feat: 记忆管理 benchmark 体系 (MemoryEvalRunner + FactRetentionGrader) #11
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] | |
| workflow_dispatch: | |
| inputs: | |
| run_eval: | |
| description: "Run full eval suite" | |
| type: boolean | |
| default: false | |
| jobs: | |
| check: | |
| runs-on: ubuntu-latest | |
| strategy: | |
| matrix: | |
| python-version: ["3.11", "3.12"] | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Install uv | |
| uses: astral-sh/setup-uv@v4 | |
| with: | |
| version: "latest" | |
| - name: Set up Python ${{ matrix.python-version }} | |
| run: uv python install ${{ matrix.python-version }} | |
| - name: Install dependencies | |
| run: uv sync --dev | |
| - name: Lint (ruff check) | |
| run: uv run ruff check . | |
| - name: Format check (ruff format) | |
| run: uv run ruff format --check . | |
| - name: Type check (mypy) | |
| continue-on-error: true | |
| run: uv run mypy src/omni_agent | |
| - name: Unit tests | |
| run: uv run pytest --ignore=tests/integration --ignore=tests/api -v --cov=src/omni_agent --cov-report=term-missing | |
| - name: Eval dry-run (validate eval cases) | |
| run: uv run python -m omni_agent.eval evals/ --dry-run | |
| - name: Upload coverage report | |
| if: matrix.python-version == '3.12' | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: coverage-report | |
| path: htmlcov/ | |
| eval: | |
| runs-on: ubuntu-latest | |
| if: github.event_name == 'workflow_dispatch' | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Install uv | |
| uses: astral-sh/setup-uv@v4 | |
| with: | |
| version: "latest" | |
| - name: Set up Python | |
| run: uv python install 3.12 | |
| - name: Install dependencies | |
| run: uv sync --dev | |
| - name: Run eval suite | |
| env: | |
| LLM_API_KEY: ${{ secrets.LLM_API_KEY }} | |
| LLM_API_BASE: ${{ secrets.LLM_API_BASE }} | |
| LLM_MODEL: ${{ secrets.LLM_MODEL }} | |
| run: uv run python -m omni_agent.eval evals/ --output eval_results | |
| - name: Upload eval report | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: eval-report | |
| path: eval_results/ |