name: LiteLLM Unit Tests (Matrix)

on:
  pull_request:
    branches: [main]

# Cancel in-progress runs for the same PR
concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

jobs:
  test:
    runs-on: ubuntu-latest
    timeout-minutes: 20  # Increased from 15 to 20
    strategy:
      fail-fast: false
      matrix:
        test-group:
          # tests/test_litellm split by subdirectory (~560 files total)
          # Vertex AI tests separated for better isolation (prevent auth/env pollution)
          - name: "llms-vertex"
            path: "tests/test_litellm/llms/vertex_ai"
            workers: 1
            reruns: 2
          - name: "llms-other"
            path: "tests/test_litellm/llms --ignore=tests/test_litellm/llms/vertex_ai"
            workers: 2
            reruns: 2
          # tests/test_litellm/proxy split by subdirectory (~180 files total)
          - name: "proxy-guardrails"
            path: "tests/test_litellm/proxy/guardrails tests/test_litellm/proxy/management_endpoints tests/test_litellm/proxy/management_helpers"
            workers: 2
            reruns: 2
          - name: "proxy-core"
            path: "tests/test_litellm/proxy/auth tests/test_litellm/proxy/client tests/test_litellm/proxy/db tests/test_litellm/proxy/hooks tests/test_litellm/proxy/policy_engine"
            workers: 2
            reruns: 2
          - name: "proxy-misc"
            path: "tests/test_litellm/proxy/_experimental tests/test_litellm/proxy/agent_endpoints tests/test_litellm/proxy/anthropic_endpoints tests/test_litellm/proxy/common_utils tests/test_litellm/proxy/discovery_endpoints tests/test_litellm/proxy/experimental tests/test_litellm/proxy/google_endpoints tests/test_litellm/proxy/health_endpoints tests/test_litellm/proxy/image_endpoints tests/test_litellm/proxy/middleware tests/test_litellm/proxy/openai_files_endpoint tests/test_litellm/proxy/pass_through_endpoints tests/test_litellm/proxy/prompts tests/test_litellm/proxy/public_endpoints tests/test_litellm/proxy/response_api_endpoints tests/test_litellm/proxy/spend_tracking tests/test_litellm/proxy/ui_crud_endpoints tests/test_litellm/proxy/vector_store_endpoints tests/test_litellm/proxy/test_*.py"
            workers: 2
            reruns: 2
          - name: "integrations"
            path: "tests/test_litellm/integrations"
            workers: 2
            reruns: 3  # Integration tests tend to be flakier
          - name: "core-utils"
            path: "tests/test_litellm/litellm_core_utils"
            workers: 2
            reruns: 1
          - name: "other-1"
            # responses (5942) + caching (1723) + types (819) ≈ 8.5k lines
            path: "tests/test_litellm/responses tests/test_litellm/caching tests/test_litellm/types"
            workers: 2
            reruns: 2
          - name: "other-2"
            # enterprise (3062) + google_genai (2511) + router_utils (1982) ≈ 7.6k lines
            path: "tests/test_litellm/enterprise tests/test_litellm/google_genai tests/test_litellm/router_utils"
            workers: 2
            reruns: 2
          - name: "other-3"
            # remaining dirs ≈ 8.0k lines
            path: "tests/test_litellm/router_strategy tests/test_litellm/secret_managers tests/test_litellm/a2a_protocol tests/test_litellm/anthropic_interface tests/test_litellm/completion_extras tests/test_litellm/containers tests/test_litellm/experimental_mcp_client tests/test_litellm/images tests/test_litellm/interactions tests/test_litellm/passthrough tests/test_litellm/vector_stores"
            workers: 2
            reruns: 2
          - name: "root"
            path: "tests/test_litellm/test_*.py"
            workers: 2
            reruns: 2
          # tests/proxy_unit_tests split alphabetically (~48 files total)
          - name: "proxy-unit-a1"
            # test_[a-j]*.py: jwt (1564) + auth_checks (978) + google_gemini (478) + e2e_pod_lock (437) + rest
            path: "tests/proxy_unit_tests/test_[a-j]*.py"
            workers: 2
            reruns: 1
          - name: "proxy-unit-a2"
            # test_[k-o]*.py: key_generate_prisma (4346) + key_generate_dynamodb + models_fallback
            path: "tests/proxy_unit_tests/test_[k-o]*.py"
            workers: 2
            reruns: 1
          - name: "proxy-unit-b1"
            # lighter config/utility proxy tests (prisma, project, prompt, proxy_[c-r]*)
            path: "tests/proxy_unit_tests/test_prisma*.py tests/proxy_unit_tests/test_project*.py tests/proxy_unit_tests/test_prompt*.py tests/proxy_unit_tests/test_proxy_[c-r]*.py"
            workers: 2
            reruns: 1
          - name: "proxy-unit-b2"
            # proxy_server.py alone (2750 lines) - isolated to avoid blocking smaller tests
            path: "tests/proxy_unit_tests/test_proxy_server.py"
            workers: 2
            reruns: 1
          - name: "proxy-unit-b3"
            # proxy_server_* (618) + proxy_setting_guardrails (71) - smaller server-related tests
            path: "tests/proxy_unit_tests/test_proxy_server_*.py tests/proxy_unit_tests/test_proxy_setting_guardrails.py"
            workers: 2
            reruns: 1
          - name: "proxy-unit-b4"
            # proxy_utils.py alone (2339 lines) - isolated to avoid blocking token counter
            path: "tests/proxy_unit_tests/test_proxy_utils.py"
            workers: 2
            reruns: 1
          - name: "proxy-unit-b5"
            # proxy_token_counter (1279) - runs independently from utils
            path: "tests/proxy_unit_tests/test_proxy_token_counter.py"
            workers: 2
            reruns: 1
          - name: "proxy-unit-b6"
            # test_[r-t]*.py: response_polling (1399) + search_api_logging (202) + server_root (64) + skills_db (261) + realtime_cache (62)
            path: "tests/proxy_unit_tests/test_[r-t]*.py"
            workers: 2
            reruns: 1
          - name: "proxy-unit-b7"
            # test_[u-z]*.py: user_api_key_auth (1136) + zero_cost (590) + update_spend (305) + unit_test_* (206) + ui_path (157)
            path: "tests/proxy_unit_tests/test_[u-z]*.py"
            workers: 2
            reruns: 1

    name: test (${{ matrix.test-group.name }})

    steps:
      - uses: actions/checkout@v4

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

      - name: Install Poetry
        uses: snok/install-poetry@v1

      - name: Cache Poetry dependencies
        uses: actions/cache@v4
        with:
          path: |
            ~/.cache/pypoetry
            ~/.cache/pip
            .venv
          key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}
          restore-keys: |
            ${{ runner.os }}-poetry-

      - name: Install dependencies
        run: |
          poetry config virtualenvs.in-project true
          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
          # pytest-rerunfailures and pytest-xdist are in pyproject.toml dev dependencies
          poetry run pip install google-genai==1.22.0 \
            google-cloud-aiplatform>=1.38 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core

      - name: Setup litellm-enterprise
        run: |
          poetry run pip install --force-reinstall --no-deps -e enterprise/

      - name: Generate Prisma client
        run: |
          poetry run prisma generate --schema litellm/proxy/schema.prisma

      - name: Run tests - ${{ matrix.test-group.name }}
        run: |
          poetry run pytest ${{ matrix.test-group.path }} \
            --tb=short -vv \
            --maxfail=10 \
            -n ${{ matrix.test-group.workers }} \
            --reruns ${{ matrix.test-group.reruns }} \
            --reruns-delay 1 \
            --dist=loadscope \
            --durations=20