docs(benchmarks): backfill RedCode-Exec + AgentDojo, refresh TL;DR #109
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: CI | |
| on: | |
| push: | |
| branches: [main] | |
| pull_request: | |
| branches: [main] | |
| permissions: | |
| contents: read | |
| jobs: | |
| test: | |
| name: Test (Python ${{ matrix.python-version }}) | |
| runs-on: ubuntu-latest | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| python-version: ["3.10", "3.11", "3.12"] | |
| steps: | |
| - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| cache: pip | |
| - name: Install core package | |
| run: pip install -e . | |
| - name: Install test + integration dependencies | |
| run: | | |
| pip install pytest pytest-cov langgraph langchain-core fastapi pydantic uvicorn python-multipart httpx opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp-proto-http | |
| pip install claude-agent-sdk vercel-ai-sdk || echo "Optional SDK install failed (platform-specific), tests will skip" | |
| - name: Run tests | |
| run: pytest --cov=sponsio --cov-report=term-missing -v | |
| test-typescript: | |
| name: Test (TypeScript — native) | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 | |
| - name: Set up Node.js | |
| uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 | |
| with: | |
| node-version: "22" | |
| - name: Install + Build TS SDK | |
| working-directory: ts-sdk | |
| run: npm install && npx tsc | |
| - name: Run cross-language tests | |
| working-directory: ts-sdk | |
| run: node dist/__tests__/core.test.js | |
| lint: | |
| name: Lint | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 | |
| - name: Set up Python | |
| uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 | |
| with: | |
| python-version: "3.12" | |
| cache: pip | |
| - name: Install ruff and dependencies | |
| run: pip install ruff fastapi pydantic -e . | |
| - name: Check formatting | |
| run: ruff format --check sponsio/ api/ tests/ | |
| - name: Check linting | |
| run: ruff check sponsio/ api/ tests/ | |
| - name: Check README/QUICKSTART command sync | |
| run: | | |
| # Canonical user-journey commands that must appear identically in | |
| # both README.md (60-second version) and QUICKSTART.md (full | |
| # walkthrough). Prevents CLI renames/drift from silently desyncing | |
| # the two onboarding paths. | |
| commands=( | |
| "pip install sponsio" | |
| "sponsio onboard" | |
| "sponsio report" | |
| "SPONSIO_MODE=enforce" | |
| ) | |
| exit_code=0 | |
| for cmd in "${commands[@]}"; do | |
| for file in README.md QUICKSTART.md; do | |
| if ! grep -qF "$cmd" "$file"; then | |
| echo "::error file=$file::Canonical command missing: $cmd" | |
| exit_code=1 | |
| fi | |
| done | |
| done | |
| exit $exit_code |