Compare commits

...

4 Commits

Author SHA1 Message Date
gavrielc db42032ca4 merge: catch up with upstream main
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-28 15:28:05 +03:00
gavrielc f773b73ee0 chore: remove direct pino/pino-pretty dependency
Pino was replaced with a built-in logger on main. For branches
with baileys (WhatsApp), pino resolves as a transitive dependency
of @whiskeysockets/baileys.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-27 22:39:12 +03:00
Gabi Simons c7a24f4716 Merge branch 'main' into feat/add-github-skill 2026-03-08 22:37:30 +02:00
Gabi Simons b582498e27 feat(skill): add GitHub skill for container agents
Installs gh CLI in the container, passes GITHUB_TOKEN and GH_REPO
via stdin, and adds agent-facing docs so agents can manage issues,
PRs, and code review.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 22:37:01 +02:00
7 changed files with 1101 additions and 0 deletions
+153
View File
@@ -0,0 +1,153 @@
---
name: add-github
description: Add GitHub skill to container agents. Installs gh CLI in the container, passes GITHUB_TOKEN via stdin, and adds the agent-github skill doc so agents can manage issues, PRs, and code review.
---
# Add GitHub Skill
This skill gives container agents access to the GitHub CLI (`gh`) for managing issues, pull requests, and code review.
## Phase 1: Pre-flight
### Check if already applied
Read `.nanoclaw/state.yaml`. If `github` is in `applied_skills`, skip to Phase 3 (Configure). The code changes are already in place.
### Ask the user
Use `AskUserQuestion` to collect the GitHub token:
AskUserQuestion: Do you have a GitHub personal access token, or do you need to create one?
If they have one, collect it now. If not, guide them in Phase 3.
## Phase 2: Apply Code Changes
### Initialize skills system (if needed)
If `.nanoclaw/` directory doesn't exist yet:
```bash
npx tsx scripts/apply-skill.ts --init
```
### Apply the skill
```bash
npx tsx scripts/apply-skill.ts .claude/skills/add-github
```
This deterministically:
- Adds `container/skills/agent-github/SKILL.md` (agent-facing GitHub CLI docs)
- Three-way merges `gh` CLI installation into `container/Dockerfile`
- Three-way merges `GITHUB_TOKEN` and `GH_REPO` into `readSecrets()` in `src/container-runner.ts`
- Records the application in `.nanoclaw/state.yaml`
If the apply reports merge conflicts, read the intent files:
- `modify/container/Dockerfile.intent.md` — what changed for the Dockerfile
- `modify/src/container-runner.ts.intent.md` — what changed for container-runner.ts
### Validate
```bash
npm run build
```
Build must be clean before proceeding.
## Phase 3: Configure Token and Repository
### Step 1: Ask for token or guide creation
Use `AskUserQuestion`:
AskUserQuestion: Do you have a GitHub personal access token already, or do you need to create one?
If they need to create one, tell them:
> Create a GitHub personal access token (classic):
>
> 1. Go to https://github.com/settings/tokens/new
> 2. **Note**: `NanoClaw agent` (or whatever you like)
> 3. **Expiration**: 90 days (recommended) or "No expiration"
> 4. **Scopes**: select `repo` (full repo access — covers issues, PRs, code, status)
> 5. Click **Generate token** and copy it immediately (you can only see it once)
>
> The token will start with `ghp_...`. Paste it here when you have it.
Wait for the user to provide the token.
### Step 2: Ask for target repository
Use `AskUserQuestion`:
AskUserQuestion: Which GitHub repository should the agent manage? (format: `owner/repo`)
### Step 3: Add to `.env`
Add both values to `.env`:
```bash
GITHUB_TOKEN=ghp_...
GH_REPO=owner/repo
```
`GH_REPO` sets the default repository so the agent doesn't need `--repo` on every command.
### Step 4: Sync env and restart
```bash
npm run build
./container/build.sh
rm -r data/sessions/*/agent-runner-src 2>/dev/null || true
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
# Linux: systemctl --user restart nanoclaw
```
## Phase 4: Verify
### Test the connection
Tell the user:
> GitHub is connected! Send this in your main channel:
>
> "List the open issues on our repo"
The agent should invoke `gh issue list` and return results.
### Check logs if needed
```bash
tail -f logs/nanoclaw.log
```
## Troubleshooting
### gh: not found
The container needs to be rebuilt with the `gh` CLI:
```bash
./container/build.sh
rm -r data/sessions/*/agent-runner-src 2>/dev/null || true
launchctl kickstart -k gui/$(id -u)/com.nanoclaw
```
### gh: authentication required
- Check `GITHUB_TOKEN` is set in `.env`
- Restart NanoClaw
### Rate limit exceeded
GitHub allows 5,000 requests/hour with token auth. If hitting limits, the agent is likely making too many API calls in a loop.
## Removal
1. Delete `container/skills/agent-github/SKILL.md`
2. Remove `gh` installation block from `container/Dockerfile`
3. Remove `GITHUB_TOKEN` and `GH_REPO` from `readSecrets()` in `src/container-runner.ts`
4. Remove `GITHUB_TOKEN` and `GH_REPO` from `.env`
5. Remove `github` from `.nanoclaw/state.yaml`
6. Rebuild: `./container/build.sh && npm run build && launchctl kickstart -k gui/$(id -u)/com.nanoclaw`
@@ -0,0 +1,86 @@
---
name: agent-github
description: Manage GitHub issues, pull requests, and code review for the repository. Use for any GitHub task — listing issues, reviewing PRs, checking CI status, adding labels, posting comments.
allowed-tools: Bash(gh:*)
---
# GitHub CLI (`gh`)
## Authentication
`gh` is pre-authenticated via `GITHUB_TOKEN` env var. The target repo is set via `GH_REPO` (e.g., `owner/repo`), so you don't need to specify `--repo` on every command.
## Read operations
### Issues
```bash
gh issue list # Open issues
gh issue list --state closed --limit 10 # Recent closed issues
gh issue list --label "bug" # Filter by label
gh issue list --assignee "@me" # Assigned to me
gh issue list --search "keyword" # Search issues
gh issue view 42 # View issue details
gh issue view 42 --comments # Include comments
```
### Pull requests
```bash
gh pr list # Open PRs
gh pr list --state merged --limit 10 # Recent merged PRs
gh pr list --author "username" # Filter by author
gh pr view 99 # View PR details
gh pr view 99 --comments # Include comments
gh pr diff 99 # View PR diff
gh pr checks 99 # CI/check status
```
### Repository info
```bash
gh api repos/{owner}/{repo}/branches # List branches
gh api repos/{owner}/{repo}/commits?per_page=10 # Recent commits
gh api repos/{owner}/{repo}/releases/latest # Latest release
gh api repos/{owner}/{repo}/actions/runs?per_page=5 # Recent workflow runs
```
## Safe write operations
### Issue comments and labels
```bash
gh issue comment 42 --body "Looks good, marking as reviewed."
gh issue edit 42 --add-label "reviewed"
gh issue edit 42 --remove-label "needs-triage"
gh issue edit 42 --add-assignee "username"
```
### PR comments and reviews
```bash
gh pr comment 99 --body "LGTM, one minor suggestion below."
gh pr review 99 --approve --body "Approved."
gh pr review 99 --request-changes --body "Please fix the failing test."
gh pr review 99 --comment --body "Looks good overall."
```
## NOT allowed
Do NOT perform these operations — they are destructive or require human decision:
- `gh pr merge` / `gh pr close` / `gh pr reopen`
- `gh issue create` / `gh issue close` / `gh issue reopen`
- `gh release create` / `gh release delete`
- `gh repo delete` / `gh repo rename`
- `git push --force` / `git push --force-with-lease`
- Any `gh api -X DELETE` call
- Any `gh api -X PUT/PATCH` on branch protection rules
## Tips
- Use `--json` for structured output: `gh issue list --json number,title,labels`
- Combine with `jq` for filtering: `gh pr list --json number,title,checks --jq '.[] | select(.checks | length > 0)'`
- Rate limits: GitHub allows 5,000 requests/hour with token auth — plenty for normal use
- For large lists, use `--limit`: `gh issue list --limit 50`
- To get the repo owner/name: `gh repo view --json nameWithOwner --jq .nameWithOwner`
+17
View File
@@ -0,0 +1,17 @@
skill: github
version: 1.0.0
description: "GitHub CLI skill for container agents"
core_version: 0.1.0
adds:
- container/skills/agent-github/SKILL.md
modifies:
- container/Dockerfile
- src/container-runner.ts
structured:
npm_dependencies: {}
env_additions:
- GITHUB_TOKEN
- GH_REPO
conflicts: []
depends: []
test: "npm run build"
@@ -0,0 +1,77 @@
# NanoClaw Agent Container
# Runs Claude Agent SDK in isolated Linux VM with browser automation
FROM node:22-slim
# Install system dependencies for Chromium
RUN apt-get update && apt-get install -y \
chromium \
fonts-liberation \
fonts-noto-cjk \
fonts-noto-color-emoji \
libgbm1 \
libnss3 \
libatk-bridge2.0-0 \
libgtk-3-0 \
libx11-xcb1 \
libxcomposite1 \
libxdamage1 \
libxrandr2 \
libasound2 \
libpangocairo-1.0-0 \
libcups2 \
libdrm2 \
libxshmfence1 \
curl \
git \
&& rm -rf /var/lib/apt/lists/*
# Install GitHub CLI
RUN curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg \
-o /usr/share/keyrings/githubcli-archive-keyring.gpg \
&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" \
> /etc/apt/sources.list.d/github-cli.list \
&& apt-get update && apt-get install -y gh \
&& rm -rf /var/lib/apt/lists/*
# Set Chromium path for agent-browser
ENV AGENT_BROWSER_EXECUTABLE_PATH=/usr/bin/chromium
ENV PLAYWRIGHT_CHROMIUM_EXECUTABLE_PATH=/usr/bin/chromium
# Install agent-browser and claude-code globally
RUN npm install -g agent-browser @anthropic-ai/claude-code
# Create app directory
WORKDIR /app
# Copy package files first for better caching
COPY agent-runner/package*.json ./
# Install dependencies
RUN npm install
# Copy source code
COPY agent-runner/ ./
# Build TypeScript
RUN npm run build
# Create workspace directories
RUN mkdir -p /workspace/group /workspace/global /workspace/extra /workspace/ipc/messages /workspace/ipc/tasks /workspace/ipc/input
# Create entrypoint script
# Secrets are passed via stdin JSON — temp file is deleted immediately after Node reads it
# Follow-up messages arrive via IPC files in /workspace/ipc/input/
RUN printf '#!/bin/bash\nset -e\ncd /app && npx tsc --outDir /tmp/dist 2>&1 >&2\nln -s /app/node_modules /tmp/dist/node_modules\nchmod -R a-w /tmp/dist\ncat > /tmp/input.json\nnode /tmp/dist/index.js < /tmp/input.json\n' > /app/entrypoint.sh && chmod +x /app/entrypoint.sh
# Set ownership to node user (non-root) for writable directories
RUN chown -R node:node /workspace && chmod 777 /home/node
# Switch to non-root user (required for --dangerously-skip-permissions)
USER node
# Set working directory to group workspace
WORKDIR /workspace/group
# Entry point reads JSON from stdin, outputs JSON to stdout
ENTRYPOINT ["/app/entrypoint.sh"]
@@ -0,0 +1,30 @@
# Intent: container/Dockerfile modifications
## What changed
Added GitHub CLI (`gh`) installation from GitHub's official apt repository, placed after the existing system dependencies block.
## Key sections
### gh CLI installation
- Added after the `rm -rf /var/lib/apt/lists/*` line that closes the system dependencies block:
```dockerfile
RUN curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg \
-o /usr/share/keyrings/githubcli-archive-keyring.gpg \
&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" \
> /etc/apt/sources.list.d/github-cli.list \
&& apt-get update && apt-get install -y gh \
&& rm -rf /var/lib/apt/lists/*
```
- Uses the official GitHub apt repo with signed keyring
- Cleans apt lists to minimize image size
## Invariants
- All existing system dependencies (chromium, fonts, curl, git) are unchanged
- The Chromium env vars below are unchanged
- All subsequent steps (npm install, COPY, build, entrypoint) are unchanged
## Must-keep
- The existing `apt-get install` block for system dependencies
- The `AGENT_BROWSER_EXECUTABLE_PATH` and `PLAYWRIGHT_CHROMIUM_EXECUTABLE_PATH` env vars
- The npm global install of `agent-browser` and `@anthropic-ai/claude-code`
- The entire build, COPY, and entrypoint sequence
@@ -0,0 +1,704 @@
/**
* Container Runner for NanoClaw
* Spawns agent execution in containers and handles IPC
*/
import { ChildProcess, exec, spawn } from 'child_process';
import fs from 'fs';
import path from 'path';
import {
CONTAINER_IMAGE,
CONTAINER_MAX_OUTPUT_SIZE,
CONTAINER_TIMEOUT,
DATA_DIR,
GROUPS_DIR,
IDLE_TIMEOUT,
TIMEZONE,
} from './config.js';
import { readEnvFile } from './env.js';
import { resolveGroupFolderPath, resolveGroupIpcPath } from './group-folder.js';
import { logger } from './logger.js';
import {
CONTAINER_RUNTIME_BIN,
readonlyMountArgs,
stopContainer,
} from './container-runtime.js';
import { validateAdditionalMounts } from './mount-security.js';
import { RegisteredGroup } from './types.js';
// Sentinel markers for robust output parsing (must match agent-runner)
const OUTPUT_START_MARKER = '---NANOCLAW_OUTPUT_START---';
const OUTPUT_END_MARKER = '---NANOCLAW_OUTPUT_END---';
export interface ContainerInput {
prompt: string;
sessionId?: string;
groupFolder: string;
chatJid: string;
isMain: boolean;
isScheduledTask?: boolean;
assistantName?: string;
secrets?: Record<string, string>;
}
export interface ContainerOutput {
status: 'success' | 'error';
result: string | null;
newSessionId?: string;
error?: string;
}
interface VolumeMount {
hostPath: string;
containerPath: string;
readonly: boolean;
}
function buildVolumeMounts(
group: RegisteredGroup,
isMain: boolean,
): VolumeMount[] {
const mounts: VolumeMount[] = [];
const projectRoot = process.cwd();
const groupDir = resolveGroupFolderPath(group.folder);
if (isMain) {
// Main gets the project root read-only. Writable paths the agent needs
// (group folder, IPC, .claude/) are mounted separately below.
// Read-only prevents the agent from modifying host application code
// (src/, dist/, package.json, etc.) which would bypass the sandbox
// entirely on next restart.
mounts.push({
hostPath: projectRoot,
containerPath: '/workspace/project',
readonly: true,
});
// Shadow .env so the agent cannot read secrets from the mounted project root.
// Secrets are passed via stdin instead (see readSecrets()).
const envFile = path.join(projectRoot, '.env');
if (fs.existsSync(envFile)) {
mounts.push({
hostPath: '/dev/null',
containerPath: '/workspace/project/.env',
readonly: true,
});
}
// Main also gets its group folder as the working directory
mounts.push({
hostPath: groupDir,
containerPath: '/workspace/group',
readonly: false,
});
} else {
// Other groups only get their own folder
mounts.push({
hostPath: groupDir,
containerPath: '/workspace/group',
readonly: false,
});
// Global memory directory (read-only for non-main)
// Only directory mounts are supported, not file mounts
const globalDir = path.join(GROUPS_DIR, 'global');
if (fs.existsSync(globalDir)) {
mounts.push({
hostPath: globalDir,
containerPath: '/workspace/global',
readonly: true,
});
}
}
// Per-group Claude sessions directory (isolated from other groups)
// Each group gets their own .claude/ to prevent cross-group session access
const groupSessionsDir = path.join(
DATA_DIR,
'sessions',
group.folder,
'.claude',
);
fs.mkdirSync(groupSessionsDir, { recursive: true });
const settingsFile = path.join(groupSessionsDir, 'settings.json');
if (!fs.existsSync(settingsFile)) {
fs.writeFileSync(
settingsFile,
JSON.stringify(
{
env: {
// Enable agent swarms (subagent orchestration)
// https://code.claude.com/docs/en/agent-teams#orchestrate-teams-of-claude-code-sessions
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS: '1',
// Load CLAUDE.md from additional mounted directories
// https://code.claude.com/docs/en/memory#load-memory-from-additional-directories
CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD: '1',
// Enable Claude's memory feature (persists user preferences between sessions)
// https://code.claude.com/docs/en/memory#manage-auto-memory
CLAUDE_CODE_DISABLE_AUTO_MEMORY: '0',
},
},
null,
2,
) + '\n',
);
}
// Sync skills from container/skills/ into each group's .claude/skills/
const skillsSrc = path.join(process.cwd(), 'container', 'skills');
const skillsDst = path.join(groupSessionsDir, 'skills');
if (fs.existsSync(skillsSrc)) {
for (const skillDir of fs.readdirSync(skillsSrc)) {
const srcDir = path.join(skillsSrc, skillDir);
if (!fs.statSync(srcDir).isDirectory()) continue;
const dstDir = path.join(skillsDst, skillDir);
fs.cpSync(srcDir, dstDir, { recursive: true });
}
}
mounts.push({
hostPath: groupSessionsDir,
containerPath: '/home/node/.claude',
readonly: false,
});
// Per-group IPC namespace: each group gets its own IPC directory
// This prevents cross-group privilege escalation via IPC
const groupIpcDir = resolveGroupIpcPath(group.folder);
fs.mkdirSync(path.join(groupIpcDir, 'messages'), { recursive: true });
fs.mkdirSync(path.join(groupIpcDir, 'tasks'), { recursive: true });
fs.mkdirSync(path.join(groupIpcDir, 'input'), { recursive: true });
mounts.push({
hostPath: groupIpcDir,
containerPath: '/workspace/ipc',
readonly: false,
});
// Copy agent-runner source into a per-group writable location so agents
// can customize it (add tools, change behavior) without affecting other
// groups. Recompiled on container startup via entrypoint.sh.
const agentRunnerSrc = path.join(
projectRoot,
'container',
'agent-runner',
'src',
);
const groupAgentRunnerDir = path.join(
DATA_DIR,
'sessions',
group.folder,
'agent-runner-src',
);
if (!fs.existsSync(groupAgentRunnerDir) && fs.existsSync(agentRunnerSrc)) {
fs.cpSync(agentRunnerSrc, groupAgentRunnerDir, { recursive: true });
}
mounts.push({
hostPath: groupAgentRunnerDir,
containerPath: '/app/src',
readonly: false,
});
// Additional mounts validated against external allowlist (tamper-proof from containers)
if (group.containerConfig?.additionalMounts) {
const validatedMounts = validateAdditionalMounts(
group.containerConfig.additionalMounts,
group.name,
isMain,
);
mounts.push(...validatedMounts);
}
return mounts;
}
/**
* Read allowed secrets from .env for passing to the container via stdin.
* Secrets are never written to disk or mounted as files.
*/
function readSecrets(): Record<string, string> {
return readEnvFile([
'CLAUDE_CODE_OAUTH_TOKEN',
'ANTHROPIC_API_KEY',
'ANTHROPIC_BASE_URL',
'ANTHROPIC_AUTH_TOKEN',
'GITHUB_TOKEN',
'GH_REPO',
]);
}
function buildContainerArgs(
mounts: VolumeMount[],
containerName: string,
): string[] {
const args: string[] = ['run', '-i', '--rm', '--name', containerName];
// Pass host timezone so container's local time matches the user's
args.push('-e', `TZ=${TIMEZONE}`);
// Run as host user so bind-mounted files are accessible.
// Skip when running as root (uid 0), as the container's node user (uid 1000),
// or when getuid is unavailable (native Windows without WSL).
const hostUid = process.getuid?.();
const hostGid = process.getgid?.();
if (hostUid != null && hostUid !== 0 && hostUid !== 1000) {
args.push('--user', `${hostUid}:${hostGid}`);
args.push('-e', 'HOME=/home/node');
}
for (const mount of mounts) {
if (mount.readonly) {
args.push(...readonlyMountArgs(mount.hostPath, mount.containerPath));
} else {
args.push('-v', `${mount.hostPath}:${mount.containerPath}`);
}
}
args.push(CONTAINER_IMAGE);
return args;
}
export async function runContainerAgent(
group: RegisteredGroup,
input: ContainerInput,
onProcess: (proc: ChildProcess, containerName: string) => void,
onOutput?: (output: ContainerOutput) => Promise<void>,
): Promise<ContainerOutput> {
const startTime = Date.now();
const groupDir = resolveGroupFolderPath(group.folder);
fs.mkdirSync(groupDir, { recursive: true });
const mounts = buildVolumeMounts(group, input.isMain);
const safeName = group.folder.replace(/[^a-zA-Z0-9-]/g, '-');
const containerName = `nanoclaw-${safeName}-${Date.now()}`;
const containerArgs = buildContainerArgs(mounts, containerName);
logger.debug(
{
group: group.name,
containerName,
mounts: mounts.map(
(m) =>
`${m.hostPath} -> ${m.containerPath}${m.readonly ? ' (ro)' : ''}`,
),
containerArgs: containerArgs.join(' '),
},
'Container mount configuration',
);
logger.info(
{
group: group.name,
containerName,
mountCount: mounts.length,
isMain: input.isMain,
},
'Spawning container agent',
);
const logsDir = path.join(groupDir, 'logs');
fs.mkdirSync(logsDir, { recursive: true });
return new Promise((resolve) => {
const container = spawn(CONTAINER_RUNTIME_BIN, containerArgs, {
stdio: ['pipe', 'pipe', 'pipe'],
});
onProcess(container, containerName);
let stdout = '';
let stderr = '';
let stdoutTruncated = false;
let stderrTruncated = false;
// Pass secrets via stdin (never written to disk or mounted as files)
input.secrets = readSecrets();
container.stdin.write(JSON.stringify(input));
container.stdin.end();
// Remove secrets from input so they don't appear in logs
delete input.secrets;
// Streaming output: parse OUTPUT_START/END marker pairs as they arrive
let parseBuffer = '';
let newSessionId: string | undefined;
let outputChain = Promise.resolve();
container.stdout.on('data', (data) => {
const chunk = data.toString();
// Always accumulate for logging
if (!stdoutTruncated) {
const remaining = CONTAINER_MAX_OUTPUT_SIZE - stdout.length;
if (chunk.length > remaining) {
stdout += chunk.slice(0, remaining);
stdoutTruncated = true;
logger.warn(
{ group: group.name, size: stdout.length },
'Container stdout truncated due to size limit',
);
} else {
stdout += chunk;
}
}
// Stream-parse for output markers
if (onOutput) {
parseBuffer += chunk;
let startIdx: number;
while ((startIdx = parseBuffer.indexOf(OUTPUT_START_MARKER)) !== -1) {
const endIdx = parseBuffer.indexOf(OUTPUT_END_MARKER, startIdx);
if (endIdx === -1) break; // Incomplete pair, wait for more data
const jsonStr = parseBuffer
.slice(startIdx + OUTPUT_START_MARKER.length, endIdx)
.trim();
parseBuffer = parseBuffer.slice(endIdx + OUTPUT_END_MARKER.length);
try {
const parsed: ContainerOutput = JSON.parse(jsonStr);
if (parsed.newSessionId) {
newSessionId = parsed.newSessionId;
}
hadStreamingOutput = true;
// Activity detected — reset the hard timeout
resetTimeout();
// Call onOutput for all markers (including null results)
// so idle timers start even for "silent" query completions.
outputChain = outputChain.then(() => onOutput(parsed));
} catch (err) {
logger.warn(
{ group: group.name, error: err },
'Failed to parse streamed output chunk',
);
}
}
}
});
container.stderr.on('data', (data) => {
const chunk = data.toString();
const lines = chunk.trim().split('\n');
for (const line of lines) {
if (line) logger.debug({ container: group.folder }, line);
}
// Don't reset timeout on stderr — SDK writes debug logs continuously.
// Timeout only resets on actual output (OUTPUT_MARKER in stdout).
if (stderrTruncated) return;
const remaining = CONTAINER_MAX_OUTPUT_SIZE - stderr.length;
if (chunk.length > remaining) {
stderr += chunk.slice(0, remaining);
stderrTruncated = true;
logger.warn(
{ group: group.name, size: stderr.length },
'Container stderr truncated due to size limit',
);
} else {
stderr += chunk;
}
});
let timedOut = false;
let hadStreamingOutput = false;
const configTimeout = group.containerConfig?.timeout || CONTAINER_TIMEOUT;
// Grace period: hard timeout must be at least IDLE_TIMEOUT + 30s so the
// graceful _close sentinel has time to trigger before the hard kill fires.
const timeoutMs = Math.max(configTimeout, IDLE_TIMEOUT + 30_000);
const killOnTimeout = () => {
timedOut = true;
logger.error(
{ group: group.name, containerName },
'Container timeout, stopping gracefully',
);
exec(stopContainer(containerName), { timeout: 15000 }, (err) => {
if (err) {
logger.warn(
{ group: group.name, containerName, err },
'Graceful stop failed, force killing',
);
container.kill('SIGKILL');
}
});
};
let timeout = setTimeout(killOnTimeout, timeoutMs);
// Reset the timeout whenever there's activity (streaming output)
const resetTimeout = () => {
clearTimeout(timeout);
timeout = setTimeout(killOnTimeout, timeoutMs);
};
container.on('close', (code) => {
clearTimeout(timeout);
const duration = Date.now() - startTime;
if (timedOut) {
const ts = new Date().toISOString().replace(/[:.]/g, '-');
const timeoutLog = path.join(logsDir, `container-${ts}.log`);
fs.writeFileSync(
timeoutLog,
[
`=== Container Run Log (TIMEOUT) ===`,
`Timestamp: ${new Date().toISOString()}`,
`Group: ${group.name}`,
`Container: ${containerName}`,
`Duration: ${duration}ms`,
`Exit Code: ${code}`,
`Had Streaming Output: ${hadStreamingOutput}`,
].join('\n'),
);
// Timeout after output = idle cleanup, not failure.
// The agent already sent its response; this is just the
// container being reaped after the idle period expired.
if (hadStreamingOutput) {
logger.info(
{ group: group.name, containerName, duration, code },
'Container timed out after output (idle cleanup)',
);
outputChain.then(() => {
resolve({
status: 'success',
result: null,
newSessionId,
});
});
return;
}
logger.error(
{ group: group.name, containerName, duration, code },
'Container timed out with no output',
);
resolve({
status: 'error',
result: null,
error: `Container timed out after ${configTimeout}ms`,
});
return;
}
const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
const logFile = path.join(logsDir, `container-${timestamp}.log`);
const isVerbose =
process.env.LOG_LEVEL === 'debug' || process.env.LOG_LEVEL === 'trace';
const logLines = [
`=== Container Run Log ===`,
`Timestamp: ${new Date().toISOString()}`,
`Group: ${group.name}`,
`IsMain: ${input.isMain}`,
`Duration: ${duration}ms`,
`Exit Code: ${code}`,
`Stdout Truncated: ${stdoutTruncated}`,
`Stderr Truncated: ${stderrTruncated}`,
``,
];
const isError = code !== 0;
if (isVerbose || isError) {
logLines.push(
`=== Input ===`,
JSON.stringify(input, null, 2),
``,
`=== Container Args ===`,
containerArgs.join(' '),
``,
`=== Mounts ===`,
mounts
.map(
(m) =>
`${m.hostPath} -> ${m.containerPath}${m.readonly ? ' (ro)' : ''}`,
)
.join('\n'),
``,
`=== Stderr${stderrTruncated ? ' (TRUNCATED)' : ''} ===`,
stderr,
``,
`=== Stdout${stdoutTruncated ? ' (TRUNCATED)' : ''} ===`,
stdout,
);
} else {
logLines.push(
`=== Input Summary ===`,
`Prompt length: ${input.prompt.length} chars`,
`Session ID: ${input.sessionId || 'new'}`,
``,
`=== Mounts ===`,
mounts
.map((m) => `${m.containerPath}${m.readonly ? ' (ro)' : ''}`)
.join('\n'),
``,
);
}
fs.writeFileSync(logFile, logLines.join('\n'));
logger.debug({ logFile, verbose: isVerbose }, 'Container log written');
if (code !== 0) {
logger.error(
{
group: group.name,
code,
duration,
stderr,
stdout,
logFile,
},
'Container exited with error',
);
resolve({
status: 'error',
result: null,
error: `Container exited with code ${code}: ${stderr.slice(-200)}`,
});
return;
}
// Streaming mode: wait for output chain to settle, return completion marker
if (onOutput) {
outputChain.then(() => {
logger.info(
{ group: group.name, duration, newSessionId },
'Container completed (streaming mode)',
);
resolve({
status: 'success',
result: null,
newSessionId,
});
});
return;
}
// Legacy mode: parse the last output marker pair from accumulated stdout
try {
// Extract JSON between sentinel markers for robust parsing
const startIdx = stdout.indexOf(OUTPUT_START_MARKER);
const endIdx = stdout.indexOf(OUTPUT_END_MARKER);
let jsonLine: string;
if (startIdx !== -1 && endIdx !== -1 && endIdx > startIdx) {
jsonLine = stdout
.slice(startIdx + OUTPUT_START_MARKER.length, endIdx)
.trim();
} else {
// Fallback: last non-empty line (backwards compatibility)
const lines = stdout.trim().split('\n');
jsonLine = lines[lines.length - 1];
}
const output: ContainerOutput = JSON.parse(jsonLine);
logger.info(
{
group: group.name,
duration,
status: output.status,
hasResult: !!output.result,
},
'Container completed',
);
resolve(output);
} catch (err) {
logger.error(
{
group: group.name,
stdout,
stderr,
error: err,
},
'Failed to parse container output',
);
resolve({
status: 'error',
result: null,
error: `Failed to parse container output: ${err instanceof Error ? err.message : String(err)}`,
});
}
});
container.on('error', (err) => {
clearTimeout(timeout);
logger.error(
{ group: group.name, containerName, error: err },
'Container spawn error',
);
resolve({
status: 'error',
result: null,
error: `Container spawn error: ${err.message}`,
});
});
});
}
export function writeTasksSnapshot(
groupFolder: string,
isMain: boolean,
tasks: Array<{
id: string;
groupFolder: string;
prompt: string;
schedule_type: string;
schedule_value: string;
status: string;
next_run: string | null;
}>,
): void {
// Write filtered tasks to the group's IPC directory
const groupIpcDir = resolveGroupIpcPath(groupFolder);
fs.mkdirSync(groupIpcDir, { recursive: true });
// Main sees all tasks, others only see their own
const filteredTasks = isMain
? tasks
: tasks.filter((t) => t.groupFolder === groupFolder);
const tasksFile = path.join(groupIpcDir, 'current_tasks.json');
fs.writeFileSync(tasksFile, JSON.stringify(filteredTasks, null, 2));
}
export interface AvailableGroup {
jid: string;
name: string;
lastActivity: string;
isRegistered: boolean;
}
/**
* Write available groups snapshot for the container to read.
* Only main group can see all available groups (for activation).
* Non-main groups only see their own registration status.
*/
export function writeGroupsSnapshot(
groupFolder: string,
isMain: boolean,
groups: AvailableGroup[],
registeredJids: Set<string>,
): void {
const groupIpcDir = resolveGroupIpcPath(groupFolder);
fs.mkdirSync(groupIpcDir, { recursive: true });
// Main sees all groups; others see nothing (they can't activate groups)
const visibleGroups = isMain ? groups : [];
const groupsFile = path.join(groupIpcDir, 'available_groups.json');
fs.writeFileSync(
groupsFile,
JSON.stringify(
{
groups: visibleGroups,
lastSync: new Date().toISOString(),
},
null,
2,
),
);
}
@@ -0,0 +1,34 @@
# Intent: src/container-runner.ts modifications
## What changed
Added `GITHUB_TOKEN` and `GH_REPO` to the `readSecrets()` allowlist so they are passed to the container via stdin JSON.
## Key sections
### readSecrets()
- Added two keys to the array passed to `readEnvFile()`:
```typescript
function readSecrets(): Record<string, string> {
return readEnvFile([
'CLAUDE_CODE_OAUTH_TOKEN',
'ANTHROPIC_API_KEY',
'ANTHROPIC_BASE_URL',
'ANTHROPIC_AUTH_TOKEN',
'GITHUB_TOKEN',
'GH_REPO',
]);
}
```
- These values flow via stdin -> `containerInput.secrets` -> `sdkEnv` -> available to Bash
- `GITHUB_TOKEN` and `GH_REPO` are NOT added to `SECRET_ENV_VARS` in agent-runner because `gh` CLI needs them visible in Bash commands
## Invariants
- All existing secrets (`CLAUDE_CODE_OAUTH_TOKEN`, `ANTHROPIC_API_KEY`, `ANTHROPIC_BASE_URL`, `ANTHROPIC_AUTH_TOKEN`) are unchanged
- The stdin-based secret passing flow is unchanged
- No changes to volume mounts, container args, or any other functions
## Must-keep
- All existing volume mounts
- The mount security model
- Container lifecycle (spawn, timeout, output parsing)
- The `buildContainerArgs`, `runContainerAgent`, and all other functions