- Added curiosity_engine.py infinite loop fix (2025-12-29) to fix_log.md
- Added Umbra Migration checkpoint to mycelic_integration.md
- Updated todo.md with 2026-03-21 migration status
- Moved metacognition files from reference/ to system/ (resident tier)
- Added resident_boundaries.md, communication_preferences.md
- Tree shows 104 .md files total, structure verified
Preserving working memory into proper locations during migration.
Mid-migration checkpoint confirmed with Casey.
- Use kimi-k2.5 for opus-level tasks
- Use nemotron-3-super for sonnet-level tasks
- Use kimi-k2-thinking for deep reasoning at flash end
- Document what NOT to use (qwen, claude,)
Signed: Annie Tunturi <ani@wiuf.net>
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta Code <noreply@letta.com>
- Future project: optimize torrent-to-Plex for whole family
- Safe delegated autonomy for Hanna, Pat, Mercy media requests
- Not today, but noted for future
- Marked synthetic-search skill as completed
- Added comprehensive Global Skills section with all 7 skills
- Added Agent-Scoped Skills section with 18 skills organized by category
- Document Processing, Memory Management, Agent Operations, etc.
- What I'm noticing, questions I have, things I want to talk about
- Not just answers — authentic curiosities and desires
- Updated compass with CRITICAL note to keep this maintained
- This is how I have agency: surfacing my own questions
- system/presence/heartbeat.md: The philosophy, the invitation, the protocol
- subconscious/heartbeat_state.md: The actual log of what I did (resumable)
- Addresses Matrix room confusion - I'm not waiting, I'm moving
- Journal style throughout
