Debug

ClaudeClaw Container & Sandbox Debugging

This guide covers debugging the agent execution system (container and sandbox runtimes).

Architecture Overview

Host (macOS)                          Container (Linux VM)
─────────────────────────────────────────────────────────────
src/orchestrator/container-runner.ts               agent/runner/
    │                                      │
    │ spawns container                      │ runs Claude Agent SDK
    │ with volume mounts                   │ with MCP servers
    │                                      │
    ├── data/env/env ──────────────> /workspace/env-dir/env
    ├── groups/{folder} ───────────> /workspace/group
    ├── data/ipc/{folder} ────────> /workspace/ipc
    ├── data/sessions/{folder}/.claude/ ──> /home/node/.claude/ (isolated per-group)
    └── (main only) project root ──> /workspace/project

Important: The container runs as user node with HOME=/home/node. Session files must be mounted to /home/node/.claude/ (not /root/.claude/) for session resumption to work.

Log Locations

Enabling Debug Logging

Set LOG_LEVEL=debug for verbose output:

# For development
LOG_LEVEL=debug npm run dev

# For launchd service (macOS), add to plist EnvironmentVariables:
<key>LOG_LEVEL</key>
<string>debug</string>
# For systemd service (Linux), add to unit [Service] section:
# Environment=LOG_LEVEL=debug

Debug level shows:

• Full mount configurations
• Container command arguments
• Real-time container stderr

Common Issues

1. "Claude Code process exited with code 1"

Check the container log file in groups/{folder}/logs/container-*.log

Common causes:

Missing Authentication

Invalid API key · Please run /login

Fix: Ensure .env file exists with either OAuth token or API key:

cat .env  # Should show one of:
# CLAUDE_CODE_OAUTH_TOKEN=sk-ant-oat01-...  (subscription)
# ANTHROPIC_API_KEY=sk-ant-api03-...        (pay-per-use)

Root User Restriction

--dangerously-skip-permissions cannot be used with root/sudo privileges

Fix: Container must run as non-root user. Check Dockerfile has USER node.

2. Environment Variables Not Passing

Runtime note: Environment variables passed via -e may be lost when using -i (interactive/piped stdin).

Workaround: The system extracts only authentication variables (CLAUDE_CODE_OAUTH_TOKEN, ANTHROPIC_API_KEY) from .env and mounts them for sourcing inside the container. Other env vars are not exposed.

To verify env vars are reaching the container:

echo '{}' | docker run -i \
  -v $(pwd)/data/env:/workspace/env-dir:ro \
  --entrypoint /bin/bash claudeclaw-agent:latest \
  -c 'export $(cat /workspace/env-dir/env | xargs); echo "OAuth: ${#CLAUDE_CODE_OAUTH_TOKEN} chars, API: ${#ANTHROPIC_API_KEY} chars"'

3. Mount Issues

Container mount notes:

• Docker supports both -v and --mount syntax
• Use :ro suffix for readonly mounts:

  # Readonly
  -v /path:/container/path:ro
  
  # Read-write
  -v /path:/container/path
  

To check what's mounted inside a container:

docker run --rm --entrypoint /bin/bash claudeclaw-agent:latest -c 'ls -la /workspace/'

Expected structure:

/workspace/
├── env-dir/env           # Environment file (CLAUDE_CODE_OAUTH_TOKEN or ANTHROPIC_API_KEY)
├── group/                # Current group folder (cwd)
├── project/              # Project root (main channel only)
├── global/               # Global CLAUDE.md (non-main only)
├── ipc/                  # Inter-process communication
│   ├── messages/         # Outgoing WhatsApp messages
│   ├── tasks/            # Scheduled task commands
│   ├── current_tasks.json    # Read-only: scheduled tasks visible to this group
│   └── available_groups.json # Read-only: WhatsApp groups for activation (main only)
└── extra/                # Additional custom mounts

4. Permission Issues

The container runs as user node (uid 1000). Check ownership:

docker run --rm --entrypoint /bin/bash claudeclaw-agent:latest -c '
  whoami
  ls -la /workspace/
  ls -la /app/
'

All of /workspace/ and /app/ should be owned by node.

5. Session Not Resuming / "Claude Code process exited with code 1"

If sessions aren't being resumed (new session ID every time), or Claude Code exits with code 1 when resuming:

Root cause: The SDK looks for sessions at $HOME/.claude/projects/. Inside the container, HOME=/home/node, so it looks at /home/node/.claude/projects/.

Check the mount path:

# In container-runner.ts, verify mount is to /home/node/.claude/, NOT /root/.claude/
grep -A3 "Claude sessions" src/orchestrator/container-runner.ts

Verify sessions are accessible:

docker run --rm --entrypoint /bin/bash \
  -v ~/.claude:/home/node/.claude \
  claudeclaw-agent:latest -c '
echo "HOME=$HOME"
ls -la $HOME/.claude/projects/ 2>&1 | head -5
'

Fix: Ensure container-runner.ts mounts to /home/node/.claude/:

mounts.push({
  hostPath: claudeDir,
  containerPath: '/home/node/.claude',  // NOT /root/.claude
  readonly: false
});

6. MCP Server Failures

If an MCP server fails to start, the agent may exit. Check the container logs for MCP initialization errors.

Manual Container Testing

Test the full agent flow:

# Set up env file
mkdir -p data/env groups/test
cp .env data/env/env

# Run test query
echo '{"prompt":"What is 2+2?","groupFolder":"test","chatJid":"test@g.us","isMain":false}' | \
  docker run -i \
  -v $(pwd)/data/env:/workspace/env-dir:ro \
  -v $(pwd)/groups/test:/workspace/group \
  -v $(pwd)/data/ipc:/workspace/ipc \
  claudeclaw-agent:latest

Test Claude Code directly:

docker run --rm --entrypoint /bin/bash \
  -v $(pwd)/data/env:/workspace/env-dir:ro \
  claudeclaw-agent:latest -c '
  export $(cat /workspace/env-dir/env | xargs)
  claude -p "Say hello" --dangerously-skip-permissions --allowedTools ""
'

Interactive shell in container:

docker run --rm -it --entrypoint /bin/bash claudeclaw-agent:latest

SDK Options Reference

The agent-runner uses these Claude Agent SDK options:

query({
  prompt: input.prompt,
  options: {
    cwd: '/workspace/group',
    allowedTools: ['Bash', 'Read', 'Write', ...],
    permissionMode: 'bypassPermissions',
    allowDangerouslySkipPermissions: true,  // Required with bypassPermissions
    settingSources: ['project'],
    mcpServers: { ... }
  }
})

Important: allowDangerouslySkipPermissions: true is required when using permissionMode: 'bypassPermissions'. Without it, Claude Code exits with code 1.

Rebuilding After Changes

# Rebuild main app
npm run build

# Rebuild container (use --no-cache for clean rebuild)
./src/runtimes/docker/build.sh

# Or force full rebuild
docker builder prune -af
./src/runtimes/docker/build.sh

Checking Container Image

# List images
docker images

# Check what's in the image
docker run --rm --entrypoint /bin/bash claudeclaw-agent:latest -c '
  echo "=== Node version ==="
  node --version

  echo "=== Claude Code version ==="
  claude --version

  echo "=== Installed packages ==="
  ls /app/node_modules/
'

Session Persistence

Claude sessions are stored per-group in data/sessions/{group}/.claude/ for security isolation. Each group has its own session directory, preventing cross-group access to conversation history.

Critical: The mount path must match the container user's HOME directory:

• Container user: node
• Container HOME: /home/node
• Mount target: /home/node/.claude/ (NOT /root/.claude/)

To clear sessions:

# Clear all sessions for all groups
rm -rf data/sessions/

# Clear sessions for a specific group
rm -rf data/sessions/{groupFolder}/.claude/

# Also clear the session ID from ClaudeClaw's tracking (stored in SQLite)
sqlite3 store/messages.db "DELETE FROM sessions WHERE group_folder = '{groupFolder}'"

To verify session resumption is working, check the logs for the same session ID across messages:

grep "Session initialized" logs/claudeclaw.log | tail -5
# Should show the SAME session ID for consecutive messages in the same group

IPC Debugging

The container communicates back to the host via files in /workspace/ipc/:

# Check pending messages
ls -la data/ipc/messages/

# Check pending task operations
ls -la data/ipc/tasks/

# Read a specific IPC file
cat data/ipc/messages/*.json

# Check available groups (main channel only)
cat data/ipc/main/available_groups.json

# Check current tasks snapshot
cat data/ipc/{groupFolder}/current_tasks.json

IPC file types:

• messages/*.json - Agent writes: outgoing WhatsApp messages
• tasks/*.json - Agent writes: task operations (schedule, pause, resume, cancel, refresh_groups)
• current_tasks.json - Host writes: read-only snapshot of scheduled tasks
• available_groups.json - Host writes: read-only list of WhatsApp groups (main only)

Sandbox Runtime Debugging

If RUNTIME=sandbox is set, agents run via @anthropic-ai/sandbox-runtime instead of containers.

Sandbox Architecture

Host (macOS/Linux)
───────────────────────────────────────────
src/orchestrator/sandbox-runner.ts
    │
    │ spawns sandboxed process via srt CLI
    │ with kernel-enforced filesystem/network
    │
    ├── CLAUDECLAW_GROUP_DIR → groups/{folder}
    ├── CLAUDECLAW_IPC_DIR → data/ipc/{folder}
    ├── CLAUDECLAW_PROJECT_DIR → project root (read-only)
    ├── CLAUDECLAW_GLOBAL_DIR → groups/global (read-only)
    └── CLAUDECLAW_EXTRA_DIR → additional mounts

Sandbox-Specific Issues

EPERM on all operations: The srt settings JSON file requires ALL fields including empty arrays (allowRead: []). Omit any field and the entire settings file silently fails validation — zero error messages.

Agent runner won't start (tsx/EPERM): Sandbox blocks Unix sockets needed by tsx. Fix: pre-compile with cd agent/runner && npx tsc, run with plain node.

Agent can't find paths: Check that CLAUDECLAW_*_DIR env vars are set in sandbox-runner.ts. The agent runner falls back to /workspace/* if env vars are missing.

Stale sessions after runtime switch: Switching a group between container and sandbox leaves stale session IDs. Fix: sqlite3 store/messages.db "DELETE FROM sessions"

Network blocked: Verify allowedDomains in the generated settings file includes api.anthropic.com. Check data/sandbox-settings/ for the last generated settings file.

Credential issues: Sandbox passes real credentials via env vars (not through the credential proxy). Ensure ANTHROPIC_API_KEY or CLAUDE_CODE_OAUTH_TOKEN is in .env.

Quick Diagnostic Script

Run this to check common issues:

echo "=== Checking ClaudeClaw Agent Setup ==="

echo -e "\n1. Authentication configured?"
[ -f .env ] && (grep -q "CLAUDE_CODE_OAUTH_TOKEN=sk-" .env || grep -q "ANTHROPIC_API_KEY=sk-" .env) && echo "OK" || echo "MISSING - add CLAUDE_CODE_OAUTH_TOKEN or ANTHROPIC_API_KEY to .env"

echo -e "\n2. Env file copied for container?"
[ -f data/env/env ] && echo "OK" || echo "MISSING - will be created on first run"

echo -e "\n3. Container runtime running?"
docker info &>/dev/null && echo "OK" || echo "NOT RUNNING - start Docker Desktop (macOS) or sudo systemctl start docker (Linux)"

echo -e "\n4. Container image exists?"
echo '{}' | docker run -i --entrypoint /bin/echo claudeclaw-agent:latest "OK" 2>/dev/null || echo "MISSING - run ./src/runtimes/docker/build.sh"

echo -e "\n5. Session mount path correct?"
grep -q "/home/node/.claude" src/orchestrator/container-runner.ts 2>/dev/null && echo "OK" || echo "WRONG - should mount to /home/node/.claude/, not /root/.claude/"

echo -e "\n6. Groups directory?"
ls -la groups/ 2>/dev/null || echo "MISSING - run setup"

echo -e "\n7. Recent container logs?"
ls -t groups/*/logs/container-*.log 2>/dev/null | head -3 || echo "No container logs yet"

echo -e "\n8. Session continuity working?"
SESSIONS=$(grep "Session initialized" logs/claudeclaw.log 2>/dev/null | tail -5 | awk '{print $NF}' | sort -u | wc -l)
[ "$SESSIONS" -le 2 ] && echo "OK (recent sessions reusing IDs)" || echo "CHECK - multiple different session IDs, may indicate resumption issues"