---
name: 'E2E Distributed Tests'

on:
  pull_request:
    # The suite's dependency graph is 99 packages, so an allowlist of paths
    # silently stops guarding the moment code moves. At ~75s the job is cheap
    # enough to run unless the diff is confined to paths it provably cannot
    # reach. See .agents/ci-caching.md.
    paths-ignore:
      - 'gallery/**'
      - 'docs/**'
      - 'examples/**'
      - '**/*.md'
  push:
    branches:
      - master

concurrency:
  group: ci-tests-e2e-distributed-${{ github.event.pull_request.number || github.sha }}-${{ github.repository }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' }}

jobs:
  tests-e2e-distributed:
    runs-on: ubuntu-latest
    # Advisory because it is deliberately not in branch protection, so a failure
    # is a visible red X rather than a blocked merge. Promoting it to a required
    # check is a repository-settings change, to be made once it has a track
    # record; a heavy suite made required on day one gets disabled instead of
    # fixed.
    timeout-minutes: 45
    steps:
      - name: Clone
        uses: actions/checkout@v7
        with:
          submodules: true
      - name: Configure apt mirror on runner
        uses: ./.github/actions/configure-apt-mirror
      - name: Setup Go
        uses: actions/setup-go@v5
        with:
          go-version: '1.26.0'
          cache: false
      - name: Dependencies
        run: |
          sudo apt-get update
          sudo apt-get install -y build-essential libopus-dev
      - name: Proto Dependencies
        run: |
          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
          rm protoc.zip
          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
          PATH="$PATH:$HOME/go/bin" make protogen-go
      - name: Pre-pull test images
        # Pulling here rather than inside the suite keeps container-start timing
        # out of the spec timeouts and makes a registry outage read as a
        # setup failure instead of a test failure. These two are the only images
        # the suite needs once the testcontainers reaper is disabled below.
        run: |
          docker pull postgres:16-alpine
          docker pull nats:2-alpine
      - name: Distributed E2E
        # TESTCONTAINERS_RYUK_DISABLED keeps the pre-pull above meaningful. The
        # reaper exists to clean up leaked containers on a long-lived host, but
        # this runner is ephemeral and every container dies with the VM. Leaving
        # it enabled would pull a third, unpinned image (testcontainers/ryuk)
        # from Docker Hub mid-suite: exactly the registry dependency the
        # pre-pull step exists to remove.
        env:
          TESTCONTAINERS_RYUK_DISABLED: "true"
        run: |
          PATH="$PATH:$HOME/go/bin" make test-e2e-distributed
      - name: Setup tmate session if tests fail
        if: ${{ failure() }}
        uses: mxschmitt/action-tmate@v3.23
        with:
          detached: true
          connect-timeout-seconds: 180
          limit-access-to-actor: true