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:
    branches: [ main ]
    types: [opened, synchronize, labeled]
    paths:
      - 'llama_stack/**'
      - 'tests/**'
      - 'uv.lock'
      - 'pyproject.toml'
      - 'requirements.txt'
      - '.github/workflows/integration-tests.yml' # This workflow
      - '.github/actions/setup-ollama/action.yml'
      - '.github/actions/run-integration-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'

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}-${{ contains(github.event.pull_request.labels.*.name, 're-record-tests') && 'rerecord' || 'replay' }}
  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 [[ "${{ 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

  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

      - name: Install dependencies
        uses: ./.github/actions/setup-runner
        with:
          python-version: "3.12"  # Use single Python version for recording
          client-version: "latest"

      - name: Setup ollama
        if: ${{ inputs.test-provider == 'ollama' }}
        uses: ./.github/actions/setup-ollama

      - name: Setup vllm
        if: ${{ inputs.test-provider == 'vllm' }}
        uses: ./.github/actions/setup-vllm

      - name: Build Llama Stack
        run: |
          uv run llama stack build --template ci-tests --image-type venv

      - name: Configure git for commits
        run: |
          git config --local user.email "github-actions[bot]@users.noreply.github.com"
          git config --local user.name "github-actions[bot]"

      - name: Run Integration Tests for All Types (Recording Mode)
        uses: ./.github/actions/run-integration-tests
        with:
          test-types: ${{ needs.discover-tests.outputs.test-types }}
          stack-config: 'ci-tests'
          provider: ${{ inputs.test-provider }}
          inference-mode: 'record'

      - name: Commit and push recordings
        run: |
          if ! git diff --quiet tests/integration/recordings/; then
            echo "Committing recordings"
            git add tests/integration/recordings/
            git commit -m "Update recordings"
            echo "Pushing all recording commits to PR"
            git push origin HEAD:${{ github.head_ref }}
          else
            echo "No recording changes"
          fi

      - name: Write inference logs to file
        if: ${{ always() }}
        run: |
          sudo docker logs ollama > ollama-recording.log || true

      - name: Upload recording logs
        if: ${{ always() }}
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
        with:
          name: recording-logs-${{ github.run_id }}
          path: |
            *.log
          retention-days: 1

  run-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: Install dependencies
        uses: ./.github/actions/setup-runner
        with:
          python-version: ${{ matrix.python-version }}
          client-version: ${{ matrix.client-version }}

      - name: Build Llama Stack
        run: |
          uv run llama stack build --template ci-tests --image-type venv

      - name: Check Storage and Memory Available Before Tests
        if: ${{ always() }}
        run: |
          free -h
          df -h

      - name: Run Integration Tests (Replay Mode)
        uses: ./.github/actions/run-integration-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'

      - name: Check Storage and Memory Available After Tests
        if: ${{ always() }}
        run: |
          free -h
          df -h

      - name: Upload test logs on failure
        if: ${{ failure() }}
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
        with:
          name: test-logs-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.provider }}-${{ matrix.client-type }}-${{ matrix.python-version }}-${{ matrix.client-version }}
          path: |
            *.log
          retention-days: 1