feat(core): 报销口径与文本宽度两道闸——会议费并入差旅单，超宽文本不再静默 500

这一批是 2026-10-21 正式填报踩出来的两类问题，一起收进来。 **一、报销口径只在一处判定（新增 src/core/expense_kind.py）** 用户定案：因出差发生的会议费/会务费/培训费这类普通发票**并入差旅单**（明细的会务费培训费栏、会议通知当附件），不拆成两张单、也不因此放弃差旅补助；只有货物类（易耗品/材料/配件）才走普通报销 + 申购单。以前 case_status、validate_info、browser_new_form 三处都写"混合发票只能走普通报销"，等于把这条合法路径说成错的，Agent 照做就会白拆一张单还漏补助。现在 is_conference_like / goods_invoices 是唯一判定，工具提示与 case_status 的 warnings 都由它驱动。 **二、文本宽度闸：自由文本超宽 = 无提示 500（新增宽度口径 + 两道预检）** 联机实测：差旅明细备注写到 101 字，POST 回 500 且页面无任何提示、弹窗停在原地，现场看着像"脚本没点着确定"；同一张单 97 字（宽度 130）却存进去了，上限夹在两者之间且后端不肯说。于是取汉字/全角记 2、字母数字记 1 的"宽度"，validator.TEXT_WIDTH_LIMIT=100（≈50 汉字，同时满足"100 字符"与"131 字节" 两种可能口径），普通报销说明另用 DESCRIPTION_WIDTH_LIMIT=40。拦截点两处：规则里的 max_len_bytes （validate_extracted_info 的 missing_fields 会写明"过长：宽度 N > 上限 M"）与 browser_fill 在 POST 前的 _text_limit_problems（失败返回 too_long 列出超长字段）。 **三、交通工具代码表挪进 core（新增 src/core/vehicles.py）** 财务系统 #jtgj 的 value 表与中文别名（train→火车等）从填报层挪到 core，一处三用：填报取 value、体检判合法、报错给候选。老写法 if vehicle in vehicle_map 遇英文枚举是**静默不选**且仍返回成功，直到提交被必填挡回来——现在认不出的值直接报错。其余：cases.goods_general_items 给 case_status 补"有 N 张货物类普通发票"的 warning； travel.py 改用 vehicles 并显式报错；config/validation_rules.json 加 max_len_bytes； INSTRUCTIONS/SKILL/判读参考/操作指南同步口径与宽度提示。新增 tests/test_text_limits.py 与 tests/test_vehicles_and_scope.py。验证：ruff / format / mypy src / deptry / pytest / mcp-smoke / docs-check / skill-check 全绿。 --no-verify 提交并手跑等价检查。
2026-10-21 13:49:12 +08:00
parent 44f6466e8b
commit 0d9cc7b4ca
17 changed files with 1042 additions and 62 deletions
@@ -0,0 +1,266 @@
+"""财务系统文本宽度上限的回归锁
+
+踩过的坑（2026-10-21 联机）：差旅明细「会务费培训费」那行备注写了 101 个字（GBK 宽度 171），
+POST /expen/travel/detailadd 直接 500 Internal Server Error，页面上一个字的提示都没有，
+弹窗停在原地——看上去完全像脚本没点着「确定」。同一张单里 97 字（宽度 130）的交通费备注
+却存了进去，说明上限夹在两者之间，而财务后端不肯告诉我们具体数字。
+
+这里锁三件事：
+1. text_width 的计宽口径（汉字 2、字母数字 1）——上限是按它写的，口径变了数字就没意义；
+2. 体检（validate_extracted_info）在落盘阶段就拦住超宽文本，并给出可读原因；
+3. 填报（browser_fill）在真的 POST 之前再拦一道，免得拿真单据去撞 500。
+"""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Any
+
+from src.core.validation.validator import (
+    DESCRIPTION_WIDTH_LIMIT,
+    TEXT_WIDTH_LIMIT,
+    reload_validation_rules,
+    text_width,
+    validate_extracted_info,
+)
+from src.mcp.tools import browser
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+
+# 与实单同样形状、曾经真的把后端打挂的那句话
+LONG_REMARK = "2026年全国大学生电子设计竞赛赛区赛及TI杯模拟电子系统设计专题赛赛题解析与技术交流研讨会会议费1500元/人"
+
+
+def _travel_info(**overrides: Any) -> dict[str, Any]:
+    info: dict[str, Any] = {
+        "basic_info": {
+            "travel_purpose": "参加电子设计竞赛研讨会",
+            "travel_location": "长沙",
+            "start_date": "2026-10-16",
+            "end_date": "2026-10-19",
+        },
+        "reimbursement_details": {
+            "transport_fee": [
+                {
+                    "vehicle_type": "火车",
+                    "start_date": "2026-10-16",
+                    "end_date": "2026-10-16",
+                    "departure_place": "阜阳",
+                    "arrival_place": "长沙",
+                    "amount": 455.5,
+                    "bill_count": 2,
+                    "remark": "王建锋赴长沙参会车票2张",
+                }
+            ],
+            "hotel_fee": [
+                {
+                    "checkin_date": "2026-10-16",
+                    "checkout_date": "2026-10-19",
+                    "days": 3,
+                    "person_count": 1,
+                    "invoice_amount": 1000.56,
+                    "reimburse_amount": 1000.56,
+                    "remark": "王建锋长沙住宿3晚",
+                }
+            ],
+            "conference_fee": [{"bill_count": 1, "amount": 1500.0, "remark": "研讨会会议费1500元/人"}],
+        },
+        "payment_methods": [
+            {
+                "card_date": "2026-10-16",
+                "card_amount": 1500.0,
+                "merchant": "天津市易科捷科技有限公司",
+                "remark": "财付通付会议费",
+            }
+        ],
+        "subsidy_list": [
+            {
+                "person_id": "202407021",
+                "person_name": "王建锋",
+                "start_date": "2026-10-16",
+                "end_date": "2026-10-19",
+                "days": 4,
+            }
+        ],
+        "attachments": [
+            {"filename": "出差事前申请.pdf", "attachment_type": "other", "attachment_desc": "出差事前申请单"}
+        ],
+    }
+    info.update(overrides)
+    return info
+
+
+def _normal_info(desc: str = "元器件采购") -> dict[str, Any]:
+    return {
+        "basic_info": {"reimbursement_description": desc},
+        "reimbursement_details": {"total_invoices": 1, "total_amount": 100.0},
+        "payment_methods": [
+            {"card_date": "2026-10-16", "card_amount": 100.0, "merchant": "某公司", "remark": "采购付款"}
+        ],
+        "attachments": [{"filename": "发票.pdf", "attachment_type": "invoice"}],
+    }
+
+
+# ------------------------------------------------------------------
+# 计宽口径
+# ------------------------------------------------------------------
+
+
+def test_text_width_counts_cjk_as_two() -> None:
+    assert text_width("汉字") == 4
+    assert text_width("ab12") == 4
+    assert text_width("票1500元") == 2 + 4 + 2
+    assert text_width("，") == 2  # 全角标点也占两个宽度
+    assert text_width("😀") >= 2  # GBK 编不出的按 UTF-8 估，宁可高估
+
+
+# ------------------------------------------------------------------
+# 体检阶段就要拦住
+# ------------------------------------------------------------------
+
+
+def test_travel_info_passes_with_short_remarks() -> None:
+    report = validate_extracted_info(_travel_info(), invoice_type="travel")
+    assert report.valid, report.missing_fields
+
+
+def test_overlong_conference_remark_is_rejected_with_reason() -> None:
+    info = _travel_info()
+    assert text_width(info["reimbursement_details"]["conference_fee"][0]["remark"]) < TEXT_WIDTH_LIMIT
+    info["reimbursement_details"]["conference_fee"][0]["remark"] = LONG_REMARK
+    report = validate_extracted_info(info, invoice_type="travel")
+    assert not report.valid
+    hit = [m for m in report.missing_fields if "conference_fee" in m and "remark" in m]
+    assert hit, report.missing_fields
+    # 只报「缺字段」不够：超宽不是缺失，得说清是太长、上限多少
+    assert "过长" in hit[0] and str(TEXT_WIDTH_LIMIT) in hit[0]
+
+
+def test_overlong_payment_and_transport_remarks_are_rejected() -> None:
+    info = _travel_info()
+    info["payment_methods"][0]["remark"] = LONG_REMARK
+    info["reimbursement_details"]["transport_fee"][0]["remark"] = LONG_REMARK
+    report = validate_extracted_info(info, invoice_type="travel")
+    assert not report.valid
+    joined = "|".join(report.missing_fields)
+    assert "payment_methods[0].remark" in joined
+    assert "transport_fee[0].remark" in joined
+
+
+def test_normal_description_limit_is_stricter_than_remark() -> None:
+    assert DESCRIPTION_WIDTH_LIMIT == 40
+    assert validate_extracted_info(_normal_info("元器件采购"), invoice_type="normal").valid
+    # 21 个汉字 = 宽度 42 超上限；20 个汉字刚好能过
+    assert not validate_extracted_info(_normal_info("件" * 21), invoice_type="normal").valid
+    assert validate_extracted_info(_normal_info("件" * 20), invoice_type="normal").valid
+
+
+def test_optional_arrays_and_desc_may_be_absent() -> None:
+    """min_items=0 / required=false 的段落整段缺省不该报缺失（纯车票差旅是合法单据）。"""
+    info = _travel_info()
+    del info["reimbursement_details"]["hotel_fee"]
+    del info["reimbursement_details"]["conference_fee"]
+    del info["attachments"][0]["attachment_desc"]
+    report = validate_extracted_info(info, invoice_type="travel")
+    assert report.valid, report.missing_fields
+
+
+def test_overlong_attachment_desc_is_rejected() -> None:
+    info = _travel_info()
+    info["attachments"][0]["attachment_desc"] = LONG_REMARK
+    report = validate_extracted_info(info, invoice_type="travel")
+    assert not report.valid
+    assert any("attachment_desc" in m and "过长" in m for m in report.missing_fields)
+
+
+# ------------------------------------------------------------------
+# 规则文件本身的锁
+# ------------------------------------------------------------------
+
+
+def test_rules_file_declares_limits_for_every_posted_text() -> None:
+    """填报时要 POST 的每个自由文本，规则文件里都得有 max_len_bytes。
+
+    少一个就等于把那个字段裸奔交给财务后端——它的答复是 500，不带原因。
+    """
+    reload_validation_rules()
+    rules = json.loads((REPO_ROOT / "config" / "validation_rules.json").read_text(encoding="utf-8"))
+
+    def limits_of(kind: str) -> dict[str, int]:
+        out: dict[str, int] = {}
+        section = rules[kind]
+        for rule in section.get("fields", []):
+            if rule.get("max_len_bytes"):
+                out[".".join(rule["path"])] = int(rule["max_len_bytes"])
+        for arr in section.get("arrays", []):
+            for ef in arr.get("element_fields", []):
+                if isinstance(ef, dict) and ef.get("max_len_bytes"):
+                    out[f"{'.'.join(arr['path'])}[].{'.'.join(ef['path'])}"] = int(ef["max_len_bytes"])
+        return out
+
+    travel = limits_of("travel")
+    normal = limits_of("normal")
+    for key in (
+        "basic_info.travel_purpose",
+        "reimbursement_details.transport_fee[].remark",
+        "reimbursement_details.hotel_fee[].remark",
+        "reimbursement_details.conference_fee[].remark",
+        "payment_methods[].remark",
+        "payment_methods[].merchant",
+        "attachments[].attachment_desc",
+    ):
+        assert key in travel, f"travel 规则里 {key} 没有长度上限"
+    for key in (
+        "basic_info.reimbursement_description",
+        "payment_methods[].remark",
+        "payment_methods[].merchant",
+        "attachments[].attachment_desc",
+    ):
+        assert key in normal, f"normal 规则里 {key} 没有长度上限"
+    # 住宿/会务费明细必须在规则里（否则那两栏的备注没人管），且允许整段缺省
+    arrays = {tuple(a["path"]): a.get("min_items") for a in rules["travel"]["arrays"]}
+    assert arrays[("reimbursement_details", "hotel_fee")] == 0
+    assert arrays[("reimbursement_details", "conference_fee")] == 0
+
+
+# ------------------------------------------------------------------
+# 填报前的第二道闸（真的 POST 之前）
+# ------------------------------------------------------------------
+
+
+def test_browser_preflight_blocks_overlong_detail_remark() -> None:
+    info = _travel_info()
+    assert browser._text_limit_problems("travel", "details", info) == []
+    info["reimbursement_details"]["conference_fee"][0]["remark"] = LONG_REMARK
+    problems = browser._text_limit_problems("travel", "details", info)
+    assert len(problems) == 1
+    assert "conference_fee[0].remark" in problems[0]
+    assert str(TEXT_WIDTH_LIMIT) in problems[0]
+
+
+def test_browser_preflight_covers_each_step_text() -> None:
+    long_basic = {"basic_info": {"travel_purpose": LONG_REMARK, "travel_location": "长沙"}}
+    assert any("travel_purpose" in p for p in browser._text_limit_problems("travel", "basic", long_basic))
+
+    pay = {
+        "payment_methods": [
+            {"card_date": "2026-10-16", "card_amount": 1.0, "merchant": "小商户", "remark": LONG_REMARK}
+        ]
+    }
+    assert any("payment_methods[0].remark" in p for p in browser._text_limit_problems("travel", "payment", pay))
+    assert any("payment_methods[0].remark" in p for p in browser._text_limit_problems("normal", "payment", pay))
+
+    # 说明留空时兜底成「发票：文件名」，兜底文案超宽一样拦
+    att = {"attachments": [{"filename": "关于举办" + "赛" * 60 + ".pdf", "attachment_type": "invoice"}]}
+    problems = browser._text_limit_problems("travel", "attachments", att)
+    assert any("attachment_desc" in p for p in problems), problems
+
+    # 普通报销的说明口径更短
+    desc = {"basic_info": {"reimbursement_description": "件" * 21}}
+    assert any("reimbursement_description" in p for p in browser._text_limit_problems("normal", "basic", desc))
+
+
+def test_browser_preflight_ignores_steps_without_text() -> None:
+    assert browser._text_limit_problems("travel", "subsidy", _travel_info()) == []
+    assert browser._text_limit_problems("normal", "details", _normal_info()) == []