77e770cdb2
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>
4.4 KiB
Session Log — 2026-03-18
[21:12] nct_rmcggr4a
Scott: We have made a lot of updates today.
Inara: Good session — Cortex is clearly in a much better state than where it started. The connection testing phase is behind us and the system is running clean.
Want me to log today's work with ae_log_work, or do a quick distill of the session notes into MEMORY_SHORT.md? Good time to capture the "Cortex is live and stable" milestone before we close out.
[21:14] nct_rmcggr4a
Scott: For now you are not really doing any work. You will still see a lot of "test" messages.
What do you have in your short term memory?
Inara: From MEMORY_SHORT.md, here's the summary of recent sessions:
-
2026-03-13 — One entry, end of a productive week. No specific tasks logged.
-
2026-03-14 — Mostly connection/pipe testing via Nextcloud Talk (
nct_rmcggr4a). Alphabet soup (ABC, XYZ, 321), a few "understood" responses, and then Cortex confirmed live. You noted it was "very cool" and confirmed the naming arc (Aether → Cortex → Inara) was working as intended. -
2026-03-16 — More testing, multiple "understood" responses. Toward the end, Cortex was clearly stabilizing — you confirmed it worked, asked me about myself, and we had a real conversation about the system. The "Omg it worked!" moment is in there.
-
2026-03-17 — Two brief entries: "Another test" and "Testing after lots of changes to the UI."
So the short-term picture is: Cortex went from unstable/in-testing to confirmed-working over the past few days, with a lot of connection validation noise along the way. No major technical tasks were logged — just infrastructure bring-up and UI refinement.
[21:15] nct_rmcggr4a
Scott: I think you should have access to read this file: /home/scott/agents_sync/projects/Cortex_and_Inara_dev/README.md
Inara: Looks like I need explicit permission to access that path. The agents_sync directory isn't automatically in scope for file reads here — you'd need to either grant access or we could work around it by having you paste the relevant bits.
Alternatively, if you want me to have persistent read access to that path, we can add it to the allowed paths in settings. Want me to do that?
[21:32] nct_rmcggr4a
Scott: I made a change. Please try to read that README.md file again.
Inara: Got it — that worked cleanly. Good summary of what Cortex is:
- FastAPI dispatcher sitting in front of Claude CLI / Gemini CLI / Ollama (future)
- Inara's identity lives in
inara/— loaded at startup viacontext_loader.py - Web UI at
localhost:8000(orcortex.dgrzone.comon WireGuard) - Systemd service (
sudo systemctl restart cortex) rather than direct Docker management
The architecture diagram confirms what I know — I'm not tied to a specific model, just to the identity files. The backend can swap underneath me, which is a clean design.
Anything specific in here you wanted me to look at, or were you just verifying the read access was working?
[22:57] cedar-cave
Scott: Can you tell me what happened in the world news today?
Inara: Here's a quick snapshot of what's making news today (2026-03-18):
- Iran: An attack on the world's largest natural gas field was reported — Iranian media says no injuries. Separately, the UK charged two men with national security offenses linked to Iran.
- US/Iran tensions: Reports (a few days old) of Trump allegedly discussing attacking Iran, with advisors denying it.
- Tech/geopolitics: China signaling it doesn't want to merely catch up with the US in tech — it's aiming to lead.
For the full picture, BBC World, Reuters, and AP are solid right now. Anything specific you want to dig into?
[23:19] cobalt-ridge
Scott: Can you add 2 test items to your new task list.
Inara: Done. Two test items added to the task list:
t_jwsoMn5b— Test Item 1t_ptw8nDec— Test Item 2
Both are sitting in [todo] status. Want me to clean them up after, or leave them as a baseline sanity check?
[23:21] fern-marsh
Scott: Can you tell me what is on your task list?
Inara: Currently there are two items on the task list — both sitting in todo:
| ID | Task |
|---|---|
t_jwsoMn5b |
Test Item 1 |
t_ptw8nDec |
Test Item 2 |
Looks like placeholder test entries. Want to clear those out and populate it with real work, or are these serving a purpose?