feat(eval): 黄金集 + 评分器（T13 架构审查整改，OV4）

- T13 (OV4, P1): 新建 src/genesis/eval/ 包
  - golden_set.py: GoldenCase/GoldenSet（YAML 加载，samples/ 真实脱敏样本作 input_ref）
  - scorer.py: ChapterScorer 按 §7.2 指标体系打分
    - 确定性维度: traceability（resolver 验证 source_uri 可解析率）/
      placeholder_residue（无 {{...}} 残留）/chapter_completeness（章节覆盖）
    - LLM 语义维度: llm_evaluators 钩子（默认中性分，待 Phase5）
  - tests/fixtures/eval/golden_set.yaml 示例黄金集
- 新增 test_eval_scorer.py（9 用例）
- 同步 design.md §7.5 黄金集与评分器（定位 CI 质量门禁）
- TDD: RED（模块缺失）→ GREEN（聚焦 8 passed）→ 全量 240 passed / 100.00%（1279 stmts/308 br）

tests/fixtures/eval/golden_set.yaml

@@ -0,0 +1,9 @@
+cases:
+  - id: g1
+    input_ref: samples/要件定義.xlsx
+    expected_min_score: 0.7
+    note: 脱敏真实样本回归基线（Phase5 Writer 实现后填充实际评分）
+  - id: g2
+    input_ref: samples/概要設計書_template.docx
+    expected_min_score: 0.7
+    note: 模板结构合规基线

tests/test_eval_scorer.py

@@ -0,0 +1,180 @@
+"""评分器测试（T13，OV4）。
+
+OV4 裁定：成功标准无量度（无黄金集/评分器）→ 建立黄金集 + 评分器。
+本文件测试确定性可机器验证维度（可追溯性/占位符残留/章节完整性），
+LLM 语义维度预留钩子；并测试黄金集加载。
+"""
+
+from __future__ import annotations
+
+import pytest
+
+from genesis.data_models import (
+    CellValue,
+    ExcelTable,
+    ParsedTemplate,
+    Provenance,
+    SheetType,
+    StructuredSource,
+)
+from genesis.eval.scorer import (
+    ChapterArtifact,
+    ChapterScorer,
+    DimensionScore,
+    EvalReport,
+)
+from genesis.eval.golden_set import GoldenCase, GoldenSet
+
+
+# ---------- 小源（供可追溯性维度定位） ----------
+
+def _source() -> StructuredSource:
+    cell = CellValue(
+        value="登録",
+        provenance=Provenance(file_name="f.xlsx", sheet_name="機能一覧", row=3, column="C", column_header="x"),
+    )
+    table = ExcelTable(
+        name="機能一覧", detected_type=SheetType.FUNCTION,
+        extraction_method="structured", headers=["v"], rows=[{"v": cell}],
+    )
+    return StructuredSource(
+        tables=[table],
+        template=ParsedTemplate(file_name="t.docx", sections=[], placeholders={}, styles={}),
+        rule_docs=[], image_analyses=[], existing_system=None, comments=[],
+    )
+
+
+# ---------- 可追溯性维度 ----------
+
+def test_traceability_full_when_all_uris_resolvable():
+    source = _source()
+    artifact = ChapterArtifact(
+        chapter_id="ch3",
+        text="機能一覧（出典: f.xlsx#機能一覧!C3）",
+        source_uris=["f.xlsx#機能一覧!C3"],
+        template_sections_expected=["ch3"],
+    )
+    report = ChapterScorer().score([artifact], source)
+    trace = _dim(report, "traceability")
+    assert trace.score == 1.0
+    assert trace.passed is True
+
+
+def test_traceability_zero_when_uris_fake():
+    source = _source()
+    artifact = ChapterArtifact(
+        chapter_id="ch3",
+        text="機能（出典: fake.xlsx#X!Z9）",
+        source_uris=["fake.xlsx#X!Z9"],
+        template_sections_expected=["ch3"],
+    )
+    report = ChapterScorer().score([artifact], source)
+    trace = _dim(report, "traceability")
+    assert trace.score == 0.0
+    assert trace.passed is False
+
+
+# ---------- 占位符残留维度 ----------
+
+def test_placeholder_residue_fails():
+    source = _source()
+    artifact = ChapterArtifact(
+        chapter_id="ch3",
+        text="未替换占位符 {{section:db_tables}}",
+        source_uris=["f.xlsx#機能一覧!C3"],
+        template_sections_expected=["ch3"],
+    )
+    report = ChapterScorer().score([artifact], source)
+    dim = _dim(report, "placeholder_residue")
+    assert dim.score == 0.0
+    assert dim.passed is False
+
+
+def test_placeholder_residue_ok_when_clean():
+    source = _source()
+    artifact = ChapterArtifact(
+        chapter_id="ch3", text="正常生成内容", source_uris=[], template_sections_expected=["ch3"],
+    )
+    report = ChapterScorer().score([artifact], source)
+    assert _dim(report, "placeholder_residue").score == 1.0
+
+
+# ---------- 章节完整性维度 ----------
+
+def test_completeness_fails_when_section_missing():
+    source = _source()
+    # 期望 ch3/ch4 两章，但只生成 ch3
+    artifacts = [ChapterArtifact(
+        chapter_id="ch3", text="a", source_uris=[], template_sections_expected=["ch3", "ch4"],
+    )]
+    report = ChapterScorer().score(artifacts, source)
+    dim = _dim(report, "chapter_completeness")
+    assert dim.score == 0.5
+    assert dim.passed is False
+
+
+# ---------- LLM 维度钩子 ----------
+
+def test_llm_dimension_hook_invoked():
+    source = _source()
+    called = {}
+
+    def fake_llm(chapter: ChapterArtifact) -> DimensionScore:
+        called["hit"] = True
+        return DimensionScore(name="llm_accuracy", score=0.8, passed=True, detail="stub")
+
+    artifact = ChapterArtifact(
+        chapter_id="ch3", text="x", source_uris=[], template_sections_expected=["ch3"],
+    )
+    scorer = ChapterScorer(llm_evaluators={"llm_accuracy": fake_llm})
+    report = scorer.score([artifact], source)
+    assert called.get("hit") is True
+    assert _dim(report, "llm_accuracy").score == 0.8
+
+
+# ---------- 总分聚合 + 通过判定 ----------
+
+def test_total_score_aggregation():
+    source = _source()
+    artifact = ChapterArtifact(
+        chapter_id="ch3", text="正常（出典: f.xlsx#機能一覧!C3）",
+        source_uris=["f.xlsx#機能一覧!C3"], template_sections_expected=["ch3"],
+    )
+    report = ChapterScorer().score([artifact], source)
+    assert isinstance(report, EvalReport)
+    assert 0.0 <= report.total_score <= 1.0
+    # 全部确定性维度满分 → 总分接近 1.0（仅 llm 维度默认中性 0.5）
+    assert report.total_score >= 0.8
+
+
+def test_empty_chapters_does_not_crash():
+    """空章节输入：无引用/无约束 → 确定性维度中性满分，不应抛错。"""
+    source = _source()
+    report = ChapterScorer().score([], source)
+    assert report.total_score == 1.0
+    assert report.passed is True
+
+
+# ---------- 黄金集加载 ----------
+
+def test_golden_set_load(tmp_path):
+    yaml_text = """
+cases:
+  - id: g1
+    input_ref: samples/要件定義.xlsx
+    expected_min_score: 0.7
+    note: 脱敏真实样本回归基线
+"""
+    p = tmp_path / "golden_set.yaml"
+    p.write_text(yaml_text, encoding="utf-8")
+    gs = GoldenSet.load(p)
+    assert len(gs.cases) == 1
+    assert gs.cases[0].id == "g1"
+    assert gs.cases[0].expected_min_score == 0.7
+
+
+def _dim(report: EvalReport, name: str) -> DimensionScore:
+    for d in report.dimensions:
+        if d.name == name:
+            return d
+    raise AssertionError(f"维度未找到: {name}")