docs(evals): S01–S10 标注集 v1、评测工具和评测报告

- evals/gold：1,887 个标注单元（AI 标注、逐条裁定，未经人工复核），规范见 GUIDELINES.md
- prepare / run_all / score / gold：导出文字层、批量抽取、打分、标注定位
- docs/architecture/extract-eval.md：修复前后的结果（三项目标全部达标）和剩余问题
- decisions.md 记 M1（只用 Flash）和 Q1–Q4；架构 §13 SK13；AGENTS.md 进度

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

evals/run_extract.py

@@ -4,7 +4,7 @@
   ../.venv/bin/python ../evals/run_extract.py <文件> ../evals/out/<名字> [--v extract.tech_param=2 ...] [--only extract.substantive]
   BD_AI_MODELS='{"reasoning": "deepseek-v4-pro"}' 换模型对比。
 同一模型 + 同一提示词版本 + 同一输入只调用一次模型（缓存在 <输出目录>/../cache/），只改规则时重放不花钱。
-输出：report.md（结果统计 + 模型输出里不合理模式的审计）、items.json（每条结果和模型原始输出）、normalized.pdf。
+输出：report.md（结果统计 + 模型输出里不合理模式的审计）、items.json（每条结果和模型原始输出）、info.json（项目基本信息和统计）、normalized.pdf。
 真实招标文件和输出都不进 git（evals/out/ 已忽略）。
 """
 
@@ -24,11 +24,12 @@ from uuid import UUID
 
 from bid_doctor.ai import prompts
 from bid_doctor.ai import service as ai_service
+from bid_doctor.ai.providers.base import near_limit
 from bid_doctor.ai.service import provider
 from bid_doctor.checklist import extract
 from bid_doctor.core.db import TenantContext
 from bid_doctor.document import formats
-from bid_doctor.document.pipeline import convert, structure, text_layer
+from bid_doctor.document.pipeline import convert, text_layer
 
 ap = argparse.ArgumentParser()
 ap.add_argument("file")
@@ -39,7 +40,7 @@ args = ap.parse_args()
 
 out = pathlib.Path(args.out)
 out.mkdir(parents=True, exist_ok=True)
-cache_dir = out.parent / "cache"
+cache_dir = pathlib.Path(__file__).resolve().parent / "out" / "cache"  # 各次评测共用
 cache_dir.mkdir(exist_ok=True)
 
 versions = dict(v.split("=") for v in args.v)
@@ -77,8 +78,8 @@ async def cached_run_json(ctx: Any, *, job_type: str, job_id: Any, task: str, pr
                 "incomplete": r.incomplete}
         f.write_text(json.dumps(data, ensure_ascii=False))
     calls.append({"task": task, "version": version, "user": user, **data})
-    if data.get("incomplete"):
-        raise ai_service.OutputIncomplete(task)  # 和线上一样：输出被截断时由 extract.run 对半重跑
+    if data.get("incomplete") or near_limit(data.get("tokens_out")):
+        raise ai_service.OutputIncomplete(task, data["data"])  # 和线上一样：输出被截断时由 extract.run 对半重跑
     return data["data"]
 
 
@@ -92,18 +93,12 @@ async def main() -> None:
     (out / "normalized.pdf").write_bytes(pdf)
     pages = text_layer.extract("D", pdf)
     body = text_layer.body_sentences(pages)
-    notes = extract.marking_notes(body)
-    doc = extract.Doc(
-        sentences=body,
-        parents=structure.parents(body),
-        continuations=text_layer.continuations(body),
-        notes=notes,
-        declared={m for n in notes for m in n.markers},
-    )
+    doc = extract.build_doc(body)
     ctx = TenantContext(tenant_id=UUID(int=1), user_id=UUID(int=1))
     items, info, run_stats = await extract.run(ctx, UUID(int=2), doc)
 
-    by_sid = {f"p{s.page_no}s{s.seq}": s for s in body}
+    _sid = extract._sid  # noqa: SLF001
+    by_sid = {_sid(s): s for s in body}
     # ---------- 结果 ----------
     zone = Counter((i.zone, i.pending_reason) for i in items)
     cats = Counter((c, i.zone) for i in items for c in i.categories)
@@ -115,6 +110,8 @@ async def main() -> None:
             "categories": i.categories,
             "title": i.summary,
             "importance": i.importance,
+            "importance_basis": i.importance_basis,
+            "basis": i.basis,
             "sentences": [f"p{s.page_no}s{s.seq}" for s in i.sentences],
             "quote_pages": sorted({s.page_no for s in i.sentences}),
             "raw": i.ai_values,
@@ -122,6 +119,15 @@ async def main() -> None:
         for i in items
     ]
     (out / "items.json").write_text(json.dumps(res, ensure_ascii=False, indent=1))
+    info_out = {
+        "fields": {k: {"value": v.value, "unit": v.unit, "sentence": _sid(v.sentence)} for k, v in info.fields.items()},
+        "status": info.status,
+        "lots": [{k: v for k, v in lot.items() if k != "sentence"} for lot in info.lots],
+        "stats": run_stats,
+        "tokens": [sum(c.get("tokens_in") or 0 for c in calls), sum(c.get("tokens_out") or 0 for c in calls)],
+        "models": sorted({c.get("model") or "" for c in calls}),
+    }
+    (out / "info.json").write_text(json.dumps(info_out, ensure_ascii=False, indent=1))
 
     # ---------- 模型原始输出的审计 ----------
     audit: dict[str, Counter[str]] = defaultdict(Counter)