import logging import re import uuid from collections.abc import AsyncGenerator from datetime import datetime, timedelta, timezone from typing import TYPE_CHECKING from sqlalchemy import select from sqlalchemy.ext.asyncio import AsyncSession from app.engine.models import ( Conversation, ConversationStatus, ConversationSource, Message, MessageRole, CustomerProfile, Evaluation, IntentLevel, LeadPushLog, ) from app.engine.services import ( cc_completion, email_service, ip_service, lead_push_service, ) from app.engine.services.ai_service import AIService from app.engine.services.boundary_filter import ( DEFAULT_WALL, asks_contact, deflection_for, no_contact_value, pivot_for, split_sentences, violates_boundary, ) from app.engine.services.contact_pipeline import ( canon, digits_only, latest_stated_contacts, merge_contacts, normalize_contacts, resolve_by_recency, scan_user_messages, split_validate, ) from app.engine.wall_schema import CompiledWall if TYPE_CHECKING: from app.platform.registry import TenantRuntime logger = logging.getLogger(__name__) # ---- Task 9: contact 行为开关 / context 种子白名单(config → 引擎消费口) ---- def resolve_contact_flags(config_data: dict | None) -> dict: """租户 config.contact → 联系方式行为开关。 cc_completion: 号码区号补全(判定树/确认状态机/CC 强制墙总闸); email_light_ask: 邮箱轻补(缺失渠道一次性追问)。False = 该行为整体 跳过(引擎级门控: 不建状态/不注入/不写计数键)。 (template_languages 暂无运行期消费方, 不在此解析——Phase 2 后台批次 再接。) """ contact = ((config_data or {}).get("contact")) or {} return { "cc_completion": bool(contact.get("cc_completion", True)), "email_light_ask": bool(contact.get("email_light_ask", True)), } def context_seed_map(config_data: dict | None) -> dict: """context 种子映射 = config.engine.context_seed_keys(ctx_key → raw_key)。 Task 9 前白名单(product_name/product_id)硬编码在本模块——两租户差异 (auto 是 vehicle_*)由此配置化;create_conversation 是唯一消费口(按 映射值写 raw_info,白名单 = 本映射的键集合——审查 Minor-4: 单一取值 路径,不留第二条内联读法)。 """ engine = ((config_data or {}).get("engine")) or {} return dict(engine.get("context_seed_keys") or {}) # 职能边界触发词(Task 13.2, 评审#1/#4 修订): 命中即注入红线提醒。精修说明: # - 裸 "how long"/"多久" 不收(规格参数类问题常用),英文要求 take/arrive/deliver/ship 邻接, # 中文只收 到货/多久能到/交货 等明确交付语境 # - 【评审#1】施压话术本身也触发: 磨价轮("just roughly"/"说个大概")没有价格词, # 却是最易破防的时刻——压力词单列一组 # - 【评审#4】v1 补齐漏词: expensive/fee/贵/价钱/总价/落地/划算/免费(短语式)等; # cost/fee 用 \b 边界,costa rica 不再误命中("costa"含cost但无词边界) # - 原则: 误触发低害(多一条提醒),漏触发高危(红线失守),词表偏宽;上线后漏词案例回流补词 # Task 4 词表数据化: 三组触发正则的数据源 = DEFAULT_WALL(jiancai 出厂) # .triggers 编译产物(seed_profiles/jiancai/wall.json),上方精修说明随数据留存 # C-1(终审): 本组模块常量降级为"默认墙视图"——供直调/旧测试按名锚定; # 运行期触发词查找一律走租户墙(manager 的 self._wall.triggers) BOUNDARY_TRIGGER_RE = DEFAULT_WALL.triggers["boundary"] # 预算路径路由(评审#9): 命中 BOUNDARY 触发词且含预算词 → 走预算 playbook BUDGET_TRIGGER_RE = DEFAULT_WALL.triggers["budget"] # 索要我方联系方式触发(15.2, doctrine v2): 客户问"你们怎么联系/你的微信多少" # = 最高意向信号。提醒层按 source 分支: web 指按钮, App 无按钮走反向留资 # - 排除第一人称将来时: "I'll call you later" 是日常告别语,不是索要联系方式。 # 必须用定宽 negative lookbehind——lookahead 在动词位置求值,永远看不到 # 前面的 let me / i'll,不生效。四个 lookbehind 全部定宽合法: i'll(5)、 # i’ll(5, 弯撇 U+2019 手机常见)、i will(7)、let me(7);IGNORECASE 兼容大写 CONTACT_ASK_TRIGGER_RE = DEFAULT_WALL.triggers["contact_ask"] # 语言跟随提醒(Task 11 真人验收发现): glm-4-flash 对拉丁字符占比高的中文 # 消息(DN800/HDPE 规格混排)会整轮漂成英文,system.md 语言规则压不住。修复位 = # 当轮 context 提醒(prompt 最末、最新鲜)——与 contact-ask 提醒"逐字话术防 # 漂移"同款方法论。2026-10-08 Task 5 收尾: 语言规则放开(模板句跟随客户语言 # 自然表达)后,ES note 的"整句使用英文原版/绝不翻译成西语"与新规则相反, # 已同步删除;两条 note 统一补"补全号码逐字照抄"(回显确认轮唯一例外)。 # Task 4 词表数据化: 话术数据源 = DEFAULT_WALL.reminders.language_follow _CJK_RE = re.compile(r"[一-鿿]") _ES_FEATURE_RE = re.compile(r"[áéíóúñãç¿¡]") LANG_NOTE_ZH = DEFAULT_WALL.reminders["language_follow"]["zh"] LANG_NOTE_ES = DEFAULT_WALL.reminders["language_follow"]["es"] def _lang_note_for(msg: str, wall: CompiledWall | None = None) -> str: # C-1(终审): wall=None = 模块级默认墙(LANG_NOTE_* 常量即该默认视图, # 旧测试锚定);manager 一律传租户墙 w = wall if wall is not None else DEFAULT_WALL if _CJK_RE.search(msg or ""): return w.reminders["language_follow"]["zh"] if _ES_FEATURE_RE.search(msg or ""): return w.reminders["language_follow"]["es"] return "" def _cc_lang_of(msg: str) -> str: """CC 话术语言路由(P3, 2026-10-08 验收): 汉字→ZH;西语特征(与 boundary_filter._lang_pool/_lang_note_for 同款重音符粗匹配)→ES; 否则 EN。只管 ECHO/ASK 模板选型——墙裁决锚(e164 digits)语言无关, no_ip 问句短语锚另含西语同词(见 cc_wall 裁决段)。""" if _CJK_RE.search(msg or ""): return "zh" if _ES_FEATURE_RE.search(msg or ""): return "es" return "en" # Task 3(spec §4.1-2/§4.4, 2026-10-08): 缺失渠道轻补逐字模板——与 system.md # 联系方式引导策略节同源。注入的是"缺失渠道"(客户没给过的),与再索要墙的 # 渠道精确化(Task 1)配套: 墙只拦已在手渠道的索要,这些话术恰好问缺失渠道。 # CC 强制墙(2026-10-08 增补设计 §2)复用同源正文: _CC_ASK_* 是追问句正文; # _CC_WALL_* 是墙的整段替换句(EN 加 "Got it — " 衔接头;ZH 与正文同句)。 # 2026-10-08 判定树设计 Task 3: cc 轻补注入分支已删(判定树接管),_CC_NOTE_* # 不再运行时注入——常量保留作 no_ip 路径/Task 4 回显模板的正文基准 # (test_boundary_filter / test_system_prompt_dual_contact 仍锚定其正文)。 # Task 4 词表数据化: CC/邮箱模板数据源 = DEFAULT_WALL.cc_templates 与 # .reminders.email_light(seed_profiles/jiancai/wall.json);_CC_WALL_*/_CC_NOTE_* # 的静态组合("Got it — " 前缀/外壳+正文)在数据文件里存整句,值逐字等价。 _CC_ASK_EN = DEFAULT_WALL.cc_templates["ask"]["en"] _CC_ASK_ZH = DEFAULT_WALL.cc_templates["ask"]["zh"] # P3(2026-10-08 真实验收): 西语轮模板补齐——修复前 ECHO/ASK 只有 EN/ZH, # 西语轮 GLM 照抄英文。WALL 沿用 EN 形态(衔接头 + 追问句正文)。 _CC_ASK_ES = DEFAULT_WALL.cc_templates["ask"]["es"] _CC_WALL_EN = DEFAULT_WALL.cc_templates["wall"]["en"] _CC_WALL_ZH = DEFAULT_WALL.cc_templates["wall"]["zh"] _CC_WALL_ES = DEFAULT_WALL.cc_templates["wall"]["es"] _CC_NOTE_EN = DEFAULT_WALL.cc_templates["note"]["en"] _CC_NOTE_ZH = DEFAULT_WALL.cc_templates["note"]["zh"] # Task 4(spec §4 回显确认轮/§4b): 判定树给出 e164 建议的等待态轮用回显确认 # 模板——{intl} 由 Python format_intl 算好填入(reminder/墙替换/测试断言三方 # 同源引用本常量),GLM 只逐字复述不拼号。no_ip 轮(无可回显号)仍走 _CC_ASK_* # (上方保留不拆),两条路径按 _cc.whatsapp 的 e164 在场分流。 _CC_ECHO_EN = DEFAULT_WALL.cc_templates["echo"]["en"] _CC_ECHO_ZH = DEFAULT_WALL.cc_templates["echo"]["zh"] _CC_ECHO_ES = DEFAULT_WALL.cc_templates["echo"]["es"] _EMAIL_NOTE_EN = DEFAULT_WALL.reminders["email_light"]["en"] _EMAIL_NOTE_ZH = DEFAULT_WALL.reminders["email_light"]["zh"] def _cc_intl(wa_state: dict | None) -> str: """等待态的分组展示号: intl 键缺失时按 e164 防御重算(存量/迁移数据)。""" e164 = str((wa_state or {}).get("e164") or "") if not e164: return "" return str((wa_state or {}).get("intl") or cc_completion.format_intl(e164)) def _cc_script(wa_state: dict | None, lang: str, wall: CompiledWall | None = None) -> str: """CC 等待态本轮逐字话术(Task 4, spec §4;P3 扩 ES): 有 e164 → 回显 确认句(intl 由 Python 算好填入,GLM 不拼号);no_ip → 追问句 (_CC_ASK_* 服务)。reminder 注入/墙替换/测试断言三方同源,统一走本函数。 C-1(终审): wall=None = 模块级默认墙(_CC_ECHO_*/_CC_ASK_* 常量即该 默认视图);manager 一律传租户墙。""" w = wall if wall is not None else DEFAULT_WALL if str((wa_state or {}).get("e164") or ""): intl = _cc_intl(wa_state) echo = w.cc_templates["echo"] return {"zh": echo["zh"], "es": echo["es"]}.get( lang, echo["en"]).format(intl=intl) ask = w.cc_templates["ask"] return {"zh": ask["zh"], "es": ask["es"]}.get(lang, ask["en"]) def _cc_wall_template(wa_state: dict | None, lang: str, wall: CompiledWall | None = None) -> str: """CC 触发轮墙整段替换句: 回显轮 = ECHO 模板(自带 "Got it —" 衔接头); no_ip 轮 = _CC_WALL_*(ASK 追问句 + 衔接头,沿用 Task 3 形态;P3 扩 ES)。 C-1(终审): wall=None = 模块级默认墙(_CC_WALL_* 常量即该默认视图); manager 一律传租户墙。""" if str((wa_state or {}).get("e164") or ""): return _cc_script(wa_state, lang, wall=wall) w = wall if wall is not None else DEFAULT_WALL tmpl = w.cc_templates["wall"] return {"zh": tmpl["zh"], "es": tmpl["es"]}.get(lang, tmpl["en"]) def _cc_confirm_note(wa_state: dict | None, lang: str, wall: CompiledWall | None = None) -> str: """cc 等待态确认句注入(Task 4, spec §4/§4b): cc_due 才注入,与邮箱轻补 cc_settled 串行互斥(两个"逐字使用这句"不同轮竞争)。外壳仿轻补指引: ⚠️ 系统指令声明 + 逐字话术 + 客户答复后致谢不追问。回显分支带零号码 唯一例外(4b-3 让位语义重建: 仅系统提供的补全号原文可写出)。 Task 4 词表数据化: 指引话术数据源 = 墙 reminders.cc_guide ({intl}/{cc_script} 占位由本函数 .format() 回填,值逐字等价)。 C-1(终审): wall=None = 模块级默认墙;manager 一律传租户墙。""" if not wa_state or not cc_completion.cc_due(wa_state): return "" w = wall if wall is not None else DEFAULT_WALL if str(wa_state.get("e164") or ""): intl = _cc_intl(wa_state) return w.reminders["cc_guide"]["echo"].format( intl=intl, cc_script=_cc_script(wa_state, lang, wall=wall)) return w.reminders["cc_guide"]["ask"].format( cc_script=_cc_script(wa_state, lang, wall=wall)) def _contact_completion_note( raw_info: dict | None, confirmed: dict | None, suspect: dict | None, lang: str = "en", email_ask: bool = True, wall: CompiledWall | None = None, ) -> tuple[str, list[str]]: """邮箱轻补提醒(spec §4.2/§4.3b,2026-10-08 判定树设计收编)。 纯函数,返回(注入文案,计数键)。 cc 追问分支已删除——号码区号补全由轮前判定树钩子接管(_cc 状态机, _cc_pre_turn),确认提醒由 cc_due 驱动(Task 4 接)。本函数只管邮箱轻补, 且串行解锁条件改为 cc_settled(_cc.whatsapp): 确认流未落定时注入邮箱 轻补会让两个"逐字使用这句"同轮竞争(旧 §4.3b 场景①教训);落定即解锁。 带 + 号客户无 _cc 状态 → cc_settled(None)=True,旧轻补行为不回归。 suspect 仅为与调用处画像判定同签名,规则只看 confirmed(spec §4.2)。 email_ask=False(Task 9: contact.email_light_ask 开关)→ 恒空,不注入 也不产计数键。 C-1(终审): wall=None = 模块级默认墙(_EMAIL_NOTE_* 常量即该默认视图); manager 一律传租户墙(流式调用处与本函数在 reminder 内的调用同参, 写回与注入永不漂移)。 """ if not email_ask: return "", [] info = raw_info or {} numbers = [str(v).strip() for k, v in (confirmed or {}).items() if k in ("whatsapp", "phone") and v] if not numbers: return "", [] if "email" in (confirmed or {}): return "", [] if info.get("_email_asked"): return "", [] if not cc_completion.cc_settled((info.get("_cc") or {}).get("whatsapp")): return "", [] # whatsapp 确认流未落定: 邮箱轻补串行等待 w = wall if wall is not None else DEFAULT_WALL return ((w.reminders["email_light"]["zh"] if lang == "zh" else w.reminders["email_light"]["en"]), ["_email_asked"]) def _cc_pre_turn(raw_info: dict, confirmed: dict, ip_iso: str | None) -> bool: """轮前判定树钩子(spec §6-1/§3/§4): 对 confirmed 号码建/重置/迁移 _cc。 - 多渠道策略: 仅 whatsapp 组走确认流;phone 与 whatsapp 同 canon 时共享 whatsapp 组状态(不建独立键),异号时 phone 组只记静默补全态 (ip_proposed/naive/no_ip,不进确认流)——确认流的消费与门控 (cc_due/cc_settled/轮末 transit)一律只看 _cc.whatsapp,phone 态 仅供出站渲染(Task 6)。 - canon 变化即重置重走判定树(旧补全永不跟随新号);同 canon 保留原状态 (attempts 只被 canon 变化重置,spec §4)。 - 显式 +/00 号码不建状态(无态=天然落定);prefix_normalized 静默规范化 态(confirmed=true)照写,供出站渲染无标注输出。 - 存量迁移(spec §4 尾): 旧 _cc_asked=True 且 whatsapp 裸号尚无 _cc 组 → 一次性落 fallback 态(已问过不再追问,直通邮箱轻补);判定树算出的 e164 建议保留(首封可拨)。_cc 组一旦存在即不再触发。 就地更新 raw_info["_cc"],返回是否有变更(调用方与计数写回同事务落库)。 """ before = raw_info.get("_cc") cc = dict(before or {}) migrate = bool(raw_info.get("_cc_asked")) wa = str(confirmed.get("whatsapp") or "").strip() ph = str(confirmed.get("phone") or "").strip() def _refresh(channel: str, value: str) -> None: existing = cc.get(channel) if existing is not None \ and str(existing.get("canon") or "") == digits_only(value): return # 同 canon: 保留原状态(attempts 不重置) kind, state = cc_completion.classify(value, ip_iso) if state is None: cc.pop(channel, None) # 显式 +/00(或防御性垃圾输入): 无态即落定 return st = dict(state) if (migrate and channel == "whatsapp" and existing is None and kind == cc_completion.NEED_CC): st["confirmed"] = False st["source"] = "fallback" # 存量迁移: 已问过,不再追问 st.pop("suggest_ask_full", None) cc[channel] = st if wa: _refresh("whatsapp", wa) else: cc.pop("whatsapp", None) # 号码不再在手: 状态清,防残留跟随 if ph: wa_state = cc.get("whatsapp") if wa_state is not None \ and str(wa_state.get("canon") or "") == digits_only(ph): cc.pop("phone", None) # 同 canon 组归并: phone 共享 whatsapp 状态 else: _refresh("phone", ph) else: cc.pop("phone", None) if cc: raw_info["_cc"] = cc else: raw_info.pop("_cc", None) return raw_info.get("_cc") != before # Task 6(spec §5 面板同步): 等待确认期间的联系方式值尾注——防"邮件带补全、 # 后台显裸号"的分裂。尾注全为非数字字符,canon() 纯数字提取不受影响 # (24h 去重/更正判定照常)。 _CC_PENDING_TAIL = "（待确认补全号）" def _panel_contact_info(confirmed: dict, cc_map: dict | None) -> dict: """ev.contact_info 存储视图(Task 6 评审钉死): 裸号原文 + 等待态尾注, e164 走派生不落本体——e164 替换本体会让"存储值 vs 每轮裸号确认值" 永远不同 canon,退化成每轮误判换号→更正连发/回访退化。 只标 whatsapp 确认流覆盖的号码(canon 与 _cc.whatsapp 一致,含同号 phone 镜像): phone 独立静默态不进确认流、attempts 永不推进,cc_due 恒真,若照标会永久滞留且语义失真。""" wa = (cc_map or {}).get("whatsapp") wa_canon = str((wa or {}).get("canon") or "") pending = bool(wa_canon) and cc_completion.cc_due(wa) out: dict = {} for k, v in (confirmed or {}).items(): if (pending and k in ("phone", "whatsapp") and digits_only(str(v)) == wa_canon): out[k] = f"{v}{_CC_PENDING_TAIL}" else: out[k] = v return out def _channel_canons(confirmed: dict, cc_map: dict | None) -> dict[str, set[str]]: """canon 口径双保险(Task 6 评审钉死): 每渠道候选集 = 裸号 canon ∪ _cc.e164 的 canon——同号换形态(裸号↔+前缀完整形态)不误判换号 (更正连发)、回访不退化成全量询盘。只扩"新值侧": 若把当前 _cc 的 e164 canon 并入旧值/历史集,换号后新号恰为前缀完整形态时会自我满足, 真更正被吞。""" out: dict[str, set[str]] = {} for k, v in (confirmed or {}).items(): cands = {canon(str(v))} state = cc_completion.cc_state_for(cc_map, k, str(v)) e164 = str((state or {}).get("e164") or "") if e164: cands.add(canon(e164)) out[k] = cands return out # P4'(2026-10-08 复验): 画像"目标国家"报国信号的占位值集——"无"/"未提及" # 是写给 extractor 的指令标记(extractor.md 明令禁止作字段值输出,但 GLM # 不保证),"未知"/"本地" 同为无信息量形态;命中占位集不当作报国消费。 _COUNTRY_PLACEHOLDERS = {"无", "未提及", "未知", "本地"} def _country_signal(cur, pre) -> str | None: """P4' 画像报国信号(纯函数): 等待态轮画像"目标国家"键**新出现或值 变化**(cur=本轮合并后值, pre=轮前快照)且值有效(非空、非占位集) → 返回该值作为 country 信号;值不变(含轮前已有同值)→ None(去抖: 同国重算幂等,重复陈述无新信息)。国名是否可识别(NAME_TO_REGION 命中)由调用方判定——不命中时信号整体忽略,不消费。""" c = str(cur or "").strip() if not c or c in _COUNTRY_PLACEHOLDERS: return None if c == str(pre or "").strip(): return None return c # 方案B(13.6): 迂回话术轮换序号——连续破防时不至于复读同一句 _boundary_seq = 0 def _boundary_rotate() -> int: global _boundary_seq _boundary_seq += 1 return _boundary_seq class ConversationManager: def __init__(self, db: AsyncSession, *, runtime: "TenantRuntime", ai_service: AIService | None = None): self.db = db # Task 6: runtime 必填(Task 5b 质量审查关门建议)——提示词/墙/会话 # 工厂全部租户化,无租户上下文的构造不再合法;默认 AI 服务用该租户 # 的 PromptProvider + compiled_wall 组装($DEFLECTION_POOL 单一事实源 # 注入)。Task 9: AI 凭据/config 全部经 runtime.config.data 接线。 self.runtime = runtime # C-1(终审审查): 执行侧墙接线——过滤/替换/提醒全走租户编译墙, # 与 AIService 的 $DEFLECTION_POOL 同源(runtime.compiled_wall); # 模块级 DEFAULT_WALL 仅供无租户上下文的直调默认(boundary_filter # 出厂视图 + 本模块旧测试锚定),会话流内一律本墙。 self._wall = runtime.compiled_wall self.ai = ai_service or AIService( prompts=runtime.prompts, wall=runtime.compiled_wall, config_data=runtime.config.data) # Task 9: contact 行为开关(cc 补全/邮箱轻补)与国名映射扩表—— # manager 生命周期内配置不变(reload 换 runtime 即换 manager 装配线; # 生效时机: WS 长连接内冻结至断连,REST 路径下一请求生效——Phase 2 # 联调改配置后按此预期,勿误判"没生效") self._contact_flags = resolve_contact_flags(runtime.config.data) self._region_extras = (((runtime.config.data.get("misc")) or {}) .get("name_to_region_extras") or None) @property def session_factory(self): """推送后台任务写结果用的工厂(写回派发租户的库);runtime 未懒建 engine 时 None(仅测试直连场景——生产装配线总在 ensure_ready 之后)。""" return self.runtime.session_factory async def create_conversation( self, source: ConversationSource = ConversationSource.standalone, client_info: dict | None = None, page_token: str | None = None, context: dict | None = None, ) -> Conversation: session_id = uuid.uuid4().hex conv = Conversation( session_id=session_id, source=source, client_info=client_info, page_token=page_token, ) self.db.add(conv) await self.db.commit() await self.db.refresh(conv) # Conditional whitelist seed of app context into raw_info (red line): # only when `context` is provided, and only keys in the tenant's # engine.context_seed_keys map (jiancai: product_*; auto: vehicle_* — # Task 9 前白名单硬编码 product_name/product_id,现读租户配置). # WS path passes no context -> raw_info stays {}. raw_info: dict = {} if context: for ctx_key, raw_key in context_seed_map( self.runtime.config.data).items(): if context.get(ctx_key): raw_info[raw_key] = context[ctx_key] profile = CustomerProfile(conversation_id=conv.id, raw_info=raw_info) self.db.add(profile) await self.db.commit() return conv async def get_by_session(self, session_id: str) -> Conversation | None: result = await self.db.execute( select(Conversation).where(Conversation.session_id == session_id) ) return result.scalar_one_or_none() async def get_by_page_token(self, page_token: str) -> Conversation | None: result = await self.db.execute( select(Conversation).where( Conversation.page_token == page_token, Conversation.status == ConversationStatus.active, ) ) return result.scalar_one_or_none() async def stream_process_message( self, session_id: str, content: str ) -> AsyncGenerator[dict, None]: """Stream AI reply token by token, then do extract/evaluate.""" conv = await self.get_by_session(session_id) if not conv: yield {"type": "error", "message": "session not found"} return if conv.status != ConversationStatus.active: yield {"type": "error", "message": "conversation ended"} return # Save user message user_msg = Message( conversation_id=conv.id, role=MessageRole.user, content=content ) self.db.add(user_msg) await self.db.commit() history = await self._load_history(conv.id) # Build context reminder (merged into system prompt) profile = await self._get_profile(conv.id) # P0 同轮竞态消除: 当前消息即时正则扫描——仅并入本轮内存视图 # (提醒/话术路由/轮前 cc 判定树),不落库;持久化仍由轮末 # extractor+scanner 负责,邮件触发时序不变。 # 合并方向(Task 3 修正): 当前消息捕获覆盖存量——客户当轮改号时, # 同轮视图必须看到新号(轮前判定树 canon 变化即重置依赖此方向; # 与轮末 Task 12 "最新显式自述优先"同语义)。存量只在当前消息 # 未提及的渠道上补位。 current_scan = scan_user_messages([{"role": "user", "content": content}]) effective_raw = dict(profile.raw_info or {}) if current_scan: effective_raw["联系方式"] = merge_contacts( effective_raw.get("联系方式"), current_scan) # P4'(2026-10-08 复验) 轮前画像快照: "目标国家"轮末信号判定基线。 # 必须在本轮任何 raw_info 写回发生前取值(下方计数写回/轮末 extractor # 合并都会覆盖同一 ORM 实例);值为 str/None 不可变,持引用即安全。 pre_turn_country = (profile.raw_info or {}).get("目标国家") # 联系方式视图(轮前钩子/计数写回/再索要墙区共用;原在 reminder 之后 # 计算,前移只为喂轮前钩子,输入相同取值不变) _contacts_now = normalize_contacts(effective_raw.get("联系方式")) _confirmed_now, _suspect_now = split_validate(_contacts_now) # Task 3 轮前判定树钩子(spec §6-1;评审 Step 3b 钉死顺序: 必须在 # _build_context_reminder 之前)——即时扫描并入裸号后同步跑判定树 # (纯计算毫秒级)建/重置/迁移 _cc,当轮即可被墙门控/轮末消费/出站 # 渲染读到;落库与下方一次性计数写回同事务。 # Task 9: contact.cc_completion=False → 判定树整体跳过(不建不迁 # _cc;存量 _cc 冻结为只读出站渲染,不再推进)。 _ip_iso = ip_service.resolve_region_code( (conv.client_info or {}).get("ip")) _cc_changed = (_cc_pre_turn(effective_raw, _confirmed_now, _ip_iso) if self._contact_flags["cc_completion"] else False) _wa_cc = (effective_raw.get("_cc") or {}).get("whatsapp") context_reminder = self._build_context_reminder( effective_raw, content, history, source=conv.source.value, contact_flags=self._contact_flags, wall=self._wall) if self._wall.triggers["contact_ask"].search(content or ""): logger.info("Contact-ask reminder fired (source=%s)", conv.source.value) # Task 3(spec §4.3/§6-1): 一次性计数写回 + _cc 状态同事务落库—— # _build_context_reminder 是 staticmethod 收内存副本,计数键/状态须由 # 调用方在流式开始前显式落库;轮末 extractor 合并起点是 # dict(profile.raw_info or {}),提前提交可存活。与 reminder 内部同参 # 调用(上方纯函数),保证写回与注入永不漂移;条件扩为"计数或 _cc # 变更任一存在"(评审 Step 3b)。 _, completion_marks = _contact_completion_note( effective_raw, _confirmed_now, _suspect_now, "zh" if _CJK_RE.search(content or "") else "en", email_ask=self._contact_flags["email_light_ask"], wall=self._wall) if completion_marks or _cc_changed: raw = dict(profile.raw_info or {}) for key in completion_marks: raw[key] = True if _cc_changed: if effective_raw.get("_cc"): raw["_cc"] = effective_raw["_cc"] else: raw.pop("_cc", None) profile.raw_info = raw self.db.add(profile) await self.db.commit() # warning 级(2026-10-08 第四轮验收): 生产曾现 2/5 裸号轮墙未介入的 # 非确定性异常(同输入容器内链路复现正常)——本行生产可见,异常会话 # 可立刻分辨"计数/状态/注入是否发生",供观察期定位 logger.warning("Contact completion state persisted (conv=%s): " "marks=%s cc_changed=%s", conv.id, completion_marks, _cc_changed) # Enrich short user messages with context so AI doesn't lose track history_for_ai = list(history) enriched = self._enrich_short_message(content, profile.raw_info or {}, history) if history_for_ai and history_for_ai[-1]["role"] == "user" and enriched != content: history_for_ai[-1] = {**history_for_ai[-1], "content": enriched} logger.info("Enriched short message: %r -> %r", content[:50], enriched[:100]) # 方案B'(13.7): 句子粒度门控——干净句子逐句流出(恢复打字机), # 违规句永不流出:已流出内容全部干净,违规时接过渡话术收尾并掐断生成。 # F6(D6联动): 客户已留联系方式时,收尾话术不得再索要——路由 contact 版 # 渠道精确化(2026-10-08): confirmed 渠道集合传给再索要墙—— # 索要缺失渠道(如已有 phone 问邮箱)放行,是 Task 3 邮箱轻补的前提 # (confirmed/suspect 已在 Task 3 写回处算好,此处复用) has_contact = bool(_confirmed_now) _confirmed_channels = set(_confirmed_now) # CC 强制墙(2026-10-08 cc 设计): 门控改线判定树——cc_due(_cc.whatsapp) # 等待态即触发(旧 `completion_marks == ["_cc_asked"]` 门控随 cc 轻补 # 分支删除而消亡,_cc_asked 停写)。流式无法撤回 → 触发轮不逐句流出, # 整段缓冲到流末统一裁决(缓冲期间价格/零号码/再索要三墙照常逐句 # 检查,优先级不变)。Task 4(spec §4/§4b): 回显轮(等待态有 e164)裁决 # 锚 = 注入 e164 的 digits 等值在场,替换句 = ECHO 模板;no_ip 轮 # (无可回显号)沿用 ASK 模板与 "country code" 问句短语锚。 # Task 9: cc_completion=False → CC 强制墙同样关闭(开关管整个补全 # 行为族: 判定树/确认流/墙);存量等待态不触发缓冲整段裁决 cc_wall = (self._contact_flags["cc_completion"] and cc_completion.cc_due(_wa_cc)) # Task 4 白名单传参(spec §4): 零号码墙逐段放行系统注入的补全号—— # 仅回显轮(等待态有 e164)传,其余轮 None 保持原行为(全拦) cc_allow_number = ((_wa_cc or {}).get("e164") if cc_wall else None) yield {"type": "stream_start"} emitted = "" pending = "" violated = False dropped_ask = False # Task 5b: 本轮是否有索要句被再索要墙丢弃 dirty = "" cc_buffer: list[str] = [] # CC 触发轮: 已过墙句子的延迟流出缓冲 # 15.3: 双墙裁决——价格墙检查在前: 同句双违规时价格路径话术优先 # (职能边界话术更具体,且自带留资引导);仅纯号码/邮箱违规时 # violation=="no_contact",用零号码墙替换句 violation = "" async for token in self.ai.stream_chat(history_for_ai, context=context_reminder): pending += token complete, pending = split_sentences(pending) for sentence in complete: if violates_boundary(sentence, wall=self._wall): violated = True dirty = sentence violation = "boundary" break if no_contact_value(sentence, allow_number=cc_allow_number, wall=self._wall): violated = True dirty = sentence violation = "no_contact" break # Task 5b 再索要墙: 已留资时索要句静默丢弃(丢句不掐断, # 其余句子照常流出——软于两墙的掐断+替换); # 渠道精确化: 只丢索要已在手渠道的句子 if has_contact and asks_contact(sentence, _confirmed_channels, wall=self._wall): logger.warning("Re-ask wall dropped sentence (conv=%s): %r", conv.id, sentence[:60]) dropped_ask = True continue if cc_wall: cc_buffer.append(sentence) # 墙照检,流出延后到流末 continue for i in range(0, len(sentence), 40): yield {"type": "stream_chunk", "content": sentence[i:i + 40]} emitted += sentence if violated: break # 提前掐断生成,省 token if not violated and pending: if violates_boundary(pending, wall=self._wall): violated = True dirty = pending violation = "boundary" elif no_contact_value(pending, allow_number=cc_allow_number, wall=self._wall): violated = True dirty = pending violation = "no_contact" elif has_contact and asks_contact(pending, _confirmed_channels, wall=self._wall): # Task 5b 再索要墙: 尾巴是索要句 → 静默丢弃(不流出不掐断) logger.warning("Re-ask wall dropped tail (conv=%s): %r", conv.id, pending[:60]) dropped_ask = True elif cc_wall: cc_buffer.append(pending) else: for i in range(0, len(pending), 40): yield {"type": "stream_chunk", "content": pending[i:i + 40]} emitted += pending if violated: if violation == "no_contact": # 零号码墙替换句: 已留资→确认话术(不再索要);未留资按 source 分支 # (App 无按钮 → 反向留资; web/widget/standalone → 指顶部按钮) logger.warning( "No-contact wall replaced sentence (conv=%s): %r", conv.id, dirty[:60]) if cc_wall: # Important-2(审查修复) + Task 4: CC 触发轮回显被拦 → # closing 改用本轮 CC 模板(回显轮 ECHO/no_ip 轮 ASK)而非 # NO_CONTACT_ALREADY——GLM 有 3/3 回显倾向,该路径概率高, # 客户该收到确认/追问而非"稍后联系"虚假承诺; # 价格墙路径(violation=="boundary")不变 closing = _cc_wall_template(_wa_cc, _cc_lang_of(content), wall=self._wall) else: # Task 9 收口: 视图直取墙 no_contact(单一事实源), # 不经 boundary_filter 的模块级常量转引;C-1(终审): # 取租户墙——替换文案各自来自自己的池 _w = self._wall closing = (_w.no_contact["already"] if has_contact else (_w.no_contact["app"] if conv.source.value == "app" else _w.no_contact["web"])) else: logger.warning( "Boundary filter intercepted sentence (conv=%s): %r | tail=%r", conv.id, dirty[:80], (pending or "")[:40]) closing = (pivot_for(content, has_contact, wall=self._wall) if emitted else deflection_for(content, _boundary_rotate(), has_contact=has_contact, wall=self._wall)) # Minor-5(审查修复): 已流出前缀与替换句之间补一个空格分隔 # ("...xxxx? Got it —"——英文衔接无空格会粘连);CC/触发轮缓冲 # 未流出,emitted 恒空,天然不受影响。空格随 closing 一起流出, # 客户所见与落库保持一致 if emitted and not emitted.endswith((" ", "\n")): closing = " " + closing for i in range(0, len(closing), 40): yield {"type": "stream_chunk", "content": closing[i:i + 40]} emitted += closing # CC 强制墙裁决(2026-10-08 cc 设计;Task 4 改造 spec §4b-4): 触发轮 # 缓冲全文在此判定——回显轮(等待态有 e164)裁决锚 = **注入 e164 的 # digits 等值在场**(GLM 任意分组形态 "+966 50 123 4567"/"+966501234567" # 均判在场;辅锚 "is that right"/"对吗" 随模板正文,不作独立判据—— # 号码在场才是回显的承重语义);no_ip 轮无可回显号,沿用问句短语锚 # ("country code"/"国家代码"/"código de país",与 _CC_ASK_* 模板句 # 同词——P3 扩西语同词,西语服从句不再被误替换)。在场 → GLM # 自发服从,缓冲原样流出零干预;不在场 → 整段替换为对应 ECHO/ASK # 模板。violated(价格/零号码墙)优先于本墙——沿用双墙裁决"更具体 # 话术优先"惯例;_cc 状态已在流前落库,不受替换影响。缓冲轮全部 # 实义句被再索要墙丢弃时 cc_buffer 为空 → 同样走替换(模板句即 # 本轮唯一实义输出,天然不触发下方兜底)。 if cc_wall and not violated: cc_full = "".join(cc_buffer) cc_lang = _cc_lang_of(content) wa_e164 = str((_wa_cc or {}).get("e164") or "") if wa_e164: obeyed = digits_only(wa_e164) in digits_only(cc_full) else: obeyed = ("country code" in cc_full.lower() or "国家代码" in cc_full or "código de país" in cc_full.lower()) if obeyed: for i in range(0, len(cc_full), 40): yield {"type": "stream_chunk", "content": cc_full[i:i + 40]} emitted = cc_full else: logger.warning( "CC enforcement wall replaced reply (conv=%s): %r", conv.id, cc_full[:60]) cc_template = _cc_wall_template(_wa_cc, cc_lang, wall=self._wall) for i in range(0, len(cc_template), 40): yield {"type": "stream_chunk", "content": cc_template[i:i + 40]} emitted = cc_template # Task 5b 评审修正: 整条回复只有索要句(全被丢)→ 兜底流出"经理主动 # 联系"句,绝不空回复。与上方墙收尾互斥——violated 路径已自带收尾, # 此处仅在无任何实义内容流出时接管;已流出的纯空白前缀一并作废, # 落库恒为完整兜底句(客户看到的比一个空格更糟的是: 什么都没有)。 if not violated and dropped_ask and not emitted.strip(): logger.warning("Re-ask wall dropped entire reply (conv=%s), " "falling back to closing", conv.id) fallback = self._wall.no_contact["already"] for i in range(0, len(fallback), 40): yield {"type": "stream_chunk", "content": fallback[i:i + 40]} emitted = fallback yield {"type": "stream_end"} ai_reply = emitted # 落库与流出统一为已流出文本(下方持久化) # Save assistant message (skip if empty) if ai_reply.strip(): assistant_msg = Message( conversation_id=conv.id, role=MessageRole.assistant, content=ai_reply ) self.db.add(assistant_msg) await self.db.commit() # Round 2: Extract info (background) full_history = history + [{"role": "assistant", "content": ai_reply}] profile = await self._get_profile(conv.id) # Task 12b: 轮前联系方式快照(extractor 深合并 + 覆盖 + 同号同步的比对基线) before_contacts = normalize_contacts((profile.raw_info or {}).get("联系方式")) # _ 前缀内部键(_cc 状态机/_email_asked 计数)不进 LLM 输入(Task 3 审查 # Minor 3 防御纵深——渲染/推送侧已过滤,此处防提示词侧意外回显) new_info = await self.ai.extract_info( full_history, existing_info={k: v for k, v in (profile.raw_info or {}).items() if not str(k).startswith("_")}, ) logger.info("Extractor result: %s", new_info) # 出口卫生(spec §4 三封堵之②/③): cc_reply 是 extractor 的单轮瞬态 # 分类,提取后即剥离——绝不进 raw_info 持久层(消费点在轮末钩子 # _cc_round_end);同时防御性丢弃 extractor 回传的任何 `_` 前缀键, # 防 LLM 回显 _cc 覆盖 Python 管理的状态机。(入口侧封堵①: 上方 # existing_info 已滤 `_`,复核通过) cc_reply = None if isinstance(new_info, dict): cc_reply = new_info.pop("cc_reply", None) stripped = {k: v for k, v in new_info.items() if not str(k).startswith("_")} if len(stripped) != len(new_info): logger.warning( "Dropped underscore keys from extractor output (conv=%s): %s", conv.id, [k for k in new_info if str(k).startswith("_")]) new_info = stripped if new_info: raw = dict(profile.raw_info or {}) for k, v in new_info.items(): # 联系方式深合并(同key新值覆盖),其余顶层覆盖 —— 堵浅合并抹数据 if k == "联系方式": raw[k] = merge_contacts(raw.get(k), v) else: raw[k] = v profile.raw_info = raw self.db.add(profile) # Round 2.5: 联系方式正则辅源(S4: 扫全量客户消息历史) # 🔴 合并方向: 扫描器只填空,extractor 已有值优先——否则扫描器的 # 首个历史值会压掉 extractor 后续捕获的改号, D4 更正邮件失效 scanned = scan_user_messages(full_history) if scanned: raw = dict(profile.raw_info or {}) raw["联系方式"] = merge_contacts(scanned, raw.get("联系方式")) profile.raw_info = raw self.db.add(profile) # Task 12: 最新显式自述优先 —— 唯一允许文本压过 extractor 回传的位置 # (extractor 受"保留已有信息"倾向会滞留旧值,实测 wrong number 场景命中) latest_stated = latest_stated_contacts(full_history) if latest_stated: current = normalize_contacts((profile.raw_info or {}).get("联系方式")) changed = False for k, v in latest_stated.items(): if v and canon(str(v)) != canon(str(current.get(k, ""))): current[k] = v changed = True if changed: raw = dict(profile.raw_info or {}) raw["联系方式"] = current profile.raw_info = raw self.db.add(profile) # Task 12c 最近提及裁决: 镜像组分歧时以客户最晚提及的号码为准 # (杀 extractor 历史振荡 + 压制幻觉;Task 12b 同号同步场景被涵盖) after_contacts = normalize_contacts((profile.raw_info or {}).get("联系方式")) resolved = resolve_by_recency(before_contacts, after_contacts, full_history) if resolved != after_contacts: raw = dict(profile.raw_info or {}) raw["联系方式"] = resolved profile.raw_info = raw self.db.add(profile) # Task 3 轮末 cc 钩子(spec §6-2): 联系方式四层合并完成后、D1 邮件 # 触发前——消费 cc_reply 推进状态机,并为本轮才入管道的号码补建 _cc # (spec §5: 首封补全号/推送派生依赖已建好的 _cc)。cc_wall_fired = # 本轮墙确有触发(P1+P2 首问轮判定输入,见 _cc_round_end)。 # P4': pre_turn_country = 轮前画像快照(本轮 extractor 合并前的 # "目标国家"值),画像报国信号的比对基线。 await self._cc_round_end(conv, profile, cc_reply, cc_wall_fired=cc_wall, pre_turn_country=pre_turn_country) # Round 3: Evaluate (仅 ≥3 条客户消息才有意义, 前两轮必然 pending —— D7) user_msg_count = sum(1 for m in full_history if m["role"] == "user") evaluation_ran = user_msg_count >= 3 if evaluation_ran: evaluation = await self.ai.evaluate( profile={k: v for k, v in (profile.raw_info or {}).items() if not str(k).startswith("_")}, recent_messages=full_history, ) else: # 客户端 evaluated 事件语义保持 pending;邮件标签由 evaluation_ran 决定(D2) evaluation = {"intent_level": "pending", "reasoning": "", "contact_info": {}, "info_sufficient": False} logger.info("Evaluation (stream): profile=%s | eval=%s", profile.raw_info, evaluation) # 邮件触发(D1): 与会话结束彻底解耦,联系方式到手即发 pending_pushes: list[LeadPushLog] = [] await self._maybe_send_lead_email( conv, profile, evaluation, evaluated=evaluation_ran, pending_pushes=pending_pushes, ) # 联系方式判定(供 D8 评估落库): 有意向但没联系方式 → 卡单供 admin 人工兜底 confirmed_now, _ = split_validate( normalize_contacts((profile.raw_info or {}).get("联系方式"))) # 评估落库(D8 泛化): 每轮评估后刷新意向;email_sent/correction_count # 永不触碰。有意向无联系方式 = 卡单(admin 可筛);已发过邮件的 # contact_info 由触发器更正分支管理,这里不覆盖。 # Task 6: 存储视图走面板尾注(等待态标注,e164 派生不落本体) if user_msg_count >= 3: ev = await self._get_or_init_evaluation(conv.id) ev.intent_level = IntentLevel(evaluation.get("intent_level", "pending")) ev.reasoning = evaluation.get("reasoning", "") if not confirmed_now: ev.contact_info = {} elif not ev.email_sent: ev.contact_info = _panel_contact_info( confirmed_now, (profile.raw_info or {}).get("_cc")) self.db.add(ev) # 决策A(2026-08-18): 自动结束移除——会话永不因评估结果结束; # evaluated 事件保留但 ended 恒为 False(客户端协议不变)。 await self.db.commit() # 询盘推送(设计 8.1): 主事务提交后才派生后台任务——payload 内存 # 传递,任务不读库只写结果;fire 为同步函数,纳秒级返回不阻塞。 # session_factory 随任务传递: 写回本租户的库(Task 5b);config_data # 同随任务传递(Task 9: 重试矩阵参数走租户配置) lead_push_service.fire_pending_pushes( pending_pushes, self.session_factory, config_data=self.runtime.config.data) yield { "type": "evaluated", "ended": False, "intent_level": evaluation.get("intent_level", "pending"), } async def _get_or_init_evaluation(self, conv_id: str) -> Evaluation: result = await self.db.execute( select(Evaluation).where(Evaluation.conversation_id == conv_id) ) ev = result.scalar_one_or_none() if not ev: ev = Evaluation( conversation_id=conv_id, intent_level=IntentLevel.pending, contact_info={}, ) self.db.add(ev) await self.db.flush() return ev async def _recently_emailed_canons(self) -> set[str]: cutoff = datetime.now(timezone.utc) - timedelta(hours=24) # 只取需要的列;🔴 禁止加 LIMIT——完整 24h 窗口才正确。 # Task 6 双保险: join 画像取历史会话的 _cc——各渠道 e164 的 canon # 一并入集(快照存裸号原文+尾注,客户以 + 前缀完整形态回访同号时 # 仍要命中,否则回访退化成全量询盘)。 result = await self.db.execute( select(Evaluation.contact_info, CustomerProfile.raw_info) .outerjoin( CustomerProfile, CustomerProfile.conversation_id == Evaluation.conversation_id) .where( Evaluation.email_sent.is_(True), Evaluation.evaluated_at >= cutoff, ) ) seen: set[str] = set() for contact_info, raw_info in result: for v in (contact_info or {}).values(): if v: seen.add(canon(str(v))) for state in ((raw_info or {}).get("_cc") or {}).values(): e164 = str((state or {}).get("e164") or "") if e164: seen.add(canon(e164)) return seen async def _cc_round_end( self, conv: Conversation, profile: CustomerProfile, cc_reply: dict | None, cc_wall_fired: bool = False, pre_turn_country: str | None = None, ) -> None: """轮末 cc 钩子(spec §6-2): 联系方式四层合并后、D1 邮件前调用。 - 首问轮免计免消费(P1+P2 一体修复,2026-10-08 真实验收): 轮前 新建的等待态 = 回显/追问**首次发出轮**——客户本轮还没机会回应 确认句,轮末既不消耗 attempts 也不消费 cc_reply(extractor 对 "确认句排给号消息之后"历史的任何回应分类必是误判,P2);attempts 从等待回应轮起计(报国/不理睬轮才递增)——修复前裸号轮轮末即耗 attempts=1,报国轮 country 分支消费到 2 直落 fallback,重算的 e164 永无回显确认机会(P1)。判据 = 本轮墙确有触发(cc_wall_fired) 且状态尚未标记 asked——统一覆盖轮前新建与轮末补建两条建态路径 的首个墙轮(补建态当轮无墙,首问轮顺延到下轮)。 - cc_reply 消费(双门控 Python 侧): 仅 whatsapp 组等待态(cc_due)消费 ——无回应/漏填也推进(attempts 随轮递增,达上限落定 fallback); 落定态仅开迟到 country 升级口: 客户主动报国(非空 country)且 source 非 no_ip 耗尽 → transit 重算 e164(客户主动给的信息不 丢弃);迟到 affirm 不升级(对已标"未经确认"旧号的确认语义模糊, confirmed 态更不重算——客户改主意请重发完整号,走 canon 重置)。 - P4'(2026-10-08 复验)画像报国信号兜底: extractor 对"画像已记、 客户重复陈述"倾向漏填 cc_reply(复验 2/2 稳定复现),报国不能赌 分类——等待态(cc_due)且非首问轮,本轮画像"目标国家"**新现或值 变化**(与轮前快照 pre_turn_country 比对,占位值不算)→ 视为 country 信号,name_to_region 转 ISO 后走 transit country 分支 (与 cc_reply.country 同路径)。cc_reply 显式分类优先(reply 已定 不介入);国名不识别 → 忽略(不重算,该轮按无回应语义消耗)。 - canon 变化(换号/号消失)→ RESET 删组状态。 - 补建 pass: 对最终联系方式重跑判定树(_cc_pre_turn)——本轮才经 extractor 入管道的裸号/换号后的新号当场建状态,不下轮补课。 - Task 9: contact.cc_completion=False → 整钩子跳过(轮前判定树 已不建态,此处不消费不推进;国名映射查表带租户 extras)。 """ if not self._contact_flags["cc_completion"]: return original_cc = (profile.raw_info or {}).get("_cc") ip_iso = ip_service.resolve_region_code( (conv.client_info or {}).get("ip")) raw = dict(profile.raw_info or {}) confirmed_end, _ = split_validate(normalize_contacts(raw.get("联系方式"))) wa_canon_end = digits_only(str(confirmed_end.get("whatsapp") or "")) cc_map = dict(raw.get("_cc") or {}) state = cc_map.get("whatsapp") # 首问轮: cc_wall_fired ⇔ 轮前等待态(墙必触发);asked 标记由本钩子 # 独占管理(cc_completion 不感知),transit 的 dict 拷贝天然携带。 # canon 分支在其后——首问轮遇换号仍以 RESET 优先,标记随旧态作废。 first_ask = (state is not None and cc_wall_fired and not state.get("asked") and cc_completion.cc_due(state)) reply = None if isinstance(cc_reply, dict) and not first_ask: country = str(cc_reply.get("country") or "").strip() if cc_reply.get("affirm") is not None or country: if cc_completion.cc_due(state): reply = cc_reply elif (state is not None and not state.get("confirmed") and country and state.get("source") != "no_ip"): reply = cc_reply # 迟到 country 升级口 # P4' 画像报国信号兜底(仅 cc_reply 未消费时介入): raw 此时已是 # extractor 合并后的本轮终态,"目标国家"新现/值变化 = 客户本轮 # 陈述了新国家——确定性信号,不赌 extractor 是否把它分类进 cc_reply if (reply is None and not first_ask and cc_completion.cc_due(state)): signal = _country_signal(raw.get("目标国家"), pre_turn_country) if signal and cc_completion.name_to_region( signal, extras=self._region_extras): reply = {"affirm": False, "country": signal} if state is not None: if not wa_canon_end or wa_canon_end != str(state.get("canon") or ""): cc_map.pop("whatsapp", None) # 换号/号消失 → RESET elif first_ask: cc_map["whatsapp"] = {**state, "asked": True} # 首问轮免计 elif reply is not None or cc_completion.cc_due(state): cc_map["whatsapp"] = cc_completion.transit( state, reply, extras=self._region_extras) if cc_map: raw["_cc"] = cc_map else: raw.pop("_cc", None) _cc_pre_turn(raw, confirmed_end, ip_iso) if raw.get("_cc") != original_cc: profile.raw_info = raw self.db.add(profile) async def _maybe_send_lead_email( self, conv: Conversation, profile: CustomerProfile, evaluation: dict, evaluated: bool = True, pending_pushes: list[LeadPushLog] | None = None, ) -> None: """D1: 联系方式是发邮件的唯一条件。confirmed 才触发;suspect 只进提醒。 evaluated=False 表示本轮跳过了 GLM 评估(<3条客户消息)——此时邮件 intent_level 必须传空串(→[未评估]),不得把客户端事件用的 "pending" 透传成 [待确认](D2 两者语义不同)。 """ contacts_all = normalize_contacts((profile.raw_info or {}).get("联系方式")) confirmed, _suspect = split_validate(contacts_all) if not confirmed: return # Task 6(spec §5): 出站渲染取 _cc(首封补全号/标注/主题行/推送派生); # 轮末钩子已保证 _cc 与最终联系方式同 canon 同步 cc_map = (profile.raw_info or {}).get("_cc") or {} ev = await self._get_or_init_evaluation(conv.id) if not ev.email_sent: # S3: 任一值已见于24h内其他会话 → 轻提醒;否则全量。 # Task 6 双保险: 比对候选集含 _cc.e164 的 canon(见 _channel_canons) # Task 9: 邮件/推送参数走租户配置(config_data 透传给 resolve_*) seen = await self._recently_emailed_canons() if any(cands & seen for cands in _channel_canons(confirmed, cc_map).values()): await self._collect_push( pending_pushes, ev, conv, profile, confirmed, "returning", evaluation, evaluated) sent = await email_service.send_returning_lead_email( confirmed, cc_info=cc_map, config_data=self.runtime.config.data) else: await self._collect_push( pending_pushes, ev, conv, profile, confirmed, "lead", evaluation, evaluated) messages = await self._load_history(conv.id) sent = await email_service.send_lead_email( customer_profile=profile.raw_info or {}, contact_info=confirmed, reasoning=evaluation.get("reasoning", ""), conversation_messages=messages, intent_level=evaluation.get("intent_level", "") if evaluated else "", cc_info=cc_map, config_data=self.runtime.config.data, ) if sent: ev.email_sent = True ev.contact_info = _panel_contact_info(confirmed, cc_map) self.db.add(ev) else: old_canons = {canon(str(v)) for v in (ev.contact_info or {}).values()} # Task 6 双保险: 新值候选集含 _cc.e164 的 canon——确认落定 # (号码未变)不补发更正;真换号(两组候选都不在旧集)才走更正 if any(not (cands & old_canons) for cands in _channel_canons(confirmed, cc_map).values()): if ev.correction_count < 3: count = ev.correction_count + 1 await self._collect_push( pending_pushes, ev, conv, profile, confirmed, "correction", evaluation, evaluated) if await email_service.send_correction_email( confirmed, count=count, cc_info=cc_map, config_data=self.runtime.config.data): ev.correction_count = count ev.contact_info = _panel_contact_info(confirmed, cc_map) self.db.add(ev) else: # D4'(2026-08-18): 锁邮件不锁快照 —— 上限已到, # admin 仍要看到客户最新号码 ev.contact_info = _panel_contact_info(confirmed, cc_map) self.db.add(ev) async def _collect_push( self, pending, ev, conv, profile, confirmed, push_type, evaluation, evaluated, ) -> None: """询盘推送派发(设计 §8): 触发条件=进入发信分支,与 SMTP 成败解耦。 dispatch 内部吞异常(失败只记日志),这里无需再兜。config_data = 租户配置(Task 9: 开关/前缀走 config, 空槽回退 env)。 """ log = await lead_push_service.dispatch_lead_push( self.db, ev, conv, profile, confirmed, push_type, evaluation, evaluated, config_data=self.runtime.config.data, ) if log is not None and pending is not None: pending.append(log) async def _load_history(self, conv_id: str) -> list[dict]: result = await self.db.execute( select(Message) .where(Message.conversation_id == conv_id) .order_by(Message.created_at) ) messages = result.scalars().all() return [{"role": m.role.value, "content": m.content} for m in messages] async def _get_profile(self, conv_id: str) -> CustomerProfile: result = await self.db.execute( select(CustomerProfile).where(CustomerProfile.conversation_id == conv_id) ) return result.scalar_one() @staticmethod def _enrich_short_message(content: str, raw_info: dict, history: list[dict] | None = None) -> str: """Enrich short user messages with conversation context. Two sources: extractor output (primary), last substantive user message (fallback when extractor hasn't run yet). """ if len(content.strip()) >= 30: return content facts = [] # Primary: extractor output if raw_info: facts = [f"{k}: {v}" for k, v in raw_info.items() if v and not str(k).startswith("_") and k != "联系方式"] # Fallback: use last substantive user message as context if not facts and history: for msg in reversed(history[:-1]): if msg.get("role") == "user" and len(msg.get("content", "").strip()) >= 5: facts.append("客户之前说: " + msg["content"][:80]) break if not facts: return content return ( content + "\n\n【系统上下文 - 系统标注，不要向客户提及】已知: " + " | ".join(facts) + "。不要重复询问这些已确认的信息！" ) @staticmethod def _build_context_reminder(raw_info: dict, latest_msg: str, history: list[dict] | None = None, source: str = "", contact_flags: dict | None = None, wall: CompiledWall | None = None) -> str: """Build a context reminder from extracted profile info. Task 4 词表数据化: 六类轮中提醒话术(boundary/contact_ask/ language_follow/lead_given/cc_guide/email_light)的数据源 = 墙 reminders(seed_profiles//wall.json); {shown}/{no_contact_web}/{no_contact_already} 占位由本函数 .format() 回填,值与数据化前逐字等价。 contact_flags(Task 9): contact 行为开关——cc_completion=False 跳过 cc 确认指引,email_light_ask=False 跳过邮箱轻补;None = 全开 (直调本函数的旧测试语义)。 wall(C-1 终审): 租户编译墙(触发词/提醒话术/no_contact 全走它); None = 模块级默认墙(直调/旧测试语义——BOUNDARY_TRIGGER_RE 等 模块常量即该默认视图)。""" w = wall if wall is not None else DEFAULT_WALL # 职能边界提醒(评审#7: 前置到早退之前,首条消息画像为空也要生效) boundary_note = "" if w.triggers["boundary"].search(latest_msg or ""): if w.triggers["budget"].search(latest_msg or ""): # 评审#9: 预算求推荐 → 预算路径(推荐+反问+引导),不一刀切要号 boundary_note = w.reminders["boundary"]["budget"] else: boundary_note = w.reminders["boundary"]["normal"] # 联系方式状态前移(供 boundary/contact 提醒共用判定) contacts_all = normalize_contacts(raw_info.get("联系方式")) confirmed, suspect = split_validate(contacts_all) # 索要我方联系方式提醒(15.2): 与 boundary_note 同样前移到早退之前, # 空画像首条消息也要生效;按 source 分支(widget/standalone 有按钮, app 无)。 # 冒烟实证: 抽象指令("用App话术")GLM 会无视并背 prompt 里更显眼的 web 脚本—— # 提醒必须携带该分支的逐字话术,不让模型自己挑。 contact_note = "" if w.triggers["contact_ask"].search(latest_msg or ""): if source == "app": if confirmed or suspect: # 已留资: 索要我方联系方式 → 逐字"经理主动联系"版, # 与"禁止再索要"提醒不再打架 # Task 3 收尾: 第三处禁令同步改写(禁令集完整)——与前两处 # 同语义,只禁已提供过的渠道,缺失渠道放行轻补一次 contact_note = w.reminders["contact_ask"]["app_already"] else: contact_note = w.reminders["contact_ask"]["app"] else: contact_note = w.reminders["contact_ask"]["web"].format( no_contact_web=w.no_contact["web"]) # 语言跟随提醒(Task 11): 与 boundary/contact 提醒同挂载位—— # 首条消息画像为空也要生效(中文客户开场即漂英文是实测重灾区) lang_note = _lang_note_for(latest_msg, wall=wall) if not raw_info: # 空画像:仅返回边界/联系/语言提醒(可能为空串) return "\n".join(x for x in (boundary_note, contact_note, lang_note) if x) parts = ["[上下文提醒 - 这是一条系统指令，绝对不要向客户提及这段内容]"] parts.append("客户已明确告知以下信息，你绝对不能再问这些：") for key, val in raw_info.items(): if str(key).startswith("_") or key == "联系方式": continue # 内部状态与联系方式单独渲染 if val: parts.append(f"{key}: {val}") # Task 9: contact 行为开关注入本函数(staticmethod 保持旧直调签名, # None = 全开);cc 确认指引与邮箱轻补按开关短路 flags = (contact_flags if contact_flags is not None else resolve_contact_flags(None)) # Task 3(spec §4.2/§4.3b): 邮箱轻补注入(cc 分支已删,判定树接管号码 # 区号补全——确认提醒由 cc_due 驱动,Task 4 接)。计数键(_marks)此处 # 弃用: 本函数是 staticmethod 收内存副本,写回由 stream 调用方以同参 # 调用纯函数取回并落库(纯函数保证两处判定不漂移)。计算前移到 # confirmed 块之前: 未落定轮邮箱轻补不注入(cc_settled 串行)。 completion_note, _marks = _contact_completion_note( raw_info, confirmed, suspect, lang="zh" if _CJK_RE.search(latest_msg or "") else "en", email_ask=flags["email_light_ask"], wall=wall) # Task 4(spec §4 回显确认轮): cc 等待态注入确认句指引——有 e164 用 # 回显模板(逐字 intl),no_ip 用 ASK 追问句;与邮箱轻补 cc_settled # 串行互斥,两个"逐字使用这句"永不同轮。无计数键: 轮次上限由状态机 # attempts 管理(轮末 transit 递增),提醒每轮等待态都在场。 # P3: 语言路由扩 ES(_cc_lang_of),西语轮注入西语模板。 cc_note = (_cc_confirm_note( (raw_info.get("_cc") or {}).get("whatsapp"), _cc_lang_of(latest_msg), wall=wall) if flags["cc_completion"] else "") # 联系方式专项(D6) 与 职能边界(D6联动) if confirmed: shown = ", ".join( f"{k}: {' '.join(str(v).split())[:60]}" for k, v in confirmed.items()) # 逐字话术直接引用墙 no_contact["already"](Task 9 收口: # 视图直取单一事实源)——与零号码墙替换句同源,三处"经理主动联系" # 话术不漂移 # Task 3 防自锁改写(spec 4.1-6): 原"绝对禁止再索要任何联系方式！" # 会抑制缺失渠道轻补——只禁已提供过的渠道,缺失渠道放行一次 parts.append(w.reminders["lead_given"]["forbidden"].format( shown=shown)) parts.append(w.reminders["lead_given"]["respond_script"].format( no_contact_already=w.no_contact["already"])) if boundary_note: parts.append(boundary_note) # Task 3 防自锁改写: 尾部补缺失渠道豁免(与上方改写同因) parts.append(w.reminders["lead_given"]["boundary_tail"]) elif suspect: shown = ", ".join( f"{k}: {' '.join(str(v).split())[:60]}" for k, v in suspect.items()) parts.append(w.reminders["lead_given"]["suspect"].format( shown=shown)) if boundary_note: parts.append(boundary_note) if boundary_note and not confirmed and not suspect: parts.append(boundary_note) # 未留资:边界提醒引导留资(职能边界话术自带) # Task 4 cc 确认指引注入(与下方邮箱轻补互斥——cc_due vs cc_settled) if cc_note: parts.append(cc_note) # Task 3 轻补注入(计算已前移到 confirmed 块之前;cc_settled 未落定时 # note 为空,天然不注入) if completion_note: parts.append(completion_note) # 15.2: 索要我方联系方式提醒注入(镜像 boundary_note 的挂载位)。 # 互留提示仅限 web 来源且客户未留资(confirmed/suspect 都算"已留"); # App 的反向留资话术本身就是主话术,不再叠加 if contact_note: note = contact_note if source != "app" and not confirmed and not suspect: note += "客户尚未留过联系方式，可顺势轻问一句（每会话最多一次）。" parts.append(note) if len(latest_msg.strip()) < 25: parts.append("⚠️ 客户发的是短消息！必须结合上面已知信息来理解，绝对不能当作独立问题！") if lang_note: parts.append(lang_note) return "\n".join(parts)