LanceDB infers the value column type from the first row in _createMetadataData().
Since vector_size (1024) was stored as a number, all subsequent string values
(embedding_provider, embedding_model_id) and booleans (indexing_complete) were
silently coerced to NaN/0/1, corrupting metadata.
On restart, _getStoredEmbeddingProfile() received NaN values, causing
needsRecreation=true every time — the database was dropped and recreated,
the file-hash cache cleared, and a full re-index triggered on every VS Code reopen.
Store all metadata values as strings to ensure consistent column type.
Extract `disposeAllInstancesAfterProviderAuthCallback` into a dedicated
module and invoke it from the provider OAuth callback handler instead of
coupling it to the ProviderAuth layer. This removes the InstanceStore
dependency from `ProviderAuth.layer`.
Additional changes:
- Add `--cloud-fork` CLI option to the run command for fetching sessions
from cloud and continuing locally
- Replace the Zod-bridged `Schema.Any` indexing config with a native
Effect `IndexingSchema` definition in kilo-indexing, propagating typed
config through the SDK OpenAPI spec
- Use `optionalOmitUndefined` for `recommendedIndex` to emit clean JSON
- Fix `request.source.signal` access by guarding with `instanceof Request`
- Replace `Effect.catchAllCause` with `Effect.catchCause` in telemetry
- Migrate tests from `BashTool` to `ShellTool`, extract `TestConfig`
fixture, and convert stats-subagent-cost tests to use `testEffect`
- Reorder SDK event union members to match updated OpenAPI schema
- Export `aggregateSessionStats` for Kilo regression test coverage
- Widen `setViewedSessions` input to accept readonly arrays
* feat: support Kilo-hosted indexing embeddings
* fix: format indexing settings
* fix: serialize local model persistence
* fix: annotate local model persistence
* fix: stabilize MCP OAuth browser test
* fix: annotate MCP OAuth test wait
* fix: keep KiloProvider under line cap
* fix: align Kilo indexing auth defaults
* fix(vscode): add missing indexing translations
* feat(indexing): fetch Kilo embedding model catalog
* fix(indexing): align Kilo embedding metadata fallback
* fix(gateway): remove unused indexing dependency
* fix(indexing): keep fallback catalog webview safe
* fix(agent-manager): include embedding model provider
* fix(vscode): provide embedding models in stories
* refactor(indexing): rely on Cloud embedding catalog
* fix(indexing): hydrate Kilo model metadata from Cloud
* fix(indexing): clear model when switching provider
Johnny Amancio