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

name: Integration Tests (Replay)

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

on:
  push:
    branches: [ main ]
  pull_request:
    branches: [ main ]
    types: [opened, synchronize, reopened]
    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'
      test-subdirs:
        description: 'Comma-separated list of test subdirectories to run'
        type: string
        default: ''
      test-pattern:
        description: 'Regex pattern to pass to pytest -k'
        type: string
        default: ''

concurrency:
  # Skip concurrency for pushes to main - each commit should be tested independently
  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
  cancel-in-progress: true

jobs:

  run-replay-mode-tests:
    runs-on: ubuntu-latest
    name: ${{ format('Integration Tests ({0}, {1}, {2}, client={3}, vision={4})', matrix.client-type, matrix.provider, matrix.python-version, matrix.client-version, matrix.run-vision-tests) }}

    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')) }}
        # Use Python 3.13 only on nightly schedule (daily latest client test), otherwise use 3.12
        python-version: ${{ github.event.schedule == '0 0 * * *' && fromJSON('["3.12", "3.13"]') || fromJSON('["3.12"]') }}
        client-version: ${{ (github.event.schedule == '0 0 * * *' || github.event.inputs.test-all-client-versions == 'true') && fromJSON('["published", "latest"]') || fromJSON('["latest"]') }}
        run-vision-tests: [true, false]

    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: ${{ matrix.run-vision-tests }}
          inference-mode: 'replay'

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