feat: RSO observation system, child safety, Discord adapter, Telegram watchdog, email attachments
Core agent improvements:
- RSO (Relevance Scoring & Observation) system: interaction_logger, memory_scorer, signal_detector
- Memory access logging (memory_access_log table) for relevance scoring; high-signal turn detection
- Rich conversation storage for notable turns; compact_conversation truncates long user messages
- Task-type classifier (query/action/analysis/creative) for observation tagging
- Nested sub-agent visibility: deep delegations now register against the main agent's manager
Child safety (Gabriel profile):
- child_safety.py: filtering, audit logging, prompt constants for restricted sessions
- .kiro/specs/child-safety-profile: requirements, design, tasks specs
- GABRIEL_BOT_PROPOSAL.md: initial proposal doc
- Reduced context window (10 msgs) and tutor-mode identity for restricted users
Telegram adapter:
- Polling watchdog: auto-restarts updater if polling drops unexpectedly
- get_me() with exponential-backoff retry on NetworkError at startup
- Correct stop() ordering: signal watchdog before cancelling tasks
Email / Gmail:
- send_email: supports file attachments (attachments list param)
- get_email: surfaces attachment metadata in response
Scheduled tasks / weather:
- Remove OpenWeatherMap API calls from morning-weather task; use wttr.in exclusively
- New scheduled tasks and scheduler state persistence
Discord:
- adapters/discord/__init__.py scaffold
- discord-plugin: MCP plugin for Claude Code Discord integration (server.ts, skills, config)
Infrastructure:
- n8n workflow exports (garvis_webhook, content_pipeline variants)
- memory_workspace: context, homelab-repo-updates, weekly observation summaries, error logs
- UCS C240 migration plan doc
- requirements.txt: new deps
- .claude/settings.json, fix_hooks.py: hook/permission tuning
2026-04-23 07:54:01 -06:00
|
|
|
{"record_type": "error", "timestamp": "2026-04-08T22:06:53.850809", "error_type": "Exception", "message": "Agent SDK error: Task timed out after 30 minutes (39 messages processed)\nLast tool used: TodoWrite\nUsed 5 different tools - this is a complex multi-step task\n\nSuggestions:\n- Break this into smaller, focused sub-tasks\n- Use 'delegate_task' tool to run parts in parallel\n- Ask me to retry with a more specific scope", "component": "agent.py:_chat_agent_sdk", "intent": "Calling Agent SDK for chat response", "attempt": 1, "context": {"model": "claude-sonnet-4-6", "message_preview": "can you go through the loki logs, specifically for network 192.168.2.0/24 and take an inventory of t"}, "self_healed": false}
|