Make incremental embedding generation content-hash based and project-safe#56
Merged
cosmocoder merged 2 commits intomainfrom Mar 8, 2026
Merged
Make incremental embedding generation content-hash based and project-safe#56cosmocoder merged 2 commits intomainfrom
cosmocoder merged 2 commits intomainfrom
Conversation
…roject-safe - use content hashes as the source of truth for incremental freshness instead of relying on mtimes - distinguish full scans from partial file updates so stale embeddings are only pruned when safe - prune deleted file and document embeddings during full scans to keep review context current - scope project structure embeddings and retrieval by project path to avoid cross-project collisions - harden retrieval and summary invalidation so code review uses up-to-date project context
|
🎉 This PR is included in version 1.2.4 🎉 The release is available on: Your semantic-release bot 📦🚀 |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
content_hashinstead ofmtime, so unchanged files are skipped correctly even in CI environments--filesruns, and prune stale file/document embeddings only when a full scan makes that safeproject_path, validating file existence before using stored context, and refreshing project summaries when embedding inventory changes