chore: jarvisChat → cAIc rename, single-node consolidation on jarvis, Qdrant UUID5 + chunk-size deploy fixes
This commit is contained in:
@@ -88,7 +88,7 @@ Refactored from single-file (`app.py`) into modules under project root:
|
||||
3. **`/v1/chat/completions`** → OpenAI-compatible for Continue.dev/IDE integration; FIM requests proxied without persistence
|
||||
4. **`/api/upload`** → multipart file upload, PDF/text extraction, `mode=(context|ingest|both)`, stores SQLite context (1hr expiry) + Qdrant upsert
|
||||
5. **`/api/ingest`** → Bearer token auth, programmatic RAG ingest (terminal hook, external tools)
|
||||
6. **`POST /api/image/generate`** → admin required, routes to corsair node agent via AMQP → ComfyUI workflow → returns PNG; `GET /api/image/status` lists available image gen nodes
|
||||
6. **`POST /api/image/generate`** → admin required, routes to an image-gen node via AMQP → ComfyUI workflow → returns PNG; `GET /api/image/status` lists available image gen nodes
|
||||
|
||||
### Perplexity / auto-search
|
||||
|
||||
@@ -131,7 +131,7 @@ All services are available bare-metal or as containers in `docker compose up`.
|
||||
- `SUPPORTED_UPLOAD_TYPES` includes images (png/jpeg/gif/svg/webp) + text + PDF + JSON
|
||||
- `UPLOAD_CONTEXT_EXPIRY_HOURS` = 1 hour
|
||||
- Rate limits and payload caps in `config.py` — patch `security.RL_*` not `config.RL_*` for tests
|
||||
- `COMFYUI_BASE` defaults to `http://192.168.50.115:8188` (overridable via `CAIC_COMFYUI_BASE`)
|
||||
- `COMFYUI_BASE` defaults to `http://localhost:8188` (overridable via `CAIC_COMFYUI_BASE`)
|
||||
- `COMFYUI_TIMEOUT` defaults to `120` seconds (overridable via `CAIC_COMFYUI_TIMEOUT`)
|
||||
- RAG embedding requests go to `EMBED_URL` at `/api/embeddings` (Ollama on worker :11434)
|
||||
|
||||
@@ -148,6 +148,8 @@ All streaming endpoints yield `data: {json}\n\n`. Key shapes:
|
||||
|
||||
### Completed this session
|
||||
- **Pre-Docker review**: Full findings report delivered -- 30+ issues across 7 categories (hardcoded hosts/paths, config/secrets, AMQP gaps, resource cleanup, SQLite container safety, completions concurrency, TASKS.md accuracy).
|
||||
- **Project rename**: `jarvisChat` → **cAIc** ("cake") — swept remaining branding (router docstrings, jc-ingest.sh env var), deleted stale `AGENTS.md.local`.
|
||||
- **Single-node consolidation**: all services moved to jarvis (192.168.50.212) — `COMFYUI_BASE` default → `localhost:8188`, AMQP URL default → `localhost:5672`, `NODE_NAME` default → `jarvis`, `DEFAULT_PROFILE` topology rewritten, cluster/AMQP/node_agent left in place (degrades gracefully).
|
||||
- **Deprecation fix**: Replaced `asyncio.ensure_future` with `asyncio.create_task` in `rag.py` and `routers/chat.py`.
|
||||
- **Documentation**: Added inline comments and docstrings to all functions in `db.py`.
|
||||
- **Uninstall scripts**: Created and committed `scripts/uninstall.sh`, `teardown-docker.sh`, `nuclear-clean.sh`.
|
||||
@@ -155,7 +157,22 @@ All streaming endpoints yield `data: {json}\n\n`. Key shapes:
|
||||
- **Docker containerization (B3)**: Created `Dockerfile`, `docker-compose.yml`, `.env.example`, `scripts/setup.sh`, `.dockerignore`, `searxng-settings.yml.dist`, `models/README.txt`. Fixed hardcoded defaults in `config.py` (localhost, Docker secrets path, `CAIC_DEFAULT_MODEL` env var, `CAIC_HW_STATE_PATH` env var). Added missing `psutil` + `jinja2` to `requirements.txt`. Fixed test discovery via `tests/conftest.py` sys.path insertion. 214 tests pass.
|
||||
|
||||
### Active
|
||||
- Image generation service backend complete — cluster handlers, router proxy, node agent ComfyUI integration, hardware probe. 27 tests pass. ComfyUI install pending on corsair.
|
||||
- Image generation service backend complete — cluster handlers, router proxy, node agent ComfyUI integration, hardware probe. 27 tests pass. ComfyUI install pending on jarvis (single-node).
|
||||
|
||||
### Deployed (2026-08-07) — v1.1.0 to production
|
||||
- **Fixed crash-loop**: ultron `llama-server.service` had 911 restarts — its `--rpc 192.168.50.210:50052` pointed at a dead IP. Corrected to `192.168.50.212:50052` (jarvis GPU rpc-server). Model now loads, `/health` = ok.
|
||||
- **Deployed v1.1.0**: workspace repo synced to `/opt/jarvischat` (jarvischat.service cwd). caic.db + venv preserved; `aio-pika` installed into prod venv (was missing → AMQP disabled).
|
||||
- **Env fixes** (`/etc/systemd/system/jarvischat.service.d/override.conf`): added `LLAMA_SERVER_BASE=http://192.168.50.108:8081`, `CAIC_QDRANT_URL=http://192.168.50.108:6333`, `CAIC_COMPLETIONS_API_KEY` (was set as legacy `JARVISCHAT_` name), kept `CAIC_EMBED_URL=http://192.168.50.108:11434` + `CAIC_ADMIN_PIN=1319`. Wrote `/opt/jarvischat/.completions_key` (jc-ingest.sh).
|
||||
- **Deploy-blocking bug fixes** (uncommitted, workspace + deploy):
|
||||
- `rag.py` `chunk_text`: chunk_size 512→200 (chunks exceeded mxbai-embed-large's 512-token context → ollama 500).
|
||||
- Qdrant 1.18.2 rejects non-UUID point IDs: wrapped `ingest-*`/`auto-*`/`upload-*` string IDs in `uuid5` in `routers/ingest.py`, `rag.py`, `routers/upload.py`.
|
||||
- `docs/jc-ingest.sh`: `JC_URL` updated `.210`→`.212`.
|
||||
- **Docs rebuilt**: 159 chunks (source `docs`) re-ingested via `/api/ingest` (README, ai.md, docker.md, CLAUDE.md, wiki/*). RAG now 378 vectors; chat verified injecting "Retrieved Context".
|
||||
- **Tests**: all 244 pass (run per-file in a throwaway venv; the full-suite run deadlocks on TestClient/AMQP ordering, not a code failure).
|
||||
|
||||
### Follow-ups
|
||||
- AMQP wiring: cluster subs degrade gracefully — **moot in the single-node (jarvis) deployment** until a multi-node cluster is stood back up. Needs `CAIC_AMQP_URL` + credentials if that happens.
|
||||
- `CAIC_TRIAGE_BASE` set but triage not yet invoked by chat (config-only until TASK 2 wiring).
|
||||
|
||||
### Blocked
|
||||
- Ball Gunner assets — waiting on Canva designs
|
||||
|
||||
Reference in New Issue
Block a user