agent-framework/.github/workflows/python-merge-tests.yml

name: Python - Merge - Tests
#
# NOTE: This workflow and python-integration-tests.yml share the same set of
# parallel test jobs. Keep them in sync — when adding, removing, or modifying a
# job here, apply the same change to python-integration-tests.yml.
#

on:
  workflow_dispatch:
  pull_request:
    branches: ["main"]
  merge_group:
    branches: ["main"]
  schedule:
    - cron: "0 0 * * *" # Run at midnight UTC daily

permissions:
  contents: read
  id-token: write

env:
  # Configure a constant location for the uv cache
  UV_CACHE_DIR: /tmp/.uv-cache
  UV_PYTHON: "3.13"
  RUN_SAMPLES_TESTS: ${{ vars.RUN_SAMPLES_TESTS }}

jobs:
  paths-filter:
    runs-on: ubuntu-latest
    permissions:
      contents: read
      pull-requests: read
    outputs:
      pythonChanges: ${{ steps.filter.outputs.python }}
      coreChanged: ${{ steps.filter.outputs.core }}
      openaiChanged: ${{ steps.filter.outputs.openai }}
      azureChanged: ${{ steps.filter.outputs.azure }}
      miscChanged: ${{ steps.filter.outputs.misc }}
      functionsChanged: ${{ steps.filter.outputs.functions }}
      azureAiChanged: ${{ steps.filter.outputs.azure-ai }}
      cosmosChanged: ${{ steps.filter.outputs.cosmos }}
    steps:
      - uses: actions/checkout@v6
      - uses: dorny/paths-filter@v3
        id: filter
        with:
          filters: |
            python:
              - 'python/**'
              - '.github/actions/setup-local-mcp-server/**'
              - '.github/workflows/python-merge-tests.yml'
              - '.github/workflows/python-integration-tests.yml'
            core:
              - 'python/packages/core/agent_framework/_*.py'
              - 'python/packages/core/agent_framework/_workflows/**'
              - 'python/packages/core/agent_framework/exceptions.py'
              - 'python/packages/core/agent_framework/observability.py'
            openai:
              - 'python/packages/core/agent_framework/openai/**'
              - 'python/packages/openai/**'
              - 'python/samples/**/providers/openai/**'
            azure:
              - 'python/packages/openai/**'
              - 'python/packages/core/agent_framework/azure/**'
              - 'python/packages/azure-ai/agent_framework_azure_ai/_deprecated_azure_openai.py'
              - 'python/packages/azure-ai/tests/azure_openai/**'
              - 'python/samples/**/providers/azure/openai_chat_completion_client_azure*.py'
            misc:
              - 'python/packages/anthropic/**'
              - 'python/packages/ollama/**'
              - 'python/packages/core/agent_framework/_mcp.py'
              - 'python/packages/core/tests/core/test_mcp.py'
              - 'python/scripts/local_mcp_streamable_http_server.py'
              - '.github/actions/setup-local-mcp-server/**'
              - '.github/workflows/python-merge-tests.yml'
              - '.github/workflows/python-integration-tests.yml'
            functions:
              - 'python/packages/azurefunctions/**'
              - 'python/packages/durabletask/**'
            azure-ai:
              - 'python/packages/azure-ai/**'
              - 'python/packages/foundry/**'
              - 'python/samples/**/providers/foundry/**'
            cosmos:
              - 'python/packages/azure-cosmos/**'
      # run only if 'python' files were changed
      - name: python tests
        if: steps.filter.outputs.python == 'true'
        run: echo "Python file"
      # run only if not 'python' files were changed
      - name: not python tests
        if: steps.filter.outputs.python != 'true'
        run: echo "NOT python file"
  # Unit tests: always run all non-integration tests across all packages
  python-tests-unit:
    name: Python Tests - Unit
    needs: paths-filter
    if: >
      github.event_name != 'pull_request' &&
      needs.paths-filter.outputs.pythonChanges == 'true'
    runs-on: ubuntu-latest
    environment: integration
    defaults:
      run:
        working-directory: python
    steps:
      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
        with:
          python-version: ${{ env.UV_PYTHON }}
          os: ${{ runner.os }}
      - name: Test with pytest (unit tests only)
        run: >
          uv run poe test -A
          -m "not integration"
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
        working-directory: ./python
      - name: Surface failing tests
        if: always()
        uses: pmeier/pytest-results-action@v0.7.2
        with:
          path: ./python/**.xml
          summary: true
          display-options: fEX
          fail-on-empty: false
          title: Unit test results

  # OpenAI integration tests
  python-tests-openai:
    name: Python Tests - OpenAI Integration
    needs: paths-filter
    if: >
      github.event_name != 'pull_request' &&
      needs.paths-filter.outputs.pythonChanges == 'true' &&
      (github.event_name != 'merge_group' ||
       needs.paths-filter.outputs.openaiChanged == 'true' ||
       needs.paths-filter.outputs.coreChanged == 'true')
    runs-on: ubuntu-latest
    environment: integration
    env:
      OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
      OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
      OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
      OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
      OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
    defaults:
      run:
        working-directory: python
    steps:
      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
        with:
          python-version: ${{ env.UV_PYTHON }}
          os: ${{ runner.os }}
      - name: Test with pytest (OpenAI integration)
        run: >
          uv run pytest --import-mode=importlib
          packages/openai/tests
          -m "integration and not azure"
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
        working-directory: ./python
      - name: Test OpenAI samples
        timeout-minutes: 10
        if: env.RUN_SAMPLES_TESTS == 'true'
        run: uv run pytest tests/samples/ -m "openai"
        working-directory: ./python
      - name: Surface failing tests
        if: always()
        uses: pmeier/pytest-results-action@v0.7.2
        with:
          path: ./python/**.xml
          summary: true
          display-options: fEX
          fail-on-empty: false
          title: OpenAI integration test results

  # Azure OpenAI integration tests
  python-tests-azure-openai:
    name: Python Tests - Azure OpenAI Integration
    needs: paths-filter
    if: >
      github.event_name != 'pull_request' &&
      needs.paths-filter.outputs.pythonChanges == 'true' &&
      (github.event_name != 'merge_group' ||
       needs.paths-filter.outputs.azureChanged == 'true' ||
       needs.paths-filter.outputs.coreChanged == 'true')
    runs-on: ubuntu-latest
    environment: integration
    env:
      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
      AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
      AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
      AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
      AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
    defaults:
      run:
        working-directory: python
    steps:
      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
        with:
          python-version: ${{ env.UV_PYTHON }}
          os: ${{ runner.os }}
      - name: Azure CLI Login
        if: github.event_name != 'pull_request'
        uses: azure/login@v2
        with:
          client-id: ${{ secrets.AZURE_CLIENT_ID }}
          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
      - name: Test with pytest (Azure OpenAI integration)
        run: >
          uv run pytest --import-mode=importlib
          packages/openai/tests/openai/test_openai_chat_completion_client_azure.py
          packages/openai/tests/openai/test_openai_chat_client_azure.py
          packages/openai/tests/openai/test_openai_embedding_client_azure.py
          packages/azure-ai/tests/azure_openai
          --ignore=packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
          -m integration
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
        working-directory: ./python
      - name: Test Azure samples
        timeout-minutes: 10
        if: env.RUN_SAMPLES_TESTS == 'true'
        run: uv run pytest tests/samples/ -m "azure"
        working-directory: ./python
      - name: Surface failing tests
        if: always()
        uses: pmeier/pytest-results-action@v0.7.2
        with:
          path: ./python/**.xml
          summary: true
          display-options: fEX
          fail-on-empty: false
          title: Azure OpenAI integration test results

  # Misc integration tests (Anthropic, Ollama, MCP)
  python-tests-misc-integration:
    name: Python Tests - Misc Integration
    needs: paths-filter
    if: >
      github.event_name != 'pull_request' &&
      needs.paths-filter.outputs.pythonChanges == 'true' &&
      (github.event_name != 'merge_group' ||
       needs.paths-filter.outputs.miscChanged == 'true' ||
       needs.paths-filter.outputs.coreChanged == 'true')
    runs-on: ubuntu-latest
    environment: integration
    env:
      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
      ANTHROPIC_CHAT_MODEL_ID: ${{ vars.ANTHROPIC_CHAT_MODEL_ID }}
      LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
    defaults:
      run:
        working-directory: python
    steps:
      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
        with:
          python-version: ${{ env.UV_PYTHON }}
          os: ${{ runner.os }}
      - name: Start local MCP server
        id: local-mcp
        uses: ./.github/actions/setup-local-mcp-server
        with:
          fallback_url: ${{ env.LOCAL_MCP_URL }}
      - name: Prefer local MCP URL when available
        run: echo "LOCAL_MCP_URL=${{ steps.local-mcp.outputs.effective_url }}" >> "$GITHUB_ENV"
      - name: Test with pytest (Anthropic, Ollama, MCP integration)
        run: >
          uv run pytest --import-mode=importlib
          packages/anthropic/tests
          packages/ollama/tests
          packages/core/tests/core/test_mcp.py
          -m integration
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
        working-directory: ./python
      - name: Stop local MCP server
        if: always()
        shell: bash
        run: |
          set -euo pipefail
          server_pid="${{ steps.local-mcp.outputs.pid }}"
          if [[ -z "$server_pid" ]]; then
            exit 0
          fi
          if ! kill -0 "$server_pid" 2>/dev/null; then
            exit 0
          fi
          kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" 2>/dev/null || true
          for _ in $(seq 1 10); do
            if ! kill -0 "$server_pid" 2>/dev/null; then
              exit 0
            fi
            sleep 1
          done
          kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" 2>/dev/null || true
      - name: Surface failing tests
        if: always()
        uses: pmeier/pytest-results-action@v0.7.2
        with:
          path: ./python/**.xml
          summary: true
          display-options: fEX
          fail-on-empty: false
          title: Misc integration test results

  # Azure Functions + Durable Task integration tests
  python-tests-functions:
    name: Python Tests - Functions Integration
    needs: paths-filter
    if: >
      github.event_name != 'pull_request' &&
      needs.paths-filter.outputs.pythonChanges == 'true' &&
      (github.event_name != 'merge_group' ||
       needs.paths-filter.outputs.functionsChanged == 'true' ||
       needs.paths-filter.outputs.coreChanged == 'true')
    runs-on: ubuntu-latest
    environment: integration
    env:
      UV_PYTHON: "3.11"
      OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
      OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
      OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
      OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
      OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
      AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
      AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
      FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
      FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
      FUNCTIONS_WORKER_RUNTIME: "python"
      DURABLE_TASK_SCHEDULER_CONNECTION_STRING: "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None"
      AzureWebJobsStorage: "UseDevelopmentStorage=true"
    defaults:
      run:
        working-directory: python
    steps:
      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
        with:
          python-version: ${{ env.UV_PYTHON }}
          os: ${{ runner.os }}
      - name: Azure CLI Login
        if: github.event_name != 'pull_request'
        uses: azure/login@v2
        with:
          client-id: ${{ secrets.AZURE_CLIENT_ID }}
          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
      - name: Set up Azure Functions Integration Test Emulators
        uses: ./.github/actions/azure-functions-integration-setup
        id: azure-functions-setup
      - name: Test with pytest (Functions + Durable Task integration)
        run: >
          uv run pytest --import-mode=importlib
          packages/azurefunctions/tests/integration_tests
          packages/durabletask/tests/integration_tests
          -m integration
          -n logical --dist worksteal
          -x
          --timeout=360 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
        working-directory: ./python
      - name: Surface failing tests
        if: always()
        uses: pmeier/pytest-results-action@v0.7.2
        with:
          path: ./python/**.xml
          summary: true
          display-options: fEX
          fail-on-empty: false
          title: Functions integration test results

  python-tests-foundry:
    name: Python Integration Tests - Foundry
    needs: paths-filter
    if: >
      github.event_name != 'pull_request' &&
      needs.paths-filter.outputs.pythonChanges == 'true' &&
      (github.event_name != 'merge_group' ||
       needs.paths-filter.outputs.azureAiChanged == 'true' ||
       needs.paths-filter.outputs.coreChanged == 'true')
    runs-on: ubuntu-latest
    environment: integration
    env:
      AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
      AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
      FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
      FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
      FOUNDRY_AGENT_NAME: ${{ vars.FOUNDRY_AGENT_NAME }}
      FOUNDRY_AGENT_VERSION: ${{ vars.FOUNDRY_AGENT_VERSION }}
      LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
    defaults:
      run:
        working-directory: python
    steps:
      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
        with:
          python-version: ${{ env.UV_PYTHON }}
          os: ${{ runner.os }}
      - name: Azure CLI Login
        if: github.event_name != 'pull_request'
        uses: azure/login@v2
        with:
          client-id: ${{ secrets.AZURE_CLIENT_ID }}
          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
      - name: Test with pytest
        timeout-minutes: 15
        run: >
          uv run pytest --import-mode=importlib
          packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
          packages/foundry/tests
          -m integration
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
        working-directory: ./python
      - name: Test Azure AI samples
        timeout-minutes: 10
        if: env.RUN_SAMPLES_TESTS == 'true'
        run: uv run pytest tests/samples/ -m "azure-ai"
        working-directory: ./python
      - name: Surface failing tests
        if: always()
        uses: pmeier/pytest-results-action@v0.7.2
        with:
          path: ./python/**.xml
          summary: true
          display-options: fEX
          fail-on-empty: false
          title: Test results

  # TODO: Add python-tests-lab

  # Azure Cosmos integration tests
  python-tests-cosmos:
    name: Python Tests - Cosmos Integration
    needs: paths-filter
    if: >
      github.event_name != 'pull_request' &&
      needs.paths-filter.outputs.pythonChanges == 'true' &&
      (github.event_name != 'merge_group' ||
       needs.paths-filter.outputs.cosmosChanged == 'true' ||
       needs.paths-filter.outputs.coreChanged == 'true')
    runs-on: ubuntu-latest
    environment: integration
    services:
      cosmosdb:
        image: mcr.microsoft.com/cosmosdb/linux/azure-cosmos-emulator:vnext-preview
        ports:
          - 8081:8081
    env:
      AZURE_COSMOS_ENDPOINT: "http://localhost:8081/"
      # Static Azure Cosmos DB emulator key (documented): https://learn.microsoft.com/en-us/azure/cosmos-db/emulator
      AZURE_COSMOS_KEY: "C2y6yDjf5/R+ob0N8A7Cgv30VRDJIWEHLM+4QDU5DE2nQ9nDuVTqobD4b8mGGyPMbIZnqyMsEcaGQy67XIw/Jw=="
      AZURE_COSMOS_DATABASE_NAME: "agent-framework-cosmos-it-db"
      AZURE_COSMOS_CONTAINER_NAME: "agent-framework-cosmos-it-container"
    defaults:
      run:
        working-directory: python
    steps:
      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
        with:
          python-version: ${{ env.UV_PYTHON }}
          os: ${{ runner.os }}
      - name: Wait for Cosmos DB emulator
        run: |
          for i in {1..60}; do
            if curl --silent --show-error http://localhost:8081/ > /dev/null; then
              echo "Cosmos DB emulator is ready."
              exit 0
            fi
            sleep 2
          done
          echo "Cosmos DB emulator did not become ready in time." >&2
          exit 1
      - name: Test with pytest (Cosmos integration)
        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
        working-directory: ./python
      - name: Surface failing tests
        if: always()
        uses: pmeier/pytest-results-action@v0.7.2
        with:
          path: ./python/**.xml
          summary: true
          display-options: fEX
          fail-on-empty: false
          title: Cosmos integration test results

  python-integration-tests-check:
    if: always()
    runs-on: ubuntu-latest
    needs:
      [
        python-tests-unit,
        python-tests-openai,
        python-tests-azure-openai,
        python-tests-misc-integration,
        python-tests-functions,
        python-tests-foundry,
        python-tests-cosmos,
      ]
    steps:
      - name: Fail workflow if tests failed
        id: check_tests_failed
        if: contains(join(needs.*.result, ','), 'failure')
        uses: actions/github-script@v8
        with:
          script: core.setFailed('Integration Tests Failed!')

      - name: Fail workflow if tests cancelled
        id: check_tests_cancelled
        if: contains(join(needs.*.result, ','), 'cancelled')
        uses: actions/github-script@v8
        with:
          script: core.setFailed('Integration Tests Cancelled!')