拆分群昵称与正文避免话题识别被昵称污染

plugins/ai_auto_response/context/context_builder.py

@@ -30,11 +30,19 @@ class ContextBuilder:
     ) -> Dict:
         selected_messages = self._select_recent_messages(recent_messages, sender, content, quote_context or {})
         recent_lines = []
-        for item in selected_messages:
+        for idx, item in enumerate(selected_messages, start=1):
             msg_sender = item.get("sender_name") or item.get("sender") or "未知成员"
             msg_content = item.get("content") or item.get("message") or ""
             if msg_content:
-                recent_lines.append(f"{msg_sender}: {msg_content}")
+                # 这里把“发言人”和“正文”拆开保存，避免后续模型把昵称词汇误当成讨论主题。
+                recent_lines.append(
+                    self._format_recent_message_line(
+                        idx=idx,
+                        sender_name=str(msg_sender),
+                        content=str(msg_content),
+                        is_at=bool(item.get("is_at")),
+                    )
+                )
         return {
             "group_profile": group_profile or {"room_id": room_id},
             "speaker_profile": {
@@ -67,7 +75,7 @@ class ContextBuilder:
             "image_safety_prompt": self._build_image_safety_prompt(
                 (quote_context or {}).get("image_safety") or {}
             ),
-            "current_message": f"{sender_name}: {content}",
+            "current_message": self._format_current_message_block(sender_name, content),
         }
 
     @staticmethod
@@ -85,6 +93,31 @@ class ContextBuilder:
             })
         return items
 
+    @staticmethod
+    def _sanitize_inline_field(value: str, max_chars: int = 120) -> str:
+        # 统一把换行和分隔符清掉，避免后续在单行结构化文本里把字段边界冲散。
+        text = re.sub(r"\s+", " ", str(value or "")).strip()
+        text = text.replace("|", "／")
+        if len(text) > max_chars:
+            return text[: max_chars - 3].rstrip() + "..."
+        return text
+
+    @classmethod
+    def _format_recent_message_line(cls, idx: int, sender_name: str, content: str, is_at: bool = False) -> str:
+        sender = cls._sanitize_inline_field(sender_name, max_chars=24) or "未知成员"
+        body = cls._sanitize_inline_field(content, max_chars=120)
+        parts = [f"[{idx:02d}]", f"发言人={sender}", f"正文={body}"]
+        if is_at:
+            parts.append("@bot=Y")
+        return " | ".join(parts)
+
+    @classmethod
+    def _format_current_message_block(cls, sender_name: str, content: str) -> str:
+        # 当前消息改成“元信息 + 正文”两段式，方便模型只把正文视为话题语义来源。
+        sender = cls._sanitize_inline_field(sender_name, max_chars=24) or "未知成员"
+        body = cls._sanitize_inline_field(content, max_chars=500)
+        return f"发言人={sender}\n正文={body}"
+
     def _select_recent_messages(
         self,
         recent_messages: List[Dict],