Scott.Idem/Cortex-Inara
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add auto memory distillation scheduler (APScheduler)

Browse Source 
- scheduler.py: AsyncIOScheduler with three cron jobs
    short  daily     03:00 (no LLM, always fast)
    mid    weekly    Sun 03:30 (LLM)
    long   monthly   1st 04:00 (LLM — off by default)
- config.py: AUTO_DISTILL, AUTO_DISTILL_SHORT/MID/LONG .env flags
- main.py: start/stop scheduler in FastAPI lifespan
- routers/distill.py: GET /distill/status — next run times + config
- requirements.txt: apscheduler>=3.10
- HELP.md: updated planned items, added /distill/status to API table

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Scott Idem
2026-03-17 22:31:38 -04:00
parent 9fb5b8ae63
commit 4253e69c0b
6 changed files with 128 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
inara/HELP.md
View File

@@ -177,6 +177,7 @@ For direct access or scripting:
| `POST` | `/distill/mid` | Summarize short → MEMORY_MID (LLM) |
| `POST` | `/distill/long` | Integrate mid → MEMORY_LONG (LLM) |
| `POST` | `/distill/all` | Run all three distillation steps |
| `GET` | `/distill/status` | Show scheduler status and next run times |
| `GET` | `/health` | Health check — returns `{"status": "ok"}` |
Chat request body (`POST /chat`):
@@ -196,7 +197,7 @@ Chat request body (`POST /chat`):
## In Progress / Planned
- **Auto memory distillation** — currently manual trigger only; scheduled auto-run planned
- **Auto memory distillation (long)** — short and mid run automatically; long-term integration is off by default (set `AUTO_DISTILL_LONG=true` in `.env` to enable)
- **Ollama local model backend** — direct Ollama API support (no CLI wrapper)
- **OAuth token auto-refresh notifications** — alert when Claude CLI token is near expiry
- **Multi-user support** — per-user identity/memory files; currently single-user (Scott)