integration-tests.yml

name: Integration Tests

on:
  pull_request_target: # zizmor: ignore[dangerous-triggers] guarded by authorize job, label gate for external PRs, and immutable head.sha checkout
    types: [opened, synchronize, reopened, labeled]
  workflow_dispatch:

permissions: {}

concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

jobs:
  authorize:
    name: authorize
    runs-on: ubuntu-latest
    steps:
      - name: Check authorization
        env:
          GH_TOKEN: ${{ github.token }}
          EVENT_NAME: ${{ github.event_name }}
          ACTOR: ${{ github.actor }}
          AUTHOR_ASSOC: ${{ github.event.pull_request.author_association }}
          EVENT_ACTION: ${{ github.event.action }}
          LABEL_NAME: ${{ github.event.label.name }}
        run: |
          # Manual dispatch: verify the actor belongs to the org
          if [[ "$EVENT_NAME" == "workflow_dispatch" ]]; then
            if gh api "orgs/Giskard-AI/members/$ACTOR" --silent 2>/dev/null; then
              echo "Org member $ACTOR — authorized."
              exit 0
            fi
            echo "::error::$ACTOR is not a member of the Giskard-AI organization."
            exit 1
          fi

          # Internal contributors are always authorized
          if [[ "$AUTHOR_ASSOC" =~ ^(MEMBER|COLLABORATOR|OWNER)$ ]]; then
            echo "Internal contributor — authorized."
            exit 0
          fi

          # External contributors: only when a maintainer adds the 'safe for build' label
          if [[ "$EVENT_ACTION" == "labeled" && "$LABEL_NAME" == "safe for build" ]]; then
            echo "External contributor — authorized via 'safe for build' label."
            exit 0
          fi

          echo "::error::External contributors require a maintainer to add the 'safe for build' label."
          exit 1

  test-agents-functional:
    needs: authorize
    runs-on: ubuntu-latest
    permissions:
      contents: read # checkout repository
    environment: ci
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        python-version: ["3.12", "3.13", "3.14"]
        backend:
          # Each backend exercises a different install combination so we
          # catch dependency regressions in the three supported layouts:
          # giskard-llm only, litellm only, and both installed together.
          # Using the top-level giskard-agents extras (not giskard-llm
          # directly) so the pass-through extras declared in
          # libs/giskard-agents/pyproject.toml are covered.
          - name: giskard-llm
            extras: "giskard-agents[google]"
            pytest_mark: "functional and google"
          - name: litellm
            extras: "giskard-agents[litellm]"
            pytest_mark: "functional and litellm"
          - name: both
            extras: "giskard-agents[google,litellm]"
            pytest_mark: "functional and (google or litellm)"
    name: agents / ${{ matrix.backend.name }} / ${{ matrix.python-version }}
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
        with:
          ref: ${{ github.event.pull_request.head.sha || github.ref }}
          persist-credentials: false
      - uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
        with:
          enable-cache: true
          python-version: ${{ matrix.python-version }}
      - run: make install
      - name: Install backend extras
        env:
          BACKEND_EXTRAS: ${{ matrix.backend.extras }}
        run: uv pip install "$BACKEND_EXTRAS"
      - name: Run functional tests
        env:
          GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
          TEST_MODEL: "google/gemini-2.0-flash"
          TEST_LITELLM_MODEL: "gemini/gemini-2.0-flash"
          TEST_EMBEDDING_MODEL: "google/gemini-embedding-001"
          PYTEST_MARK: ${{ matrix.backend.pytest_mark }}
        run: uv run pytest libs/giskard-agents -m "$PYTEST_MARK"

  test-llm-functional:
    needs: authorize
    runs-on: ubuntu-latest
    environment: ci
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        # One cell per routing prefix we want to exercise end-to-end.
        # `extras` is the giskard-llm optional-dependency group to install;
        # aliases share an install (bare/azure_ai reuse openai/azure, gemini reuses google).
        include:
          - { python-version: "3.12", provider: openai,    extras: openai    }
          - { python-version: "3.12", provider: bare,      extras: openai    }
          - { python-version: "3.12", provider: google,    extras: google    }
          - { python-version: "3.12", provider: gemini,    extras: google    }
          - { python-version: "3.12", provider: anthropic, extras: anthropic }
          - { python-version: "3.12", provider: azure,     extras: azure     }
          - { python-version: "3.12", provider: azure_ai,  extras: azure     }
    name: llm / ${{ matrix.provider }} / ${{ matrix.python-version }}
    env:
      PROVIDER: ${{ matrix.provider }}
      EXTRAS: ${{ matrix.extras }}
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
        with:
          ref: ${{ github.event.pull_request.head.sha || github.ref }}
          persist-credentials: false
      - uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
        with:
          enable-cache: true
          python-version: ${{ matrix.python-version }}
      - run: make install
      - name: Install provider SDK
        run: uv pip install "giskard-llm[$EXTRAS]"
      - name: Run functional tests
        env:
          OPENAI_API_KEY: ${{ (matrix.provider == 'openai' || matrix.provider == 'bare') && secrets.OPENAI_API_KEY || '' }}
          GOOGLE_API_KEY: ${{ (matrix.provider == 'google' || matrix.provider == 'gemini') && secrets.GEMINI_API_KEY || '' }}
          ANTHROPIC_API_KEY: ${{ matrix.provider == 'anthropic' && secrets.ANTHROPIC_API_KEY || '' }}
          AZURE_API_KEY: ${{ matrix.provider == 'azure' && secrets.AZURE_API_KEY || '' }}
          AZURE_API_BASE: ${{ matrix.provider == 'azure' && secrets.AZURE_API_BASE || '' }}
          AZURE_API_VERSION: ${{ matrix.provider == 'azure' && secrets.AZURE_API_VERSION || '' }}
          AZURE_AI_API_KEY: ${{ matrix.provider == 'azure_ai' && secrets.AZURE_AI_API_KEY || '' }}
          AZURE_AI_ENDPOINT: ${{ matrix.provider == 'azure_ai' && secrets.AZURE_AI_ENDPOINT || '' }}
        run: make test-functional PACKAGE=giskard-llm PROVIDER=$PROVIDER

  test-checks-functional:
    needs: authorize
    runs-on: ubuntu-latest
    environment: ci
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        python-version: ["3.12", "3.13", "3.14"]
        provider: [google]
    name: checks / ${{ matrix.provider }} / ${{ matrix.python-version }}
    env:
      PROVIDER: ${{ matrix.provider }}
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
        with:
          ref: ${{ github.event.pull_request.head.sha || github.ref }}
          persist-credentials: false
      - uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
        with:
          enable-cache: true
          python-version: ${{ matrix.python-version }}
      - run: make install
      - name: Install provider SDK
        run: uv pip install "giskard-llm[$PROVIDER]"
      - name: Run functional tests
        env:
          GOOGLE_API_KEY: ${{ matrix.provider == 'google' && secrets.GEMINI_API_KEY || '' }}
          TEST_MODEL: "google/gemini-2.0-flash"
          TEST_EMBEDDING_MODEL: "google/gemini-embedding-001"
        run: make test-functional PACKAGE=giskard-checks PROVIDER=$PROVIDER