- Fix startup recovery running before WhatsApp connects, which could
permanently lose agent responses by advancing lastAgentTimestamp
before sock is initialized
- Add 5s retry on container failure so messages aren't silently dropped
until a new message arrives for the group
- Use `container stop` in shutdown instead of raw SIGTERM to CLI wrapper,
ensuring proper container cleanup
- Replace unnecessary dynamic imports with static imports in processTaskIpc
- Guard JSON.parse of DB-stored last_agent_timestamp against corruption
- Validate MAX_CONCURRENT_CONTAINERS (default 5, min 1, NaN-safe)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add per-group container locking with global concurrency limit to prevent
concurrent containers for the same group (#89) and cap total containers.
Fix message batching bug where lastAgentTimestamp advanced to trigger
message instead of latest in batch, causing redundant re-processing.
Move router state, sessions, and registered groups from JSON files to
SQLite with automatic one-time migration. Add SIGTERM/SIGINT handlers
with graceful shutdown (SIGTERM -> grace period -> SIGKILL). Add startup
recovery for messages missed during crash. Remove dead code: utils.ts,
Session type, isScheduledTask flag, ContainerConfig.env, getTaskRunLogs,
GroupQueue.isActive.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Name containers (nanoclaw-{group}-{timestamp}) for trackability
- Replace SIGKILL timeout with graceful `container stop` so --rm fires
- Add startup sweep to clean up stopped nanoclaw containers from previous runs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
WhatsApp reconnections called startMessageLoop/startSchedulerLoop/
startIpcWatcher and setInterval again without stopping the previous
instances, creating parallel loops that processed the same messages.
Add guard flags so each loop starts only once per process lifetime.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
three files created identical pino logger instances with the same config.
extract into src/logger.ts and import from each consumer.
net -9 lines, no behavior change.
Co-authored-by: ejae <ejae_dev@ejaes-Mac-mini.home>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
WhatsApp recently changed to send self-chat messages using LID (Linked
ID) format (e.g., xxxxxx@lid) instead of phone number format (e.g.,
xxxxxx@s.whatsapp.net). This caused messages to yourself to be silently
dropped because they didn't match any registered group.
## How to reproduce
1. Send a message to yourself on WhatsApp with the trigger
2. Message is received by Baileys but remoteJid is in LID format
3. LID JID doesn't match registered group JID (phone format)
4. Message is not stored and no response is sent
## The fix
- Build a LID-to-phone mapping from sock.user on connection open
- Translate incoming LID JIDs to phone JIDs before storing/processing messages
- This allows self-chat messages to correctly match the registered main channel
The mapping is populated from sock.user.id (phone) and sock.user.lid (LID)
which Baileys provides after successful authentication.
Main agent can now register new groups via MCP tool without restart.
Host updates both in-memory state and JSON file, creates group folders.
Authorization enforced at both agent and host level.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, lastTimestamp was unconditionally advanced after each message,
even if processMessage failed. This caused transient errors to permanently
drop messages since they would never be retried.
Now the cursor only advances after successful processing, implementing
at-least-once delivery semantics. On failure, the loop breaks and the
failed message will be retried on the next poll iteration.
https://claude.ai/code/session_01SEQDWxXeZHe7t1bb5cw2CA
Co-authored-by: Claude <noreply@anthropic.com>
- Remove unused claude-agent-sdk from host deps (only used in container)
- Remove dead scheduler MCP config (built into IPC)
- Remove unused eslint script
- Add clear error message when Apple Container fails to start
- Auto-generate launchd plist with real paths in setup skill
- Standardize Node.js version to 20+ everywhere
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add TIMEZONE config using system timezone for cron expressions
- Filter bot messages by content prefix instead of is_from_me
(user shares WhatsApp account with bot)
- Format messages as XML for cleaner agent parsing
- Update schedule_task tool to clarify local time usage
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Sync group names from WhatsApp via groupFetchAllParticipating()
- Store group names in chats table (jid -> name mapping)
- Daily sync with 24h cache, on-demand refresh via IPC
- Write available_groups.json snapshot for agent (main group only)
- Agent can request refresh_groups via IPC if group not found
- Update documentation in main CLAUDE.md and debug skill
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Scheduled tasks can now run in either:
- "group" mode: uses the group's conversation session for context
- "isolated" mode: runs with a fresh session (previous behavior)
The tool description guides the agent on when to use each mode and
prompts them to ask the user if unclear. Group mode is now the default.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- PR #10: Add sentinel markers for robust JSON parsing between container
and host. Fallback to last-line parsing for backwards compatibility.
- PR #5: Look up target JID from registeredGroups instead of trusting
IPC payload, fixing cross-group scheduled tasks getting wrong chat_jid.
- PR #8: Add lightweight schedule validation in container MCP that
returns errors to agents (cron syntax, positive interval, valid ISO
timestamp). Also defensive validation on host side.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, lastAgentTimestamp was updated regardless of whether
runAgent succeeded or failed. This caused messages to be skipped
on retry after a failure since they were already marked as processed.
Now the timestamp is only advanced when the agent returns a valid
response, ensuring failed messages will be included in the next retry.
https://claude.ai/code/session_0118wNAJCKY2Asr17Lb91TE2
Previously, lastTimestamp was advanced before processing messages.
If processMessage threw an error, those messages would be skipped
on the next tick since the timestamp had already moved past them.
Now we advance lastTimestamp after each message is successfully
processed (or after catching an error), ensuring no messages are
lost on retry.
https://claude.ai/code/session_01LgHSAs9XbcvZckCe8xPipj
Each container now gets its own IPC directory (/data/ipc/{groupFolder}/)
instead of a shared global directory. Identity is determined by which
directory a request came from, not by self-reported data in IPC files.
Authorization enforced:
- send_message: only to chatJids belonging to the source group
- schedule_task: only for the source group (main can target any)
- pause/resume/cancel_task: only for tasks owned by source group
https://claude.ai/code/session_018nmxNEbtgJH7cKDyBSQGAw
Keep only comments that explain non-obvious behavior or add context
not apparent from reading the code.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add authorization checks to IPC task operations (pause/resume/cancel)
to prevent cross-group task manipulation
- Only store message content for registered groups; unregistered chats
only get metadata stored for group discovery
- Container logs now only include full input/output in debug mode;
default logging omits sensitive message content
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add PreCompact hook in agent-runner that archives conversations before
compaction, using session summary from sessions-index.json for filename
- Remove /clear command (programmatic compaction not supported by SDK)
- Add /add-clear to RFS for future implementation
- Update CLAUDE.md templates with memory system instructions
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Shows "typing..." in WhatsApp while the agent container is running.
Uses Baileys sendPresenceUpdate with 'composing' and 'paused' states.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix session mount path: ~/.claude/ now mounts to /home/node/.claude/
(container runs as 'node' user with HOME=/home/node, not root)
- Fix ~/.gmail-mcp/ mount path similarly
- Use absolute paths for GROUPS_DIR and DATA_DIR (required for container mounts)
- Auto-start Apple Container system on NanoClaw startup
- Update debug skill with session troubleshooting guide
- Update spec.md with startup sequence and troubleshooting
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Agents run in isolated Linux VMs via Apple Container
- All groups get Bash access (safe - sandboxed in container)
- Browser automation via agent-browser + Chromium
- Per-group configurable additional directory mounts
- File-based IPC for messages and scheduled tasks
- Container image with Node.js 22, Chromium, agent-browser
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Custom nanoclaw MCP server with scheduling tools (schedule_task,
list_tasks, get_task, update_task, pause/resume/cancel_task, send_message)
- Tasks run as full agents in their group's context
- Support for cron, interval, and one-time schedules
- Task run logging with duration and results
- Main channel has Bash access for admin tasks (query DB, manage groups)
- Other groups restricted to file operations only
- Updated docs and requirements
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Format: [Jan 31 2:35 PM] instead of [14:35:00]
Date provides important context for ongoing conversations.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Use pushName from baileys to get the sender's display name instead
of just the phone number. Falls back to phone number if no name.
Includes migration to add sender_name column to existing databases.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Include the full message with @trigger so agent sees exactly
what was written. Current message is already in missedMessages
query so no need to add separately.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When a triggered message comes in, fetch all messages in that chat
since the last agent interaction and include them in the prompt.
Each message is formatted with timestamp and sender.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove context building (group name, chat JID, permissions)
- Agent runs in group folder which determines its permissions
- Caller handles response prefixing and where to send reply
- Session provides continuity, no need for metadata in each message
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- src/db.ts: initDatabase, closeDatabase, storeMessage, getNewMessages
- Removes SQL from index.ts
- Database initialization happens once at startup
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The daemon should never show interactive QR codes. If auth is needed,
send a macOS notification alerting the user to run /setup, then exit.
Also removes unused qrcode-terminal dependency.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
If WhatsApp authentication is required but the process is running
non-interactively (as a launchd daemon), exit with an error instead
of showing a QR code that nobody will see.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
A minimal Node.js application that connects Claude Agent SDK to WhatsApp
using baileys. Features per-group memory via CLAUDE.md files, session
continuity, scheduled tasks, and Gmail integration via MCP.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
