name: Vision Inference Integration Tests

run-name: Run vision inference integration test suite from tests/integration/inference

on:
  push:
    branches: [ main ]
  pull_request_target:
    branches: [ main ]
    types: [opened, synchronize, labeled]
    paths:
      - 'llama_stack/**'
      - 'tests/**'
      - 'uv.lock'
      - 'pyproject.toml'
      - '.github/workflows/integration-vision-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'
  workflow_dispatch:
    inputs:
      test-all-client-versions:
        description: 'Test against both the latest and published versions'
        type: boolean
        default: false
      force-inference-mode:
        description: 'Force inference mode (record or replay)'
        type: string
        default: ''

concurrency:
  # Skip concurrency for pushes to main - each commit should be tested independently
  # For other events, create concurrency groups:
  #   ${{ github.workflow }}-${{ github.ref }}-rerecord (for labeled events with re-record-tests label)
  #   ${{ github.workflow }}-${{ github.ref }}-replay (for all non-labeled events)
  #   ${{ github.workflow }}-${{ github.ref }}-no-run (for labeled events without re-record-tests label)
  # The "no-run" group ensures that irrelevant label events don't interfere with the real workflows.
  group: >-
    ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-${{
    github.event.action == 'labeled' && (
      contains(github.event.pull_request.labels.*.name, 're-record-tests') && 'rerecord' || 'no-run'
    ) || 'replay'
    }}
  cancel-in-progress: true

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

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

      - 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: 'ollama'
          run-vision-tests: 'true'

      - name: Run and record tests
        uses: ./.github/actions/run-and-record-tests
        with:
          test-types: '["vision"]'
          stack-config: 'server:ci-tests'  # re-recording must be done in server mode
          provider: 'ollama'
          inference-mode: 'record'
          run-vision-tests: 'true'

  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]
        provider: [ollama]
        python-version: ["3.12"]
        client-version: ["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 }}
          run-vision-tests: 'true'

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