gstack/.github/workflows/windows-free-tests.yml

name: Windows Free Tests

# The Windows-safe subset of the free suite on GitHub's free `windows-latest`
# runners. 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, Dia on macOS) are dispatch-only in native-qualification.yml.

on:
  pull_request:
    branches: [main]
  workflow_dispatch:
    inputs:
      record_durations:
        description: Record per-file Windows durations (artifact) instead of running the lane
        type: boolean
        default: false
  # free-durations-record.yml calls the recording path weekly.
  workflow_call:
    inputs:
      record_durations:
        type: boolean
        default: false

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:
  windows-plan:
    if: ${{ !inputs.record_durations }}
    runs-on: ubuntu-24.04
    timeout-minutes: 5
    outputs:
      matrix: ${{ steps.plan.outputs.matrix }}
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          persist-credentials: false
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2
      - id: plan
        name: Curate and balance the Windows-safe free suite
        # Six shards: ~85 s of Linux-measured work each, ~2.5 min on a
        # 4-vCPU Windows runner, so the lane lands near 4 min with setup.
        env:
          GSTACK_FREE_TEST_DURATIONS: scripts/free-test-durations-windows.json
        run: |
          matrix=$(bun run scripts/test-free-shards.ts --windows-only --ci-plan "$RUNNER_TEMP/windows-plan.json" --shards 6)
          echo "matrix=$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:
    needs: windows-plan
    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 }}

      # bun's install cache lives under ~/.bun/install/cache on every platform.
      - uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6
        with:
          path: ~/.bun/install/cache
          key: windows-bun-${{ hashFiles('bun.lock') }}
          # A lockfile bump starts from the previous cache instead of cold.
          restore-keys: |
            windows-bun-

      - 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: [windows-plan, windows-free-shard]
    runs-on: ubuntu-24.04
    timeout-minutes: 5
    steps:
      - name: Require the plan and every Windows shard
        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
        with:
          persist-credentials: false
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2
      - uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
        with:
          name: windows-plan
          path: ${{ runner.temp }}
      - uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
        with:
          pattern: windows-result-*
          merge-multiple: true
          path: ${{ runner.temp }}/windows-results
      - name: Require exact coverage and complete strict results
        run: bun run scripts/test-free-shards.ts --windows-only --ci-verify "$RUNNER_TEMP/windows-plan.json" --results "$RUNNER_TEMP/windows-results"

  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