Resolve uncertainty findings against referenced repository files - #117
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The reviewer receives only the diff, so an uncertainty finding can name a repository file it cannot see. With reviews.uncertaintyResolution enabled (default off, POSTIL_UNCERTAINTY_RESOLUTION override), a bounded post-scoring pass fetches the backtick-quoted repository paths from each uncertainty finding (filesystem locally, contents API at the PR head SHA on GitHub, capped at 3 files and 64KB per finding) and makes one additional model call that must return byte-verbatim evidence from the supplied material: refuted findings drop into the existing suppression accounting, confirmed findings get an evidence-based body, and everything else, errors included, keeps the original finding untouched. Generator and scorer prompts are unchanged.