test(#1062): failing tests for checkup review-loop no-diff verification gap

[prompt-driven-github]

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_changed returned 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_fixed closes the finding without proof.

Test Files

• Unit tests: tests/test_checkup_review_loop.py — new class TestPostFixNoDiffPushVerification (4 tests)

What This PR Contains

• 3 failing reproductions covering the bug across three observable channels:
  • rendered report still says fixed after a no-diff push
  • in-memory finding state is marked closed without evidence
  • verification-gap signal (verification=verified; changed_files=none; fixed) is emitted
• 1 happy-path regression guard (currently passes) so the eventual fix does not regress the success path
• All 97 pre-existing tests in the file still pass

Root Cause

pdd/checkup_review_loop.py:1037-1112 — the post-fix push guard treats pushed=True as success even when _commit_and_push_if_changed returned 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

1. Implement the no-op-push guard in pdd/checkup_review_loop.py
2. Verify the 3 reproduction tests now pass
3. Verify the happy-path regression guard still passes
4. Run full test suite to check for regressions
5. Mark PR as ready for review

Fixes #1062

---

Generated by PDD agentic bug workflow