HealthLog/.github/workflows/e2e.yml

name: e2e

on:
  pull_request:
    branches: [main]
  push:
    branches: [main]

permissions:
  contents: read

# Cancel in-progress runs when a new commit lands on the same PR.
concurrency:
  group: e2e-${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

jobs:
  # The suite outgrew the runner the same way the integration suite did: the
  # single job passed at ~18 minutes against a 20-minute cap, and the settings
  # geometry measurements pushed it over. Same remedy, split rather than raise:
  # Playwright shards, each with its own database and production build, and
  # a gate job below that carries the exact name branch protection requires.
  # Two shards grew to 14–19 minutes against the 20-minute cap once the
  # mobile route sweep landed, and a slow runner tipped them over; three
  # shards with a 30-minute cap leave room for both.
  shard:
    runs-on: ubuntu-24.04
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        shard: [1, 2, 3]
    name: e2e shard ${{ matrix.shard }}/3
    services:
      postgres:
        image: postgres:16-alpine
        env:
          POSTGRES_USER: healthlog
          POSTGRES_PASSWORD: healthlog
          POSTGRES_DB: healthlog
        ports:
          - 5432:5432
        options: >-
          --health-cmd "pg_isready -U healthlog"
          --health-interval 5s
          --health-timeout 5s
          --health-retries 10

    env:
      DATABASE_URL: postgresql://healthlog:healthlog@localhost:5432/healthlog?schema=public
      ENCRYPTION_KEYS: '{"v1":"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"}'
      ENCRYPTION_ACTIVE_KEY_ID: v1
      API_TOKEN_HMAC_KEY: bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
      AUTH_RP_NAME: HealthLog
      AUTH_RP_ID: localhost
      AUTH_RP_ORIGIN: http://localhost:3000
      SESSION_COOKIE_SECURE: "false"
      NODE_ENV: production

    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1

      - uses: pnpm/action-setup@ea17c68df8912ef543352723c149a84f56e3d413 # v6.1.0

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
        with:
          node-version: 22
          cache: pnpm

      - run: pnpm install --frozen-lockfile

      - run: pnpm db:generate

      - run: pnpm db:migrate:deploy

      - name: Cache Playwright browsers
        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
        with:
          path: ~/.cache/ms-playwright
          key: playwright-${{ runner.os }}-${{ hashFiles('pnpm-lock.yaml') }}
          restore-keys: |
            playwright-${{ runner.os }}-

      - run: pnpm exec playwright install --with-deps chromium

      # `pnpm build` (not bare `next build`): the prebuild hook generates
      # the versioned service-worker stamp AND the static i18n catalog
      # assets (public/i18n/<locale>.js) the client boots from — without
      # them every UI interaction waits on missing catalogs.
      # The repository-wide Next type worker exceeds V8's ~4 GiB default
      # old-space ceiling. Keep the larger heap scoped to this production
      # build only; tests and the runtime retain their normal limits.
      - run: NODE_OPTIONS=--max-old-space-size=8192 pnpm build

      # Client-bundle budget gate — rides this job because it is the one
      # place CI already has a production build on disk. Catches the
      # regressions the dead webpack-era tooling (ANALYZE=1, the old
      # bundle-report) let through: a statically imported message catalog
      # (~100 KB gz on every route) or a chart import bypassing the shared
      # chart-runtime boundary (a duplicated ~92 KB gz recharts chunk).
      - run: pnpm bundle-check

      - run: pnpm exec playwright test --shard=${{ matrix.shard }}/3
        env:
          E2E_BASE_URL: http://localhost:3000

      - name: Upload Playwright HTML report
        if: always()
        uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
        with:
          name: playwright-report-shard-${{ matrix.shard }}
          path: playwright-report/
          retention-days: 7
          if-no-files-found: ignore

      # The machine-readable report, for the skipped-spec check in the gate
      # job below. Only uploaded when the shard ran to completion, so a missing
      # artifact there means a shard that did not finish, not an empty suite.
      - name: Upload Playwright JSON report
        uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
        with:
          name: playwright-json-shard-${{ matrix.shard }}
          path: playwright-json/results.json
          retention-days: 7
          if-no-files-found: error

  # Branch protection requires a check named exactly "e2e". This job carries
  # that name and answers for both shards: it fails when any shard failed or
  # was cancelled, so a half-green matrix cannot satisfy the gate.
  e2e:
    runs-on: ubuntu-24.04
    needs: shard
    if: always()
    timeout-minutes: 5
    steps:
      - name: Every shard finished green
        run: |
          if [ "${{ needs.shard.result }}" != "success" ]; then
            echo "shard result: ${{ needs.shard.result }}"
            exit 1
          fi

      # A spec file that skipped every one of its tests reports green. The
      # check aggregates both shards' reports, because Playwright splits a
      # file's tests across shards; see the script's header for the allowlist.
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          sparse-checkout: scripts
      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
        with:
          node-version: 22
      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
        with:
          pattern: playwright-json-shard-*
          path: playwright-json
      - name: No spec file skipped all of its tests
        run: node scripts/check-e2e-skipped-specs.mjs playwright-json/*/results.json