fix: harden outbound leak guard and title naming

core/repository.py

@@ -1,5 +1,6 @@
 import logging
 import asyncio
+import re
 from typing import Optional, List, Any
 from datetime import datetime
 from db.customer_db import db as customer_db
@@ -8,6 +9,43 @@ from db.chat_log_db import log_message, get_conversation
 
 logger = logging.getLogger("cs_agent")
 
+_OUTBOUND_BLOCK_MARKERS = (
+    "【历史记录摘要】",
+    "【详细记录】",
+    "【订单摘要】",
+    "【订单详情】",
+    "<think",
+    "think_never_used",
+    '[{"name":',
+)
+
+_HISTORY_LEAK_PATTERNS = [
+    r'\[\d{4}-\d{2}-\d{2}[^\]]*\]\s*(客户|客服)[：:]',
+    r'\[\d{2}:\d{2}:\d{2}\]\s*(客户|客服|我)[：:]',
+    r'(根据|查看|查询|翻看)(历史|聊天|对话)(记录|内容)',
+    r'历史(记录|对话|消息)(显示|表明|中)',
+    r'之前的(聊天|对话|记录)(中|里|显示)',
+    r'共\d+条(历史|对话)?消息',
+    r'订单号[:：]\s*\d{10,}',
+    r'(状态|金额|数量)[:：].*(状态|金额|数量)[:：]',
+]
+
+
+def _sanitize_outbound_archive_text(content: str) -> str:
+    if not content:
+        return ""
+    cleaned = str(content).strip()
+    if "[转移会话]" in cleaned:
+        return cleaned
+    if any(marker in cleaned for marker in _OUTBOUND_BLOCK_MARKERS):
+        logger.warning("[Repository] 拦截到内部内容写入外发记录，替换为安全兜底回复")
+        return "我在帮你看记录，稍等哈"
+    for pattern in _HISTORY_LEAK_PATTERNS:
+        if re.search(pattern, cleaned):
+            logger.warning(f"[Repository] 检测到历史记录泄露模式，拦截出站入库: {pattern[:30]}...")
+            return "我在帮你看记录，稍等哈"
+    return cleaned
+
 class DataRepository:
     """
     异步数据仓库：使用 asyncio.to_thread 屏蔽底层同步 IO 阻塞。
@@ -29,6 +67,8 @@ class DataRepository:
         msg_type: int = 0,
     ):
         """异步持久化存储聊天记录"""
+        if direction == "out" and int(msg_type or 0) == 0:
+            content = _sanitize_outbound_archive_text(content)
         # 将图片URL列表转为\n分隔的字符串
         urls_str = "\n".join(image_urls) if image_urls else ""
         return await asyncio.to_thread(

core/websocket_send_flow.py

@@ -1,13 +1,54 @@
 import json
+import logging
+import re
 import websockets
 
+logger = logging.getLogger("cs_agent")
+
+_OUTBOUND_BLOCK_MARKERS = (
+    "【历史记录摘要】",
+    "【详细记录】",
+    "【订单摘要】",
+    "【订单详情】",
+    "<think",
+    "think_never_used",
+    '[{"name":',
+)
+
+_HISTORY_LEAK_PATTERNS = [
+    r'\[\d{4}-\d{2}-\d{2}[^\]]*\]\s*(客户|客服)[：:]',
+    r'\[\d{2}:\d{2}:\d{2}\]\s*(客户|客服|我)[：:]',
+    r'(根据|查看|查询|翻看)(历史|聊天|对话)(记录|内容)',
+    r'历史(记录|对话|消息)(显示|表明|中)',
+    r'之前的(聊天|对话|记录)(中|里|显示)',
+    r'共\d+条(历史|对话)?消息',
+    r'订单号[:：]\s*\d{10,}',
+    r'(状态|金额|数量)[:：].*(状态|金额|数量)[:：]',
+]
+
+
+def _sanitize_outbound_text(content: str) -> str:
+    if not content:
+        return ""
+    cleaned = str(content).strip()
+    if "[转移会话]" in cleaned:
+        return cleaned
+    if any(marker in cleaned for marker in _OUTBOUND_BLOCK_MARKERS):
+        logger.warning("[WebSocketSend] 拦截到内部内容外发，替换为安全兜底回复")
+        return "我在帮你看记录，稍等哈"
+    for pattern in _HISTORY_LEAK_PATTERNS:
+        if re.search(pattern, cleaned):
+            logger.warning(f"[WebSocketSend] 检测到历史记录泄露模式: {pattern[:30]}...")
+            return "我在帮你看记录，稍等哈"
+    return cleaned
+
 
 async def send_text_flow(client, cy_id, acc_type, content):
     """主动发送文本消息。"""
     message = {
         "msg_id": "",
         "acc_id": "",
-        "msg": content,
+        "msg": _sanitize_outbound_text(content),
         "from_id": client.reply_id,
         "from_name": client.reply_id,
         "cy_id": cy_id,
@@ -38,10 +79,12 @@ async def send_message_flow(client, message):
     """发送消息到服务器。"""
     if client.websocket and client.websocket.state == websockets.protocol.State.OPEN:
         try:
-            payload = message if isinstance(message, dict) else {}
-            msg_json = json.dumps(message, ensure_ascii=False)
+            payload = dict(message) if isinstance(message, dict) else {}
+            if int(payload.get("msg_type", 0) or 0) == 0:
+                payload["msg"] = _sanitize_outbound_text(payload.get("msg", ""))
+            msg_json = json.dumps(payload, ensure_ascii=False)
             await client.websocket.send(msg_json)
-            pretty = json.dumps(message, ensure_ascii=False, indent=2)
+            pretty = json.dumps(payload, ensure_ascii=False, indent=2)
             client.logger.info(f"[{client.get_time()}] 发送成功:\n{pretty}")
             client._activity_log(
                 "send_message_success",