fix: remove stale chunks for empty reingest - #23
Merged
Merged
Conversation
haolpku
requested changes
Sep 20, 2026
haolpku
left a comment
haolpku
left a comment
Collaborator
There was a problem hiding this comment.
Requesting changes because the empty-reingest path still calls provider.embed_texts([]) at the start of _upsert_chunks before reaching the new if not chunks branch. Real embedding APIs may reject an empty input even though the fake test accepts it, so stale chunks would remain. Please handle the empty replacement before embedding and add a provider fake that raises if called with an empty list.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
KB source replacement removed stale chunks when a file changed to new non-empty content, but an empty revision returned before cleanup and left the previous content searchable. Route empty revisions through the existing source-replacement cleanup so the live index and manifest reflect the current source. Added a deterministic re-ingest regression with a fake vector store. Validation: 2 KB ingest revision tests passed; no public API or index schema change; targets main.