0f3959516c
* fix(#4106): drop the orphaned test:mutation:since script `"test:mutation:since": "stryker run --incremental --since origin/next"` could not run. Stryker has no `--since` flag — verified against the pinned `@stryker-mutator/core` 9.6.1, whose options schema has no `since` property and whose CLI exits `error: unknown option '--since'`. It went unnoticed because nothing invokes it. `.github/workflows/mutation.yml` uses the per-module matrix instead: `scripts/mutation-matrix.cjs` computes the changed covered modules and each shard runs its own `npx stryker run --incremental --mutate "${MUTATE_GLOB}"`. That path works, so no gate ever exercised the script. It is still worth removing rather than leaving: its name makes it the obvious thing to reach for when a reviewer asks for a mutation score on changed scope, and the Commander parse error it produces says nothing about the matrix being the real entry point — the next person has to reverse-engineer mutation.yml to find that out. Delete rather than repoint. The issue offered both, and the maintainer had not picked; delete is the option that stays scoped to the reported bug. The suggested replacement (`node scripts/mutation-matrix.cjs --base origin/next`) emits a CI matrix rather than running mutants, so shipping it under a `test:mutation:*` name would be a second, differently-shaped claim, and documenting the per-module invocation in CONTRIBUTING.md is enhancement-shaped work that belongs in its own issue. The discovery command is named in the changeset instead. Flipping this PR to the pointer script is a one-line change if that is preferred. The regression test asserts that every `stryker` script in package.json passes only flags Stryker's own options schema defines. It carries its own control — the historical `--incremental --since origin/next` string is checked to still be rejected by the same predicate — so the sweep cannot go quietly vacuous if the remaining invocations lose their flags. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017zgWzB96uz3LVKdJePYTLR * chore(#4106): backfill the changeset PR number Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017zgWzB96uz3LVKdJePYTLR * docs(#4106): mark the changeset docs-exempt `type: Removed` makes docs-lint require a `docs/` change. Nothing under `docs/` or in CONTRIBUTING.md ever referenced `test:mutation:since` — the script was orphaned and could not run — so there is no documented behaviour to update. Using the gate's own per-fragment escape hatch rather than weakening the changeset type to dodge the requirement. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017zgWzB96uz3LVKdJePYTLR --------- Co-authored-by: Claude Opus 5 <noreply@anthropic.com> Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
723 B
723 B
type, pr
| type | pr |
|---|---|
| Removed | 4179 |
Dropped the test:mutation:since npm script — it passed --since, which Stryker 9.x does not accept (error: unknown option '--since'), so it could not run at all. Nothing invoked it: the mutation gate runs the per-module matrix from scripts/mutation-matrix.cjs instead, so no workflow regresses. To see which modules a change puts in scope, run node scripts/mutation-matrix.cjs --base origin/next --print. (#4106)