refactor: migrate workflow to v2 core and archive legacy modules

utils/daily_summary.py

@@ -1,300 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-每日聊天汇总定时任务
-- 每天 23:50 自动统计当日各店铺数据
-- 用 AI 生成自然语言摘要
-- 发送到企业微信 Webhook + QQ 邮件
-"""
-
-import asyncio
-import os
-import json
-import logging
-from datetime import datetime, date, timedelta
-from typing import Optional
-
-import httpx
-from dotenv import load_dotenv
-
-load_dotenv()
-logger = logging.getLogger("cs_agent")
-
-WECHAT_WEBHOOK = os.getenv("WECHAT_WEBHOOK", "")
-SUMMARY_EMAIL  = os.getenv("SUMMARY_EMAIL", "")   # 收摘要的邮箱
-SEND_HOUR      = int(os.getenv("SUMMARY_HOUR", "23"))
-SEND_MINUTE    = int(os.getenv("SUMMARY_MINUTE", "50"))
-
-
-# ──────────────────────────────────────────
-# 统计数据整理
-# ──────────────────────────────────────────
-
-def _build_stats_text(target_date: str = "") -> str:
-    """整理今日数据，返回给 AI 的原始统计文本"""
-    from db import chat_log_db as db
-    from db.deal_outcome_db import get_daily_summary
-
-    if not target_date:
-        target_date = datetime.now().strftime("%Y-%m-%d")
-
-    stats   = db.get_daily_stats(target_date)
-    convs   = db.get_daily_conversations(target_date)
-    deal_sum = get_daily_summary(target_date)
-
-    if not stats:
-        return f"{target_date} 当日无任何聊天记录。"
-
-    # 按 acc_id 分组对话片段
-    conv_map: dict[str, list] = {}
-    for c in convs:
-        aid = c.get("acc_id") or "未知店铺"
-        conv_map.setdefault(aid, []).append(c)
-
-    lines = [f"【{target_date} 各店铺数据】\n"]
-
-    # 成交/未成交汇总（供 AI 摘要与数据分析）
-    lines.append("【成交与未成交】")
-    lines.append(f"  成交：{deal_sum['成交数']} 笔，金额 {deal_sum['成交金额']:.0f} 元")
-    lines.append(f"  未成交：{deal_sum['未成交数']} 笔")
-    if deal_sum["未成交原因分布"]:
-        for reason, cnt in deal_sum["未成交原因分布"].items():
-            lines.append(f"    - {reason}：{cnt} 笔")
-    if deal_sum["成交明细"]:
-        for o in deal_sum["成交明细"][:5]:
-            r = "让价后" if o.get("discount_given") else "直接"
-            lines.append(f"    ✓ {o.get('customer_name', '')[:6]} {r}成交 {o.get('amount', 0):.0f}元")
-    if deal_sum["未成交明细"]:
-        for o in deal_sum["未成交明细"][:5]:
-            lines.append(f"    ✗ {o.get('customer_name', '')[:6]} {o.get('reason', '')}")
-    lines.append("")
-
-    for s in stats:
-        acc  = s.get("acc_id") or "未知店铺"
-        plat = s.get("platform") or ""
-        label = f"{acc}（{plat}）" if plat else acc
-
-        lines.append(f"▶ 店铺：{label}")
-        lines.append(f"  接待客户：{s['unique_customers']} 人，共 {s['total_msgs']} 条消息（收 {s['recv']} 发 {s['sent']}）")
-        lines.append(f"  首条：{(s.get('first_msg') or '')[-8:-3]}  末条：{(s.get('last_msg') or '')[-8:-3]}")
-
-        shop_convs = conv_map.get(acc, [])
-        for c in shop_convs[:6]:   # 最多展示6个客户片段
-            name = c.get("customer_name") or c.get("customer_id", "")[:8]
-            snippet = (c.get("snippet") or "")[:120]
-            lines.append(f"  · {name}（{c['msg_count']}条）{snippet}")
-        if len(shop_convs) > 6:
-            lines.append(f"  ... 还有 {len(shop_convs)-6} 位客户")
-        lines.append("")
-
-    return "\n".join(lines)
-
-
-# ──────────────────────────────────────────
-# AI 生成摘要
-# ──────────────────────────────────────────
-
-async def _ai_summary(raw_text: str) -> str:
-    """调用 AI 把统计文本转成自然语言日报"""
-    try:
-        from openai import AsyncOpenAI
-        client = AsyncOpenAI(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            base_url=os.getenv("OPENAI_BASE_URL"),
-        )
-        model = os.getenv("OPENAI_MODEL", "doubao-seed-2-0-lite-260215")
-        resp = await client.chat.completions.create(
-            model=model,
-            messages=[
-                {
-                    "role": "system",
-                    "content": (
-                        "你是一名电商运营助理。根据下面的客服聊天数据，"
-                        "为老板写一份简洁的当日运营日报（200字以内）。"
-                        "要包含：接待总人数、各店铺情况、有无成交或异常情况。"
-                        "语气轻松，像发给老板的微信消息，不需要标题。"
-                    ),
-                },
-                {"role": "user", "content": raw_text},
-            ],
-            max_tokens=300,
-            temperature=0.5,
-        )
-        return resp.choices[0].message.content.strip()
-    except Exception as e:
-        # AI 失败就直接返回原始统计
-        return raw_text
-
-
-# ──────────────────────────────────────────
-# 推送：企业微信
-# ──────────────────────────────────────────
-
-async def _send_wechat(content: str):
-    """推送到企业微信群机器人（markdown 格式，单条 ≤4096 字节自动分段）"""
-    if not WECHAT_WEBHOOK:
-        logger.info("[DailySummary] 未配置 WECHAT_WEBHOOK，跳过推送")
-        return
-
-    # 企业微信单条 markdown 限 4096 字节，超长自动分段
-    encoded = content.encode("utf-8")
-    chunks = []
-    while encoded:
-        chunk = encoded[:3800].decode("utf-8", errors="ignore")
-        chunks.append(chunk)
-        encoded = encoded[len(chunk.encode("utf-8")):]
-
-    async with httpx.AsyncClient(timeout=10) as client:
-        for i, chunk in enumerate(chunks):
-            payload = {"msgtype": "markdown", "markdown": {"content": chunk}}
-            try:
-                resp = await client.post(WECHAT_WEBHOOK, json=payload)
-                data = resp.json()
-                if data.get("errcode") == 0:
-                    logger.info("[DailySummary] 企业微信推送成功（第%s段）", i + 1)
-                else:
-                    logger.warning("[DailySummary] 企业微信推送失败: %s", data)
-            except Exception as e:
-                logger.exception("[DailySummary] 企业微信推送异常: %s", e)
-
-
-# ──────────────────────────────────────────
-# 推送：邮件
-# ──────────────────────────────────────────
-
-def _send_email(subject: str, body: str):
-    """发送日报邮件"""
-    if not SUMMARY_EMAIL:
-        return
-    try:
-        from mail.email_sender import email_sender
-        import smtplib
-        from email.mime.text import MIMEText
-        from email.header import Header
-
-        msg = MIMEText(body, "plain", "utf-8")
-        msg["Subject"] = Header(subject, "utf-8").encode()
-        msg["From"]    = f"{Header(email_sender.sender_name, 'utf-8').encode()} <{email_sender.smtp_user}>"
-        msg["To"]      = SUMMARY_EMAIL
-
-        with smtplib.SMTP(email_sender.smtp_host, email_sender.smtp_port) as s:
-            s.starttls()
-            s.login(email_sender.smtp_user, email_sender.smtp_password)
-            s.sendmail(email_sender.smtp_user, [SUMMARY_EMAIL], msg.as_string())
-        logger.info("[DailySummary] 日报邮件已发送至 %s", SUMMARY_EMAIL)
-    except Exception as e:
-        logger.exception("[DailySummary] 日报邮件发送失败: %s", e)
-
-
-# ──────────────────────────────────────────
-# 企业微信 Markdown 排版
-# ──────────────────────────────────────────
-
-def _build_wechat_markdown(title: str, ai_text: str, raw_text: str, target_date: str = "") -> str:
-    """
-    构建符合企业微信规范的 markdown 内容。
-    支持：**bold**、<font color="...">、> 引用、``` 代码块、- 列表
-    不支持：<details>、<summary>、HTML 标签（除 font/br）
-    """
-    from db import chat_log_db as db
-    from db.deal_outcome_db import get_daily_summary
-    date = target_date or datetime.now().strftime("%Y-%m-%d")
-    stats = db.get_daily_stats(date)
-    deal_sum = get_daily_summary(date)
-
-    lines = [f"## {title}\n"]
-
-    # AI 摘要部分
-    lines.append("> " + ai_text.replace("\n", "\n> "))
-    lines.append("")
-
-    # 成交/未成交
-    lines.append("**📈 成交与未成交**")
-    lines.append(f"- 成交 **{deal_sum['成交数']}** 笔 · 金额 **{deal_sum['成交金额']:.0f}** 元")
-    lines.append(f"- 未成交 **{deal_sum['未成交数']}** 笔")
-    if deal_sum["未成交原因分布"]:
-        for reason, cnt in deal_sum["未成交原因分布"].items():
-            lines.append(f"  - {reason}：{cnt} 笔")
-    lines.append("")
-
-    # 各店铺数据表格（企业微信不支持 | 表格，用列表代替）
-    if stats:
-        lines.append("**📋 各店铺明细**")
-        for s in stats:
-            acc   = s.get("acc_id") or "未知店铺"
-            plat  = s.get("platform") or ""
-            label = f"{acc}（{plat}）" if plat else acc
-            first = (s.get("first_msg") or "")[-8:-3]
-            last  = (s.get("last_msg")  or "")[-8:-3]
-            lines.append(
-                f"- <font color=\"info\">{label}</font>  "
-                f"接待 **{s['unique_customers']}** 人 · "
-                f"消息 {s['total_msgs']} 条（收{s['recv']}/发{s['sent']}）"
-                f"  {first}~{last}"
-            )
-    lines.append("")
-    lines.append(f"<font color=\"comment\">发送时间：{datetime.now().strftime('%H:%M:%S')}</font>")
-
-    return "\n".join(lines)
-
-
-# ──────────────────────────────────────────
-# 主入口：生成并推送日报
-# ──────────────────────────────────────────
-
-async def send_daily_summary(target_date: str = ""):
-    """生成并推送当日汇总"""
-    if not target_date:
-        target_date = datetime.now().strftime("%Y-%m-%d")
-
-    logger.info("[DailySummary] 开始生成 %s 日报...", target_date)
-
-    raw_text = _build_stats_text(target_date)
-    ai_text  = await _ai_summary(raw_text)
-    title    = f"📊 {target_date} 客服日报"
-
-    # ── 企业微信 markdown（不支持 <details>，用标准语法）──
-    wechat_md = _build_wechat_markdown(title, ai_text, raw_text, target_date)
-    await _send_wechat(wechat_md)
-
-    # ── 邮件：纯文本 ──
-    email_body = f"{ai_text}\n\n{'='*40}\n\n{raw_text}"
-    _send_email(title, email_body)
-
-    logger.info("[DailySummary] 日报推送完成")
-    return ai_text
-
-
-# ──────────────────────────────────────────
-# 定时调度（由 websocket_client 启动）
-# ──────────────────────────────────────────
-
-async def scheduler():
-    """每天 SEND_HOUR:SEND_MINUTE 触发日报"""
-    logger.info("[DailySummary] 定时日报已启动，发送时间 %02d:%02d", SEND_HOUR, SEND_MINUTE)
-    sent_today: Optional[str] = None   # 记录已发日期，防重复
-
-    while True:
-        now  = datetime.now()
-        today = now.strftime("%Y-%m-%d")
-
-        if now.hour == SEND_HOUR and now.minute == SEND_MINUTE and sent_today != today:
-            sent_today = today
-            try:
-                await send_daily_summary(today)
-            except Exception as e:
-                logger.exception("[DailySummary] 日报生成出错: %s", e)
-
-        # 每 30 秒检查一次
-        await asyncio.sleep(30)
-
-
-# ──────────────────────────────────────────
-# 命令行手动触发
-# ──────────────────────────────────────────
-
-if __name__ == "__main__":
-    import sys
-    target = sys.argv[1] if len(sys.argv) > 1 else ""
-    result = asyncio.run(send_daily_summary(target))
-    logger.info("\n=== AI 摘要 ===")
-    logger.info(result)

utils/intent_analyzer.py

@@ -1,159 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-语义匹配 - 用 embedding 做意图/情绪识别
-配置 EMBEDDING_MODEL 后启用，否则回退到关键词
-"""
-import os
-import logging
-from dataclasses import dataclass
-from typing import Optional
-
-logger = logging.getLogger(__name__)
-
-# 意图模板（用于 embedding 相似度匹配）
-INTENT_TEMPLATES = {
-    "询价": "我想问一下价格多少钱",
-    "发图": "我发图给你看看",
-    "砍价": "能不能便宜点太贵了",
-    "批量": "我要做很多张图批量",
-    "加急": "能不能快点很急",
-    "售后": "已经付款了什么时候好",
-    "修改": "不满意要改一下",
-    "转接": "我要退款投诉",
-    "打招呼": "你好在吗有人吗",
-}
-EMOTION_TEMPLATES = {
-    "平静": "好的谢谢",
-    "着急": "快点啊很急",
-    "不满": "怎么这么慢不满意",
-    "砍价": "太贵了便宜点",
-}
-
-
-_template_embeddings: dict = {}
-
-
-@dataclass
-class IntentDecision:
-    intent: str = ""
-    source: str = "none"  # embedding / keyword / none
-    score: float = 0.0
-
-def _get_embedding(text: str, cache_key: str = None) -> Optional[list]:
-    """调用 embedding API，失败返回 None。cache_key 用于缓存模板向量"""
-    model = os.getenv("EMBEDDING_MODEL", "")
-    if not model:
-        return None
-    if cache_key and cache_key in _template_embeddings:
-        return _template_embeddings[cache_key]
-    try:
-        from openai import OpenAI
-        client = OpenAI(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            base_url=os.getenv("OPENAI_BASE_URL"),
-        )
-        resp = client.embeddings.create(model=model, input=text[:2000])
-        emb = resp.data[0].embedding
-        if cache_key:
-            _template_embeddings[cache_key] = emb
-        return emb
-    except Exception as e:
-        logger.debug(f"embedding 失败: {e}")
-        return None
-
-
-def _cosine_sim(a: list, b: list) -> float:
-    if not a or not b or len(a) != len(b):
-        return 0.0
-    dot = sum(x * y for x, y in zip(a, b))
-    na = sum(x * x for x in a) ** 0.5
-    nb = sum(y * y for y in b) ** 0.5
-    if na == 0 or nb == 0:
-        return 0.0
-    return dot / (na * nb)
-
-
-def detect_intent_embedding(msg: str) -> Optional[str]:
-    """用 embedding 检测意图，未配置或失败返回 None。"""
-    decision = detect_intent_embedding_decision(msg)
-    return decision.intent or None
-
-
-def detect_intent_embedding_decision(msg: str) -> IntentDecision:
-    """返回 embedding 意图决策（含分值）。"""
-    msg_emb = _get_embedding(msg)
-    if not msg_emb:
-        return IntentDecision()
-    best_intent, best_score = "", 0.0
-    for intent, template in INTENT_TEMPLATES.items():
-        tpl_emb = _get_embedding(template, cache_key=f"intent_{intent}")
-        if not tpl_emb:
-            continue
-        sim = _cosine_sim(msg_emb, tpl_emb)
-        if sim > best_score:
-            best_score = sim
-            best_intent = intent
-    if best_score > 0.6:
-        return IntentDecision(intent=best_intent, source="embedding", score=float(best_score))
-    return IntentDecision()
-
-
-def detect_emotion_embedding(msg: str) -> Optional[str]:
-    """用 embedding 检测情绪"""
-    msg_emb = _get_embedding(msg)
-    if not msg_emb:
-        return None
-    best_emotion, best_score = "", 0.0
-    for emotion, template in EMOTION_TEMPLATES.items():
-        tpl_emb = _get_embedding(template, cache_key=f"emotion_{emotion}")
-        if not tpl_emb:
-            continue
-        sim = _cosine_sim(msg_emb, tpl_emb)
-        if sim > best_score:
-            best_score = sim
-            best_emotion = emotion
-    return best_emotion if best_score > 0.55 else None
-
-
-def detect_intent_keywords(msg: str) -> str:
-    """关键词回退：无 embedding 时使用"""
-    m = (msg or "").strip().lower()
-    if any(k in m for k in ["退款", "退货", "投诉"]):
-        return "转接"
-    if any(k in m for k in ["多张", "批量", "很多", "几十张"]):
-        return "批量"
-    if any(k in m for k in ["快点", "加急", "很急", "着急"]):
-        return "加急"
-    if any(k in m for k in ["便宜", "贵", "少点", "打折"]):
-        return "砍价"
-    if any(k in m for k in ["改", "修改", "不满意"]):
-        return "修改"
-    if any(k in m for k in ["多少钱", "价格", "报价", "多钱", "收费", "怎么收费", "咋收费"]):
-        return "询价"
-    if any(k in m for k in ["在吗", "你好", "有人"]):
-        return "打招呼"
-    return ""
-
-
-def detect_intent(msg: str) -> IntentDecision:
-    """
-    AI 意图判定 + 规则兜底：
-    1) 有 embedding 配置时先走 embedding。
-    2) 失败/低置信时回退关键词规则。
-    """
-    text = (msg or "").strip()
-    if not text:
-        return IntentDecision()
-
-    try:
-        emb_decision = detect_intent_embedding_decision(text)
-    except Exception:
-        emb_decision = IntentDecision()
-    if emb_decision.intent:
-        return emb_decision
-
-    kw_intent = detect_intent_keywords(text)
-    if kw_intent:
-        return IntentDecision(intent=kw_intent, source="keyword", score=0.0)
-    return IntentDecision()
-

utils/wechat_chat_log.py

@@ -1,150 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-客服对话推送到企业微信群 - 客户消息与AI回复成对发送，保持上下文
-"""
-import asyncio
-import os
-import logging
-from datetime import datetime
-
-import httpx
-from dotenv import load_dotenv
-
-load_dotenv()
-logger = logging.getLogger("cs_agent")
-
-_last_push: dict[tuple[str, str], tuple[str, str, float]] = {}
-
-def _get_webhook() -> str:
-    """优先从 config 读取，与健康检查/日报保持一致"""
-    try:
-        from config.config import WECHAT_WEBHOOK
-        return WECHAT_WEBHOOK or os.getenv("WECHAT_WEBHOOK", "")
-    except Exception:
-        return os.getenv("WECHAT_WEBHOOK", "")
-
-
-def _truncate(text: str, max_len: int = 200) -> str:
-    """截断过长内容"""
-    if not text:
-        return ""
-    text = str(text).strip()
-    if len(text) > max_len:
-        return text[:max_len] + "..."
-    return text
-
-
-def _get_recent_conversation(customer_id: str, acc_id: str, last_n: int = 8) -> list:
-    """获取近期对话（同店铺），保持连贯上下文"""
-    try:
-        from db.chat_log_db import get_recent_conversation
-        return get_recent_conversation(customer_id, acc_id, limit=last_n)
-    except Exception:
-        logger.debug("[WechatChatLog] 获取近期对话失败，返回空列表", exc_info=True)
-        return []
-
-
-async def push_chat_to_wechat(
-    customer_name: str,
-    customer_id: str,
-    acc_id: str,
-    customer_msg: str,
-    reply_msg: str,
-    goods_name: str = "",
-):
-    """
-    将客户消息与AI回复推送到企业微信群，附带近期对话保持连贯。
-    """
-    webhook = _get_webhook()
-    if not webhook:
-        return
-    # 去重：同一客户+店铺，若客户消息与回复完全相同且在窗口期内，则跳过
-    try:
-        import time
-        key = (customer_id or "", acc_id or "")
-        now = time.time()
-        last = _last_push.get(key)
-        if last:
-            last_customer_msg, last_reply_msg, last_ts = last
-            if (last_customer_msg or "") == (customer_msg or "") and (last_reply_msg or "") == (reply_msg or ""):
-                if now - last_ts < 30:
-                    return
-        _last_push[key] = ((customer_msg or ""), (reply_msg or ""), now)
-    except Exception:
-        logger.debug("[WechatChatLog] 去重检查异常，忽略本次去重", exc_info=True)
-    reply_msg = _truncate(reply_msg, 300)
-    ts = datetime.now().strftime("%H:%M")
-    shop = acc_id or "未知店铺"
-    name = (customer_name or customer_id or "客户")[:12]
-
-    lines = [f"**📩 {ts} | {shop}**"]
-    if goods_name:
-        lines.append(f"**商品** {_truncate(goods_name, 80)}")
-    if customer_id:
-        lines.append(f"**客户ID** {customer_id}")
-    lines.append("")
-
-    # 附带近期对话，保持连贯
-    recent = _get_recent_conversation(customer_id, acc_id, last_n=8)
-    last_line = None
-    for m in recent:
-        role = customer_id if m.get("direction") == "in" else "客服"
-        msg = _truncate((m.get("message") or "").strip(), 120)
-        if msg:
-            line = f"{role}：{msg}"
-            # 防止日志中的重复记录在企微里连续刷屏
-            if line == last_line:
-                continue
-            lines.append(line)
-            last_line = line
-    # 当前回复（可能已在 recent 中有客户消息，客服回复是新的）
-    lines.append(f"客服：{reply_msg or '(无回复)'}")
-
-    content = "\n".join(lines)
-    enc = content.encode("utf-8")
-    if len(enc) > 3800:
-        content = enc[:3750].decode("utf-8", errors="ignore") + "\n...(略)"
-    try:
-        async with httpx.AsyncClient(timeout=8) as client:
-            resp = await client.post(
-                webhook,
-                json={"msgtype": "markdown", "markdown": {"content": content}},
-            )
-            data = resp.json()
-            if data.get("errcode") == 0:
-                return
-            else:
-                logger.warning("[WechatChatLog] 推送失败: %s", data)
-    except Exception as e:
-        logger.exception("[WechatChatLog] 推送异常: %s", e)
-
-
-async def send_morning_startup():
-    """每天早上8点发送客服启动消息到企微群"""
-    webhook = _get_webhook()
-    if not webhook:
-        return
-    ts = datetime.now().strftime("%Y-%m-%d %H:%M")
-    content = f"**☀️ 客服已启动**\n{ts}"
-    try:
-        async with httpx.AsyncClient(timeout=8) as client:
-            await client.post(
-                webhook,
-                json={"msgtype": "markdown", "markdown": {"content": content}},
-            )
-        logger.info("[WechatChatLog] 早8点启动消息已发送")
-    except Exception as e:
-        logger.exception("[WechatChatLog] 启动消息发送失败: %s", e)
-
-
-async def morning_startup_scheduler():
-    """每天 8:00 发送启动消息"""
-    logger.info("[WechatChatLog] 早8点启动消息定时任务已启动")
-    sent_today = None
-    while True:
-        now = datetime.now()
-        today = now.strftime("%Y-%m-%d")
-        if now.hour == 8 and now.minute == 0 and sent_today != today:
-            sent_today = today
-            await send_morning_startup()
-        await asyncio.sleep(30)