pediatric-ai-scribe-v3/TODO.md
Daniel 5cfd47ea66 docs: operator is built from source now
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GmpYHPSLGmXGZMyLpn2Lbe
2026-09-10 04:31:12 +02:00

58 lines
3.4 KiB
Markdown

# TODO
Live state as of 2026-09-10. Everything not listed here is deployed and green.
## Open
- [ ] **Basic index has no reader.** `MilvusVectorStore.search()` exists now, but no
tool calls it. Decide where the query path lives: put pymilvus into the
deliberately-lean `nextcloud-basic-mcp` server image, or expose a query API
from the indexer container. Nothing can read that index until this is done.
Source: `/home/danvics/docker/nextcloud-basic-mcp`
- [ ] **Multi-collection, ped-ai half.** The MCP side is deployed
(`clinical_semantic_search(collection=…)` + `clinical_list_collections`,
allowlisted by `MILVUS_COLLECTIONS`). ped-ai still searches one collection
per request. Needs an admin setting for which collections to search, then
fan-out and merge — `dedupeSources` in `src/utils/clinicalRetrieval.js`
already merges and renumbers. See `clinical-assist/COLLECTIONS.md`.
- [ ] **Confirm mail indexing end to end.** Six separate breaks are fixed and the
scan now reaches mail, but the file pass has not finished a full cycle
since the Milvus rebuild, so no mail has been indexed yet. Watch for
`[SCAN-*] Mail messages: N seen, M queued`.
- [ ] **Apply the restored clinical vector-store compose.** Written, committed and
validated at `/home/danvics/docker/nextcloud-mcp-server`, deliberately NOT
applied — `up -d` recreates the live clinical Milvus. Owner's call when.
## Done since this file was written
- Storage stack is under version control (`/home/danvics/docker/ped-ai-storage`),
secrets verified excluded, with a README recording the misleading project names
and the MinIO/separate-etcd requirements.
- Both Milvus stores keep objects in MinIO; verified end to end on the basic side
(16 objects in the bucket, rows queryable, collection Loaded).
- The operator image is built from source (`Dockerfile.operator`), so the drifted
`check.py` that broke image generation can no longer be run by accident.
## Worth knowing
- **Four repos were rescued from container images today**: `nextcloud-basic-mcp`,
`clinical-assist`, the deleted `nextcloud-mcp-server` compose file, and the
operator's `check.py` drift. Prefer building from a repo over a live container.
- **Two Milvus instances, historically misleading names.**
Clinical index = `nextcloud-mcp-server-milvus-1` (MinIO-backed, collection
`mcp_bge_m3_1024`). Nextcloud basic index = `ped-ai-storage-basic-milvus-1`
(db `basic`, collection `basic_bge_m3_1024_v2`).
- **Embedded etcd is unusable with authorization on.** Every non-root Milvus user
failed `etcdserver: invalid auth token`. Both stores now run a separate etcd
container, matching the profile that always worked.
- **Both Milvus stores now keep objects in MinIO**, matching what clinical always
did. `COMMON_STORAGETYPE=local` wrote segment files relative to the working
directory, so a recreate destroyed them while etcd kept referencing them and the
collection hung at Loading forever. S3 semantics also mean either store can be
pointed at a managed bucket without touching Milvus — which is what makes a
Terraform-managed deployment straightforward.
- **Milvus object-store credentials live in `milvus-user.yaml`** in the protected
secrets dir, not in the compose, because Milvus has no file-based option for
them and the compose should stay reviewable.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>