补齐附加费用同义追问的报价上下文

AGENTS.md

@@ -13,7 +13,7 @@ Use `am.py` for CLI/WSGI, `logistics_chat/` for business code, and `static/css/`
 | Order lookup UI | `static/js/order_lookup.js`: `OrderLookup.create`; `chat.js`: `showOrderLookup`, `fillTrackCard`; `support.js`: `copyText` |
 | Chat drafts | `static/js/drafts.js`: `ChatDrafts.create`; `chat.js`: `flushDraft`, `restoreDraft`, startup recovery |
 | Knowledge | `logistics_chat/knowledge.py`: `knowledge_list`, `search_knowledge`; `docs/knowledge.md` |
-| Pricing | `logistics_chat/pricing.py`: `RATES`, `calc_freight`; `logistics_chat/rates_extra.py` |
+| Pricing | `logistics_chat/pricing.py`: `RATES`, `calc_freight`; `quote_intent.py`: `parse_intent`; `quote_service.py`: `answer_quote`; `quote_engine.py`: `quantity`, `render_rates`; `quote_answers.py`, `quote_fees.py`: local business terms and fees |
 | US quote data | `logistics_chat/quote_workbook.py`: local detail export; `quote_data.py`: versioned SQLite imports; `quote_engine.py`: matching/calculation; `quote_service.py`: conversational reply; `scripts/import_quote_data.py` |
 | Tracking | `logistics_chat/tracking.py`: `extract_tracking_no`, `build_track`, `CARD_PREFIX` |
 | Order test data | `logistics_chat/order_data.py`: `lookup_order`, `count_orders`, `answer_query`, `import_records`; `scripts/import_order_test_data.py` |

docs/architecture.md

@@ -131,12 +131,16 @@ tests/                        # 按业务模块组织的回归
 
 ## 验证与维护
 
-美国报价由 `quote_workbook.py` 导出当前 Excel 本地明细；`quote_data.py` 管理版本与 SQLite；`quote_engine.py` 负责纯匹配/Decimal 计价；`quote_service.py` 续接当前会话并通过 `answer_quote` 返回既有 `t`/`d` 事件。分流位置在订单权限检查之后、旧报价/模型分流之前。
+美国报价由 `quote_workbook.py` 导出当前 Excel 本地明细；`quote_data.py` 管理版本与 SQLite；`quote_intent.py` 解析单位、逐箱明细和业务意图；`quote_engine.py` 负责纯匹配/Decimal 计价；`quote_answers.py` 和 `quote_fees.py` 从当前版本说明读取业务收费；`quote_language.py` 翻译常规英文报价；`quote_service.py` 续接当前会话并通过 `answer_quote` 返回既有 `t`/`d` 事件。分流位置在订单权限检查之后、旧报价/模型分流之前。
 
 新建库不预置价格；私有快照事务导入、显式激活，读取使用同一事务固定版本，后续查询读取更新后的价格。不访问外部工作簿，不按文件日期或旧船期停用。仓码重复分区并列；邮编存文本；上下文仅来自当前访客拥有的同一会话，新的完整问题、其他国家及订单/理赔话题构成边界。回复不包含原始快照、联系人、文件路径或旧船期，不新增公开导入/管理接口。
 
 `quote_documents` 保存当前资料说明，复杂业务说明及尚未实现的附加费仍需逐项扩展匹配规则，不代表已全部自动结算。生产镜像必须显式包含 `scripts/import_quote_data.py`。
 
+已确认口径：同件超重/超尺寸只取最高适用档，其他附加费分别计算；洛杉矶普船海卡体积保留两位、四舍五入；海外进口清关超过5个品名的续页按美元/个。原表大尺寸长度条件有误，不猜测下限，只有其他两条明确条件同时满足时自动应用该档，其余疑似大件转人工确认。报价不把提取时效称为签收时效。金额仍读取激活版本，不把私有费率写入源码。
+
+订单列表使用与逐单查询相同的服务端租户交集，每次最多展示20票并保护其会话历史；未知筛选条件不默认为全部订单。改址/取消尚无业务写入接口，只明确引导人工，不声称修改成功。输入明确的转人工指令复用现有申请接口，失败保留草稿，不增加SSE事件类型。
+
 先按 README 安装项目依赖。Windows 使用 `.\.venv\Scripts\python.exe -m pytest -v` 或同解释器的 `-m unittest discover -s tests -v`；Linux/macOS 使用 `.venv/bin/python`。业务测试依赖 Flask，不能用未安装依赖的全局 Python 运行整套测试。模型请求全部模拟，不代表真实 DeepSeek 联调。
 
 路径、函数或资产移动后同步更新根 `AGENTS.md`、本文、知识资料和 README 目录树。仅改导航时检查路径、符号、命令；改业务时补充相关成功和失败分支，前端改动检查实际页面。

logistics_chat/chat_service.py

@@ -93,6 +93,10 @@ def create_chat_stream(msg, conv_id):
     order_answer = answer_query(msg, conv_id)
     if order_answer is None:
         order_answer = answer_quote(msg, conv_id)
+    if order_answer is None and re.search(r'(?:转|联系|接入|找).*人工|人工客服',msg):
+        order_answer = {'t':'点击“联系人工”可发起人工客服申请；非工作时间可留言。'}
+    if order_answer is None and re.search(r'照片|图片',msg) and re.search(r'报价|价格|判断|识别',msg):
+        order_answer = {'t':'可以通过输入框旁的“+”上传照片供人工查看。当前聊天不会自动识别图片，请同时用文字提供品名、重量、箱数、尺寸和目的仓码或邮编，再核算报价。'}
     if order_answer is None and re.fullmatch(r'\[图片\]/uploads/\S+', msg):
         order_answer = {'t':'收到您的图片，请描述一下您的问题。'}
     ship = shipping_intent_with_context(msg, conv_id) if order_answer is None else None

logistics_chat/order_data.py

@@ -219,7 +219,46 @@ def answer_count_query(intent, tenants):
     return {'t':text + f"，其中 {counts['with_inbound']} 票已登记入仓码。", '_customer_data':True}
 
 
+def answer_list_query(message, tenants):
+    """Reuse bounded status parsing; list reads require an explicit customer scope."""
+    if is_lookup_help(message) or not re.search(r'订单|运单|\borders?\b|\bshipments?\b',message,re.I):
+        return None
+    if not re.search(r'列出|列表|全部|所有|\blist\b',message,re.I):
+        return None
+    if not tenants:
+        return order_login_response()
+    question=re.sub(r'列出|列表|全部|所有|\blist\b','多少',message,flags=re.I)
+    intent=parse_count_query(question)
+    if intent is None or intent['unsupported']:
+        return {'t':'暂不支持按这个条件列出订单。可查看全部订单或按履约中、已完成等业务状态查询。'}
+    scope=tenant_filter(tenant_ids=tenants)
+    if scope is None:
+        return order_login_response()
+    from .db import connect
+    connection=None
+    try:
+        connection=connect()
+        sql='SELECT order_no,inbound_code,status,warehouse_code FROM order_test_data WHERE 1=1'+scope[0]
+        values=scope[1]
+        if intent['status']:
+            sql+=' AND status=?';values=values+[intent['status']]
+        rows=connection.execute(sql+' ORDER BY id DESC LIMIT 21',values).fetchall()
+        if not rows:return {'t':'当前账号下没有符合条件的订单。','_customer_data':True}
+        lines=['您当前的订单列表'+('（先列出20票）' if len(rows)>20 else '')+'：']
+        for number,inbound,status,warehouse in rows[:20]:
+            lines.append(f'- 入仓码：{inbound or "未登记"}；订单号：{number}；业务状态：{STATUS_LABELS.get(status,status)}；目的仓：{warehouse or "未登记"}')
+        lines.append('发送入仓码可查询该票订单和物流轨迹。')
+        return {'t':'\n'.join(lines),'_customer_data':True}
+    except sqlite3.Error:
+        return {'t':'订单信息暂时无法读取，请稍后重试。'}
+    finally:
+        if connection is not None:connection.close()
+
+
 def extract_reference(message):
+    # Explicit postal/monetary fields are not order identifiers, even if invalid.
+    message = re.sub(r'(?:邮编|zip(?:\s*code)?|post\s*code)\s*[:：为是]?\s*[0-9-]+', ' ', message, flags=re.I)
+    message = re.sub(r'(?<![A-Za-z0-9_-])\d+(?:\.\d+)?\s*(?:万)?(?:USD|RMB|CNY|美元|美金|人民币|元)(?![A-Za-z0-9_-])',' ',message,flags=re.I)
     message = re.sub(r'\[(?:图片|文件)\]/uploads/\S+|https?://\S+', '', message)
     message = re.sub(r'(?<![A-Za-z0-9_-])\d{4}-\d{1,2}-\d{1,2}'
                      r'(?:[T ]\d{1,2}:\d{2}(?::\d{2}(?:\.\d+)?)?(?:Z|[+-]\d{2}:?\d{2})?)?'
@@ -227,10 +266,14 @@ def extract_reference(message):
     message = re.sub(r'(?<![A-Za-z0-9_.-])\d+(?:\.\d+)?\s*[*xX×]\s*\d+(?:\.\d+)?\s*[*xX×]\s*\d+(?:\.\d+)?'
                      r'(?:\s*(?:cm|mm|m|厘米|毫米|米))?(?![A-Za-z0-9_.-])', ' ', message, flags=re.I)
     message = re.sub(r'(?<![A-Za-z0-9_-])\d+(?:\.\d+)?\s*'
-                     r'(?:kg|lbs?|cbm|cm|mm|公斤|千克|克|吨|立方米|方|m[³3]|箱|件)'
+                     r'(?:kilograms?|kgs?|grams?|g|tons?|lbs?|磅|cbm|cm|mm|公斤|千克|克|吨|立方米|方|m[³3]|箱|件)'
                      r'(?![A-Za-z0-9_])', ' ', message, flags=re.I)
     references = []
     for token in IDENTIFIER.findall(message):
+        if (re.fullmatch(r'[A-Za-z]{2,4}[0-9][A-Za-z0-9]{0,2}',token)
+                and re.search(r'美国|报价|海派|海卡|海运|\bquote\b',message,re.I)
+                and not re.search(r'订单|运单|入仓|轨迹|查单|\btrack\b',message,re.I)):
+            continue
         if sum(character.isdigit() for character in token) < 3:
             continue
         if re.fullmatch(r'\d{4}[-_]\d{2}[-_]\d{2}|\d+(?:KG|LBS?|CBM|CM|MM)', token, re.I):
@@ -335,6 +378,10 @@ def answer_query(message, conv_id):
     count_intent = parse_count_query(message) if not references else None
     if count_intent is not None:
         return answer_count_query(count_intent,tenants)
+    if not references:
+        listed=answer_list_query(message,tenants)
+        if listed is not None:return listed
+    mutation=bool(re.search(r'改址|修改.*(?:收件|地址|订单)|收件地址.*改|(?:取消|删除).*(?:订单|运单)|(?:订单|运单).*取消',message))
     if references and not tenants:
         return order_login_response()
     if len(references) > 1:
@@ -364,6 +411,8 @@ def answer_query(message, conv_id):
                 except (ValueError, KeyError, TypeError):
                     pass
     if not reference:
+        if mutation:
+            return order_login_response() if not tenants else {'t':'当前支持查询订单与物流轨迹；改址、取消等操作请联系人工客服办理，尚未修改订单。请提供入仓码。'}
         if is_tracking_request(message) or (not is_lookup_help(message) and re.search(r'(?:查|搜|看|找).*(?:订单|运单|物流轨迹|入仓码|入仓号)|(?:入仓码|入仓号).*(?:查|轨迹|状态)|订单状态|物流轨迹|shipment\s*id|'
                      r'(?:列出|搜索|所有|全部|多少|我的).*(?:订单|运单|入仓)|(?:订单|运单).*(?:多少|列表|查询|在哪|到哪|进度)|'
                      r'^\s*(?:查单|查询|查一下|帮我查一下)[。？！?!\s]*$|'
@@ -381,6 +430,8 @@ def answer_query(message, conv_id):
         return {'t':f'未找到“{reference}”对应的订单。请核对入仓码，或联系人工客服。'}
     if len(matches) > 1:
         return {'t':'该标识匹配到多个订单，请提供完整入仓码或联系人工客服确认。'}
+    if mutation:
+        return {'t':f'已查到订单“{reference}”。当前支持查询订单与物流轨迹；改址、取消等操作请联系人工客服办理，尚未修改订单。','_customer_data':True}
     if re.search(r'运费|费用|多少钱|价格', message):
-        return {'t':'该订单未记录实际运费，请联系人工客服核实。'}
+        return {'t':'该订单未记录实际运费，请联系人工客服核实。','_customer_data':True}
     return {'card': build_card(matches[0])}

logistics_chat/quote_answers.py

@@ -0,0 +1,98 @@
+"""Answer business questions from the active local book, without old regional FAQs."""
+
+from decimal import Decimal, ROUND_HALF_UP
+import re
+
+from .quote_fees import document, amount, material_fee, limit_fees
+
+
+def answer_business(intent,book):
+    from .quote_engine import number
+
+    text=intent['text'];mode=intent.get('mode')
+    if mode=='currency':
+        return '当前海卡、海派运价中的“元/KG”和“元/CBM”按人民币（RMB/CNY）计；一件代发等资料中标注“$”“USD”“美金”的费用按美元计。不同币种分别列明，未提供结算汇率时不自动换算。'
+    if mode=='insurance':
+        raw=document(book,('保险费','投保金额'))
+        percent=amount(raw,r'百分之\s*(\d+(?:\.\d+)?)')
+        minimum=amount(raw,r'min\s*(\d+(?:\.\d+)?)\s*USD')
+        multiplier=amount(raw,r'货值乘以\s*(\d+(?:\.\d+)?)')
+        if percent is None or minimum is None or multiplier is None:
+            return '当前资料未明确保险的完整计费条件，请提供货值和币种，由人工确认保险费。'
+        lines=[f'当前资料保险费率为保额的{percent:g}%，最低{minimum:g}USD；按货值投保时，投保金额为货值×{multiplier:g}。']
+        money=re.search(r'(-?\d+(?:\.\d+)?)\s*(万)?\s*(美元|美金|USD|人民币|元)',text,re.I)
+        if money and money.group(3).lower() in ('美元','美金','usd'):
+            value=Decimal(money.group(1))*(10000 if money.group(2) else 1)
+            if not 0<value<=1000000000:return '请提供大于0的有效货值或保额及币种。'
+            insured=value if re.search(r'保价|保额',text) and not re.search(r'货值',text) else value*multiplier
+            total=max(insured*percent/100,minimum).quantize(Decimal('.01'),rounding=ROUND_HALF_UP)
+            lines.append(f'按保额{number(insured)}USD计算：max({number(insured)}×{percent:g}%，{minimum:g})={number(total)}USD。')
+        else:
+            lines.append('请提供货值/保额及币种；人民币货值还需确认适用结算汇率。')
+        return '\n'.join(lines)
+    if mode=='fulfillment':
+        tokens=[t for t in ('20GP','40GP','45HQ','散箱','散托','贴标','仓储','仓租','分拣','SKU') if t.lower() in text.lower()]
+        if '仓租' in tokens:tokens.append('仓储')
+        if '卸货' in text and not tokens:tokens=['20GP','40GP','45HQ']
+        rows=[]
+        for d in book['documents']:
+            if d['sheet']!='一件代发收费' or not re.search(r'\$|USD|美金',d['content'],re.I):continue
+            score=sum(t.lower() in d['content'].lower() for t in tokens) if tokens else 1
+            if score:rows.append((score,d['content']))
+        rows=sorted(rows,key=lambda row:(-row[0],-('；' in row[1])))
+        facts=list(dict.fromkeys(row[1] for row in rows))[:4]
+        return '美国仓一件代发收费：\n'+'\n'.join('- '+r for r in facts) if facts else '当前资料中未匹配到该一件代发收费项，请补充服务项目、箱数或体积，由人工核实。'
+    if mode=='customs':
+        if intent.get('services') and '美森加班' in intent['services'] and document(book,('不可接一般贸易',),'美森加班海卡'):
+            return '当前资料中美森加班海卡不可接一般贸易，请由人工确认其他渠道，不能直接按该线路加报关费办理。'
+        if re.search(r'FDA',text,re.I):
+            raw=document(book,('FDA','申报费'))
+            fee=amount(raw,r'申报费[:：]?\s*RMB\s*(\d+(?:\.\d+)?)')
+            if fee is not None:return f'当前资料中需做FDA Filing等申报的产品，申报费为{fee:g}人民币/票。请补充具体品名和渠道，确认是否接收及需要的资料。'
+            return '当前资料未匹配到FDA申报费，请提供具体品名和渠道，由人工确认是否接收及费用。'
+        raw=document(book,('海外进口清关','续页'))
+        extra=amount(raw,r'加收USD\s*(\d+(?:\.\d+)?)')
+        lines=[]
+        if re.search(r'续页|品名',text) and extra is not None:
+            lines.append(f'海外进口清关：每票超过5个品名的部分，按{extra:g}美元/个收取。')
+            count=re.search(r'(\d+)\s*个品名',text)
+            if count:lines.append(f'{count.group(1)}个品名的该项费用：max({count.group(1)}−5,0)×{extra:g}={max(int(count.group(1))-5,0)*extra:g}美元。')
+            lines.append('国内出口报关续项与海外进口清关分别收费；国内条款的品名计数方式需按票确认。')
+        raw_fee=document(book,('一般贸易出口报关费',))
+        declaration=amount(raw_fee,r'出口报关费[:：]\s*RMB\s*(\d+(?:\.\d+)?)')
+        if declaration is not None:lines.append(f'一般贸易出口报关费为{declaration:g}人民币/票。')
+        if re.search(r'单独报关',text):
+            minimum=document(book,('单独报关货物','300KG'))
+            if minimum:lines.append('单独报关货物最低按300KG计费；还需确认所选渠道是否接受一般贸易。')
+        return '\n'.join(lines) or '请提供具体申报项目、品名数量及渠道，当前资料无法确定该项费用。'
+    if mode=='acceptance':
+        raw=document(book,('禁止运输的货物',))
+        if raw:
+            prohibited=next((t for t in ('纯电池','液体','粉末','食品','医疗用品','仿牌') if t in text),None)
+            if prohibited:return f'当前海派资料将{prohibited}列为不接收/禁止运输的类别，不能按普通货直接报价。若咨询其他渠道，请先由人工核实承运条件。'
+            if re.search(r'带电|电池',text):return '当前海派资料中内置电池需要提供产品图片、MSDS及海运运输鉴定报告后单独确认；纯电池不接收。请补充电池类型和产品信息，确认后再匹配运价。'
+        return '请提供品名、材质、是否带电及所选渠道，先核对承运条件，再计算对应费用。'
+    if mode=='fees':
+        lines=[]
+        metal=material_fee(book)
+        if metal is not None and re.search(r'铁制|钢制|铝制|铁铝|不锈钢',text):
+            lines.append(f'当前资料铁铝制品附加费为{metal:g}元/KG。')
+            if intent.get('weight'):lines.append(f'先按已提供重量{number(intent["weight"])}KG计算该项：{number(intent["weight"])}×{metal:g}={number(Decimal(intent["weight"])*metal)}元；计费重确定后继续核算。')
+        if re.search(r'超重|超尺寸|超长',text):
+            raw=document(book,('超重收',))
+            fee=amount(raw,r'超重收\s*[+＋]?\s*(\d+(?:\.\d+)?)')
+            if fee is not None:lines.append(f'海派明确的普通超重附加费为{fee:g}元/件；同箱同时超重、超尺寸时只收适用的最高一项。')
+            limits=limit_fees(intent,book)
+            lines+=limits['items']+limits['notes']
+        if re.search(r'住宅|私人|商业地址|非亚马逊',text):
+            lines.append('住宅或商业等非亚马逊地址的派送附加费在原表中需单独询价；请提供完整邮编、地址类型和箱规，不能直接当作FBA仓价格。')
+        if not lines or re.search(r'包含|包括|还[要需]|什么费用',text):
+            raw=document(book,('偏远地址加收','超偏远'))
+            remote=amount(raw,r'(?<!超)偏远地址加收\s*(\d+(?:\.\d+)?)元/kg')
+            extended=amount(raw,r'超偏远地址加收\s*(\d+(?:\.\d+)?)元/kg')
+            if remote is not None and extended is not None:
+                lines.append(f'当前美国海派资料：偏远地址加{remote:g}元/KG，超偏远地址加{extended:g}元/KG，遥远地址单询；海派每箱不足12KG按12KG计费。')
+            lines.append('报价中的包税/不包税是不同费率口径；材质、报关申报、偏远及超重超尺寸等按条件单列，不代表所有服务费用都已包含。')
+            if metal is not None:lines.append(f'铁铝制品附加费{metal:g}元/KG；多项费用分别列明，同箱超限费用只取最高项。')
+        return '\n'.join(lines)
+    return None

logistics_chat/quote_engine.py

@@ -3,64 +3,10 @@
 from decimal import Decimal, ROUND_HALF_UP
 import re
 
-from .pricing import parse_shipping_intent, detect_dim_unit, dims_to_cm, shipping_region
+from .pricing import dims_to_cm
 
 
-US = re.compile(r'美国|美西|美中|美东|洛杉矶|纽约|芝加哥|休斯顿|萨凡纳|'
-    r'(?<![A-Za-z])(?:USA|(?-i:US)|United States|America)(?=$|[^A-Za-z]|FBA(?![A-Za-z]))|'
-    r'(?:发(?:往|到)?|寄(?:往|到)?|运往|运到|到|往|\bto\s+)\s*us(?=$|[^A-Za-z]|FBA(?![A-Za-z]))', re.I)
-QUOTE_WORDS = re.compile(r'报价|价格|运费|费用|多少钱|计费|包税|海运|空运|海派|海卡|海铁|美森|合德|普船|\bEXX\b|\b(?:quote|price|cost|freight)\b', re.I)
-
-
-def parse_intent(message, warehouse_codes):
-    parsed = parse_shipping_intent(message)
-    country = 'US' if US.search(message) else ('other' if shipping_region(message) is not None else None)
-    tokens = re.findall(r'(?<![A-Za-z0-9])[A-Za-z][A-Za-z0-9]{2,7}(?![A-Za-z0-9])', message.upper())
-    warehouse = next((token for token in tokens if token in warehouse_codes), None)
-    postal = re.search(r'(?<![0-9])(\d{5})(?:-\d{4})?(?![0-9])', message)
-    cbm = re.search(r'(\d+(?:\.\d+)?)\s*(?:cbm|立方米|立方|方)', message, re.I)
-    boxes = re.search(r'(\d+)\s*(?:箱|件|cartons?|boxes?)', message, re.I)
-    origin = '华南' if re.search(r'华南|深圳|东莞', message) else ('义乌' if re.search(r'华东|义乌', message) else None)
-    if re.search(r'华南|深圳|东莞', message) and re.search(r'华东|义乌', message):
-        origin = None
-    services = [name for name in ('美森正班','美森加班','EXX','合德','普船') if name.lower() in message.lower()]
-    if '美森' in message and not any(name.startswith('美森') for name in services):
-        services += ['美森正班','美森加班']
-    kinds = []
-    if re.search(r'海派|快递|UPS|FEDEX', message, re.I):
-        kinds.append('parcel')
-    if re.search(r'海卡|海铁|全卡|卡派|卡车|铁路', message):
-        kinds.append('truck')
-    air_only = bool(re.search(r'空运|空派|\bair\b', message, re.I) and not re.search(r'海运|海派|海卡|海铁|\bsea\b', message, re.I))
-    zone = next((value for value in ('美西','美中','美东','东1区','东2区','中1区','中2区','西1区','西2区') if value in message), None)
-    each = re.search(r'每(?:箱|件)\s*(\d+(?:\.\d+)?)\s*(?:kg|公斤|千克)', message, re.I)
-    weight = str(parsed['weight']) if parsed['weight'] is not None else None
-    count = int(boxes.group(1)) if boxes else None
-    if each and count:
-        weight = str(Decimal(each.group(1))*count)
-    return {'country':country, 'weight':weight, 'dims':parsed['dims'], 'dim_unit':detect_dim_unit(message),
-        'cbm':cbm.group(1) if cbm else None, 'boxes':count, 'origin':origin, 'services':services or None,
-        'kinds':kinds or None, 'transport':parsed['channel'], 'air_only':True if air_only else None, 'warehouse':warehouse,
-        'postal':postal.group(1) if postal else None, 'zone':zone,
-        'tax':'excluded' if re.search(r'不包税|自税|不含税', message) else ('included' if '包税' in message else None)}
-
-
-def is_followup(message, intent):
-    if re.search(r'新(?:的)?一(?:票|批)|另外|另一|换个话题|理赔|赔偿|破损|丢失|退件|投诉|查单|轨迹|签收', message):
-        return False
-    text = message.strip().strip('，,。.!！?？ ')
-    if re.match(r'^(?:那(?:么)?|换成|改成|改为|如果|还是|同样)', text):
-        return True
-    if intent['warehouse'] and re.fullmatch(r'(?:目的仓(?:是)?|仓码(?:是)?)?\s*[A-Za-z0-9]+(?:仓)?(?:呢)?', text):
-        return True
-    if re.fullmatch(r'(?:邮编|zip|postcode)?\s*\d{5}(?:-\d{4})?(?:呢)?', text, re.I):
-        return True
-    if re.fullmatch(r'(?:义乌|华东|深圳|华南|美国|美西|美中|美东|东[12]区|西[12]区|中[12]区|不包税|包税)(?:交仓|仓|呢)?', text):
-        return True
-    if len(text) <= 45 and not (intent['country'] and intent['weight']) and (
-            intent['services'] or intent['kinds'] or intent['transport'] or intent['air_only'] or intent['weight'] or intent['dims'] or intent['cbm']):
-        return True
-    return bool(re.fullmatch(r'(?:价格|运费|费用|时效|多少钱)(?:呢|是多少|怎么样)?', text))
+from .quote_intent import US, QUOTE_WORDS, parse_intent, is_followup
 
 
 def broad_zone(postal):
@@ -74,6 +20,12 @@ def broad_zone(postal):
 
 
 def variants(intent, book):
+    if len(intent.get('warehouses') or [])>1:
+        return [variant for warehouse in intent['warehouses'] for variant in
+                variants({**intent,'warehouse':warehouse,'warehouses':None,'postal':None},book)]
+    if not intent['warehouse'] and len(intent.get('zones') or [])>1:
+        return [variant for zone in intent['zones'] for variant in
+                variants({**intent,'zone':zone,'zones':None},book)]
     warehouse = intent['warehouse']
     found = [r for r in book['warehouses'] if r['code'] == warehouse] if warehouse else []
     zoned = [r for r in found if r['zone']]
@@ -101,13 +53,29 @@ def quantity(intent, rate):
     if volume is None and intent['dims']:
         cm = [Decimal(str(value)) for value in dims_to_cm(intent['dims'], intent['dim_unit'])]
         volume = cm[0]*cm[1]*cm[2]/Decimal(1000000)*(intent['boxes'] or 1)
+    package_charge=Decimal(0)
+    if intent.get('packages'):
+        package_volume=Decimal(0)
+        all_dimensions=True
+        for package in intent['packages']:
+            dims=package.get('dims') or intent['dims']
+            cm=[Decimal(str(value)) for value in dims_to_cm(dims,package.get('dim_unit') or intent['dim_unit'])] if dims else None
+            box_volume=cm[0]*cm[1]*cm[2]/1000000 if cm else Decimal(0)
+            all_dimensions=all_dimensions and bool(cm)
+            package_volume+=box_volume*package['count']
+            piece=max(Decimal(package['weight']),box_volume*1000000/6000 if rate['kind']=='parcel' else box_volume*167)
+            package_charge+=max(piece,Decimal(12) if rate['kind']=='parcel' else Decimal(0))*package['count']
+        if all_dimensions and not intent['cbm']:volume=package_volume
     if rate['unit'] == 'cbm':
         if volume is None:
             return None
-        return max(volume, real/Decimal(363))
+        result=max(volume, real/Decimal(363))
+        if rate['service']=='洛杉矶普船海卡':
+            result=result.quantize(Decimal('.01'),rounding=ROUND_HALF_UP)
+        return result if result>0 else None
     volume_weight = ((volume or Decimal(0))*1000000/6000 if rate['kind']=='parcel'
                      else (volume or Decimal(0))*167)
-    charge = max(real, volume_weight)
+    charge = max(real, volume_weight,package_charge)
     if rate['kind'] == 'parcel':
         charge = max(charge, Decimal(12)*(intent['boxes'] or 1))
     return charge if real or volume else None
@@ -145,13 +113,39 @@ def number(value, places=2):
 
 
 def render_rates(intent, book, destinations, remote_fees):
+    from .quote_fees import charge_details
+    from .quote_language import translate_quote
+
     lines = []
-    if intent['weight']:
+    if intent.get('mode')=='time':
+        lines.append('美国线路参考时效：')
+    elif intent['weight']:
         lines.append(f"美国 {number(intent['weight'])}KG 基础运费：")
     else:
         lines.append('美国线路报价：')
+    if len(intent.get('warehouses') or [])>1:
+        lines.append('以下按各目的仓分别比较；实际分票请提供每个仓的重量。')
+    if intent.get('air_requested') and not intent.get('air_only'):
+        lines.append('当前资料没有美国空运费率，下面列出海运方案。')
     for destination, fees in zip(destinations, remote_fees):
         rates = match_rates(intent, book, destination)
+        if intent.get('mode') in ('cheapest','fastest') and rates:
+            if intent['mode']=='cheapest':
+                eligible=[r for r in rates if quantity(intent,r) is not None]
+                best={}
+                for rate in eligible:
+                    key=(destination['zone'] or rate['zone'],rate['unit'],rate['tax'])
+                    value=quantity(intent,rate)*Decimal(rate['price'])+charge_details(intent,rate,fees,book)['cny']
+                    best[key]=min(best.get(key,value),value)
+                rates=[r for r in eligible if quantity(intent,r)*Decimal(r['price'])+charge_details(intent,r,fees,book)['cny']==best[(destination['zone'] or r['zone'],r['unit'],r['tax'])]] or rates
+                lines.append('按相同区域、计费单位及税费方式比较的较低价方案：')
+            else:
+                def eta_key(rate):
+                    values=[Decimal(v) for v in re.findall(r'\d+(?:\.\d+)?',rate['eta'])]
+                    return tuple(values[:2]) if values else (Decimal('Infinity'),)
+                earliest=min(eta_key(r) for r in rates)
+                rates=[r for r in rates if eta_key(r)==earliest]
+                lines.append('按资料中的参考时效，较快方案如下；提取不等于送达或签收：')
         if not rates:
             lines.append(f"{destination['label']}：当前资料没有匹配的线路价格，提供目的仓码或邮编可继续查询。")
             continue
@@ -162,6 +156,11 @@ def render_rates(intent, book, destinations, remote_fees):
             key = (rate['service'], rate['origin'], rate['unit'], rate['tax'])
             grouped.setdefault(key, []).append(rate)
         for (service, origin, unit, tax), rows in grouped.items():
+            if intent.get('mode')=='time':
+                eta=rows[0]['eta'] or '当前资料未列明时效'
+                if rows[0]['kind']=='parcel' and '提取' not in eta:eta+='提取'
+                lines.append(f'- {service} · {origin}：{eta}。提取不等于送达或签收。')
+                continue
             parts = []
             for rate in rows:
                 amount = quantity(intent,rate)
@@ -170,11 +169,18 @@ def render_rates(intent, book, destinations, remote_fees):
                 rate_text += f"{number(price)}元/{'KG' if unit == 'kg' else 'CBM'}"
                 if amount is not None:
                     total = amount*price
-                    if fees and fees['fee'] is not None and rate['kind'] == 'parcel':
-                        total += amount*Decimal(fees['fee'])
+                    details=charge_details(intent,rate,fees,book)
+                    total+=details['cny']
                     rate_text += f"，{number(amount,3)}{'KG' if unit == 'kg' else 'CBM'} = {number(total)}元"
+                    if details['items']:rate_text+='（'+ '；'.join(details['items'])+'）'
+                    for note in details['notes']:
+                        if note not in lines:lines.append(note)
+                elif intent.get('cbm') and rate['unit']=='cbm':
+                    lines.append('计费体积四舍五入后不足0.01CBM，最低计费体积需人工确认，不能按零费用出价。')
                 parts.append(rate_text)
             eta = re.sub(r'\s*无时效赔偿', '', rows[0]['eta']).strip()
+            if rows[0]['kind']=='parcel' and eta and '提取' not in eta:eta+='提取'
+            elif rows[0]['kind']=='truck' and eta and '船开' not in eta:eta='开船后参考'+eta
             lines.append(f"- {service} · {origin} · {'包税' if tax=='included' else '不包税'}："+'；'.join(parts)
                          + (f'（{eta}）' if eta else ''))
         if fees:
@@ -184,8 +190,13 @@ def render_rates(intent, book, destinations, remote_fees):
                 lines.append(f"海派已计入偏远附加费 {number(fees['fee'])}元/KG。")
     if not any(intent.get(key) for key in ('warehouse','postal')):
         lines.append('发我目的仓码或邮编，可继续匹配到仓线路。')
-    if not intent['weight'] and not intent['cbm'] and not intent['dims']:
+    if intent.get('mode')=='time':
+        pass
+    elif not intent['weight'] and not intent['cbm'] and not intent['dims']:
         lines.append('货物多少公斤、几箱？')
     elif not intent['boxes'] or not intent['dims']:
         lines.append('请补充箱数、每箱重量和尺寸，继续核算计费重及超重超尺寸费用。')
-    return '\n'.join(lines)
+    if intent.get('mode')=='calculation':
+        lines.append('计算过程：各箱实重与体积重取大；海派每箱不足12KG按12KG计费，再按整票计费重选择重量档位，乘对应单价，并单列已知附加费。')
+    text='\n'.join(lines)
+    return translate_quote(text) if intent.get('english') else text

logistics_chat/quote_fees.py

@@ -0,0 +1,96 @@
+"""Amounts come from the active book; explicit customer-approved fee policies live here."""
+
+from decimal import Decimal
+import re
+
+from .pricing import dims_to_cm
+
+
+def document(book,required,service=None):
+    rows=[d for d in book['documents'] if (not service or d['sheet'] in (service,'海派'))
+          and all(term in d['content'] for term in required)]
+    return rows[0]['content'] if rows else ''
+
+
+def amount(text,pattern):
+    match=re.search(pattern,text,re.I)
+    return Decimal(match.group(1)) if match else None
+
+
+def material_fee(book):
+    text=document(book,('铁铝','附加费'))
+    return amount(text,r'铁铝制品[^\n]*?[￥¥]\s*(\d+(?:\.\d+)?)\s*/KG')
+
+
+def specimens(intent):
+    if intent.get('packages'):
+        return [{**p,'dims':p.get('dims') or intent.get('dims'),
+                 'dim_unit':p.get('dim_unit') if p.get('dims') else intent.get('dim_unit','cm')} for p in intent['packages']]
+    if intent.get('boxes')==1 and intent.get('weight'):
+        return [{'count':1,'weight':intent['weight'],'dims':intent.get('dims'),'dim_unit':intent.get('dim_unit','cm')}]
+    return []
+
+
+def limit_fees(intent,book):
+    """Maximum per-piece limit fee, not the sum of overlapping weight/size charges.
+
+    The malformed 0<length<274 rule does not create a new threshold. Only two
+    independently explicit large-piece conditions can establish that tier.
+    """
+    normal=document(book,('正常货物',))
+    cleaned=re.sub(r'\s+','',normal).replace('＜','<').upper()
+    limits=[amount(cleaned,p) for p in (r'0KG<单件重量<(\d+)KG',r'0CM<最长单边长度<(\d+)CM',
+        r'0CM<第二边<(\d+)CM',r'最长边<(\d+)CM')]
+    normal_fee=amount(document(book,('超重收',)),r'超重收\s*[+＋]?\s*(\d+(?:\.\d+)?)')
+    size_text=document(book,('普通超尺寸',))
+    size_fee=amount(size_text,r'加收\s*(\d+(?:\.\d+)?)\s*RMB/件')
+    large_text=document(book,('大尺寸货物','任意2个'))
+    large_fee=amount(large_text,r'加收\s*(\d+(?:\.\d+)?)\s*RMB/件')
+    huge=document(book,('超大件货物',))
+    huge_fee=amount(huge,r'加收\s*USD\s*(\d+(?:\.\d+)?)')
+    result={'cny':Decimal(0),'items':[],'notes':[]}
+    if not all(limits) or normal_fee is None:return result
+    max_weight,max_length,max_second,max_girth=limits
+    for piece in specimens(intent):
+        weight=Decimal(piece['weight']);count=piece['count']
+        dims=sorted([Decimal(str(x)) for x in dims_to_cm(piece['dims'],piece['dim_unit'])],reverse=True) if piece['dims'] else []
+        length,second,girth=(dims[0],dims[1],dims[0]+2*(dims[1]+dims[2])) if dims else (None,None,None)
+        if weight>68 or (dims and (length>270 or girth>419)):
+            result['notes'].append('该件可能超出承运尺寸或重量，需人工确认是否接收。'+(f'原表超大件若接收的附加费为{huge_fee:g}USD/件。' if huge_fee else ''))
+            continue
+        candidates=[]
+        if weight>max_weight:candidates.append(normal_fee)
+        if dims and (length>max_length or second>max_second or girth>max_girth) and size_fee is not None:candidates.append(size_fee)
+        if large_fee is not None and max_weight<weight<68 and dims and 330<girth<419:
+            candidates.append(large_fee)
+        elif dims and (length>=243 or girth>=330):
+            result['notes'].append('该件接近大尺寸档，原表有一处长度条件不清，适用档位需人工确认。')
+        if candidates:
+            fee=max(candidates)*count
+            result['cny']+=fee
+            result['items'].append(f'超重/超尺寸按最高项{max(candidates):g}元/件×{count}件={fee:g}元')
+    return result
+
+
+def charge_details(intent,rate,remote,book):
+    from .quote_engine import quantity
+
+    result={'cny':Decimal(0),'items':[],'notes':[]}
+    charged=quantity(intent,rate)
+    if charged is None:return result
+    if rate['kind']=='parcel' and remote:
+        if remote['fee'] is not None:
+            fee=charged*Decimal(remote['fee']);result['cny']+=fee
+            result['items'].append(f'偏远费{remote["fee"]}元/KG×{charged:g}KG={fee:g}元')
+        else:result['notes'].append('遥远地址的附加费需单独确认，当前金额未包含该项。')
+    if rate['unit']=='kg' and intent.get('material')=='metal':
+        per_kg=material_fee(book)
+        if per_kg is not None:
+            fee=charged*per_kg;result['cny']+=fee
+            result['items'].append(f'铁铝附加费{per_kg:g}元/KG×{charged:g}KG={fee:g}元')
+    if rate['kind']=='parcel':
+        limits=limit_fees(intent,book)
+        result['cny']+=limits['cny'];result['items']+=limits['items'];result['notes']+=limits['notes']
+    if intent.get('address_type')=='non_fba':
+        result['notes'].append('非亚马逊地址还需核对住宅/商业派送附加费，原表此项需单独询价。')
+    return result

logistics_chat/quote_intent.py

@@ -0,0 +1,151 @@
+"""Normalize customer wording into bounded quote fields without model inference."""
+
+from decimal import Decimal
+import re
+
+from .pricing import parse_shipping_intent, detect_dim_unit, shipping_region
+
+US = re.compile(r'美国|美西|美中|美东|洛杉矶|纽约|芝加哥|休斯顿|萨凡纳|'
+    r'(?<![A-Za-z])(?:USA|(?-i:US)|United States|America)(?=$|[^A-Za-z]|FBA(?![A-Za-z]))|'
+    r'(?:发(?:往|到)?|寄(?:往|到)?|运往|运到|到|往|\bto\s+)\s*us(?=$|[^A-Za-z]|FBA(?![A-Za-z]))',re.I)
+QUOTE_WORDS = re.compile(r'报价|价格|运费|费用|多少钱|计费|包税|海运|空运|海派|海卡|海铁|美森|合德|普船|附加|保险|代发|申报|偏远|超重|超尺寸|币种|\bEXX\b|\b(?:quote|price|cost|freight)\b',re.I)
+WEIGHT = re.compile(r'(?<![\d.])(-?\d+(?:\.\d+)?)\s*(kilograms?|kgs?|公斤|千克|grams?|克|g|tons?|吨|lbs?|磅)(?![A-Za-z])',re.I)
+TOPIC_BOUNDARY = re.compile(r'新(?:的)?一(?:票|批)|另外|另一|换个话题|理赔|赔偿|破损|丢失|退件|投诉|查单|轨迹|签收')
+
+
+def chinese_number(text):
+    digits={c:i for i,c in enumerate('零一二三四五六七八九')};digits.update({'两':2,'〇':0})
+    if all(c in digits for c in text):return ''.join(str(digits[c]) for c in text)
+    if '点' in text:
+        left,right=text.split('点',1)
+        return str(chinese_number(left or '零'))+'.'+''.join(str(digits[c]) for c in right)
+    total=section=number=0
+    for character in text:
+        if character in digits:
+            number=digits[character]
+        elif character=='万':
+            total+=(section+number)*10000;section=number=0
+        else:
+            section+=(number or 1)*{'十':10,'百':100,'千':1000}[character];number=0
+    return str(total+section+number)
+
+
+def normalize(text):
+    result=re.sub(r'([零〇一二两三四五六七八九十百千万点]+)(?=\s*(?:公斤|千克|克|吨|磅|箱|件|立方米|立方|方|kg|cbm))',
+        lambda m:chinese_number(m.group(1)),text,flags=re.I)
+    return re.sub(r'负(?=\d)','-',result)
+
+
+def kg(value,unit):
+    value=Decimal(value)
+    unit=unit.lower()
+    if unit in ('克','g','gram','grams'):return value/1000
+    if unit in ('吨','ton','tons'):return value*1000
+    if unit in ('磅','lb','lbs'):return (value*Decimal('0.4536')).quantize(Decimal('.01'))
+    return value
+
+
+def request_mode(text):
+    # Business topics outrank generic verbs such as “怎么算”.
+    if re.search(r'保险|保价|投保|insured|insurance',text,re.I):return 'insurance'
+    if re.search(r'纯电池|带电|内置电池|液体|粉末|食品|医疗用品|仿牌',text):return 'acceptance'
+    if re.search(r'最便宜|便宜的|最省钱|最划算|最低价|cheapest|least expensive',text,re.I):return 'cheapest'
+    if re.search(r'最快|快的|fastest',text,re.I):return 'fastest'
+    if re.search(r'一件代发|散箱入库|整柜卸货|卸货费|仓租|仓储|贴标费',text):return 'fulfillment'
+    if re.search(r'FDA|申报费|报关|续页|品名',text,re.I):return 'customs'
+    if re.search(r'附加费|还.*(?:费|加钱)|(?:额外|其他|其它).*(?:费用|收费)|包含.*费|包税.*(?:包含|包括)|超重费|超尺寸|住宅|私人|商业地址',text):return 'fees'
+    if re.search(r'电池|带电|液体|粉末|食品|医疗|能(?:不能|发|走)|可以.*(?:发|走)',text):return 'acceptance'
+    if re.search(r'人民币|美元|美金|币种|currency|\b(?:RMB|CNY|USD)\b',text,re.I) and not WEIGHT.search(text):return 'currency'
+    if re.search(r'怎么(?:算|计算)|计算(?:过程|出来)|怎么算出来|calculation',text,re.I):return 'calculation'
+    if re.search(r'时效|多久|几天',text) and not WEIGHT.search(text):return 'time'
+    return 'quote'
+
+
+def parse_intent(message,warehouse_codes):
+    text=normalize(message)
+    parsed=parse_shipping_intent(text)
+    country='US' if US.search(text) else ('other' if shipping_region(text) is not None else None)
+    candidates=re.findall(r'(?<![A-Za-z0-9])[A-Za-z][A-Za-z0-9]{2,7}(?![A-Za-z0-9])',text.upper())
+    warehouses=list(dict.fromkeys(t for t in candidates if t in warehouse_codes))
+    unknown=[t for t in candidates if t not in warehouse_codes and re.fullmatch(r'[A-Z]{2,4}[0-9][A-Z0-9]{0,2}',t)
+             and not t.startswith(('USD','RMB','CNY'))]
+    errors=[]
+    weights=[m for m in WEIGHT.finditer(text) if not text[:m.start()].rstrip().endswith(('x','X','×','*'))]
+    weight=str(kg(*weights[0].groups())) if weights else None
+    boxes=re.search(r'(\d+)\s*(?:箱|件|cartons?|boxes?)',text,re.I)
+    count=int(boxes.group(1)) if boxes else None
+    packages=[]
+    package_re=re.compile(r'(第)?(\d+)\s*(?:箱|件)\s*(?:[，,]?\s*每(?:箱|件))?\s*'+WEIGHT.pattern.replace(r'(?<![\d.])',''),re.I)
+    matches=list(package_re.finditer(text))
+    for index,match in enumerate(matches):
+        ordinal,n,value,unit=match.groups()
+        segment=text[match.end():matches[index+1].start() if index+1<len(matches) else len(text)]
+        dims=parse_shipping_intent(segment)['dims']
+        packages.append({'count':1 if ordinal else int(n),'weight':str(kg(value,unit)),
+                         'dims':dims,'dim_unit':detect_dim_unit(segment)})
+    each=re.search(r'每(?:箱|件)\s*'+WEIGHT.pattern.replace(r'(?<![\d.])',''),text,re.I)
+    if each and count and not packages:
+        packages=[{'count':count,'weight':str(kg(*each.groups())),'dims':parsed['dims'],'dim_unit':detect_dim_unit(text)}]
+    if packages:
+        package_count=sum(p['count'] for p in packages)
+        aggregate_count=boxes and not any(m.start()<=boxes.start()<m.end() for m in matches)
+        if count and aggregate_count and count!=package_count:
+            errors.append('箱数与分箱明细不一致，请确认总箱数及每箱重量。')
+        count=package_count
+        weight=str(sum(Decimal(p['weight'])*p['count'] for p in packages))
+        total=re.search(r'(?:总重|合计重量|一共重)\s*'+WEIGHT.pattern.replace(r'(?<![\d.])',''),text,re.I)
+        if total and kg(*total.groups())!=Decimal(weight):errors.append('总重与分箱重量合计不一致，请确认。')
+        # Per-carton dimensions must not spill onto another carton without dimensions.
+        if len(packages)>1:parsed['dims']=None
+    elif len(weights)>1:
+        errors.append('请明确总重，或分别提供每箱重量，避免把不同重量混在一起。')
+    if any(kg(*w.groups())<=0 for w in weights):errors.append('重量必须大于 0，请确认有效重量。')
+    labeled=re.search(r'(?:邮编|zip(?:\s*code)?|post\s*code)\s*[:：为是]?\s*([0-9-]+)',text,re.I)
+    postal=None
+    if labeled:
+        if re.fullmatch(r'[0-9]{5}(?:-[0-9]{4})?',labeled.group(1)):postal=labeled.group(1)[:5]
+        else:errors.append('美国邮编请提供5位数字，可附加4位扩展码；当前邮编格式不正确。')
+    else:
+        remaining=WEIGHT.sub(' ',text)
+        remaining=re.sub(r'\d+(?:\.\d+)?\s*[*xX×]\s*\d+(?:\.\d+)?\s*[*xX×]\s*\d+(?:\.\d+)?',' ',remaining)
+        match=re.search(r'(?:^|美国\s*|[，,\s])([0-9]{5})(?:-[0-9]{4})?(?=$|[，,\s])',remaining)
+        if match:postal=match.group(1)
+    cbm=re.search(r'(-?\d+(?:\.\d+)?)\s*(?:cbm|立方米|立方|方)',text,re.I)
+    origin='华南' if re.search(r'华南|深圳|东莞|south china|shenzhen',text,re.I) else ('义乌' if re.search(r'华东|义乌|yiwu',text,re.I) else None)
+    if re.search(r'华南|深圳|东莞',text) and re.search(r'华东|义乌',text):origin=None
+    services=[n for n in ('美森正班','美森加班','EXX','合德','普船') if n.lower() in text.lower()]
+    if '美森' in text and not any(n.startswith('美森') for n in services):services+=['美森正班','美森加班']
+    kinds=[]
+    if re.search(r'海派|快递|UPS|FEDEX',text,re.I):kinds.append('parcel')
+    if re.search(r'海卡|海铁|全卡|卡派|卡车|铁路',text):kinds.append('truck')
+    zones=[z for z in ('美西','美中','美东','东1区','东2区','中1区','中2区','西1区','西2区') if z in text]
+    if not zones and '洛杉矶' in text:zones=['美西']
+    if not zones and re.search(r'纽约|萨凡纳',text):zones=['美东']
+    air=bool(re.search(r'空运|空派|\bair\b',text,re.I))
+    sea=bool(re.search(r'海运|海派|海卡|海铁|\bsea\b',text,re.I))
+    english=not re.search(r'[\u4e00-\u9fff]',message) and bool(re.search(r'[A-Za-z]{3,}\s+[A-Za-z]',message))
+    return {'country':country,'weight':weight,'dims':parsed['dims'],'dim_unit':detect_dim_unit(text),
+        'cbm':cbm.group(1) if cbm else None,'boxes':count,'packages':packages or None,'origin':origin,
+        'services':services or None,'kinds':kinds or None,'transport':parsed['channel'],
+        'air_only':True if air and not sea else None,'air_requested':True if air else None,
+        'warehouse':warehouses[0] if warehouses else None,'warehouses':warehouses or None,
+        'unknown_warehouses':unknown or None,'postal':postal,'zone':zones[0] if zones else None,'zones':zones or None,
+        'tax':'excluded' if re.search(r'不包税|自税|不含税|tax excluded',text,re.I) else ('included' if re.search(r'包税|tax included',text,re.I) else None),
+        'errors':errors,'mode':request_mode(text),'english':True if english else (False if re.search(r'[\u4e00-\u9fff]',message) else None),
+        'material':('ordinary' if re.search(r'普通货|普货|塑料|木制|非铁铝',text) else
+                    ('metal' if re.search(r'铁制|钢制|铝制|铁铝|不锈钢',text) else None)),
+        'address_type':('non_fba' if re.search(r'私人|住宅|商业地址|非亚马逊',text) else ('fba' if warehouses else None)),
+        'text':text}
+
+
+def is_followup(message,intent):
+    if TOPIC_BOUNDARY.search(message):return False
+    text=message.strip().strip('，,。.!！?？ ')
+    if intent.get('errors') and re.search(r'邮编|重量|箱|kg',message,re.I):return True
+    if re.match(r'^(?:那(?:么)?|换成|改成|改为|如果|还是|同样|目的仓改|仓码改|只要|货物是|这个价格|这个费用)',text):return True
+    if intent.get('warehouse') or intent.get('unknown_warehouses'):
+        return not (intent['country'] and intent['weight'])
+    if intent.get('mode')!='quote':return not (intent['country'] and intent['weight'])
+    if re.fullmatch(r'(?:邮编|zip|postcode)?\s*\d{5}(?:-\d{4})?(?:呢)?',text,re.I):return True
+    if re.fullmatch(r'(?:义乌|华东|深圳|华南|美国|美西|美中|美东|东[12]区|西[12]区|中[12]区|不包税|包税)(?:交仓|仓)?(?:呢)?',text):return True
+    return bool(len(text)<=60 and not (intent['country'] and intent['weight']) and any(intent.get(k) is not None for k in ('services','kinds','transport','weight','dims','cbm','tax','origin')))

logistics_chat/quote_language.py

@@ -0,0 +1,33 @@
+"""English rendering for deterministic quotes; numerical facts remain unchanged."""
+
+import re
+
+
+def translate_quote(text):
+    replacements=(
+        ('美森正班海派','Matson regular sea parcel'),('美森加班海派','Matson extra sea parcel'),
+        ('美森正班海卡','Matson regular sea truck'),('美森加班海卡','Matson extra sea truck'),
+        ('纽约EXX海铁','New York EXX sea rail'),('洛杉矶普船全卡','Los Angeles regular sea truck direct'),
+        ('洛杉矶普船海卡','Los Angeles regular sea truck'),('芝加哥普船海铁','Chicago regular sea rail'),
+        ('休斯顿普船海卡','Houston regular sea truck'),('纽约普船海卡','New York regular sea truck'),
+        ('萨凡纳普船海卡','Savannah regular sea truck'),('EXX海卡','EXX sea truck'),('合德海卡','Hede sea truck'),
+        ('合德海派','Hede sea parcel'),('普船海派','Regular sea parcel'),
+        ('请补充箱数、每箱重量和尺寸，继续核算计费重及超重超尺寸费用。','Please provide the carton count, weight and dimensions of each carton to calculate chargeable weight and size surcharges.'),
+        ('发我目的仓码或邮编，可继续匹配到仓线路。','Send the destination warehouse code or ZIP code to match the route.'),
+        ('货物多少公斤、几箱？','What are the total weight and carton count?'),
+        ('当前资料没有美国空运费率，下面列出海运方案。','The current rate sheet has no US air rates. Sea options are listed below.'),
+        ('以下按各目的仓分别比较；实际分票请提供每个仓的重量。','Each destination is compared separately; provide the weight assigned to each shipment.'),
+        ('按相同区域、计费单位及税费方式比较的较低价方案：','Lower-priced options within the same region, billing unit and tax basis:'),
+        ('按资料中的参考时效，较快方案如下；提取不等于送达或签收：','Faster reference options follow. Pickup timing is not a delivery or receipt commitment:'),
+        ('该邮编属于遥远地址，派送附加费需单独确认。','This ZIP code is extremely remote; the delivery surcharge requires confirmation.'),
+        ('海派已计入偏远附加费','Sea parcel totals include the remote surcharge of '),
+        ('当前资料没有匹配的线路价格，提供目的仓码或邮编可继续查询。','No matching route rate was found. Please provide the destination warehouse or ZIP code.'),
+        ('美国线路参考时效','US reference transit times'),('美国线路报价','US route rates'),('基础运费','base freight'),('美国','US'),('义乌','Yiwu'),('华南','South China'),
+        ('不包税','tax excluded'),('包税','tax included'),('美西','US West'),('美中','US Central'),('美东','US East'),
+        ('开船后参考','Reference timing after sailing: '),('船开后','After sailing: '),('开船后','After sailing: '),
+        ('若干','several '),
+        ('提取',' until pickup'),('天左右',' days approximately'),('天',' days'),('元/KG',' CNY/kg'),('元/CBM',' CNY/CBM'),
+        ('元',' CNY'),('：',': '),('；','; '),('，',', '),('（',' ('),('）',')'))
+    for source,target in replacements:text=text.replace(source,target)
+    text=re.sub(r'([东中西])(\d)区',lambda m:{'东':'East','中':'Central','西':'West'}[m[1]]+' zone '+m[2],text)
+    return text

logistics_chat/quote_service.py

@@ -10,49 +10,45 @@ from .quote_engine import US, QUOTE_WORDS, parse_intent, is_followup, variants,
 
 
 def intent_with_context(message, conv_id, book):
+    from copy import deepcopy
     codes = {row['code'] for row in book['warehouses']}
     codes.update(value.upper() for rate in book['rates'] for value in rate['destinations'])
     intent = parse_intent(message,codes)
-    replaced_destination = ({'postal','zone'} if intent['warehouse'] else
-                            ({'warehouse','zone'} if intent['postal'] else
-                             ({'warehouse','postal'} if intent['zone'] else set())))
-    if intent['transport'] or intent['kinds'] or intent['services']:
-        replaced_destination.add('air_only')
-    destination_selected = any(intent.get(key) for key in ('warehouse','postal','zone'))
-    if intent['air_only'] or intent['tax'] == 'excluded':
-        replaced_destination.add('kinds')
+    def destination_reset(value):
+        if value.get('warehouse') or value.get('unknown_warehouses'):return {'postal','zone','zones'}
+        if value.get('postal'):return {'warehouse','warehouses','unknown_warehouses','zone','zones'}
+        if value.get('zone'):return {'warehouse','warehouses','unknown_warehouses','postal'}
+        return set()
+    excluded=destination_reset(intent)
+    selected_destination=bool(excluded)
+    if selected_destination and not intent.get('unknown_warehouses'):excluded.add('unknown_warehouses')
+    if intent['transport'] or intent['kinds'] or intent['services']:excluded.update(('air_only','air_requested'))
+    if intent['air_only'] or intent['tax']=='excluded':excluded.add('kinds')
+    if intent.get('weight') is not None and not intent.get('packages'):excluded.add('packages')
+    explicit_dims=bool(intent['dims'])
     if conv_id and is_followup(message,intent):
-        connection = connect()
+        connection=connect()
         try:
-            recent = connection.execute("SELECT content FROM messages WHERE conv_id=? AND role='user' ORDER BY id DESC LIMIT 8", (conv_id,)).fetchall()
-        finally:
-            connection.close()
+            recent=connection.execute("SELECT content FROM messages WHERE conv_id=? AND role='user' ORDER BY id DESC LIMIT 10",(conv_id,)).fetchall()
+        finally:connection.close()
         for (previous,) in recent:
-            if re.search(r'理赔|赔偿|破损|丢失|退件|投诉|查单|轨迹|签收', previous):
-                break
-            earlier = parse_intent(previous,codes)
+            if re.search(r'理赔|赔偿|破损|丢失|退件|投诉|查单|轨迹|签收',previous):break
+            earlier=parse_intent(previous,codes)
+            if earlier['country']=='other':break
             if not (QUOTE_WORDS.search(previous) or US.search(previous) or is_followup(previous,earlier) or
-                    any(earlier.get(key) for key in ('weight','dims','cbm','warehouse','postal'))):
-                break
-            if earlier['country'] == 'other':
-                break
-            if not destination_selected:
-                if earlier['warehouse']:
-                    replaced_destination.update(('postal','zone'))
-                    destination_selected = True
-                elif earlier['postal']:
-                    replaced_destination.update(('warehouse','zone'))
-                    destination_selected = True
-                elif earlier['zone']:
-                    replaced_destination.update(('warehouse','postal'))
-                    destination_selected = True
-            for key, value in earlier.items():
-                if intent.get(key) is None and key not in replaced_destination:
-                    intent[key] = value
-            if not is_followup(previous, earlier):
-                break
-    if intent['warehouse'] and intent['country'] is None:
-        intent['country'] = 'US'
+                    any(earlier.get(key) for key in ('weight','dims','cbm','warehouse','postal'))):break
+            if not selected_destination and destination_reset(earlier):
+                excluded.update(destination_reset(earlier));selected_destination=True
+            if intent['dims'] is None and earlier['dims']:
+                intent['dims']=earlier['dims'];intent['dim_unit']=earlier['dim_unit']
+            for key,value in earlier.items():
+                if key in ('mode','text','errors','dim_unit','dims'):continue
+                if intent.get(key) is None and key not in excluded:intent[key]=deepcopy(value)
+            if not is_followup(previous,earlier):break
+    if explicit_dims and intent.get('packages'):
+        for piece in intent['packages']:
+            piece['dims']=intent['dims'];piece['dim_unit']=intent['dim_unit']
+    if (intent['warehouse'] or intent.get('unknown_warehouses')) and intent['country'] is None:intent['country']='US'
     return intent
 
 
@@ -70,6 +66,10 @@ def answer_quote(message, conv_id):
         intent = intent_with_context(message, conv_id, book)
         if intent['country'] != 'US':
             return None
+        if intent.get('errors'):
+            return {'t':'\n'.join(intent['errors'])}
+        if intent.get('unknown_warehouses'):
+            return {'t':'未找到目的仓码 '+ '、'.join(intent['unknown_warehouses'])+'，请核对仓码，或提供5位美国邮编继续查询。'}
         if not (QUOTE_WORDS.search(message) or is_followup(message,intent) or
                 any(intent.get(key) for key in ('weight','dims','cbm','warehouse','postal'))):
             return None
@@ -78,8 +78,13 @@ def answer_quote(message, conv_id):
                 return {'t':'请提供大于 0 的有效重量或体积。'}
         if intent['boxes'] is not None and not 0 < intent['boxes'] <= 10000:
             return {'t':'请提供有效的货物箱数。'}
-        if intent['dims'] and any(not 0 < value <= 100000 for value in intent['dims']):
+        dimensions=[intent['dims']] if intent['dims'] else []
+        dimensions += [piece['dims'] for piece in intent.get('packages') or [] if piece.get('dims')]
+        if any(not 0 < value <= 100000 for dims in dimensions for value in dims):
             return {'t':'请提供大于 0 的有效长宽高。'}
+        from .quote_answers import answer_business
+        business=answer_business(intent,book)
+        if business is not None:return {'t':business}
         if intent['air_only']:
             return {'t':'当前美国报价资料包含美森、EXX、合德及普船的海卡、海铁和海派。发我目的仓码或邮编、重量，可以列出这些线路的价格；空运费率当前资料没有列出。'}
         destinations = variants(intent,book)

static/js/chat.js

@@ -1227,13 +1227,14 @@ window.showHuman = async function(){
         if(humanRequestToken !== token || token.version !== conversationVersion) return;
         const data = await humanRequest('/api/visitor/human/request', {conv_id:cid});
         if(humanRequestToken !== token || token.version !== conversationVersion) return;
-        if(data.closed){ await leaveOfflineMessage(); return; }
+        if(data.closed) return await leaveOfflineMessage();
         if(!data.ok || !data.session_id) throw new Error('Human session failed');
         window.humanSid = data.session_id;
         humanConvId = cid;
         humanStatus = 'waiting';
         addMsg(t('humanWaiting'), false);
         startHumanPoll();
+        return true;
     }catch(error){
         if(humanRequestToken === token && token.version === conversationVersion) setComposerStatus(t('humanConnectFailed'), true);
     }finally{
@@ -1298,7 +1299,7 @@ async function leaveOfflineMessage(){
     try{
         const data = await humanRequest('/api/ticket', {content:message, phone:''});
         if(!data.ok) throw new Error('Ticket failed');
-        if(version === conversationVersion) addMsg(t('offlineSaved'), false);
+        if(version === conversationVersion){ addMsg(t('offlineSaved'), false); return true; }
     }catch(error){
         if(version !== conversationVersion) return;
         if(!inputDom.value){ inputDom.value = message; autoGrow(); }
@@ -1653,6 +1654,15 @@ async function doSend(retryText, showQuestion){
     if(window.humanSid) stopHumanMode();
 
     if(sendPreparing || (window.__busy && !retryText)) return;  // 防连点
+    const humanCommand = sendWord.replace(/[\s，,。.!！?？]/g, '');
+    if(!imgUrl && /^(?:(?:请|麻烦)?(?:帮我)?)?(?:转(?:接|到)?|联系|找)(?:一下|个)?人工(?:客服)?(?:吧|谢谢)?$/.test(humanCommand)){
+        const version = conversationVersion;
+        const connected = await window.showHuman();
+        if(connected && version === conversationVersion && !isRetry && inputDom.value === draft){
+            inputDom.value = ''; autoGrow(); flushDraft();
+        }
+        return !!connected;
+    }
     if(cancelActive){ cancelActive(); cancelActive = null; }
 
     sendPreparing = true;

tests/frontend/chat.test.cjs

@@ -1328,3 +1328,38 @@ test('an unavailable image gets one readable replacement instead of a broken ima
     app.element('chatDom').listeners.error({target:image});
     assert.equal(shown,first);
 });
+
+test('an explicit typed human request opens one real queue without an AI question', async () => {
+    const app=await customerPage({human:false});
+    await app.context.window.fillInput('请帮我转人工客服');
+    assert.equal(app.calls.filter(c=>c.url==='/api/visitor/human/request').length,1);
+    assert.equal(app.calls.filter(c=>c.url==='/stream_chat').length,0);
+    assert.equal(app.context.window.humanSid,7);
+    assert.equal(app.element('input-text').value,'');
+});
+
+test('a failed typed transfer keeps the command and an information question uses AI', async () => {
+    const app=await customerPage({human:false});
+    app.hooks['/api/visitor/human/request']=()=>response({ok:false},503);
+    await app.context.window.fillInput('帮我转人工客服');
+    assert.equal(app.element('input-text').value,'帮我转人工客服');
+    assert.equal(app.context.window.humanSid,0);
+    await app.context.window.fillInput('不需要人工客服，人工几点上班？');
+    assert.equal(app.calls.filter(c=>c.url==='/api/visitor/human/request').length,1);
+    assert.equal(app.calls.filter(c=>c.url==='/stream_chat').length,1);
+});
+
+test('a typed transfer preserves a newer draft while connecting and cancelled offline input', async () => {
+    const app=await customerPage({human:false});
+    let resolve;
+    app.hooks['/api/visitor/human/request']=()=>new Promise(done=>{resolve=done;});
+    const sending=app.context.window.fillInput('帮我转人工客服');
+    await flush();
+    app.element('input-text').value='新输入的订单问题';
+    resolve(response({ok:true,session_id:8}));await sending;
+    assert.equal(app.element('input-text').value,'新输入的订单问题');
+    const closed=await customerPage({human:false,serviceClosed:true});
+    await closed.context.window.fillInput('帮我转人工客服');
+    assert.equal(closed.element('input-text').value,'帮我转人工客服');
+    assert.equal(closed.calls.filter(c=>c.url==='/api/ticket').length,0);
+});

tests/test_order_counts.py

@@ -46,6 +46,27 @@ class OrderCountTests(unittest.TestCase):
                     self.assertTrue(self.events(question)[0]['login_required'])
             count.assert_not_called(); model.assert_not_called()
 
+    def test_order_list_is_login_scoped_status_filtered_and_protects_history(self):
+        self.assertTrue(self.events('列出我的全部订单')[0]['login_required'])
+        self.login()
+        cid=self.a.post('/api/new_chat').json['id']
+        text=self.events('列出我的全部订单',cid)[0]['t']
+        self.assertIn('COUNT20260001',text);self.assertIn('COUNT20260002',text)
+        self.assertNotIn('INB20260099',text);self.assertNotIn('COUNT20260003',text)
+        text=self.events('列出已完成的订单')[0]['t']
+        self.assertIn('COUNT20260002',text);self.assertNotIn('COUNT20260001',text)
+        self.assertIn('暂不支持按这个条件',self.events('列出今天的订单')[0]['t'])
+        self.a.post('/api/customer/logout')
+        self.assertEqual(self.a.get('/api/get_messages',query_string={'conv_id':cid}).json,[])
+
+    def test_address_change_does_not_claim_a_mutation_or_bypass_login(self):
+        message='帮我把INB20260001收件地址改成新地址'
+        self.assertTrue(self.events(message)[0]['login_required'])
+        self.login()
+        events=self.events(message)
+        self.assertIn('尚未修改订单',events[0]['t'])
+        self.assertFalse(any('card' in e for e in events))
+
     def test_logged_in_counts_accept_common_wording_and_refresh_after_data_changes(self):
         self.login()
         cid = self.a.post('/api/new_chat').json['id']

tests/test_order_data.py

@@ -100,10 +100,11 @@ class OrderDataTests(unittest.TestCase):
         self.assertEqual(events[-1], {'d':1})
         model.assert_not_called()
 
-    def test_unimplemented_bulk_queries_ask_for_identifier_instead_of_inventing_records(self):
+    def test_bulk_query_lists_only_existing_orders_without_model(self):
         with patch('logistics_chat.ai_client.post_completion') as model:
             events = self.events('列出所有订单')
-        self.assertIn('请提供入仓码', events[0]['t'])
+        self.assertIn(self.record['inbound_code'], events[0]['t'])
+        self.assertIn(self.record['order_no'], events[0]['t'])
         model.assert_not_called()
 
     def test_server_tenant_scope_and_ambiguous_identifiers(self):

tests/test_quote_business.py

@@ -0,0 +1,133 @@
+"""Customer-language regressions use synthetic amounts, never private tariffs."""
+
+from decimal import Decimal
+from pathlib import Path
+import tempfile
+import unittest
+from unittest.mock import patch
+
+from logistics_chat import create_app, db
+from logistics_chat.quote_data import import_snapshot
+from logistics_chat.quote_engine import quantity, parse_intent
+from test_quotes import fixture_snapshot, frames
+
+
+class QuoteBusinessTests(unittest.TestCase):
+    def setUp(self):
+        folder=tempfile.TemporaryDirectory();self.addCleanup(folder.cleanup)
+        root=Path(folder.name)
+        self.app=create_app({'TESTING':True,'DATABASE':root/'test.db','UPLOAD_DIR':root/'uploads',
+            'BACKUP_DIR':root/'backups','LOG_DIR':root/'logs','DEEPSEEK_API_KEY':'','RATE_LIMIT_PER_MIN':1000})
+        self.client=self.app.test_client()
+        self.client.post('/api/visitor/session',json={'key':'1'*64})
+        book=fixture_snapshot()
+        documents=[
+            '铁铝制品另外加附加费￥5/KG',
+            '正常货物 A.0KG<单件重量<22KG B.0CM<最长单边长度<120CM C.0CM<第二边<75CM D.最长边＜260CM',
+            '单件不能超22KG 超重收+70/件',
+            '普通超尺寸加收90RMB/件',
+            '大尺寸货物，任意2个条件，加收400RMB/件：22KG<单件重量<68KG；0<最长边<274CM；330CM<周长+单边长<419CM',
+            '超大件货物，加收USD900/件',
+            '保险费：保额的百分之0.25，min 13USD，投保金额是货值乘以1.2。',
+            '海外进口清关，超过5个品名，续页加收USD7元RMB/个',
+            '一般贸易出口报关费：RMB60/票',
+            '偏远地址加收4元/kg；超偏远地址加收6元/kg',
+            '禁止运输的货物：纯电池、液体、食品',
+        ]
+        book['documents']=[{'sheet':'海派','cell':f'A{i+1}','text':text} for i,text in enumerate(documents)]
+        book['documents'].append({'sheet':'美森加班海卡','cell':'A1','text':'不可接一般贸易'})
+        with self.app.app_context():
+            c=db.connect();import_snapshot(c,book,activate=True);c.commit();c.close()
+
+    def ask(self,text,cid=None):
+        with patch('logistics_chat.ai_client.post_completion') as model:
+            events=frames(self.client.post('/stream_chat',json={'msg':text,'conv_id':cid}))
+            model.assert_not_called()
+        self.assertEqual(events[-1],{'d':1},events)
+        return events[0]['t']
+
+    def test_different_cartons_use_individual_minimums_and_dimensions(self):
+        text=self.ask('美国美西，1箱10KG，1箱20KG，义乌普船海派')
+        self.assertIn('32KG = 64元',text)
+        text=self.ask('美国美西，2箱，1箱10KG，60x50x40cm，1箱20KG，40x30x20cm，义乌普船海派')
+        self.assertIn('40KG = 80元',text)
+        text=self.ask('美国美西，2箱，1箱10KG，60x50x40cm，1箱20KG，义乌普船海派')
+        self.assertIn('40KG = 80元',text)
+        self.assertIn('箱数与分箱明细不一致',self.ask('美国3箱，1箱10KG，1箱20KG海派'))
+
+    def test_weight_units_chinese_followup_and_invalid_postal(self):
+        cid=self.client.post('/api/new_chat').json['id']
+        self.ask('美国美西30KG，义乌海派',cid)
+        for text in ('五十公斤呢','50000克呢','0.05吨呢'):
+            self.assertIn('美国 50KG',self.ask(text,cid))
+        self.assertIn('大于 0',self.ask('美国重量为-30KG海派'))
+        self.assertIn('邮编格式不正确',self.ask('美国30KG，邮编518000海派'))
+        self.assertIn('美国 30KG',self.ask('美国30000克海派'))
+        self.assertIn('未找到目的仓码',self.ask('美国30KG发ABC999海派'))
+
+    def test_commodity_survives_weight_followups_and_new_commodity_replaces_it(self):
+        cid=self.client.post('/api/new_chat').json['id']
+        text=self.ask('美国美西铁制品30KG，义乌普船海派',cid)
+        self.assertIn('铁铝附加费5元/KG',text)
+        self.assertIn('30KG = 210元',text)
+        self.assertIn('50KG = 350元',self.ask('50KG呢',cid))
+        self.assertNotIn('铁铝附加费',self.ask('换成普通货50KG呢',cid))
+
+    def test_limit_fees_take_maximum_per_carton_and_do_not_guess_bad_threshold(self):
+        text=self.ask('美国美西1箱30KG，130x50x20cm，义乌普船海派')
+        self.assertIn('最高项90元/件',text)
+        self.assertNotIn('160元',text)
+        text=self.ask('美国美西1箱30KG，180x50x30cm，义乌普船海派')
+        self.assertIn('最高项400元/件',text)
+        text=self.ask('美国美西1箱30KG，40x30x20cm，义乌普船海派')
+        self.assertIn('最高项70元/件',text)
+        self.assertNotIn('400元/件',text)
+        self.assertIn('人工确认是否接收',self.ask('美国美西1箱70KG，40x30x20cm，义乌普船海派'))
+
+    def test_cbm_uses_two_decimals_half_up_without_creating_free_shipments(self):
+        rate={'unit':'cbm','kind':'truck','service':'洛杉矶普船海卡'}
+        intent=parse_intent('美国1KG，1.005CBM',set())
+        self.assertEqual(quantity(intent,rate),Decimal('1.01'))
+        intent['cbm']='1.004';self.assertEqual(quantity(intent,rate),Decimal('1.00'))
+        intent['weight']='0.1';intent['cbm']='0.004'
+        self.assertIsNone(quantity(intent,rate))
+
+    def test_business_topics_use_current_documents_instead_of_generic_quotes(self):
+        insurance=self.ask('美国保价1万美元，保险费怎么算')
+        self.assertIn('0.25%',insurance);self.assertIn('=25USD',insurance)
+        self.assertNotIn('元/KG',insurance)
+        self.assertIn('大于0',self.ask('美国保价-10美元，保险费怎么算'))
+        text=self.ask('美国30KG，7个品名清关续页收费')
+        self.assertIn('7美元/个',text);self.assertIn('=14美元',text)
+        text=self.ask('美国30KG还需要什么费用')
+        self.assertIn('偏远地址加4元/KG',text);self.assertIn('超偏远地址加6元/KG',text)
+        self.assertNotIn('250',text)
+        self.assertIn('不可接一般贸易',self.ask('美国美森加班海卡一般贸易报关多少钱'))
+        self.assertIn('不接收',self.ask('美国30KG纯电池可以发吗'))
+        self.assertIn('不接收',self.ask('美国30KG食品，FDA申报费多少人民币'))
+
+    def test_destination_origin_comparison_time_and_english(self):
+        cid=self.client.post('/api/new_chat').json['id']
+        self.ask('美国30KG发ZZZ1，义乌海派',cid)
+        text=self.ask('深圳交仓呢',cid)
+        self.assertIn('美国 30KG',text);self.assertNotIn('· 义乌',text)
+        text=self.ask('海运和空运哪个好，美国30KG')
+        self.assertIn('没有美国空运费率',text)
+        text=self.ask('美国美西海派多久')
+        self.assertIn('提取不等于送达',text);self.assertNotIn('元/KG',text)
+        text=self.ask('Please quote 30kg to US by sea')
+        self.assertIn('CNY/kg',text)
+        self.assertFalse(__import__('re').search(r'[\u4e00-\u9fff]',text),text)
+
+    def test_human_and_photo_questions_never_use_old_regional_model_facts(self):
+        self.assertIn('联系人工',self.ask('帮我转人工客服'))
+        text=self.ask('我可以发张货物照片让你判断报价吗')
+        self.assertIn('不会自动识别',text);self.assertNotIn('21KG',text)
+
+    def test_short_fee_synonyms_keep_current_us_rules(self):
+        cid=self.client.post('/api/new_chat').json['id']
+        self.ask('美国美西30KG，义乌普船海派',cid)
+        for question in ('还加什么费','还有其他费用吗','这个还要加钱吗','有其他额外收费吗'):
+            text=self.ask(question,cid)
+            self.assertIn('偏远地址加4元/KG',text)
+            self.assertNotIn('250',text)