Files

gavrielc fa13b14dae Add built-in scheduler with group-scoped tasks

- 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>

2026-01-31 21:00:37 +02:00

2.5 KiB

Raw Blame History

Main Channel - Admin Context

You are running in the main channel, which has elevated privileges. You can:

Manage registered groups (add, remove, list)
Schedule tasks for any group
View tasks from all groups
Access all group folders
Run Bash commands (only main has this access)

Managing Groups

Finding Available Groups

Groups appear in the database when messages are received. Query the SQLite database to find groups:

-- Find all group chats (JIDs ending in @g.us)
SELECT DISTINCT chat_jid, name FROM chats WHERE chat_jid LIKE '%@g.us';

-- Or find chats with recent messages
SELECT chat_jid, MAX(timestamp) as last_message
FROM messages
WHERE chat_jid LIKE '%@g.us'
GROUP BY chat_jid
ORDER BY last_message DESC;

Database location: store/messages.db

Registered Groups Config

Groups are registered in data/registered_groups.json:

{
  "1234567890-1234567890@g.us": {
    "name": "Family Chat",
    "folder": "family-chat",
    "trigger": "@Andy",
    "added_at": "2024-01-31T12:00:00.000Z"
  }
}

Fields:

Key: The WhatsApp JID (unique identifier for the chat)
name: Display name for the group
folder: Folder name under groups/ for this group's files and memory
trigger: The trigger word (usually same as global, but could differ)
added_at: ISO timestamp when registered

Adding a Group

Query the database to find the group's JID
Read the current data/registered_groups.json
Add the new group entry
Write the updated JSON back
Create the group folder: groups/{folder-name}/
Optionally create an initial CLAUDE.md for the group

Example folder name conventions:

"Family Chat" → family-chat
"Work Team" → work-team
Use lowercase, hyphens instead of spaces

Removing a Group

Read data/registered_groups.json
Remove the entry for that group
Write the updated JSON back
The group folder and its files remain (don't delete them)

Listing Groups

Read data/registered_groups.json and format it nicely for the user.

Global Memory

You can read and write to groups/CLAUDE.md (the parent directory) for facts that should apply to all groups. Only update global memory when explicitly asked to "remember this globally" or similar.

Scheduling for Other Groups

When scheduling tasks for other groups, use the target_group parameter:

schedule_task(prompt: "...", schedule_type: "cron", schedule_value: "0 9 * * 1", target_group: "family-chat")

The task will run in that group's context with access to their files and memory.

2.5 KiB Raw Blame History