test(#1062): failing tests for checkup review-loop no-diff verification gap#1071
Draft
prompt-driven-github[bot] wants to merge 1 commit into
Draft
test(#1062): failing tests for checkup review-loop no-diff verification gap#1071prompt-driven-github[bot] wants to merge 1 commit into
prompt-driven-github[bot] wants to merge 1 commit into
Conversation
…ification gap Reproduces the bug in #1062 where the checkup review loop treats a fixer's self-reported success as a completed fix even when _commit_and_push_if_changed returns the "No changes to push." no-op sentinel and the PR head never advances. Adds class TestPostFixNoDiffPushVerification to tests/test_checkup_review_loop.py with 3 failing reproductions plus 1 happy-path regression guard. Refs #1062
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds failing tests that detect the bug reported in #1062: the checkup review loop reports a fixer success even when
_commit_and_push_if_changedreturned the no-op sentinel"No changes to push."and the PR head never advanced. The verifier then runs against an unchanged worktree with the fixer's claim injected into its prompt and_mark_findings_fixedcloses the finding without proof.Test Files
tests/test_checkup_review_loop.py— new classTestPostFixNoDiffPushVerification(4 tests)What This PR Contains
fixedafter a no-diff pushverification=verified; changed_files=none; fixed) is emittedRoot Cause
pdd/checkup_review_loop.py:1037-1112— the post-fix push guard treatspushed=Trueas success even when_commit_and_push_if_changedreturned the sentinel"No changes to push.". The fix is a localized guard insertion extending the existing pattern at lines 1042-1047 that already handles the analogous "failed push" case.See investigation steps in #1062 for full root-cause analysis.
Next Steps
pdd/checkup_review_loop.pyFixes #1062
Generated by PDD agentic bug workflow