9723d2b7e0
Nine assertions drove a real fault through a real seam and then checked only that the call did not throw, or that a result was a string, a boolean, an array. Each passed whether the code was right or wrong. #3050 is the canonical instance of the shape: its counter-test asserted effectiveRoot was a string and never which root, so a silent misroute passed it. All nine now assert the exact verdict, derived from the production branch each one reaches and traced back to source rather than taken from the survey. One was worse than a weak assertion. The test targeting resolveWorktreeLinkage's main_worktree path used createTempGitProject, which always seeds .planning/ — so the reason was always has_local_planning and the git-dir comparison the test appears to exercise was unreachable from its own fixture. It was not asserting loosely, it was pointed at the wrong path. The fixture now builds a git project without .planning (projectDoc had to be disabled too, since it defaults to git and would have re-seeded it), and the test reaches the branch it names. Another had no reason assertion anywhere in the file while its four siblings all pinned theirs — the odd one out rather than a convention. The last is mine. The parity guard shipped in #3077 checked typeof and doesNotThrow across four ExecGitFn seams, and that PR described it as failing "the moment any site re-grows its own shape". It could not: a site returning a different value of the same type passed it. All four benign-passthrough outputs are derivable exact values, so it now asserts them and the claim is true. Test names that promised more than their assertions established are corrected to match what they prove. Refs #3057 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
15 KiB
15 KiB