feat: prevent duplicate review comments with content-based dedup - #2
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Prevents the review agent from posting the same review comment repeatedly, even when the LLM reports the same concern on a different line.
Previously,
incrementalmode only skipped comments whose line range overlapped a previously-posted bot comment. With content-based dedup, a comment is also skipped when its wording matches a bot comment already posted on the same path, regardless of line.Changes
src/domain/post-comments.ts)normalizeContent— strips the summary marker, Markdown decoration, collapses whitespace, lowercases.jaccardSimilarity— token-set Jaccard coefficient.isDuplicateContent— normalized exact match or Jaccard similarity at-or-above threshold.isDuplicateComment— combines the existing line-overlap rule with the content rule (OR-ed), same path + RIGHT-side history only.incrementalis now enabled by default (actions/review/action.yml, README) — default changedfalse→true.content-based-deduplication(defaulttrue) — enable/disable the content rule.content-similarity-threshold(default0.8) — Jaccard threshold in(0, 1].src/cli.ts) —REVIEW_CONTENT_BASED_DEDUPLICATION,REVIEW_CONTENT_SIMILARITY_THRESHOLDenv vars wired throughReviewCliConfig→ReviewOptions→postReview.normalizeContent,jaccardSimilarity,resolveContentThreshold,isDuplicateContent,isDuplicateComment, andpostReviewcontent-based dedup integration.Validation
pnpm typecheck✅pnpm test— 215/215 ✅pnpm lint✅Notes
This branch is based on
mainand contains only the dedup feature (no formatting/refactor changes — those live in PR #1).