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

name: Integration Tests

on:
  push:
    branches: [ main ]
  pull_request:
    branches: [ main ]
    paths:
      - 'distributions/**'
      - 'llama_stack/**'
      - 'tests/integration/**'
      - 'uv.lock'
      - 'pyproject.toml'
      - 'requirements.txt'
      - '.github/workflows/integration-tests.yml' # This workflow

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

jobs:
  test-matrix:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        # Listing tests manually since some of them currently fail
        # TODO: generate matrix list from tests/integration when fixed
        test-type: [agents, inference, datasets, inspect, scoring, post_training, providers]
        client-type: [library, http]
      fail-fast: false # we want to run all tests regardless of failure

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

      - name: Install uv
        uses: astral-sh/setup-uv@0c5e2b8115b80b4c7c5ddf6ffdd634974642d182 # v5.4.1
        with:
          python-version: "3.10"

      - name: Install and start Ollama
        run: |
          # the ollama installer also starts the ollama service
          curl -fsSL https://ollama.com/install.sh | sh

      - name: Pull Ollama image
        run: |
          # TODO: cache the model. OLLAMA_MODELS defaults to ~ollama/.ollama/models.
          ollama pull llama3.2:3b-instruct-fp16

      - name: Set Up Environment and Install Dependencies
        run: |
          uv sync --extra dev --extra test
          uv pip install ollama faiss-cpu
          # always test against the latest version of the client
          # TODO: this is not necessarily a good idea. we need to test against both published and latest
          # to find out backwards compatibility issues.
          uv pip install git+https://github.com/meta-llama/llama-stack-client-python.git@main
          uv pip install -e .
          llama stack build --template ollama --image-type venv

      - name: Start Llama Stack server in background
        if: matrix.client-type == 'http'
        env:
          INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
        run: |
          source .venv/bin/activate
          nohup uv run llama stack run ./llama_stack/templates/ollama/run.yaml --image-type venv > server.log 2>&1 &

      - name: Wait for Llama Stack server to be ready
        if: matrix.client-type == 'http'
        run: |
          echo "Waiting for Llama Stack server..."
          for i in {1..30}; do
            if curl -s http://localhost:8321/v1/health | grep -q "OK"; then
              echo "Llama Stack server is up!"
              exit 0
            fi
            sleep 1
          done
          echo "Llama Stack server failed to start"
          cat server.log
          exit 1

      - name: Verify Ollama status is OK
        if: matrix.client-type == 'http'
        run: |
          echo "Verifying Ollama status..."
          ollama_status=$(curl -s -L http://127.0.0.1:8321/v1/providers/ollama|jq --raw-output .health.status)
          echo "Ollama status: $ollama_status"
          if [ "$ollama_status" != "OK" ]; then
            echo "Ollama health check failed"
            exit 1
          fi

      - name: Run Integration Tests
        env:
          INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
        run: |
          if [ "${{ matrix.client-type }}" == "library" ]; then
            stack_config="ollama"
          else
            stack_config="http://localhost:8321"
          fi
          uv run pytest -v tests/integration/${{ matrix.test-type }} --stack-config=${stack_config} \
            -k "not(builtin_tool or safety_with_image or code_interpreter or test_rag)" \
            --text-model="meta-llama/Llama-3.2-3B-Instruct" \
            --embedding-model=all-MiniLM-L6-v2