fix: persist embedding state to S3 so stale vectors are deleted on re…#424
Merged
fix: persist embedding state to S3 so stale vectors are deleted on re…#424
Conversation
…-ingestion The state file (state/indexed-hashes.json) was written to the ephemeral CI runner's disk and lost when the runner terminated. Every subsequent run started with an empty previousHashes set, causing: - Vectors deleted: 0 — removed content vectors accumulated in Pinecone forever - All 4109 embeddings regenerated on every push (wasteful Bedrock API calls) Fix: download the state from S3 before embedding sync, upload it after. Uses embed-state/indexed-hashes.json in the existing CONTENT_BUCKET_NAME bucket. Co-Authored-By: claude-flow <ruv@ruv.net>
Checklist to merge a PR 🚀To merge this pull request, please take time to complete the checklist. What action did you perform?Review the corresponding checklist items for the action you performed and mark them done. Edit an existing content (MDX) pageChecklist
Edit an existing API reference pageChecklist
Add a new content (MDX) pageChecklist
Add a new API reference pageChecklist
|
KruthikGowda
approved these changes
Mar 30, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
…-ingestion
The state file (state/indexed-hashes.json) was written to the ephemeral CI runner's disk and lost when the runner terminated. Every subsequent run started with an empty previousHashes set, causing:
Fix: download the state from S3 before embedding sync, upload it after. Uses embed-state/indexed-hashes.json in the existing CONTENT_BUCKET_NAME bucket.