litellm/.github/workflows/test-merge-smoke.yml

name: smoke

on:
  pull_request:
    branches: [main, litellm_internal_staging, litellm_oss_staging, "litellm_**"]
  workflow_dispatch:

permissions:
  contents: read

concurrency:
  group: merge-smoke-${{ github.event.pull_request.number || github.run_id }}
  cancel-in-progress: true

jobs:
  dashboard-build:
    name: dashboard-build
    runs-on: ubuntu-24.04
    timeout-minutes: 30
    steps:
      - name: Checkout
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          persist-credentials: false

      - name: Build the dashboard stage
        run: docker build --target ui-builder -f Dockerfile .

  core-checks:
    name: py${{ matrix.python-version }}
    runs-on: ubuntu-24.04
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14", "3.15"]
    env:
      LITELLM_LOCAL_MODEL_COST_MAP: "True"
    steps:
      - name: Checkout
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
        with:
          python-version: ${{ matrix.python-version }}

      - name: Set up uv
        uses: ./.github/actions/setup-uv-with-retries
        with:
          version: "0.10.9"

      - name: Install dependencies
        run: .github/scripts/uv_sync_with_retries.sh --frozen --extra proxy --extra cli --group dev --group proxy-dev --python ${{ matrix.python-version }}

      - name: Create the loopback-only network namespace
        run: |
          sudo ip netns add smoke
          sudo ip netns exec smoke ip link set lo up
          cat > "${RUNNER_TEMP}/in-netns" <<'WRAP'
          #!/usr/bin/env bash
          set -euo pipefail
          exec sudo --preserve-env=LITELLM_LOCAL_MODEL_COST_MAP ip netns exec smoke setpriv --reuid "$(id -u)" --regid "$(id -g)" --init-groups -- env HOME="${HOME}" PATH="${PATH}" "$@"
          WRAP
          chmod +x "${RUNNER_TEMP}/in-netns"
          echo "IN_NETNS=${RUNNER_TEMP}/in-netns" >> "${GITHUB_ENV}"

      - name: Verify namespace isolation
        run: $IN_NETNS .venv/bin/python .github/scripts/run_merge_smoke.py verify-isolation

      - name: Verify interpreter version
        run: $IN_NETNS .venv/bin/python .github/scripts/run_merge_smoke.py interpreter --expect ${{ matrix.python-version }}

      - name: Import and CLI checks
        run: $IN_NETNS .venv/bin/python .github/scripts/run_merge_smoke.py cli

      - name: Routing and UUID compatibility
        run: >-
          $IN_NETNS .venv/bin/python -m pytest
          tests/unit/router_strategy/test_complexity_router.py::TestCustomDimensions
          tests/unit/test_uuid_helper.py -q

      - name: Proxy startup check
        run: $IN_NETNS .venv/bin/python .github/scripts/run_merge_smoke.py proxy-startup --diagnostics-dir "${RUNNER_TEMP}/smoke-diagnostics"

      - name: Upload smoke diagnostics
        if: always()
        uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
        with:
          name: merge-smoke-diagnostics-py${{ matrix.python-version }}
          path: ${{ runner.temp }}/smoke-diagnostics
          if-no-files-found: ignore

      - name: Remove the network namespace
        if: always()
        run: sudo ip netns delete smoke

  all-extras:
    name: all-extras-py${{ matrix.python-version }}
    runs-on: ubuntu-24.04
    timeout-minutes: 10
    strategy:
      fail-fast: false
      matrix:
        python-version: ["3.12", "3.13"]
    env:
      LITELLM_LOCAL_MODEL_COST_MAP: "True"
    steps:
      - name: Checkout
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
        with:
          python-version: ${{ matrix.python-version }}

      - name: Set up uv
        uses: ./.github/actions/setup-uv-with-retries
        with:
          version: "0.10.9"

      - name: Install every extra and dependency group
        run: .github/scripts/uv_sync_with_retries.sh --frozen --all-groups --all-extras --python ${{ matrix.python-version }}

      - name: Import the SDK, the proxy server and the enterprise package
        run: .venv/bin/python -c "import litellm, litellm.proxy.proxy_server, litellm_enterprise"

  windows-sdk:
    name: windows-sdk
    runs-on: windows-2025
    timeout-minutes: 30
    env:
      LITELLM_LOCAL_MODEL_COST_MAP: "True"
    defaults:
      run:
        shell: bash
    steps:
      - name: Checkout
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
        with:
          python-version: "3.11"

      - name: Set up uv
        uses: ./.github/actions/setup-uv-with-retries
        with:
          version: "0.10.9"

      - name: Set up the Rust bridge
        uses: ./.github/actions/rust-bridge

      - name: Install dependencies
        run: .github/scripts/uv_sync_with_retries.sh --frozen --group dev --python 3.11

      - name: Run the Windows tests
        run: uv run --no-sync python -m pytest --tb=short -v tests/windows_tests

  proxy-build-from-pip:
    name: proxy-build-from-pip
    runs-on: ubuntu-24.04
    timeout-minutes: 10
    services:
      postgres:
        image: postgres:14@sha256:6a70deda415ec296f977890e11aba04a0db9f632a362e3fce45e845e3db74f26
        env:
          POSTGRES_USER: postgres
          POSTGRES_PASSWORD: postgres
          POSTGRES_DB: circle_test
        ports:
          - 5432:5432
        options: >-
          --health-cmd "pg_isready -U postgres"
          --health-interval 2s
          --health-timeout 5s
          --health-retries 30
    steps:
      - name: Checkout
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
        with:
          python-version: "3.12"

      - name: Set up uv
        uses: ./.github/actions/setup-uv-with-retries
        with:
          version: "0.10.9"

      - name: Install the test client dependencies
        run: .github/scripts/uv_sync_with_retries.sh --frozen --no-install-workspace --extra proxy --group dev --python 3.12

      - name: Build the image from the published package
        run: docker build -t litellm-build-from-pip:smoke -f docker/build_from_pip/Dockerfile.build_from_pip .

      - name: Start the fake OpenAI endpoint
        run: |
          nohup .venv/bin/python tests/_fake_openai_endpoint_server.py --host 0.0.0.0 --port 8190 > "${RUNNER_TEMP}/fake-openai.log" 2>&1 &
          for _ in $(seq 1 30); do
            curl -sf http://localhost:8190/health > /dev/null && exit 0
            sleep 1
          done
          cat "${RUNNER_TEMP}/fake-openai.log"
          exit 1

      - name: Generate a master key
        run: |
          key="sk-$(openssl rand -hex 16)"
          echo "::add-mask::${key}"
          echo "LITELLM_MASTER_KEY=${key}" >> "${GITHUB_ENV}"

      - name: Start the proxy container
        run: |
          docker run -d \
            -p 4000:4000 \
            -e DATABASE_URL=postgresql://postgres:postgres@host.docker.internal:5432/circle_test \
            -e LITELLM_MASTER_KEY \
            -e FAKE_OPENAI_API_BASE=http://host.docker.internal:8190 \
            -e OTEL_EXPORTER=in_memory \
            -e USE_DDTRACE=True \
            -e GCS_FLUSH_INTERVAL=1 \
            -e LITELLM_LOG=ERROR \
            --add-host host.docker.internal:host-gateway \
            --name litellm-build-from-pip \
            -v "${GITHUB_WORKSPACE}/docker/build_from_pip/litellm_config.yaml:/app/config.yaml" \
            litellm-build-from-pip:smoke \
            --config /app/config.yaml \
            --port 4000
          for _ in $(seq 1 150); do
            curl -sf --max-time 5 -o /dev/null http://localhost:4000 && exit 0
            sleep 2
          done
          exit 1

      - name: Run the startup tests
        shell: bash
        run: |
          set -euo pipefail
          base_url=http://localhost:4000
          readiness_response="$(curl -sS --fail-with-body --write-out $'\n%{http_code}' "${base_url}/health/readiness")"
          readiness_status="${readiness_response##*$'\n'}"
          readiness_body="${readiness_response%$'\n'*}"
          [[ "${readiness_status}" == "200" ]]
          jq -e '.status == "healthy" or .status == "connected"' <<< "${readiness_body}" > /dev/null
          liveness_status="$(curl -sS --fail-with-body --output /dev/null --write-out '%{http_code}' "${base_url}/health/liveness")"
          [[ "${liveness_status}" == "200" ]]
          completion_response="$(curl -sS --fail-with-body --write-out $'\n%{http_code}' \
            --header "Authorization: Bearer ${LITELLM_MASTER_KEY}" \
            --header 'Content-Type: application/json' \
            --data '{"model":"gpt-4","messages":[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Hello!"}]}' \
            "${base_url}/chat/completions")"
          completion_status="${completion_response##*$'\n'}"
          completion_body="${completion_response%$'\n'*}"
          [[ "${completion_status}" == "200" ]]
          jq -e '
            (.choices | length) == 1 and
            .choices[0].message.role == "assistant" and
            .choices[0].message.content == "Hello! This is a mock response from the fake OpenAI endpoint."
          ' <<< "${completion_body}" > /dev/null

      - name: Show the proxy logs
        if: always()
        run: docker logs litellm-build-from-pip || true

  smoke-passed:
    name: smoke passed
    needs: [dashboard-build, core-checks, all-extras, windows-sdk, proxy-build-from-pip]
    if: always()
    runs-on: ubuntu-latest
    timeout-minutes: 2
    permissions: {}
    steps:
      - name: Require every smoke job to succeed
        env:
          NEEDS: ${{ toJSON(needs) }}
        run: |
          jq -r 'to_entries[] | "\(.key): \(.value.result)"' <<< "$NEEDS"
          jq -e 'all(.[]; .result == "success")' <<< "$NEEDS" > /dev/null