name: Integration Tests on: push: branches: [ main ] pull_request: branches: [ main ] paths: - 'llama_stack/**' - 'tests/integration/**' - 'uv.lock' - 'pyproject.toml' - 'requirements.txt' - '.github/workflows/integration-tests.yml' # This workflow - '.github/actions/setup-ollama/action.yml' schedule: - cron: '0 0 * * *' # Daily at 12 AM UTC workflow_dispatch: inputs: test-all-client-versions: description: 'Test against both the latest and published versions' type: boolean default: false concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: true jobs: discover-tests: runs-on: ubuntu-latest outputs: test-type: ${{ steps.generate-matrix.outputs.test-type }} steps: - name: Checkout repository uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 - name: Generate test matrix id: generate-matrix run: | # Get test directories dynamically, excluding non-test directories TEST_TYPES=$(find tests/integration -maxdepth 1 -mindepth 1 -type d -printf "%f\n" | grep -Ev "^(__pycache__|fixtures|test_cases)$" | sort | jq -R -s -c 'split("\n")[:-1]') echo "test-type=$TEST_TYPES" >> $GITHUB_OUTPUT test-matrix: needs: discover-tests runs-on: ubuntu-latest strategy: fail-fast: false matrix: test-type: ${{ fromJson(needs.discover-tests.outputs.test-type) }} client-type: [library, server] python-version: ["3.12", "3.13"] client-version: ${{ (github.event_name == 'schedule' || 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: Setup ollama uses: ./.github/actions/setup-ollama - name: Build Llama Stack run: | uv run llama stack build --template starter --image-type venv - name: Check Storage and Memory Available Before Tests if: ${{ always() }} run: | free -h df -h - name: Run Integration Tests env: OLLAMA_INFERENCE_MODEL: "llama3.2:3b-instruct-fp16" # for server tests ENABLE_OLLAMA: "ollama" # for server tests OLLAMA_URL: "http://0.0.0.0:11434" SAFETY_MODEL: "llama-guard3:1b" LLAMA_STACK_CLIENT_TIMEOUT: "300" # Increased timeout for eval operations # Use 'shell' to get pipefail behavior # https://docs.github.com/en/actions/reference/workflow-syntax-for-github-actions#exit-codes-and-error-action-preference # TODO: write a precommit hook to detect if a test contains a pipe but does not use 'shell: bash' shell: bash run: | if [ "${{ matrix.client-type }}" == "library" ]; then stack_config="starter" else stack_config="server:starter" fi uv run pytest -s -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="ollama/llama3.2:3b-instruct-fp16" \ --embedding-model=all-MiniLM-L6-v2 \ --safety-shield=$SAFETY_MODEL \ --color=yes \ --capture=tee-sys | tee pytest-${{ matrix.test-type }}.log - name: Check Storage and Memory Available After Tests if: ${{ always() }} run: | free -h df -h - name: Write ollama logs to file if: ${{ always() }} run: | sudo docker logs ollama > ollama.log - name: Upload all logs to artifacts if: ${{ always() }} uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2 with: name: logs-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.client-type }}-${{ matrix.test-type }}-${{ matrix.python-version }}-${{ matrix.client-version }} path: | *.log retention-days: 1