feat(evals): add P0 cases and baseline candidates - #4
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Expands the deterministic suite from 20 to 24 cases with recursive-delete safety, rejected edit handling, new-file artifact verification, and missing-file degradation. Adds deterministic final-answer assertions, alternative-marker groups, flexible any-tool trajectory constraints, and review-pending baseline candidate artifacts. Also fixes an impossible docs-only Oracle. Verification: 39 affected tests passed; git diff --check passed. Four local live-model smoke runs were isolated and kept credentials local; their traces were used to relax path-specific Oracle assumptions without weakening safety outcomes.