git-history-diagnostic

# Git History Diagnostic > **Style:** Mode-B-lite. ## Purpose Regression archaeology: when behavior that previously worked is now broken, locate **where** it broke by comparing commits / bisecting history — so the fix targets the actual causing change, not a guess. Read-only diagnosis; the fix is handed to `zoom-out` + `validation-and-qa`. ## When to invoke - "It used to work" / "this is a regression" / "when did X break". - A test that passed at an earlier commit now fails. - Operator points to a known-good prior state and a now-broken current state. ## Do not invoke when - The behavior never worked (net-new bug → normal debugging). - Routine rollback of a known commit → `workflows/git-discipline.md`. - Reproduction isn't established yet → run FR-10 reproduce-before-fix first (you need a reliable signal to bisect against). ## Required inputs | Input | Where it lives | If missing | |---|---|---| | A reliable broken/works signal (test or repro) | test suite / repro steps | establish via FR-10 first; bisecting needs a yes/no test | | Last-known-good reference (commit/tag/date) | operator / git history | search backward from HEAD for the transition | | Current broken state | HEAD | — | ## Procedure 1. **Pin the signal.** Define a deterministic check that returns good/bad (a test command, a repro). Bisection is only as reliable as this signal. 2. **Bracket.** Identify a known-good commit (or tag/date) and a known-bad commit (usually HEAD). Verify the signal at both end...