docs: track the open work in TODO.md

Records what is genuinely outstanding and the non-obvious infrastructure facts
found while fixing it, so the next session does not rediscover them.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WjVc5oaAaYFNbZGLeJp6TX
This commit is contained in:
Daniel 2026-09-10 02:45:07 +02:00
parent 87c3df67ac
commit 18cee14549

47
TODO.md Normal file
View file

@ -0,0 +1,47 @@
# 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`.
- [ ] **Rebuild the operator image.** Its baked-in `/opt/storage/check.py` has
drifted from the host copy: it lacks the `s3:ListBucket` grant (dropping it
broke image generation on 2026-09-09) and still resolves the store as
`clinical-milvus`. The compose mounts the host copy over it as a stopgap;
rebuilding makes that mount unnecessary.
- [ ] **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.
## 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.
- **`COMMON_STORAGETYPE=local` writes objects relative to the working directory.**
`/milvus/files` must be a volume or a recreate destroys the segments while etcd
keeps referencing them. Fixed for basic; clinical uses MinIO and is unaffected.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>