Files
gstack/.github/workflows/windows-free-tests.yml
garrytan f02e95e158 Merge main dd9834d44d (v1.92.61.0) into gsta203-pr3-subshards (rule 19 grant, GSTA-203 PR 3)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

# Conflicts:
#	.github/workflows/free-tests.yml
#	docs/TESTING_INTERNALS.md
#	scripts/harness-version.json
#	scripts/lib/shard-jobs.ts
#	scripts/test-free-shards.ts
#	test/shard-jobs.test.ts
#	test/windows-native-workflows.test.ts
2026-11-02 05:56:20 +00:00

371 lines
16 KiB
YAML

name: Windows Free Tests
# Nightly, not a PR gate. Windows has minimal support (docs/support-tiers.md):
# the required Windows check is windows-smoke.yml (./setup plus the core
# skills). This workflow runs the curated Windows-safe subset of the free suite
# on main every night and on workflow_dispatch, and never blocks a pull
# request. A red nightly run gets a fix only when it shows an install, startup
# or core-workflow break; other Windows-only failures close as won't fix.
#
# scripts/test-free-shards.ts --windows-only is the single source of truth for
# which files run: POSIX-bound tests (bin/ shebang spawns, raw /tmp paths,
# /bin/sh, mode bitmasks, the Bun-driven browse server) are excluded by
# pattern there, with explicit force-include and known-incompatible lists.
# Every run prints the curated count and top exclusion reasons in the job
# summary so a shrinking subset is visible.
#
# Same plan/run/verify model as free-tests.yml: one duration-balanced plan of
# the curated files, one shard per Windows job, and an aggregate that requires
# every strict result and exact coverage. The plan and the verify step are
# static (file contents and the git revision), so they run on Linux. Packing
# reads Windows-measured durations (scripts/free-test-durations-windows.json):
# Windows-only files such as the native cookie job cost minutes there and
# nothing on Linux. Refresh it with a `record_durations` dispatch and commit
# the artifact.
#
# Native browser qualification campaigns (Windows cookie extraction, launch
# diagnostics) are dispatch-only in native-qualification.yml.
#
# One full suite per tree (GSTA-156, docs/pregate.md#ci-reuse), as in
# free-tests.yml: the aggregate uploads `tested-tree` only after strict
# verification passes, and a push to main whose merged pull request already
# ran this workflow green on the same tree reuses that run. Pull request,
# dispatch and duration-recording runs never consume.
on:
# 09:17 UTC, about 2 AM Pacific, on the default branch (main).
schedule:
- cron: '17 9 * * *'
workflow_dispatch:
inputs:
record_durations:
description: Record per-file Windows durations (artifact) instead of running the lane
type: boolean
default: false
windows_jobs:
description: 'Sub-shard experiments only: sub-shards per Windows shard (--shard-jobs), 1-4 (empty keeps WINDOWS_FREE_JOBS). Never cite such a run as a PR result.'
type: string
default: ''
# free-durations-record.yml calls the recording path weekly.
workflow_call:
inputs:
record_durations:
type: boolean
default: false
# k in `--ci-plan --shard-jobs k`: each Windows shard runs min(k, its parallel
# files) sandboxed sub-shards side by side (scripts/lib/shard-jobs.ts).
env:
WINDOWS_FREE_JOBS: '1'
concurrency:
group: windows-free-${{ github.event.pull_request.number || github.run_id }}
cancel-in-progress: true
# Test-only lane — no token writes.
permissions:
contents: read
jobs:
# Main pushes only, and the one job with actions: read; see free-tests.yml.
# A skipped or failed reuse job runs every job below as before.
reuse:
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
runs-on: ubuntu-24.04
timeout-minutes: 5
permissions:
contents: read
actions: read
outputs:
reused: ${{ steps.find.outputs.reused }}
run_id: ${{ steps.find.outputs.run_id }}
run_url: ${{ steps.find.outputs.run_url }}
tree: ${{ steps.find.outputs.tree }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
persist-credentials: false
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
with:
bun-version: 1.4.2
- id: find
name: Find a green pull request or dispatch run of this exact tree
env:
GH_TOKEN: ${{ github.token }}
run: bun run scripts/ci-tree-reuse.ts find --workflow windows-free-tests.yml --profile ci-reuse/windows-free-tests
windows-plan:
needs: reuse
if: ${{ !cancelled() && !inputs.record_durations && (needs.reuse.result != 'success' || needs.reuse.outputs.reused != 'true') }}
runs-on: ubuntu-24.04
timeout-minutes: 5
outputs:
matrix: ${{ steps.plan.outputs.matrix }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
persist-credentials: false
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
with:
bun-version: 1.4.2
- id: plan
name: Curate and balance the Windows-safe free suite
# Six shards: ~85 s of Linux-measured work each, ~2.5 min on a
# 4-vCPU Windows runner, so the lane lands near 4 min with setup.
env:
GSTACK_FREE_TEST_DURATIONS: scripts/free-test-durations-windows.json
JOBS_OVERRIDE: ${{ inputs.windows_jobs }}
run: |
set -euo pipefail
jobs="${JOBS_OVERRIDE:-$WINDOWS_FREE_JOBS}"
case "$jobs" in
''|*[!0-9]*) echo "::error::windows_jobs '$jobs' is not a whole number"; exit 1 ;;
esac
if [ "$jobs" -lt 1 ] || [ "$jobs" -gt 4 ]; then echo "::error::windows_jobs $jobs is outside 1-4"; exit 1; fi
if [ "$jobs" != "$WINDOWS_FREE_JOBS" ]; then
echo "- Sub-shard experiment: $jobs sub-shards per Windows shard (default $WINDOWS_FREE_JOBS); not a PR Windows Free Tests result" >> "$GITHUB_STEP_SUMMARY"
fi
matrix=$(bun run scripts/test-free-shards.ts --windows-only --ci-plan "$RUNNER_TEMP/windows-plan.json" --shards 6 --shard-jobs "$jobs")
echo "matrix=$matrix" >> "$GITHUB_OUTPUT"
- uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
with:
name: windows-plan
path: ${{ runner.temp }}/windows-plan.json
if-no-files-found: error
windows-free-shard:
# gstack-pregate reads a job keyed on a dispatch input as manual, never a
# PR obligation; this lane runs only nightly or by hand.
needs: [windows-plan, reuse]
if: ${{ !cancelled() && !inputs.record_durations && needs.windows-plan.result == 'success' && (needs.reuse.result != 'success' || needs.reuse.outputs.reused != 'true') }}
runs-on: windows-latest
timeout-minutes: 15
strategy:
fail-fast: false
matrix: ${{ fromJSON(needs.windows-plan.outputs.matrix) }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
persist-credentials: false
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
with:
bun-version: 1.4.2
- uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
with:
node-version: 24.18.0
- uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
with:
name: windows-plan
path: ${{ runner.temp }}
# No bun install cache: restoring the ~450 MB entry took 33-42 s per
# shard, a cold install 16-17 s (GSTA-203 PR 1 A/B, 3 runs per arm).
- name: Configure git identity (required by tests that init temp repos)
run: |
git config --global user.email "windows-ci@gstack.test"
git config --global user.name "Windows CI"
git config --global init.defaultBranch main
shell: bash
- name: Install dependencies
run: bun install --frozen-lockfile
- name: Build server-node.mjs (required by Windows browse path)
# browse/src/cli.ts throws at module load on Windows if server-node.mjs
# is missing — Bun can't drive Playwright's Chromium on Windows
# (oven-sh/bun#4253), so any test that transitively loads cli.ts needs
# the Node-compatible server bundle. The full build is unnecessary.
run: bash browse/scripts/build-node-server.sh
shell: bash
- name: Generate host SKILL.md outputs (.agents, .factory)
# Golden-file tests read gitignored generated host outputs.
run: bun run gen:skill-docs --host all
shell: bash
- name: Install Chromium for the Node worker smoke
run: bunx playwright install chromium
- name: Run Windows-safe shard
env:
# Same policy as the required Linux lane: an attributed failure gets
# one serial retry (cap 5 files, truncation veto) and a clean retry
# is a loud flaky pass, appended to the ledger uploaded below and
# listed in the aggregate job summary.
GSTACK_FREE_RETRY_FLAKY: '1'
GSTACK_FLAKE_LEDGER: ${{ runner.temp }}/flake-ledger.jsonl
TEMP: ${{ runner.temp }}
TMP: ${{ runner.temp }}
run: bun run test:windows --ci-run "$RUNNER_TEMP/windows-plan.json" --shard ${{ matrix.shard }} --result "$RUNNER_TEMP/windows-results/shard-${{ matrix.shard }}.json"
shell: bash
- name: Upload strict shard result
if: always()
uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
with:
name: windows-result-${{ matrix.shard }}
path: ${{ runner.temp }}/windows-results/*.json
if-no-files-found: error
# A red lane must carry the WHY: the runner's quiet console names files,
# not causes, so complete shard logs are kept on every run.
- name: Upload full shard logs
if: always()
uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
with:
name: windows-free-test-shard-logs-${{ matrix.shard }}
path: |
.context/free-test-logs/gstack-free-test-*.log
${{ runner.temp }}/gstack-free-test-*.log
include-hidden-files: true
if-no-files-found: ignore
- name: Upload flake ledger
if: always()
uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
with:
name: flake-ledger-windows-${{ matrix.shard }}
path: ${{ runner.temp }}/flake-ledger.jsonl
if-no-files-found: ignore
retention-days: 90
windows-free-tests:
if: ${{ always() && !inputs.record_durations }}
needs: [reuse, windows-plan, windows-free-shard]
runs-on: ubuntu-24.04
timeout-minutes: 5
steps:
- name: Take the reuse path only for a verified main-push reuse
id: route
env:
REUSE_RESULT: ${{ needs.reuse.result }}
REUSED: ${{ needs.reuse.outputs.reused }}
REUSE_RUN_ID: ${{ needs.reuse.outputs.run_id }}
REUSE_RUN_URL: ${{ needs.reuse.outputs.run_url }}
REUSE_TREE: ${{ needs.reuse.outputs.tree }}
run: |
set -eu
if [ "$REUSE_RESULT" != success ] || [ "$REUSED" != true ]; then
echo 'reused=false' >> "$GITHUB_OUTPUT"
exit 0
fi
test "$GITHUB_EVENT_NAME" = push
test "$GITHUB_REF" = refs/heads/main
case "$REUSE_RUN_ID" in ''|*[!0-9]*) echo "::error::the reuse job named no run id"; exit 1 ;; esac
case "$REUSE_TREE" in ''|*[!0-9a-f]*) echo "::error::the reuse job named no tree"; exit 1 ;; esac
test "$REUSE_RUN_URL" = "$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$REUSE_RUN_ID"
echo "Reused $REUSE_RUN_URL, which passed on tree $REUSE_TREE; this push ran no suite of its own." >> "$GITHUB_STEP_SUMMARY"
echo 'reused=true' >> "$GITHUB_OUTPUT"
- name: Require the plan and every Windows shard
if: steps.route.outputs.reused != 'true'
env:
PLAN_RESULT: ${{ needs.windows-plan.result }}
SHARD_RESULT: ${{ needs.windows-free-shard.result }}
run: |
set -eu
test "$PLAN_RESULT" = success
test "$SHARD_RESULT" = success
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
if: steps.route.outputs.reused != 'true'
with:
persist-credentials: false
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
if: steps.route.outputs.reused != 'true'
with:
bun-version: 1.4.2
- uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
if: steps.route.outputs.reused != 'true'
with:
name: windows-plan
path: ${{ runner.temp }}
- uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
if: steps.route.outputs.reused != 'true'
with:
pattern: windows-result-*
merge-multiple: true
path: ${{ runner.temp }}/windows-results
- name: Require exact coverage and complete strict results
if: steps.route.outputs.reused != 'true'
run: bun run scripts/test-free-shards.ts --windows-only --ci-verify "$RUNNER_TEMP/windows-plan.json" --results "$RUNNER_TEMP/windows-results"
# Only after strict verification passed; the reuse path never reaches here.
- name: Record the tested tree
if: steps.route.outputs.reused != 'true'
env:
PR_HEAD_SHA: ${{ github.event.pull_request.head.sha }}
run: bun run scripts/ci-tree-reuse.ts record --plan "$RUNNER_TEMP/windows-plan.json" --results "$RUNNER_TEMP/windows-results" --os Windows --out "$RUNNER_TEMP/tested-tree/tree.json"
- name: Upload the tested tree
if: steps.route.outputs.reused != 'true'
uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
with:
name: tested-tree
path: ${{ runner.temp }}/tested-tree/tree.json
if-no-files-found: error
windows-record-durations:
if: ${{ inputs.record_durations }}
runs-on: windows-latest
timeout-minutes: 30
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
persist-credentials: false
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
with:
bun-version: 1.4.2
- uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
with:
node-version: 24.18.0
- name: Prepare the same inputs as a Windows shard
shell: bash
run: |
git config --global user.email "windows-ci@gstack.test"
git config --global user.name "Windows CI"
git config --global init.defaultBranch main
bun install --frozen-lockfile
bash browse/scripts/build-node-server.sh
bun run gen:skill-docs --host all
bunx playwright install chromium
# Records into this checkout's default seed path: GSTACK_FREE_TEST_DURATIONS
# would leak into every timed test, and seed-reading tests would then read
# the half-written recording instead of their fixtures.
- name: Time every Windows-safe file alone
id: record
shell: bash
env:
TEMP: ${{ runner.temp }}
TMP: ${{ runner.temp }}
run: |
set -o pipefail
bun run test:windows --record-durations --wall-timeout 1200 2>&1 | tee "$RUNNER_TEMP/record.log"
- name: Name the recording as the Windows seed
id: seed
if: always() && steps.record.outcome != 'skipped'
shell: bash
run: |
grep -q 'wrote [0-9]* durations to' "$RUNNER_TEMP/record.log" || { echo "::error::The recording was interrupted; no Windows seed to upload."; exit 1; }
cp scripts/free-test-durations.json "$RUNNER_TEMP/free-test-durations-windows.json"
sed -n '/failed while recording:/,$p' "$RUNNER_TEMP/record.log" | sed 's/\r$//' | { grep -E '^ ✗ [^ ]+$' || true; } | sed 's/^ ✗ //' > "$RUNNER_TEMP/record-failures.txt"
- name: Upload full recording logs
if: always()
uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
with:
name: windows-record-durations-logs
path: |
.context/free-test-logs/gstack-free-test-*.log
${{ runner.temp }}/gstack-free-test-*.log
include-hidden-files: true
if-no-files-found: ignore
- uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
if: always() && steps.seed.outcome == 'success'
with:
name: free-test-durations-windows
path: |
${{ runner.temp }}/free-test-durations-windows.json
${{ runner.temp }}/record-failures.txt
if-no-files-found: error