feat(check): 规则检查（报价形式、形式要件、响应表），表格按单元格分行

- check/rules.py（规则集 2026.11-r1，不调模型）：大小写金额、分项合计、超最高限价、多个报价、别的项目名称、没填的地方、落款日期、投标有效期、附加条件、响应表里的未响应；每条挂投标原文，有依据的挂招标侧出处；缺限价、截止时间、有效期要求时写进覆盖范围 - 文字层的句子带上单元格框，表格按单元格上沿分行 - 按 Fable 审读意见收紧致命级：认不准的降为重要或提示 - 评测：score.py 评规则问题；P07 注入记录改为空白处前后原文，剔除注入到人员表的 D10 - 上传页的检查范围文案同步 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 16:44:22 +08:00
parent 47c6a1258e
commit db1b1f6f9f
17 changed files with 1792 additions and 20 deletions
--- a/server/src/bid_doctor/check/match.py
+++ b/server/src/bid_doctor/check/match.py
@@ -53,6 +53,7 @@ class BidDoc:
    label: str
    sentences: list[Sentence]
    scanned_pages: list[int] = field(default_factory=list[int])  # 没有文字层的页（扫描件），C10
+    header_footer: list[Sentence] = field(default_factory=list[Sentence])  # 页眉页脚（规则检查看页眉里的项目名称）


@dataclass(slots=True)
--- a/server/src/bid_doctor/check/rules.py
+++ b/server/src/bid_doctor/check/rules.py
--- a/server/src/bid_doctor/check/runner.py
+++ b/server/src/bid_doctor/check/runner.py
@@ -3,15 +3,17 @@
 - 和解析任务同一套做法（架构 §3.4）：阶段之间检查取消标记；结局由错误类别决定扣不扣点，失败、取消都退回。
 - 健全性检查：投标文件几乎读不出文字时按输入问题失败，不扣点、不生成问题（参考项目的同类闸门）。
 - 认不出、查不了、没查的都写进检查覆盖范围（coverage），不静默跳过（m3-plan §2.5）。
-TODO(第 2 步)：规则检查（报价形式、形式要件、需人工核对）；投标侧结构识别（偏离表、开标一览表、格式文件）。
+- 规则检查（报价形式、形式要件）在 rules.py，项目侧的值（限价、截止时间、有效期要求）带招标侧出处，见 _facts。
 """

 from __future__ import annotations

 import logging
 from datetime import UTC, datetime
+from decimal import Decimal
 from typing import Any
 from uuid import UUID
+from zoneinfo import ZoneInfo

 import httpx
 from sqlalchemy import delete, func, select
@@ -20,7 +22,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 from bid_doctor.ai.models import AiCall
 from bid_doctor.ai.providers.base import TransientError
 from bid_doctor.billing import service as billing
-from bid_doctor.check import applicability, findings, match
+from bid_doctor.check import applicability, findings, match, rules
 from bid_doctor.check.models import CheckItemResult, CheckRun, CheckRunDocument, Finding, FindingCitation
 from bid_doctor.check.service import RULE_SET_VERSION, open_fatal
 from bid_doctor.checklist import edit as checklist_edit
@@ -35,13 +37,16 @@ from bid_doctor.document import service as documents
 from bid_doctor.document.citations import document_label
 from bid_doctor.document.models import SourceDocument
 from bid_doctor.document.pipeline import normalize, text_layer
+from bid_doctor.document.pipeline.text_layer import norm
 from bid_doctor.notification.models import Notification
 from bid_doctor.project import service as projects
+from bid_doctor.project.models import Lot, Project, ProjectField

 log = logging.getLogger(__name__)
 PROGRESS = {"prepare_bid": 5, "match": 30, "rules": 85, "verify": 90, "carry_over": 93, "summarize": 96}
 MIN_BID_CHARS = 200  # 所有分册加起来读不出这么多字：按「投标文件几乎读不出文字」失败
 REGIMES_VERIFIED = {"gov_procurement"}  # 招标投标体系没有样本，规则未经验证（m3-plan §2.4）
+LOCAL_TZ = ZoneInfo("Asia/Shanghai")  # 投标截止时间按北京时间取日期


 class Cancelled(Exception):
@@ -126,6 +131,7 @@ async def _stages(ctx: TenantContext, run_id: UUID) -> None:
                label,
                text_layer.body_sentences(pages),
                [p.page_no for p in pages if p.text_source == "empty"],
+                [x for p in pages for x in p.sentences if x.location == "header_footer"],
            )
        )
        pages_info.append(
@@ -163,6 +169,7 @@ async def _stages(ctx: TenantContext, run_id: UUID) -> None:
                [text_layer.Page.from_json(pg) for pg in await documents.text_layer(s, ctx, d)]
            )
        ]
+        facts = await _facts(s, ctx, r, snapshot)
    # 招标文件按类别的响应方式（C12）：用清单里存的（人工改过的为准）；解析早于这项功能的项目临时识别
    modes = response_mode.from_stored(stored_modes) if stored_modes else response_mode.detect(tender_sents)
    bidding = set(r.lot_ids)
@@ -191,7 +198,15 @@ async def _stages(ctx: TenantContext, run_id: UUID) -> None:
    match.apply_modes(results, items, decisions)
    match.scanned_fallback(results, items, decisions, bid_docs)

-    await _stage(ctx, run_id, "rules")  # 第 2 步：报价形式、形式要件、需人工核对
+    await _stage(ctx, run_id, "rules")
+    hits, rule_cov = rules.run(facts, bid_docs, tender_sents)
+    covered = {
+        (d.label, x.page_no, norm(x.text))
+        for res in results.values()
+        if res.verdict == "negative_deviation"
+        for d, x in res.evidence
+    }
+    hits = rules.drop_covered(hits, covered)
    await _stage(ctx, run_id, "verify")  # 前两道校验在匹配时逐条做完；这里只是进度节点
    await _stage(ctx, run_id, "carry_over")
    async with tenant_tx(ctx) as s:
@@ -201,6 +216,7 @@ async def _stages(ctx: TenantContext, run_id: UUID) -> None:
            d.id: d for d in (await s.execute(select(SourceDocument).where(SourceDocument.id.in_(doc_ids)))).scalars()
        }
        await _write(s, ctx, r, items, results, by_doc)
+        await _write_rules(s, ctx, r, hits, facts, by_doc)
        await _carry_over(s, ctx, r, set(items))
        _stage_nowait(r, "summarize")
        tokens = (
@@ -211,7 +227,9 @@ async def _stages(ctx: TenantContext, run_id: UUID) -> None:
            )
        ).one()
        r.counts = await _counts(s, run_id)
-        r.coverage = _coverage(r, pages_info, items, results, pending, other_lot, stats, tokens, skipped, modes)
+        r.coverage = _coverage(
+            r, pages_info, items, results, pending, other_lot, stats, tokens, skipped, modes, rule_cov
+        )
    await _publish(ctx, r, "running", "summarize", PROGRESS["summarize"])


@@ -219,6 +237,90 @@ def _stage_nowait(r: CheckRun, stage: str) -> None:
    r.stage, r.progress = stage, PROGRESS[stage]


+async def _facts(s: AsyncSession, ctx: TenantContext, r: CheckRun, snapshot: dict[UUID, dict[str, Any]]) -> rules.Facts:
+    """规则检查要的项目侧值：项目基本信息（人工改过的为准）、所投采购包的限价、清单里的投标有效期要求，各带招标侧出处。"""
+    p = (await s.execute(select(Project).where(Project.id == r.project_id))).scalar_one()
+    fields = {
+        f.field_key: f for f in (await s.execute(select(ProjectField).where(ProjectField.project_id == p.id))).scalars()
+    }
+
+    def value(key: str) -> Any:
+        f = fields.get(key)
+        return None if f is None else f.human_value if f.human_value is not None else f.ai_value
+
+    refs = {k: [f.ai_citation_id] for k, f in fields.items() if f.ai_citation_id and f.human_value is None}
+    lots = [x for x in (await s.execute(select(Lot).where(Lot.project_id == p.id))).scalars() if not x.is_default]
+    bidding = [x for x in lots if x.id in set(r.lot_ids)] if r.lot_ids else lots
+    ceiling, scope, note = None, "total", None
+    if len(bidding) > 1:
+        scope, note = "multi", "投了多个采购包，报价按包和限价比对还没有上线"
+    elif len(bidding) == 1:
+        ceiling, scope = bidding[0].ceiling_amount, "lot" if len(lots) > 1 else "total"
+        refs.pop("ceiling_total", None)  # 包的限价没有单独的出处；说明里写明取自所投采购包
+    elif value("ceiling_total"):
+        ceiling = Decimal(str(value("ceiling_total")))
+    days, item = rules.required_validity(snapshot)
+    if item is not None:
+        refs["validity"] = [UUID(c) for c in snapshot[item].get("citation_ids") or []]
+    refs["deadline"] = refs.pop("deadline_at", [])
+    refs["ceiling"] = refs.pop("ceiling_total", [])
+    return rules.Facts(
+        name=value("name") or p.name,
+        code=value("code") or p.code,
+        purchaser=value("purchaser") or p.purchaser,
+        agency=value("agency") or p.agency,
+        deadline=p.deadline_at.astimezone(LOCAL_TZ).date() if p.deadline_at else None,
+        ceiling=ceiling,
+        ceiling_scope=scope,
+        ceiling_note=note,
+        validity_days=days,
+        validity_item=item,
+        refs=refs,
+    )
+
+
+async def _write_rules(
+    s: AsyncSession,
+    ctx: TenantContext,
+    r: CheckRun,
+    hits: list[rules.Hit],
+    facts: rules.Facts,
+    by_doc: dict[UUID, SourceDocument],
+) -> None:
+    """规则问题：挂投标原文的句子；有依据的（限价、有效期要求、项目名称）再挂招标侧出处。"""
+    for h in hits:
+        bid_cites = []
+        for doc_id in dict.fromkeys(d.id for d, _ in h.evidence):
+            sents = [x for d, x in h.evidence if d.id == doc_id]
+            bid_cites += await citations.from_sentences(s, ctx, by_doc[doc_id], sents, "rule", [])
+        f = Finding(
+            id=uuid7(),
+            tenant_id=ctx.tenant_id,
+            project_id=r.project_id,
+            check_run_id=r.id,
+            checklist_item_id=h.item,
+            rule_code=h.code,
+            match_key=f"rule:{h.code}:{h.target}",
+            type=h.type,
+            severity=h.severity,
+            title=h.title[:200],
+            explanation=h.explanation,
+            detector="rule",
+            detail=h.detail,
+            checks_passed=[],
+            presence="new",
+        )
+        s.add(f)
+        await s.flush()
+        for pos, cid in enumerate(facts.refs.get(h.basis or "", [])):
+            s.add(
+                FindingCitation(tenant_id=ctx.tenant_id, finding_id=f.id, citation_id=cid, side="tender", position=pos)
+            )
+        for pos, c in enumerate(bid_cites):
+            s.add(FindingCitation(tenant_id=ctx.tenant_id, finding_id=f.id, citation_id=c.id, side="bid", position=pos))
+    await s.flush()
+
+
 async def _write(
    s: AsyncSession,
    ctx: TenantContext,
@@ -391,6 +493,7 @@ def _coverage(
    tokens: Any,
    skipped: dict[str, int],
    modes: dict[str, response_mode.Mode],
+    rule_cov: dict[str, Any],
 ) -> dict[str, Any]:
    """检查覆盖范围：报告首页、查标页顶部都读这里（FR-M3-09、m3-plan §2.5）。"""
    undetermined = sum(x.verdict == "undetermined" for x in results.values())
@@ -419,7 +522,9 @@ def _coverage(
    implicit = sum(x.verdict in ("implicit_accepted", "implicit_review") for x in results.values())
    if implicit:
        checked.append(f"其中 {implicit} 条按招标文件「未列入偏离的视为接受」处理，没有复述不算问题")
-    not_checked.append("报价形式、形式要件、资质匹配：规则检查还没有上线")
+    checked.append(rule_cov["checked"])
+    not_checked += rule_cov["not_checked"]
+    not_checked.append("资质匹配（证书有效期、主体一致）：还没有上线")
    if not r.checklist_confirmed:
        not_checked.append("清单未确认，检查结果以当前清单为准")
    return {
--- a/server/src/bid_doctor/check/service.py
+++ b/server/src/bid_doctor/check/service.py
@@ -19,6 +19,7 @@ from sqlalchemy.ext.asyncio import AsyncSession

 from bid_doctor.audit import service as audit
 from bid_doctor.billing import service as billing
+from bid_doctor.check import rules
 from bid_doctor.check.models import CheckItemResult, CheckRun, CheckRunDocument, Finding, FindingCitation
 from bid_doctor.checklist import edit as checklist_edit
 from bid_doctor.checklist import service as checklist
@@ -35,7 +36,9 @@ from bid_doctor.project import service as projects
 from bid_doctor.project.models import Project

 CHECK_TASK = "check_project"
-RULE_SET_VERSION = "2026.11-r0"  # 第 1 步还没有规则；规则集有版本，检查批次记下当时用的版本（架构 §3.7）
+RULE_SET_VERSION = (
+    "2026.11-r1"  # 规则集有版本，检查批次记下当时用的版本（架构 §3.7）；r1：报价形式、形式要件（rules.py）
+)
 WAIVE_WINDOW = timedelta(hours=24)
 ERROR_MESSAGES = {
    "bid_text_missing": "投标文件里几乎读不出文字（可能都是扫描件），扫描件识别还没有上线",
@@ -307,7 +310,9 @@ async def _to_api_many(s: AsyncSession, run: CheckRun, rows: list[Finding]) -> l
            }
            if item
            else None,
-            "rule": {"code": f.rule_code, "description": ""} if f.rule_code and not item else None,
+            "rule": {"code": f.rule_code, "description": rules.LABELS.get(f.rule_code, "")}
+            if f.rule_code and not item
+            else None,
            "detail": f.detail,
            "tender_citations": [cites[x.citation_id] for x in ls if x.side == "tender" and x.citation_id in cites],
            "bid_citations": [cites[x.citation_id] for x in ls if x.side == "bid" and x.citation_id in cites],
--- a/server/src/bid_doctor/document/pipeline/text_layer.py
+++ b/server/src/bid_doctor/document/pipeline/text_layer.py
@@ -59,6 +59,7 @@ class Sentence:
    fmt_runs: list[tuple[int, int, str]] = field(default_factory=list)  # [起, 止, 格式]，格式取 b / i / u 的组合
    location: str = "body"
    open_end: bool = False  # 写到页面末尾还没结束（没有句末标点、末行写满），可能接续到下一页
+    cell: list[float] | None = None  # 在有框线的表格里：所在单元格 [x0, top, x1, bottom]（查标按单元格分行）

    @property
    def marked(self) -> str:
@@ -83,6 +84,7 @@ class Sentence:
            "format_runs": [list(r) for r in self.fmt_runs],
            "location": self.location,
            "open_end": self.open_end,
+            **({"cell": self.cell} if self.cell else {}),
        }

    @classmethod
@@ -96,6 +98,7 @@ class Sentence:
            fmt_runs=[(a, b, f) for a, b, f in d["format_runs"]],
            location=d["location"],
            open_end=d.get("open_end", False),
+            cell=d.get("cell"),
        )


@@ -150,6 +153,7 @@ Cell = tuple[float, float, float, float]  # 单元格 (x0, top, x1, bottom)
 class FragInfo:
    right: float | None = None  # 单元格的右边界：判断段落末行用它，不用页面右边距
    cell_end: bool = False  # 单元格的最后一个片段：句子在这里结束
+    cell: Cell | None = None


 def _cell_of(c: dict[str, Any], cells: list[Cell]) -> int | None:
@@ -171,13 +175,13 @@ def _fragments(
    for i, cell_chars in by_cell.items():
        assert i is not None
        x0, top, x1, _ = cells[i]
-        blocks.append(((top, x0), _line_fragments(cell_chars), FragInfo(right=x1)))
+        blocks.append(((top, x0), _line_fragments(cell_chars), FragInfo(right=x1, cell=cells[i])))
    frags: list[list[dict[str, Any]]] = []
    infos: list[FragInfo] = []
    for _, fs, info in sorted(blocks, key=lambda b: b[0]):
        for j, f in enumerate(fs):
            frags.append(f)
-            infos.append(FragInfo(right=info.right, cell_end=j == len(fs) - 1) if info else FragInfo())
+            infos.append(FragInfo(right=info.right, cell_end=j == len(fs) - 1, cell=info.cell) if info else FragInfo())
    return frags, infos


@@ -310,6 +314,7 @@ def _page(doc_id: str, page: Any, frags: list[list[dict[str, Any]]], infos: list
                fmt_runs=runs,
                location=location,
                open_end=seq == tail_seq,
+                cell=[round(v, 2) for v in cell] if (cell := infos[g[0][0]].cell) and location == "body" else None,
            )
        )
    return Page(
--- a/server/tests/fixtures/bid-mini-forms.pdf
+++ b/server/tests/fixtures/bid-mini-forms.pdf
--- a/server/tests/fixtures/make_bid_fixtures.py
+++ b/server/tests/fixtures/make_bid_fixtures.py
@@ -3,7 +3,9 @@
    cd server && ../.venv/bin/python tests/fixtures/make_bid_fixtures.py   # 需要 Gotenberg（:3109）

 - bid-mini-v1.pdf：响应了资质证书和服务器内存，漏了交换机硬件 BFD → 1 个致命问题「未找到响应」；
- bid-mini-v2.pdf：补上了交换机硬件 BFD → 复查时这个问题「本次已解决」。
+- bid-mini-v2.pdf：补上了交换机硬件 BFD → 复查时这个问题「本次已解决」；
+- bid-mini-forms.pdf：v2 的内容 + 格式文件里的规则问题（大写和小写金额不一致、授权书没填投标人名称、
+  报价附加条件、另外给了一个优惠报价），措辞故意和评测集的开发词库不同。
 """

 from __future__ import annotations
@@ -18,6 +20,7 @@ GOTENBERG = "http://127.0.0.1:3109/forms/chromium/convert/html"
 HEAD = """<!doctype html><html><head><meta charset="utf-8"><style>
 body { font-family: "Noto Serif CJK SC", "Noto Sans CJK SC", serif; font-size: 12pt; line-height: 1.8; margin: 0; }
 h1 { font-size: 16pt; text-align: center; }
+table { border-collapse: collapse; width: 100%; } td, th { border: 1pt solid #333; padding: 4pt; }
 </style></head><body>"""

 COMMON = [
@@ -41,6 +44,16 @@ def render(name: str, parts: list[str]) -> None:
    print(name, len(r.content))


+FORMS = [
+    "<p>五、法定代表人授权委托书。本人王某（姓名）系（投标人名称）的法定代表人，现授权李某为我方代理人。</p>",
+    "<p>六、开标一览表</p>",
+    "<table><tr><th>项目名称</th><th>投标总报价（元）</th><th>投标总报价（大写）</th></tr>"
+    "<tr><td>某市智慧政务系统集成项目</td><td>1,280,000.00</td><td>壹拾贰万捌仟元整</td></tr></table>",
+    "<p>让利后总价：1,250,000.00元。</p>",
+    "<p>七、本次报价未包含设备运输费用，运输费用由采购人另行承担。</p>",
+]
+
 if __name__ == "__main__":
    render("bid-mini-v1.pdf", [*COMMON, *TAIL])
    render("bid-mini-v2.pdf", [*COMMON, BFD, *TAIL])
+    render("bid-mini-forms.pdf", [*COMMON, BFD, *FORMS, *TAIL])
--- a/server/tests/test_check_flow.py
+++ b/server/tests/test_check_flow.py
@@ -272,3 +272,36 @@ async def test_response_modes_are_stored_editable_and_used(user: User) -> None:
    (f,) = await findings(user, run["id"])
    assert f["type"] == "manual_review" and f["severity"] == "hint"
    assert run["counts"]["fatal"] == 0
+
+
+async def test_rule_findings_are_written_with_citations_and_carried(user: User) -> None:
+    """规则检查（报价形式、形式要件）：问题挂规则编号和投标原文，复查时按 match_key 沿用处理状态。"""
+    project_id, tender_id = await project_with_tender(user)
+    await run_parse(user, tender_id)
+    bid = await upload_bid(user, project_id, "bid-mini-forms.pdf")
+    run = await run_check(user, project_id, [bid["id"]])
+    assert run["status"] == "succeeded", run
+    rule = {f["rule"]["code"]: f for f in await findings(user, run["id"]) if f["detector"] == "rule"}
+    assert set(rule) == {
+        "PRICE.CAPITAL_MISMATCH",
+        "PRICE.MULTIPLE_QUOTES",
+        "FORM.BLANK_FIELD",
+        "FORM.CONDITION_ADDED",
+    }
+    cap = rule["PRICE.CAPITAL_MISMATCH"]
+    assert cap["type"] == "price_form" and cap["severity"] == "important" and cap["checklist_item"] is None
+    assert cap["rule"]["description"] == "大写金额和小写金额核对"
+    (c,) = cap["bid_citations"]  # 同一页的几句合成一条出处，各句分别画框
+    assert "壹拾贰万捌仟元整" in c["quote"] and "1,280,000.00" in c["quote"] and len(c["quads"]) >= 2
+    assert c["document_label"] == "技术分册"
+    # 「让利后总价」和投标总价不同：多半另报了一个价，但不是「备选方案」那种明确的两个报价，按重要
+    assert rule["PRICE.MULTIPLE_QUOTES"]["severity"] == "important" and rule["FORM.BLANK_FIELD"]["severity"] == "hint"
+    assert any("报价形式" in x for x in run["coverage"]["checked"])
+    assert run["coverage"]["rule_set_version"] == "2026.11-r1"
+
+    await user.post(f"/findings/{cap['id']}/resolve", json={"status": "ignored", "note": "大写栏已手工更正"})
+    again = await run_check(user, project_id, [bid["id"]])
+    cap2 = next(
+        f for f in await findings(user, again["id"]) if (f["rule"] or {}).get("code") == "PRICE.CAPITAL_MISMATCH"
+    )
+    assert cap2["presence"] == "carried" and cap2["status"] == "ignored"
--- a/server/tests/test_check_rules.py
+++ b/server/tests/test_check_rules.py
@@ -0,0 +1,259 @@
+"""查标的规则检查（报价形式、形式要件）：纯函数，投标文件用虚构的句子拼（rules.py，GUIDELINES §3.2）。
+
+措辞故意和评测集的开发词库不同：规则按招投标文件的通用写法写，不按评测集的句子写。
+"""
+
+from __future__ import annotations
+
+from datetime import date
+from decimal import Decimal
+from uuid import uuid4
+
+from bid_doctor.check import match, rules
+from bid_doctor.document.pipeline.text_layer import Sentence
+
+
+def cell(seq: int, text: str, x: float, y: float, page: int = 1, w: float = 60) -> Sentence:
+    return Sentence(key=f"b:p{page}:s{seq}", page_no=page, seq=seq, text=text, quads=[[x, y, x + w, y + 12]])
+
+
+def para(seq: int, text: str, page: int = 1) -> Sentence:
+    return cell(seq, text, 74, 30 + seq * 24, page, 440)
+
+
+def doc(sentences: list[Sentence], header: list[Sentence] | None = None) -> match.BidDoc:
+    return match.BidDoc(uuid4(), 1, "商务分册", sentences, [], header or [])
+
+
+def codes(hits: list[rules.Hit]) -> list[str]:
+    return sorted(h.code for h in hits)
+
+
+def test_upper_amount_and_day_counts() -> None:
+    assert rules.upper_amount("壹佰贰拾贰万柒仟陆佰元整") == Decimal(1_227_600)
+    assert rules.upper_amount("壹亿零伍佰万元零伍角") == Decimal("105000000.5")
+    assert rules.upper_amount("拾万元整") == Decimal(100_000)
+    assert rules.validity_days("投标有效期为开标之日起一百二十（120）天。") == [120]
+    assert rules.validity_days("本投标文件自投标截止之日起三个月内有效。") == [90]
+    assert rules.validity_days("投标有效期内中标的，须在30日内签订合同。") == []  # 「有效期内」后面的天数不是有效期
+
+
+def opening_table(lower: str, upper: str) -> list[Sentence]:
+    return [
+        cell(1, "项目名称", 80, 100),
+        cell(2, "投标总价（小写，元）", 220, 100),
+        cell(3, "投标总价（大写）", 380, 100),
+        cell(4, "某市数据中心扩容项目", 80, 124),
+        cell(5, lower, 220, 124),
+        cell(6, upper, 380, 124),
+    ]
+
+
+def test_capital_mismatch_and_over_ceiling() -> None:
+    d = doc(opening_table("2,050,000.00", "贰佰万元整"))
+    hits, _ = rules.run(rules.Facts(ceiling=Decimal(2_000_000)), [d], [])
+    assert codes(hits) == ["PRICE.CAPITAL_MISMATCH", "PRICE.OVER_CEILING_TOTAL"]
+    over = next(h for h in hits if h.code == "PRICE.OVER_CEILING_TOTAL")
+    assert over.severity == "fatal" and over.basis == "ceiling" and over.evidence[0][1].text == "2,050,000.00"
+    assert "建议" not in over.explanation and "应改为" not in over.explanation  # 红线 6：不写数字建议
+
+    same = doc(opening_table("2,050,000.00", "贰佰零伍万元整"))
+    assert rules.run(rules.Facts(ceiling=Decimal(3_000_000)), [same], [])[0] == []
+
+
+def item_table(rows: list[tuple[str, str, str, str]], total: str, page: int = 1) -> list[Sentence]:
+    out = [
+        cell(1, "序号", 80, 100, page, 20),
+        cell(2, "货物名称", 110, 100, page, 100),
+        cell(3, "数量", 260, 100, page, 30),
+        cell(4, "单价（元）", 320, 100, page),
+        cell(5, "合价（元）", 420, 100, page),
+    ]
+    for i, (name, qty, unit, line) in enumerate(rows):
+        y, n = 124 + i * 22, 10 + i * 5
+        out += [
+            cell(n, str(i + 1), 82, y, page, 8),
+            cell(n + 1, name, 110, y, page, 100),
+            cell(n + 2, qty, 272, y, page, 8),  # 窄数字居中，和表头「数量」不重叠
+            cell(n + 3, unit, 320, y, page),
+            cell(n + 4, line, 420, y, page),
+        ]
+    out.append(cell(99, f"合计：{total}元", 80, 124 + len(rows) * 22 + 6, page, 300))
+    return out
+
+
+def test_item_table_arithmetic() -> None:
+    ok = item_table(
+        [("服务器", "3", "100,000.33", "300,001.00"), ("存储", "1", "50,000.00", "50,000.00")], "350,001.00"
+    )
+    assert rules.run(rules.Facts(), [doc(ok)], [])[0] == []  # 单价舍入到分，合价差几分钱不算错
+
+    bad = item_table(
+        [("服务器", "3", "100,000.00", "310,000.00"), ("存储", "1", "50,000.00", "50,000.00")], "350,000.00"
+    )
+    (h,) = rules.run(rules.Facts(), [doc(bad)], [])[0]
+    assert h.code == "PRICE.SUM_MISMATCH" and "服务器" in h.explanation and "合计行" in h.explanation
+    assert "310,000.00" in [s.text for _, s in h.evidence]
+
+
+def test_foreign_project_in_header_and_filled_fields() -> None:
+    facts = rules.Facts(name="某市数据中心扩容项目", code="ZC-2026-0815-A", purchaser="某市大数据局")
+    header = [
+        Sentence(
+            key=f"b:p{p}:s0",
+            page_no=p,
+            seq=0,
+            text="某县人民医院信息化改造工程",
+            quads=[[0, 0, 1, 1]],
+            location="header_footer",
+        )
+        for p in (1, 2)
+    ]
+    body = [
+        para(1, "致：某市大数据局（采购人名称）"),
+        para(2, "参加ZC-2026-0815-A（项目编号）某市数据中心扩容项目（项目名称）的投标。"),
+        para(3, "我方承诺参加ZC-2025-0311-B（项目编号）的投标活动。"),
+        para(4, "类似业绩：项目名称：某省政务云平台运维服务项目，合同金额200万元。"),  # 业绩不在填写位里，不查
+    ]
+    hits, _ = rules.run(facts, [doc(body, header)], [])
+    assert codes(hits) == ["FORM.FOREIGN_PROJECT", "FORM.FOREIGN_PROJECT"]
+    head = next(h for h in hits if h.target.startswith("header:"))
+    assert head.detail["pages"] == [1, 2] and head.basis == "name"
+    assert any("ZC-2025-0311-B" in h.explanation for h in hits)
+
+
+def test_blank_fields_and_kept_annotations() -> None:
+    d = doc(
+        [
+            para(1, "投标人名称（盖单位章）：某某科技有限公司"),  # 括注保留、名称已填：不算
+            para(2, "本授权书于年月日签署生效。"),
+            para(3, "被授权人：＿＿＿＿（签字）"),
+            para(4, "法定代表人身份证号：/"),  # 划除：不算
+        ]
+    )
+    hits, _ = rules.run(rules.Facts(), [d], [])
+    assert [h.evidence[0][1].seq for h in hits] == [2, 3] and {h.severity for h in hits} == {"hint"}
+
+
+def test_sign_dates_validity_conditions_and_extra_quotes() -> None:
+    facts = rules.Facts(deadline=date(2026, 12, 1), validity_days=90)
+    d = doc(
+        [
+            para(1, "签署日期：2026年12月3日"),
+            para(2, "日期：2026年11月31日"),
+            para(3, "证书发证日期：2027年1月1日"),  # 不是落款日期
+            para(4, "本投标有效期为自投标截止之日起六十日。"),
+            para(5, "供货数量按实际需求结算，安装调试费用由采购人负责。"),
+            para(6, "培训费用已包含在报价中，不另行收费。"),  # 承诺，不是附加条件
+            para(7, "第二套报价方案总价：1,880,000.00元"),
+            para(8, "我方不提交备选方案报价。"),
+        ]
+    )
+    hits, _ = rules.run(facts, [d], [])
+    got = {(h.code, h.evidence[0][1].seq) for h in hits}
+    assert got == {
+        ("FORM.DATE_AFTER_DEADLINE", 1),
+        ("FORM.DATE_AFTER_DEADLINE", 2),
+        ("FORM.VALIDITY_SHORT", 4),
+        ("FORM.CONDITION_ADDED", 5),
+        ("PRICE.MULTIPLE_QUOTES", 7),
+    }
+    bad_date = next(h for h in hits if h.evidence[0][1].seq == 2)
+    assert bad_date.title == "落款日期写法有误"
+
+
+def test_response_table_negative_and_dedupe() -> None:
+    rows = [
+        cell(1, "实质性要求响应表", 74, 76, w=200),
+        cell(2, "序号", 80, 100, w=20),
+        cell(3, "实质性要求", 110, 100, w=150),
+        cell(4, "响应情况", 300, 100),
+        cell(5, "1", 82, 124, w=8),
+        cell(6, "“交货期”的响应情况", 110, 124, w=150),
+        cell(7, "完全响应", 300, 124),
+        cell(8, "2", 82, 146, w=8),
+        cell(9, "“付款方式”的响应情况", 110, 146, w=150),
+        cell(10, "部分满足", 300, 146),
+        cell(11, "3", 82, 168, w=8),
+        cell(12, "“质保期”的响应情况", 110, 168, w=150),
+    ]
+    d = doc(rows)
+    hits, _ = rules.run(rules.Facts(), [d], [])
+    assert [(h.title, h.severity) for h in hits] == [
+        ("响应表里写了「部分满足」", "fatal"),
+        ("响应表里有一行没有填响应情况", "important"),  # 「空着」可能是版面没认准：不给致命
+    ]
+    covered = {("商务分册", 1, "部分满足")}  # 响应匹配已经按清单项报了这一句
+    assert [h.title for h in rules.drop_covered(hits, covered)] == ["响应表里有一行没有填响应情况"]
+
+
+def test_missing_facts_go_to_coverage() -> None:
+    _, cov = rules.run(rules.Facts(), [doc([para(1, "我方承诺按招标文件要求提供服务。")])], [])
+    text = "；".join(cov["not_checked"])
+    for want in ("没有认出开标一览表", "最高限价", "投标截止时间", "投标有效期", "项目名称"):
+        assert want in text
+
+
+def boxed(seq: int, text: str, cell: list[float], dy: float = 0) -> Sentence:
+    """有框线表格里的句子：文字框可以比单元格上沿低（垂直居中），分行按单元格。"""
+    x0, top, x1, _ = cell
+    s = cell_sentence = Sentence(
+        key=f"b:p1:s{seq}", page_no=1, seq=seq, text=text, quads=[[x0 + 2, top + 2 + dy, x1 - 2, top + 14 + dy]]
+    )
+    cell_sentence.cell = cell
+    return s
+
+
+def test_real_layout_negatives() -> None:
+    """真实投标文件常见、但不该报的写法（Fable 审读提出的反例）。"""
+    # 分组小计不算进明细；金额栏叫「投标报价」的分项表不是开标一览表，几行金额不算「多个总价」
+    rows = item_table([("服务器", "2", "10,000.00", "20,000.00"), ("交换机", "1", "5,000.00", "5,000.00")], "25,000.00")
+    rows.insert(-1, cell(90, "硬件小计", 110, 175, w=100))
+    rows.insert(-1, cell(91, "25,000.00", 420, 175))
+    multi = [
+        cell(1, "年度", 80, 300, page=2),
+        cell(2, "投标报价（元）", 220, 300, page=2),
+        cell(3, "第一年", 80, 324, page=2),
+        cell(4, "100,000.00", 220, 324, page=2),
+        cell(5, "第二年", 80, 348, page=2),
+        cell(6, "120,000.00", 220, 348, page=2),
+    ]
+    # 响应表：短格垂直居中，文字比编号低半行，但在同一个单元格行里
+    resp = [
+        boxed(20, "序号", [80, 400, 100, 420]),
+        boxed(21, "符合性审查要求", [100, 400, 300, 420]),
+        boxed(22, "响应情况", [300, 400, 380, 420]),
+        boxed(23, "1", [80, 420, 100, 460]),
+        boxed(24, "投标人须承诺按期交货，交货期不超过合同签订后三十日", [100, 420, 300, 460]),
+        boxed(25, "完全响应", [300, 420, 380, 460], dy=14),
+    ]
+    header = [
+        Sentence(
+            key="b:p1:s0", page_no=1, seq=0, text="第三章 技术服务方案", quads=[[0, 0, 1, 1]], location="header_footer"
+        )
+    ]
+    body = [
+        para(30, "致：贵单位"),
+        para(31, "附件：原厂报价单。本报价有效期30天，过期另行报价。", page=3),
+        para(32, "优惠后报价：25,000.00元", page=3),
+        para(33, "日  期：二〇二六年十一月二十日", page=3),
+    ]
+    facts = rules.Facts(
+        name="某市数据中心扩容项目", purchaser="某市大数据局", deadline=date(2026, 12, 1), validity_days=60
+    )
+    hits, _ = rules.run(facts, [doc([*rows, *multi, *resp, *body], header)], [])
+    assert [(h.code, h.severity) for h in hits] == [("FORM.CONDITION_ADDED", "important")]  # 「过期另行报价」照报
+
+
+def test_validity_in_letter_table_and_chinese_dates() -> None:
+    page = [
+        para(1, "投标函"),
+        cell(2, "投标有效期", 80, 200),
+        cell(3, "四十五天", 220, 200),
+        para(4, "落款日期：二〇二六年十二月三日"),
+    ]
+    hits, _ = rules.run(rules.Facts(deadline=date(2026, 12, 1), validity_days=60), [doc(page)], [])
+    assert {(h.code, h.severity) for h in hits} == {
+        ("FORM.VALIDITY_SHORT", "fatal"),
+        ("FORM.DATE_AFTER_DEADLINE", "hint"),
+    }