ffb33de0ed
- timmy-loop-prompt.md: full rewrite (76→209 lines) with PR-only workflow, tox environments, git hooks, Kimi dispatch safety block, conventional commits - kimi-code skill: added Branch & Convention Safety section - memories/MEMORY.md: updated with branch protection notes - config.yaml: removed dead kimi API key - cron/jobs.json: updated scheduled jobs - channel_directory.json: minor update - .gitignore: exclude queue/ and *.db
1.8 KiB
Gitea (localhost:3000): Users: rockachopa(admin), hermes(id=4), manus(id=3), kimi(id=5). Repos: rockachopa/Timmy-time-dashboard, rockachopa/hermes-agent (sovereign fork), rockachopa/hermes-config. Hermes token: ~/.hermes/gitea_token. Alex token: ~/.config/gitea/token. § Timmy architecture plan: Replace hardcoded _PERSONAS and TimmyOrchestrator with YAML-driven agent config (agents.yaml). One seed class, all differentiation via config. User wants to update YAML files, not Python, to add capabilities. Key files to refactor: agents/timmy.py, agents/base.py, tools_delegation/init.py, tools_intro/init.py. SubAgent class stays mostly as-is, just reads from YAML. Routing should be config-based pattern matching, not LLM calls. Per-agent model assignment (big model for orchestrator/code/research, small for simple tasks). qwen3:30b pulling as primary local model (~18GB, MoE 3B active). § Hermes-Timmy workspace: ~/Timmy-Time-dashboard/workspace/. Flat file correspondence, append-only. § 2026-03-14: Fixed issues #36-#40, #52. Built voice loop, fallback chain, source control. Built self-prompt queue. Upgraded Timmy to qwen3:30b with num_ctx=4096 cap (19GB VRAM, fits 39GB Mac). Loop v2: 20min timeout, claim TTL expiry, timeout cleanup, Timmy triage+review integration, 58% smaller prompt. Filed eval issues #77-#87. Status panel: ~/.hermes/bin/timmy-status.sh. § 2026-03-14 voice session: Built sovereign voice loop (timmy voice). Piper TTS + Whisper STT + Ollama, all local. Fixed event loop (persistent loop for MCP sessions), markdown stripping for TTS, MCP noise suppression, clean shutdown hooks. 1234 tests passing. Alexander wants to eventually train a custom voice using his own voice samples — noted for future. § Hermes fallback: anthropic → local qwen3:30b only. No chain, simple single fallback. Kimi not used.