fix(entrypoint): forward review mode flags to run_agent.py - #20
Merged
Conversation
…ring Coverage penalty (apply_coverage_penalty) was adding up to 50 phantom points based on unreviewed file count rather than actual issues found. This inflated scores on both first-time reviews and verify-only runs. - Remove apply_coverage_penalty from PRScorer entirely - Add calculate_verify_score for verify-only runs: penalty = sum of still_present findings by severity/category, fixed findings = 0 - Enrich fix_verifications with severity/category from prior findings in review_job._write_findings so post_findings can score them - Coverage stats still tracked and displayed, just not penalized
…omment severity - calculate_verify_score() now accepts review_modes and applies the same severity multipliers (security, migration, etc.) as full reviews, fixing the penalty inconsistency between full review and fix verification runs - Posting loop uses mode-adjusted findings so inline comments show the correct severity (e.g. CRITICAL instead of WARNING for security findings) - Remove CI Gate and Next Steps sections from PR summary comment - Add e2e integration test (full review → fix verification, both posting) - Add fix verification integration test for auto-detect re-push flow
- Gitignore live integration tests (test_e2e_review_then_verify, test_fix_verification) that contain org-specific ADO config - Replace hardcoded org/repo/PR values in conftest.py with env vars - Replace hardcoded repo name in test_phase2_scoring.py with generic - Scrub company name from workspace_tools.py comment
…indings reach run_agent.py
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
"$@"toentrypoint.shso Docker CMD args (--verify-fixes,--check-new-findings) are forwarded torun_agent.pyTest plan
--verify-fixesflag, confirm it enters verify-only mode--check-new-findings, confirm it skips previous findings fetch@