ci: move Windows and macOS out of the blocking path (#420)

The maintainer deferred Windows and macOS to the end of the redesign. The merge queue now runs Linux on Python 3.12-3.14, real ComfyUI, the frontend coverage shards and the Firefox/WebKit page workflows; pull requests keep the Linux 3.12 subset. The six Windows/macOS legs move to the new portability.yml, which runs on push to main, nightly and on demand, keeps the 27-minute limit and is never a required check. Red runs there are fixed at their cause before the cutover (#334).
2026-10-28 04:39:08 -07:00
parent 508dee4f59
commit 0c93777972
4 changed files with 103 additions and 25 deletions
@@ -0,0 +1,55 @@
+name: Windows and macOS
+
+permissions:
+  contents: read
+
+# Non-blocking portability runs (#420): never on pull requests or in the merge queue, and no context
+# here is a required check. A red run is fixed at its cause before the workspace cutover (#334).
+on:
+  push:
+    branches: [main]
+  schedule:
+    - cron: "17 3 * * *"
+  workflow_dispatch:
+
+# Every run gets its own group (run_id), so no main commit's run is ever cancelled or dropped as pending.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.run_id }}
+  cancel-in-progress: false
+
+env:
+  PYTHONFAULTHANDLER: "1"
+
+# Time limit rule as in test.yml: ceil(1.5 x the slowest of three recent green runs on main) + 3
+# minutes, never under 5. Measured 2026-10-26 in test.yml on runs 40257217681 (3be0ada),
+# 40240706568 (fb9134f), 40228167328 (f9835aa), before these legs moved here in #420:
+#   slowest py3.10 on windows-latest: 12m43s / 15m54s / 14m53s -> 27 min
+#     (macos 6m14s-8m30s, windows 11m42s-15m54s)
+jobs:
+  test:
+    name: py${{ matrix.python-version }} on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 27
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [windows-latest, macos-latest]
+        python-version: ["3.12", "3.13", "3.14"]
+
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v7
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+          cache-dependency-path: requirements-dev.txt
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements-dev.txt
+
+      - name: Run tests
+        run: python -m tests.run_suite -v
@@ -28,6 +28,8 @@ env:
 #   py matrix, slowest py3.10 on windows-latest: 12m43s / 15m54s / 14m53s -> 27 min
 #     (ubuntu 5m27s-6m27s, macos 6m14s-8m30s, windows 11m42s-15m54s)
 #     3.10 and 3.11 left the matrix and 3.14 joined it in #356; re-measure after three green main runs.
+#     Windows and macOS moved to portability.yml (#420), which keeps this 27-minute limit; this
+#     Linux-only matrix keeps it too until it is re-measured.
 #   real ComfyUI compatibility: 13m32s / 8m55s / 11m46s -> 24 min
 #   coverage gate (85%): 7m26s / 7m22s / 7m54s -> 15 min
 #   perf budget 30s / 29s / 27s, black and flake8 39s / 37s / 39s,
@@ -35,8 +37,9 @@ env:
 #   all tests: a result check without setup, 5 min (the floor)
 #
 # Pull requests run a fast subset (#420): Python 3.12 on ubuntu-latest, coverage, lint and frontend
-# modules. The merge queue (merge_group), pushes to main and manual runs take the full matrix and the
-# real ComfyUI job. "all tests" is the required gate that holds the queue to that full set.
+# modules. The merge queue (merge_group), pushes to main and manual runs add Python 3.13 and 3.14 on
+# Linux and the real ComfyUI job. "all tests" is the required gate that holds the queue to that set.
+# Windows and macOS run in portability.yml (push to main, nightly, on demand) and never gate a merge.
 jobs:
  test:
    name: py${{ matrix.python-version }} on ${{ matrix.os }}
@@ -45,7 +48,7 @@ jobs:
    strategy:
      fail-fast: false
      matrix:
-        os: ${{ github.event_name == 'pull_request' && fromJSON('["ubuntu-latest"]') || fromJSON('["ubuntu-latest", "windows-latest", "macos-latest"]') }}
+        os: [ubuntu-latest]
        python-version: ${{ github.event_name == 'pull_request' && fromJSON('["3.12"]') || fromJSON('["3.12", "3.13", "3.14"]') }}

    steps:
@@ -273,11 +273,12 @@ gh run view <run id> --json jobs                          # shows a job that alr
 gh run view --job <job id> --log-failed                   # that job's failed log, at once
 ```

-Windows, macOS, Python 3.13/3.14, real ComfyUI and Firefox/WebKit failures
-first show up in the merge queue, on the merge-group commit rather than the
+Python 3.13/3.14, real ComfyUI and Firefox/WebKit failures first show up in the
+merge queue, on the merge-group commit rather than the
 pushed one. Find that run with `gh run list --event merge_group --workflow test.yml`
 (or `viewerjs-check.yml`) and match its head branch
-(`gh-readonly-queue/main/pr-<N>-...`).
+(`gh-readonly-queue/main/pr-<N>-...`). Windows and macOS failures show up only
+after the merge, in `gh run list --workflow portability.yml`.

 Start fixing as soon as a failed log shows the cause, but push the fix only after
 the run for that commit has finished: pull-request runs use `cancel-in-progress`,
@@ -527,12 +528,11 @@ Before changing paths, SQLite, streams, restore or cleanup:
  open with `FirstWriterHold`) and give peers that must all succeed the
  ordinary busy timeout; cross-thread handoffs wait on events with generous
  ceilings, never a short wall clock (#242).
- Run native Windows CI early for these changes: pull requests run only Linux, so
-  start the full matrix on the branch with `gh workflow run test.yml --ref <branch>`.
-  That run reports the same check names on the PR head, and a red one can hold
-  the PR out of the queue until it is fixed.
-  Include a Windows impact and evidence note in the PR. All nine OS/Python
-  combinations (they run again in the merge queue) and every applicable
+- Run native Windows CI early for these changes. Pull requests and the merge
+  queue run only Linux, so start Windows and macOS on the branch with
+  `gh workflow run portability.yml --ref <branch>`.
+  Include a Windows impact and evidence note in the PR. All six Windows/macOS
+  combinations in that run, every Linux leg and every applicable
  exact-head check must pass before merge. Portable `ntpath`/`PureWindowsPath`
  controls do not establish native filesystem, locking or cleanup success.

@@ -544,13 +544,14 @@ what runs:
 | Job | `pull_request` | `merge_group`, push to `main`, `workflow_dispatch` |
 | --- | --- | --- |
 | `py3.12 on ubuntu-latest` | runs | runs |
-| other Python/OS legs (3.12-3.14 x Linux/Windows/macOS) | not created | run |
+| `py3.13 on ubuntu-latest`, `py3.14 on ubuntu-latest` | not created | run |
 | `real ComfyUI compatibility` | skipped | runs |
 | `coverage gate (85%)`, `black and flake8`, `frontend modules`, `bandit (high severity)` | run | run |
 | `frontend coverage (shard N/3)`, `frontend coverage (merge)` (vendor pins and tooling tests on shard 3) | run | run |
 | `page workflows (firefox\|webkit, shard N/2)` | skipped | run |
 | `all tests`, `viewerjs` (gates) | run | run |
 | `perf budget` | skipped | push and dispatch only (not in the queue) |
+| `py3.12-3.14 on windows-latest/macos-latest` (`portability.yml`) | not run | push to `main`, nightly, `workflow_dispatch` only; never required |

 GitHub has one required set for pull requests and the queue. A job skipped by
 its `if:` reports Success. A dropped matrix leg never reports, so it would stay
@@ -560,8 +561,14 @@ guarantee:
  to be skipped.
 - On every other event they require every job to succeed.

-So a merge group cannot turn green unless all nine Python/OS legs, real ComfyUI
-and the four browser shards passed. `tests/vendor/ci-workflow.test.mjs` pins the
+So a merge group cannot turn green unless all three Linux Python legs, real
+ComfyUI and the four browser shards passed.
+
+Windows and macOS (Python 3.12-3.14) are out of the blocking path for now
+(maintainer, 2026-10-28). They run in `portability.yml` on every push to `main`,
+nightly and on demand, and no context there is required. A red portability run
+is still a failure: fix it at its cause, not by rerunning, and have every one
+green before the workspace cutover (#334). `tests/vendor/ci-workflow.test.mjs` pins the
 event split and runs both gate scripts for each event.

 ## Required merge checks
@@ -248,7 +248,8 @@ test('browser job timeouts keep a real margin over measured runs', () => {
 });

 // Every job is bounded (#350): a hang ends at a measured limit instead of GitHub's 6-hour default.
-const BOUNDED_WORKFLOWS = ['test.yml', 'code-quality.yml', 'viewerjs-check.yml'];
+const GATING_WORKFLOWS = ['test.yml', 'code-quality.yml', 'viewerjs-check.yml'];
+const BOUNDED_WORKFLOWS = [...GATING_WORKFLOWS, 'portability.yml'];
 const readWorkflow = name => readFileSync(new URL(`../../.github/workflows/${name}`, import.meta.url), 'utf8');

 test('every job in the CI workflows has a numeric timeout-minutes', () => {
@@ -304,19 +305,30 @@ test('the bandit pre-commit hook fails at the severity CI enforces and passes ev
 // Event split (#420): pull requests run a fast subset, the merge queue and main run everything.
 const testJobs = () => jobs(readWorkflow('test.yml'));

-test('the Python matrix is one leg on a pull request and the full matrix on every other event', () => {
+test('the Python matrix is Linux 3.12 on a pull request and Linux 3.12-3.14 on every other event', () => {
    const body = testJobs().get('test');
-    const lists = key => {
-        const match = new RegExp(`^ {8}${key}: \\$\\{\\{ github\\.event_name == 'pull_request' && fromJSON\\('(\\[[^\\]]*\\])'\\) \\|\\| fromJSON\\('(\\[[^\\]]*\\])'\\) \\}\\}$`, 'm').exec(body);
-        assert.ok(match, `${key} is chosen by event`);
-        return { pr: JSON.parse(match[1]), other: JSON.parse(match[2]) };
-    };
-    assert.deepEqual(lists('os'), { pr: ['ubuntu-latest'], other: ['ubuntu-latest', 'windows-latest', 'macos-latest'] });
-    assert.deepEqual(lists('python-version'), { pr: ['3.12'], other: ['3.12', '3.13', '3.14'] });
+    assert.deepEqual(matrixList(body, 'os'), ['ubuntu-latest'], 'Windows and macOS never gate a merge');
+    const match = /^ {8}python-version: \$\{\{ github\.event_name == 'pull_request' && fromJSON\('(\[[^\]]*\])'\) \|\| fromJSON\('(\[[^\]]*\])'\) \}\}$/m.exec(body);
+    assert.ok(match, 'python-version is chosen by event');
+    assert.deepEqual({ pr: JSON.parse(match[1]), other: JSON.parse(match[2]) }, { pr: ['3.12'], other: ['3.12', '3.13', '3.14'] });
    assert.match(body, /^ {6}fail-fast: false$/m);
    assert.match(body, /^ {4}name: py\$\{\{ matrix\.python-version \}\} on \$\{\{ matrix\.os \}\}$/m);
 });

+test('Windows and macOS run 3.12-3.14 on main, nightly and on demand, never on a PR or in the queue', () => {
+    const text = readWorkflow('portability.yml');
+    const triggers = text.slice(text.indexOf('\non:'), text.indexOf('\nconcurrency:'));
+    for (const event of ['push', 'schedule', 'workflow_dispatch']) assert.match(triggers, new RegExp(`^ {2}${event}:`, 'm'));
+    for (const event of ['pull_request', 'merge_group']) assert.doesNotMatch(triggers, new RegExp(`^ {2}${event}`, 'm'));
+    assert.match(triggers, /^ {4}branches: \[main\]$/m, 'push runs only for main');
+    const body = jobs(text).get('test');
+    assert.deepEqual(matrixList(body, 'os'), ['windows-latest', 'macos-latest']);
+    assert.deepEqual(matrixList(body, 'python-version'), ['"3.12"', '"3.13"', '"3.14"']);
+    assert.match(body, /^ {6}fail-fast: false$/m);
+    assert.match(body, /^ {8}run: python -m tests\.run_suite -v$/m);
+    assert.doesNotMatch(text, /cancel-in-progress: true|cancel-in-progress: \$/, 'no portability run is cancelled');
+});
+
 test('real ComfyUI runs only outside pull requests; the other test.yml checks run on every event', () => {
    const found = testJobs();
    assert.match(found.get('comfyui'), QUEUE_ONLY_IF);
@@ -338,7 +350,7 @@ test('all tests needs every gating test.yml job and requires the full set outsid
 });

 test('the CI workflows run on pull_request, merge_group and push without path filters', () => {
-    for (const name of BOUNDED_WORKFLOWS) {
+    for (const name of GATING_WORKFLOWS) {
        const text = readWorkflow(name);
        const triggers = text.slice(text.indexOf('\non:'), text.indexOf('\n', text.indexOf('\non:') + 1) + 400);
        for (const event of ['merge_group', 'pull_request', 'push']) {
@@ -357,4 +369,5 @@ test('every required check reports on a pull request and the gates carry the ful
    ].sort());
    assert.equal(contexts.filter(context => /^py/.test(context)).length, 1,
        'a dropped matrix leg never reports on a pull request, so it cannot be required');
+    assert.ok(!contexts.some(context => /windows|macos/.test(context)), 'Windows and macOS never gate a merge');
 });