Files
msd-core/tests
Michel Moreira c9d3e66631 fix(#4341): reference-count the git-config sandbox the three guard suites share (#4389)
* fix(#4341): reference-count the git-config sandbox the three guard suites share

node:test evaluates every describe body during collection, before any test
runs, so the three isolateGlobalGitConfig() calls happened back to back and
each captured the PREVIOUS call's temp path as its "original": A captured
undefined, B captured A's path, D captured B's. Suite A's after() fires first
and restored undefined — deleting GIT_CONFIG_GLOBAL outright — so suites B and
D ran against the developer's real ~/.gitconfig for the rest of the file. A
also cleanup()'d a directory B still pointed at.

One sandbox now, with the true original captured once and released when the
last holder lets go; each returned restorer is idempotent, so an extra call
cannot release someone else's hold. The three call sites are unchanged.

Reproduced with a global core.hooksPath (via a fixture HOME carrying a
.gitconfig, so the developer's real one is never touched):

  next:   ℹ pass 291  ℹ fail 7   — "core.hooksPath is set to ...; a hook
                                    written to .../pre-commit would never run"
  branch: ℹ pass 296  ℹ fail 3

The 3 that remain are two suites (pr-subrepo, #3776 query commit --files) that
never called isolateGlobalGitConfig at all — the same class, a different gap,
and outside this issue's scope. Noted on the PR.

D0 is the regression guard and is deterministic on every lane: suite A's
after() runs before this suite's tests, so on the old helper GIT_CONFIG_GLOBAL
is already gone by then regardless of what the host's git config contains —
which is what makes it fail on CI, where the core.hooksPath that exposed the
defect is absent. Verified: full-file run reds on the old helper, greens on the
new one.

* test(#4341): clean filtered gitconfig sandboxes on exit

* test(#4341): retain exit cleanup until release succeeds
2026-09-09 02:31:45 +00:00
..