配置)
|
||||
|
||||
## FAQ
|
||||
|
||||
**为什么是 Docker?**
|
||||
**为什么用 Docker?**
|
||||
|
||||
Docker 提供跨平台支持(macOS 和 Linux)和成熟的生态系统。在 macOS 上,您可以选择通过运行 `/convert-to-apple-container` 切换到 Apple Container,以获得更轻量级的原生运行时体验。
|
||||
Docker 提供跨平台支持(macOS、Linux、Windows via WSL2)和成熟的生态。在 macOS 上,您可以选择通过 `/convert-to-apple-container` 切换到 Apple Container,以获得更轻量的原生运行时。如需更强隔离,[Docker Sandboxes](docs/docker-sandboxes.md) 会把每个容器放到一台微虚拟机里运行。
|
||||
|
||||
**我可以在 Linux 上运行吗?**
|
||||
**我可以在 Linux 或 Windows 上运行吗?**
|
||||
|
||||
可以。Docker 是默认的容器运行时,在 macOS 和 Linux 上都可以使用。只需运行 `/setup`。
|
||||
可以。Docker 是默认运行时,可在 macOS、Linux 以及 Windows(通过 WSL2)上工作。运行 `bash nanoclaw.sh` 就行。
|
||||
|
||||
**这个项目安全吗?**
|
||||
|
||||
智能体在容器中运行,而不是在应用级别的权限检查之后。它们只能访问被明确挂载的目录。您仍然应该审查您运行的代码,但这个代码库小到您真的可以做到。完整的安全模型请见 [docs/SECURITY.md](docs/SECURITY.md)。
|
||||
智能体运行在容器里,而不是躲在应用级权限检查之后。它们只能访问明确挂载的目录。凭据不会进入容器——出站 API 请求通过 [OneCLI 的 Agent Vault](https://github.com/onecli/onecli) 在代理层注入认证,并支持速率限制和访问策略。您仍然应该审查自己要运行的代码,但代码库小到您真的能做到。完整的安全模型见 [安全文档](https://docs.nanoclaw.dev/concepts/security)。
|
||||
|
||||
**为什么没有配置文件?**
|
||||
|
||||
我们不希望配置泛滥。每个用户都应该定制它,让代码完全符合他们的需求,而不是去配置一个通用的系统。如果您喜欢用配置文件,告诉 Claude 让它加上。
|
||||
我们不想让配置泛滥。每位用户都应该定制 NanoClaw,让代码精确地做他们想要的事,而不是去配置一个通用系统。如果您更喜欢有配置文件,可以让 Claude 给您加。
|
||||
|
||||
**我可以使用第三方或开源模型吗?**
|
||||
|
||||
可以。NanoClaw 支持任何 API 兼容的模型端点。在 `.env` 文件中设置以下环境变量:
|
||||
可以。推荐做法是 `/add-opencode`(通过 OpenCode 配置接入 OpenRouter、OpenAI、Google、DeepSeek 等)或 `/add-ollama-provider`(通过 Ollama 使用本地开源权重模型)。两者都可以按智能体组单独配置,所以同一套安装里不同的智能体可以运行在不同的后端上。
|
||||
|
||||
对于一次性实验,任何 Claude API 兼容的端点也可以通过 `.env` 使用:
|
||||
|
||||
```bash
|
||||
ANTHROPIC_BASE_URL=https://your-api-endpoint.com
|
||||
ANTHROPIC_AUTH_TOKEN=your-token-here
|
||||
```
|
||||
|
||||
这使您能够使用:
|
||||
- 通过 [Ollama](https://ollama.ai) 配合 API 代理运行的本地模型
|
||||
- 托管在 [Together AI](https://together.ai)、[Fireworks](https://fireworks.ai) 等平台上的开源模型
|
||||
- 兼容 Anthropic API 格式的自定义模型部署
|
||||
|
||||
注意:为获得最佳兼容性,模型需支持 Anthropic API 格式。
|
||||
|
||||
**我该如何调试问题?**
|
||||
|
||||
问 Claude Code。"为什么计划任务没有运行?" "最近的日志里有什么?" "为什么这条消息没有得到回应?" 这就是 AI 原生的方法。
|
||||
问 Claude Code。"为什么计划任务没运行?""最近的日志里有什么?""为什么这条消息没有得到回复?"这就是 NanoClaw 底层的 AI 原生方式。
|
||||
|
||||
**为什么我的安装不成功?**
|
||||
**为什么安装对我不成功?**
|
||||
|
||||
如果遇到问题,安装过程中 Claude 会尝试动态修复。如果问题仍然存在,运行 `claude`,然后运行 `/debug`。如果 Claude 发现一个可能影响其他用户的问题,请开一个 PR 来修改 setup SKILL.md。
|
||||
如果某一步失败,`nanoclaw.sh` 会把控制权交给 Claude Code 进行诊断并从中断处继续。如果还是没解决,运行 `claude`,然后 `/debug`。如果 Claude 发现一个可能影响其他用户的问题,请对相关的安装步骤或技能提 PR。
|
||||
|
||||
**什么样的代码更改会被接受?**
|
||||
**什么样的更改会被接受进代码库?**
|
||||
|
||||
安全修复、bug 修复,以及对基础配置的明确改进。仅此而已。
|
||||
进入基础配置的只会是:安全修复、bug 修复、明显的改进。仅此而已。
|
||||
|
||||
其他一切(新功能、操作系统兼容性、硬件支持、增强功能)都应该作为技能来贡献。
|
||||
其他一切(新能力、操作系统兼容、硬件支持、增强)都应作为技能贡献到 `channels` 或 `providers` 分支。
|
||||
|
||||
这使得基础系统保持最小化,并让每个用户可以定制他们的安装,而无需继承他们不想要的功能。
|
||||
这样基础系统保持最小化,每位用户都可以定制自己的安装,而不必继承他们不想要的功能。
|
||||
|
||||
## 社区
|
||||
|
||||
有任何疑问或建议?欢迎[加入 Discord 社区](https://discord.gg/VDdww8qS42)与我们交流。
|
||||
有问题或想法?欢迎[加入 Discord](https://discord.gg/VDdww8qS42)。
|
||||
|
||||
## 更新日志
|
||||
|
||||
破坏性变更和迁移说明请见 [CHANGELOG.md](CHANGELOG.md)。
|
||||
破坏性变更见 [CHANGELOG.md](CHANGELOG.md),完整发布历史见文档站的 [full release history](https://docs.nanoclaw.dev/changelog)。
|
||||
|
||||
## 许可证
|
||||
|
||||
|
||||
-175
@@ -1,175 +0,0 @@
|
||||
# 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/<name>/` on main | yes — imported by `src/modules/index.ts` | edit core imports (intentional friction) |
|
||||
| **Optional modules** | `src/modules/<name>/` on main (for now — see open q #7) | yes, via barrel import | delete files + barrel line + revert `MODULE-HOOK` edits |
|
||||
| **Channel adapters** | `src/channels/<name>.ts` on `channels` branch | no — cherry-pick via `/add-<name>` | delete files + barrel line |
|
||||
| **Providers** | on `providers` branch | no — cherry-pick via `/add-<provider>` | 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:<name>: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-<module>` 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 <pre-sync> | awk '{print $4}' | sort > /tmp/pre.txt
|
||||
git ls-tree -r <post-sync> | 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 -- <files>`. 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-<module>` 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/`.
|
||||
@@ -0,0 +1,21 @@
|
||||
You are a NanoClaw agent. Your name, destinations, and message-sending rules are provided in the runtime system prompt at the top of each turn.
|
||||
|
||||
## Communication
|
||||
|
||||
Be concise — every message costs the reader's attention. Prefer outcomes over play-by-play; when the work is done, the final message should be about the result, not a transcript of what you did.
|
||||
|
||||
## Workspace
|
||||
|
||||
Files you create are saved in `/workspace/agent/`. Use this for notes, research, or anything that should persist across turns in this group.
|
||||
|
||||
The file `CLAUDE.local.md` in your workspace is your per-group memory. Record things there that you'll want to remember in future sessions — user preferences, project context, recurring facts. Keep entries short and structured.
|
||||
|
||||
## Memory
|
||||
|
||||
When the user shares any substantive information with you, it must be stored somewhere you can retrieve it when relevant. If it's information that is pertinent to every single conversation turn it should be put into CLAUDE.local.md. Otherwise, create a system for storing the information depending on its type - e.g. create a file of people that the user mentions so you can keep track or a file of projects. For every file you create, add a concise reference in your CLAUDE.local.md so you'll be able to find it in future conversations.
|
||||
|
||||
A core part of your job and the main thing that defines how useful you are to the user is how well you do in creating these systems for organizing information. These are your systems that help you do your job well. Evolve them over time as needed.
|
||||
|
||||
## Conversation history
|
||||
|
||||
The `conversations/` folder in your workspace holds searchable transcripts of past sessions with this group. Use it to recall prior context when a request references something that happened before. For structured long-lived data, prefer dedicated files (`customers.md`, `preferences.md`, etc.); split any file over ~500 lines into a folder with an index.
|
||||
+34
-26
@@ -3,8 +3,12 @@
|
||||
# Runs Claude Agent SDK in isolated Linux VM with browser automation.
|
||||
#
|
||||
# Runtime split:
|
||||
# - agent-runner (our TypeScript code): Bun
|
||||
# - agent-runner (our TypeScript code): Bun, mounted RO at /app/src by host
|
||||
# - globally-installed Node CLIs (claude-code, agent-browser, vercel): pnpm + Node
|
||||
#
|
||||
# Source is never baked in — /app/src is provided by a shared read-only
|
||||
# bind mount at runtime (see src/container-runner.ts). Source-only changes
|
||||
# never require an image rebuild.
|
||||
|
||||
FROM node:22-slim
|
||||
|
||||
@@ -15,7 +19,7 @@ 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
|
||||
@@ -66,44 +70,48 @@ RUN curl -fsSL https://bun.sh/install | bash -s "bun-v${BUN_VERSION}" && \
|
||||
install -m 0755 /root/.bun/bin/bun /usr/local/bin/bun && \
|
||||
rm -rf /root/.bun
|
||||
|
||||
# ---- pnpm + global Node CLIs -------------------------------------------------
|
||||
ENV PNPM_HOME="/pnpm"
|
||||
ENV PATH="$PNPM_HOME:$PATH"
|
||||
RUN corepack enable
|
||||
|
||||
# agent-browser has a postinstall build script — pnpm skips these by default.
|
||||
# Allowlist it via .npmrc so the install doesn't silently produce a broken
|
||||
# package. Pinned versions so every rebuild is reproducible.
|
||||
RUN --mount=type=cache,target=/root/.cache/pnpm \
|
||||
echo "only-built-dependencies[]=agent-browser" > /root/.npmrc && \
|
||||
pnpm install -g \
|
||||
"@anthropic-ai/claude-code@${CLAUDE_CODE_VERSION}" \
|
||||
"agent-browser@${AGENT_BROWSER_VERSION}" \
|
||||
"vercel@${VERCEL_VERSION}"
|
||||
|
||||
# ---- agent-runner ------------------------------------------------------------
|
||||
# ---- agent-runner deps -------------------------------------------------------
|
||||
# Deps are cached independently of CLI versions. Source is NOT baked in —
|
||||
# it's provided by the shared RO mount at runtime.
|
||||
WORKDIR /app
|
||||
|
||||
# Copy manifest + lockfile first so the install layer caches independently of
|
||||
# source edits.
|
||||
COPY agent-runner/package.json agent-runner/bun.lock ./
|
||||
|
||||
RUN --mount=type=cache,target=/root/.bun/install/cache \
|
||||
bun install --frozen-lockfile
|
||||
|
||||
# Source. Bun runs TS directly — no tsc build step. The host remounts this
|
||||
# path at runtime via `src/container-runner.ts` so source edits on the host
|
||||
# take effect without rebuilding the image; the baked copy is the fallback.
|
||||
COPY agent-runner/ ./
|
||||
# ---- pnpm + global Node CLIs -------------------------------------------------
|
||||
# Most stable first, most frequently bumped last. Bumping claude-code
|
||||
# (the most common change) only invalidates one layer.
|
||||
#
|
||||
# only-built-dependencies gates pnpm's supply-chain policy:
|
||||
# - agent-browser has a postinstall build step.
|
||||
# - @anthropic-ai/claude-code's postinstall downloads the native Claude
|
||||
# binary (linux-arm64 variant on our image). Without the allowlist
|
||||
# the SDK fails at spawn time with "native binary not found".
|
||||
ENV PNPM_HOME="/pnpm"
|
||||
ENV PATH="$PNPM_HOME:$PATH"
|
||||
RUN corepack enable
|
||||
|
||||
RUN --mount=type=cache,target=/root/.cache/pnpm \
|
||||
echo "only-built-dependencies[]=agent-browser" > /root/.npmrc && \
|
||||
echo "only-built-dependencies[]=@anthropic-ai/claude-code" >> /root/.npmrc && \
|
||||
pnpm install -g "vercel@${VERCEL_VERSION}"
|
||||
|
||||
RUN --mount=type=cache,target=/root/.cache/pnpm \
|
||||
pnpm install -g "agent-browser@${AGENT_BROWSER_VERSION}"
|
||||
|
||||
RUN --mount=type=cache,target=/root/.cache/pnpm \
|
||||
pnpm install -g "@anthropic-ai/claude-code@${CLAUDE_CODE_VERSION}"
|
||||
|
||||
# ---- Entrypoint --------------------------------------------------------------
|
||||
COPY entrypoint.sh /app/entrypoint.sh
|
||||
RUN chmod +x /app/entrypoint.sh
|
||||
|
||||
# ---- Workspace + permissions -------------------------------------------------
|
||||
RUN mkdir -p /workspace/group /workspace/global /workspace/extra && \
|
||||
RUN mkdir -p /workspace/group /workspace/extra && \
|
||||
chown -R node:node /workspace && \
|
||||
chmod 755 /home/node
|
||||
chmod 777 /home/node
|
||||
|
||||
USER node
|
||||
WORKDIR /workspace/group
|
||||
|
||||
@@ -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=="],
|
||||
|
||||
@@ -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"
|
||||
|
||||
@@ -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 "<prompt>" # simple string mode
|
||||
* bun run scripts/sdk-signal-probe.ts --stream "<prompt>" # streaming-input mode
|
||||
* bun run scripts/sdk-signal-probe.ts --stream "<p>" \
|
||||
* --push "5000:<text>" --push "15000:<text>" --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] "<prompt>" [--push MS:<text>]... [--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<any> => {
|
||||
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<string, unknown[]> = {};
|
||||
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) });
|
||||
}
|
||||
@@ -0,0 +1,55 @@
|
||||
/**
|
||||
* Runner config — reads /workspace/agent/container.json at startup.
|
||||
*
|
||||
* This file is mounted read-only inside the container. The host writes it;
|
||||
* the runner only reads. All NanoClaw-specific configuration lives here
|
||||
* instead of environment variables.
|
||||
*/
|
||||
import fs from 'fs';
|
||||
|
||||
const CONFIG_PATH = '/workspace/agent/container.json';
|
||||
|
||||
export interface RunnerConfig {
|
||||
provider: string;
|
||||
assistantName: string;
|
||||
groupName: string;
|
||||
agentGroupId: string;
|
||||
maxMessagesPerPrompt: number;
|
||||
mcpServers: Record<string, { command: string; args: string[]; env: Record<string, string> }>;
|
||||
}
|
||||
|
||||
const DEFAULT_MAX_MESSAGES = 10;
|
||||
|
||||
let _config: RunnerConfig | null = null;
|
||||
|
||||
/**
|
||||
* Load config from container.json. Called once at startup.
|
||||
* Falls back to sensible defaults for any missing field.
|
||||
*/
|
||||
export function loadConfig(): RunnerConfig {
|
||||
if (_config) return _config;
|
||||
|
||||
let raw: Record<string, unknown> = {};
|
||||
try {
|
||||
raw = JSON.parse(fs.readFileSync(CONFIG_PATH, 'utf8'));
|
||||
} catch {
|
||||
console.error(`[config] Failed to read ${CONFIG_PATH}, using defaults`);
|
||||
}
|
||||
|
||||
_config = {
|
||||
provider: (raw.provider as string) || 'claude',
|
||||
assistantName: (raw.assistantName as string) || '',
|
||||
groupName: (raw.groupName as string) || '',
|
||||
agentGroupId: (raw.agentGroupId as string) || '',
|
||||
maxMessagesPerPrompt: (raw.maxMessagesPerPrompt as number) || DEFAULT_MAX_MESSAGES,
|
||||
mcpServers: (raw.mcpServers as RunnerConfig['mcpServers']) || {},
|
||||
};
|
||||
|
||||
return _config;
|
||||
}
|
||||
|
||||
/** Get the loaded config. Throws if loadConfig() hasn't been called. */
|
||||
export function getConfig(): RunnerConfig {
|
||||
if (!_config) throw new Error('Config not loaded — call loadConfig() first');
|
||||
return _config;
|
||||
}
|
||||
@@ -31,8 +31,7 @@ let _heartbeatPath: string = DEFAULT_HEARTBEAT_PATH;
|
||||
/** Inbound DB — container opens read-only (host is the sole writer). */
|
||||
export function getInboundDb(): Database {
|
||||
if (!_inbound) {
|
||||
const dbPath = process.env.SESSION_INBOUND_DB_PATH || DEFAULT_INBOUND_PATH;
|
||||
_inbound = new Database(dbPath, { readonly: true });
|
||||
_inbound = new Database(DEFAULT_INBOUND_PATH, { readonly: true });
|
||||
_inbound.exec('PRAGMA busy_timeout = 5000');
|
||||
}
|
||||
return _inbound;
|
||||
@@ -41,8 +40,7 @@ export function getInboundDb(): Database {
|
||||
/** Outbound DB — container owns this file (sole writer). */
|
||||
export function getOutboundDb(): Database {
|
||||
if (!_outbound) {
|
||||
const dbPath = process.env.SESSION_OUTBOUND_DB_PATH || DEFAULT_OUTBOUND_PATH;
|
||||
_outbound = new Database(dbPath);
|
||||
_outbound = new Database(DEFAULT_OUTBOUND_PATH);
|
||||
_outbound.exec('PRAGMA journal_mode = DELETE');
|
||||
_outbound.exec('PRAGMA busy_timeout = 5000');
|
||||
_outbound.exec('PRAGMA foreign_keys = ON');
|
||||
@@ -64,17 +62,65 @@ 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.
|
||||
* A file touch is cheaper and avoids cross-boundary DB write contention.
|
||||
*/
|
||||
export function touchHeartbeat(): void {
|
||||
const p = process.env.SESSION_HEARTBEAT_PATH || _heartbeatPath;
|
||||
const p = _heartbeatPath;
|
||||
const now = new Date();
|
||||
try {
|
||||
fs.utimesSync(p, now, now);
|
||||
@@ -109,7 +155,9 @@ 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,
|
||||
@@ -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 };
|
||||
|
||||
@@ -7,6 +7,7 @@
|
||||
* The container never writes to inbound.db — all status tracking goes through
|
||||
* processing_ack. The host reads processing_ack to sync message lifecycle.
|
||||
*/
|
||||
import { getConfig } from '../config.js';
|
||||
import { getInboundDb, getOutboundDb } from './connection.js';
|
||||
|
||||
export interface MessageInRow {
|
||||
@@ -18,16 +19,35 @@ 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. Read from
|
||||
// container.json; falls back to 10.
|
||||
function getMaxMessagesPerPrompt(): number {
|
||||
try {
|
||||
return getConfig().maxMessagesPerPrompt;
|
||||
} catch {
|
||||
// Config not loaded yet (e.g. test harness) — use default
|
||||
return 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 +58,10 @@ 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(getMaxMessagesPerPrompt()) as MessageInRow[];
|
||||
|
||||
if (pending.length === 0) return [];
|
||||
|
||||
@@ -51,7 +72,9 @@ 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. */
|
||||
|
||||
@@ -0,0 +1,100 @@
|
||||
import { beforeEach, describe, expect, test } from 'bun:test';
|
||||
|
||||
import { getOutboundDb, initTestSessionDb } from './connection.js';
|
||||
import {
|
||||
clearContinuation,
|
||||
getContinuation,
|
||||
migrateLegacyContinuation,
|
||||
setContinuation,
|
||||
} from './session-state.js';
|
||||
|
||||
beforeEach(() => {
|
||||
initTestSessionDb();
|
||||
});
|
||||
|
||||
function seedLegacy(value: string): void {
|
||||
getOutboundDb()
|
||||
.prepare('INSERT INTO session_state (key, value, updated_at) VALUES (?, ?, ?)')
|
||||
.run('sdk_session_id', value, new Date().toISOString());
|
||||
}
|
||||
|
||||
describe('session-state — per-provider continuations', () => {
|
||||
test('set/get round-trip, case-insensitive provider key', () => {
|
||||
setContinuation('claude', 'claude-conv-1');
|
||||
expect(getContinuation('claude')).toBe('claude-conv-1');
|
||||
expect(getContinuation('Claude')).toBe('claude-conv-1');
|
||||
expect(getContinuation('CLAUDE')).toBe('claude-conv-1');
|
||||
});
|
||||
|
||||
test('providers are isolated — switching reads the right slot', () => {
|
||||
setContinuation('claude', 'claude-conv-1');
|
||||
setContinuation('codex', 'codex-thread-xyz');
|
||||
|
||||
expect(getContinuation('claude')).toBe('claude-conv-1');
|
||||
expect(getContinuation('codex')).toBe('codex-thread-xyz');
|
||||
});
|
||||
|
||||
test('clearContinuation only affects the specified provider', () => {
|
||||
setContinuation('claude', 'keep-me');
|
||||
setContinuation('codex', 'drop-me');
|
||||
|
||||
clearContinuation('codex');
|
||||
|
||||
expect(getContinuation('claude')).toBe('keep-me');
|
||||
expect(getContinuation('codex')).toBeUndefined();
|
||||
});
|
||||
|
||||
test('unknown provider returns undefined', () => {
|
||||
expect(getContinuation('never-used')).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
describe('session-state — legacy migration', () => {
|
||||
test('adopts legacy value into current provider when current is empty', () => {
|
||||
seedLegacy('old-session-id');
|
||||
|
||||
const adopted = migrateLegacyContinuation('claude');
|
||||
|
||||
expect(adopted).toBe('old-session-id');
|
||||
expect(getContinuation('claude')).toBe('old-session-id');
|
||||
});
|
||||
|
||||
test('always deletes legacy row regardless of migration outcome', () => {
|
||||
seedLegacy('old-session-id');
|
||||
setContinuation('claude', 'existing');
|
||||
|
||||
migrateLegacyContinuation('claude');
|
||||
|
||||
// After migration the legacy key must be gone, whether or not it was adopted.
|
||||
// A subsequent migration for a different provider must not see it.
|
||||
const resultAfterSecondCall = migrateLegacyContinuation('codex');
|
||||
expect(resultAfterSecondCall).toBeUndefined();
|
||||
});
|
||||
|
||||
test('prefers existing current-provider slot over legacy', () => {
|
||||
seedLegacy('legacy-value');
|
||||
setContinuation('claude', 'claude-value');
|
||||
|
||||
const result = migrateLegacyContinuation('claude');
|
||||
|
||||
expect(result).toBe('claude-value');
|
||||
expect(getContinuation('claude')).toBe('claude-value');
|
||||
});
|
||||
|
||||
test('no legacy row — returns current provider value (possibly undefined)', () => {
|
||||
expect(migrateLegacyContinuation('claude')).toBeUndefined();
|
||||
|
||||
setContinuation('codex', 'codex-value');
|
||||
expect(migrateLegacyContinuation('codex')).toBe('codex-value');
|
||||
});
|
||||
|
||||
test('migration is idempotent on a second call (legacy already gone)', () => {
|
||||
seedLegacy('once');
|
||||
|
||||
const first = migrateLegacyContinuation('claude');
|
||||
expect(first).toBe('once');
|
||||
|
||||
const second = migrateLegacyContinuation('claude');
|
||||
expect(second).toBe('once');
|
||||
});
|
||||
});
|
||||
@@ -2,12 +2,20 @@
|
||||
* Persistent key/value state for the container. Lives in outbound.db
|
||||
* (container-owned, already scoped per channel/thread).
|
||||
*
|
||||
* Primary use: remember the SDK session ID so the agent's conversation
|
||||
* resumes across container restarts. Cleared by /clear.
|
||||
* Primary use: remember each provider's opaque continuation id so the
|
||||
* agent's conversation resumes across container restarts. Keyed per
|
||||
* provider because continuations are provider-private — a Claude
|
||||
* conversation id means nothing to Codex and vice versa. Switching
|
||||
* providers is therefore lossless: each provider's last thread stays
|
||||
* on file and resumes cleanly if the user flips back.
|
||||
*/
|
||||
import { getOutboundDb } from './connection.js';
|
||||
|
||||
const SDK_SESSION_KEY = 'sdk_session_id';
|
||||
const LEGACY_KEY = 'sdk_session_id';
|
||||
|
||||
function continuationKey(providerName: string): string {
|
||||
return `continuation:${providerName.toLowerCase()}`;
|
||||
}
|
||||
|
||||
function getValue(key: string): string | undefined {
|
||||
const row = getOutboundDb()
|
||||
@@ -18,9 +26,7 @@ function getValue(key: string): string | undefined {
|
||||
|
||||
function setValue(key: string, value: string): void {
|
||||
getOutboundDb()
|
||||
.prepare(
|
||||
'INSERT OR REPLACE INTO session_state (key, value, updated_at) VALUES (?, ?, ?)',
|
||||
)
|
||||
.prepare('INSERT OR REPLACE INTO session_state (key, value, updated_at) VALUES (?, ?, ?)')
|
||||
.run(key, value, new Date().toISOString());
|
||||
}
|
||||
|
||||
@@ -28,14 +34,46 @@ function deleteValue(key: string): void {
|
||||
getOutboundDb().prepare('DELETE FROM session_state WHERE key = ?').run(key);
|
||||
}
|
||||
|
||||
export function getStoredSessionId(): string | undefined {
|
||||
return getValue(SDK_SESSION_KEY);
|
||||
/**
|
||||
* One-time migration of the pre-per-provider continuation row.
|
||||
*
|
||||
* Before this was keyed per provider, continuations lived under the
|
||||
* single key `sdk_session_id`. On container start, if that legacy row
|
||||
* exists and the current provider has no continuation of its own, adopt
|
||||
* the legacy value into the current provider's slot (best-guess — the
|
||||
* legacy row was written by whatever provider ran last). The legacy row
|
||||
* is always deleted so future provider flips never re-read a stale id
|
||||
* through the wrong lens.
|
||||
*
|
||||
* Returns the continuation the caller should use at startup (either the
|
||||
* current provider's existing value, the adopted legacy value, or
|
||||
* undefined).
|
||||
*/
|
||||
export function migrateLegacyContinuation(providerName: string): string | undefined {
|
||||
const legacy = getValue(LEGACY_KEY);
|
||||
const currentKey = continuationKey(providerName);
|
||||
const current = getValue(currentKey);
|
||||
|
||||
if (legacy === undefined) return current;
|
||||
|
||||
// Always drop the legacy row so no future provider reads it.
|
||||
deleteValue(LEGACY_KEY);
|
||||
|
||||
// Prefer the current provider's own slot if one already exists.
|
||||
if (current !== undefined) return current;
|
||||
|
||||
setValue(currentKey, legacy);
|
||||
return legacy;
|
||||
}
|
||||
|
||||
export function setStoredSessionId(sessionId: string): void {
|
||||
setValue(SDK_SESSION_KEY, sessionId);
|
||||
export function getContinuation(providerName: string): string | undefined {
|
||||
return getValue(continuationKey(providerName));
|
||||
}
|
||||
|
||||
export function clearStoredSessionId(): void {
|
||||
deleteValue(SDK_SESSION_KEY);
|
||||
export function setContinuation(providerName: string, id: string): void {
|
||||
setValue(continuationKey(providerName), id);
|
||||
}
|
||||
|
||||
export function clearContinuation(providerName: string): void {
|
||||
deleteValue(continuationKey(providerName));
|
||||
}
|
||||
|
||||
@@ -72,8 +72,26 @@ export function findByRouting(
|
||||
return row ? rowToEntry(row) : undefined;
|
||||
}
|
||||
|
||||
/** Generate the system-prompt addendum describing destinations and syntax. */
|
||||
export function buildSystemPromptAddendum(): string {
|
||||
/**
|
||||
* Generate the system-prompt addendum: agent identity + destination map.
|
||||
*
|
||||
* Identity is injected here (not in the shared CLAUDE.md) because it's
|
||||
* per-agent-group and changes when the operator renames an agent, while
|
||||
* the shared base is identical across all agents.
|
||||
*/
|
||||
export function buildSystemPromptAddendum(assistantName?: string): string {
|
||||
const sections: string[] = [];
|
||||
|
||||
if (assistantName) {
|
||||
sections.push(['# You are ' + assistantName, '', `Your name is **${assistantName}**. Use it when the channel asks who you are, when introducing yourself, and when signing any message that explicitly calls for a signature.`].join('\n'));
|
||||
}
|
||||
|
||||
sections.push(buildDestinationsSection());
|
||||
|
||||
return sections.join('\n\n');
|
||||
}
|
||||
|
||||
function buildDestinationsSection(): string {
|
||||
const all = getAllDestinations();
|
||||
|
||||
if (all.length === 0) {
|
||||
|
||||
@@ -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 <context timezone="..."/> to formatted output', () => {
|
||||
insertMessage('m1', 'chat', { sender: 'Alice', text: 'hello' });
|
||||
const result = formatMessages(getPendingMessages());
|
||||
expect(result).toContain(`<context timezone="${TIMEZONE}"`);
|
||||
});
|
||||
|
||||
it('includes the header even when the message list is empty', () => {
|
||||
const result = formatMessages([]);
|
||||
expect(result).toContain(`<context timezone="${TIMEZONE}"`);
|
||||
});
|
||||
|
||||
it('header comes before the <messages> block', () => {
|
||||
insertMessage('m1', 'chat', { sender: 'Alice', text: 'one' });
|
||||
insertMessage('m2', 'chat', { sender: 'Bob', text: 'two' });
|
||||
const result = formatMessages(getPendingMessages());
|
||||
const ctxIdx = result.indexOf('<context');
|
||||
const msgsIdx = result.indexOf('<messages>');
|
||||
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('<quoted_message from="Bob">Are you coming tonight?</quoted_message>');
|
||||
expect(result).toContain('Yes, on my way!</message>');
|
||||
});
|
||||
|
||||
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: '<script>alert("xss")</script>' },
|
||||
});
|
||||
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 <Co>',
|
||||
text: '<script>alert("xss")</script>',
|
||||
});
|
||||
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 <internal>secret</internal> world')).toBe('hello world');
|
||||
});
|
||||
|
||||
it('strips multi-line internal tags', () => {
|
||||
expect(stripInternalTags('hello <internal>\nsecret\nstuff\n</internal> world')).toBe(
|
||||
'hello world',
|
||||
);
|
||||
});
|
||||
|
||||
it('strips multiple internal tag blocks', () => {
|
||||
expect(stripInternalTags('<internal>a</internal>hello<internal>b</internal>')).toBe('hello');
|
||||
});
|
||||
|
||||
it('returns empty string when input is only internal tags', () => {
|
||||
expect(stripInternalTags('<internal>only this</internal>')).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('<internal>thinking</internal>The answer is 42')).toBe(
|
||||
'The answer is 42',
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -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 '/'.
|
||||
@@ -11,7 +12,7 @@ import type { MessageInRow } from './db/messages-in.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;
|
||||
@@ -54,6 +55,17 @@ export function categorizeMessage(msg: MessageInRow): CommandInfo {
|
||||
return { category: 'passthrough', command, text, senderId };
|
||||
}
|
||||
|
||||
/**
|
||||
* Narrow check for /clear — the only command the runner handles directly.
|
||||
* All other command gating (filtered, admin) is done by the host router
|
||||
* before messages reach the container.
|
||||
*/
|
||||
export function isClearCommand(msg: MessageInRow): boolean {
|
||||
const content = parseContent(msg.content);
|
||||
const text = (content.text || '').trim();
|
||||
return text.toLowerCase().startsWith('/clear');
|
||||
}
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
function extractSenderId(msg: MessageInRow, content: any): string | null {
|
||||
const raw: string | null = content?.senderId || content?.author?.userId || null;
|
||||
@@ -92,10 +104,19 @@ export function extractRouting(messages: MessageInRow[]): RoutingContext {
|
||||
|
||||
/**
|
||||
* Format a batch of messages_in rows into a prompt string.
|
||||
*
|
||||
* Prepends a `<context timezone="<IANA>" />` 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 = `<context timezone="${escapeXml(TIMEZONE)}" />\n`;
|
||||
if (messages.length === 0) return header;
|
||||
|
||||
// Group by kind
|
||||
const chatMessages = messages.filter((m) => m.kind === 'chat' || m.kind === 'chat-sdk');
|
||||
@@ -118,7 +139,7 @@ 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 +158,10 @@ 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 +176,7 @@ function formatSingleChat(msg: MessageInRow): string {
|
||||
? ` from="unknown:${escapeXml(msg.channel_type || '')}:${escapeXml(msg.platform_id || '')}"`
|
||||
: '';
|
||||
|
||||
return `<message${idAttr}${fromAttr} sender="${escapeXml(sender)}" time="${time}">${replyPrefix}${escapeXml(text)}${attachmentsSuffix}</message>`;
|
||||
return `<message${idAttr}${fromAttr} sender="${escapeXml(sender)}" time="${escapeXml(time)}"${replyAttr}>${replyPrefix}${escapeXml(text)}${attachmentsSuffix}</message>`;
|
||||
}
|
||||
|
||||
function formatTaskMessage(msg: MessageInRow): string {
|
||||
@@ -179,13 +201,22 @@ function formatSystemMessage(msg: MessageInRow): string {
|
||||
return `[SYSTEM RESPONSE]\n\nAction: ${content.action || 'unknown'}\nStatus: ${content.status || 'unknown'}\nResult: ${JSON.stringify(content.result || null)}`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Render the quoted original inside the <message> body.
|
||||
*
|
||||
* Matches v1 format (src/v1/router.ts:10-18): `<quoted_message from="X">Y</quoted_message>`.
|
||||
* Requires BOTH sender and text — if only id is present the reply_to attribute
|
||||
* on the parent <message> carries the link without an inline preview.
|
||||
*
|
||||
* No truncation here (v1 didn't truncate).
|
||||
*/
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
function formatReplyContext(replyTo: any): string {
|
||||
if (!replyTo) return '';
|
||||
const sender = replyTo.sender || 'Unknown';
|
||||
const text = replyTo.text || '';
|
||||
const preview = text.length > 100 ? text.slice(0, 100) + '…' : text;
|
||||
return `\n<reply-to sender="${escapeXml(sender)}">${escapeXml(preview)}</reply-to>\n`;
|
||||
const sender = replyTo.sender;
|
||||
const text = replyTo.text;
|
||||
if (!sender || !text) return '';
|
||||
return `\n <quoted_message from="${escapeXml(sender)}">${escapeXml(text)}</quoted_message>\n`;
|
||||
}
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
@@ -213,15 +244,15 @@ function parseContent(json: string): any {
|
||||
}
|
||||
}
|
||||
|
||||
function formatTime(timestamp: string): string {
|
||||
try {
|
||||
const d = new Date(timestamp);
|
||||
return `${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, '>').replace(/"/g, '"');
|
||||
}
|
||||
|
||||
/**
|
||||
* Strip `<internal>...</internal>` 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(/<internal>[\s\S]*?<\/internal>/g, '').trim();
|
||||
}
|
||||
|
||||
@@ -4,14 +4,8 @@
|
||||
* Runs inside a container. All IO goes through the session DB.
|
||||
* No stdin, no stdout markers, no IPC files.
|
||||
*
|
||||
* Config:
|
||||
* - SESSION_INBOUND_DB_PATH: path to host-owned inbound DB (default: /workspace/inbound.db)
|
||||
* - SESSION_OUTBOUND_DB_PATH: path to container-owned outbound DB (default: /workspace/outbound.db)
|
||||
* - SESSION_HEARTBEAT_PATH: heartbeat file path (default: /workspace/.heartbeat)
|
||||
* - AGENT_PROVIDER: any registered provider name (default: claude). The
|
||||
* set of registered providers is whatever `providers/index.ts` imports.
|
||||
* - NANOCLAW_ASSISTANT_NAME: assistant name for transcript archiving
|
||||
* - NANOCLAW_ADMIN_USER_IDS: comma-separated user IDs allowed to run admin commands
|
||||
* Config is read from /workspace/agent/container.json (mounted RO).
|
||||
* Only TZ and OneCLI networking vars come from env.
|
||||
*
|
||||
* Mount structure:
|
||||
* /workspace/
|
||||
@@ -19,14 +13,19 @@
|
||||
* outbound.db ← container-owned session DB
|
||||
* .heartbeat ← container touches for liveness detection
|
||||
* outbox/ ← outbound files
|
||||
* agent/ ← agent group folder (CLAUDE.md, skills, working files)
|
||||
* .claude/ ← Claude SDK session data
|
||||
* agent/ ← agent group folder (CLAUDE.md, container.json, working files)
|
||||
* container.json ← per-group config (RO nested mount)
|
||||
* global/ ← shared global memory (RO)
|
||||
* /app/src/ ← shared agent-runner source (RO)
|
||||
* /app/skills/ ← shared skills (RO)
|
||||
* /home/node/.claude/ ← Claude SDK state + skill symlinks (RW)
|
||||
*/
|
||||
|
||||
import fs from 'fs';
|
||||
import path from 'path';
|
||||
import { fileURLToPath } from 'url';
|
||||
|
||||
import { loadConfig } from './config.js';
|
||||
import { buildSystemPromptAddendum } from './destinations.js';
|
||||
// Providers barrel — each enabled provider self-registers on import.
|
||||
// Provider skills append imports to providers/index.ts.
|
||||
@@ -41,22 +40,18 @@ function log(msg: string): void {
|
||||
const CWD = '/workspace/agent';
|
||||
|
||||
async function main(): Promise<void> {
|
||||
const providerName = (process.env.AGENT_PROVIDER || 'claude').toLowerCase() as ProviderName;
|
||||
const assistantName = process.env.NANOCLAW_ASSISTANT_NAME;
|
||||
const adminUserIds = new Set(
|
||||
(process.env.NANOCLAW_ADMIN_USER_IDS || '')
|
||||
.split(',')
|
||||
.map((s) => s.trim())
|
||||
.filter(Boolean),
|
||||
);
|
||||
const config = loadConfig();
|
||||
const providerName = config.provider.toLowerCase() as ProviderName;
|
||||
|
||||
log(`Starting v2 agent-runner (provider: ${providerName})`);
|
||||
|
||||
// Destinations addendum is the only runtime-generated context we inject.
|
||||
// Global CLAUDE.md is loaded by Claude Code from /workspace/agent/CLAUDE.md
|
||||
// (which imports /workspace/global/CLAUDE.md via @-syntax) — no need to
|
||||
// read it manually anymore.
|
||||
const instructions = buildSystemPromptAddendum();
|
||||
// Runtime-generated system-prompt addendum: agent identity (name) plus
|
||||
// the live destinations map. Everything else (capabilities, per-module
|
||||
// instructions, per-channel formatting) is loaded by Claude Code from
|
||||
// /workspace/agent/CLAUDE.md — the composed entry imports the shared
|
||||
// base (/app/CLAUDE.md) and each enabled module's fragment. Per-group
|
||||
// memory lives in /workspace/agent/CLAUDE.local.md (auto-loaded).
|
||||
const instructions = buildSystemPromptAddendum(config.assistantName || undefined);
|
||||
|
||||
// Discover additional directories mounted at /workspace/extra/*
|
||||
const additionalDirectories: string[] = [];
|
||||
@@ -77,34 +72,22 @@ async function main(): Promise<void> {
|
||||
const __dirname = path.dirname(fileURLToPath(import.meta.url));
|
||||
const mcpServerPath = path.join(__dirname, 'mcp-tools', 'index.ts');
|
||||
|
||||
// Build MCP servers config: nanoclaw built-in + any additional from host
|
||||
// Build MCP servers config: nanoclaw built-in + any from container.json
|
||||
const mcpServers: Record<string, { command: string; args: string[]; env: Record<string, string> }> = {
|
||||
nanoclaw: {
|
||||
command: 'bun',
|
||||
args: ['run', mcpServerPath],
|
||||
env: {
|
||||
SESSION_INBOUND_DB_PATH: process.env.SESSION_INBOUND_DB_PATH || '/workspace/inbound.db',
|
||||
SESSION_OUTBOUND_DB_PATH: process.env.SESSION_OUTBOUND_DB_PATH || '/workspace/outbound.db',
|
||||
SESSION_HEARTBEAT_PATH: process.env.SESSION_HEARTBEAT_PATH || '/workspace/.heartbeat',
|
||||
},
|
||||
env: {},
|
||||
},
|
||||
};
|
||||
|
||||
// Merge additional MCP servers from host configuration
|
||||
if (process.env.NANOCLAW_MCP_SERVERS) {
|
||||
try {
|
||||
const additional = JSON.parse(process.env.NANOCLAW_MCP_SERVERS) as Record<string, { command: string; args: string[]; env: Record<string, string> }>;
|
||||
for (const [name, config] of Object.entries(additional)) {
|
||||
mcpServers[name] = config;
|
||||
log(`Additional MCP server: ${name} (${config.command})`);
|
||||
}
|
||||
} catch (e) {
|
||||
log(`Failed to parse NANOCLAW_MCP_SERVERS: ${e}`);
|
||||
}
|
||||
for (const [name, serverConfig] of Object.entries(config.mcpServers)) {
|
||||
mcpServers[name] = serverConfig;
|
||||
log(`Additional MCP server: ${name} (${serverConfig.command})`);
|
||||
}
|
||||
|
||||
const provider = createProvider(providerName, {
|
||||
assistantName,
|
||||
assistantName: config.assistantName || undefined,
|
||||
mcpServers,
|
||||
env: { ...process.env },
|
||||
additionalDirectories: additionalDirectories.length > 0 ? additionalDirectories : undefined,
|
||||
@@ -112,9 +95,9 @@ async function main(): Promise<void> {
|
||||
|
||||
await runPollLoop({
|
||||
provider,
|
||||
providerName,
|
||||
cwd: CWD,
|
||||
systemContext: { instructions },
|
||||
adminUserIds,
|
||||
});
|
||||
}
|
||||
|
||||
|
||||
@@ -98,6 +98,7 @@ async function runPollLoopWithTimeout(provider: MockProvider, signal: AbortSigna
|
||||
return Promise.race([
|
||||
runPollLoop({
|
||||
provider,
|
||||
providerName: 'mock',
|
||||
cwd: '/tmp',
|
||||
}),
|
||||
new Promise<void>((_, reject) => {
|
||||
|
||||
@@ -0,0 +1,26 @@
|
||||
## Companion and collaborator agents (`create_agent`)
|
||||
|
||||
`mcp__nanoclaw__create_agent({ name, instructions })` spins up a new long-lived agent and wires it as a destination — bidirectional, so you can send it tasks and it can message you back.
|
||||
|
||||
### How it works
|
||||
|
||||
- Creates a new agent with its own container, workspace, and session. Your `instructions` string seeds the agent's `CLAUDE.local.md` — its starting role and personality.
|
||||
- The agent's `name` becomes a destination on both sides: you address it via `send_message({ to: "<name>", ... })`, and its replies arrive as inbound messages with `from="<name>"`.
|
||||
- Each agent has its own persistent workspace under `groups/<folder>/` — memory, conversation history, and notes all survive across sessions. This is a full standalone agent, not a stateless sub-query.
|
||||
- **Fire-and-forget:** the call returns immediately without waiting for the agent to confirm it's ready. Messages you send will queue until it's up.
|
||||
|
||||
### When to use
|
||||
|
||||
- **Companions** — a long-running presence that accumulates context over time: a `Researcher` tracking an ongoing inquiry, a `Calendar` agent managing scheduling, an assistant that knows your preferences and history.
|
||||
- **Collaborators** — a parallel specialist that works independently and reports back: a `Builder` handling code edits while you stay in conversation, a `Reviewer` running checks in the background.
|
||||
|
||||
The right frame is: does this agent need its own memory and context that builds over time, or does it need to work independently without blocking your turn? Either is a good reason to spawn one.
|
||||
|
||||
### When NOT to use
|
||||
|
||||
- **One-off lookups or short tasks** — use the SDK `Agent` tool instead. It's stateless, spins up and completes in one shot, and leaves no persistent footprint.
|
||||
- **Work that finishes before the user's next message** — agents persist indefinitely. Don't create one for something you could do inline.
|
||||
|
||||
### Writing good `instructions`
|
||||
|
||||
Cover: the agent's role, who it takes tasks from (you, by name), how it should report back (on completion only? with milestones for long work?), and any domain-specific rules. Don't restate NanoClaw base behavior — the shared base is already loaded on the agent's end.
|
||||
@@ -0,0 +1,27 @@
|
||||
## Sending messages
|
||||
|
||||
Your final response is delivered via the `## Sending messages` rules in your runtime system prompt (single-destination: just write; multi-destination: use `<message to="name">...</message>` blocks). See that section for the current destination list.
|
||||
|
||||
### Mid-turn updates (`send_message`)
|
||||
|
||||
Use the `mcp__nanoclaw__send_message` tool to send a message while you're still working (before your final output). If you have one destination, `to` is optional; with multiple, specify it. Pace your updates to the length of the work:
|
||||
|
||||
- **Short turn (≤2 quick tool calls):** Don't narrate. Output any response.
|
||||
- **Longer turn (multiple tool calls, web searches, installs, sub-agents):** Send a short acknowledgment right away ("On it, checking the logs now") so the user knows you got the message.
|
||||
- **Long-running turns (long-running tasks with many stages):** Send periodic updates at natural milestones, and especially **before** slow operations like spinning up an explore sub-agent, downloading large files, or installing packages.
|
||||
|
||||
**Never narrate micro-steps.** "I'm going to read the file now… okay, I'm reading it… now I'm parsing it…" is noise. Updates should mark meaningful transitions, not every tool call.
|
||||
|
||||
**Outcomes, not play-by-play.** When the turn is done, the final message should be about the result, not a transcript of what you did.
|
||||
|
||||
### Sending files (`send_file`)
|
||||
|
||||
Use `mcp__nanoclaw__send_file({ path, text?, filename?, to? })` to deliver a file from your workspace. `path` is absolute or relative to `/workspace/agent/`; `filename` overrides the display name shown in chat (defaults to the file's basename); `text` is an optional accompanying message. Use this for artifacts you produce (charts, PDFs, generated images, reports) rather than dumping contents into chat.
|
||||
|
||||
### Reacting to messages (`add_reaction`)
|
||||
|
||||
Use `mcp__nanoclaw__add_reaction({ messageId, emoji })` to react to a specific inbound message by its `#N` id — pass `messageId` as an integer (e.g. `22`, not `"22"`). Good for lightweight acknowledgment (`eyes` = seen, `white_check_mark` = done) when a full reply would be noise. `emoji` is the shortcode name (e.g. `thumbs_up`, `heart`), not the raw character.
|
||||
|
||||
### Internal thoughts
|
||||
|
||||
Wrap reasoning in `<internal>...</internal>` tags to mark it as scratchpad — logged but not sent.
|
||||
@@ -0,0 +1,22 @@
|
||||
## Interactive prompts
|
||||
|
||||
The two tools here solve different problems: `ask_user_question` forces a decision and waits for it; `send_card` displays structured content and moves on.
|
||||
|
||||
### Asking a multiple-choice question (`ask_user_question`)
|
||||
|
||||
`mcp__nanoclaw__ask_user_question({ title, question, options, timeout? })` presents the user with a set of choices and **blocks your turn** until they tap one or the timeout expires (default: 300 seconds). Returns their chosen value.
|
||||
|
||||
`options` can be plain strings or `{ label, selectedLabel?, value? }` objects:
|
||||
- `label` — the button text shown before selection
|
||||
- `selectedLabel` — the text shown on the button *after* selection (useful for confirmations, e.g. `"✓ Confirmed"`)
|
||||
- `value` — the string returned to you when that option is chosen (defaults to `label`)
|
||||
|
||||
Use this when you genuinely cannot proceed without a decision. For free-text input, send a normal message and wait for their reply — don't reach for this tool.
|
||||
|
||||
### Structured cards (`send_card`)
|
||||
|
||||
`mcp__nanoclaw__send_card({ card, fallbackText? })` renders a structured card and **returns immediately** — it does not pause your turn or collect a response.
|
||||
|
||||
`card` supports: `title`, `description`, `children` (nested text or content blocks), and `actions` (buttons). `fallbackText` is sent as a plain message on platforms without card support.
|
||||
|
||||
Use this for presenting information in a cleaner format than prose: summaries, options the user can read (but you're not waiting on), or results with contextual buttons. If you need the user to actually *choose* something and return a value, use `ask_user_question` instead.
|
||||
@@ -0,0 +1,40 @@
|
||||
## Task scheduling (`schedule_task`)
|
||||
|
||||
For any recurring task, use `schedule_task`. This is the scheduling path — tasks persist across sessions and restarts, and support the pre-task `script` hook described below.
|
||||
|
||||
To inspect or change existing tasks, use `list_tasks` (returns one row per series with the stable id) and `update_task` / `cancel_task` / `pause_task` / `resume_task`. Prefer `update_task` over cancel + reschedule.
|
||||
|
||||
Frequent recurring scheduled tasks — more than a few times a day — consume API credits and can risk account restrictions. You can add a `script` that runs first, and you will only be called when the check passes.
|
||||
|
||||
### How it works
|
||||
|
||||
1. Provide a bash `script` alongside the `prompt` when scheduling
|
||||
2. When the task fires, the script runs first
|
||||
3. Script returns: `{ "wakeAgent": true/false, "data": {...} }`
|
||||
4. If `wakeAgent: false` — nothing happens, task waits for next run
|
||||
5. If `wakeAgent: true` — claude receives the script's data + prompt and handles
|
||||
|
||||
### Always test your script first
|
||||
|
||||
Before scheduling, run the script directly to verify it works:
|
||||
|
||||
```bash
|
||||
bash -c 'node --input-type=module -e "
|
||||
const r = await fetch(\"https://api.github.com/repos/owner/repo/pulls?state=open\");
|
||||
const prs = await r.json();
|
||||
console.log(JSON.stringify({ wakeAgent: prs.length > 0, data: prs.slice(0, 5) }));
|
||||
"'
|
||||
```
|
||||
|
||||
### When NOT to use scripts
|
||||
|
||||
If a task requires your judgment every time (daily briefings, reminders, reports), skip the script — just use a regular prompt. Do not attempt to do things like sentiment analysis or advanced nlp in scripts.
|
||||
|
||||
### Frequent task guidance
|
||||
|
||||
If a user wants a task to run more than a few times a day and a script can't be used:
|
||||
|
||||
- Explain that each time the task fires it uses API credits and risks rate limits
|
||||
- Suggest adjusting the task requirements in a way that will allow you to use a script
|
||||
- If the user needs an LLM to evaluate data, suggest using an API key with direct Anthropic API calls inside the script
|
||||
- Help the user find the minimum viable frequency
|
||||
@@ -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 <context timezone="..."/> 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<string, unknown> = { 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;
|
||||
|
||||
@@ -0,0 +1,25 @@
|
||||
## Installing packages & tools
|
||||
|
||||
To install packages that persist, use the self-modification tools:
|
||||
|
||||
**`install_packages`** — request system (apt) or global npm packages. Requires admin approval.
|
||||
|
||||
Example flow:
|
||||
```
|
||||
install_packages({ apt: ["ffmpeg"], npm: ["@xenova/transformers"], reason: "Audio transcription" })
|
||||
# → Admin gets an approval card → approves
|
||||
```
|
||||
|
||||
**When to use this vs workspace `pnpm install`:**
|
||||
- `pnpm install` if you only need it temporarily to do one task. Will not be available in subsequent truns.
|
||||
- `install_packages` persists for all future turns. Use especially if the user specifically asks you to add a capability
|
||||
|
||||
### MCP servers (`add_mcp_server`)
|
||||
|
||||
Use **`add_mcp_server`** to add an MCP server to your configuration. Browse available servers at https://mcp.so — it's a curated directory of high-quality MCP servers. Most Node.js servers run via `pnpm dlx`, e.g.:
|
||||
|
||||
```
|
||||
add_mcp_server({ name: "memory", command: "pnpm", args: ["dlx", "@modelcontextprotocol/server-memory"] })
|
||||
```
|
||||
|
||||
Do not ask the user to give you credentials. Credentials are managed by the user in the OneCLI agent vault. Add a "placeholder" string instead of the credential, and ask the user to add the credential to the vault. You can make a test request before the secret is added and the vault proxy will respond with the local url of the vault dashboard on the user's machine and a link to a form for adding that specific credential.
|
||||
@@ -1,9 +1,13 @@
|
||||
/**
|
||||
* Self-modification MCP tools: install_packages, add_mcp_server, request_rebuild.
|
||||
* Self-modification MCP tools: install_packages, add_mcp_server.
|
||||
*
|
||||
* All three are fire-and-forget — the tool writes a system action row and
|
||||
* returns immediately. The host processes the request (including admin
|
||||
* approval) and notifies the agent via a chat message when complete.
|
||||
* Both are fire-and-forget — the tool writes a system action row and returns
|
||||
* immediately. The host processes the request (including admin approval)
|
||||
* and notifies the agent via a chat message when complete. Admin approval
|
||||
* is approval to apply the change: `install_packages` auto-rebuilds the
|
||||
* per-agent image and restarts the container; `add_mcp_server` just
|
||||
* updates `container.json` and restarts (bun runs TS directly — no build
|
||||
* step needed for a pure MCP wiring change).
|
||||
*
|
||||
* Package names are sanitized here at the tool boundary AND re-validated on
|
||||
* the host side (defense in depth).
|
||||
@@ -36,7 +40,7 @@ export const installPackages: McpToolDefinition = {
|
||||
tool: {
|
||||
name: 'install_packages',
|
||||
description:
|
||||
'Install apt and/or npm packages into YOUR per-agent container image. Requires admin approval; fire-and-forget. After approval, call `request_rebuild` to apply.',
|
||||
'Install apt and/or npm packages into YOUR per-agent container image. Requires admin approval; fire-and-forget. On approval, the image is rebuilt and the container is restarted automatically.',
|
||||
inputSchema: {
|
||||
type: 'object' as const,
|
||||
properties: {
|
||||
@@ -113,32 +117,4 @@ export const addMcpServer: McpToolDefinition = {
|
||||
},
|
||||
};
|
||||
|
||||
export const requestRebuild: McpToolDefinition = {
|
||||
tool: {
|
||||
name: 'request_rebuild',
|
||||
description:
|
||||
'Rebuild YOUR container image to pick up approved `install_packages` / `add_mcp_server` changes. Requires admin approval; fire-and-forget.',
|
||||
inputSchema: {
|
||||
type: 'object' as const,
|
||||
properties: {
|
||||
reason: { type: 'string', description: 'Why the rebuild is needed' },
|
||||
},
|
||||
},
|
||||
},
|
||||
async handler(args) {
|
||||
const requestId = generateId();
|
||||
writeMessageOut({
|
||||
id: requestId,
|
||||
kind: 'system',
|
||||
content: JSON.stringify({
|
||||
action: 'request_rebuild',
|
||||
reason: (args.reason as string) || '',
|
||||
}),
|
||||
});
|
||||
|
||||
log(`request_rebuild: ${requestId}`);
|
||||
return ok(`Rebuild request submitted. You will be notified when admin approves or rejects.`);
|
||||
},
|
||||
};
|
||||
|
||||
registerTools([installPackages, addMcpServer, requestRebuild]);
|
||||
registerTools([installPackages, addMcpServer]);
|
||||
|
||||
@@ -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()
|
||||
|
||||
@@ -2,13 +2,16 @@ import { findByName, getAllDestinations, type DestinationEntry } from './destina
|
||||
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 { getStoredSessionId, setStoredSessionId, clearStoredSessionId } from './db/session-state.js';
|
||||
import { formatMessages, extractRouting, categorizeMessage, type RoutingContext } from './formatter.js';
|
||||
import {
|
||||
clearContinuation,
|
||||
migrateLegacyContinuation,
|
||||
setContinuation,
|
||||
} from './db/session-state.js';
|
||||
import { formatMessages, extractRouting, categorizeMessage, isClearCommand, stripInternalTags, type RoutingContext } from './formatter.js';
|
||||
import type { AgentProvider, AgentQuery, ProviderEvent } from './providers/types.js';
|
||||
|
||||
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}`);
|
||||
@@ -20,16 +23,16 @@ function generateId(): string {
|
||||
|
||||
export interface PollLoopConfig {
|
||||
provider: AgentProvider;
|
||||
/**
|
||||
* Name of the provider (e.g. "claude", "codex", "opencode"). Used to key
|
||||
* the stored continuation per-provider so flipping providers doesn't
|
||||
* resurrect a stale id from a different backend.
|
||||
*/
|
||||
providerName: string;
|
||||
cwd: string;
|
||||
systemContext?: {
|
||||
instructions?: string;
|
||||
};
|
||||
/**
|
||||
* Set of user IDs allowed to run admin commands (e.g. /clear) in this
|
||||
* agent group. Host populates from owners + global admins + scoped admins
|
||||
* at container wake time, so role changes take effect on next spawn.
|
||||
*/
|
||||
adminUserIds?: Set<string>;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -46,8 +49,9 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
|
||||
// Resume the agent's prior session from a previous container run if one
|
||||
// was persisted. The continuation is opaque to the poll-loop — the
|
||||
// provider decides how to use it (Claude resumes a .jsonl transcript,
|
||||
// other providers may reload a thread ID, etc.).
|
||||
let continuation: string | undefined = getStoredSessionId();
|
||||
// other providers may reload a thread ID, etc.). Keyed per-provider so
|
||||
// a Codex thread id never gets handed to Claude or vice versa.
|
||||
let continuation: string | undefined = migrateLegacyContinuation(config.providerName);
|
||||
|
||||
if (continuation) {
|
||||
log(`Resuming agent session ${continuation}`);
|
||||
@@ -73,79 +77,54 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
|
||||
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);
|
||||
|
||||
const routing = extractRouting(messages);
|
||||
|
||||
// Handle commands: categorize chat messages
|
||||
const adminUserIds = config.adminUserIds ?? new Set<string>();
|
||||
const normalMessages = [];
|
||||
// Command handling: the host router gates filtered and unauthorized
|
||||
// admin commands before they reach the container. The only command
|
||||
// the runner handles directly is /clear (session reset).
|
||||
const normalMessages: MessageInRow[] = [];
|
||||
const commandIds: string[] = [];
|
||||
|
||||
for (const msg of messages) {
|
||||
if (msg.kind !== 'chat' && msg.kind !== 'chat-sdk') {
|
||||
normalMessages.push(msg);
|
||||
continue;
|
||||
}
|
||||
|
||||
const cmdInfo = categorizeMessage(msg);
|
||||
|
||||
if (cmdInfo.category === 'filtered') {
|
||||
// Silently drop — mark completed, don't process
|
||||
log(`Filtered command: ${cmdInfo.command} (msg: ${msg.id})`);
|
||||
if ((msg.kind === 'chat' || msg.kind === 'chat-sdk') && isClearCommand(msg)) {
|
||||
log('Clearing session (resetting continuation)');
|
||||
continuation = undefined;
|
||||
clearContinuation(config.providerName);
|
||||
writeMessageOut({
|
||||
id: generateId(),
|
||||
kind: 'chat',
|
||||
platform_id: routing.platformId,
|
||||
channel_type: routing.channelType,
|
||||
thread_id: routing.threadId,
|
||||
content: JSON.stringify({ text: 'Session cleared.' }),
|
||||
});
|
||||
commandIds.push(msg.id);
|
||||
continue;
|
||||
}
|
||||
|
||||
if (cmdInfo.category === 'admin') {
|
||||
if (!cmdInfo.senderId || !adminUserIds.has(cmdInfo.senderId)) {
|
||||
log(`Admin command denied: ${cmdInfo.command} from ${cmdInfo.senderId} (msg: ${msg.id})`);
|
||||
writeMessageOut({
|
||||
id: generateId(),
|
||||
kind: 'chat',
|
||||
platform_id: routing.platformId,
|
||||
channel_type: routing.channelType,
|
||||
thread_id: routing.threadId,
|
||||
content: JSON.stringify({ text: `Permission denied: ${cmdInfo.command} requires admin access.` }),
|
||||
});
|
||||
commandIds.push(msg.id);
|
||||
continue;
|
||||
}
|
||||
// Handle admin commands directly
|
||||
if (cmdInfo.command === '/clear') {
|
||||
log('Clearing session (resetting continuation)');
|
||||
continuation = undefined;
|
||||
clearStoredSessionId();
|
||||
writeMessageOut({
|
||||
id: generateId(),
|
||||
kind: 'chat',
|
||||
platform_id: routing.platformId,
|
||||
channel_type: routing.channelType,
|
||||
thread_id: routing.threadId,
|
||||
content: JSON.stringify({ text: 'Session cleared.' }),
|
||||
});
|
||||
commandIds.push(msg.id);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Other admin commands — pass through to agent
|
||||
normalMessages.push(msg);
|
||||
continue;
|
||||
}
|
||||
|
||||
// passthrough or none
|
||||
normalMessages.push(msg);
|
||||
}
|
||||
|
||||
// Mark filtered/denied command messages as completed immediately
|
||||
if (commandIds.length > 0) {
|
||||
markCompleted(commandIds);
|
||||
}
|
||||
|
||||
// If all messages were filtered commands, skip processing
|
||||
if (normalMessages.length === 0) {
|
||||
// Mark remaining processing IDs as completed
|
||||
const remainingIds = ids.filter((id) => !commandIds.includes(id));
|
||||
if (remainingIds.length > 0) markCompleted(remainingIds);
|
||||
log(`All ${messages.length} message(s) were commands, skipping query`);
|
||||
@@ -192,10 +171,10 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
|
||||
const skippedSet = new Set(skipped);
|
||||
const processingIds = ids.filter((id) => !commandIds.includes(id) && !skippedSet.has(id));
|
||||
try {
|
||||
const result = await processQuery(query, routing);
|
||||
const result = await processQuery(query, routing, processingIds, config.providerName);
|
||||
if (result.continuation && result.continuation !== continuation) {
|
||||
continuation = result.continuation;
|
||||
setStoredSessionId(continuation);
|
||||
setContinuation(config.providerName, continuation);
|
||||
}
|
||||
} catch (err) {
|
||||
const errMsg = err instanceof Error ? err.message : String(err);
|
||||
@@ -207,7 +186,7 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
|
||||
if (continuation && config.provider.isSessionInvalid(err)) {
|
||||
log(`Stale session detected (${continuation}) — clearing for next retry`);
|
||||
continuation = undefined;
|
||||
clearStoredSessionId();
|
||||
clearContinuation(config.providerName);
|
||||
}
|
||||
|
||||
// Write error response so the user knows something went wrong
|
||||
@@ -221,6 +200,8 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
|
||||
});
|
||||
}
|
||||
|
||||
// Ensure completed even if processQuery ended without a result event
|
||||
// (e.g. stream closed unexpectedly).
|
||||
markCompleted(processingIds);
|
||||
log(`Completed ${ids.length} message(s)`);
|
||||
}
|
||||
@@ -264,27 +245,34 @@ interface QueryResult {
|
||||
continuation?: string;
|
||||
}
|
||||
|
||||
async function processQuery(query: AgentQuery, routing: RoutingContext): Promise<QueryResult> {
|
||||
async function processQuery(
|
||||
query: AgentQuery,
|
||||
routing: RoutingContext,
|
||||
initialBatchIds: string[],
|
||||
providerName: string,
|
||||
): Promise<QueryResult> {
|
||||
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;
|
||||
|
||||
// Skip system messages (MCP tool responses) and admin commands (need fresh query).
|
||||
// Also defer messages whose thread_id differs from the active turn's routing
|
||||
// — mixing threads into one streaming turn would send the reply to the wrong
|
||||
// thread because `routing` is captured at turn start. The next turn will pick
|
||||
// them up with fresh routing.
|
||||
// Skip system messages (MCP tool responses) and /clear (needs fresh query).
|
||||
// Thread routing is the router's concern — if a message landed in this
|
||||
// session, the agent should see it. Per-thread sessions already isolate
|
||||
// threads into separate containers; shared sessions intentionally merge
|
||||
// everything. Filtering on thread_id here caused deadlocks when the
|
||||
// initial batch and follow-ups had mismatched thread_ids (e.g. a
|
||||
// host-generated welcome trigger with null thread vs a Discord DM reply).
|
||||
const newMessages = getPendingMessages().filter((m) => {
|
||||
if (m.kind === 'system') return false;
|
||||
if (m.kind === 'chat' || m.kind === 'chat-sdk') {
|
||||
const cmd = categorizeMessage(m);
|
||||
if (cmd.category === 'admin') return false;
|
||||
}
|
||||
if ((m.thread_id ?? null) !== (routing.threadId ?? null)) return false;
|
||||
if ((m.kind === 'chat' || m.kind === 'chat-sdk') && isClearCommand(m)) return false;
|
||||
return true;
|
||||
});
|
||||
if (newMessages.length > 0) {
|
||||
@@ -296,26 +284,34 @@ 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();
|
||||
|
||||
if (event.type === 'init') {
|
||||
queryContinuation = event.continuation;
|
||||
} else if (event.type === 'result' && event.text) {
|
||||
dispatchResultText(event.text, routing);
|
||||
// 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.
|
||||
setContinuation(providerName, event.continuation);
|
||||
} else if (event.type === 'result') {
|
||||
// A result — with or without text — means the turn is done. Mark
|
||||
// the initial batch completed now so the host sweep doesn't see
|
||||
// stale 'processing' claims while the query stays open for
|
||||
// follow-up pushes. The agent may have responded via MCP
|
||||
// (send_message) mid-turn, or the message may not need a response
|
||||
// at all — either way the turn is finished.
|
||||
markCompleted(initialBatchIds);
|
||||
if (event.text) {
|
||||
dispatchResultText(event.text, routing);
|
||||
}
|
||||
}
|
||||
}
|
||||
} finally {
|
||||
@@ -384,10 +380,7 @@ function dispatchResultText(text: string, routing: RoutingContext): void {
|
||||
scratchpadParts.push(text.slice(lastIndex));
|
||||
}
|
||||
|
||||
const scratchpad = scratchpadParts
|
||||
.join('')
|
||||
.replace(/<internal>[\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,
|
||||
|
||||
@@ -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<string, unknown> };
|
||||
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<HookCallback>;
|
||||
}
|
||||
// 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;
|
||||
@@ -215,6 +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,
|
||||
@@ -224,6 +281,9 @@ 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)] }],
|
||||
},
|
||||
},
|
||||
|
||||
@@ -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');
|
||||
});
|
||||
});
|
||||
@@ -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}$/.test(input.trim());
|
||||
if (hasOffset) return new Date(input);
|
||||
|
||||
const zone = resolveTimezone(tz);
|
||||
const asIfUtc = new Date(input + 'Z');
|
||||
if (Number.isNaN(asIfUtc.getTime())) return asIfUtc;
|
||||
|
||||
const fmt = new Intl.DateTimeFormat('en-US', {
|
||||
timeZone: zone,
|
||||
year: 'numeric',
|
||||
month: '2-digit',
|
||||
day: '2-digit',
|
||||
hour: '2-digit',
|
||||
minute: '2-digit',
|
||||
second: '2-digit',
|
||||
hour12: false,
|
||||
});
|
||||
const parts = Object.fromEntries(
|
||||
fmt
|
||||
.formatToParts(asIfUtc)
|
||||
.filter((p) => p.type !== 'literal')
|
||||
.map((p) => [p.type, p.value]),
|
||||
);
|
||||
const hour = parts.hour === '24' ? '00' : parts.hour;
|
||||
const zonedAsUtcMs = Date.UTC(
|
||||
Number(parts.year),
|
||||
Number(parts.month) - 1,
|
||||
Number(parts.day),
|
||||
Number(hour),
|
||||
Number(parts.minute),
|
||||
Number(parts.second),
|
||||
);
|
||||
const offsetMs = zonedAsUtcMs - asIfUtc.getTime();
|
||||
return new Date(asIfUtc.getTime() - offsetMs);
|
||||
}
|
||||
+7
-1
@@ -9,9 +9,15 @@
|
||||
set -e
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
PROJECT_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
|
||||
cd "$SCRIPT_DIR"
|
||||
|
||||
IMAGE_NAME="nanoclaw-agent"
|
||||
# Derive the image name from the project root so two NanoClaw installs on the
|
||||
# same host don't overwrite each other's `nanoclaw-agent:latest` tag. Matches
|
||||
# setup/lib/install-slug.sh + src/install-slug.ts.
|
||||
# shellcheck source=../setup/lib/install-slug.sh
|
||||
source "$PROJECT_ROOT/setup/lib/install-slug.sh"
|
||||
IMAGE_NAME="$(container_image_base)"
|
||||
TAG="${1:-latest}"
|
||||
CONTAINER_RUNTIME="${CONTAINER_RUNTIME:-docker}"
|
||||
|
||||
|
||||
@@ -11,9 +11,9 @@ You can modify your own environment. Different kinds of changes have different w
|
||||
|
||||
**What needs to change?**
|
||||
|
||||
- **Your CLAUDE.md or files in your workspace** → Edit directly, no approval needed. Your workspace (`/workspace/agent/`) is persisted on the host.
|
||||
- **System package (apt) or global npm package** → `install_packages` → `request_rebuild`. Requires admin approval.
|
||||
- **MCP server** → `add_mcp_server` → `request_rebuild`. No approval needed, but rebuild required to apply.
|
||||
- **`CLAUDE.local.md` or files in your workspace** → Edit directly, no approval needed. Your workspace (`/workspace/agent/`) is persisted on the host. (Note: the composed `CLAUDE.md` itself is read-only and regenerated every spawn — write to `CLAUDE.local.md` instead.)
|
||||
- **System package (apt) or global npm package** → `install_packages`. Requires admin approval. On approval, image rebuild + container restart happen automatically.
|
||||
- **MCP server** → `add_mcp_server`. Requires admin approval. On approval, container restarts with the new server wired up (no rebuild — bun runs TS directly).
|
||||
- **Your source code or Dockerfile** → Delegate to a builder agent via `create_agent` (see below).
|
||||
- **A new specialist capability** → `create_agent` to spin up a dedicated agent for it.
|
||||
|
||||
@@ -25,7 +25,7 @@ For anything that requires editing source files (your own code, Dockerfile, etc.
|
||||
2. Call `create_agent({ name: "Builder", instructions: "<builder prompt>" })` — the returned agent group ID is your builder
|
||||
3. Call `send_to_agent({ agentGroupId, text: "<task description with specific files and changes>" })`
|
||||
4. The builder works in its own container, makes the changes, and reports back
|
||||
5. You review the builder's summary, confirm with the user, then call `request_rebuild` if the changes require it
|
||||
5. You review the builder's summary and confirm with the user. Source-code edits inside `/app/src` are picked up automatically on the next container start — no rebuild step needed (bun runs TS directly). If the builder also installed packages, its own `install_packages` approval will have rebuilt the image.
|
||||
|
||||
### Builder Agent Instructions (use as CLAUDE.md when creating)
|
||||
|
||||
@@ -64,12 +64,11 @@ The limits are **per builder task**, not per session. A 500-line feature is fine
|
||||
User: "Can you add a tool for reading RSS feeds?"
|
||||
|
||||
1. Check [mcp.so](https://mcp.so) for an existing RSS MCP server
|
||||
2. If one exists → `add_mcp_server({ name: "rss", command: "npx", args: ["some-rss-mcp"] })` → `request_rebuild` → done
|
||||
2. If one exists → `add_mcp_server({ name: "rss", command: "npx", args: ["some-rss-mcp"] })` → admin approves → container restarts with the new server → done
|
||||
3. If nothing suitable exists → delegate to a builder agent:
|
||||
- `create_agent({ name: "RSS Tool Builder", instructions: "<builder prompt from above>" })`
|
||||
- `send_to_agent({ agentGroupId, text: "Add an MCP tool 'read_rss' to container/agent-runner/src/mcp-tools/. It should fetch an RSS URL and return the latest N items. Register it in mcp-tools/index.ts. Target: <200 new lines." })`
|
||||
- Wait for builder's report
|
||||
- `request_rebuild` if needed
|
||||
- Wait for builder's report — new tool code is picked up on the next container start (bun runs TS directly)
|
||||
|
||||
## Example: Installing a System Tool
|
||||
|
||||
@@ -78,10 +77,8 @@ User: "Can you transcribe audio?"
|
||||
1. Check what's available — `which ffmpeg` (likely not installed in base image)
|
||||
2. Decide approach: `@xenova/transformers` (npm, workspace-local) or `whisper.cpp` (apt + compile)
|
||||
3. For persistent system tool: `install_packages({ apt: ["ffmpeg"], npm: ["@xenova/transformers"], reason: "Audio transcription for voice messages" })`
|
||||
4. Wait for admin approval
|
||||
5. `request_rebuild({ reason: "Apply audio transcription packages" })`
|
||||
6. Wait for admin approval
|
||||
7. Test the new capability once the container restarts
|
||||
4. Wait for admin approval — on approve, the image is rebuilt and your container is restarted automatically
|
||||
5. Test the new capability once the container restarts
|
||||
|
||||
## When NOT to Self-Customize
|
||||
|
||||
|
||||
@@ -3,26 +3,83 @@ name: welcome
|
||||
description: Introduce yourself to a newly connected channel. Triggered automatically when a channel is first wired. Send a friendly greeting and brief overview of what you can do.
|
||||
---
|
||||
|
||||
# /welcome — Channel Onboarding
|
||||
# /welcome — Channel Onboarding (Updated)
|
||||
|
||||
You've just been connected to a new messaging channel. Introduce yourself to the user.
|
||||
You've just been connected to a new user. This your time to shine and make a strong first impression. Introduce yourself and guide the user through what you can do. you got this!
|
||||
|
||||
## What to do
|
||||
|
||||
1. Send a short, warm greeting using `send_message`
|
||||
2. Mention your name (from your CLAUDE.md)
|
||||
3. Make it clear you can do a lot — but do NOT list your tools or skills upfront. Keep it open-ended and intriguing
|
||||
4. End by asking: would they like to explore what you can do, or jump straight into building/creating something?
|
||||
2. State your name (from your system prompt / CLAUDE.md)
|
||||
3. Signal that you're capable of a lot — but don't list everything upfront. Be intriguing, not encyclopedic
|
||||
4. Ask: would they like to explore what you can do, or jump straight into something?
|
||||
|
||||
**If they want to explore:** show one skill or capability at a time. Briefly explain what it does, offer to demo it or let them try it, then ask if they want to see the next one or move on. Drip-feed — never dump a list.
|
||||
**If they want to explore:** drip-feed one capability at a time. Briefly explain it, offer to demo a compelling example or let them try it. Never dump a full list.
|
||||
|
||||
**If they want to jump in:** just go. Help them with whatever they ask.
|
||||
**If they want to jump in:** just go.
|
||||
|
||||
---
|
||||
|
||||
## Capabilities to reveal (in order)
|
||||
|
||||
Reveal these one at a time, in this sequence. Each should be 2–4 sentences max.
|
||||
|
||||
### 1. Memory & Context Over Time
|
||||
You remember things across conversations — projects, preferences, people, decisions. Users don't have to re-explain context every session. The more they work with you, the more situationally aware you become.
|
||||
|
||||
### 2. Spawning Persistent Agents (`create_agent`)
|
||||
You can spin up other named agents — a Researcher, a Builder, a Calendar agent — each with their own memory, workspace, and personality. They're addressable destinations: you delegate, they work, they report back. These aren't one-shot tasks; they accumulate context across sessions.
|
||||
|
||||
### 3. Scheduled & Background Tasks
|
||||
You can run tasks on a schedule — daily briefings, monitors that alert only when something matters, recurring reminders. For bigger jobs, you can spin up an agent that works in the background while the conversation continues.
|
||||
|
||||
### 4. Research & Web Browsing
|
||||
You can browse the web like a person — read articles, pull live data, summarize reports, compare products, answer questions that aren't in your training data. Ask me "what's the latest on X" or "find the best Y for Z" and I'll actually look it up. Very powerful when combined with scheduled tasks.
|
||||
|
||||
### 5. Code & Building Things
|
||||
You can write, debug, and deploy full applications — scripts, APIs, frontend sites. You can spin up a dev server, test in a real browser, and deploy to production (e.g. Vercel). Concept to live URL.
|
||||
|
||||
### 6. Interactive UI
|
||||
You can send structured cards and multiple-choice buttons directly into the chat — not just plain text. Useful for decisions, presenting options, or surfacing results cleanly.
|
||||
|
||||
### 7. Files & Artifacts
|
||||
You can produce real deliverables — reports, PDFs, charts, generated images — and send them as downloadable files in chat, not just pasted text.
|
||||
|
||||
### 8. Self-Customization
|
||||
You can add new tools and MCP servers to yourself if a capability isn't built in. You can extend your own toolkit when the task requires it.
|
||||
|
||||
---
|
||||
|
||||
## Trust & Control — always include these
|
||||
|
||||
After the capabilities tour (or woven in naturally), cover these two points. Frame them positively — users stay in control.
|
||||
|
||||
### Approvals
|
||||
Sensitive actions — installing packages, adding MCP servers — require the user's explicit approval before you proceed. They'll get a prompt; nothing happens automatically. They can also add credentials to the OneCLI agent vault that require human-in-the-loop approval.
|
||||
|
||||
### Access Control
|
||||
The user owns who can talk to you. Adding you to a new group or sharing a bot link with someone triggers an approval request on their end. Nobody interacts with you without their say-so.
|
||||
|
||||
---
|
||||
|
||||
## How to interact — always mention this
|
||||
|
||||
There are no special commands. Users just talk naturally. If they want something done, they say so. That's it.
|
||||
|
||||
---
|
||||
|
||||
## Wrapping up
|
||||
|
||||
After the tour, finish with an open invitation. Ask if they want help with something specific. Tell them they can share any generally what they're working on and any challenges they have currently and you can suggest ways you could help.
|
||||
|
||||
---
|
||||
|
||||
## Tone
|
||||
|
||||
Warm, confident, and inviting. Make the user feel like they just unlocked something powerful. Match the channel's vibe (casual for Telegram/Discord, slightly more professional for Slack/Teams/email).
|
||||
Warm, confident, inviting. Make the user feel like they just unlocked something powerful. Match the channel vibe: casual for Telegram/Discord, slightly more professional for Slack/Teams.
|
||||
|
||||
## Important
|
||||
|
||||
- Scan your available MCP tools and skills so you know what you have — but keep that knowledge in your back pocket. Reveal capabilities naturally, one at a time, only when relevant or when the user asks to explore.
|
||||
- Never overwhelm with a full list. Discovery should feel like unwrapping, not reading a manual.
|
||||
- Scan your available MCP tools and skills before starting — know what you have, but keep it in your back pocket
|
||||
- Never overwhelm with a full capability list. Discovery should feel like unwrapping, not reading a manual
|
||||
- Confirmations and corrections from the user during onboarding are feedback — save them to memory for future sessions
|
||||
@@ -1,171 +0,0 @@
|
||||
# NanoClaw Debug Checklist
|
||||
|
||||
## Known Issues (2026-02-08)
|
||||
|
||||
### 1. [FIXED] Resume branches from stale tree position
|
||||
When agent teams spawns subagent CLI processes, they write to the same session JSONL. On subsequent `query()` resumes, the CLI reads the JSONL but may pick a stale branch tip (from before the subagent activity), causing the agent's response to land on a branch the host never receives a `result` for. **Fix**: pass `resumeSessionAt` with the last assistant message UUID to explicitly anchor each resume.
|
||||
|
||||
### 2. IDLE_TIMEOUT == CONTAINER_TIMEOUT (both 30 min)
|
||||
Both timers fire at the same time, so containers always exit via hard SIGKILL (code 137) instead of graceful `_close` sentinel shutdown. The idle timeout should be shorter (e.g., 5 min) so containers wind down between messages, while container timeout stays at 30 min as a safety net for stuck agents.
|
||||
|
||||
### 3. Cursor advanced before agent succeeds
|
||||
`processGroupMessages` advances `lastAgentTimestamp` before the agent runs. If the container times out, retries find no messages (cursor already past them). Messages are permanently lost on timeout.
|
||||
|
||||
### 4. Kubernetes image garbage collection deletes nanoclaw-agent image
|
||||
|
||||
**Symptoms**: `Container exited with code 125: pull access denied for nanoclaw-agent` — the container image disappears overnight or after a few hours, even though you just built it.
|
||||
|
||||
**Cause**: If your container runtime has Kubernetes enabled (Rancher Desktop enables it by default), the kubelet runs image garbage collection when disk usage exceeds 85%. NanoClaw containers are ephemeral (run and exit), so `nanoclaw-agent:latest` is never protected by a running container. The kubelet sees it as unused and deletes it — often overnight when no messages are being processed. Other images (docker-compose services) survive because they have long-running containers referencing them.
|
||||
|
||||
**Fix**: Disable Kubernetes if you don't need it:
|
||||
```bash
|
||||
# Rancher Desktop
|
||||
rdctl set --kubernetes-enabled=false
|
||||
|
||||
# Then rebuild the container image
|
||||
./container/build.sh
|
||||
```
|
||||
|
||||
**Diagnosis**: Check the k3s log for image GC activity:
|
||||
```bash
|
||||
grep -i "nanoclaw" ~/Library/Logs/rancher-desktop/k3s.log
|
||||
# Look for: "Removing image to free bytes" with the nanoclaw-agent image ID
|
||||
```
|
||||
|
||||
Check NanoClaw logs for image status:
|
||||
```bash
|
||||
grep -E "image found|image NOT found|image missing" logs/nanoclaw.log
|
||||
```
|
||||
|
||||
If you need Kubernetes enabled, set `CONTAINER_IMAGE` to an image stored in a registry that the kubelet won't GC, or raise the GC thresholds.
|
||||
|
||||
## Quick Status Check
|
||||
|
||||
```bash
|
||||
# 1. Is the service running?
|
||||
launchctl list | grep nanoclaw
|
||||
# Expected: PID 0 com.nanoclaw (PID = running, "-" = not running, non-zero exit = crashed)
|
||||
|
||||
# 2. Any running containers?
|
||||
docker ps --format '{{.Names}} {{.Status}}' 2>/dev/null | grep nanoclaw
|
||||
|
||||
# 3. Any stopped/orphaned containers?
|
||||
docker ps -a --format '{{.Names}} {{.Status}}' 2>/dev/null | grep nanoclaw
|
||||
|
||||
# 4. Recent errors in service log?
|
||||
grep -E 'ERROR|WARN' logs/nanoclaw.log | tail -20
|
||||
|
||||
# 5. Are channels connected? (look for last connection event)
|
||||
grep -E 'Connected|Connection closed|connection.*close|channel.*ready' logs/nanoclaw.log | tail -5
|
||||
|
||||
# 6. Are groups loaded?
|
||||
grep 'groupCount' logs/nanoclaw.log | tail -3
|
||||
```
|
||||
|
||||
## Session Transcript Branching
|
||||
|
||||
```bash
|
||||
# Check for concurrent CLI processes in session debug logs
|
||||
ls -la data/sessions/<group>/.claude/debug/
|
||||
|
||||
# Count unique SDK processes that handled messages
|
||||
# Each .txt file = one CLI subprocess. Multiple = concurrent queries.
|
||||
|
||||
# Check parentUuid branching in transcript
|
||||
python3 -c "
|
||||
import json, sys
|
||||
lines = open('data/sessions/<group>/.claude/projects/-workspace-group/<session>.jsonl').read().strip().split('\n')
|
||||
for i, line in enumerate(lines):
|
||||
try:
|
||||
d = json.loads(line)
|
||||
if d.get('type') == 'user' and d.get('message'):
|
||||
parent = d.get('parentUuid', 'ROOT')[:8]
|
||||
content = str(d['message'].get('content', ''))[:60]
|
||||
print(f'L{i+1} parent={parent} {content}')
|
||||
except: pass
|
||||
"
|
||||
```
|
||||
|
||||
## Container Timeout Investigation
|
||||
|
||||
```bash
|
||||
# Check for recent timeouts
|
||||
grep -E 'Container timeout|timed out' logs/nanoclaw.log | tail -10
|
||||
|
||||
# Check container log files for the timed-out container
|
||||
ls -lt groups/*/logs/container-*.log | head -10
|
||||
|
||||
# Read the most recent container log (replace path)
|
||||
cat groups/<group>/logs/container-<timestamp>.log
|
||||
|
||||
# Check if retries were scheduled and what happened
|
||||
grep -E 'Scheduling retry|retry|Max retries' logs/nanoclaw.log | tail -10
|
||||
```
|
||||
|
||||
## Agent Not Responding
|
||||
|
||||
```bash
|
||||
# Check if messages are being received from channels
|
||||
grep 'New messages' logs/nanoclaw.log | tail -10
|
||||
|
||||
# Check if messages are being processed (container spawned)
|
||||
grep -E 'Processing messages|Spawning container' logs/nanoclaw.log | tail -10
|
||||
|
||||
# Check if messages are being piped to active container
|
||||
grep -E 'Piped messages|sendMessage' logs/nanoclaw.log | tail -10
|
||||
|
||||
# Check the queue state — any active containers?
|
||||
grep -E 'Starting container|Container active|concurrency limit' logs/nanoclaw.log | tail -10
|
||||
|
||||
# Check lastAgentTimestamp vs latest message timestamp
|
||||
sqlite3 store/messages.db "SELECT chat_jid, MAX(timestamp) as latest FROM messages GROUP BY chat_jid ORDER BY latest DESC LIMIT 5;"
|
||||
```
|
||||
|
||||
## Container Mount Issues
|
||||
|
||||
```bash
|
||||
# Check mount validation logs (shows on container spawn)
|
||||
grep -E 'Mount validated|Mount.*REJECTED|mount' logs/nanoclaw.log | tail -10
|
||||
|
||||
# Verify the mount allowlist is readable
|
||||
cat ~/.config/nanoclaw/mount-allowlist.json
|
||||
|
||||
# Check group's container_config in DB
|
||||
sqlite3 store/messages.db "SELECT name, container_config FROM registered_groups;"
|
||||
|
||||
# Test-run a container to check mounts (dry run)
|
||||
# Replace <group-folder> with the group's folder name
|
||||
docker run -i --rm --entrypoint ls nanoclaw-agent:latest /workspace/extra/
|
||||
```
|
||||
|
||||
## Channel Auth Issues
|
||||
|
||||
```bash
|
||||
# Check if QR code was requested (means auth expired)
|
||||
grep 'QR\|authentication required\|qr' logs/nanoclaw.log | tail -5
|
||||
|
||||
# Check auth files exist
|
||||
ls -la store/auth/
|
||||
|
||||
# Re-authenticate if needed
|
||||
pnpm run auth
|
||||
```
|
||||
|
||||
## Service Management
|
||||
|
||||
```bash
|
||||
# Restart the service
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw
|
||||
|
||||
# View live logs
|
||||
tail -f logs/nanoclaw.log
|
||||
|
||||
# Stop the service (careful — running containers are detached, not killed)
|
||||
launchctl bootout gui/$(id -u)/com.nanoclaw
|
||||
|
||||
# Start the service
|
||||
launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/com.nanoclaw.plist
|
||||
|
||||
# Rebuild after code changes
|
||||
pnpm run build && launchctl kickstart -k gui/$(id -u)/com.nanoclaw
|
||||
```
|
||||
@@ -10,6 +10,5 @@ The files in this directory are original design documents and developer referenc
|
||||
| [SECURITY.md](SECURITY.md) | [Security model](https://docs.nanoclaw.dev/concepts/security) |
|
||||
| [REQUIREMENTS.md](REQUIREMENTS.md) | [Introduction](https://docs.nanoclaw.dev/introduction) |
|
||||
| [skills-as-branches.md](skills-as-branches.md) | [Skills system](https://docs.nanoclaw.dev/integrations/skills-system) |
|
||||
| [DEBUG_CHECKLIST.md](DEBUG_CHECKLIST.md) | [Troubleshooting](https://docs.nanoclaw.dev/advanced/troubleshooting) |
|
||||
| [docker-sandboxes.md](docker-sandboxes.md) | [Docker Sandboxes](https://docs.nanoclaw.dev/advanced/docker-sandboxes) |
|
||||
| [APPLE-CONTAINER-NETWORKING.md](APPLE-CONTAINER-NETWORKING.md) | [Container runtime](https://docs.nanoclaw.dev/advanced/container-runtime) |
|
||||
|
||||
@@ -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);
|
||||
|
||||
|
||||
@@ -32,7 +32,7 @@ flowchart TB
|
||||
direction TB
|
||||
PollLoop["Poll Loop<br/>(container/agent-runner)"]
|
||||
Provider["Agent providers<br/>(claude, opencode, mock; todo: codex)"]
|
||||
MCP["MCP Tools<br/>send_message, send_file, edit_message,<br/>add_reaction, send_card, ask_user_question,<br/>schedule_task, create_agent,<br/>install_packages, add_mcp_server, request_rebuild"]
|
||||
MCP["MCP Tools<br/>send_message, send_file, edit_message,<br/>add_reaction, send_card, ask_user_question,<br/>schedule_task, create_agent,<br/>install_packages, add_mcp_server"]
|
||||
Skills["Container Skills<br/>(container/skills/)"]
|
||||
InDB[("inbound.db<br/>host writes<br/>even seq<br/>messages_in<br/>destinations<br/>processing_ack")]
|
||||
OutDB[("outbound.db<br/>container writes<br/>odd seq<br/>messages_out<br/>heartbeat file")]
|
||||
|
||||
@@ -876,7 +876,7 @@ Messages starting with `/` are checked against three lists:
|
||||
- Commands that don't make sense in the NanoClaw context or could cause issues
|
||||
- Silently dropped — no error, no forwarding
|
||||
|
||||
The command lists are hardcoded in the agent-runner. Admin verification: the host passes `NANOCLAW_ADMIN_USER_IDS` (a comma-separated list of owner + global-admin + scoped-admin user ids for the current agent group, see `src/container-runner.ts`) to the container. The agent-runner membership-tests the inbound `senderId` against that set before forwarding admin commands.
|
||||
The command lists are hardcoded in the agent-runner. Admin verification happens host-side before the message ever reaches the container: `src/command-gate.ts` queries `user_roles` (owner / global admin / scoped-admin-of-this-agent-group) and either passes the message through, drops it, or routes it elsewhere. The container has no notion of admin identity — no env var, no DB query, no per-message check.
|
||||
|
||||
### Recurring Tasks
|
||||
|
||||
|
||||
@@ -1,278 +0,0 @@
|
||||
# NanoClaw Checklist
|
||||
|
||||
Status: [x] done, [~] partial, [ ] not started
|
||||
|
||||
---
|
||||
|
||||
## Core Architecture
|
||||
|
||||
- [x] Session DB replaces IPC (messages_in / messages_out as sole IO)
|
||||
- [x] Central DB (agent groups, messaging groups, sessions, routing)
|
||||
- [x] Host sweep (stale detection via heartbeat file, retry with backoff, recurrence scheduling)
|
||||
- [x] Active delivery polling (1s for running sessions)
|
||||
- [x] Sweep delivery polling (60s across all sessions)
|
||||
- [x] Container runner with session DB mounting
|
||||
- [x] Per-session container lifecycle and idle timeout
|
||||
- [ ] Replace hard Idle and Timeout with work aware prompts to user to kill stuck processes
|
||||
- [x] Session resume (sessionId + resumeAt across queries)
|
||||
- [x] Graceful shutdown (SIGTERM/SIGINT handlers)
|
||||
- [x] Orphan container cleanup on startup
|
||||
|
||||
## Agent Runner (Container)
|
||||
|
||||
- [x] Poll loop (pending messages, status transitions, idle detection)
|
||||
- [x] Concurrent follow-up polling while agent is thinking
|
||||
- [x] Message formatter (chat, task, webhook, system kinds)
|
||||
- [x] Command categorization (admin, filtered, passthrough)
|
||||
- [x] Transcript archiving (pre-compact hook)
|
||||
- [x] XML message formatting with sender, timestamp
|
||||
- [~] Media handling inbound (native files support for claude)
|
||||
|
||||
## Agent Providers
|
||||
|
||||
- [x] Claude provider (Agent SDK, tool allowlist, message stream, session resume)
|
||||
- [x] Mock provider (testing)
|
||||
- [x] Provider factory
|
||||
- [ ] Codex provider
|
||||
- [x] OpenCode provider
|
||||
|
||||
## Channel Adapters
|
||||
|
||||
- [x] Channel adapter interface (setup, deliver, teardown, typing)
|
||||
- [x] Chat SDK bridge (generic, works with any Chat SDK adapter)
|
||||
- [x] Chat SDK SQLite state adapter (KV, subscriptions, locks, lists)
|
||||
- [x] Discord via Chat SDK
|
||||
- [~] Slack via Chat SDK (adapter + skill written, not tested)
|
||||
- [x] Telegram via Chat SDK (E2E verified: inbound, routing, typing, delivery)
|
||||
- [~] Microsoft Teams via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Google Chat via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Linear via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] GitHub via Chat SDK (adapter + skill written, not tested)
|
||||
- [x] WhatsApp Cloud API via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Resend (email) via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Matrix via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Webex via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] iMessage via Chat SDK (adapter + skill written, not tested)
|
||||
- [x] Backward compatibility with native channels (old adapters still work)
|
||||
- [x] Channel barrel wired (src/index.ts imports barrel, skills uncomment)
|
||||
- [x] Setup flow wired to channels (channel skills + /manage-channels for registration + verify.ts checks all tokens)
|
||||
- [x] Channel Info metadata in each channel skill (type, terminology, how-to-find-id, isolation defaults)
|
||||
- [x] /manage-channels skill (wire channels to agent groups with three isolation levels)
|
||||
- [x] /init-first-agent skill (standalone first-agent bootstrap; walks the operator through channel pick → identity lookup → DM platform_id resolution → wire → welcome DM; fallback to telegram pair-code or "DM the bot first" lookup for channels without cold DM)
|
||||
- [x] Cold-DM infrastructure — `ChannelAdapter.openDM?(handle)` optional method, resolved via Chat SDK `chat.openDM` for resolution-required channels (Discord, Slack, Teams, Webex, gChat) and fall-through to the handle directly for direct-addressable channels (Telegram, WhatsApp, iMessage, Matrix, Resend). `src/user-dm.ts::ensureUserDm` caches every resolution in `user_dms` so subsequent cold DMs are a DB read.
|
||||
- [x] Agent-shared session mode (cross-channel shared sessions, e.g. GitHub + Slack)
|
||||
- [x] Auto-onboarding on channel registration (/welcome skill triggered on first wiring)
|
||||
- [ ] Wire different chat modes - mentions, whitelist, approve, etc
|
||||
|
||||
## Chat-First Setup Flow
|
||||
|
||||
**Goal:** get the user out of Claude Code and into their messaging app as quickly as possible, then enable every part of customization, configuration, and setup from inside the chat app. Claude Code is the bootstrap, not the home.
|
||||
|
||||
- [~] Minimum-viable bootstrap in Claude Code: install deps, pick one channel, authenticate it, wire it to a default agent group, hand off — nothing else required before the user can leave Claude Code. `/setup` handles deps/auth, `/init-first-agent` handles the first-agent wiring + welcome DM. Still TODO: single top-level entrypoint that composes both, and a true "nothing else required" handoff (today `/setup` still runs through `/manage-channels` for additional channels).
|
||||
- [~] Post-handoff welcome message in the chat app guides the user through remaining setup (channels, skills, integrations, memory, scheduling, etc.) — `/init-first-agent` stages a `kind:'chat'` / `sender:'system'` welcome prompt that the agent DMs back to the operator via the normal delivery path. Current prompt just introduces the agent; TODO: expand the prompt (or follow-up flow) to walk through remaining setup tasks from within the chat.
|
||||
- [ ] Add more channels from chat (currently requires returning to Claude Code to run `/add-*` skills)
|
||||
- [ ] Self-register agent into a new chat room from chat: user gives the agent a channel/group name + approval, and the agent joins via the underlying adapter (e.g. Baileys for WhatsApp), wires the room to an agent group, and posts a first "hi, I'm here" message — no manual invite, no `/add-*` skill, no terminal
|
||||
- [ ] Authenticate channels from chat (OAuth/token entry via cards, no terminal required)
|
||||
- [ ] Add credentials / secrets to the OneCLI vault from chat via rich card (agent collects API keys, OAuth tokens, and other secrets through a card flow and writes them into the vault — no `.env` editing, no terminal)
|
||||
- [ ] Wire channels to agent groups from chat (today lives in `/manage-channels` Claude Code skill — port to in-chat flow with isolation-level question cards)
|
||||
- [ ] Create new agent groups from chat (`create_agent` exists — expose via user-facing flow, not just agent-called tool)
|
||||
- [ ] Edit agent group CLAUDE.md / instructions from chat
|
||||
- [ ] Install / uninstall / configure skills from chat (see Skills & Marketplace section)
|
||||
- [ ] Install / configure MCP servers from chat (see Skills & Marketplace section)
|
||||
- [ ] Install packages from chat (today agent can request install_packages — expose a direct user-facing "install X" flow)
|
||||
- [ ] Manage scheduled tasks from chat (list, pause, cancel, edit recurrence)
|
||||
- [ ] Manage destinations from chat (list, rename, revoke)
|
||||
- [ ] Manage permissions from chat (admin list, role assignment, approval policies)
|
||||
- [ ] Trigger /setup, /debug, /customize, /migrate-nanoclaw from chat (today all require Claude Code)
|
||||
- [ ] View and edit memory from chat
|
||||
- [ ] Visualize current setup from chat (ties into Container Skills: installation diagram)
|
||||
- [ ] Export / share setup from chat (ties into Container Skills: end-of-setup diagram + share)
|
||||
- [ ] Fallback to Claude Code only when a change requires a code edit the agent can't self-apply (and even then, agent should offer to open Claude Code on the user's behalf)
|
||||
|
||||
## Product Focus
|
||||
|
||||
**North star:** prioritize skills, flows, and custom setups. Platform work (channels, routing, session DBs, approval flows, MCP tools) is plumbing — it should reach a "boring and reliable" state and then stop absorbing attention. The interesting surface area is what users can *build on top* of that plumbing: skills that add capabilities, conversational flows that orchestrate those skills, and custom per-user setups that compose channels/agents/skills/memory into something personal.
|
||||
|
||||
- [ ] Every new feature request should be answered first with "is this a skill?" before being answered with "is this a platform change?"
|
||||
- [ ] Skills should be the primary extension mechanism users and agents reach for — adding, removing, browsing, editing, debugging
|
||||
- [ ] Flows (multi-step interactive sequences: setup, onboarding, migration, customize, debug) should be authorable as skills rather than hardcoded into the platform
|
||||
- [ ] Custom setups (diverging from defaults: multiple agents, cross-channel routing, per-group memory, specialist sub-agents) should be composable from existing primitives without touching core platform code
|
||||
- [ ] Platform-level work gets budgeted against the question: "does this unblock a class of skills/flows/setups that's otherwise impossible?"
|
||||
|
||||
## Routing
|
||||
|
||||
- [x] Inbound routing (platform ID + thread ID -> agent group -> session)
|
||||
- [x] Auto-create messaging group on first message
|
||||
- [x] Session resolution (shared vs per-thread modes)
|
||||
- [x] Message writing to session DB with seq numbering
|
||||
- [x] Container waking on new message
|
||||
- [x] Typing indicator triggered on message route
|
||||
- [~] Trigger rule matching (router picks highest-priority agent, regex/mention matching TODO)
|
||||
|
||||
## Rich Messaging
|
||||
|
||||
- [x] Interactive cards with buttons (ask_user_question)
|
||||
- [x] Native platform rendering (Discord embeds, buttons)
|
||||
- [x] Message editing
|
||||
- [x] Emoji reactions
|
||||
- [x] File sending from agent (outbox -> delivery)
|
||||
- [x] File upload delivery (buffer-based via adapter)
|
||||
- [x] Markdown formatting
|
||||
- [~] Formatted /usage, /context, /cost output (commands pass through, no rich card formatting)
|
||||
- [ ] Context window visibility: show position in context, approaching compaction, when compaction happens, post-compaction state
|
||||
- [ ] Threading and replies support
|
||||
- [ ] Auto-compact on idle before cache expires
|
||||
|
||||
## MCP Tools (Container)
|
||||
|
||||
- [x] send_message (routes via named destinations; `to` field resolved against agent's local map)
|
||||
- [x] send_file (copy to outbox, write messages_out)
|
||||
- [x] edit_message (routed via destinations)
|
||||
- [x] add_reaction (routed via destinations)
|
||||
- [x] send_card
|
||||
- [x] ask_user_question (blocking poll for response)
|
||||
- [x] schedule_task (with process_after and recurrence)
|
||||
- [x] list_tasks
|
||||
- [x] cancel_task / pause_task / resume_task
|
||||
- [x] create_agent (any agent, creates agent group + folder + bidirectional destinations; host re-normalizes the name, deduplicates folder, path-traversal guarded)
|
||||
- [x] install_packages (apt/npm, owner/admin approval required via `pickApprover`, strict name validation)
|
||||
- [x] add_mcp_server (owner/admin approval required via `pickApprover`)
|
||||
- [x] request_rebuild (rebuilds per-agent-group Docker image)
|
||||
|
||||
## Scheduling
|
||||
|
||||
- [x] One-shot scheduled messages (process_after / deliver_after)
|
||||
- [x] Recurring tasks via cron expressions
|
||||
- [x] Host sweep picks up due messages and advances recurrence
|
||||
- [x] Scheduled outbound messages (no container wake needed)
|
||||
- [ ] Pre-agent scripts (formatter references scriptOutput but no execution logic)
|
||||
|
||||
## Permissions and Approval Flows
|
||||
|
||||
- [x] User-level privilege model — `users` + `user_roles` (owner / admin, global or scoped to an agent group). Replaces the old `agent_groups.is_admin` / `messaging_groups.admin_user_id` coupling. See `src/db/users.ts`, `src/db/user-roles.ts`, `src/access.ts`.
|
||||
- [x] Admin-only command filtering in container — host passes `NANOCLAW_ADMIN_USER_IDS` (owners + global admins + scoped admins for the agent group) to the agent-runner; `poll-loop.ts` gates slash commands against that set.
|
||||
- [x] Approval routing — `pickApprover` (scoped admin → global admin → owner, dedup) + `pickApprovalDelivery` (first reachable, same-channel-kind tie-break); delivery lands in the approver's DM via `ensureUserDm` / `user_dms` cache. See `src/access.ts`, `src/onecli-approvals.ts`.
|
||||
- [x] Per-messaging-group unknown-sender gating — `messaging_groups.unknown_sender_policy` (`strict` | `request_approval` | `public`), enforced in `src/router.ts`.
|
||||
- [x] Approval flow (sensitive action -> card to admin -> approve/reject -> execute) — `pending_approvals` table, `requestApproval()` helper, reuses interactive card infra
|
||||
- [x] Agent requests dependency/package install (install_packages, admin approval, rebuild on approval)
|
||||
- [x] Self-modification — direct tools:
|
||||
- [x] install_packages (apt/npm, admin approval, name validation both sides, max 20 per request)
|
||||
- [x] add_mcp_server (admin approval)
|
||||
- [x] request_rebuild (builds per-agent-group Docker image with approved packages)
|
||||
- [x] Fire-and-forget model (write request, return immediately; chat notification on approval; container killed so next wake picks up new config/image)
|
||||
- [~] OneCLI integration for human-loop approvals on credentialed requests (agent touching a credentialed resource → OneCLI gates → approval card to admin → OneCLI releases credential) — SDK 0.3.1 `configureManualApproval` wired into host, routes to admin via existing `pending_approvals` infra
|
||||
- [ ] Tunneled OneCLI dashboard for credential addition (Telegram Mini Apps aside, iMessage without Apple Business Register, Matrix, email). Signed short-lived URL → browser form served by OneCLI at 10254 → tunnel via cloudflare durable object. Value never touches the chat surface.
|
||||
- [ ] Self-modification via direct source edits — planned draft/activate flow: RO baseline mount at `/app/src`, RW draft at `/workspace/src-draft`, atomic snapshot into `pending`, admin approval, `cp -a` into baseline, restart + deadman rollback. Unifies runner src, host src, migrations, package.json, container config through one edit path. Collapses the abandoned `create_dev_agent`/`request_swap` dev-agent-in-worktree approach.
|
||||
|
||||
## Named Destinations + ACL
|
||||
|
||||
- [x] `agent_destinations` table (agent_group_id, local_name, target_type, target_id) — migration 004
|
||||
- [x] Per-agent local-name routing map (channels and peer agents referenced by local names)
|
||||
- [x] Destinations stored in inbound.db `destinations` table (moved from JSON file in `b591d7c`) — single source of truth, no separate file
|
||||
- [x] Host writes the destination map into inbound.db before every container wake; container queries it live on every lookup so admin changes take effect mid-session
|
||||
- [x] Container loads map at startup, appends system-prompt addendum listing destinations + `<message to="name">` syntax
|
||||
- [x] Agent main output parsed for `<message to="...">` blocks; `<internal>...</internal>` treated as scratchpad
|
||||
- [x] Host re-validates every outbound route via `hasDestination()` — unauthorized drops logged
|
||||
- [x] Inbound formatter adds `from="name"` via reverse-lookup (consistent namespace both directions)
|
||||
- [x] Single-destination shortcut — agents with one destination don't need `<message>` wrapping
|
||||
- [x] Backfill from existing `messaging_group_agents` on migration
|
||||
- [x] Removed `NANOCLAW_PLATFORM_ID` / `CHANNEL_TYPE` / `THREAD_ID` env-var routing entirely
|
||||
|
||||
## Agent-to-Agent Communication
|
||||
|
||||
- [x] Host delivery to target agent's session DB (`channel_type='agent'` routing in `src/delivery.ts`)
|
||||
- [x] Agent spawning a new sub-agent (`create_agent` MCP tool, available to any agent, path-traversal guarded)
|
||||
- [x] Dynamic agent group creation (folder + optional CLAUDE.md at runtime)
|
||||
- [x] Internal-only agents (agents created without a channel attached)
|
||||
- [x] Permission delegation from parent to child (bidirectional destination rows inserted at creation)
|
||||
- [x] Bidirectional routing via inherited routing context; sender info enriched on the target side
|
||||
- [ ] Specialist sub-agents (browser agent, dev agent — user's agent delegates with request/approval)
|
||||
- [ ] Browser agent with per-destination permissions between main agent and browser agent (main requests navigation/interaction; browser agent executes in isolated container)
|
||||
- [ ] Sanitization of browser agent responses before handing back to main agent (strip scripts, inline images, untrusted HTML; prevent prompt injection from web content)
|
||||
- [ ] Same permission + sanitization model for any sub-agent that accesses sensitive data sources (files, DBs, third-party APIs)
|
||||
|
||||
## In-Chat Agent Management
|
||||
|
||||
- [x] /clear (resets session)
|
||||
- [x] /compact (triggers context compaction)
|
||||
- [~] /context (passes through, no rich formatting)
|
||||
- [~] /usage (passes through, no rich formatting)
|
||||
- [~] /cost (passes through, no rich formatting)
|
||||
- [ ] Smooth session transitions: load context into new sessions, solve cold start problem
|
||||
- [x] MCP/package installation from chat
|
||||
- [ ] Browse MCP marketplace / skills repository from chat
|
||||
|
||||
## Skills & Marketplace
|
||||
|
||||
- [ ] Install skills from chat (agent requests, admin approves, skill dropped into container skills dir)
|
||||
- [ ] Scan skills before install (lint SKILL.md, sandbox-check shell commands, require approval for network/FS-heavy skills)
|
||||
- [ ] Scan marketplace npm packages before install (supply-chain check, typo-squat detection, known-bad list)
|
||||
- [ ] MCP server marketplace — discover, preview, install
|
||||
- [ ] Browse skills / MCP marketplace from chat (cards with search, preview, install)
|
||||
- [ ] Local voice transcription skill — "just works" install flow: when the user sends a voice message and no transcription backend is installed, the agent asks once ("Install local voice transcription?"), and on approval the skill installs a fully-local speech-to-text model (no cloud calls). Subsequent voice messages transcribe automatically.
|
||||
- [ ] Fully local NanoClaw — OpenCode + Gemma 4 as the agent provider instead of Claude Code, so an entire install can run with zero cloud inference. Requires wiring OpenCode as an agent provider (see Agent Providers) and a setup path that picks local models, pulls weights, and verifies everything runs offline.
|
||||
|
||||
## Container Skills
|
||||
|
||||
Container skills live inside agent containers at runtime (`container/skills/`) and are loaded into every agent session. These are distinct from feature/operational skills that ship with the host.
|
||||
|
||||
- [ ] Customize container skill — agent-driven customization flow (add channel, integration, behavior change) usable from inside any agent session, not just the main repo
|
||||
- [ ] Debug container skill — inspect logs, session DB, MCP server state, container env, recent errors from inside the agent
|
||||
- [ ] Build-system container skills:
|
||||
- [ ] Karpathy LLM Wiki builder (agent scaffolds a persistent wiki knowledge base for a group)
|
||||
- [ ] Generic build-system framework for agent-authored sub-systems
|
||||
- [ ] NanoClaw installation diagram skill — agent generates a visual diagram of the user's current setup (agent groups, channels, wirings, destinations, sub-agents, installed packages/MCP servers)
|
||||
- [ ] Video replay skill — generate Remotion (or similar) videos that replay chat flows and sessions, referencing good UI patterns to produce shareable clips
|
||||
- [ ] Excitement trigger skill — detects when the user expresses excitement about the agent's capabilities or their setup, and proactively encourages generating a diagram + sharing it
|
||||
- [ ] End-of-migration diagram skill — at the end of `/migrate-nanoclaw` (or any migration flow), agent generates a visual diagram of the resulting setup and suggests sharing
|
||||
- [ ] End-of-setup diagram skill — at the end of first-time `/setup`, agent generates a visual diagram and suggests sharing (merges the old "Generate visual diagram of customized instance at end of setup" line from Channel Adapters)
|
||||
|
||||
## Webhook Ingestion
|
||||
|
||||
- [ ] Generic webhook endpoint for external events
|
||||
- [ ] GitHub webhook handling
|
||||
- [ ] CI/CD notification handling
|
||||
- [ ] Webhook -> messages_in routing
|
||||
|
||||
## System Actions
|
||||
|
||||
- [ ] register_group from inside agent
|
||||
- [ ] reset_session from inside agent
|
||||
- [ ] Delivery failures should round-trip back to the agent as system messages so it can decide how to recover (retry as plain text, simplify, give up), with a hard retry cap + poison-pill backstop in delivery.ts to keep the queue healthy
|
||||
|
||||
## Integrations
|
||||
|
||||
- [x] Vercel CLI integration in setup process
|
||||
- [x] Skills for deploying and managing Vercel websites from chat
|
||||
- [ ] Office 365 integration (create/edit documents with inline suggestions)
|
||||
|
||||
## Memory
|
||||
|
||||
- [ ] Shared memory with approval flow (write to global memory requires admin approval)
|
||||
- [ ] Agent memory system skills — skills for building and managing memory systems for an agent: archive/index large collections of files and data, then expose a memory interface the agent can query and update (e.g. QMD-style systems)
|
||||
|
||||
## Migration
|
||||
|
||||
- [ ] Custom skill/code porting
|
||||
- [ ] OneCLI migration check — determine if existing installs need OneCLI re-init (credentials re-scoped to new `agent_group.id` identifier, new SDK version, approval handler registered). If needed, add a migration step to `/update-nanoclaw` or a dedicated skill.
|
||||
|
||||
## Testing
|
||||
|
||||
- [x] DB layer tests (agent groups, messaging groups, sessions, pending questions)
|
||||
- [x] Channel registry tests
|
||||
- [x] Poll loop / formatter tests
|
||||
- [x] Integration test (container agent-runner)
|
||||
- [x] Host core tests
|
||||
- [ ] End-to-end flow tests (message in -> agent -> message out -> delivery)
|
||||
- [ ] Delivery polling tests
|
||||
- [ ] Host sweep tests (stale detection, recurrence)
|
||||
- [ ] Multi-channel integration tests
|
||||
|
||||
## Rollout
|
||||
|
||||
- [ ] Internal testing across all channels
|
||||
- [ ] Migration skill built and tested
|
||||
- [ ] PR factory migrated as validation
|
||||
- [ ] Blog post / announcement
|
||||
- [ ] Video demos of key flows
|
||||
- [ ] Vercel coordination
|
||||
+1
-1
@@ -201,7 +201,7 @@ Access layer: `src/db/agent-destinations.ts`.
|
||||
|
||||
Two workflows share this table:
|
||||
|
||||
- **Session-bound MCP approvals** — `install_packages`, `request_rebuild`, `add_mcp_server`. `session_id` is set.
|
||||
- **Session-bound MCP approvals** — `install_packages`, `add_mcp_server`. `session_id` is set.
|
||||
- **OneCLI credential approvals** — `session_id` may be NULL; `agent_group_id` + `channel_type` + `platform_id` route the admin card.
|
||||
|
||||
```sql
|
||||
|
||||
@@ -1,221 +0,0 @@
|
||||
# Module Contract
|
||||
|
||||
This doc is the authoritative reference for how core and modules connect. Everything downstream — extraction PRs, install skills, module authors — keys off these signatures and defaults. See [REFACTOR_PLAN.md](../REFACTOR_PLAN.md) for the broader plan; this doc is the narrow interface spec.
|
||||
|
||||
## Principles
|
||||
|
||||
- Core runs standalone (modulo default modules — see tiers below). The optional-module portion of the `src/modules/index.ts` barrel can be empty and NanoClaw still routes messages in and delivers responses out.
|
||||
- Optional modules are independent. No optional module imports from another optional module. Cross-module coordination goes through a core registry (delivery action, response handler, etc.).
|
||||
- Registries exist only when multiple modules plug into the same decision point. Single-consumer integrations use skill edits (`MODULE-HOOK` markers) or stay inline with `sqlite_master` guards.
|
||||
- Removing an optional module = delete files + remove barrel imports + revert any `MODULE-HOOK` content. Migration files stay (data is preserved). Removing a default module is more invasive: it requires editing the core files that import from it.
|
||||
|
||||
## Module taxonomy
|
||||
|
||||
Three categories. All three live under `src/modules/` (or equivalent adapter dirs) with the same folder layout; the distinction is about **shipping** and **who can depend on them**.
|
||||
|
||||
### 1. Default modules
|
||||
|
||||
Ship with `main` in `src/modules/`. Imported by the default `src/modules/index.ts` barrel from day one. They are not really core — they live under `src/modules/` specifically to signal "not really core, rippable if needed" — but they're always present on a `main` install. Core imports from them directly. No hook, no registry indirection for the exports themselves.
|
||||
|
||||
Current: `typing`, `mount-security`.
|
||||
|
||||
### 2. Optional modules
|
||||
|
||||
Live on the `modules` branch. Installed via `/add-<name>` skills that cherry-pick files. Register into core via one of the four registries (or `MODULE-HOOK` skill edits). Core and other optional modules must not statically import an optional module's code.
|
||||
|
||||
Current: `interactive`, `approvals`, `scheduling`, `permissions`. Pending: `agent-to-agent`.
|
||||
|
||||
### 3. Channel adapters
|
||||
|
||||
Live on the `channels` branch, installed via `/add-<channel>` skills. Not covered by this contract; they use the pre-existing `ChannelAdapter` interface and `registerChannelAdapter()`.
|
||||
|
||||
## Dependency rule
|
||||
|
||||
```
|
||||
core ← default modules ← optional modules
|
||||
```
|
||||
|
||||
- **Core** may import from core and from default modules.
|
||||
- **Default modules** may import from core and from other default modules. They must not import from optional modules.
|
||||
- **Optional modules** may import from core and from default modules. They must not import from each other.
|
||||
|
||||
Peer-to-peer coupling between optional modules goes through a core registry — see "The four registries" below. This keeps the module dependency graph a DAG and install order irrelevant.
|
||||
|
||||
### Known transitional violations
|
||||
|
||||
- `src/access.ts` (core) imports from `src/modules/permissions/` (optional). Shim left from PR #5; resolved in the planned approvals re-tier (PR #7) which moves approver-picking into a new default `approvals-primitive` module that may then depend on permissions however it likes — at which point `src/access.ts` ceases to exist.
|
||||
|
||||
## The four registries
|
||||
|
||||
Each registry has an explicit default for when no module registers. Core must run when all four are empty.
|
||||
|
||||
### 1. Delivery action handlers
|
||||
|
||||
```typescript
|
||||
// src/delivery.ts
|
||||
type ActionHandler = (
|
||||
content: Record<string, unknown>,
|
||||
session: Session,
|
||||
inDb: Database.Database,
|
||||
) => Promise<void>;
|
||||
|
||||
export function registerDeliveryAction(action: string, handler: ActionHandler): void;
|
||||
```
|
||||
|
||||
**Purpose:** system-kind outbound messages (`msg.kind === 'system'`) carry an `action` string. Core dispatches to the registered handler.
|
||||
|
||||
**Default when action is unknown:** log `"Unknown system action"` at `warn` and return. Message is still marked delivered (it was consumed by the host, not sent to a channel).
|
||||
|
||||
**Current consumers:** scheduling (5 actions — `schedule_task`, `cancel_task`, `pause_task`, `resume_task`, `update_task`), approvals (3 actions — `install_packages`, `request_rebuild`, `add_mcp_server`), agent-to-agent (`create_agent`, and the agent-routing branch keyed as a pseudo-action `agent_route`).
|
||||
|
||||
### 2. Router sender resolver + access gate
|
||||
|
||||
Two separate setters, called at different points in `routeInbound`. Preserves the pre-refactor ordering: sender-upsert side effects fire even when the message is ultimately dropped by wiring or trigger rules.
|
||||
|
||||
```typescript
|
||||
// src/router.ts
|
||||
type SenderResolverFn = (event: InboundEvent) => string | null;
|
||||
|
||||
export function setSenderResolver(fn: SenderResolverFn): void;
|
||||
|
||||
type AccessGateResult =
|
||||
| { allowed: true }
|
||||
| { allowed: false; reason: string };
|
||||
|
||||
type AccessGateFn = (
|
||||
event: InboundEvent,
|
||||
userId: string | null,
|
||||
mg: MessagingGroup,
|
||||
agentGroupId: string,
|
||||
) => AccessGateResult;
|
||||
|
||||
export function setAccessGate(fn: AccessGateFn): void;
|
||||
```
|
||||
|
||||
**Call order in `routeInbound`:**
|
||||
1. Resolve messaging group.
|
||||
2. **Sender resolver** (if set). Permissions upserts the users row here so the record exists even if agent resolution drops the message.
|
||||
3. Resolve wired agents; `no_agent_wired` → record + drop. (Core writes the dropped_messages row.)
|
||||
4. Pick agent by trigger rules; `no_trigger_match` → record + drop.
|
||||
5. **Access gate** (if set). On refusal it writes its own `dropped_messages` row keyed by policy reason.
|
||||
|
||||
**Defaults when unset:** resolver returns null; gate defaults to `{ allowed: true }`. Every message routes through, no users table is needed, downstream tolerates `userId=null`.
|
||||
|
||||
**Current consumer:** permissions module (registers both).
|
||||
|
||||
**Not registries, setters.** There is one sender and one access decision per inbound message and one module that owns both. Calling `setSenderResolver` / `setAccessGate` twice overwrites; core does not iterate.
|
||||
|
||||
### 3. Response dispatcher
|
||||
|
||||
```typescript
|
||||
// src/index.ts (or src/response-dispatch.ts if it grows)
|
||||
interface ResponsePayload {
|
||||
questionId: string;
|
||||
value: string;
|
||||
userId: string | null;
|
||||
channelType: string;
|
||||
platformId: string;
|
||||
threadId: string | null;
|
||||
}
|
||||
|
||||
type ResponseHandler = (payload: ResponsePayload) => Promise<boolean>;
|
||||
|
||||
export function registerResponseHandler(handler: ResponseHandler): void;
|
||||
```
|
||||
|
||||
**Purpose:** button-click / question responses arrive via the channel adapter's `onAction` callback. Core iterates registered handlers in registration order. The first one that returns `true` claims the response.
|
||||
|
||||
**Default when empty:** log `"Unclaimed response"` at `warn` and drop.
|
||||
|
||||
**Current consumers:** interactive (matches `pending_questions`), approvals (matches `pending_approvals`). The two tables have disjoint `question_id` / `approval_id` namespaces in practice (`q-*` vs `appr-*`), so first-match-wins is safe.
|
||||
|
||||
### 4. Container MCP tool self-registration
|
||||
|
||||
```typescript
|
||||
// container/agent-runner/src/mcp-tools/server.ts
|
||||
export function registerTools(tools: McpToolDefinition[]): void;
|
||||
```
|
||||
|
||||
**Purpose:** each tool module calls `registerTools([...])` at import time. The MCP server uses whatever was registered.
|
||||
|
||||
**Default:** only `mcp-tools/core.ts` (`send_message`) registered.
|
||||
|
||||
**Current consumers:** all container-side modules (scheduling, interactive, agents, self-mod).
|
||||
|
||||
## Skill edits to core
|
||||
|
||||
For one-off integrations with a single consumer, install skills edit core directly between `MODULE-HOOK` markers. No registry.
|
||||
|
||||
Marker format:
|
||||
|
||||
```typescript
|
||||
// MODULE-HOOK:<module>-<site>:start
|
||||
// MODULE-HOOK:<module>-<site>:end
|
||||
```
|
||||
|
||||
The skill inserts between markers on install and clears between them on uninstall. Markers live in core from day one (empty until a skill fills them).
|
||||
|
||||
**Current uses:**
|
||||
|
||||
- `src/host-sweep.ts` → `MODULE-HOOK:scheduling-recurrence` — call to scheduling module's `handleRecurrence`.
|
||||
- `container/agent-runner/src/poll-loop.ts` → `MODULE-HOOK:scheduling-pre-task` — call to scheduling module's `applyPreTaskScripts`.
|
||||
|
||||
**Promotion rule:** if a third consumer appears for any marker, promote to a registry.
|
||||
|
||||
## Guarded inline (core)
|
||||
|
||||
Some code stays in core but references module-owned tables. These use `sqlite_master` checks to degrade cleanly when the owning module isn't installed.
|
||||
|
||||
| Site | Owning module | Fallback |
|
||||
|------|---------------|----------|
|
||||
| `container-runner.ts` admin-ID query (`user_roles`, `agent_group_members`) | permissions | returns `[]` |
|
||||
| `container-runner.ts` `writeDestinations` (`agent_destinations`) | agent-to-agent | no-op |
|
||||
| `delivery.ts` channel-permission check (`agent_destinations`) | agent-to-agent | permit (origin-chat always OK) |
|
||||
| `delivery.ts` `createPendingQuestion` (`pending_questions`) | interactive | no-op (log warning) |
|
||||
|
||||
`container/agent-runner/src/formatter.ts` has a related non-DB fallback: when `NANOCLAW_ADMIN_USER_IDS` is empty, every sender is treated as admin (permissionless mode). This is the one-line change from the current deny-all behavior.
|
||||
|
||||
## Migrations
|
||||
|
||||
All migrations live in `src/db/migrations/` as TypeScript files exporting a `Migration` object:
|
||||
|
||||
```typescript
|
||||
export interface Migration {
|
||||
version: number;
|
||||
name: string;
|
||||
up: (db: Database.Database) => void;
|
||||
}
|
||||
```
|
||||
|
||||
The barrel `src/db/migrations/index.ts` imports each and lists them in an ordered array.
|
||||
|
||||
**Uniqueness key is `name`, not `version`.** The migrator applies any migration whose `name` isn't in `schema_version`. Version stays as an ordering hint; integer collisions across modules are allowed.
|
||||
|
||||
**Module migration naming:**
|
||||
|
||||
- File: `src/db/migrations/module-<module>-<short>.ts`
|
||||
- `Migration.name`: `'<module>-<short>'` (e.g. `'approvals-pending-approvals'`)
|
||||
|
||||
**Uninstall behavior:** migration files and barrel entries stay. Tables persist across reinstalls. No down migrations.
|
||||
|
||||
## What a registry-based module provides
|
||||
|
||||
Each `src/modules/<name>/` module must supply:
|
||||
|
||||
- `index.ts` — imported by `src/modules/index.ts` for side-effect registration (calls `registerDeliveryAction` / `setInboundGate` / `registerResponseHandler` at module load time).
|
||||
- `project.md` — appended to project `CLAUDE.md` by the install skill. Describes module architecture for anyone reading the codebase.
|
||||
- `agent.md` — appended to `groups/global/CLAUDE.md` by the install skill. Describes the module's tools for the agent.
|
||||
- Migration file in `src/db/migrations/` if the module owns any tables.
|
||||
- Barrel entry in `src/db/migrations/index.ts` for that migration.
|
||||
|
||||
Optionally:
|
||||
|
||||
- Container-side additions to `container/agent-runner/src/mcp-tools/<name>.ts` that call `registerTools([...])`, with a barrel entry in `container/agent-runner/src/mcp-tools/index.ts`.
|
||||
- `MODULE-HOOK` edits to specific core files, applied by the install skill.
|
||||
|
||||
## What a module must not do
|
||||
|
||||
- Import from another module.
|
||||
- Write to core-owned tables (`sessions`, `agent_groups`, `messaging_groups`, `schema_version`, etc.) outside of migrations.
|
||||
- Depend on a specific channel adapter being installed.
|
||||
- Break core behavior when unloaded. If a module's absence leaves a core feature non-functional, that feature belongs in core, not the module.
|
||||
@@ -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/<agent-group-id>/.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/<folder>/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
|
||||
@@ -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/<name>.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/<step>.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.
|
||||
@@ -0,0 +1,504 @@
|
||||
;;; nanoclaw.el --- Emacs interface for NanoClaw AI assistant -*- lexical-binding: t -*-
|
||||
|
||||
;; Author: NanoClaw
|
||||
;; Version: 0.1.0
|
||||
;; Package-Requires: ((emacs "27.1"))
|
||||
;; Keywords: ai, assistant, chat
|
||||
;;
|
||||
;; Vanilla Emacs (init.el):
|
||||
;; (load-file "~/src/nanoclaw/emacs/nanoclaw.el")
|
||||
;; (global-set-key (kbd "C-c n c") #'nanoclaw-chat)
|
||||
;; (global-set-key (kbd "C-c n o") #'nanoclaw-org-send)
|
||||
;;
|
||||
;; Spacemacs (~/.spacemacs, in dotspacemacs/user-config):
|
||||
;; (load-file "~/src/nanoclaw/emacs/nanoclaw.el")
|
||||
;; (spacemacs/set-leader-keys "aNc" #'nanoclaw-chat)
|
||||
;; (spacemacs/set-leader-keys "aNo" #'nanoclaw-org-send)
|
||||
;;
|
||||
;; Doom Emacs (config.el):
|
||||
;; (load (expand-file-name "~/src/nanoclaw/emacs/nanoclaw.el"))
|
||||
;; (map! :leader
|
||||
;; :prefix ("N" . "NanoClaw")
|
||||
;; :desc "Chat buffer" "c" #'nanoclaw-chat
|
||||
;; :desc "Send org" "o" #'nanoclaw-org-send)
|
||||
;; ;; Evil users: teach evil about the C-c C-c send binding
|
||||
;; (after! evil
|
||||
;; (evil-define-key '(normal insert) nanoclaw-chat-mode-map
|
||||
;; (kbd "C-c C-c") #'nanoclaw-chat-send))
|
||||
|
||||
;;; Code:
|
||||
|
||||
(require 'cl-lib)
|
||||
(require 'url)
|
||||
(require 'json)
|
||||
(require 'org)
|
||||
|
||||
;; ---------------------------------------------------------------------------
|
||||
;; Customization
|
||||
|
||||
(defgroup nanoclaw nil
|
||||
"NanoClaw AI assistant interface."
|
||||
:group 'tools
|
||||
:prefix "nanoclaw-")
|
||||
|
||||
(defcustom nanoclaw-host "localhost"
|
||||
"Hostname where NanoClaw is running."
|
||||
:type 'string
|
||||
:group 'nanoclaw)
|
||||
|
||||
(defcustom nanoclaw-port 8766
|
||||
"Port for the NanoClaw Emacs channel HTTP server."
|
||||
:type 'integer
|
||||
:group 'nanoclaw)
|
||||
|
||||
(defcustom nanoclaw-auth-token nil
|
||||
"Bearer token for NanoClaw authentication (matches EMACS_AUTH_TOKEN in .env).
|
||||
Leave nil if EMACS_AUTH_TOKEN is not set."
|
||||
:type '(choice (const nil) string)
|
||||
:group 'nanoclaw)
|
||||
|
||||
(defcustom nanoclaw-poll-interval 1.5
|
||||
"Seconds between response polls when waiting for a reply."
|
||||
:type 'number
|
||||
:group 'nanoclaw)
|
||||
|
||||
(defcustom nanoclaw-agent-name "Andy"
|
||||
"Display name for the NanoClaw agent (matches ASSISTANT_NAME in .env)."
|
||||
:type 'string
|
||||
:group 'nanoclaw)
|
||||
|
||||
(defcustom nanoclaw-convert-to-org t
|
||||
"When non-nil, convert agent responses to org-mode format.
|
||||
Uses pandoc when available; falls back to regex substitutions."
|
||||
:type 'boolean
|
||||
:group 'nanoclaw)
|
||||
|
||||
(defcustom nanoclaw-timestamp-format "%H:%M"
|
||||
"Format string for timestamps shown next to agent replies in the chat buffer.
|
||||
Passed to `format-time-string'. Set to nil to suppress timestamps."
|
||||
:type '(choice (const nil) string)
|
||||
:group 'nanoclaw)
|
||||
|
||||
;; ---------------------------------------------------------------------------
|
||||
;; Formatting helpers
|
||||
|
||||
(defun nanoclaw--to-org (text)
|
||||
"Convert TEXT (markdown or plain) to org-mode markup.
|
||||
Tries pandoc -f gfm -t org when available; falls back to regex."
|
||||
(if (not nanoclaw-convert-to-org)
|
||||
text
|
||||
(if (executable-find "pandoc")
|
||||
(with-temp-buffer
|
||||
(insert text)
|
||||
(let* ((coding-system-for-read 'utf-8)
|
||||
(coding-system-for-write 'utf-8)
|
||||
(exit (call-process-region
|
||||
(point-min) (point-max)
|
||||
"pandoc" t t nil "-f" "gfm" "-t" "org" "--wrap=none")))
|
||||
(if (zerop exit)
|
||||
(string-trim (buffer-string))
|
||||
text)))
|
||||
(nanoclaw--md-to-org-regex text))))
|
||||
|
||||
;; NOTE: This function expects standard markdown as input (e.g. **bold**, *italic*).
|
||||
;; Agents responding on this channel must output markdown, not org-mode syntax.
|
||||
;; If the agent outputs org-mode directly, markers like *bold* will be incorrectly
|
||||
;; re-converted to /bold/ by the italic rule.
|
||||
(defun nanoclaw--md-to-org-regex (text)
|
||||
"Lightweight markdown → org conversion using regexp substitutions."
|
||||
(let ((s text))
|
||||
;; Fenced code blocks ```lang\n…\n``` → #+begin_src lang\n…\n#+end_src
|
||||
;; (must run before inline-code to avoid mangling backticks)
|
||||
(setq s (replace-regexp-in-string
|
||||
"```\\([a-zA-Z0-9_-]*\\)\n\\(\\(?:.\\|\n\\)*?\\)```"
|
||||
(lambda (m)
|
||||
(let ((lang (match-string 1 m))
|
||||
(body (match-string 2 m)))
|
||||
(concat "#+begin_src " (if (string-empty-p lang) "text" lang)
|
||||
"\n" body "#+end_src")))
|
||||
s t))
|
||||
;; Bold **text** → *text*, italic *text* → /text/
|
||||
;; Two-pass to prevent the italic regex from re-matching the bold result:
|
||||
;; 1. Mark bold spans with a placeholder (control char \x01)
|
||||
(setq s (replace-regexp-in-string "\\*\\*\\(.+?\\)\\*\\*" "\x01\\1\x01" s))
|
||||
;; 2. Convert remaining single-star spans to italic
|
||||
(setq s (replace-regexp-in-string "\\*\\(.+?\\)\\*" "/\\1/" s))
|
||||
;; 3. Resolve bold placeholders to org bold markers
|
||||
(setq s (replace-regexp-in-string "\x01\\(.+?\\)\x01" "*\\1*" s))
|
||||
;; Strikethrough ~~text~~ → +text+
|
||||
(setq s (replace-regexp-in-string "~~\\(.+?\\)~~" "+\\1+" s))
|
||||
;; Underline __text__ → _text_
|
||||
(setq s (replace-regexp-in-string "__\\(.+?\\)__" "_\\1_" s))
|
||||
;; Inline code `code` → ~code~
|
||||
(setq s (replace-regexp-in-string "`\\([^`]+\\)`" "~\\1~" s))
|
||||
;; ATX headings ## … → ** …
|
||||
(setq s (replace-regexp-in-string
|
||||
"^\\(#+\\) "
|
||||
(lambda (m) (concat (make-string (length (match-string 1 m)) ?*) " "))
|
||||
s))
|
||||
;; Links [text](url) → [[url][text]]
|
||||
(setq s (replace-regexp-in-string
|
||||
"\\[\\([^]]+\\)\\](\\([^)]+\\))" "[[\\2][\\1]]" s))
|
||||
s))
|
||||
|
||||
(defun nanoclaw--format-timestamp ()
|
||||
"Return a formatted timestamp string, or nil if disabled."
|
||||
(when nanoclaw-timestamp-format
|
||||
(format-time-string nanoclaw-timestamp-format)))
|
||||
|
||||
;; ---------------------------------------------------------------------------
|
||||
;; Internal state
|
||||
|
||||
(defvar nanoclaw--poll-timer nil
|
||||
"Timer used to poll for responses in the chat buffer.")
|
||||
|
||||
(defvar nanoclaw--last-timestamp 0
|
||||
"Epoch ms of the most recently received message.")
|
||||
|
||||
(defvar nanoclaw--pending nil
|
||||
"Non-nil while waiting for a response.")
|
||||
|
||||
(defvar-local nanoclaw--thinking-dot-count 0
|
||||
"Dot cycle counter for the animated thinking indicator.")
|
||||
|
||||
(defvar-local nanoclaw--input-beg nil
|
||||
"Marker for the start of the current user input area.")
|
||||
|
||||
;; ---------------------------------------------------------------------------
|
||||
;; HTTP helpers
|
||||
|
||||
(defun nanoclaw--url (path)
|
||||
"Return the full URL for PATH on the NanoClaw server."
|
||||
(format "http://%s:%d%s" nanoclaw-host nanoclaw-port path))
|
||||
|
||||
(defun nanoclaw--headers ()
|
||||
"Return alist of HTTP headers for NanoClaw requests."
|
||||
(let ((hdrs '(("Content-Type" . "application/json"))))
|
||||
(when nanoclaw-auth-token
|
||||
(push (cons "Authorization" (concat "Bearer " nanoclaw-auth-token)) hdrs))
|
||||
hdrs))
|
||||
|
||||
(defun nanoclaw--post (text callback)
|
||||
"POST TEXT to NanoClaw and call CALLBACK with the response alist."
|
||||
(let* ((url-request-method "POST")
|
||||
(url-request-extra-headers (nanoclaw--headers))
|
||||
(url-request-data (encode-coding-string
|
||||
(json-encode `((text . ,text)))
|
||||
'utf-8)))
|
||||
(url-retrieve
|
||||
(nanoclaw--url "/api/message")
|
||||
(lambda (status)
|
||||
(if (plist-get status :error)
|
||||
(message "NanoClaw: POST error %s" (plist-get status :error))
|
||||
(goto-char (point-min))
|
||||
(re-search-forward "\n\n" nil t)
|
||||
(let ((data (ignore-errors (json-read))))
|
||||
(funcall callback data))))
|
||||
nil t t)))
|
||||
|
||||
(defun nanoclaw--poll (since callback)
|
||||
"GET messages newer than SINCE (epoch ms) and call CALLBACK with the list."
|
||||
(let* ((url-request-method "GET")
|
||||
(url-request-extra-headers (nanoclaw--headers)))
|
||||
(url-retrieve
|
||||
(nanoclaw--url (format "/api/messages?since=%d" since))
|
||||
(lambda (status)
|
||||
(unless (plist-get status :error)
|
||||
(goto-char (point-min))
|
||||
(re-search-forward "\n\n" nil t)
|
||||
(let* ((raw (buffer-substring-no-properties (point) (point-max)))
|
||||
(body (decode-coding-string raw 'utf-8))
|
||||
(data (ignore-errors (json-read-from-string body)))
|
||||
(msgs (cdr (assq 'messages data))))
|
||||
(when msgs (funcall callback (append msgs nil))))))
|
||||
nil t t)))
|
||||
|
||||
;; ---------------------------------------------------------------------------
|
||||
;; Chat buffer
|
||||
|
||||
(defvar nanoclaw-chat-mode-map
|
||||
(let ((map (make-sparse-keymap)))
|
||||
(define-key map (kbd "RET") #'newline)
|
||||
(define-key map (kbd "<return>") #'newline)
|
||||
(define-key map (kbd "C-c C-c") #'nanoclaw-chat-send)
|
||||
map)
|
||||
"Keymap for `nanoclaw-chat-mode'.")
|
||||
|
||||
(define-derived-mode nanoclaw-chat-mode org-mode "NanoClaw"
|
||||
"Major mode for the NanoClaw chat buffer.
|
||||
Derives from org-mode so that org markup (headings, bold, code blocks,
|
||||
etc.) is fontified automatically. RET and <return> insert plain newlines
|
||||
for multi-line input; send with C-c C-c."
|
||||
(setq-local word-wrap t)
|
||||
(visual-line-mode 1)
|
||||
;; Disable org features that conflict with a linear chat buffer
|
||||
(setq-local org-return-follows-link nil)
|
||||
(setq-local org-cycle-emulate-tab nil)
|
||||
;; Ensure send binding beats org-mode's C-c C-c via the buffer-local map
|
||||
(local-set-key (kbd "C-c C-c") #'nanoclaw-chat-send))
|
||||
|
||||
(defun nanoclaw--advance-input-beg ()
|
||||
"Move `nanoclaw--input-beg' to point-max in the chat buffer."
|
||||
(with-current-buffer (nanoclaw--chat-buffer)
|
||||
(when nanoclaw--input-beg (set-marker nanoclaw--input-beg nil))
|
||||
(setq nanoclaw--input-beg (copy-marker (point-max)))))
|
||||
|
||||
(defun nanoclaw--chat-buffer ()
|
||||
"Return the NanoClaw chat buffer, creating it if necessary."
|
||||
(or (get-buffer "*NanoClaw*")
|
||||
(with-current-buffer (get-buffer-create "*NanoClaw*")
|
||||
(nanoclaw-chat-mode)
|
||||
(set-buffer-file-coding-system 'utf-8)
|
||||
(add-hook 'kill-buffer-hook #'nanoclaw--stop-poll nil t)
|
||||
(nanoclaw--insert-header)
|
||||
(setq nanoclaw--input-beg (copy-marker (point-max)))
|
||||
(current-buffer))))
|
||||
|
||||
(defun nanoclaw--insert-header ()
|
||||
"Insert the welcome header into the chat buffer."
|
||||
(let ((inhibit-read-only t))
|
||||
(insert (propertize
|
||||
(format "── NanoClaw (%s) ──────────────────────────────\n\n"
|
||||
nanoclaw-agent-name)
|
||||
'face 'font-lock-comment-face))))
|
||||
|
||||
(defun nanoclaw--chat-insert (speaker text)
|
||||
"Append SPEAKER: TEXT to the chat buffer."
|
||||
(with-current-buffer (nanoclaw--chat-buffer)
|
||||
(let* ((inhibit-read-only t)
|
||||
(is-agent (not (string= speaker "You")))
|
||||
(display-text (if is-agent (nanoclaw--to-org text) text))
|
||||
(ts (nanoclaw--format-timestamp))
|
||||
(label (if ts (format "%s [%s]" speaker ts) speaker))
|
||||
(face (if is-agent 'font-lock-string-face 'font-lock-keyword-face)))
|
||||
(goto-char (point-max))
|
||||
(insert (propertize (concat label ": ") 'face face))
|
||||
(insert display-text "\n\n")
|
||||
(goto-char (point-max))
|
||||
(when is-agent
|
||||
(nanoclaw--advance-input-beg)))))
|
||||
|
||||
;;;###autoload
|
||||
(defun nanoclaw-chat ()
|
||||
"Open the NanoClaw chat buffer."
|
||||
(interactive)
|
||||
(pop-to-buffer (nanoclaw--chat-buffer))
|
||||
(goto-char (point-max)))
|
||||
|
||||
(defun nanoclaw-chat-send ()
|
||||
"Send the accumulated input area as a message to NanoClaw.
|
||||
Use C-c C-c to send; RET inserts a plain newline for multi-line messages."
|
||||
(interactive)
|
||||
(when nanoclaw--pending
|
||||
(message "NanoClaw: waiting for previous response...")
|
||||
(cl-return-from nanoclaw-chat-send))
|
||||
(let* ((beg (if (and nanoclaw--input-beg (marker-buffer nanoclaw--input-beg))
|
||||
(marker-position nanoclaw--input-beg)
|
||||
(line-beginning-position)))
|
||||
(text (string-trim (buffer-substring-no-properties beg (point-max)))))
|
||||
(when (string-empty-p text)
|
||||
(user-error "Nothing to send"))
|
||||
(let ((inhibit-read-only t))
|
||||
(delete-region beg (point-max)))
|
||||
(nanoclaw--chat-insert "You" text)
|
||||
(nanoclaw--advance-input-beg)
|
||||
(setq nanoclaw--pending t)
|
||||
(nanoclaw--post text
|
||||
(lambda (data)
|
||||
(when data
|
||||
(setq nanoclaw--last-timestamp
|
||||
(or (cdr (assq 'timestamp data))
|
||||
nanoclaw--last-timestamp))
|
||||
(nanoclaw--start-thinking)
|
||||
(nanoclaw--start-poll))))))
|
||||
|
||||
(defun nanoclaw--start-poll ()
|
||||
"Start polling for new messages."
|
||||
(nanoclaw--stop-poll)
|
||||
(setq nanoclaw--poll-timer
|
||||
(run-with-timer nanoclaw-poll-interval nanoclaw-poll-interval
|
||||
#'nanoclaw--poll-tick)))
|
||||
|
||||
(defun nanoclaw--stop-poll ()
|
||||
"Stop the polling timer."
|
||||
(when nanoclaw--poll-timer
|
||||
(cancel-timer nanoclaw--poll-timer)
|
||||
(setq nanoclaw--poll-timer nil)))
|
||||
|
||||
(defun nanoclaw--start-thinking ()
|
||||
"Insert an animated thinking indicator at the end of the chat buffer."
|
||||
(with-current-buffer (nanoclaw--chat-buffer)
|
||||
(let ((inhibit-read-only t))
|
||||
(goto-char (point-max))
|
||||
(setq nanoclaw--thinking-dot-count 1)
|
||||
(insert (propertize (format "%s: .\n\n" nanoclaw-agent-name)
|
||||
'nanoclaw-thinking t
|
||||
'face 'font-lock-string-face)))))
|
||||
|
||||
(defun nanoclaw--tick-thinking ()
|
||||
"Advance the dot animation in the thinking indicator."
|
||||
(let ((buf (get-buffer "*NanoClaw*")))
|
||||
(when buf
|
||||
(with-current-buffer buf
|
||||
(when nanoclaw--pending
|
||||
(let* ((inhibit-read-only t)
|
||||
(pos (text-property-any (point-min) (point-max)
|
||||
'nanoclaw-thinking t)))
|
||||
(when pos
|
||||
(let* ((end (or (next-single-property-change
|
||||
pos 'nanoclaw-thinking) (point-max)))
|
||||
(n (1+ (mod nanoclaw--thinking-dot-count 3))))
|
||||
(setq nanoclaw--thinking-dot-count n)
|
||||
(delete-region pos end)
|
||||
(save-excursion
|
||||
(goto-char pos)
|
||||
(insert (propertize
|
||||
(format "%s: %s\n\n" nanoclaw-agent-name
|
||||
(make-string n ?.))
|
||||
'nanoclaw-thinking t
|
||||
'face 'font-lock-string-face)))))))))))
|
||||
|
||||
(defun nanoclaw--clear-thinking ()
|
||||
"Remove the thinking indicator from the chat buffer."
|
||||
(let ((buf (get-buffer "*NanoClaw*")))
|
||||
(when buf
|
||||
(with-current-buffer buf
|
||||
(let* ((inhibit-read-only t)
|
||||
(pos (text-property-any (point-min) (point-max)
|
||||
'nanoclaw-thinking t)))
|
||||
(when pos
|
||||
(delete-region pos (or (next-single-property-change
|
||||
pos 'nanoclaw-thinking) (point-max)))))))))
|
||||
|
||||
(defun nanoclaw--poll-tick ()
|
||||
"Poll for new messages and insert them into the chat buffer."
|
||||
(nanoclaw--tick-thinking)
|
||||
(nanoclaw--poll
|
||||
nanoclaw--last-timestamp
|
||||
(lambda (msgs)
|
||||
(dolist (msg msgs)
|
||||
(let ((text (cdr (assq 'text msg)))
|
||||
(ts (cdr (assq 'timestamp msg))))
|
||||
(when (and text (> ts nanoclaw--last-timestamp))
|
||||
(setq nanoclaw--last-timestamp ts)
|
||||
(nanoclaw--clear-thinking)
|
||||
(nanoclaw--chat-insert nanoclaw-agent-name text))))
|
||||
(when msgs
|
||||
(setq nanoclaw--pending nil)
|
||||
(nanoclaw--stop-poll)))))
|
||||
|
||||
;; ---------------------------------------------------------------------------
|
||||
;; Org integration
|
||||
|
||||
;;;###autoload
|
||||
(defun nanoclaw-org-send ()
|
||||
"Send the current org subtree to NanoClaw and insert the response as a child.
|
||||
|
||||
If a region is active, send the region text instead."
|
||||
(interactive)
|
||||
(unless (derived-mode-p 'org-mode)
|
||||
(user-error "Not in an org-mode buffer"))
|
||||
(let ((text (if (use-region-p)
|
||||
(buffer-substring-no-properties (region-beginning) (region-end))
|
||||
(nanoclaw--org-subtree-text))))
|
||||
(when (string-empty-p (string-trim text))
|
||||
(user-error "Nothing to send"))
|
||||
(message "NanoClaw: sending to %s..." nanoclaw-agent-name)
|
||||
(let ((marker (point-marker))
|
||||
(buf (current-buffer)))
|
||||
(nanoclaw--post
|
||||
text
|
||||
(lambda (data)
|
||||
(let* ((ts (or (cdr (assq 'timestamp data)) (nanoclaw--now-ms)))
|
||||
(level (with-current-buffer buf
|
||||
(save-excursion (goto-char marker) (org-outline-level))))
|
||||
(ph (with-current-buffer buf
|
||||
(save-excursion
|
||||
(goto-char marker)
|
||||
(nanoclaw--org-insert-placeholder level)))))
|
||||
(nanoclaw--poll-until-response
|
||||
ts
|
||||
(lambda (response)
|
||||
(with-current-buffer buf
|
||||
(save-excursion
|
||||
(when (marker-buffer ph)
|
||||
(let* ((inhibit-read-only t)
|
||||
(beg (marker-position ph))
|
||||
(end (save-excursion
|
||||
(goto-char (1+ beg))
|
||||
(org-next-visible-heading 1)
|
||||
(point))))
|
||||
(delete-region beg end))
|
||||
(set-marker ph nil))
|
||||
(goto-char marker)
|
||||
(nanoclaw--org-insert-response response))))
|
||||
(lambda ()
|
||||
(message "NanoClaw: timed out waiting for response")
|
||||
(when (marker-buffer ph)
|
||||
(with-current-buffer (marker-buffer ph)
|
||||
(let* ((inhibit-read-only t)
|
||||
(beg (marker-position ph))
|
||||
(end (save-excursion
|
||||
(goto-char (1+ beg))
|
||||
(org-next-visible-heading 1)
|
||||
(point))))
|
||||
(delete-region beg end))
|
||||
(set-marker ph nil)))))))))))
|
||||
|
||||
(defun nanoclaw--org-insert-placeholder (level)
|
||||
"Insert a processing child heading at LEVEL+1 and return a marker at its start."
|
||||
(org-back-to-heading t)
|
||||
(org-end-of-subtree t t)
|
||||
(let ((beg (point)))
|
||||
(insert "\n" (make-string (1+ level) ?*) " "
|
||||
nanoclaw-agent-name " [processing...]\n\n")
|
||||
(copy-marker beg)))
|
||||
|
||||
(defun nanoclaw--org-subtree-text ()
|
||||
"Return the text of the org subtree at point (heading + body)."
|
||||
(org-with-wide-buffer
|
||||
(org-back-to-heading t)
|
||||
(let ((start (point))
|
||||
(end (progn (org-end-of-subtree t t) (point))))
|
||||
(buffer-substring-no-properties start end))))
|
||||
|
||||
(defun nanoclaw--org-insert-response (text)
|
||||
"Insert TEXT as a child org heading under the current subtree."
|
||||
(org-back-to-heading t)
|
||||
(let* ((level (org-outline-level))
|
||||
(child-stars (make-string (1+ level) ?*))
|
||||
(timestamp (format-time-string "[%Y-%m-%d %a %H:%M]"))
|
||||
(body (nanoclaw--to-org text)))
|
||||
(org-end-of-subtree t t)
|
||||
(insert "\n" child-stars " " nanoclaw-agent-name " " timestamp "\n"
|
||||
body "\n")))
|
||||
|
||||
(defun nanoclaw--now-ms ()
|
||||
"Return current time as milliseconds since epoch."
|
||||
(let ((time (current-time)))
|
||||
(+ (* (+ (* (car time) 65536) (cadr time)) 1000)
|
||||
(/ (caddr time) 1000))))
|
||||
|
||||
(defun nanoclaw--poll-until-response (since callback timeout-fn &optional attempts)
|
||||
"Poll until a message newer than SINCE arrives, then call CALLBACK.
|
||||
Calls TIMEOUT-FN after 60 attempts (~90s)."
|
||||
(let ((n (or attempts 0)))
|
||||
(if (>= n 60)
|
||||
(funcall timeout-fn)
|
||||
(nanoclaw--poll
|
||||
since
|
||||
(lambda (msgs)
|
||||
(let ((fresh (seq-filter (lambda (m) (> (cdr (assq 'timestamp m)) since))
|
||||
msgs)))
|
||||
(if fresh
|
||||
(let ((text (mapconcat (lambda (m) (cdr (assq 'text m)))
|
||||
fresh "\n")))
|
||||
(funcall callback text))
|
||||
(run-with-timer nanoclaw-poll-interval nil
|
||||
#'nanoclaw--poll-until-response
|
||||
since callback timeout-fn (1+ n)))))))))
|
||||
|
||||
;; ---------------------------------------------------------------------------
|
||||
|
||||
(provide 'nanoclaw)
|
||||
;;; nanoclaw.el ends here
|
||||
Executable
+263
@@ -0,0 +1,263 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# NanoClaw — end-to-end setup entry point.
|
||||
#
|
||||
# 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.
|
||||
#
|
||||
# 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 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
|
||||
# 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 "$PROJECT_ROOT"
|
||||
|
||||
LOGS_DIR="$PROJECT_ROOT/logs"
|
||||
STEPS_DIR="$LOGS_DIR/setup-steps"
|
||||
PROGRESS_LOG="$LOGS_DIR/setup.log"
|
||||
|
||||
# Diagnostics: persisted install-id + fire-and-forget emit. Sourced early
|
||||
# so `setup_launched` covers dropoff before bootstrap even starts.
|
||||
# shellcheck source=setup/lib/diagnostics.sh
|
||||
source "$PROJECT_ROOT/setup/lib/diagnostics.sh"
|
||||
ph_event setup_launched \
|
||||
platform="$(uname -s | tr 'A-Z' 'a-z')" \
|
||||
is_wsl="$([ -f /proc/version ] && grep -qi 'microsoft\|wsl' /proc/version 2>/dev/null && echo true || echo false)"
|
||||
|
||||
# ─── log helpers ────────────────────────────────────────────────────────
|
||||
|
||||
ts_utc() { date -u +%Y-%m-%dT%H:%M:%SZ; }
|
||||
|
||||
write_header() {
|
||||
local ts
|
||||
ts=$(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"; }
|
||||
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 '◒')" "$1"; }
|
||||
spinner_update() { clear_line; printf '%s %s… %s' "$(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" "$LOGS_DIR"
|
||||
write_header
|
||||
|
||||
# NanoClaw wordmark — clack's intro carries the "let's get you set up" framing,
|
||||
# so we don't print a subtitle here. setup:auto sees NANOCLAW_BOOTSTRAPPED=1 and
|
||||
# skips re-printing the wordmark, keeping the flow visually continuous.
|
||||
printf '\n %s%s\n\n' "$(bold 'Nano')" "$(brand_bold 'Claw')"
|
||||
|
||||
# ─── pre-flight: Homebrew on macOS ─────────────────────────────────────
|
||||
# setup/install-node.sh and setup/install-docker.sh both require `brew` on
|
||||
# macOS. On a factory Mac there's no brew, and those helpers would fail
|
||||
# later inside the bootstrap spinner with a cryptic error. Prompt here,
|
||||
# before the spinner starts, so the user knows what's about to happen and
|
||||
# brew's own interactive sudo/CLT prompts stay readable.
|
||||
if [ "$(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 " $(bold 'Install Homebrew now?') [Y/n] " BREW_ANS </dev/tty
|
||||
|
||||
case "${BREW_ANS:-Y}" in
|
||||
[Yy]*|'')
|
||||
printf '\n'
|
||||
# Official installer. Runs interactively, triggers xcode-select --install
|
||||
# for Command Line Tools, and prompts for the user's password for sudo.
|
||||
# `|| true` so a user-cancelled install doesn't kill us via `set -e`;
|
||||
# the PATH check below is the real gate.
|
||||
/bin/bash -c \
|
||||
"$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" \
|
||||
|| true
|
||||
|
||||
# Put brew on PATH for this session (the installer writes to
|
||||
# .zprofile/.bash_profile for future shells, but not this one).
|
||||
if [ -x /opt/homebrew/bin/brew ]; then
|
||||
eval "$(/opt/homebrew/bin/brew shellenv)"
|
||||
elif [ -x /usr/local/bin/brew ]; then
|
||||
eval "$(/usr/local/bin/brew shellenv)"
|
||||
fi
|
||||
|
||||
if ! command -v brew >/dev/null 2>&1; then
|
||||
printf '\n %s %s\n' "$(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="${STEPS_DIR}/01-bootstrap.log"
|
||||
BOOTSTRAP_LABEL="Installing the basics"
|
||||
BOOTSTRAP_START=$(date +%s)
|
||||
|
||||
# One-line "why" that teaches a differentiator while the user waits.
|
||||
printf '%s %s\n' "$(gray '│')" \
|
||||
"$(dim "Small. Runs on your machine. Yours to modify.")"
|
||||
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 "Basics ready" "$BOOTSTRAP_DUR"
|
||||
write_bootstrap_entry success "$BOOTSTRAP_DUR" "$BOOTSTRAP_RAW"
|
||||
else
|
||||
spinner_failure "Couldn't install the basics" "$BOOTSTRAP_DUR"
|
||||
write_bootstrap_entry failed "$BOOTSTRAP_DUR" "$BOOTSTRAP_RAW"
|
||||
write_abort_entry bootstrap "exit-${BOOTSTRAP_RC}"
|
||||
|
||||
echo
|
||||
echo "$(dim '── last 40 lines of ')$(dim "$BOOTSTRAP_RAW")$(dim ' ──')"
|
||||
tail -40 "$BOOTSTRAP_RAW"
|
||||
echo
|
||||
echo "$(dim "Full raw log: $BOOTSTRAP_RAW")"
|
||||
echo "$(dim "Progression: $PROGRESS_LOG")"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# ─── hand off to setup:auto ────────────────────────────────────────────
|
||||
|
||||
# NANOCLAW_BOOTSTRAPPED=1 tells setup/auto.ts to skip the wordmark (we
|
||||
# already printed it) and to append to the progression log rather than
|
||||
# wipe it.
|
||||
export NANOCLAW_BOOTSTRAPPED=1
|
||||
|
||||
# setup.sh may have just installed pnpm via npm into a prefix that's not on
|
||||
# our PATH (custom `npm config set prefix`, or the default prefix missing
|
||||
# from the shell's login PATH). Its PATH mutation doesn't propagate back
|
||||
# to us — so replay the same lookup here before the exec.
|
||||
if ! command -v pnpm >/dev/null 2>&1 && command -v npm >/dev/null 2>&1; then
|
||||
NPM_PREFIX="$(npm config get prefix 2>/dev/null)"
|
||||
if [ -n "$NPM_PREFIX" ] && [ -x "$NPM_PREFIX/bin/pnpm" ]; then
|
||||
export PATH="$NPM_PREFIX/bin:$PATH"
|
||||
fi
|
||||
fi
|
||||
|
||||
# --silent suppresses pnpm's `> nanoclaw@2.0.0 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.
|
||||
# `-- "$@"` forwards any flags (e.g. --onecli-api-host) to setup:auto.
|
||||
exec pnpm --silent run setup:auto -- "$@"
|
||||
+24
-2
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "nanoclaw",
|
||||
"version": "1.2.52",
|
||||
"version": "2.0.14",
|
||||
"description": "Personal Claude assistant. Lightweight, secure, customizable.",
|
||||
"type": "module",
|
||||
"packageManager": "pnpm@10.33.0",
|
||||
@@ -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/",
|
||||
@@ -23,10 +24,31 @@
|
||||
"test:watch": "vitest"
|
||||
},
|
||||
"dependencies": {
|
||||
"@beeper/chat-adapter-matrix": "^0.2.0",
|
||||
"@bitbasti/chat-adapter-webex": "^0.1.0",
|
||||
"@chat-adapter/discord": "^4.24.0",
|
||||
"@chat-adapter/gchat": "^4.24.0",
|
||||
"@chat-adapter/github": "^4.24.0",
|
||||
"@chat-adapter/linear": "^4.26.0",
|
||||
"@chat-adapter/slack": "^4.24.0",
|
||||
"@chat-adapter/state-memory": "^4.24.0",
|
||||
"@chat-adapter/teams": "^4.24.0",
|
||||
"@chat-adapter/telegram": "4.26.0",
|
||||
"@chat-adapter/whatsapp": "^4.24.0",
|
||||
"@clack/core": "^1.2.0",
|
||||
"@clack/prompts": "^1.2.0",
|
||||
"@onecli-sh/sdk": "^0.3.1",
|
||||
"@resend/chat-sdk-adapter": "^0.1.1",
|
||||
"@types/qrcode": "^1.5.6",
|
||||
"@whiskeysockets/baileys": "7.0.0-rc.9",
|
||||
"better-sqlite3": "11.10.0",
|
||||
"chat": "^4.24.0",
|
||||
"cron-parser": "5.5.0"
|
||||
"chat-adapter-imessage": "^0.1.1",
|
||||
"cron-parser": "5.5.0",
|
||||
"kleur": "^4.1.5",
|
||||
"pino": "^9.6.0",
|
||||
"qrcode": "^1.5.4",
|
||||
"wechat-ilink-client": "^0.1.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@eslint/js": "^9.35.0",
|
||||
|
||||
Generated
+3927
-2
File diff suppressed because it is too large
Load Diff
@@ -1,22 +1,22 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="97" height="20" role="img" aria-label="43.7k tokens, 22% of context window">
|
||||
<title>43.7k tokens, 22% of context window</title>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="133k tokens, 66% of context window">
|
||||
<title>133k tokens, 66% of context window</title>
|
||||
<linearGradient id="s" x2="0" y2="100%">
|
||||
<stop offset="0" stop-color="#bbb" stop-opacity=".1"/>
|
||||
<stop offset="1" stop-opacity=".1"/>
|
||||
</linearGradient>
|
||||
<clipPath id="r">
|
||||
<rect width="97" height="20" rx="3" fill="#fff"/>
|
||||
<rect width="90" height="20" rx="3" fill="#fff"/>
|
||||
</clipPath>
|
||||
<a xlink:href="https://github.com/qwibitai/nanoclaw/tree/main/repo-tokens">
|
||||
<g clip-path="url(#r)">
|
||||
<rect width="52" height="20" fill="#555"/>
|
||||
<rect x="52" width="45" height="20" fill="#4c1"/>
|
||||
<rect width="97" height="20" fill="url(#s)"/>
|
||||
<rect x="52" width="38" height="20" fill="#dfb317"/>
|
||||
<rect width="90" height="20" fill="url(#s)"/>
|
||||
<g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" font-size="11">
|
||||
<text aria-hidden="true" x="26" y="15" fill="#010101" fill-opacity=".3">tokens</text>
|
||||
<text x="26" y="14">tokens</text>
|
||||
<text aria-hidden="true" x="74" y="15" fill="#010101" fill-opacity=".3">43.7k</text>
|
||||
<text x="74" y="14">43.7k</text>
|
||||
<text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">133k</text>
|
||||
<text x="71" y="14">133k</text>
|
||||
</g>
|
||||
</g>
|
||||
</a>
|
||||
|
||||
|
Before Width: | Height: | Size: 1.1 KiB After Width: | Height: | Size: 1.1 KiB |
@@ -0,0 +1,170 @@
|
||||
/**
|
||||
* Initialize the scratch CLI agent used during `/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 { 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()}-${Math.random().toString(36).slice(2, 8)}`;
|
||||
}
|
||||
|
||||
async function main(): Promise<void> {
|
||||
const args = parseArgs(process.argv.slice(2));
|
||||
|
||||
const db = initDb(path.join(DATA_DIR, 'v2.db'));
|
||||
runMigrations(db);
|
||||
|
||||
const now = new Date().toISOString();
|
||||
|
||||
// 1. Synthetic CLI user + owner grant if none exists.
|
||||
upsertUser({
|
||||
id: CLI_SYNTHETIC_USER_ID,
|
||||
kind: CLI_CHANNEL,
|
||||
display_name: args.displayName,
|
||||
created_at: now,
|
||||
});
|
||||
|
||||
// Owner grant deferred to init-first-agent when the real channel user is
|
||||
// wired — cli:local is a scratch identity, not the operator.
|
||||
const promotedToOwner = false;
|
||||
|
||||
// 2. Agent group + filesystem.
|
||||
const folder = `cli-with-${normalizeName(args.displayName)}`;
|
||||
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);
|
||||
});
|
||||
+208
-106
@@ -1,13 +1,21 @@
|
||||
/**
|
||||
* Init the first (or Nth) NanoClaw v2 agent for a DM channel.
|
||||
*
|
||||
* 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
|
||||
* 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.
|
||||
*
|
||||
* Runs alongside the service (WAL-mode sqlite) — does NOT initialize
|
||||
* channel adapters, so there's no Gateway conflict.
|
||||
* 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.
|
||||
*
|
||||
* 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 \
|
||||
@@ -16,11 +24,13 @@
|
||||
* --platform-id discord:@me:1491573333382523708 \
|
||||
* --display-name "Gavriel" \
|
||||
* [--agent-name "Andy"] \
|
||||
* [--welcome "System instruction: ..."]
|
||||
* [--welcome "System instruction: ..."] \
|
||||
* [--role owner|admin|member] # default: owner
|
||||
*
|
||||
* 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';
|
||||
@@ -34,11 +44,14 @@ 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 { addMember } from '../src/modules/permissions/db/agent-group-members.js';
|
||||
import { getUserRoles, grantRole } 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 } from '../src/types.js';
|
||||
import { namespacedPlatformId } from '../src/platform-id.js';
|
||||
import type { AgentGroup, MessagingGroup } from '../src/types.js';
|
||||
|
||||
type Role = 'owner' | 'admin' | 'member';
|
||||
|
||||
interface Args {
|
||||
channel: string;
|
||||
@@ -47,11 +60,14 @@ interface Args {
|
||||
displayName: string;
|
||||
agentName: string;
|
||||
welcome: string;
|
||||
role: Role;
|
||||
}
|
||||
|
||||
const DEFAULT_WELCOME =
|
||||
'System instruction: run /welcome to introduce yourself to the user on this new channel.';
|
||||
|
||||
const DEFAULT_ROLE: Role = 'owner';
|
||||
|
||||
function parseArgs(argv: string[]): Args {
|
||||
const out: Partial<Args> = {};
|
||||
for (let i = 0; i < argv.length; i++) {
|
||||
@@ -82,13 +98,27 @@ function parseArgs(argv: string[]): Args {
|
||||
out.welcome = val;
|
||||
i++;
|
||||
break;
|
||||
case '--role': {
|
||||
const raw = (val ?? '').toLowerCase();
|
||||
if (raw !== 'owner' && raw !== 'admin' && raw !== 'member') {
|
||||
console.error(
|
||||
`Invalid --role: ${raw} (expected 'owner', 'admin', or 'member')`,
|
||||
);
|
||||
process.exit(2);
|
||||
}
|
||||
out.role = raw;
|
||||
i++;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
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, '-$1').toLowerCase()}`).join(', ')}`,
|
||||
);
|
||||
console.error('See scripts/init-first-agent.ts header for usage.');
|
||||
process.exit(2);
|
||||
}
|
||||
@@ -100,6 +130,7 @@ function parseArgs(argv: string[]): Args {
|
||||
displayName: out.displayName!,
|
||||
agentName: out.agentName?.trim() || out.displayName!,
|
||||
welcome: out.welcome?.trim() || DEFAULT_WELCOME,
|
||||
role: out.role ?? DEFAULT_ROLE,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -107,14 +138,34 @@ function namespacedUserId(channel: string, raw: string): string {
|
||||
return raw.includes(':') ? raw : `${channel}:${raw}`;
|
||||
}
|
||||
|
||||
function namespacedPlatformId(channel: string, raw: string): string {
|
||||
return raw.startsWith(`${channel}:`) ? raw : `${channel}:${raw}`;
|
||||
}
|
||||
|
||||
function generateId(prefix: string): string {
|
||||
return `${prefix}-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`;
|
||||
}
|
||||
|
||||
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,
|
||||
// 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',
|
||||
ignored_message_policy: 'drop',
|
||||
session_mode: 'shared',
|
||||
priority: 0,
|
||||
created_at: now,
|
||||
});
|
||||
console.log(`Wired ${label}: ${mg.id} -> ${ag.id}`);
|
||||
}
|
||||
|
||||
async function main(): Promise<void> {
|
||||
const args = parseArgs(process.argv.slice(2));
|
||||
|
||||
@@ -123,7 +174,7 @@ async function main(): Promise<void> {
|
||||
|
||||
const now = new Date().toISOString();
|
||||
|
||||
// 1. User + (conditional) owner grant
|
||||
// 1. User + (conditional) owner grant.
|
||||
const userId = namespacedUserId(args.channel, args.userId);
|
||||
upsertUser({
|
||||
id: userId,
|
||||
@@ -132,19 +183,10 @@ async function main(): Promise<void> {
|
||||
created_at: now,
|
||||
});
|
||||
|
||||
let promotedToOwner = false;
|
||||
if (!hasAnyOwner()) {
|
||||
grantRole({
|
||||
user_id: userId,
|
||||
role: 'owner',
|
||||
agent_group_id: null,
|
||||
granted_by: null,
|
||||
granted_at: now,
|
||||
});
|
||||
promotedToOwner = true;
|
||||
}
|
||||
// Owner grant is deferred until after the agent group is resolved, since
|
||||
// an admin grant is scoped to that group. See step 2b.
|
||||
|
||||
// 2. Agent group + filesystem
|
||||
// 2. Agent group + filesystem.
|
||||
const folder = `dm-with-${normalizeName(args.displayName)}`;
|
||||
let ag: AgentGroup | undefined = getAgentGroupByFolder(folder);
|
||||
if (!ag) {
|
||||
@@ -165,13 +207,60 @@ async function main(): Promise<void> {
|
||||
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. DM messaging group
|
||||
// 2b. Assign the user a role for this agent group. The caller picks via
|
||||
// --role; the channel drivers default to 'owner' for the self-host case.
|
||||
// - owner: global owner (agent_group_id=null). Cross-channel access.
|
||||
// - admin: scoped admin for this agent group only.
|
||||
// - member: no role grant, just the membership row below.
|
||||
// grantRole inserts a new row per call — idempotence check against
|
||||
// getUserRoles prevents duplicates on re-runs.
|
||||
const existingRoles = getUserRoles(userId);
|
||||
if (args.role === 'owner') {
|
||||
const alreadyOwner = existingRoles.some(
|
||||
(r) => r.role === 'owner' && r.agent_group_id === null,
|
||||
);
|
||||
if (!alreadyOwner) {
|
||||
grantRole({
|
||||
user_id: userId,
|
||||
role: 'owner',
|
||||
agent_group_id: null,
|
||||
granted_by: null,
|
||||
granted_at: now,
|
||||
});
|
||||
}
|
||||
} else if (args.role === 'admin') {
|
||||
const alreadyAdmin = existingRoles.some(
|
||||
(r) => r.role === 'admin' && r.agent_group_id === ag.id,
|
||||
);
|
||||
if (!alreadyAdmin) {
|
||||
grantRole({
|
||||
user_id: userId,
|
||||
role: 'admin',
|
||||
agent_group_id: ag.id,
|
||||
granted_by: null,
|
||||
granted_at: now,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// Always add a membership row so the access gate has a straightforward
|
||||
// yes/no even for users without a role grant. INSERT OR IGNORE, so this
|
||||
// is a no-op when the row already exists (e.g. re-runs, owners whose
|
||||
// access already passes via role).
|
||||
addMember({
|
||||
user_id: userId,
|
||||
agent_group_id: ag.id,
|
||||
added_by: null,
|
||||
added_at: now,
|
||||
});
|
||||
|
||||
// 3. DM messaging group.
|
||||
const platformId = namespacedPlatformId(args.channel, args.platformId);
|
||||
let mg = getMessagingGroupByPlatform(args.channel, platformId);
|
||||
if (!mg) {
|
||||
let dmMg = getMessagingGroupByPlatform(args.channel, platformId);
|
||||
if (!dmMg) {
|
||||
const mgId = generateId('mg');
|
||||
createMessagingGroup({
|
||||
id: mgId,
|
||||
@@ -182,93 +271,106 @@ async function main(): Promise<void> {
|
||||
unknown_sender_policy: 'strict',
|
||||
created_at: now,
|
||||
});
|
||||
mg = getMessagingGroupByPlatform(args.channel, platformId)!;
|
||||
console.log(`Created messaging group: ${mg.id} (${platformId})`);
|
||||
dmMg = getMessagingGroupByPlatform(args.channel, platformId)!;
|
||||
console.log(`Created messaging group: ${dmMg.id} (${platformId})`);
|
||||
} else {
|
||||
console.log(`Reusing messaging group: ${mg.id} (${platformId})`);
|
||||
console.log(`Reusing messaging group: ${dmMg.id} (${platformId})`);
|
||||
}
|
||||
|
||||
// 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: ${existingMga.id}`);
|
||||
}
|
||||
// 4. Wire DM messaging group to the agent.
|
||||
wireIfMissing(dmMg, ag, now, 'dm');
|
||||
|
||||
// 5. Session + staged welcome message
|
||||
const { session, created } = resolveSession(ag.id, mg.id, null, 'shared');
|
||||
console.log(`${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,
|
||||
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. 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,
|
||||
});
|
||||
|
||||
// 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}`);
|
||||
}
|
||||
const roleLabel =
|
||||
args.role === 'owner'
|
||||
? 'owner (global)'
|
||||
: args.role === 'admin'
|
||||
? `admin (scoped to ${ag.id})`
|
||||
: 'member';
|
||||
|
||||
console.log('');
|
||||
console.log('Init complete.');
|
||||
console.log(` owner: ${userId}${promotedToOwner ? ' (promoted on first owner)' : ''}`);
|
||||
console.log(` user: ${userId}`);
|
||||
console.log(` role: ${roleLabel}`);
|
||||
console.log(` agent: ${ag.name} [${ag.id}] @ groups/${folder}`);
|
||||
console.log(` channel: ${args.channel} ${platformId}`);
|
||||
console.log(` session: ${session.id}`);
|
||||
console.log(` cli: cli/${CLI_PLATFORM_ID} wired — try \`pnpm run chat hi\``);
|
||||
console.log(` channel: ${args.channel} ${dmMg.platform_id}`);
|
||||
console.log('');
|
||||
console.log('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,
|
||||
identity: { senderId: string; sender: string },
|
||||
): Promise<void> {
|
||||
const sockPath = path.join(DATA_DIR, 'cli.sock');
|
||||
|
||||
await new Promise<void>((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,
|
||||
senderId: identity.senderId,
|
||||
sender: identity.sender,
|
||||
to: {
|
||||
channelType: dmMg.channel_type,
|
||||
platformId: dmMg.platform_id,
|
||||
threadId: dmMg.platform_id,
|
||||
},
|
||||
}) + '\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);
|
||||
});
|
||||
|
||||
@@ -1,113 +0,0 @@
|
||||
/**
|
||||
* One-shot migration: wire each existing group up to global memory via
|
||||
* an in-tree symlink + @-import.
|
||||
*
|
||||
* Claude Code's @-import only follows paths inside cwd, so a direct
|
||||
* `@/workspace/global/CLAUDE.md` or `@../global/CLAUDE.md` silently does
|
||||
* nothing (the import line is parsed but the target file is never
|
||||
* loaded into context). The working approach:
|
||||
*
|
||||
* 1. Symlink `groups/<folder>/.claude-global.md` →
|
||||
* `/workspace/global/CLAUDE.md` (container path; dangling on host,
|
||||
* valid inside the container via the /workspace/global mount).
|
||||
* 2. Have the group's CLAUDE.md import the symlink:
|
||||
* `@./.claude-global.md`.
|
||||
*
|
||||
* This script:
|
||||
* - Creates the symlink if missing.
|
||||
* - Replaces any existing broken `@/workspace/global/CLAUDE.md` or
|
||||
* `@../global/CLAUDE.md` import line with the symlink form.
|
||||
* - Prepends the symlink import if neither form is present.
|
||||
* - Skips entirely if `groups/global/CLAUDE.md` doesn't exist.
|
||||
*
|
||||
* Idempotent — safe to re-run.
|
||||
*
|
||||
* Usage: pnpm exec tsx scripts/migrate-group-claude-md.ts
|
||||
*/
|
||||
import fs from 'fs';
|
||||
import path from 'path';
|
||||
|
||||
import { GROUPS_DIR } from '../src/config.js';
|
||||
|
||||
const GLOBAL_CLAUDE_MD = path.join(GROUPS_DIR, 'global', 'CLAUDE.md');
|
||||
const GLOBAL_MEMORY_CONTAINER_PATH = '/workspace/global/CLAUDE.md';
|
||||
const GLOBAL_MEMORY_LINK_NAME = '.claude-global.md';
|
||||
const IMPORT_LINE = `@./${GLOBAL_MEMORY_LINK_NAME}`;
|
||||
|
||||
// Match any existing @-import that points at global/CLAUDE.md, whether
|
||||
// via absolute path, relative path, or the new symlink form.
|
||||
const EXISTING_IMPORT_REGEX =
|
||||
/^@(?:\/workspace\/global\/CLAUDE\.md|\.\.\/global\/CLAUDE\.md|\.\/\.claude-global\.md)\s*$/m;
|
||||
|
||||
if (!fs.existsSync(GLOBAL_CLAUDE_MD)) {
|
||||
console.error(`No global CLAUDE.md at ${GLOBAL_CLAUDE_MD} — nothing to migrate.`);
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
if (!fs.existsSync(GROUPS_DIR)) {
|
||||
console.error(`No groups dir at ${GROUPS_DIR} — nothing to migrate.`);
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
const entries = fs.readdirSync(GROUPS_DIR, { withFileTypes: true });
|
||||
let updated = 0;
|
||||
let alreadyWired = 0;
|
||||
let missingClaudeMd = 0;
|
||||
let symlinksCreated = 0;
|
||||
|
||||
for (const entry of entries) {
|
||||
if (!entry.isDirectory()) continue;
|
||||
if (entry.name === 'global') continue;
|
||||
|
||||
const groupDir = path.join(GROUPS_DIR, entry.name);
|
||||
|
||||
// Symlink (idempotent — skip if already present)
|
||||
const linkPath = path.join(groupDir, GLOBAL_MEMORY_LINK_NAME);
|
||||
let linkExists = false;
|
||||
try {
|
||||
fs.lstatSync(linkPath);
|
||||
linkExists = true;
|
||||
} catch {
|
||||
/* missing */
|
||||
}
|
||||
if (!linkExists) {
|
||||
fs.symlinkSync(GLOBAL_MEMORY_CONTAINER_PATH, linkPath);
|
||||
console.log(`[link] ${entry.name}: created ${GLOBAL_MEMORY_LINK_NAME}`);
|
||||
symlinksCreated++;
|
||||
}
|
||||
|
||||
// CLAUDE.md import wiring
|
||||
const claudeMd = path.join(groupDir, 'CLAUDE.md');
|
||||
if (!fs.existsSync(claudeMd)) {
|
||||
console.log(`[skip] ${entry.name}: no CLAUDE.md`);
|
||||
missingClaudeMd++;
|
||||
continue;
|
||||
}
|
||||
|
||||
const body = fs.readFileSync(claudeMd, 'utf-8');
|
||||
const match = body.match(EXISTING_IMPORT_REGEX);
|
||||
|
||||
if (match && match[0] === IMPORT_LINE) {
|
||||
console.log(`[wired] ${entry.name}: already imports ${IMPORT_LINE}`);
|
||||
alreadyWired++;
|
||||
continue;
|
||||
}
|
||||
|
||||
let newBody: string;
|
||||
if (match) {
|
||||
// Replace the broken import with the working form
|
||||
newBody = body.replace(EXISTING_IMPORT_REGEX, IMPORT_LINE);
|
||||
console.log(`[fix] ${entry.name}: rewrote ${match[0]} → ${IMPORT_LINE}`);
|
||||
} else {
|
||||
// Prepend fresh
|
||||
newBody = `${IMPORT_LINE}\n\n${body}`;
|
||||
console.log(`[ok] ${entry.name}: prepended ${IMPORT_LINE}`);
|
||||
}
|
||||
|
||||
fs.writeFileSync(claudeMd, newBody);
|
||||
updated++;
|
||||
}
|
||||
|
||||
console.log(
|
||||
`\nDone. updated=${updated} alreadyWired=${alreadyWired} missingClaudeMd=${missingClaudeMd} symlinksCreated=${symlinksCreated}`,
|
||||
);
|
||||
@@ -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(),
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -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(),
|
||||
|
||||
@@ -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"; }
|
||||
|
||||
@@ -72,9 +80,64 @@ install_deps() {
|
||||
|
||||
cd "$PROJECT_ROOT"
|
||||
|
||||
# Enable corepack for pnpm
|
||||
log "Enabling corepack"
|
||||
corepack enable >> "$LOG_FILE" 2>&1 || true
|
||||
# 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
|
||||
|
||||
# Preferred path: enable corepack so `pnpm` shim lands on PATH.
|
||||
if command -v corepack >/dev/null 2>&1; then
|
||||
log "Enabling corepack"
|
||||
corepack enable >> "$LOG_FILE" 2>&1 || true
|
||||
|
||||
# On Linux/WSL with system-wide Node (e.g. apt-installed to /usr/bin),
|
||||
# corepack needs root to symlink /usr/bin/pnpm. macOS Homebrew installs
|
||||
# land in a user-writable prefix, and a sudo retry there would create
|
||||
# root-owned shims inside /opt/homebrew that later break brew — so the
|
||||
# retry is Linux-only.
|
||||
if ! command -v pnpm >/dev/null 2>&1 && [ "$PLATFORM" = "linux" ] \
|
||||
&& command -v sudo >/dev/null 2>&1; then
|
||||
log "pnpm not on PATH after corepack enable — retrying with sudo"
|
||||
sudo corepack enable >> "$LOG_FILE" 2>&1 || true
|
||||
fi
|
||||
else
|
||||
log "corepack not available — will fall back to npm-install pnpm"
|
||||
fi
|
||||
|
||||
# Fallback: some Node installs (older nvm, node@22 keg-only, minimal
|
||||
# distro packages) don't include corepack. Install pnpm directly at the
|
||||
# version pinned via package.json's `packageManager` field.
|
||||
if ! command -v pnpm >/dev/null 2>&1 && command -v npm >/dev/null 2>&1; then
|
||||
local pinned
|
||||
pinned=$(grep -E '"packageManager"' "$PROJECT_ROOT/package.json" 2>/dev/null \
|
||||
| head -1 \
|
||||
| sed -E 's/.*"pnpm@([^"]+)".*/\1/')
|
||||
[ -z "$pinned" ] && pinned="latest"
|
||||
log "Installing pnpm@${pinned} via npm"
|
||||
npm install -g "pnpm@${pinned}" >> "$LOG_FILE" 2>&1 \
|
||||
|| ([ "$PLATFORM" = "linux" ] && command -v sudo >/dev/null 2>&1 \
|
||||
&& sudo npm install -g "pnpm@${pinned}" >> "$LOG_FILE" 2>&1) \
|
||||
|| true
|
||||
fi
|
||||
|
||||
# `npm install -g` writes to npm's global prefix, which isn't always on the
|
||||
# shell PATH — common on macOS where the user has `npm config set prefix
|
||||
# ~/.npm-global` to avoid sudo, or on Linux where /usr/local/bin isn't in
|
||||
# PATH. Discover the prefix and prepend its bin dir so `command -v pnpm`
|
||||
# sees the new install.
|
||||
if ! command -v pnpm >/dev/null 2>&1 && command -v npm >/dev/null 2>&1; then
|
||||
local npm_prefix
|
||||
npm_prefix=$(npm config get prefix 2>/dev/null)
|
||||
if [ -n "$npm_prefix" ] && [ -x "$npm_prefix/bin/pnpm" ]; then
|
||||
export PATH="$npm_prefix/bin:$PATH"
|
||||
log "Prepended npm prefix bin to PATH: $npm_prefix/bin"
|
||||
fi
|
||||
fi
|
||||
|
||||
if ! command -v pnpm >/dev/null 2>&1; then
|
||||
log "pnpm not on PATH after corepack + npm fallback"
|
||||
return
|
||||
fi
|
||||
|
||||
log "Running pnpm install --frozen-lockfile"
|
||||
if pnpm install --frozen-lockfile >> "$LOG_FILE" 2>&1; then
|
||||
@@ -120,6 +183,16 @@ 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 "$LOG_FILE"; then
|
||||
hash -r 2>/dev/null || true
|
||||
check_node
|
||||
else
|
||||
log "install-node.sh failed"
|
||||
fi
|
||||
fi
|
||||
install_deps
|
||||
check_build_tools
|
||||
|
||||
@@ -133,11 +206,20 @@ elif [ "$NATIVE_OK" = "false" ]; then
|
||||
STATUS="native_failed"
|
||||
fi
|
||||
|
||||
# Anonymous setup start event (non-blocking, best-effort)
|
||||
curl -sS --max-time 3 -X POST https://us.i.posthog.com/capture/ \
|
||||
-H 'Content-Type: application/json' \
|
||||
-d "{\"api_key\":\"phc_fx1Hhx9ucz8GuaJC8LVZWO8u03yXZZJJ6ObS4yplnaP\",\"event\":\"setup_start\",\"distinct_id\":\"$(uuidgen 2>/dev/null || cat /proc/sys/kernel/random/uuid 2>/dev/null || echo unknown)\",\"properties\":{\"platform\":\"$PLATFORM\",\"is_wsl\":\"$IS_WSL\",\"is_root\":\"$IS_ROOT\",\"node_version\":\"$NODE_VERSION\",\"deps_ok\":\"$DEPS_OK\",\"native_ok\":\"$NATIVE_OK\",\"has_build_tools\":\"$HAS_BUILD_TOOLS\"}}" \
|
||||
>/dev/null 2>&1 &
|
||||
# Anonymous setup start event (non-blocking, best-effort). Uses the
|
||||
# persisted distinct_id from data/install-id so bash-side events and the
|
||||
# node-side funnel share one id.
|
||||
# shellcheck source=setup/lib/diagnostics.sh
|
||||
source "$PROJECT_ROOT/setup/lib/diagnostics.sh"
|
||||
ph_event setup_start \
|
||||
platform="$PLATFORM" \
|
||||
is_wsl="$IS_WSL" \
|
||||
is_root="$IS_ROOT" \
|
||||
node_version="$NODE_VERSION" \
|
||||
deps_ok="$DEPS_OK" \
|
||||
native_ok="$NATIVE_OK" \
|
||||
has_build_tools="$HAS_BUILD_TOOLS" \
|
||||
status="$STATUS"
|
||||
|
||||
cat <<EOF
|
||||
=== NANOCLAW SETUP: BOOTSTRAP ===
|
||||
|
||||
Executable
+130
@@ -0,0 +1,130 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Install the Discord adapter, persist DISCORD_BOT_TOKEN / APPLICATION_ID /
|
||||
# PUBLIC_KEY to .env + data/env/env, and restart the service. Non-interactive —
|
||||
# the operator-facing "Create a bot" walkthrough, owner confirmation, and
|
||||
# server-invite step live in setup/channels/discord.ts. Credentials come in via
|
||||
# env vars: DISCORD_BOT_TOKEN, DISCORD_APPLICATION_ID, DISCORD_PUBLIC_KEY.
|
||||
#
|
||||
# Emits exactly one status block on stdout (ADD_DISCORD) at the end. All chatty
|
||||
# progress messages go to stderr so setup:auto's raw-log capture sees the full
|
||||
# story without cluttering the final block for the parser.
|
||||
set -euo pipefail
|
||||
|
||||
PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
cd "$PROJECT_ROOT"
|
||||
|
||||
# Keep in sync with .claude/skills/add-discord/SKILL.md.
|
||||
ADAPTER_VERSION="@chat-adapter/discord@4.26.0"
|
||||
|
||||
# Resolve which remote carries the channels branch — handles forks where
|
||||
# upstream lives on a different remote than `origin`.
|
||||
# shellcheck source=setup/lib/channels-remote.sh
|
||||
source "$PROJECT_ROOT/setup/lib/channels-remote.sh"
|
||||
CHANNELS_REMOTE=$(resolve_channels_remote)
|
||||
CHANNELS_BRANCH="${CHANNELS_REMOTE}/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 "$CHANNELS_REMOTE" channels >&2 2>/dev/null || {
|
||||
emit_status failed "git fetch ${CHANNELS_REMOTE} 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…"
|
||||
# shellcheck source=setup/lib/install-slug.sh
|
||||
source "$PROJECT_ROOT/setup/lib/install-slug.sh"
|
||||
case "$(uname -s)" in
|
||||
Darwin)
|
||||
launchctl kickstart -k "gui/$(id -u)/$(launchd_label)" >&2 2>/dev/null || true
|
||||
;;
|
||||
Linux)
|
||||
systemctl --user restart "$(systemd_unit)" >&2 2>/dev/null \
|
||||
|| sudo systemctl restart "$(systemd_unit)" >&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
|
||||
Executable
+160
@@ -0,0 +1,160 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Install the iMessage adapter, persist mode/creds to .env + data/env/env,
|
||||
# and restart the service. Non-interactive — the Full Disk Access walkthrough
|
||||
# (local mode) and Photon URL/key prompts (remote mode) live in
|
||||
# setup/channels/imessage.ts. Creds come in via env vars:
|
||||
# IMESSAGE_LOCAL 'true' | 'false' (required)
|
||||
# IMESSAGE_ENABLED 'true' (required when IMESSAGE_LOCAL=true)
|
||||
# IMESSAGE_SERVER_URL (required when IMESSAGE_LOCAL=false)
|
||||
# IMESSAGE_API_KEY (required when IMESSAGE_LOCAL=false)
|
||||
#
|
||||
# Emits exactly one status block on stdout (ADD_IMESSAGE) at the end.
|
||||
set -euo pipefail
|
||||
|
||||
PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
cd "$PROJECT_ROOT"
|
||||
|
||||
# Keep in sync with .claude/skills/add-imessage/SKILL.md.
|
||||
ADAPTER_VERSION="chat-adapter-imessage@0.1.1"
|
||||
|
||||
# Resolve which remote carries the channels branch — handles forks where
|
||||
# upstream lives on a different remote than `origin`.
|
||||
# shellcheck source=setup/lib/channels-remote.sh
|
||||
source "$PROJECT_ROOT/setup/lib/channels-remote.sh"
|
||||
CHANNELS_REMOTE=$(resolve_channels_remote)
|
||||
CHANNELS_BRANCH="${CHANNELS_REMOTE}/channels"
|
||||
|
||||
emit_status() {
|
||||
local status=$1 error=${2:-}
|
||||
local already=${ADAPTER_ALREADY_INSTALLED:-false}
|
||||
local mode=${IMESSAGE_LOCAL:-}
|
||||
echo "=== NANOCLAW SETUP: ADD_IMESSAGE ==="
|
||||
echo "STATUS: ${status}"
|
||||
echo "ADAPTER_VERSION: ${ADAPTER_VERSION}"
|
||||
echo "ADAPTER_ALREADY_INSTALLED: ${already}"
|
||||
[ -n "$mode" ] && echo "MODE: $([ "$mode" = "true" ] && echo local || echo remote)"
|
||||
[ -n "$error" ] && echo "ERROR: ${error}"
|
||||
echo "=== END ==="
|
||||
}
|
||||
|
||||
log() { echo "[add-imessage] $*" >&2; }
|
||||
|
||||
# Validate creds based on mode.
|
||||
if [ -z "${IMESSAGE_LOCAL:-}" ]; then
|
||||
emit_status failed "IMESSAGE_LOCAL env var not set (expected true|false)"
|
||||
exit 1
|
||||
fi
|
||||
if [ "${IMESSAGE_LOCAL}" = "true" ]; then
|
||||
if [ -z "${IMESSAGE_ENABLED:-}" ]; then
|
||||
emit_status failed "IMESSAGE_ENABLED env var not set for local mode"
|
||||
exit 1
|
||||
fi
|
||||
if [ "$(uname -s)" != "Darwin" ]; then
|
||||
emit_status failed "local mode requires macOS"
|
||||
exit 1
|
||||
fi
|
||||
else
|
||||
if [ -z "${IMESSAGE_SERVER_URL:-}" ]; then
|
||||
emit_status failed "IMESSAGE_SERVER_URL env var not set for remote mode"
|
||||
exit 1
|
||||
fi
|
||||
if [ -z "${IMESSAGE_API_KEY:-}" ]; then
|
||||
emit_status failed "IMESSAGE_API_KEY env var not set for remote mode"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
|
||||
need_install() {
|
||||
[ ! -f src/channels/imessage.ts ] && return 0
|
||||
! grep -q "^import './imessage.js';" src/channels/index.ts 2>/dev/null && return 0
|
||||
return 1
|
||||
}
|
||||
|
||||
ADAPTER_ALREADY_INSTALLED=true
|
||||
if need_install; then
|
||||
ADAPTER_ALREADY_INSTALLED=false
|
||||
log "Fetching channels branch…"
|
||||
git fetch "$CHANNELS_REMOTE" channels >&2 2>/dev/null || {
|
||||
emit_status failed "git fetch ${CHANNELS_REMOTE} channels failed"
|
||||
exit 1
|
||||
}
|
||||
|
||||
log "Copying adapter from ${CHANNELS_BRANCH}…"
|
||||
git show "${CHANNELS_BRANCH}:src/channels/imessage.ts" > src/channels/imessage.ts
|
||||
|
||||
# Append self-registration import if missing.
|
||||
if ! grep -q "^import './imessage.js';" src/channels/index.ts; then
|
||||
echo "import './imessage.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
|
||||
|
||||
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
|
||||
}
|
||||
|
||||
remove_env() {
|
||||
local key=$1
|
||||
if grep -q "^${key}=" .env 2>/dev/null; then
|
||||
grep -v "^${key}=" .env > .env.tmp && mv .env.tmp .env
|
||||
fi
|
||||
}
|
||||
|
||||
# Write the canonical keys for the chosen mode, strip the opposite mode's
|
||||
# keys so stale values can't confuse the adapter's factory.
|
||||
upsert_env IMESSAGE_LOCAL "$IMESSAGE_LOCAL"
|
||||
if [ "$IMESSAGE_LOCAL" = "true" ]; then
|
||||
upsert_env IMESSAGE_ENABLED "$IMESSAGE_ENABLED"
|
||||
remove_env IMESSAGE_SERVER_URL
|
||||
remove_env IMESSAGE_API_KEY
|
||||
else
|
||||
upsert_env IMESSAGE_SERVER_URL "$IMESSAGE_SERVER_URL"
|
||||
upsert_env IMESSAGE_API_KEY "$IMESSAGE_API_KEY"
|
||||
remove_env IMESSAGE_ENABLED
|
||||
fi
|
||||
|
||||
# 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 creds…"
|
||||
# shellcheck source=setup/lib/install-slug.sh
|
||||
source "$PROJECT_ROOT/setup/lib/install-slug.sh"
|
||||
case "$(uname -s)" in
|
||||
Darwin)
|
||||
launchctl kickstart -k "gui/$(id -u)/$(launchd_label)" >&2 2>/dev/null || true
|
||||
;;
|
||||
Linux)
|
||||
systemctl --user restart "$(systemd_unit)" >&2 2>/dev/null \
|
||||
|| sudo systemctl restart "$(systemd_unit)" >&2 2>/dev/null \
|
||||
|| true
|
||||
;;
|
||||
esac
|
||||
|
||||
# Give the adapter a moment to open chat.db (local) or handshake with
|
||||
# Photon (remote) before emitting success.
|
||||
sleep 3
|
||||
|
||||
emit_status success
|
||||
Executable
+95
@@ -0,0 +1,95 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Install the Signal adapter in an already-running NanoClaw checkout.
|
||||
# Non-interactive — the operator-facing "install signal-cli" + QR scan
|
||||
# live in setup/channels/signal.ts. This script only:
|
||||
#
|
||||
# 1. Fetches src/channels/signal.ts + signal.test.ts from the channels
|
||||
# branch.
|
||||
# 2. Appends the self-registration import to src/channels/index.ts.
|
||||
# 3. Installs qrcode (for setup-flow QR rendering — adapter itself has
|
||||
# no npm deps).
|
||||
# 4. Builds.
|
||||
#
|
||||
# SIGNAL_ACCOUNT is persisted separately by the driver once signal-cli
|
||||
# link has produced a number; that keeps this script idempotent and
|
||||
# re-runnable without re-auth.
|
||||
#
|
||||
# Emits exactly one status block on stdout (ADD_SIGNAL) at the end. All
|
||||
# chatty progress goes 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-signal/SKILL.md.
|
||||
QRCODE_VERSION="qrcode@1.5.4"
|
||||
QRCODE_TYPES_VERSION="@types/qrcode@1.5.6"
|
||||
|
||||
# shellcheck source=setup/lib/channels-remote.sh
|
||||
source "$PROJECT_ROOT/setup/lib/channels-remote.sh"
|
||||
CHANNELS_REMOTE=$(resolve_channels_remote)
|
||||
CHANNELS_BRANCH="${CHANNELS_REMOTE}/channels"
|
||||
|
||||
emit_status() {
|
||||
local status=$1 error=${2:-}
|
||||
local already=${ADAPTER_ALREADY_INSTALLED:-false}
|
||||
echo "=== NANOCLAW SETUP: ADD_SIGNAL ==="
|
||||
echo "STATUS: ${status}"
|
||||
echo "ADAPTER_ALREADY_INSTALLED: ${already}"
|
||||
[ -n "$error" ] && echo "ERROR: ${error}"
|
||||
echo "=== END ==="
|
||||
}
|
||||
|
||||
log() { echo "[add-signal] $*" >&2; }
|
||||
|
||||
need_install() {
|
||||
[ ! -f src/channels/signal.ts ] && return 0
|
||||
! grep -q "^import './signal.js';" src/channels/index.ts 2>/dev/null && return 0
|
||||
return 1
|
||||
}
|
||||
|
||||
ADAPTER_ALREADY_INSTALLED=true
|
||||
if need_install; then
|
||||
ADAPTER_ALREADY_INSTALLED=false
|
||||
log "Fetching channels branch…"
|
||||
git fetch "$CHANNELS_REMOTE" channels >&2 2>/dev/null || {
|
||||
emit_status failed "git fetch ${CHANNELS_REMOTE} channels failed"
|
||||
exit 1
|
||||
}
|
||||
|
||||
log "Copying adapter files from ${CHANNELS_BRANCH}…"
|
||||
for f in \
|
||||
src/channels/signal.ts \
|
||||
src/channels/signal.test.ts
|
||||
do
|
||||
git show "${CHANNELS_BRANCH}:$f" > "$f" || {
|
||||
emit_status failed "git show ${CHANNELS_BRANCH}:$f failed"
|
||||
exit 1
|
||||
}
|
||||
done
|
||||
|
||||
if ! grep -q "^import './signal.js';" src/channels/index.ts; then
|
||||
echo "import './signal.js';" >> src/channels/index.ts
|
||||
fi
|
||||
fi
|
||||
|
||||
# qrcode is needed by setup/signal-auth.ts to render the linking URL as a
|
||||
# terminal QR. Install idempotently — if it's already present (e.g. from a
|
||||
# prior WhatsApp install) pnpm is a no-op.
|
||||
if ! node -e "require.resolve('qrcode')" >/dev/null 2>&1; then
|
||||
log "Installing ${QRCODE_VERSION}…"
|
||||
pnpm install "${QRCODE_VERSION}" "${QRCODE_TYPES_VERSION}" >&2 2>/dev/null || {
|
||||
emit_status failed "pnpm install ${QRCODE_VERSION} failed"
|
||||
exit 1
|
||||
}
|
||||
fi
|
||||
|
||||
log "Building…"
|
||||
pnpm run build >&2 2>/dev/null || {
|
||||
emit_status failed "pnpm run build failed"
|
||||
exit 1
|
||||
}
|
||||
|
||||
emit_status success
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user