Function build_report

src/evaluation/report.py:106–138

(results: list[ScenarioResult])

def build_report(results: list[ScenarioResult]) -> EvalReport:
    total = len(results)
    passed = sum(1 for r in results if r.score.passed)

    by_type: dict[str, list[ScenarioResult]] = defaultdict(list)
    for r in results:
        by_type[r.scenario_type or "unknown"].append(r)

    breakdown: dict[str, TypeBreakdown] = {}
    for stype, items in by_type.items():
        n = len(items)
        p = sum(1 for r in items if r.score.passed)
        breakdown[stype] = TypeBreakdown(
            total=n,
            passed=p,
            pass_rate=round(p / n, 4) if n else 0.0,
        )

    return EvalReport(
        generated_at=_dt.datetime.now(_dt.timezone.utc).isoformat(),
        runners=sorted({r.runner for r in results}),
        models=sorted({r.model for r in results}),
        totals={
            "scenarios": total,
            "scored": total,
            "passed": passed,
            "pass_rate": round(passed / total, 4) if total else 0.0,
        },
        by_scenario_type=breakdown,
        ops=aggregate_ops(results),
        score_summary=_aggregate_score_summary(results),
        results=results,
    )


def write_report(report: EvalReport, output: Path) -> Path: