fix：

1.优化声纹称呼人提示词和注入逻辑，减少次次都称呼的频率

main/xiaozhi-server/core/connection.py

@@ -156,6 +156,8 @@ class ConnectionHandler:
         self.asr_audio = []
         self.asr_audio_queue = queue.Queue()
         self.current_speaker = None  # 存储当前说话人
+        self.introduced_speakers = set()  # 已"首次引入"的说话人，控制只在首轮带名字
+        self.system_introduced_speakers = set()  # 已在 system 注入过身份的说话人，控制 system 身份只首轮出现
 
         # llm相关变量
         self.dialogue = Dialogue()
@@ -978,12 +980,20 @@ class ConnectionHandler:
                 )
                 memory_str = future.result()
 
+            # 仅在该说话人首次出现时把身份注入 system，之后靠对话历史首轮保留，
+            # 避免每轮在 system 重复出现名字诱导模型反复称呼
+            speaker_for_system = None
+            cs = (self.current_speaker or "").strip()
+            if cs and cs != "未知说话人" and cs not in self.system_introduced_speakers:
+                self.system_introduced_speakers.add(cs)
+                speaker_for_system = cs
+
             if self.intent_type == "function_call" and functions is not None:
                 # 使用支持functions的streaming接口
                 llm_responses = self.llm.response_with_functions(
                     self.session_id,
                     self.dialogue.get_llm_dialogue_with_memory(
-                        memory_str, self.config.get("voiceprint", {}), self.current_speaker
+                        memory_str, self.config.get("voiceprint", {}), speaker_for_system
                     ),
                     functions=functions,
                 )
@@ -991,7 +1001,7 @@ class ConnectionHandler:
                 llm_responses = self.llm.response(
                     self.session_id,
                     self.dialogue.get_llm_dialogue_with_memory(
-                        memory_str, self.config.get("voiceprint", {}), self.current_speaker
+                        memory_str, self.config.get("voiceprint", {}), speaker_for_system
                     ),
                 )
         except Exception as e:

main/xiaozhi-server/core/handle/receiveAudioHandle.py

@@ -39,7 +39,6 @@ async def resume_vad_detection(conn: "ConnectionHandler"):
 async def startToChat(conn: "ConnectionHandler", text):
     # 检查输入是否是JSON格式（包含说话人信息）
     speaker_name = None
-    language_tag = None
     actual_text = text
 
     try:
@@ -48,12 +47,16 @@ async def startToChat(conn: "ConnectionHandler", text):
             data = json.loads(text)
             if "speaker" in data and "content" in data:
                 speaker_name = data["speaker"]
-                language_tag = data["language"]
-                actual_text = data["content"]
+                actual_content = data["content"]
                 conn.logger.bind(tag=TAG).info(f"解析到说话人信息: {speaker_name}")
 
-                # 直接使用JSON格式的文本，不解析
-                actual_text = text
+                # 仅在该说话人首次出现时保留 {"speaker":...} JSON，让模型自然称呼一次；
+                # 后续轮降为纯文本，避免每轮重复出现名字诱导模型反复称呼
+                if speaker_name not in conn.introduced_speakers:
+                    conn.introduced_speakers.add(speaker_name)
+                    actual_text = text
+                else:
+                    actual_text = actual_content
     except (json.JSONDecodeError, KeyError):
         # 如果解析失败，继续使用原始文本
         pass

main/xiaozhi-server/core/utils/dialogue.py

@@ -145,13 +145,13 @@ class Dialogue:
 
             # 追加说话人信息
             try:
-                speakers = voiceprint_config.get("speakers", [])
                 current_speaker_name = (current_speaker or "").strip()
-                if speakers or (current_speaker_name and current_speaker_name != "未知说话人"):
+                # 仅在本轮注入了有效身份时才输出 speakers_info，避免列表里的名字每轮
+                # 重复出现诱导模型反复称呼；后续轮不再注入身份，靠对话历史首轮保留
+                if current_speaker_name and current_speaker_name != "未知说话人":
+                    speakers = voiceprint_config.get("speakers", [])
                     dynamic_part += "\n<speakers_info>"
-                    # 当前说话人置于块首，确保弱模型也能稳定获取身份
-                    if current_speaker_name and current_speaker_name != "未知说话人":
-                        dynamic_part += f"\n当前说话人：{current_speaker_name}"
+                    dynamic_part += f"\n当前说话人：{current_speaker_name}"
                     for speaker_str in speakers:
                         try:
                             parts = speaker_str.split(",", 2)