litellm/.github/workflows/mutation-test.yml

name: "Mutation Test (manual)"

# Manually-triggered mutation testing. Runs mutmut against the scope
# configured in [tool.mutmut] in pyproject.toml (currently the
# litellm/proxy/management_endpoints/ folder). Intended cadence is roughly
# weekly — clicked from the Actions tab when someone wants a fresh report.
#
# Uploads a structured `mutation-report.md` (Meta ACH-style: original +
# mutated function with `# MUTANT START`/`# MUTANT END` delimiters + the
# existing tests + a task instruction) as a workflow artifact. Failures
# do not block anything because nothing depends on this workflow.

on:
  workflow_dispatch:

permissions:
  contents: read

concurrency:
  group: mutation-test-${{ github.ref }}
  cancel-in-progress: true

jobs:
  mutation:
    name: Run mutmut
    runs-on: ubuntu-latest
    # Whole-folder mutation against ~15 files / ~7.5k LOC can take hours.
    # 350 minutes is just under the GitHub-hosted job cap of 360 minutes.
    timeout-minutes: 350

    steps:
      - 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: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
        with:
          version: "0.10.9"

      - name: Cache uv dependencies
        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
        with:
          path: |
            ~/.cache/uv
            .venv
          key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
          restore-keys: |
            ${{ runner.os }}-uv-

      - name: Install dependencies
        run: |
          .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router

      - name: Generate Prisma client
        env:
          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
        run: |
          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma

      # mutmut 3.x runs tests inside a `mutants/` sandbox where it injects
      # mutation trampolines. uv installs the project as editable by default,
      # which puts the original source dir on sys.path via a .pth file and
      # shadows the sandbox copy — so tests would never exercise the mutated
      # code. Reinstalling non-editable removes the .pth shadow.
      - name: Reinstall litellm non-editable (so mutants/ is not shadowed)
        run: |
          uv pip uninstall litellm
          uv pip install . --no-deps

      # pytest-retry's pytest_configure hook crashes with
      # `INTERNALERROR: no option named 'filtered_exceptions'` when invoked
      # via mutmut's in-process pytest.main() call. The entry-point name
      # doesn't normalize cleanly with `-p no:<name>`, so just remove the
      # package outright. Reruns are wrong for mutation testing anyway —
      # rerunning a "failed" mutant test would mask which mutants are killed.
      - name: Remove pytest plugins that conflict with mutmut
        run: |
          uv pip uninstall pytest-retry || true

      - name: Run mutmut
        env:
          # Make the mutants/ sandbox win over site-packages on sys.path so the
          # trampolined files are imported instead of the installed copy.
          PYTHONPATH: ${{ github.workspace }}/mutants
        run: |
          set -o pipefail
          mkdir -p mutants
          uv run --no-sync --with mutmut==3.5.0 mutmut run 2>&1 | tee mutmut-run.log

      # Generate the structured report. The script embeds the enclosing
      # function source for each survivor (via Python AST) and includes the
      # existing test files, so an LLM agent has enough context to write
      # killing tests without further file lookups. Modeled on Meta's ACH
      # prompt template (arXiv 2501.12862).
      - name: Generate detailed mutation report
        if: always()
        run: |
          set +e
          uv run --no-sync --with mutmut==3.5.0 mutmut export-cicd-stats > /dev/null 2>&1
          uv run --no-sync --with mutmut==3.5.0 mutmut results > mutmut-results.txt 2>&1
          uv run --no-sync python scripts/mutation_report.py
          # The full report can be very long for big test files; the run-page
          # summary cuts off at 1 MB. Append the head of the report (summary
          # + survivor list) and link out to the artifact for the full body.
          {
            head -c 900000 mutation-report.md
            echo ""
            echo ""
            echo "_Full report (with embedded function bodies and test files) is in the workflow artifact._"
          } >> "$GITHUB_STEP_SUMMARY"

      - name: Upload mutmut artifacts
        if: always()
        uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
        with:
          name: mutmut-${{ github.run_id }}-${{ github.run_attempt }}
          path: |
            mutation-report.md
            mutmut-results.txt
            mutmut-run.log
            mutants/mutmut-stats.json
            mutants/mutmut-cicd-stats.json
            mutants/litellm/proxy/management_endpoints/**/*.py
          if-no-files-found: warn
          retention-days: 14