Function test_run_all_benchmarks

tests/test_eval.py:466–533

run_all_benchmarks returns results for all workflows.

()

def test_run_all_benchmarks():
    """run_all_benchmarks returns results for all workflows."""
    from code_review_graph.eval.token_benchmark import run_all_benchmarks

    with tempfile.TemporaryDirectory() as tmpdir:
        repo_path = Path(tmpdir) / "all_bench_repo"
        repo_path.mkdir()

        subprocess.run(
            ["git", "init"], cwd=str(repo_path), capture_output=True,
        )
        subprocess.run(
            ["git", "config", "user.email", "test@test.com"],
            cwd=str(repo_path), capture_output=True,
        )
        subprocess.run(
            ["git", "config", "user.name", "Test"],
            cwd=str(repo_path), capture_output=True,
        )

        (repo_path / "app.py").write_text(
            'def main():\n    print("hello")\n',
            encoding="utf-8",
        )

        subprocess.run(
            ["git", "add", "."], cwd=str(repo_path), capture_output=True,
        )
        subprocess.run(
            ["git", "commit", "-m", "initial"],
            cwd=str(repo_path), capture_output=True,
        )

        (repo_path / "app.py").write_text(
            'def main():\n    print("hi")\n',
            encoding="utf-8",
        )
        subprocess.run(
            ["git", "add", "."], cwd=str(repo_path), capture_output=True,
        )
        subprocess.run(
            ["git", "commit", "-m", "update"],
            cwd=str(repo_path), capture_output=True,
        )

        from code_review_graph.graph import GraphStore
        from code_review_graph.incremental import full_build, get_db_path

        db_path = get_db_path(repo_path)
        store = GraphStore(db_path)
        full_build(repo_path, store)
        store.close()

        results = run_all_benchmarks(repo_root=str(repo_path), base="HEAD~1")

        # Should have one result per workflow (5 total)
        assert len(results) == 5