llama-stack-mirror/.github/workflows/integration-tests.yml

name: Integration Tests

run-name: Run the integration test suite from tests/integration

on:
  push:
    branches: [ main ]
  pull_request_target:
    branches: [ main ]
    types: [opened, synchronize, labeled]
    paths:
      - 'llama_stack/**'
      - 'tests/**'
      - 'uv.lock'
      - 'pyproject.toml'
      - '.github/workflows/integration-tests.yml' # This workflow
      - '.github/actions/setup-ollama/action.yml'
      - '.github/actions/setup-test-environment/action.yml'
      - '.github/actions/run-and-record-tests/action.yml'
  schedule:
    # If changing the cron schedule, update the provider in the test-matrix job
    - cron: '0 0 * * *'  # (test latest client) Daily at 12 AM UTC
    - cron: '1 0 * * 0'  # (test vllm) Weekly on Sunday at 1 AM UTC
  workflow_dispatch:
    inputs:
      test-all-client-versions:
        description: 'Test against both the latest and published versions'
        type: boolean
        default: false
      test-provider:
        description: 'Test against a specific provider'
        type: string
        default: 'ollama'
      force-inference-mode:
        description: 'Force inference mode (record or replay)'
        type: string
        default: ''

concurrency:
  # This creates three concurrency groups:
  #   ${{ github.workflow }}-${{ github.ref }}-rerecord (for valid triggers with re-record-tests label)
  #   ${{ github.workflow }}-${{ github.ref }}-replay (for valid triggers without re-record-tests label)
  #   ${{ github.workflow }}-${{ github.ref }}-no-run (for invalid triggers that will be skipped)
  # The "no-run" group ensures that irrelevant label events don't interfere with the real workflows.
  group: >-
    ${{ github.workflow }}-${{ github.ref }}-${{
    ((github.event.action == 'opened' || github.event.action == 'synchronize') && 'replay') ||
    ((github.event.action == 'labeled' && contains(github.event.pull_request.labels.*.name, 're-record-tests')) && 'rerecord' ||
    'no-run')
    }}
  cancel-in-progress: true

jobs:
  discover-tests:
    if: |
      github.event.action == 'opened' ||
      github.event.action == 'synchronize' ||
      (github.event.action == 'labeled' && contains(github.event.pull_request.labels.*.name, 're-record-tests'))
    runs-on: ubuntu-latest
    outputs:
      test-types: ${{ steps.generate-test-types.outputs.test-types }}
      rerecord-tests: ${{ steps.check-rerecord-tests.outputs.rerecord-tests }}

    steps:
      - name: Checkout repository
        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2

      - name: Generate test types
        id: generate-test-types
        run: |
          # Get test directories dynamically, excluding non-test directories
          TEST_TYPES=$(find tests/integration -maxdepth 1 -mindepth 1 -type d -printf "%f\n" |
            grep -Ev "^(__pycache__|fixtures|test_cases|recordings)$" |
            sort | jq -R -s -c 'split("\n")[:-1]')
          echo "test-types=$TEST_TYPES" >> $GITHUB_OUTPUT

      - name: Check if re-record-tests label exists
        id: check-rerecord-tests
        run: |
          if [[ "${{ inputs.force-inference-mode }}" == "record" ]]; then
            echo "rerecord-tests=true" >> $GITHUB_OUTPUT
          elif [[ "${{ inputs.force-inference-mode }}" == "replay" ]]; then
            echo "rerecord-tests=false" >> $GITHUB_OUTPUT
          else
            if [[ "${{ contains(github.event.pull_request.labels.*.name, 're-record-tests') }}" == "true" ]]; then
              echo "rerecord-tests=true" >> $GITHUB_OUTPUT
            else
              echo "rerecord-tests=false" >> $GITHUB_OUTPUT
            fi
          fi

  record-tests:
    # Sequential job for recording to avoid SQLite conflicts
    if: ${{ needs.discover-tests.outputs.rerecord-tests == 'true' }}
    needs: discover-tests
    runs-on: ubuntu-latest

    permissions:
      contents: write
      pull-requests: write

    steps:
      - name: Checkout repository
        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
        with:
          ref: ${{ github.event.pull_request.head.ref }}
          fetch-depth: 0

      - name: Setup test environment
        uses: ./.github/actions/setup-test-environment
        with:
          python-version: "3.12"  # Use single Python version for recording
          client-version: "latest"
          provider: ${{ inputs.test-provider || 'ollama' }}

      - name: Run and record tests
        uses: ./.github/actions/run-and-record-tests
        with:
          test-types: ${{ needs.discover-tests.outputs.test-types }}
          stack-config: 'server:ci-tests'  # recording must be done with server since more tests are run
          provider: ${{ inputs.test-provider || 'ollama' }}
          inference-mode: 'record'

  run-replay-mode-tests:
    # Skip this job if we're in recording mode (handled by record-tests job)
    if: ${{ needs.discover-tests.outputs.rerecord-tests != 'true' }}
    needs: discover-tests
    runs-on: ubuntu-latest

    strategy:
      fail-fast: false
      matrix:
        client-type: [library, server]
        # Use vllm on weekly schedule, otherwise use test-provider input (defaults to ollama)
        provider: ${{ (github.event.schedule == '1 0 * * 0') && fromJSON('["vllm"]') || fromJSON(format('["{0}"]', github.event.inputs.test-provider || 'ollama')) }}
        python-version: ["3.12", "3.13"]
        client-version: ${{ (github.event.schedule == '0 0 * * 0' || github.event.inputs.test-all-client-versions == 'true') && fromJSON('["published", "latest"]') || fromJSON('["latest"]') }}

    steps:
      - name: Checkout repository
        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2

      - name: Setup test environment
        uses: ./.github/actions/setup-test-environment
        with:
          python-version: ${{ matrix.python-version }}
          client-version: ${{ matrix.client-version }}
          provider: ${{ matrix.provider }}

      - name: Run and record tests
        uses: ./.github/actions/run-and-record-tests
        with:
          test-types: ${{ needs.discover-tests.outputs.test-types }}
          stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || 'server:ci-tests' }}
          provider: ${{ matrix.provider }}
          inference-mode: 'replay'