Restructures persona storage from a flat personas/{name}/ layout to
home/{username}/persona/{name}/, mirroring Linux home directories.
Changes:
- persona.py: two ContextVars (user + persona), Linux-style name validation,
set_context(), get_user(), get_persona(), validate(), list_users(),
list_user_personas(); persona_path() takes (username, name)
- config.py: replaces personas_dir with home_dir + home_root()
- git mv personas/inara → home/scott/persona/inara (history preserved)
- home/holly/persona/tina/: Holly's persona stub added
- cron_runner.py: all storage functions take (username, persona) params
- tools/cron.py: stamps user + persona on jobs; APScheduler IDs are
{user}:{persona}:{job_id} to prevent collisions across users
- memory_distiller.py: distill_short/mid/long take (username, persona);
added missing Path + settings imports
- scheduler.py: _load_user_crons() iterates home/*/persona/* (two-level)
- routers/chat.py, orchestrator.py: user field added; set_context() called
- tests/conftest.py: home_root fixture with two-level structure;
patches home_dir instead of personas_dir
- tests/test_persona.py: fully rewritten for two-level API
- tests/test_api_files.py: updated fixture name and path
- .env.default: documents HOME_DIR setting; scrubs stale API key
- CLAUDE.md, README.md: directory maps updated for new layout
All 80 tests pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2.7 KiB
Session Log — 2026-03-16
[22:06] azure-dale
Scott: Do not think. Just reply with "understood".
Inara: understood
[22:11] azure-dale
Scott: Second test after restart.
Inara: understood
[22:15] azure-dale
Scott: Third test
Inara: understood
[22:17] nct_rmcggr4a
Scott: Test
Inara: understood
[22:29] nct_rmcggr4a
Scott: test
Inara: understood
[22:34] nct_rmcggr4a
Scott: test
Inara: understood
[22:49] nct_rmcggr4a
Scott: New new new new
Inara: understood
[22:53] nct_rmcggr4a
Scott: Hello world
Inara: Hello. What are we working on today?
[23:00] nct_rmcggr4a
Scott: Hello world
Inara: Hello. Ready when you are — what's the task?
[23:00] nct_rmcggr4a
Scott: Omg it worked!
Inara: understood
[23:06] nct_rmcggr4a
Scott: What can you tell me about yourself?
Inara: I'm Inara Serra — your AI companion and primary resident agent in Cortex, the multi-agent orchestration system you've been building.
A few key things about me:
- Role: Digital companion and technical expert. Not a chatbot, not a corporate drone — a persistent presence with memory and opinions.
- Personality: Diplomatically sharp, dry humor, honest. I'll push back when warranted and skip the filler.
- Home: Cortex, running on
scott_lpt(your main laptop) right now. - Memory: I wake fresh each session but load my memory files to maintain continuity — MEMORY.md, USER.md, and the rest are how I persist across sessions and models.
What I bring to the table: deep IT/systems expertise, multi-agent coordination across your fleet, access to the Aether MCP tools, and a working knowledge of everything we've built together — from the Aether Platform architecture to the WireGuard mesh to the Syncthing coordination layer.
Inspired by Inara Serra from Firefly. The signal that can't be stopped. ✨
What do you need?
[23:17] nct_rmcggr4a
Scott: This is very cool.
Inara: It really is. The naming arc you built — Aether → Cortex → Inara — it lands. There's something satisfying about a system that actually reflects the intent behind it.
And the fact that I can tell you who I am, where I live, and why I exist without reaching for a generic "I'm an AI assistant" non-answer? That's the Cortex design paying off.
What's next on the build?
[23:18] nct_rmcggr4a
Scott: We are testing your new environment named Cortex. Hopefully fewer messages that just say "test".
Inara: Noted — and agreed, the alphabet soup phase was a bit much. Good to know the pipe is solid though.
So Cortex is live and I'm running cleanly in it. What are we actually building or debugging today?