chore: harden runtime checks and split websocket inbound/outbound flows

core/websocket_inbound_flow.py

@@ -0,0 +1,123 @@
+import json
+import logging
+
+logger = logging.getLogger("cs_agent")
+
+
+async def handle_incoming_message(client, message: str, *, shop_type_resolver):
+    """处理单条入站消息（从 websocket_client.py 拆出）。"""
+    timestamp = client.get_time()
+    try:
+        data = json.loads(message)
+
+        # 多进程分片检查：确保同一客户只由一个 worker 处理
+        customer_key = client._customer_key(data)
+        if not client._is_owned_by_this_worker(customer_key):
+            return
+
+        timestamp = client.get_time()
+
+        # 保存最后一条消息用于回复
+        client.last_msg = data
+
+        # 打印格式化的消息
+        logger.info(f"\n{'='*50}")
+        logger.info(f"[{timestamp}] 收到新消息:")
+        logger.info(f"{'='*50}")
+        logger.info(f"  消息ID: {data.get('msg_id', 'N/A')}")
+        logger.info(f"  账号ID: {client.to_chinese(data.get('acc_id', 'N/A'))}")
+        logger.info(f"  发送者ID: {client.to_chinese(data.get('from_id', 'N/A'))}")
+        logger.info(f"  发送者名称: {client.to_chinese(data.get('from_name', 'N/A'))}")
+        logger.info(f"  会话ID: {client.to_chinese(data.get('cy_id', 'N/A'))}")
+        logger.info(f"  平台类型: {data.get('acc_type', 'N/A')}")
+        logger.info(f"  消息类型: {client.get_msg_type_name(data.get('msg_type', 0))}")
+        logger.info(f"  消息内容: {client.to_chinese(data.get('msg', 'N/A'))}")
+
+        # 显示商品信息（如果有）
+        if data.get('goods_name'):
+            logger.info(f"  商品名称: {client.to_chinese(data.get('goods_name', ''))}")
+        if data.get('goods_order'):
+            logger.info(f"  订单信息: {client.to_chinese(data.get('goods_order', ''))}")
+
+        logger.info(f"{'='*50}\n")
+
+        # 消息去重：同一条消息不重复处理
+        msg_id = data.get('msg_id', '')
+        if msg_id and msg_id in client._replied_msg_ids:
+            logger.info(f"重复消息，跳过: {msg_id}")
+            return
+        if msg_id:
+            client._replied_msg_ids.append(msg_id)  # deque 自动淘汰最旧的
+
+        # 空消息/无效消息过滤（N/A 或关键字段全为空）
+        from_id = data.get('from_id', '')
+        acc_id = data.get('acc_id', '')
+        if not from_id or from_id == 'N/A' or not acc_id or acc_id == 'N/A':
+            logger.info(f"[{client.get_time()}] 空消息跳过（from_id={from_id!r} acc_id={acc_id!r}）")
+            return
+        client._log_inbound_once(data)
+        client._fire_and_forget(client._post_tianwang_callback("message_received", data))
+
+        # Gemini 店铺：不回复，直接跳过
+        goods_name = client.to_chinese(data.get('goods_name', '') or '')
+        if shop_type_resolver(acc_id, goods_name) == "gemini_api":
+            logger.info(f"[{client.get_time()}] Gemini 店铺消息，跳过")
+            client._push_chat_to_wechat_safe(
+                data=data,
+                customer_msg=data.get('msg', ''),
+                reply_msg="",
+                goods_name=goods_name,
+                tag="gemini店铺跳过",
+            )
+            return
+
+        # 使用 Agent 自动回复（仅处理文本消息）
+        if client.enable_agent:
+            msg_type = data.get('msg_type', 0)
+            if msg_type == 0:
+                if client._is_transfer_msg(data):
+                    # 会话转交 → 主动打招呼
+                    logger.info(f"[{client.get_time()}] 收到转交消息，发送问候")
+                    greeting = client._pick_transfer_greeting()
+                    await client.send_reply(data, greeting)
+                    client._push_chat_to_wechat_safe(
+                        data=data,
+                        customer_msg=data.get('msg', ''),
+                        reply_msg=greeting,
+                        tag="转交问候",
+                    )
+                elif client._is_shop_card(data):
+                    # 进店卡片：有历史对话就不回复，没有才打招呼（Gemini 已在上面统一跳过）
+                    cid = data.get('from_id', '')
+                    acc_id = data.get('acc_id', '')
+                    residual_text = client._extract_customer_text_from_shop_card_msg(data.get('msg', ''))
+                    if residual_text:
+                        logger.info(f"[{client.get_time()}] 进店卡片携带客户文本，转普通消息处理: {residual_text}")
+                        patched = dict(data)
+                        patched['msg'] = residual_text
+                        await client._debounce_agent_reply(patched)
+                    elif client._has_chat_history(cid, acc_id=acc_id):
+                        logger.info(f"[{client.get_time()}] 进店卡片（已有记录），跳过")
+                    else:
+                        logger.info(f"[{client.get_time()}] 进店卡片（新客户），发送问候")
+                        greeting = "在呢，发图来我看看"
+                        await client.send_reply(data, greeting)
+                        client._push_chat_to_wechat_safe(
+                            data=data,
+                            customer_msg=data.get('msg', ''),
+                            reply_msg=greeting,
+                            goods_name=goods_name,
+                            tag="进店卡片问候",
+                        )
+                elif await client._handle_system_inquiry(data):
+                    logger.info(f"[{client.get_time()}] 系统客服询单消息，已按规则处理")
+                elif client._should_ignore(data):
+                    logger.info(f"[{client.get_time()}] 系统通知，跳过回复")
+                else:
+                    await client._debounce_agent_reply(data)
+            elif msg_type == 1:
+                # 图片消息直接处理，不走防抖（图片不会连续多发）
+                await client.handle_image_message(data)
+
+    except json.JSONDecodeError:
+        logger.info(f"[{timestamp}] 收到非JSON消息: {message}")

core/websocket_outbound_flow.py

@@ -0,0 +1,285 @@
+import os
+import re
+import time
+from typing import Any
+
+
+async def send_reply_flow(client, original_msg: dict, reply_content: str):
+    """
+    发送回复消息（从 websocket_client.py 拆出）。
+
+    Args:
+        original_msg: 收到的原始消息字典
+        reply_content: 回复内容（文本或本地文件路径/http地址）
+    """
+    trace_id = original_msg.get("_trace_id", "")
+    if not client.websocket:
+        client._activity_log(
+            "send_reply_skipped",
+            trace_id=trace_id,
+            reason="websocket_not_connected",
+            acc_id=original_msg.get("acc_id", ""),
+            customer_id=original_msg.get("from_id", ""),
+        )
+        return
+
+    reply_content = colloquialize_outbound_reply(reply_content)
+    reply_content = await ai_generate_outbound_reply(
+        client=client,
+        original_msg=original_msg,
+        reply_content=str(reply_content or ""),
+    )
+
+    # 同一客户外发限流：N 秒内最多 1 条
+    try:
+        from config.config import OUTBOUND_PER_CUSTOMER_COOLDOWN_SECONDS
+        cooldown = max(0, int(OUTBOUND_PER_CUSTOMER_COOLDOWN_SECONDS))
+    except Exception:
+        cooldown = 5
+    if cooldown > 0:
+        ckey = f"{original_msg.get('acc_id', '')}:{original_msg.get('from_id', '')}"
+        now_mono = time.monotonic()
+        last = client._last_reply_sent_at.get(ckey, 0.0)
+        if (now_mono - last) < cooldown:
+            client._activity_log(
+                "send_reply_throttled",
+                trace_id=trace_id,
+                key=ckey,
+                cooldown_s=cooldown,
+                msg=str(reply_content),
+            )
+            return
+        client._last_reply_sent_at[ckey] = now_mono
+
+    shop_id = original_msg.get("acc_id", "")
+
+    # 根据轻简API文档：
+    # from_id = 客户ID（收消息方）
+    # cy_id   = 非群聊时与 from_id 相同
+    customer_id = original_msg.get("from_id", "")
+    customer_name = original_msg.get("from_name", "")
+
+    allow_send, checked_reply, guard_reason = await ai_guard_outbound_reply(
+        client=client,
+        original_msg=original_msg,
+        reply_content=str(reply_content),
+    )
+    client._activity_log(
+        "reply_guard_decision",
+        trace_id=trace_id,
+        acc_id=shop_id,
+        customer_id=customer_id,
+        result="ok" if allow_send else "blocked",
+        reason=guard_reason,
+        original_reply=str(reply_content),
+        final_reply=str(checked_reply or ""),
+    )
+    if not allow_send:
+        return
+
+    reply_content = checked_reply or str(reply_content)
+    pass_send, _ = client._outbound_arbiter(
+        original_msg=original_msg,
+        reply_content=reply_content,
+        trace_id=trace_id,
+    )
+    if not pass_send:
+        return
+
+    reply = {
+        "msg_id": "",
+        "acc_id": shop_id,
+        "msg": reply_content,
+        "from_id": customer_id,
+        "from_name": customer_name,
+        "cy_id": customer_id,
+        "acc_type": original_msg.get("acc_type", ""),
+        "msg_type": 0,
+        "cy_name": customer_name,
+    }
+    client._log_outbound_once(original_msg, str(reply_content))
+    client._activity_log(
+        "send_reply_attempt",
+        trace_id=trace_id,
+        acc_id=shop_id,
+        customer_id=customer_id,
+        msg=str(reply_content),
+    )
+    reply["_trace_id"] = trace_id
+    await client.send_message(reply)
+
+
+async def ai_generate_outbound_reply(client, original_msg: dict, reply_content: str) -> str:
+    """
+    强制全量 AI 出站生成层：
+    - 所有普通文本外发先由 AI 生成最终话术；
+    - 控制命令/纯链接/转接指令直接绕过。
+    """
+    text = (reply_content or "").strip()
+    if not text:
+        return text
+    if text.startswith("话术|") or "[转移会话]" in text or "TRANSFER_REQUESTED" in text:
+        return text
+    if re.fullmatch(r"https?://\S+", text):
+        return text
+    if not client._force_ai_generate_reply or not client.enable_agent or not client.agent or not client.AgentDeps:
+        return text
+    try:
+        deps = client.AgentDeps(
+            msg_id=str(original_msg.get("msg_id", "") or "outbound_generate"),
+            acc_id=str(original_msg.get("acc_id", "") or ""),
+            from_id=str(original_msg.get("from_id", "") or ""),
+            platform=str(original_msg.get("acc_type", "") or ""),
+        )
+        customer_msg = client.to_chinese(str(original_msg.get("msg", "") or ""))
+        prompt = (
+            "你是淘宝客服外发文案生成器。请根据“回复意图草稿”生成最终发给客户的话。\n"
+            "要求：\n"
+            "1) 保留原意，不新增价格/承诺/流程；\n"
+            "2) 自然像真人聊天，不用固定模板句；\n"
+            "3) 1-2句；\n"
+            "4) 只输出最终回复文本。\n\n"
+            f"客户原话: {customer_msg}\n"
+            f"回复意图草稿: {text}\n"
+        )
+        result = await client.agent.agent_natural_reply.run(prompt, deps=deps, message_history=[])
+        out = str(getattr(result, "output", "") or "").strip()
+        if not out:
+            return text
+        if out.startswith("话术|") or "[转移会话]" in out:
+            return text
+        client._activity_log(
+            "ai_generate_reply",
+            acc_id=str(original_msg.get("acc_id", "") or ""),
+            customer_id=str(original_msg.get("from_id", "") or ""),
+            draft=text[:160],
+            generated=out[:160],
+        )
+        return out
+    except Exception as e:
+        client._activity_log(
+            "ai_generate_reply_error",
+            acc_id=str(original_msg.get("acc_id", "") or ""),
+            customer_id=str(original_msg.get("from_id", "") or ""),
+            error=str(e),
+        )
+        return text
+
+
+def colloquialize_outbound_reply(text: Any) -> Any:
+    """统一外发口语化处理，避免机械话术。"""
+    if not isinstance(text, str):
+        return text
+    raw = text.strip()
+    if not raw:
+        return text
+    # 控制指令/转接命令不得改写
+    if raw.startswith("话术|") or "[转移会话]" in raw:
+        return text
+    # 纯链接不改
+    if re.fullmatch(r"https?://\S+", raw):
+        return text
+
+    out = raw
+    replacements = {
+        "我这边": "我这边",
+        "请您": "你",
+        "您好": "你好",
+        "稍后": "一会儿",
+        "可以的话": "可以的话",
+        "请稍等": "稍等哈",
+        "先不乱报价": "先不急着给你乱报",
+        "建议转人工评估更稳": "建议转人工看会更稳",
+        "统一报价": "一起报价",
+        "马上安排": "马上给你安排",
+        "确认我就安排": "你点头我就开做",
+        "收到，我看看哈": "收到，我先看下",
+        "收到，我找找刚才那几张": "收到，我把刚才那几张一起看下",
+        "这组图我这边暂时识别不稳定": "这组图我这边识别得不太稳",
+        "这组图我这边暂时识别异常": "这组图我这边刚才识别有点异常",
+        "你可以换一张更清晰的，我再给你准报价。": "你换张更清晰的发我，我再给你报准点。",
+        "你可以换清晰图再发我。": "你换张清晰点的再发我哈。",
+        "你可以稍后再发我。": "你晚点再发我也行。",
+        "收到付款，我马上安排处理，有需要第一时间联系您": "收到付款啦，我马上安排处理，有进展第一时间告诉你",
+        "亲，正在为您转接人工客服，请稍等~": "我这就给你转人工，稍等哈~",
+    }
+    for k, v in replacements.items():
+        out = out.replace(k, v)
+    return out
+
+
+async def ai_guard_outbound_reply(client, original_msg: dict, reply_content: str) -> tuple[bool, str, str]:
+    """
+    专用AI质检：发送前判断“这句是否该发”，可拦截或改写。
+    读取当前客户在当前店铺的完整对话上下文。
+    """
+    text = (reply_content or "").strip()
+    if not text:
+        return False, "", "empty_reply"
+    if text.startswith("话术|") or "[转移会话]" in text:
+        return True, text, "command_bypass"
+    if not client._reply_guard_enabled or not client.enable_agent or not client.agent or not client.AgentDeps:
+        return True, text, "guard_disabled"
+    try:
+        from db.chat_log_db import get_conversation
+        import json as _json
+        import re as _re
+
+        acc_id = str(original_msg.get("acc_id", "") or "")
+        customer_id = str(original_msg.get("from_id", "") or "")
+        if not customer_id:
+            return True, text, "no_customer_id"
+
+        # 默认读取较大窗口，尽量覆盖完整上下文；可用环境变量继续放大。
+        try:
+            max_rows = max(50, int(os.getenv("AI_REPLY_GUARD_CONTEXT_ROWS", "500")))
+        except Exception:
+            max_rows = 500
+        rows = get_conversation(customer_id=customer_id, limit=max_rows) or []
+        shop_rows = [r for r in rows if str(r.get("acc_id", "") or "") == acc_id] if acc_id else rows
+
+        context_lines = []
+        for r in shop_rows:
+            role = "客" if (r.get("direction") == "in") else "服"
+            msg = client.to_chinese((r.get("message") or "").strip())
+            if msg:
+                context_lines.append(f"{role}:{msg}")
+        context_text = "\n".join(context_lines) if context_lines else "无历史"
+
+        deps = client.AgentDeps(
+            msg_id=str(original_msg.get("msg_id", "") or "reply_guard"),
+            acc_id=acc_id,
+            from_id=customer_id,
+            platform=str(original_msg.get("acc_type", "") or ""),
+        )
+        prompt = (
+            "你是淘宝客服回复质检器。目标：判断候选回复是否和上下文一致，是否会造成重复触发式答复。\n"
+            "必须检查：\n"
+            "1) 是否答非所问；\n"
+            "2) 是否重复说“马上报价/继续发图”但当前上下文不需要；\n"
+            "3) 是否与历史状态冲突；\n"
+            "4) 语气是否自然可直接发给客户。\n"
+            "若不合适，给可直接发送的一句改写。\n"
+            "只输出 JSON：{\"allow\":true/false,\"rewrite\":\"...\",\"reason\":\"...\"}\n\n"
+            f"完整上下文(当前店铺):\n{context_text}\n\n"
+            f"客户当前消息:{client.to_chinese(original_msg.get('msg', '') or '')}\n"
+            f"候选回复:{text}\n"
+        )
+        result = await client.agent.agent_natural_reply.run(prompt, deps=deps, message_history=[])
+        raw = str(getattr(result, "output", "") or "").strip()
+        if not raw:
+            return True, text, "guard_empty_output"
+        m = _re.search(r"\{[\s\S]*\}", raw)
+        if not m:
+            return True, text, "guard_non_json"
+        obj = _json.loads(m.group(0))
+        allow = bool(obj.get("allow", True))
+        rewrite = str(obj.get("rewrite", "") or "").strip()
+        reason = str(obj.get("reason", "") or "").strip() or "guard_decision"
+        if allow:
+            return True, (rewrite or text), reason
+        if rewrite:
+            return True, rewrite, reason
+        return False, "", reason
+    except Exception as e:
+        return True, text, f"guard_error:{e}"