orca/.github/workflows/win-crash-survival-e2e.yml

name: Windows Crash-Survival E2E

# #7742: build/install unsigned branch artifact on disposable CI, crash only main and require same daemon/shell survival, adoption and input without FailFast. Companion update proof tests installer survival; see relocation post-mortem.

on:
  workflow_dispatch:
    inputs:
      expect:
        description: Expected outcome profile
        required: true
        type: choice
        default: survival
        options:
          - survival
          - orphaned

permissions:
  contents: read

concurrency:
  group: win-crash-survival-e2e-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

jobs:
  crash-survival:
    name: crash-survival (packaged build)
    runs-on: windows-2022
    timeout-minutes: 50
    env:
      EXPECT: ${{ inputs.expect || 'survival' }}
      ORCA_BACKGROUND_LAUNCH: '1'

    steps:
      - name: Checkout
        uses: actions/checkout@v6
        with:
          # This job only builds and runs the harness locally; it never pushes.
          persist-credentials: false

      # Why: setup-node can restore pnpm's content-addressed store only after
      # the pnpm binary exists, avoiding repeat dependency downloads per run.
      - name: Setup pnpm
        uses: pnpm/setup@v2
        with:
          install: false

      - name: Setup Node.js
        uses: actions/setup-node@v6
        with:
          node-version-file: package.json
          check-latest: true
          cache: pnpm
          cache-dependency-path: |
            pnpm-lock.yaml
            mobile/pnpm-lock.yaml

      - name: Install dependencies
        run: pnpm install --frozen-lockfile

      # Why: cache the built installer by production build inputs, excluding
      # tests/reliability metadata so harness-only edits skip electron-builder.
      # The daemon relocation lives under src/, so product changes still rebuild.
      - name: Cache branch installer
        id: cache-installer
        uses: actions/cache@v4
        with:
          path: dist/orca-windows-setup.exe
          # The mobile page trees are in the key because beforePack builds the mobile web bundle
          # into the installer; config/** already covers the builder, the verifier and the manifest
          # writer. A mobile-only change must miss this cache, not reuse a stale exe.
          key: >-
            crash-survival-installer-${{ hashFiles(
              'src/**',
              '!src/**/*.test.*',
              '!src/**/*.bench.*',
              'config/**',
              '!config/**/*.test.*',
              '!config/reliability-gates.jsonc',
              '!config/max-lines-baseline.txt',
              '!config/vitest.config.ts',
              'native/**',
              'resources/**',
              'electron.vite.config.ts',
              'tsconfig.json',
              'vite.web.config.ts',
              '.npmrc',
              'package.json',
              'pnpm-lock.yaml',
              'pnpm-workspace.yaml',
              'mobile/package.json',
              'mobile/pnpm-lock.yaml',
              'mobile/app/**',
              'mobile/src/**',
              'mobile/web-entry/**'
            ) }}

      # Why: production edits miss the installer cache by design, but Electron
      # and NSIS downloads are lockfile-owned and need not be fetched again.
      - name: Cache electron-builder downloads
        if: steps.cache-installer.outputs.cache-hit != 'true'
        uses: actions/cache@v5
        with:
          path: |
            ~\AppData\Local\electron\Cache
            ~\AppData\Local\electron-builder\Cache
          key: crash-survival-electron-builder-${{ hashFiles('pnpm-lock.yaml') }}
          restore-keys: |
            crash-survival-electron-builder-

      # Why here: electron-builder's beforePack requires out/mobile-web, and the bundle
      # build resolves React Native and Expo from mobile/node_modules. Gated with the
      # build it feeds, so a cache hit does not pay for an install nothing consumes.
      - uses: ./.github/actions/install-mobile-dependencies
        if: steps.cache-installer.outputs.cache-hit != 'true'

      - uses: ./.github/actions/prepare-windows-agent-hook
        if: steps.cache-installer.outputs.cache-hit != 'true'

      - name: Build Windows installer (unsigned)
        if: steps.cache-installer.outputs.cache-hit != 'true'
        run: |
          node config/scripts/ensure-native-runtime.mjs --runtime=electron
          pnpm run build:desktop
          pnpm exec electron-builder --config config/electron-builder.config.cjs --win --publish never

      # Why: silent-install the branch build so the crash harness has a packaged
      # Orca.exe to drive. A clean CI runner installs to the default per-user
      # location (%LOCALAPPDATA%\Programs\Orca), which the harness auto-locates.
      - name: Silent-install branch build
        shell: pwsh
        run: |
          $exe = "dist/orca-windows-setup.exe"
          if (-not (Test-Path $exe)) { throw "Installer not found at $exe" }
          Start-Process -FilePath $exe -ArgumentList '/S' -Wait
          $installed = Join-Path $env:LOCALAPPDATA 'Programs/Orca/Orca.exe'
          if (-not (Test-Path $installed)) {
            $installed = Join-Path $env:LOCALAPPDATA 'Programs/orca/Orca.exe'
          }
          if (-not (Test-Path $installed)) { throw "Installed Orca.exe not found after silent install" }
          "ORCA_EXE=$installed" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8

      # Why: crash ONLY the app main and assert the relocated daemon + its shell
      # survive, then that relaunch adopts them and input causes no pwsh FailFast.
      - name: Run crash-survival harness
        id: harness
        shell: pwsh
        env:
          ORCA_E2E_DIAG_DIR: artifacts/diag
        run: |
          New-Item -ItemType Directory -Force artifacts | Out-Null
          $log = "artifacts/crash-survival-output.log"
          node tests/tools/win-crash-survival-e2e/run.mjs `
            --expect "$env:EXPECT" `
            --exe-path "$env:ORCA_EXE" `
            --soak-seconds 8 2>&1 | Tee-Object -FilePath $log
          exit $LASTEXITCODE

      - name: Upload crash-survival output
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: win-crash-survival-output
          path: |
            artifacts/crash-survival-output.log
            artifacts/diag/**
          retention-days: 7
          if-no-files-found: warn