openswarm/.github/workflows/e2e.yml

name: E2E (packaged app, mac + win)

# Builds the UNSIGNED packaged app on each OS, then runs the FULL deterministic
# gate against the real artifact plus the Playwright smoke. Signing/notarization +
# release upload are handled separately by release-windows.yml / release-macos.yml.
#
# The gate, per leg:
#   1. selftest-gate.js  - "test the tests": mutation-checks the gate's own logic
#      so a weakened guard fails loudly (runs first, no build needed).
#   2. build the packaged app.
#   3. verify-all.js     - boot/paint/serve/provenance + signature state +
#      resilience (locked-port, double-launch) + network/auth/9router. Provenance
#      goes GREEN here because the build is AT the checked-out commit.
#   4. mcp/selftest.js   - proves the Playwright "GUI hand" can launch + drive +
#      read the real app.
#   5. playwright npm test - the renderer-level smoke.
#   6. (windows) verify-installer --destructive - the runner is a CLEAN box with no
#      prior install, so the real install -> verify -> uninstall cycle is safe here
#      (it refuses to run where an install already exists).
#
# Matrix: windows-latest (Win Server 2022) + macos-13 (Intel x64) + macos-14
# (Apple Silicon) for arch+OS-version span, pinned for reproducibility. GitHub
# retired windows-2019 and ships no Win10 client image, so true Win10 coverage
# needs the SELF-HOSTED e2e-win10 job (activates when a runner labeled
# [self-hosted, windows, win10] exists and repo var WIN10_SELF_HOSTED=true).

on:
  push:
    branches: [eric/lock]
    paths-ignore: ['**.md', 'docs/**', '.gitleaksignore']
  pull_request:
  workflow_dispatch:

permissions:
  contents: read

jobs:
  e2e:
    strategy:
      fail-fast: false
      matrix:
        os: [windows-latest, macos-13, macos-14]
    runs-on: ${{ matrix.os }}
    timeout-minutes: 90
    env:
      CSC_IDENTITY_AUTO_DISCOVERY: 'false'
      GOOGLE_OAUTH_CLIENT_ID: 'e2e-placeholder.apps.googleusercontent.com'
      GOOGLE_OAUTH_CLIENT_SECRET: 'e2e-placeholder-secret'
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: '20.18.1'
      - uses: actions/setup-python@v5
        with:
          python-version: '3.13'

      # Test the tests first: cheap, pure, no build. If a guard stopped
      # discriminating good from broken, fail before spending a build.
      - name: Gate selftest (mutation)
        shell: bash
        run: node scripts/ci/selftest-gate.js

      # Preflight Layer 1+2+3+4 (unit, hang fuzz, failure rigs, race) - pure node, ~5s.
      - name: Preflight selftest (Layers 1+2)
        shell: bash
        run: node scripts/ci/selftest-preflight.js
      - name: Preflight failure rigs (Layer 3)
        shell: bash
        run: node scripts/ci/verify-preflight-rigs.js
      - name: Preflight race / cache (Layer 4)
        shell: bash
        run: node scripts/ci/verify-preflight-race.js

      # Preflight Layer 5: hostile-env scenarios. Each leg asserts the verdict
      # matches the expected envelope for that scenario; network=blocked
      # producing 'fail' instead of 'warn' is the false-positive bug class.
      - name: Preflight matrix (normal)
        shell: bash
        run: node scripts/ci/verify-preflight.js
      - name: Preflight matrix (network=blocked must -> warn)
        shell: bash
        env: { OPENSWARM_TEST_NETWORK: blocked }
        run: node scripts/ci/verify-preflight.js
      - name: Preflight matrix (appdata=readonly must -> fail)
        shell: bash
        env: { OPENSWARM_TEST_APPDATA: readonly }
        run: node scripts/ci/verify-preflight.js
      - name: Preflight matrix (lang=de-DE must stay -> ok)
        shell: bash
        env: { OPENSWARM_TEST_LANG: de-DE }
        run: node scripts/ci/verify-preflight.js

      - name: Build packaged app (Windows)
        if: startsWith(matrix.os, 'windows')
        shell: pwsh
        run: pwsh -NoProfile -File scripts/build-app-win.ps1

      - name: Build packaged app (macOS)
        if: startsWith(matrix.os, 'macos')
        shell: bash
        run: bash scripts/build-app.sh

      - name: Deterministic gate (verify-all)
        shell: bash
        run: node scripts/ci/verify-all.js

      - name: Install e2e deps
        shell: bash
        working-directory: e2e
        env:
          PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD: '1'
        run: npm ci

      - name: GUI hand selftest (MCP)
        shell: bash
        working-directory: e2e
        run: node mcp/selftest.js

      - name: Run E2E (Playwright)
        shell: bash
        working-directory: e2e
        run: npm test

      - name: Installer cycle (Windows, clean runner)
        if: startsWith(matrix.os, 'windows')
        shell: pwsh
        run: node scripts/ci/verify-installer.js --destructive

      - name: Upload E2E results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: e2e-results-${{ matrix.os }}
          path: e2e/results.json
          if-no-files-found: ignore
          retention-days: 14

      # Per-test traces: playwright-trace.zip (open via `npx playwright show-trace`),
      # events.jsonl (unified timestamped stream), mousepath.jsonl, backend.log.tail.
      # Always-upload so a failed run is debuggable without re-running.
      - name: Upload E2E visibility traces
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: e2e-traces-${{ matrix.os }}
          path: e2e/traces/
          if-no-files-found: ignore
          retention-days: 14

  # Real Windows 10 coverage. Skipped unless a self-hosted Win10 runner exists
  # and WIN10_SELF_HOSTED=true (repo variable). Mirrors the windows steps above.
  e2e-win10:
    if: ${{ vars.WIN10_SELF_HOSTED == 'true' }}
    runs-on: [self-hosted, windows, win10]
    timeout-minutes: 90
    env:
      CSC_IDENTITY_AUTO_DISCOVERY: 'false'
      GOOGLE_OAUTH_CLIENT_ID: 'e2e-placeholder.apps.googleusercontent.com'
      GOOGLE_OAUTH_CLIENT_SECRET: 'e2e-placeholder-secret'
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: '20.18.1'
      - uses: actions/setup-python@v5
        with:
          python-version: '3.13'
      - name: Gate selftest (mutation)
        shell: bash
        run: node scripts/ci/selftest-gate.js
      - name: Preflight selftest + rigs + race + matrix (Layers 1-5)
        shell: bash
        run: |
          node scripts/ci/selftest-preflight.js
          node scripts/ci/verify-preflight-rigs.js
          node scripts/ci/verify-preflight-race.js
          node scripts/ci/verify-preflight.js
          OPENSWARM_TEST_NETWORK=blocked node scripts/ci/verify-preflight.js
          OPENSWARM_TEST_APPDATA=readonly node scripts/ci/verify-preflight.js
      - name: Build packaged app (Windows)
        shell: pwsh
        run: pwsh -NoProfile -File scripts/build-app-win.ps1
      - name: Deterministic gate (verify-all)
        shell: bash
        run: node scripts/ci/verify-all.js
      - name: Install e2e deps
        shell: bash
        working-directory: e2e
        env:
          PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD: '1'
        run: npm ci
      - name: GUI hand selftest (MCP)
        shell: bash
        working-directory: e2e
        run: node mcp/selftest.js
      - name: Run E2E (Playwright)
        shell: bash
        working-directory: e2e
        run: npm test
      - name: Installer cycle (clean runner)
        shell: pwsh
        run: node scripts/ci/verify-installer.js --destructive