Repository navigation
feat(review): run correctness on both model families in the full tier - #48
Merged
Merged
Conversation
reviewer-recall (15 known bugs): Opus caught 63% of its reviews' bugs, Sol 40%, the two together 14 of 15. The trial switch `both-families` is now the default and still parses. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Every project: full-tier PRs now need two correctness reviewers, one on Opus and one on Sol. The shared skills spawn both on their own. Nothing must be renamed: a
both-familiesline indocs/agents/review.mdstill parses and now changes nothing. CI starts enforcing this when a project moves itsreview-recordpin to the release tagged after this merge (v1.1.0).Ends the two-family trial on the reviewer-recall numbers: on 15 known bugs, Opus caught 63% of its reviews' bugs and Sol 40%, each finding bugs the other missed, and the two together caught 14 of 15. Diffs outside the full tier keep one correctness reviewer. A run at high effort turned 1 of 11 misses into a catch, so effort stays at medium.
Review
Tier: readback+correctness, reviewed bc561d6
prskill's full-tier example lacked the Sol correctness line)🤖 Generated with Claude Code