refactor(git-history): retrofit to the ADR-0020 context contract

Description 450 -> 266 chars, body 1044 -> 462 words. The bisect procedure
moves to references/bisect.md.

The boundary clause read 'not writing or rewriting commits', which
disclaimed the cherry-pick and revert this skill's own Step 3 executes; it
now excludes authoring and rebasing only. Adds 'backport' so cherry-pick is
reachable by natural language at all, accepting 266 chars against a 250
soft target and a 400 ceiling.
This commit is contained in:
2026-08-30 13:10:53 +00:00
parent 261e5b5491
commit 7cb8e95379
12 changed files with 240 additions and 154 deletions

View File

@@ -0,0 +1,68 @@
---
topic: bisect
source_keys:
- git-scm-bisect-docs
---
# Finding a commit with `git bisect`
Read this when the question is *which commit changed the behaviour* and there is no string, file,
or line range to search the log for. Binary search reduces the trials from O(N) to O(log N).
## Manual flow
```bash
git bisect start
git bisect bad [HEAD] # mark current (or specified) as broken
git bisect good <commit> # mark known-good baseline
# Git checks out the midpoint; test it
git bisect good # test passes
git bisect bad # test fails
# Repeat until git reports "X is the first bad commit"
git bisect reset # return to the original HEAD
```
## Automated
With a test command available, use `git bisect run <cmd>`. Git reads the exit code: `0` good,
`1`–`124` bad, `125` skip (build broken), `126`–`127` POSIX shell errors, treated as bad, and
`128` or above aborts the session outright rather than marking the commit bad.
## Untestable commits
`git bisect skip` excludes a commit that cannot be built or tested without deciding good or bad
for it. When the first bad commit is adjacent to a skipped range, bisect reports that it cannot
pinpoint the culprit and lists the candidates — that is the precise answer the skip range allows,
not a failure.
## Undoing a wrong good/bad call
`git bisect log` prints the session's decision history. Save it, edit out the mistaken entry, and
resume from the corrected log rather than restarting the search:
```bash
git bisect log > bisect.log
# edit bisect.log, removing the wrong decision
git bisect reset && git bisect replay bisect.log
```
## Narrowing and speeding up
- `git bisect start HEAD v1.2 -- src/` restricts bisection to a path, cutting the trial count.
- `--no-checkout` updates the `BISECT_HEAD` ref instead of checking out a working tree — useful
for tests that do not need one, and automatic in bare repos.
- `--first-parent` follows only first parents at merges, finding the integration commit that
introduced a regression while ignoring broken side branches.
## Inspecting the remaining candidates
`git bisect visualize` (alias `view`) opens the suspects in gitk, falling back to `git log` when
no graphical display is detected. Add `--stat` or `-p` for a diffstat or full patches.
## Hunting a non-bug property change
`git bisect start --term-new <new> --term-old <old>` searches for any property change — a
performance regression, say — instead of a bug. Use the custom terms in place of `good` and `bad`
for the rest of the session.
Once the first bad commit is identified, return to Step 3 to act on it and Step 4 to report it.