name: e2e

on:
  push:
    branches: [master]
    paths:
      - ".github/workflows/e2e-tests.yml"
      - "backend/**"
      - "frontend/**"
      - "e2e/**"
      - "compose-e2e-test.yml"
      - "Dockerfile"

  pull_request:
    branches: [master]
    paths:
      - ".github/workflows/e2e-tests.yml"
      - "backend/**"
      - "frontend/**"
      - "e2e/**"
      - "compose-e2e-test.yml"
      - "Dockerfile"

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

jobs:
  # cheap gate: catches a compile break or a lint regression in the build-tagged suite
  # without paying for the docker build and the browser download
  vet:
    name: Vet
    timeout-minutes: 10
    runs-on: ubuntu-latest
    permissions:
      contents: read
    steps:
      - name: Checkout
        uses: actions/checkout@v7
        with:
          persist-credentials: false

      - name: Set up Go
        uses: actions/setup-go@v7
        with:
          go-version-file: e2e/go.mod
          cache-dependency-path: e2e/go.sum

      - name: Vet
        run: cd e2e && go vet -tags=e2e ./...

      - name: Lint
        uses: golangci/golangci-lint-action@v9
        with:
          version: v2.13.1
          working-directory: e2e
          args: --build-tags=e2e --config ../backend/.golangci.yml

  tests:
    name: Tests
    needs: vet
    # generous against the docker build plus two go test invocations: a job cancelled on
    # timeout skips its own failure steps, so the run would end with neither logs nor traces
    timeout-minutes: 45
    runs-on: ubuntu-latest
    permissions:
      contents: read
    steps:
      - name: Checkout
        uses: actions/checkout@v7
        with:
          persist-credentials: false

      - name: Set up Go
        uses: actions/setup-go@v7
        with:
          go-version-file: e2e/go.mod
          cache-dependency-path: e2e/go.sum

      # two directories: the driver (node plus the npm package) and the browser builds,
      # which include firefox and webkit for the rendering tests
      - name: Cache playwright driver and browsers
        uses: actions/cache@v6
        with:
          path: |
            ~/.cache/ms-playwright
            ~/.cache/ms-playwright-go
          key: playwright-${{ hashFiles('e2e/go.sum') }}
          restore-keys: playwright-

      - name: Build & start the stack
        run: COMPOSE_DOCKER_CLI_BUILD=1 DOCKER_BUILDKIT=1 docker compose -f compose-e2e-test.yml up -d --build --quiet-pull --wait

      - name: Install gotestsum
        run: go install gotest.tools/gotestsum@v1.13.0

      # each rerun is its own `go test` process carrying the same timeout, so the ceiling is
      # 8m for the first attempt plus 4 x 8m of reruns, inside the job's 45. a job cancelled on
      # timeout skips its own upload steps, which is the one outcome worth designing against.
      # four failures covers one test failing across all three engines, counted as its three
      # subtests plus their parent; more than that is a regression and should not be rerun.
      # a browser suite has a flake floor no amount of care removes, and one flake failing the
      # build is what makes people stop trusting it. one rerun, not two: a rerun stops at the
      # first pass, so each further attempt only widens the window in which a real intermittent
      # regression is absorbed. what needed a rerun is written to a report and uploaded, since
      # a green job is a job nobody reads the log of
      - name: Run e2e
        # shared across the rerun so it exercises the same threads as the attempt that failed
        env:
          E2E_RUN_ID: ${{ github.run_id }}-${{ github.run_attempt }}
        run: |
          cd e2e && gotestsum \
            --rerun-fails=1 \
            --rerun-fails-max-failures=4 \
            --rerun-fails-report=rerun-report.txt \
            --packages=./... \
            --format standard-verbose \
            -- -tags=e2e -count 1 -timeout 8m

      - name: Server logs on failure
        if: failure()
        run: docker compose -f compose-e2e-test.yml logs --tail=200

      - name: Upload browser traces and any rerun report
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: playwright-traces
          path: |
            e2e/traces/
            e2e/rerun-report.txt
          retention-days: 30
          if-no-files-found: ignore