Commit Graph

8 Commits (37837c00a92d976efe2373c74bd3c232bea8a2aa)

Author SHA1 Message Date
ochan.kwon c15c3e972f fix(retriever): rebuild a missing vector store engine on demand
The engine registry is per-process, so a store's engine is missing
whenever this process did not create it. That happens three ways:

  - Startup skips a store whose engine fails to construct and never
    retries it, so that instance cannot serve the store again -- not
    even after a restart, if the backend is slow to come up.
  - A store registered on one instance is absent on every other until
    they restart, because registration is not broadcast.
  - Registration can fail on the instance handling the create, leaving
    the store missing even there.

Each one surfaces as "vector store is currently unavailable" and is
cleared today only by restarting the process.

Add GetOrLoadByStoreID, which falls back to building the engine from the
store row when the lookup misses, and route the two bound-store lookups
through it. The method goes on RetrieveEngineRegistry rather than
StoreRegistry because that is the interface the factory functions
receive; the two declare GetByStoreID separately and neither embeds the
other.

Concurrent callers collapse onto one build. That build runs on a context
detached from the caller that started it: callers share the result, so
letting the first one's cancellation abort it would fail everyone else
waiting. A panic inside the build is contained, because singleflight
re-raises it on a goroutine the HTTP recovery middleware cannot reach
and the build calls third-party client constructors.

Publishing is guarded by a per-store generation sampled before the
build, so an engine that finishes after the entry was registered or
removed by someone else does not overwrite it and leave that engine
orphaned with its connections open. A failed build starts a cooldown:
collapsing only helps concurrent callers, so without it a backend that
stays down would cost a full build timeout on every sequential request.

Separate "the store is gone" from "its engine cannot be built right
now". Async delete handlers answer ErrVectorStoreNotFound with
asynq.SkipRetry, so reporting a database blip or a backend outage that
way would permanently discard knowledge-base and index delete tasks and
orphan the vector data they exist to remove. ErrVectorStoreUnavailable
covers the retryable cases; the repository already distinguishes them,
returning (nil, nil) for a missing row and an error for a failure.

For the same reason a caller's own cancellation is never folded into a
store sentinel. The ownership check runs first and queries the database
with that context, so on a shutdown it is usually where cancellation is
noticed.

A search resolves one engine per distinct store, sequentially, and this
server sets no HTTP read or write timeout, so the resolution loop gets a
budget above a single build. An exhausted budget still leaves the
engines warming, since the build is detached, and is reported as an
unavailable store because retrying is likely to succeed.

Build failures are logged where they happen, with the panic stack. The
cause cannot travel back to the caller -- factory errors embed endpoints
and credentials -- so without this the one thing an operator needs when
self-healing fails to heal would be discarded with the error.

Note a deliberate contract change: an ownership lookup failure used to
be reported as not-found, and a test asserted that on purpose. A
database failure says nothing about whether the store exists, and
treating it as permanent is what discards the task, so that assertion is
inverted rather than preserved.
2026-07-29 12:25:18 +08:00
wizardchen 139ec1e6b8 fix(storage): align default provider fallback with STORAGE_ALLOW_LIST
Extract storage allowlist into internal/storageallowlist so KB creation
uses FirstAllowed when tenant default_provider is empty or disallowed.
Share pickUsableStorageProvider via editorResources for consistent UI
selection, and add regression tests for OBS status and allow-list defaults.
2026-07-15 11:05:00 +08:00
wizardchen 6ac1703198 Simplify KB duplicate API and improve naming/docs coverage.
Drop client-supplied target_id, generate IDs server-side, localize duplicate
names from request language, document the endpoint, and expand handler/client tests.
2026-07-08 20:55:54 +08:00
wizardchen 58b79876ae Add knowledge base duplicate flow 2026-07-08 20:55:54 +08:00
wizardchen 7855f36799 fix(model): block deletion when model is referenced by KB or agent
Reject model delete with HTTP 400 when the current tenant still has
knowledge bases or custom agents bound to the model ID.
2026-06-23 20:36:16 +08:00
wizardchen 48381fbaf5 feat: implement tenant default storage provider handling in Knowledge Base creation
This commit introduces functionality to utilize the tenant's default storage provider when creating a Knowledge Base. It includes updates to the frontend to load the default provider from settings and apply it during Knowledge Base initialization. Additionally, the backend has been enhanced to ensure that the storage provider is set correctly based on tenant configuration, improving consistency across the application. Tests have been added to verify the correct application of the default storage provider in various scenarios.
2026-05-29 13:47:32 +08:00
wizardchen bbcedbee63 feat(tests): enhance vector store tests with fake Elasticsearch server and add user pinning methods to knowledge base repository
Introduced a new helper function to create a fake Elasticsearch server for testing, improving the reliability of connection probes in vector store tests. Additionally, added methods for setting and listing user-specific knowledge base pins in the knowledge base repository, aligning with recent user pinning features.

Refs: #1303
2026-05-18 17:57:46 +08:00
ochan.kwon 0e8de6192c feat(knowledge-base): validate vector store bindings on create, copy, and delete
Wires KnowledgeBase.VectorStoreID and the ownership-aware retrieve factory
into the user-facing knowledge-base lifecycle:

- POST /knowledge-bases validates the requested vector_store_id against
  the caller's tenant scope and the engine registry. New error codes
  ErrVectorStoreBindingInvalid (2200) and ErrVectorStoreUnavailable (2201)
  distinguish the typed branches without echoing UUIDs to the client.
- GET / POST / PUT / PUT-pin responses embed the bound store's display
  metadata (name, source, engine_type, status) without exposing any
  connection credentials. Cross-tenant shared KBs receive a suppressed
  payload (vector_store_id stripped, source="shared") so operator-chosen
  store names cannot be enumerated across tenants.
- POST /knowledge-bases/copy synchronously rejects clones whose target
  has a different embedding model or vector store, before the async
  clone task is enqueued. The async clone worker re-applies the same
  checks for defense in depth.
- DELETE /vector-stores/:id refuses to remove a store with bound KBs,
  inside a transaction that row-locks the store on PostgreSQL and
  serializes via WAL on SQLite. unregister-from-registry is wrapped in
  defer/recover so a panic surfaces as a structured warning instead of
  silently leaking a stale engine.
- vector_store_id is immutable after creation. The GORM <-:create tag
  blocks every ORM update path; the service-layer DTO omits the field
  entirely; a reflection-based regression test catches any future
  maintainer who adds it back to either layer.
- Empty-string vector_store_id is normalized to nil at both the create
  path and inside SharesStoreWith, so rows persisted by callers that
  did not run Normalize first cannot trip false same-store comparisons.

Part of #993. Depends on #994 and #1310.
2026-05-18 15:58:46 +08:00