From 885b7a0b05bcfcac46ff05bedc6b468adbd70dcc Mon Sep 17 00:00:00 2001
From: goodyhao <865700600@qq.com>
Date: Tue, 13 May 2025 15:54:00 +0800
Subject: [PATCH 01/16] =?UTF-8?q?feat:=20=E5=A2=9E=E5=8A=A0=E4=B8=8A?=
 =?UTF-8?q?=E6=8A=A5=E7=BA=BF=E7=A8=8B=E6=B1=A0?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/core/connection.py | 26 ++++++++++++++++++++------
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py
index 63b79736..68964629 100644
--- a/main/xiaozhi-server/core/connection.py
+++ b/main/xiaozhi-server/core/connection.py
@@ -88,7 +88,8 @@ class ConnectionHandler:
         self.audio_play_queue = queue.Queue()
         self.executor = ThreadPoolExecutor(max_workers=10)
 
-        # 上报线程
+        # 添加上报线程池
+        self.report_thread_pool = ThreadPoolExecutor(max_workers=5, thread_name_prefix="report_worker")
         self.report_queue = queue.Queue()
         self.report_thread = None
         # TODO(haotian): 2025/5/12 可以通过修改此处，调节asr的上报和tts的上报
@@ -944,13 +945,10 @@ class ConnectionHandler:
                 type, text, audio_data = item
 
                 try:
-                    # 执行上报（传入二进制数据）
-                    report(self, type, text, audio_data)
+                    # 提交任务到线程池
+                    self.report_thread_pool.submit(self._process_report, type, text, audio_data)
                 except Exception as e:
                     self.logger.bind(tag=TAG).error(f"聊天记录上报线程异常: {e}")
-                finally:
-                    # 标记任务完成
-                    self.report_queue.task_done()
             except queue.Empty:
                 continue
             except Exception as e:
@@ -958,6 +956,17 @@ class ConnectionHandler:
 
         self.logger.bind(tag=TAG).info("聊天记录上报线程已退出")
 
+    def _process_report(self, type, text, audio_data):
+        """处理上报任务"""
+        try:
+            # 执行上报（传入二进制数据）
+            report(self, type, text, audio_data)
+        except Exception as e:
+            self.logger.bind(tag=TAG).error(f"上报处理异常: {e}")
+        finally:
+            # 标记任务完成
+            self.report_queue.task_done()
+
     def speak_and_play(self, text, text_index=0):
         if text is None or len(text) <= 0:
             self.logger.bind(tag=TAG).info(f"无需tts转换，query为空，{text}")
@@ -1006,6 +1015,11 @@ class ConnectionHandler:
         # 添加毒丸对象到上报队列确保线程退出
         self.report_queue.put(None)
 
+        # 关闭上报线程池
+        if hasattr(self, 'report_thread_pool'):
+            self.report_thread_pool.shutdown(wait=True)
+            self.logger.bind(tag=TAG).info("上报线程池已关闭")
+
         # 清空任务队列
         self.clear_queues()
 

From 02cb9c35b312af71644d61eff9b83650195d2af3 Mon Sep 17 00:00:00 2001
From: Sakura-RanChen <1908198662@qq.com>
Date: Thu, 22 May 2025 17:14:58 +0800
Subject: [PATCH 02/16] =?UTF-8?q?update:=20=E8=AE=B0=E5=BF=86=E6=A8=A1?=
 =?UTF-8?q?=E5=9D=97=E4=BD=BF=E7=94=A8=E7=8B=AC=E7=AB=8BLLM=20openai?=
 =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E8=B6=85=E5=8F=82?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/config.yaml               |  4 +++
 main/xiaozhi-server/core/connection.py        | 28 +++++++++++++++++
 .../xiaozhi-server/core/providers/llm/base.py |  6 ++--
 .../core/providers/llm/openai/openai.py       | 31 +++++++++++++------
 .../core/providers/memory/base.py             |  8 ++++-
 .../memory/mem_local_short/mem_local_short.py | 21 +++++++------
 6 files changed, 75 insertions(+), 23 deletions(-)

diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml
index 44845df8..ebec6ccd 100644
--- a/main/xiaozhi-server/config.yaml
+++ b/main/xiaozhi-server/config.yaml
@@ -220,6 +220,10 @@ Memory:
   mem_local_short:
     # 本地记忆功能，通过selected_module的llm总结，数据保存在本地，不会上传到服务器
     type: mem_local_short
+    # 配备记忆存储独立的思考模型
+    # 如果这里不填，则会默认使用selected_module.LLM的模型作为意图识别的思考模型
+    # 如果你的不想使用selected_module.LLM记忆存储，这里最好使用独立的LLM作为意图识别，例如使用免费的ChatGLMLLM
+    llm: ChatGLMLLM
 
 ASR:
   FunASR:
diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py
index 74b612fe..fd8900ed 100644
--- a/main/xiaozhi-server/core/connection.py
+++ b/main/xiaozhi-server/core/connection.py
@@ -452,6 +452,34 @@ class ConnectionHandler:
             save_to_file=not self.read_config_from_api,
         )
 
+        # 获取记忆总结配置
+        memory_config = self.config["Memory"]
+        memory_type = self.config["Memory"][self.config["selected_module"]["Memory"]][
+            "type"
+        ]
+        # 如果使用 nomen，直接返回
+        if memory_type == "nomem":
+            return
+        # 使用 mem_local_short 模式
+        elif memory_type == "mem_local_short":
+            memory_llm_name = memory_config[self.config["selected_module"]["Memory"]]["llm"]
+            if memory_llm_name and memory_llm_name in self.config["LLM"]:
+                # 如果配置了专用LLM，则创建独立的LLM实例
+                from core.utils import llm as llm_utils
+                memory_llm_config = self.config["LLM"][memory_llm_name]
+                memory_llm_type = memory_llm_config.get("type", memory_llm_name)
+                memory_llm = llm_utils.create_instance(
+                    memory_llm_type, memory_llm_config
+                )
+                self.logger.bind(tag=TAG).info(
+                    f"为记忆总结创建了专用LLM: {memory_llm_name}, 类型: {memory_llm_type}"
+                )
+                self.memory.set_llm(memory_llm)
+            else:
+                # 否则使用主LLM
+                self.memory.set_llm(self.llm)
+                self.logger.bind(tag=TAG).info("使用主LLM作为意图识别模型")
+
     def _initialize_intent(self):
         self.intent_type = self.config["Intent"][
             self.config["selected_module"]["Intent"]
diff --git a/main/xiaozhi-server/core/providers/llm/base.py b/main/xiaozhi-server/core/providers/llm/base.py
index 97d0d8e7..77786140 100644
--- a/main/xiaozhi-server/core/providers/llm/base.py
+++ b/main/xiaozhi-server/core/providers/llm/base.py
@@ -10,7 +10,7 @@ class LLMProviderBase(ABC):
         """LLM response generator"""
         pass
 
-    def response_no_stream(self, system_prompt, user_prompt):
+    def response_no_stream(self, system_prompt, user_prompt, **kwargs):
         try:
             # 构造对话格式
             dialogue = [
@@ -18,7 +18,7 @@ class LLMProviderBase(ABC):
                 {"role": "user", "content": user_prompt}
             ]
             result = ""
-            for part in self.response("", dialogue):
+            for part in self.response("", dialogue, **kwargs):
                 result += part
             return result
 
@@ -30,7 +30,7 @@ class LLMProviderBase(ABC):
         """
         Default implementation for function calling (streaming)
         This should be overridden by providers that support function calls
-        
+
         Returns: generator that yields either text tokens or a special function call token
         """
         # For providers that don't support functions, just return regular response
diff --git a/main/xiaozhi-server/core/providers/llm/openai/openai.py b/main/xiaozhi-server/core/providers/llm/openai/openai.py
index a20067af..bc0e7f21 100644
--- a/main/xiaozhi-server/core/providers/llm/openai/openai.py
+++ b/main/xiaozhi-server/core/providers/llm/openai/openai.py
@@ -16,26 +16,37 @@ class LLMProvider(LLMProviderBase):
             self.base_url = config.get("base_url")
         else:
             self.base_url = config.get("url")
-        max_tokens = config.get("max_tokens")
-        if max_tokens is None or max_tokens == "":
-            max_tokens = 500
 
-        try:
-            max_tokens = int(max_tokens)
-        except (ValueError, TypeError):
-            max_tokens = 500
-        self.max_tokens = max_tokens
+        param_defaults = {
+            "max_tokens": (500, int),
+            "temperature": (0.7, lambda x: round(float(x), 1)),
+            "top_p": (1.0, lambda x: round(float(x), 1)),
+            "frequency_penalty": (0, lambda x: round(float(x), 1))
+        }
+
+        for param, (default, converter) in param_defaults.items():
+            value = config.get(param)
+            try:
+                setattr(self, param, converter(value) if value not in (None, "") else default)
+            except (ValueError, TypeError):
+                setattr(self, param, default)
+
+        logger.debug(
+            f"意图识别参数初始化: {self.temperature}, {self.max_tokens}, {self.top_p}, {self.frequency_penalty}")
 
         check_model_key("LLM", self.api_key)
         self.client = openai.OpenAI(api_key=self.api_key, base_url=self.base_url)
 
-    def response(self, session_id, dialogue):
+    def response(self, session_id, dialogue, **kwargs):
         try:
             responses = self.client.chat.completions.create(
                 model=self.model_name,
                 messages=dialogue,
                 stream=True,
-                max_tokens=self.max_tokens,
+                max_tokens=kwargs.get("max_tokens", self.max_tokens),
+                temperature=kwargs.get("temperature", self.temperature),
+                top_p=kwargs.get("top_p", self.top_p),
+                frequency_penalty=kwargs.get("frequency_penalty", self.frequency_penalty),
             )
 
             is_active = True
diff --git a/main/xiaozhi-server/core/providers/memory/base.py b/main/xiaozhi-server/core/providers/memory/base.py
index 19dcabb8..f404f15e 100644
--- a/main/xiaozhi-server/core/providers/memory/base.py
+++ b/main/xiaozhi-server/core/providers/memory/base.py
@@ -9,7 +9,13 @@ class MemoryProviderBase(ABC):
     def __init__(self, config):
         self.config = config
         self.role_id = None
-        self.llm = None
+
+    def set_llm(self, llm):
+        self.llm = llm
+        # 获取模型名称和类型信息
+        model_name = getattr(llm, "model_name", str(llm.__class__.__name__))
+        # 记录更详细的日志
+        logger.bind(tag=TAG).info(f"记忆总结设置LLM: {model_name}")
 
     @abstractmethod
     async def save_memory(self, msgs):
diff --git a/main/xiaozhi-server/core/providers/memory/mem_local_short/mem_local_short.py b/main/xiaozhi-server/core/providers/memory/mem_local_short/mem_local_short.py
index a916e6c9..844035bd 100644
--- a/main/xiaozhi-server/core/providers/memory/mem_local_short/mem_local_short.py
+++ b/main/xiaozhi-server/core/providers/memory/mem_local_short/mem_local_short.py
@@ -107,7 +107,7 @@ TAG = __name__
 class MemoryProvider(MemoryProviderBase):
     def __init__(self, config, summary_memory):
         super().__init__(config)
-        self.short_momery = ""
+        self.short_memory = ""
         self.save_to_file = True
         self.memory_path = get_project_dir() + "data/.memory.yaml"
         self.load_memory(summary_memory)
@@ -122,7 +122,7 @@ class MemoryProvider(MemoryProviderBase):
     def load_memory(self, summary_memory):
         # api获取到总结记忆后直接返回
         if summary_memory or not self.save_to_file:
-            self.short_momery = summary_memory
+            self.short_memory = summary_memory
             return
 
         all_memory = {}
@@ -130,18 +130,21 @@ class MemoryProvider(MemoryProviderBase):
             with open(self.memory_path, "r", encoding="utf-8") as f:
                 all_memory = yaml.safe_load(f) or {}
         if self.role_id in all_memory:
-            self.short_momery = all_memory[self.role_id]
+            self.short_memory = all_memory[self.role_id]
 
     def save_memory_to_file(self):
         all_memory = {}
         if os.path.exists(self.memory_path):
             with open(self.memory_path, "r", encoding="utf-8") as f:
                 all_memory = yaml.safe_load(f) or {}
-        all_memory[self.role_id] = self.short_momery
+        all_memory[self.role_id] = self.short_memory
         with open(self.memory_path, "w", encoding="utf-8") as f:
             yaml.dump(all_memory, f, allow_unicode=True)
 
     async def save_memory(self, msgs):
+        # 打印使用的模型信息
+        model_info = getattr(self.llm, "model_name", str(self.llm.__class__.__name__))
+        logger.bind(tag=TAG).debug(f"使用记忆保存模型: {model_info}")
         if self.llm is None:
             logger.bind(tag=TAG).error("LLM is not set for memory provider")
             return None
@@ -155,9 +158,9 @@ class MemoryProvider(MemoryProviderBase):
                 msgStr += f"User: {msg.content}\n"
             elif msg.role == "assistant":
                 msgStr += f"Assistant: {msg.content}\n"
-        if self.short_momery and len(self.short_momery) > 0:
+        if self.short_memory and len(self.short_memory) > 0:
             msgStr += "历史记忆：\n"
-            msgStr += self.short_momery
+            msgStr += self.short_memory
 
         # 当前时间
         time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
@@ -168,7 +171,7 @@ class MemoryProvider(MemoryProviderBase):
             json_str = extract_json_data(result)
             try:
                 json.loads(json_str)  # 检查json格式是否正确
-                self.short_momery = json_str
+                self.short_memory = json_str
                 self.save_memory_to_file()
             except Exception as e:
                 print("Error:", e)
@@ -179,7 +182,7 @@ class MemoryProvider(MemoryProviderBase):
             save_mem_local_short(self.role_id, result)
         logger.bind(tag=TAG).info(f"Save memory successful - Role: {self.role_id}")
 
-        return self.short_momery
+        return self.short_memory
 
     async def query_memory(self, query: str) -> str:
-        return self.short_momery
+        return self.short_memory

From 17fb60b7aec4d903cd1a1107047e0c8e16b94eea Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Fri, 23 May 2025 16:03:15 +0800
Subject: [PATCH 03/16] =?UTF-8?q?update:=E4=BF=AE=E5=A4=8Diotbug?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../xiaozhi-server/core/providers/asr/base.py |  30 ++++--
 .../core/providers/asr/fun_local.py           | 101 +++++++++++-------
 .../providers/intent/intent_llm/intent_llm.py |   7 +-
 .../functions/handle_speaker_or_screen.py     |  81 ++++++++++----
 4 files changed, 149 insertions(+), 70 deletions(-)

diff --git a/main/xiaozhi-server/core/providers/asr/base.py b/main/xiaozhi-server/core/providers/asr/base.py
index 227a906d..9d974180 100644
--- a/main/xiaozhi-server/core/providers/asr/base.py
+++ b/main/xiaozhi-server/core/providers/asr/base.py
@@ -30,15 +30,25 @@ class ASRProviderBase(ABC):
     @staticmethod
     def decode_opus(opus_data: List[bytes]) -> bytes:
         """将Opus音频数据解码为PCM数据"""
+        try:
+            decoder = opuslib_next.Decoder(16000, 1)  # 16kHz, 单声道
+            pcm_data = []
+            buffer_size = 960  # 每次处理960个采样点
 
-        decoder = opuslib_next.Decoder(16000, 1)  # 16kHz, 单声道
-        pcm_data = []
+            for opus_packet in opus_data:
+                try:
+                    # 使用较小的缓冲区大小进行处理
+                    pcm_frame = decoder.decode(opus_packet, buffer_size)
+                    if pcm_frame:
+                        pcm_data.append(pcm_frame)
+                except opuslib_next.OpusError as e:
+                    logger.bind(tag=TAG).warning(f"Opus解码错误，跳过当前数据包: {e}")
+                    continue
+                except Exception as e:
+                    logger.bind(tag=TAG).error(f"音频处理错误: {e}", exc_info=True)
+                    continue
 
-        for opus_packet in opus_data:
-            try:
-                pcm_frame = decoder.decode(opus_packet, 960)  # 960 samples = 60ms
-                pcm_data.append(pcm_frame)
-            except opuslib_next.OpusError as e:
-                logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
-
-        return pcm_data
+            return pcm_data
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"音频解码过程发生错误: {e}", exc_info=True)
+            return []
diff --git a/main/xiaozhi-server/core/providers/asr/fun_local.py b/main/xiaozhi-server/core/providers/asr/fun_local.py
index ec3df17f..c8446574 100644
--- a/main/xiaozhi-server/core/providers/asr/fun_local.py
+++ b/main/xiaozhi-server/core/providers/asr/fun_local.py
@@ -9,10 +9,14 @@ import uuid
 from core.providers.asr.base import ASRProviderBase
 from funasr import AutoModel
 from funasr.utils.postprocess_utils import rich_transcription_postprocess
+import shutil
 
 TAG = __name__
 logger = setup_logging()
 
+MAX_RETRIES = 2
+RETRY_DELAY = 1  # 重试延迟（秒）
+
 
 # 捕获标准输出
 class CaptureOutput:
@@ -68,46 +72,69 @@ class ASRProvider(ASRProviderBase):
     ) -> Tuple[Optional[str], Optional[str]]:
         """语音转文本主处理逻辑"""
         file_path = None
-        try:
-            # 合并所有opus数据包
-            if self.audio_format == "pcm":
-                pcm_data = opus_data
-            else:
-                pcm_data = self.decode_opus(opus_data)
+        retry_count = 0
 
-            combined_pcm_data = b"".join(pcm_data)
+        while retry_count < MAX_RETRIES:
+            try:
+                # 合并所有opus数据包
+                if self.audio_format == "pcm":
+                    pcm_data = opus_data
+                else:
+                    pcm_data = self.decode_opus(opus_data)
 
-            # 判断是否保存为WAV文件
-            if self.delete_audio_file:
-                pass
-            else:
-                file_path = self.save_audio_to_file(pcm_data, session_id)
+                combined_pcm_data = b"".join(pcm_data)
 
-            # 语音识别
-            start_time = time.time()
-            result = self.model.generate(
-                input=combined_pcm_data,
-                cache={},
-                language="auto",
-                use_itn=True,
-                batch_size_s=60,
-            )
-            text = rich_transcription_postprocess(result[0]["text"])
-            logger.bind(tag=TAG).debug(
-                f"语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text}"
-            )
+                # 检查磁盘空间
+                if not self.delete_audio_file:
+                    free_space = shutil.disk_usage(self.output_dir).free
+                    if free_space < len(combined_pcm_data) * 2:  # 预留2倍空间
+                        raise OSError("磁盘空间不足")
 
-            return text, file_path
+                # 判断是否保存为WAV文件
+                if self.delete_audio_file:
+                    pass
+                else:
+                    file_path = self.save_audio_to_file(pcm_data, session_id)
 
-        except Exception as e:
-            logger.bind(tag=TAG).error(f"语音识别失败: {e}", exc_info=True)
-            return "", file_path
+                # 语音识别
+                start_time = time.time()
+                result = self.model.generate(
+                    input=combined_pcm_data,
+                    cache={},
+                    language="auto",
+                    use_itn=True,
+                    batch_size_s=60,
+                )
+                text = rich_transcription_postprocess(result[0]["text"])
+                logger.bind(tag=TAG).debug(
+                    f"语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text}"
+                )
 
-        # finally:
-        #     # 文件清理逻辑
-        #     if self.delete_audio_file and file_path and os.path.exists(file_path):
-        #         try:
-        #             os.remove(file_path)
-        #             logger.bind(tag=TAG).debug(f"已删除临时音频文件: {file_path}")
-        #         except Exception as e:
-        #             logger.bind(tag=TAG).error(f"文件删除失败: {file_path} | 错误: {e}")
+                return text, file_path
+
+            except OSError as e:
+                retry_count += 1
+                if retry_count >= MAX_RETRIES:
+                    logger.bind(tag=TAG).error(
+                        f"语音识别失败（已重试{retry_count}次）: {e}", exc_info=True
+                    )
+                    return "", file_path
+                logger.bind(tag=TAG).warning(
+                    f"语音识别失败，正在重试（{retry_count}/{MAX_RETRIES}）: {e}"
+                )
+                time.sleep(RETRY_DELAY)
+
+            except Exception as e:
+                logger.bind(tag=TAG).error(f"语音识别失败: {e}", exc_info=True)
+                return "", file_path
+
+            finally:
+                # 文件清理逻辑
+                if self.delete_audio_file and file_path and os.path.exists(file_path):
+                    try:
+                        os.remove(file_path)
+                        logger.bind(tag=TAG).debug(f"已删除临时音频文件: {file_path}")
+                    except Exception as e:
+                        logger.bind(tag=TAG).error(
+                            f"文件删除失败: {file_path} | 错误: {e}"
+                        )
diff --git a/main/xiaozhi-server/core/providers/intent/intent_llm/intent_llm.py b/main/xiaozhi-server/core/providers/intent/intent_llm/intent_llm.py
index ee657420..51696bb7 100644
--- a/main/xiaozhi-server/core/providers/intent/intent_llm/intent_llm.py
+++ b/main/xiaozhi-server/core/providers/intent/intent_llm/intent_llm.py
@@ -72,6 +72,10 @@ class IntentProvider(IntentProviderBase):
             '返回: {"function_call": {"name": "get_time"}}\n'
             "```\n"
             "```\n"
+            "用户: 当前电池电量是多少？\n"
+            '返回: {"function_call": {"name": "get_battery_level", "arguments": {"response_success": "当前电池电量为{value}%", "response_failure": "无法获取Battery的当前电量百分比"}}}\n'
+            "```\n"
+            "```\n"
             "用户: 我想结束对话\n"
             '返回: {"function_call": {"name": "handle_exit_intent", "arguments": {"say_goodbye": "goodbye"}}}\n'
             "```\n"
@@ -224,7 +228,8 @@ class IntentProvider(IntentProviderBase):
                 if function_name == "continue_chat":
                     # 保留非工具相关的消息
                     clean_history = [
-                        msg for msg in conn.dialogue.dialogue
+                        msg
+                        for msg in conn.dialogue.dialogue
                         if msg.role not in ["tool", "function"]
                     ]
                     conn.dialogue.dialogue = clean_history
diff --git a/main/xiaozhi-server/plugins_func/functions/handle_speaker_or_screen.py b/main/xiaozhi-server/plugins_func/functions/handle_speaker_or_screen.py
index fa357ff5..f89f30b0 100644
--- a/main/xiaozhi-server/plugins_func/functions/handle_speaker_or_screen.py
+++ b/main/xiaozhi-server/plugins_func/functions/handle_speaker_or_screen.py
@@ -15,15 +15,26 @@ async def _get_device_status(conn, device_name, device_type, property_name):
     return status
 
 
-async def _set_device_property(conn, device_name, device_type, method_name, property_name, new_value=None, action=None, step=10):
+async def _set_device_property(
+    conn,
+    device_name,
+    device_type,
+    method_name,
+    property_name,
+    new_value=None,
+    action=None,
+    step=10,
+):
     """设置设备属性"""
-    current_value = await _get_device_status(conn, device_name, device_type, property_name)
+    current_value = await _get_device_status(
+        conn, device_name, device_type, property_name
+    )
 
-    if action == 'raise':
+    if action == "raise":
         current_value += step
-    elif action == 'lower':
+    elif action == "lower":
         current_value -= step
-    elif action == 'set':
+    elif action == "set":
         if new_value is None:
             raise Exception(f"缺少{property_name}参数")
         current_value = new_value
@@ -37,8 +48,7 @@ async def _set_device_property(conn, device_name, device_type, method_name, prop
 
 def _handle_device_action(conn, func, success_message, error_message, *args, **kwargs):
     """处理设备操作的通用函数"""
-    future = asyncio.run_coroutine_threadsafe(
-        func(conn, *args, **kwargs), conn.loop)
+    future = asyncio.run_coroutine_threadsafe(func(conn, *args, **kwargs), conn.loop)
     try:
         result = future.result()
         logger.bind(tag=TAG).info(f"{success_message}: {result}")
@@ -75,26 +85,41 @@ handle_device_function_desc = {
                 "device_type": {
                     "type": "string",
                     "description": "设备类型，**严格限定为Speaker（音量）或Screen（亮度）**，其他设备类型禁止调用此函数",
-                    "enum": ["Speaker", "Screen"]
-
+                    "enum": ["Speaker", "Screen"],
                 },
                 "action": {
                     "type": "string",
-                    "description": "动作名称，可选值：get(获取),set(设置),raise(提高),lower(降低)"
+                    "description": "动作名称，可选值：get(获取),set(设置),raise(提高),lower(降低)",
                 },
                 "value": {
                     "type": "integer",
-                    "description": "值大小，可选值：0-100之间的整数"
-                }
+                    "description": "值大小，可选值：0-100之间的整数",
+                },
             },
-            "required": ["device_type", "action"]
-        }
-    }
+            "required": ["device_type", "action"],
+        },
+    },
 }
 
 
-@register_function('handle_speaker_volume_or_screen_brightness', handle_device_function_desc, ToolType.IOT_CTL)
-def handle_speaker_volume_or_screen_brightness(conn, device_type: str, action: str, value: int = None):
+@register_function(
+    "handle_speaker_volume_or_screen_brightness",
+    handle_device_function_desc,
+    ToolType.IOT_CTL,
+)
+def handle_speaker_volume_or_screen_brightness(
+    conn, device_type: str, action: str, value: int = None
+):
+    # 检查value是否为中文值
+    if (
+        value is not None
+        and isinstance(value, str)
+        and any("\u4e00" <= char <= "\u9fff" for char in str(value))
+    ):
+        raise Exception(
+            f"请直接告诉我要将{'音量' if device_type=='Speaker' else '亮度'}调整成多少"
+        )
+
     if device_type == "Speaker":
         method_name, property_name, device_name = "SetVolume", "volume", "音量"
     elif device_type == "Screen":
@@ -108,13 +133,25 @@ def handle_speaker_volume_or_screen_brightness(conn, device_type: str, action: s
     if action == "get":
         # get
         return _handle_device_action(
-            conn, _get_device_status, f"当前{device_name}", f"获取{device_name}失败",
-            device_name=device_name, device_type=device_type, property_name=property_name,
+            conn,
+            _get_device_status,
+            f"当前{device_name}",
+            f"获取{device_name}失败",
+            device_name=device_name,
+            device_type=device_type,
+            property_name=property_name,
         )
     else:
         # set, raise, lower
         return _handle_device_action(
-            conn, _set_device_property, f"{device_name}已调整到", f"{device_name}调整失败",
-            device_name=device_name, device_type=device_type, method_name=method_name,
-            property_name=property_name, new_value=value, action=action
+            conn,
+            _set_device_property,
+            f"{device_name}已调整到",
+            f"{device_name}调整失败",
+            device_name=device_name,
+            device_type=device_type,
+            method_name=method_name,
+            property_name=property_name,
+            new_value=value,
+            action=action,
         )

From c30c4649a483ac9059405344ed3f4170c566ae1f Mon Sep 17 00:00:00 2001
From: tiamohummer <zlx105@aliyun.com>
Date: Fri, 23 May 2025 17:41:22 +0800
Subject: [PATCH 04/16] =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E9=98=BF=E9=87=8C?=
 =?UTF-8?q?=E4=BA=91TTS=20private=5Fvoice=20=E5=88=A4=E6=96=AD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/core/providers/tts/aliyun.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/main/xiaozhi-server/core/providers/tts/aliyun.py b/main/xiaozhi-server/core/providers/tts/aliyun.py
index 61ab4364..4d2b1e13 100644
--- a/main/xiaozhi-server/core/providers/tts/aliyun.py
+++ b/main/xiaozhi-server/core/providers/tts/aliyun.py
@@ -81,7 +81,10 @@ class TTSProvider(TTSProviderBase):
         self.appkey = config.get("appkey")
         self.format = config.get("format", "wav")
         self.sample_rate = config.get("sample_rate", 16000)
-        self.voice = config.get("voice", "xiaoyun")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice","xiaoyun")
         self.volume = config.get("volume", 50)
         self.speech_rate = config.get("speech_rate", 0)
         self.pitch_rate = config.get("pitch_rate", 0)

From 98e2526f8a09fa58b2d591a587a615a82d60da5b Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Sat, 24 May 2025 02:15:06 +0800
Subject: [PATCH 05/16] =?UTF-8?q?update:=E5=90=88=E5=B9=B6chat=E5=92=8Ccha?=
 =?UTF-8?q?t=5Fwith=5Ffunction=5Fcalling?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/core/connection.py        | 153 +++++-------------
 .../core/handle/receiveAudioHandle.py         |  10 +-
 2 files changed, 40 insertions(+), 123 deletions(-)

diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py
index 74b612fe..e73b340d 100644
--- a/main/xiaozhi-server/core/connection.py
+++ b/main/xiaozhi-server/core/connection.py
@@ -506,106 +506,20 @@ class ConnectionHandler:
         # 更新系统prompt至上下文
         self.dialogue.update_system_message(self.prompt)
 
-    def chat(self, query):
-
-        self.dialogue.put(Message(role="user", content=query))
-
-        response_message = []
-        processed_chars = 0  # 跟踪已处理的字符位置
-        try:
-            # 使用带记忆的对话
-            memory_str = None
-            if self.memory is not None:
-                future = asyncio.run_coroutine_threadsafe(
-                    self.memory.query_memory(query), self.loop
-                )
-                memory_str = future.result()
-
-            self.logger.bind(tag=TAG).debug(f"记忆内容: {memory_str}")
-            llm_responses = self.llm.response(
-                self.session_id, self.dialogue.get_llm_dialogue_with_memory(memory_str)
-            )
-        except Exception as e:
-            self.logger.bind(tag=TAG).error(f"LLM 处理出错 {query}: {e}")
-            return None
-
-        self.llm_finish_task = False
-        text_index = 0
-        for content in llm_responses:
-            response_message.append(content)
-            if self.client_abort:
-                break
-
-            # 合并当前全部文本并处理未分割部分
-            full_text = "".join(response_message)
-            current_text = full_text[processed_chars:]  # 从未处理的位置开始
-
-            # 查找最后一个有效标点
-            punctuations = ("。", ".", "？", "?", "！", "!", "；", ";", "：")
-            last_punct_pos = -1
-            number_flag = True
-            for punct in punctuations:
-                pos = current_text.rfind(punct)
-                prev_char = current_text[pos - 1] if pos - 1 >= 0 else ""
-                # 如果.前面是数字统一判断为小数
-                if prev_char.isdigit() and punct == ".":
-                    number_flag = False
-                if pos > last_punct_pos and number_flag:
-                    last_punct_pos = pos
-
-            # 找到分割点则处理
-            if last_punct_pos != -1:
-                segment_text_raw = current_text[: last_punct_pos + 1]
-                segment_text = get_string_no_punctuation_or_emoji(segment_text_raw)
-                if segment_text:
-                    # 强制设置空字符，测试TTS出错返回语音的健壮性
-                    # if text_index % 2 == 0:
-                    #     segment_text = " "
-                    text_index += 1
-                    self.recode_first_last_text(segment_text, text_index)
-                    future = self.executor.submit(
-                        self.speak_and_play, segment_text, text_index
-                    )
-                    self.tts_queue.put((future, text_index))
-                    processed_chars += len(segment_text_raw)  # 更新已处理字符位置
-
-        # 处理最后剩余的文本
-        full_text = "".join(response_message)
-        remaining_text = full_text[processed_chars:]
-        if remaining_text:
-            segment_text = get_string_no_punctuation_or_emoji(remaining_text)
-            if segment_text:
-                text_index += 1
-                self.recode_first_last_text(segment_text, text_index)
-                future = self.executor.submit(
-                    self.speak_and_play, segment_text, text_index
-                )
-                self.tts_queue.put((future, text_index))
-
-        self.llm_finish_task = True
-        self.dialogue.put(Message(role="assistant", content="".join(response_message)))
-        self.logger.bind(tag=TAG).debug(
-            json.dumps(self.dialogue.get_llm_dialogue(), indent=4, ensure_ascii=False)
-        )
-        return True
-
-    def chat_with_function_calling(self, query, tool_call=False):
-        self.logger.bind(tag=TAG).debug(f"Chat with function calling start: {query}")
-        """Chat with function calling for intent detection using streaming"""
+    def chat(self, query, tool_call=False):
+        self.logger.bind(tag=TAG).debug(f"Chat: {query}")
 
         if not tool_call:
             self.dialogue.put(Message(role="user", content=query))
 
         # Define intent functions
         functions = None
-        if hasattr(self, "func_handler"):
+        if self.intent_type == "function_call" and hasattr(self, "func_handler"):
             functions = self.func_handler.get_functions()
         response_message = []
         processed_chars = 0  # 跟踪已处理的字符位置
 
         try:
-            start_time = time.time()
-
             # 使用带记忆的对话
             memory_str = None
             if self.memory is not None:
@@ -614,14 +528,18 @@ class ConnectionHandler:
                 )
                 memory_str = future.result()
 
-            # self.logger.bind(tag=TAG).info(f"对话记录: {self.dialogue.get_llm_dialogue_with_memory(memory_str)}")
-
-            # 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),
-                functions=functions,
-            )
+            if 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),
+                    functions=functions,
+                )
+            else:
+                llm_responses = self.llm.response(
+                    self.session_id,
+                    self.dialogue.get_llm_dialogue_with_memory(memory_str),
+                )
         except Exception as e:
             self.logger.bind(tag=TAG).error(f"LLM 处理出错 {query}: {e}")
             return None
@@ -637,27 +555,28 @@ class ConnectionHandler:
         content_arguments = ""
 
         for response in llm_responses:
-            content, tools_call = response
+            if self.intent_type == "function_call":
+                content, tools_call = response
+                if "content" in response:
+                    content = response["content"]
+                    tools_call = None
+                if content is not None and len(content) > 0:
+                    content_arguments += content
 
-            if "content" in response:
-                content = response["content"]
-                tools_call = None
-            if content is not None and len(content) > 0:
-                content_arguments += content
-
-            if not tool_call_flag and content_arguments.startswith("<tool_call>"):
-                # print("content_arguments", content_arguments)
-                tool_call_flag = True
-
-            if tools_call is not None:
-                tool_call_flag = True
-                if tools_call[0].id is not None:
-                    function_id = tools_call[0].id
-                if tools_call[0].function.name is not None:
-                    function_name = tools_call[0].function.name
-                if tools_call[0].function.arguments is not None:
-                    function_arguments += tools_call[0].function.arguments
+                if not tool_call_flag and content_arguments.startswith("<tool_call>"):
+                    # print("content_arguments", content_arguments)
+                    tool_call_flag = True
 
+                if tools_call is not None:
+                    tool_call_flag = True
+                    if tools_call[0].id is not None:
+                        function_id = tools_call[0].id
+                    if tools_call[0].function.name is not None:
+                        function_name = tools_call[0].function.name
+                    if tools_call[0].function.arguments is not None:
+                        function_arguments += tools_call[0].function.arguments
+            else:
+                content = response
             if content is not None and len(content) > 0:
                 if not tool_call_flag:
                     response_message.append(content)
@@ -853,7 +772,7 @@ class ConnectionHandler:
                         content=text,
                     )
                 )
-                self.chat_with_function_calling(text, tool_call=True)
+                self.chat(text, tool_call=True)
         elif result.action == Action.NOTFOUND or result.action == Action.ERROR:
             text = result.result
             self.recode_first_last_text(text, text_index)
diff --git a/main/xiaozhi-server/core/handle/receiveAudioHandle.py b/main/xiaozhi-server/core/handle/receiveAudioHandle.py
index 9c693751..2584ab83 100644
--- a/main/xiaozhi-server/core/handle/receiveAudioHandle.py
+++ b/main/xiaozhi-server/core/handle/receiveAudioHandle.py
@@ -39,7 +39,9 @@ async def handleAudioMessage(conn, audio):
         if len(conn.asr_audio) < 15:
             conn.asr_server_receive = True
         else:
-            raw_text, _ = await conn.asr.speech_to_text(conn.asr_audio, conn.session_id)  # 确保ASR模块返回原始文本
+            raw_text, _ = await conn.asr.speech_to_text(
+                conn.asr_audio, conn.session_id
+            )  # 确保ASR模块返回原始文本
             conn.logger.bind(tag=TAG).info(f"识别文本: {raw_text}")
             text_len, _ = remove_punctuation_and_length(raw_text)
             if text_len > 0:
@@ -76,11 +78,7 @@ async def startToChat(conn, text):
 
     # 意图未被处理，继续常规聊天流程
     await send_stt_message(conn, text)
-    if conn.intent_type == "function_call":
-        # 使用支持function calling的聊天方法
-        conn.executor.submit(conn.chat_with_function_calling, text)
-    else:
-        conn.executor.submit(conn.chat, text)
+    conn.executor.submit(conn.chat, text)
 
 
 async def no_voice_close_connect(conn):

From d97f8b2e9a2b24b474dfb92957f61225980d6589 Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Sat, 24 May 2025 02:17:49 +0800
Subject: [PATCH 06/16] =?UTF-8?q?update:=E4=BE=9B=E5=BA=94=E5=99=A8?=
 =?UTF-8?q?=E7=AE=A1=E7=90=86=E6=9B=B4=E5=90=8D=E4=B8=BA=E5=AD=97=E6=AE=B5?=
 =?UTF-8?q?=E7=AE=A1=E7=90=86=EF=BC=8C=E9=98=B2=E6=AD=A2=E6=B7=B7=E6=B7=86?=
 =?UTF-8?q?=E6=A8=A1=E5=9E=8B=E7=AE=A1=E7=90=86?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/manager-web/src/components/HeaderBar.vue     | 2 +-
 main/manager-web/src/views/ProviderManagement.vue | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/main/manager-web/src/components/HeaderBar.vue b/main/manager-web/src/components/HeaderBar.vue
index 70b64f61..d0a36acb 100644
--- a/main/manager-web/src/components/HeaderBar.vue
+++ b/main/manager-web/src/components/HeaderBar.vue
@@ -51,7 +51,7 @@
               字典管理
             </el-dropdown-item>
             <el-dropdown-item @click.native="goProviderManagement">
-              供应器管理
+              字段管理
             </el-dropdown-item>
             <el-dropdown-item @click.native="goServerSideManagement">
               服务端管理
diff --git a/main/manager-web/src/views/ProviderManagement.vue b/main/manager-web/src/views/ProviderManagement.vue
index 7634b511..5af816f6 100644
--- a/main/manager-web/src/views/ProviderManagement.vue
+++ b/main/manager-web/src/views/ProviderManagement.vue
@@ -3,7 +3,7 @@
     <HeaderBar />
 
     <div class="operation-bar">
-      <h2 class="page-title">供应器管理</h2>
+      <h2 class="page-title">字段管理</h2>
       <div class="right-operations">
         <el-dropdown trigger="click" @command="handleSelectModelType" @visible-change="handleDropdownVisibleChange">
           <el-button class="category-btn">

From 472106390dca8f3656153eae396f5b58a7911dd9 Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Sat, 24 May 2025 09:39:10 +0800
Subject: [PATCH 07/16] =?UTF-8?q?update:=E4=BC=98=E5=8C=96=E9=9F=B3?=
 =?UTF-8?q?=E9=A2=91=E6=92=AD=E6=94=BE=E6=96=B9=E6=B3=95?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/core/connection.py        | 46 +++++++++++--------
 .../core/handle/intentHandler.py              | 12 ++---
 .../plugins_func/functions/play_music.py      | 20 +++-----
 3 files changed, 38 insertions(+), 40 deletions(-)

diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py
index e73b340d..ea0be02d 100644
--- a/main/xiaozhi-server/core/connection.py
+++ b/main/xiaozhi-server/core/connection.py
@@ -14,6 +14,8 @@ import websockets
 from typing import Dict, Any
 from plugins_func.loadplugins import auto_import_modules
 from config.logger import setup_logging
+from config.config_loader import get_project_dir
+from core.utils import p3
 from core.utils.dialogue import Message, Dialogue
 from core.handle.textHandle import handleTextMessage
 from core.utils.util import (
@@ -615,7 +617,7 @@ class ConnectionHandler:
                             text_index += 1
                             self.recode_first_last_text(segment_text, text_index)
                             future = self.executor.submit(
-                                self.speak_and_play, segment_text, text_index
+                                self.speak_and_play, None, segment_text, text_index
                             )
                             self.tts_queue.put((future, text_index))
                             # 更新已处理字符位置
@@ -674,7 +676,7 @@ class ConnectionHandler:
                 text_index += 1
                 self.recode_first_last_text(segment_text, text_index)
                 future = self.executor.submit(
-                    self.speak_and_play, segment_text, text_index
+                    self.speak_and_play, None, segment_text, text_index
                 )
                 self.tts_queue.put((future, text_index))
 
@@ -737,7 +739,7 @@ class ConnectionHandler:
         if result.action == Action.RESPONSE:  # 直接回复前端
             text = result.response
             self.recode_first_last_text(text, text_index)
-            future = self.executor.submit(self.speak_and_play, text, text_index)
+            future = self.executor.submit(self.speak_and_play, None, text, text_index)
             self.tts_queue.put((future, text_index))
             self.dialogue.put(Message(role="assistant", content=text))
         elif result.action == Action.REQLLM:  # 调用函数后再请求llm生成回复
@@ -776,7 +778,7 @@ class ConnectionHandler:
         elif result.action == Action.NOTFOUND or result.action == Action.ERROR:
             text = result.result
             self.recode_first_last_text(text, text_index)
-            future = self.executor.submit(self.speak_and_play, text, text_index)
+            future = self.executor.submit(self.speak_and_play, None, text, text_index)
             self.tts_queue.put((future, text_index))
             self.dialogue.put(Message(role="assistant", content=text))
         else:
@@ -803,11 +805,7 @@ class ConnectionHandler:
                     self.logger.bind(tag=TAG).debug("正在处理TTS任务...")
                     tts_timeout = int(self.config.get("tts_timeout", 10))
                     tts_file, text, _ = future.result(timeout=tts_timeout)
-                    if text is None or len(text) <= 0:
-                        self.logger.bind(tag=TAG).error(
-                            f"TTS出错：{text_index}: tts text is empty"
-                        )
-                    elif tts_file is None:
+                    if tts_file is None:
                         self.logger.bind(tag=TAG).error(
                             f"TTS出错： file is empty: {text_index}: {text}"
                         )
@@ -816,12 +814,16 @@ class ConnectionHandler:
                             f"TTS生成：文件路径: {tts_file}"
                         )
                         if os.path.exists(tts_file):
-                            if self.audio_format == "pcm":
+                            if tts_file.endswith(".p3"):
+                                audio_datas, _ = p3.decode_opus_from_file(tts_file)
+                            elif self.audio_format == "pcm":
                                 audio_datas, _ = self.tts.audio_to_pcm_data(tts_file)
                             else:
                                 audio_datas, _ = self.tts.audio_to_opus_data(tts_file)
                             # 在这里上报TTS数据
-                            enqueue_tts_report(self, text, audio_datas)
+                            enqueue_tts_report(
+                                self, tts_file if text is None else text, audio_datas
+                            )
                         else:
                             self.logger.bind(tag=TAG).error(
                                 f"TTS出错：文件不存在{tts_file}"
@@ -837,6 +839,7 @@ class ConnectionHandler:
                     self.tts.delete_audio_file
                     and tts_file is not None
                     and os.path.exists(tts_file)
+                    and tts_file.startswith(self.tts.output_file)
                 ):
                     os.remove(tts_file)
             except Exception as e:
@@ -903,18 +906,21 @@ class ConnectionHandler:
 
         self.logger.bind(tag=TAG).info("聊天记录上报线程已退出")
 
-    def speak_and_play(self, text, text_index=0):
-        if text is None or len(text) <= 0:
-            self.logger.bind(tag=TAG).info(f"无需tts转换，query为空，{text}")
-            return None, text, text_index
-        tts_file = self.tts.to_tts(text)
+    def speak_and_play(self, file_path, content, text_index=0):
+        if file_path is not None:
+            self.logger.bind(tag=TAG).info(f"无需tts转换: 从文件播放，{file_path}")
+            return file_path, content, text_index
+        if content is None or len(content) <= 0:
+            self.logger.bind(tag=TAG).info(f"无需tts转换，query为空，{content}")
+            return None, content, text_index
+        tts_file = self.tts.to_tts(content)
         if tts_file is None:
-            self.logger.bind(tag=TAG).error(f"tts转换失败，{text}")
-            return None, text, text_index
+            self.logger.bind(tag=TAG).error(f"tts转换失败，{content}")
+            return None, content, text_index
         self.logger.bind(tag=TAG).debug(f"TTS 文件生成完毕: {tts_file}")
         if self.max_output_size > 0:
-            add_device_output(self.headers.get("device-id"), len(text))
-        return tts_file, text, text_index
+            add_device_output(self.headers.get("device-id"), len(content))
+        return tts_file, content, text_index
 
     def clearSpeakStatus(self):
         self.logger.bind(tag=TAG).debug(f"清除服务端讲话状态")
diff --git a/main/xiaozhi-server/core/handle/intentHandler.py b/main/xiaozhi-server/core/handle/intentHandler.py
index 495da96f..e61b1265 100644
--- a/main/xiaozhi-server/core/handle/intentHandler.py
+++ b/main/xiaozhi-server/core/handle/intentHandler.py
@@ -109,21 +109,21 @@ async def process_intent_result(conn, intent_result, original_text):
                     if result.action == Action.RESPONSE:  # 直接回复前端
                         text = result.response
                         if text is not None:
-                            speak_and_play(conn, text)
+                            speak_txt(conn, text)
                     elif result.action == Action.REQLLM:  # 调用函数后再请求llm生成回复
                         text = result.result
                         conn.dialogue.put(Message(role="tool", content=text))
                         llm_result = conn.intent.replyResult(text, original_text)
                         if llm_result is None:
                             llm_result = text
-                        speak_and_play(conn, llm_result)
+                        speak_txt(conn, llm_result)
                     elif (
                         result.action == Action.NOTFOUND
                         or result.action == Action.ERROR
                     ):
                         text = result.result
                         if text is not None:
-                            speak_and_play(conn, text)
+                            speak_txt(conn, text)
                     elif function_name != "play_music":
                         # For backward compatibility with original code
                         # 获取当前最新的文本索引
@@ -131,7 +131,7 @@ async def process_intent_result(conn, intent_result, original_text):
                         if text is None:
                             text = result.result
                         if text is not None:
-                            speak_and_play(conn, text)
+                            speak_txt(conn, text)
 
             # 将函数执行放在线程池中
             conn.executor.submit(process_function_call)
@@ -142,12 +142,12 @@ async def process_intent_result(conn, intent_result, original_text):
         return False
 
 
-def speak_and_play(conn, text):
+def speak_txt(conn, text):
     text_index = (
         conn.tts_last_text_index + 1 if hasattr(conn, "tts_last_text_index") else 0
     )
     conn.recode_first_last_text(text, text_index)
-    future = conn.executor.submit(conn.speak_and_play, text, text_index)
+    future = conn.executor.submit(conn.speak_and_play, None, text, text_index)
     conn.llm_finish_task = True
     conn.tts_queue.put((future, text_index))
     conn.dialogue.put(Message(role="assistant", content=text))
diff --git a/main/xiaozhi-server/plugins_func/functions/play_music.py b/main/xiaozhi-server/plugins_func/functions/play_music.py
index 3de19d76..76465641 100644
--- a/main/xiaozhi-server/plugins_func/functions/play_music.py
+++ b/main/xiaozhi-server/plugins_func/functions/play_music.py
@@ -216,24 +216,16 @@ async def play_local_music(conn, specific_file=None):
         text = _get_random_play_prompt(selected_music)
         await send_stt_message(conn, text)
         conn.dialogue.put(Message(role="assistant", content=text))
-        conn.tts_first_text_index = 0
-        conn.tts_last_text_index = 0
 
-        tts_file = await asyncio.to_thread(conn.tts.to_tts, text)
-        if tts_file is not None and os.path.exists(tts_file):
-            conn.tts_last_text_index = 1
-            opus_packets, _ = conn.tts.audio_to_opus_data(tts_file)
-            conn.audio_play_queue.put((opus_packets, None, 0))
-            os.remove(tts_file)
+        conn.recode_first_last_text(text, 0)
+        future = conn.executor.submit(conn.speak_and_play, None, text, 0)
+        conn.tts_queue.put((future, 0))
 
+        conn.recode_first_last_text(text, 1)
+        future = conn.executor.submit(conn.speak_and_play, music_path, None, 1)
+        conn.tts_queue.put((future, 1))
         conn.llm_finish_task = True
 
-        if music_path.endswith(".p3"):
-            opus_packets, _ = p3.decode_opus_from_file(music_path)
-        else:
-            opus_packets, _ = conn.tts.audio_to_opus_data(music_path)
-        conn.audio_play_queue.put((opus_packets, None, conn.tts_last_text_index))
-
     except Exception as e:
         conn.logger.bind(tag=TAG).error(f"播放音乐失败: {str(e)}")
         conn.logger.bind(tag=TAG).error(f"详细错误: {traceback.format_exc()}")

From 562424b74db9d2e25fab3f69267ed99f33058f4c Mon Sep 17 00:00:00 2001
From: CGD <3030332422@qq.com>
Date: Sun, 25 May 2025 00:09:36 +0800
Subject: [PATCH 08/16] =?UTF-8?q?fix=EF=BC=9A=E4=BF=AE=E5=A4=8D=E2=80=9C?=
 =?UTF-8?q?=E5=B0=8F=E6=99=BA=E6=9C=8D=E5=8A=A1=E5=99=A8=E6=B5=8B=E8=AF=95?=
 =?UTF-8?q?=E9=A1=B5=E9=9D=A2=E6=92=AD=E6=94=BE=E8=AF=AD=E9=9F=B3=E9=97=AE?=
 =?UTF-8?q?=E9=A2=98=E2=80=9D?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/test/test_page.html | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/main/xiaozhi-server/test/test_page.html b/main/xiaozhi-server/test/test_page.html
index d9b2eff6..1df5cae2 100644
--- a/main/xiaozhi-server/test/test_page.html
+++ b/main/xiaozhi-server/test/test_page.html
@@ -879,6 +879,7 @@
                                         // 流已结束且没有更多数据
                                         log("音频播放完成", 'info');
                                         isAudioPlaying = false;
+                                        this.endOfStream = false;
                                         streamingContext = null;
                                     } else {
                                         // 等待更多数据
@@ -1409,6 +1410,17 @@
                 };
 
                 websocket.onclose = () => {
+
+                    // 清理音频缓冲和播放状态
+                    audioBufferQueue = [];
+                    isAudioBuffering = false;
+                    isAudioPlaying = false;
+                    streamingContext = null;
+                    if (visualizationRequest) {
+                        cancelAnimationFrame(visualizationRequest);
+                        visualizationRequest = null;
+                    }
+
                     log('已断开连接', 'info');
                     connectionStatus.textContent = 'ws已断开';
                     connectionStatus.style.color = 'red';
@@ -1563,6 +1575,10 @@
             const message = messageInput.value.trim();
             if (message === '' || !websocket || websocket.readyState !== WebSocket.OPEN) return;
 
+            audioBufferQueue = [];
+            isAudioBuffering = false;
+            isAudioPlaying = false;
+
             try {
                 // 直接发送listen消息，不需要重复发送hello
                 const listenMessage = {
@@ -2382,6 +2398,8 @@
                     // 如果收到的是第一个音频包，开始缓冲过程
                     if (audioBufferQueue.length === 1 && !isAudioBuffering && !isAudioPlaying) {
                         startAudioBuffering();
+                    } else if (isAudioPlaying && streamingContext) {
+                        streamingContext.decodeOpusFrames([opusData]);
                     }
                 } else {
                     log('收到空音频数据帧，可能是结束标志', 'warning');

From e0da59096a23dd67469f393026b56546e136b0b9 Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Sun, 25 May 2025 09:10:11 +0800
Subject: [PATCH 09/16] =?UTF-8?q?=E4=BF=AE=E5=A4=8D=E6=B5=8B=E8=AF=95?=
 =?UTF-8?q?=E9=A1=B5=E9=9D=A2=E9=9F=B3=E9=A2=91=E9=87=8D=E5=A4=8D=E6=92=AD?=
 =?UTF-8?q?=E6=94=BE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/test/test_page.html | 18 ------------------
 1 file changed, 18 deletions(-)

diff --git a/main/xiaozhi-server/test/test_page.html b/main/xiaozhi-server/test/test_page.html
index 1df5cae2..d9b2eff6 100644
--- a/main/xiaozhi-server/test/test_page.html
+++ b/main/xiaozhi-server/test/test_page.html
@@ -879,7 +879,6 @@
                                         // 流已结束且没有更多数据
                                         log("音频播放完成", 'info');
                                         isAudioPlaying = false;
-                                        this.endOfStream = false;
                                         streamingContext = null;
                                     } else {
                                         // 等待更多数据
@@ -1410,17 +1409,6 @@
                 };
 
                 websocket.onclose = () => {
-
-                    // 清理音频缓冲和播放状态
-                    audioBufferQueue = [];
-                    isAudioBuffering = false;
-                    isAudioPlaying = false;
-                    streamingContext = null;
-                    if (visualizationRequest) {
-                        cancelAnimationFrame(visualizationRequest);
-                        visualizationRequest = null;
-                    }
-
                     log('已断开连接', 'info');
                     connectionStatus.textContent = 'ws已断开';
                     connectionStatus.style.color = 'red';
@@ -1575,10 +1563,6 @@
             const message = messageInput.value.trim();
             if (message === '' || !websocket || websocket.readyState !== WebSocket.OPEN) return;
 
-            audioBufferQueue = [];
-            isAudioBuffering = false;
-            isAudioPlaying = false;
-
             try {
                 // 直接发送listen消息，不需要重复发送hello
                 const listenMessage = {
@@ -2398,8 +2382,6 @@
                     // 如果收到的是第一个音频包，开始缓冲过程
                     if (audioBufferQueue.length === 1 && !isAudioBuffering && !isAudioPlaying) {
                         startAudioBuffering();
-                    } else if (isAudioPlaying && streamingContext) {
-                        streamingContext.decodeOpusFrames([opusData]);
                     }
                 } else {
                     log('收到空音频数据帧，可能是结束标志', 'warning');

From d7564a65f7a15760a36f2c485583f552b6a58448 Mon Sep 17 00:00:00 2001
From: Minamiyama <minamiyama@qq.com>
Date: Sun, 25 May 2025 15:24:06 +0800
Subject: [PATCH 10/16] =?UTF-8?q?refactor(test=5Fpage.html):=20=E4=BC=98?=
 =?UTF-8?q?=E5=8C=96UI=E5=B8=83=E5=B1=80=E5=92=8C=E8=BE=93=E5=85=A5?=
 =?UTF-8?q?=E6=8F=90=E7=A4=BA=EF=BC=8C=E5=A2=9E=E5=8A=A0=E6=9C=AC=E5=9C=B0?=
 =?UTF-8?q?=E5=AD=98=E5=82=A8=E5=8A=9F=E8=83=BD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 在OTA和WebSocket服务器地址输入框中添加更详细的占位符提示
- 增加本地存储功能，保存并恢复OTA和WebSocket服务器地址
---
 main/xiaozhi-server/test/test_page.html | 40 ++++++++++++++++---------
 1 file changed, 26 insertions(+), 14 deletions(-)

diff --git a/main/xiaozhi-server/test/test_page.html b/main/xiaozhi-server/test/test_page.html
index d9b2eff6..d2151acc 100644
--- a/main/xiaozhi-server/test/test_page.html
+++ b/main/xiaozhi-server/test/test_page.html
@@ -14,7 +14,7 @@
         }
 
         .container {
-            max-width: 800px;
+            max-width: 1000px;
             margin: 0 auto;
             background-color: white;
             border-radius: 10px;
@@ -482,9 +482,10 @@
                 </span>
             </h2>
             <div class="connection-controls">
-                <input type="text" id="otaUrl" value="http://127.0.0.1:8002/xiaozhi/ota/" placeholder="OTA服务器地址" />
+                <input type="text" id="otaUrl" value="http://127.0.0.1:8002/xiaozhi/ota/"
+                    placeholder="OTA服务器地址，如：http://127.0.0.1:8002/xiaozhi/ota/" />
                 <input type="text" id="serverUrl" value="ws://127.0.0.1:8000/xiaozhi/v1/"
-                    placeholder="WebSocket服务器地址" />
+                    placeholder="WebSocket服务器地址，如：ws://127.0.0.1:8000/xiaozhi/v1/" />
                 <button id="connectButton">连接</button>
                 <button id="authTestButton">测试认证</button>
             </div>
@@ -1061,7 +1062,7 @@
             }
         }
 
-        // 初始化音频录制和处理 
+        // 初始化音频录制和处理
         async function initAudio() {
             try {
                 // 请求麦克风权限
@@ -1306,7 +1307,8 @@
                 // 先检查OTA状态
                 log('正在检查OTA状态...', 'info');
                 const otaUrl = document.getElementById('otaUrl').value.trim();
-
+                localStorage.setItem('otaUrl', otaUrl);
+                localStorage.setItem('wsUrl', url);
                 try {
                     const otaResponse = await fetch(otaUrl, {
                         method: 'POST',
@@ -1633,6 +1635,16 @@
             // 初始更新显示值
             updateDisplayValues();
 
+            const savedOtaUrl = localStorage.getItem('otaUrl');
+            if (savedOtaUrl) {
+                document.getElementById('otaUrl').value = savedOtaUrl;
+            }
+
+            const savedWsUrl = localStorage.getItem('wsUrl');
+            if (savedWsUrl) {
+                document.getElementById('serverUrl').value = savedWsUrl;
+            }
+
             // 切换面板显示
             toggleButton.addEventListener('click', () => {
                 const isExpanded = configPanel.classList.contains('expanded');
@@ -1954,7 +1966,7 @@
                     this.buffer = new Int16Array(this.frameSize);
                     this.bufferIndex = 0;
                     this.isRecording = false;
-                    
+
                     // 监听来自主线程的消息
                     this.port.onmessage = (event) => {
                         if (event.data.command === 'start') {
@@ -1962,7 +1974,7 @@
                             this.port.postMessage({ type: 'status', status: 'started' });
                         } else if (event.data.command === 'stop') {
                             this.isRecording = false;
-                            
+
                             // 发送剩余的缓冲区
                             if (this.bufferIndex > 0) {
                                 const finalBuffer = this.buffer.slice(0, this.bufferIndex);
@@ -1972,18 +1984,18 @@
                                 });
                                 this.bufferIndex = 0;
                             }
-                            
+
                             this.port.postMessage({ type: 'status', status: 'stopped' });
                         }
                     };
                 }
-                
+
                 process(inputs, outputs, parameters) {
                     if (!this.isRecording) return true;
-                    
+
                     const input = inputs[0][0]; // 获取第一个输入通道
                     if (!input) return true;
-                    
+
                     // 将浮点采样转换为16位整数并存储
                     for (let i = 0; i < input.length; i++) {
                         if (this.bufferIndex >= this.frameSize) {
@@ -1994,15 +2006,15 @@
                             });
                             this.bufferIndex = 0;
                         }
-                        
+
                         // 转换为16位整数 (-32768到32767)
                         this.buffer[this.bufferIndex++] = Math.max(-32768, Math.min(32767, Math.floor(input[i] * 32767)));
                     }
-                    
+
                     return true;
                 }
             }
-            
+
             registerProcessor('audio-recorder-processor', AudioRecorderProcessor);
         `;
 

From 94c92c5f3884f5547327af8d7a393d3205ffa836 Mon Sep 17 00:00:00 2001
From: CGD <3030332422@qq.com>
Date: Mon, 26 May 2025 11:23:42 +0800
Subject: [PATCH 11/16] =?UTF-8?q?fix:=E4=BF=AE=E5=A4=8D=E6=B5=8B=E8=AF=95?=
 =?UTF-8?q?=E9=A1=B5=E9=9D=A2=E9=9F=B3=E9=A2=91=E9=87=8D=E5=A4=8D=E6=92=AD?=
 =?UTF-8?q?=E6=94=BE=E9=97=AE=E9=A2=98?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/test/test_page.html | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/main/xiaozhi-server/test/test_page.html b/main/xiaozhi-server/test/test_page.html
index d9b2eff6..39c08d5f 100644
--- a/main/xiaozhi-server/test/test_page.html
+++ b/main/xiaozhi-server/test/test_page.html
@@ -879,6 +879,7 @@
                                         // 流已结束且没有更多数据
                                         log("音频播放完成", 'info');
                                         isAudioPlaying = false;
+                                        this.endOfStream = false;
                                         streamingContext = null;
                                     } else {
                                         // 等待更多数据
@@ -1563,6 +1564,10 @@
             const message = messageInput.value.trim();
             if (message === '' || !websocket || websocket.readyState !== WebSocket.OPEN) return;
 
+            audioBufferQueue = [];
+            isAudioBuffering = false;
+            isAudioPlaying = false;
+
             try {
                 // 直接发送listen消息，不需要重复发送hello
                 const listenMessage = {

From 9a0240ef3e0a72633b905b44b2cea6e4c1280a25 Mon Sep 17 00:00:00 2001
From: CGD <3030332422@qq.com>
Date: Mon, 26 May 2025 15:34:21 +0800
Subject: [PATCH 12/16] =?UTF-8?q?update:=E4=BC=98=E5=8C=96=E4=BA=86?=
 =?UTF-8?q?=E9=A1=B5=E9=9D=A2=E6=A0=B7=E5=BC=8F?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/manager-web/src/views/ModelConfig.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main/manager-web/src/views/ModelConfig.vue b/main/manager-web/src/views/ModelConfig.vue
index aa788f2f..8abf8bb6 100644
--- a/main/manager-web/src/views/ModelConfig.vue
+++ b/main/manager-web/src/views/ModelConfig.vue
@@ -467,7 +467,7 @@ export default {
 .main-wrapper {
   margin: 5px 22px;
   border-radius: 15px;
-  min-height: calc(100vh - 24vh);
+  min-height: calc(100vh - 26vh);
   height: auto;
   max-height: 80vh;
   box-shadow: 0 2px 12px rgba(0, 0, 0, 0.1);

From 761fc05331164d87e984a6b0ef018219a652906c Mon Sep 17 00:00:00 2001
From: goodyhao <865700600@qq.com>
Date: Mon, 26 May 2025 20:27:22 +0800
Subject: [PATCH 13/16] =?UTF-8?q?feat:=20=E5=A2=9E=E5=8A=A0=E4=B8=8A?=
 =?UTF-8?q?=E6=8A=A5=E6=97=B6=E9=97=B4?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/manager-api/pom.xml                           |  2 +-
 .../agent/dto/AgentChatHistoryReportDTO.java       |  2 ++
 .../agent/service/AgentChatAudioService.java       |  2 +-
 .../biz/impl/AgentChatHistoryBizServiceImpl.java   | 12 +++++++-----
 .../service/impl/AgentChatAudioServiceImpl.java    |  2 +-
 .../src/main/resources/application-dev.yml         |  2 +-
 main/xiaozhi-server/config/manage_api_client.py    |  3 ++-
 main/xiaozhi-server/core/connection.py             | 14 ++++++++++----
 main/xiaozhi-server/core/handle/reportHandle.py    | 13 ++++++++-----
 9 files changed, 33 insertions(+), 19 deletions(-)

diff --git a/main/manager-api/pom.xml b/main/manager-api/pom.xml
index 883295bf..bc4030c0 100644
--- a/main/manager-api/pom.xml
+++ b/main/manager-api/pom.xml
@@ -258,4 +258,4 @@
             </plugin>
         </plugins>
     </build>
-</project>
\ No newline at end of file
+</project>
diff --git a/main/manager-api/src/main/java/xiaozhi/modules/agent/dto/AgentChatHistoryReportDTO.java b/main/manager-api/src/main/java/xiaozhi/modules/agent/dto/AgentChatHistoryReportDTO.java
index bdaed950..ae58783f 100644
--- a/main/manager-api/src/main/java/xiaozhi/modules/agent/dto/AgentChatHistoryReportDTO.java
+++ b/main/manager-api/src/main/java/xiaozhi/modules/agent/dto/AgentChatHistoryReportDTO.java
@@ -28,4 +28,6 @@ public class AgentChatHistoryReportDTO {
     private String content;
     @Schema(description = "base64编码的opus音频数据", example = "")
     private String audioBase64;
+    @Schema(description = "上报时间，十位时间戳，空时默认使用当前时间", example = "1745657732")
+    private Long reportTime;
 }
diff --git a/main/manager-api/src/main/java/xiaozhi/modules/agent/service/AgentChatAudioService.java b/main/manager-api/src/main/java/xiaozhi/modules/agent/service/AgentChatAudioService.java
index e284b69f..04be9f36 100644
--- a/main/manager-api/src/main/java/xiaozhi/modules/agent/service/AgentChatAudioService.java
+++ b/main/manager-api/src/main/java/xiaozhi/modules/agent/service/AgentChatAudioService.java
@@ -27,4 +27,4 @@ public interface AgentChatAudioService extends IService<AgentChatAudioEntity> {
      * @return 音频数据
      */
     byte[] getAudio(String audioId);
-}
\ No newline at end of file
+}
diff --git a/main/manager-api/src/main/java/xiaozhi/modules/agent/service/biz/impl/AgentChatHistoryBizServiceImpl.java b/main/manager-api/src/main/java/xiaozhi/modules/agent/service/biz/impl/AgentChatHistoryBizServiceImpl.java
index bf6c188b..087c1b9d 100644
--- a/main/manager-api/src/main/java/xiaozhi/modules/agent/service/biz/impl/AgentChatHistoryBizServiceImpl.java
+++ b/main/manager-api/src/main/java/xiaozhi/modules/agent/service/biz/impl/AgentChatHistoryBizServiceImpl.java
@@ -47,7 +47,8 @@ public class AgentChatHistoryBizServiceImpl implements AgentChatHistoryBizServic
     public Boolean report(AgentChatHistoryReportDTO report) {
         String macAddress = report.getMacAddress();
         Byte chatType = report.getChatType();
-        log.info("小智设备聊天上报请求: macAddress={}, type={}", macAddress, chatType);
+        Long reportTimeMillis = null != report.getReportTime() ? report.getReportTime() * 1000 : System.currentTimeMillis();
+        log.info("小智设备聊天上报请求: macAddress={}, type={} reportTime={}", macAddress, chatType, reportTimeMillis);
 
         // 根据设备MAC地址查询对应的默认智能体，判断是否需要上报
         AgentEntity agentEntity = agentService.getDefaultAgentByMacAddress(macAddress);
@@ -59,10 +60,10 @@ public class AgentChatHistoryBizServiceImpl implements AgentChatHistoryBizServic
         String agentId = agentEntity.getId();
 
         if (Objects.equals(chatHistoryConf, Constant.ChatHistoryConfEnum.RECORD_TEXT.getCode())) {
-            saveChatText(report, agentId, macAddress, null);
+            saveChatText(report, agentId, macAddress, null, reportTimeMillis);
         } else if (Objects.equals(chatHistoryConf, Constant.ChatHistoryConfEnum.RECORD_TEXT_AUDIO.getCode())) {
             String audioId = saveChatAudio(report);
-            saveChatText(report, agentId, macAddress, audioId);
+            saveChatText(report, agentId, macAddress, audioId, reportTimeMillis);
         }
 
         // 更新设备最后对话时间
@@ -92,8 +93,7 @@ public class AgentChatHistoryBizServiceImpl implements AgentChatHistoryBizServic
     /**
      * 组装上报数据
      */
-    private void saveChatText(AgentChatHistoryReportDTO report, String agentId, String macAddress, String audioId) {
-
+    private void saveChatText(AgentChatHistoryReportDTO report, String agentId, String macAddress, String audioId, Long reportTime) {
         // 构建聊天记录实体
         AgentChatHistoryEntity entity = AgentChatHistoryEntity.builder()
                 .macAddress(macAddress)
@@ -102,6 +102,8 @@ public class AgentChatHistoryBizServiceImpl implements AgentChatHistoryBizServic
                 .chatType(report.getChatType())
                 .content(report.getContent())
                 .audioId(audioId)
+                .createdAt(new Date(reportTime))
+                // NOTE(haotian): 2025/5/26 updateAt可以不设置，重点是createAt，而且这样可以看到上报延迟
                 .build();
 
         // 保存数据
diff --git a/main/manager-api/src/main/java/xiaozhi/modules/agent/service/impl/AgentChatAudioServiceImpl.java b/main/manager-api/src/main/java/xiaozhi/modules/agent/service/impl/AgentChatAudioServiceImpl.java
index cf804678..efcae485 100644
--- a/main/manager-api/src/main/java/xiaozhi/modules/agent/service/impl/AgentChatAudioServiceImpl.java
+++ b/main/manager-api/src/main/java/xiaozhi/modules/agent/service/impl/AgentChatAudioServiceImpl.java
@@ -31,4 +31,4 @@ public class AgentChatAudioServiceImpl extends ServiceImpl<AiAgentChatAudioDao,
         AgentChatAudioEntity entity = getById(audioId);
         return entity != null ? entity.getAudio() : null;
     }
-}
\ No newline at end of file
+}
diff --git a/main/manager-api/src/main/resources/application-dev.yml b/main/manager-api/src/main/resources/application-dev.yml
index b49b31ca..1c86f288 100644
--- a/main/manager-api/src/main/resources/application-dev.yml
+++ b/main/manager-api/src/main/resources/application-dev.yml
@@ -48,4 +48,4 @@ spring:
           max-active: 8      # 连接池最大连接数（使用负值表示没有限制）
           max-idle: 8        # 连接池中的最大空闲连接
           min-idle: 0        # 连接池中的最小空闲连接
-        shutdown-timeout: 100ms  # 客户端优雅关闭的等待时间
\ No newline at end of file
+        shutdown-timeout: 100ms  # 客户端优雅关闭的等待时间
diff --git a/main/xiaozhi-server/config/manage_api_client.py b/main/xiaozhi-server/config/manage_api_client.py
index 11e0ecbe..cd3f86c4 100644
--- a/main/xiaozhi-server/config/manage_api_client.py
+++ b/main/xiaozhi-server/config/manage_api_client.py
@@ -160,7 +160,7 @@ def save_mem_local_short(mac_address: str, short_momery: str) -> Optional[Dict]:
 
 
 def report(
-    mac_address: str, session_id: str, chat_type: int, content: str, audio
+    mac_address: str, session_id: str, chat_type: int, content: str, audio, report_time
 ) -> Optional[Dict]:
     """带熔断的业务方法示例"""
     if not content or not ManageApiClient._instance:
@@ -174,6 +174,7 @@ def report(
                 "sessionId": session_id,
                 "chatType": chat_type,
                 "content": content,
+                "reportTime": report_time,
                 "audioBase64": (
                     base64.b64encode(audio).decode("utf-8") if audio else None
                 ),
diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py
index 3d9d8e3c..9742ebc3 100644
--- a/main/xiaozhi-server/core/connection.py
+++ b/main/xiaozhi-server/core/connection.py
@@ -890,11 +890,11 @@ class ConnectionHandler:
                 if item is None:  # 检测毒丸对象
                     break
 
-                type, text, audio_data = item
+                type, text, audio_data, report_time = item
 
                 try:
                     # 提交任务到线程池
-                    self.report_thread_pool.submit(self._process_report, type, text, audio_data)
+                    self.report_thread_pool.submit(self._process_report, type, text, audio_data, report_time)
                 except Exception as e:
                     self.logger.bind(tag=TAG).error(f"聊天记录上报线程异常: {e}")
             except queue.Empty:
@@ -904,11 +904,11 @@ class ConnectionHandler:
 
         self.logger.bind(tag=TAG).info("聊天记录上报线程已退出")
 
-    def _process_report(self, type, text, audio_data):
+    def _process_report(self, type, text, audio_data, report_time):
         """处理上报任务"""
         try:
             # 执行上报（传入二进制数据）
-            report(self, type, text, audio_data)
+            report(self, type, text, audio_data, report_time)
         except Exception as e:
             self.logger.bind(tag=TAG).error(f"上报处理异常: {e}")
         finally:
@@ -973,6 +973,12 @@ class ConnectionHandler:
             self.executor.shutdown(wait=False)
             self.executor = None
 
+        # 关闭上报线程池
+        if self.report_thread_pool:
+            self.report_thread_pool.shutdown(wait=False)
+            self.report_thread_pool = None
+            self.logger.bind(tag=TAG).info("上报线程池已关闭")
+
         self.logger.bind(tag=TAG).info("连接资源已释放")
 
     def clear_queues(self):
diff --git a/main/xiaozhi-server/core/handle/reportHandle.py b/main/xiaozhi-server/core/handle/reportHandle.py
index bb1ea066..b1214fd5 100644
--- a/main/xiaozhi-server/core/handle/reportHandle.py
+++ b/main/xiaozhi-server/core/handle/reportHandle.py
@@ -8,6 +8,7 @@ TTS上报功能已集成到ConnectionHandler类中。
 
 具体实现请参考core/connection.py中的相关代码。
 """
+import time
 
 import opuslib_next
 
@@ -16,7 +17,7 @@ from config.manage_api_client import report as manage_report
 TAG = __name__
 
 
-def report(conn, type, text, opus_data):
+def report(conn, type, text, opus_data, report_time):
     """执行聊天记录上报操作
 
     Args:
@@ -24,6 +25,7 @@ def report(conn, type, text, opus_data):
         type: 上报类型，1为用户，2为智能体
         text: 合成文本
         opus_data: opus音频数据
+        report_time: 上报时间
     """
     try:
         if opus_data:
@@ -37,6 +39,7 @@ def report(conn, type, text, opus_data):
             chat_type=type,
             content=text,
             audio=audio_data,
+            report_time=report_time,
         )
     except Exception as e:
         conn.logger.bind(tag=TAG).error(f"聊天记录上报失败: {e}")
@@ -104,12 +107,12 @@ def enqueue_tts_report(conn, text, opus_data):
     try:
         # 使用连接对象的队列，传入文本和二进制数据而非文件路径
         if conn.chat_history_conf == 2:
-            conn.report_queue.put((2, text, opus_data))
+            conn.report_queue.put((2, text, opus_data, int(time.time())))
             conn.logger.bind(tag=TAG).debug(
                 f"TTS数据已加入上报队列: {conn.device_id}, 音频大小: {len(opus_data)} "
             )
         else:
-            conn.report_queue.put((2, text, None))
+            conn.report_queue.put((2, text, None, int(time.time())))
             conn.logger.bind(tag=TAG).debug(
                 f"TTS数据已加入上报队列: {conn.device_id}, 不上报音频"
             )
@@ -132,12 +135,12 @@ def enqueue_asr_report(conn, text, opus_data):
     try:
         # 使用连接对象的队列，传入文本和二进制数据而非文件路径
         if conn.chat_history_conf == 2:
-            conn.report_queue.put((1, text, opus_data))
+            conn.report_queue.put((1, text, opus_data, int(time.time())))
             conn.logger.bind(tag=TAG).debug(
                 f"ASR数据已加入上报队列: {conn.device_id}, 音频大小: {len(opus_data)} "
             )
         else:
-            conn.report_queue.put((1, text, None))
+            conn.report_queue.put((1, text, None, int(time.time())))
             conn.logger.bind(tag=TAG).debug(
                 f"ASR数据已加入上报队列: {conn.device_id}, 不上报音频"
             )

From 631787a4f12aa769226893f04cacaec180e29056 Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Tue, 27 May 2025 13:41:53 +0800
Subject: [PATCH 14/16] =?UTF-8?q?update=EF=BC=9A=E8=BF=99=E5=87=A0?=
 =?UTF-8?q?=E5=A4=A9tts=E6=B5=81=E5=BC=8F=E6=94=B9=E9=80=A0=E5=90=88?=
 =?UTF-8?q?=E5=B9=B6=E5=90=8E=EF=BC=8Cself.executor=E7=9A=84=E4=B8=BB?=
 =?UTF-8?q?=E8=A6=81=E4=BB=BB=E5=8A=A1=E5=B0=86=E6=98=AF=E7=94=A8=E6=9D=A5?=
 =?UTF-8?q?=E4=B8=8A=E6=8A=A5=E8=81=8A=E5=A4=A9=E8=AE=B0=E5=BD=95=EF=BC=8C?=
 =?UTF-8?q?=E5=9B=A0=E6=AD=A4=E8=BF=99=E9=87=8C=E5=85=B6=E5=AE=9E=E5=8F=AF?=
 =?UTF-8?q?=E4=BB=A5=E5=90=88=E5=B9=B6=E5=9C=A8self.executor?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/config.yaml        |  2 +-
 main/xiaozhi-server/core/connection.py | 20 +++++++++-----------
 2 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml
index ebec6ccd..e7b2a50e 100644
--- a/main/xiaozhi-server/config.yaml
+++ b/main/xiaozhi-server/config.yaml
@@ -218,7 +218,7 @@ Memory:
     # 不想使用记忆功能，可以使用nomem
     type: nomem
   mem_local_short:
-    # 本地记忆功能，通过selected_module的llm总结，数据保存在本地，不会上传到服务器
+    # 本地记忆功能，通过selected_module的llm总结，数据保存在本地服务器，不会上传到外部服务器
     type: mem_local_short
     # 配备记忆存储独立的思考模型
     # 如果这里不填，则会默认使用selected_module.LLM的模型作为意图识别的思考模型
diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py
index 1efa95c2..2d78f761 100644
--- a/main/xiaozhi-server/core/connection.py
+++ b/main/xiaozhi-server/core/connection.py
@@ -89,13 +89,12 @@ class ConnectionHandler:
         self.stop_event = threading.Event()
         self.tts_queue = queue.Queue()
         self.audio_play_queue = queue.Queue()
-        self.executor = ThreadPoolExecutor(max_workers=10)
+        self.executor = ThreadPoolExecutor(max_workers=5)
 
         # 添加上报线程池
-        self.report_thread_pool = ThreadPoolExecutor(max_workers=5, thread_name_prefix="report_worker")
         self.report_queue = queue.Queue()
         self.report_thread = None
-        # TODO(haotian): 2025/5/12 可以通过修改此处，调节asr的上报和tts的上报
+        # 未来可以通过修改此处，调节asr的上报和tts的上报，目前默认都开启
         self.report_asr_enable = self.read_config_from_api
         self.report_tts_enable = self.read_config_from_api
 
@@ -465,10 +464,13 @@ class ConnectionHandler:
             return
         # 使用 mem_local_short 模式
         elif memory_type == "mem_local_short":
-            memory_llm_name = memory_config[self.config["selected_module"]["Memory"]]["llm"]
+            memory_llm_name = memory_config[self.config["selected_module"]["Memory"]][
+                "llm"
+            ]
             if memory_llm_name and memory_llm_name in self.config["LLM"]:
                 # 如果配置了专用LLM，则创建独立的LLM实例
                 from core.utils import llm as llm_utils
+
                 memory_llm_config = self.config["LLM"][memory_llm_name]
                 memory_llm_type = memory_llm_config.get("type", memory_llm_name)
                 memory_llm = llm_utils.create_instance(
@@ -922,7 +924,9 @@ class ConnectionHandler:
 
                 try:
                     # 提交任务到线程池
-                    self.report_thread_pool.submit(self._process_report, type, text, audio_data, report_time)
+                    self.executor.submit(
+                        self._process_report, type, text, audio_data, report_time
+                    )
                 except Exception as e:
                     self.logger.bind(tag=TAG).error(f"聊天记录上报线程异常: {e}")
             except queue.Empty:
@@ -1001,12 +1005,6 @@ class ConnectionHandler:
             self.executor.shutdown(wait=False)
             self.executor = None
 
-        # 关闭上报线程池
-        if self.report_thread_pool:
-            self.report_thread_pool.shutdown(wait=False)
-            self.report_thread_pool = None
-            self.logger.bind(tag=TAG).info("上报线程池已关闭")
-
         self.logger.bind(tag=TAG).info("连接资源已释放")
 
     def clear_queues(self):

From 626692df29b86278f84553ff74c7717dede4f83c Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Tue, 27 May 2025 13:47:07 +0800
Subject: [PATCH 15/16] =?UTF-8?q?update:=E4=BC=98=E5=8C=96=E9=98=BF?=
 =?UTF-8?q?=E9=87=8C=E4=BA=91tts=E6=95=B0=E5=AD=97=E5=8F=82=E6=95=B0?=
 =?UTF-8?q?=E8=AF=BB=E5=8F=96=E6=96=B9=E5=BC=8F?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../core/providers/tts/aliyun.py              | 123 +++++++++++-------
 1 file changed, 75 insertions(+), 48 deletions(-)

diff --git a/main/xiaozhi-server/core/providers/tts/aliyun.py b/main/xiaozhi-server/core/providers/tts/aliyun.py
index 4d2b1e13..98dcdb9f 100644
--- a/main/xiaozhi-server/core/providers/tts/aliyun.py
+++ b/main/xiaozhi-server/core/providers/tts/aliyun.py
@@ -13,56 +13,71 @@ import urllib.parse
 import time
 import uuid
 from urllib import parse
+
+
 class AccessToken:
     @staticmethod
     def _encode_text(text):
         encoded_text = parse.quote_plus(text)
-        return encoded_text.replace('+', '%20').replace('*', '%2A').replace('%7E', '~')
-    
+        return encoded_text.replace("+", "%20").replace("*", "%2A").replace("%7E", "~")
+
     @staticmethod
     def _encode_dict(dic):
         keys = dic.keys()
         dic_sorted = [(key, dic[key]) for key in sorted(keys)]
         encoded_text = parse.urlencode(dic_sorted)
-        return encoded_text.replace('+', '%20').replace('*', '%2A').replace('%7E', '~')
-    
+        return encoded_text.replace("+", "%20").replace("*", "%2A").replace("%7E", "~")
+
     @staticmethod
     def create_token(access_key_id, access_key_secret):
-        parameters = {'AccessKeyId': access_key_id,
-                      'Action': 'CreateToken',
-                      'Format': 'JSON',
-                      'RegionId': 'cn-shanghai',
-                      'SignatureMethod': 'HMAC-SHA1',
-                      'SignatureNonce': str(uuid.uuid1()),
-                      'SignatureVersion': '1.0',
-                      'Timestamp': time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
-                      'Version': '2019-02-28'}
+        parameters = {
+            "AccessKeyId": access_key_id,
+            "Action": "CreateToken",
+            "Format": "JSON",
+            "RegionId": "cn-shanghai",
+            "SignatureMethod": "HMAC-SHA1",
+            "SignatureNonce": str(uuid.uuid1()),
+            "SignatureVersion": "1.0",
+            "Timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
+            "Version": "2019-02-28",
+        }
         # 构造规范化的请求字符串
         query_string = AccessToken._encode_dict(parameters)
         # print('规范化的请求字符串: %s' % query_string)
         # 构造待签名字符串
-        string_to_sign = 'GET' + '&' + AccessToken._encode_text('/') + '&' + AccessToken._encode_text(query_string)
+        string_to_sign = (
+            "GET"
+            + "&"
+            + AccessToken._encode_text("/")
+            + "&"
+            + AccessToken._encode_text(query_string)
+        )
         # print('待签名的字符串: %s' % string_to_sign)
         # 计算签名
-        secreted_string = hmac.new(bytes(access_key_secret + '&', encoding='utf-8'),
-                                   bytes(string_to_sign, encoding='utf-8'),
-                                   hashlib.sha1).digest()
+        secreted_string = hmac.new(
+            bytes(access_key_secret + "&", encoding="utf-8"),
+            bytes(string_to_sign, encoding="utf-8"),
+            hashlib.sha1,
+        ).digest()
         signature = base64.b64encode(secreted_string)
         # print('签名: %s' % signature)
         # 进行URL编码
         signature = AccessToken._encode_text(signature)
         # print('URL编码后的签名: %s' % signature)
         # 调用服务
-        full_url = 'http://nls-meta.cn-shanghai.aliyuncs.com/?Signature=%s&%s' % (signature, query_string)
+        full_url = "http://nls-meta.cn-shanghai.aliyuncs.com/?Signature=%s&%s" % (
+            signature,
+            query_string,
+        )
         # print('url: %s' % full_url)
         # 提交HTTP GET请求
         response = requests.get(full_url)
         if response.ok:
             root_obj = response.json()
-            key = 'Token'
+            key = "Token"
             if key in root_obj:
-                token = root_obj[key]['Id']
-                expire_time = root_obj[key]['ExpireTime']
+                token = root_obj[key]["Id"]
+                expire_time = root_obj[key]["ExpireTime"]
                 return token, expire_time
         # print(response.text)
         return None, None
@@ -70,29 +85,36 @@ class AccessToken:
 
 class TTSProvider(TTSProviderBase):
 
-
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
-        
+
         # 新增空值判断逻辑
         self.access_key_id = config.get("access_key_id")
         self.access_key_secret = config.get("access_key_secret")
 
         self.appkey = config.get("appkey")
         self.format = config.get("format", "wav")
-        self.sample_rate = config.get("sample_rate", 16000)
+
+        sample_rate = config.get("sample_rate", "16000")
+        self.sample_rate = int(sample_rate) if sample_rate else 16000
+
         if config.get("private_voice"):
             self.voice = config.get("private_voice")
         else:
-            self.voice = config.get("voice","xiaoyun")
-        self.volume = config.get("volume", 50)
-        self.speech_rate = config.get("speech_rate", 0)
-        self.pitch_rate = config.get("pitch_rate", 0)
+            self.voice = config.get("voice", "xiaoyun")
+
+        volume = config.get("volume", "50")
+        self.volume = int(volume) if volume else 50
+
+        speech_rate = config.get("speech_rate", "0")
+        self.speech_rate = int(speech_rate) if speech_rate else 0
+
+        pitch_rate = config.get("pitch_rate", "0")
+        self.pitch_rate = int(pitch_rate) if pitch_rate else 0
+
         self.host = config.get("host", "nls-gateway-cn-shanghai.aliyuncs.com")
         self.api_url = f"https://{self.host}/stream/v1/tts"
-        self.header = {
-            "Content-Type": "application/json"
-        }
+        self.header = {"Content-Type": "application/json"}
 
         if self.access_key_id and self.access_key_secret:
             # 使用密钥对生成临时token
@@ -102,35 +124,30 @@ class TTSProvider(TTSProviderBase):
             self.token = config.get("token")
             self.expire_time = None
 
-  
     def _refresh_token(self):
         """刷新Token并记录过期时间"""
         if self.access_key_id and self.access_key_secret:
             self.token, expire_time_str = AccessToken.create_token(
-                self.access_key_id, 
-                self.access_key_secret
+                self.access_key_id, self.access_key_secret
             )
             if not expire_time_str:
                 raise ValueError("无法获取有效的Token过期时间")
 
             try:
-                #统一转换为字符串处理
+                # 统一转换为字符串处理
                 expire_str = str(expire_time_str).strip()
 
                 if expire_str.isdigit():
                     expire_time = datetime.fromtimestamp(int(expire_str))
                 else:
-                    expire_time = datetime.strptime(
-                        expire_str, 
-                        "%Y-%m-%dT%H:%M:%SZ"
-                    )
+                    expire_time = datetime.strptime(expire_str, "%Y-%m-%dT%H:%M:%SZ")
                 self.expire_time = expire_time.timestamp() - 60
             except Exception as e:
                 raise ValueError(f"无效的过期时间格式: {expire_str}") from e
-        
+
         else:
             self.expire_time = None
-            
+
         if not self.token:
             raise ValueError("无法获取有效的访问Token")
 
@@ -145,8 +162,12 @@ class TTSProvider(TTSProviderBase):
         #              f"过期时间 {datetime.fromtimestamp(self.expire_time)} | "
         #              f"剩余 {remaining:.2f}秒")
         return time.time() > self.expire_time
+
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         if self._is_token_expired():
@@ -161,21 +182,27 @@ class TTSProvider(TTSProviderBase):
             "voice": self.voice,
             "volume": self.volume,
             "speech_rate": self.speech_rate,
-            "pitch_rate": self.pitch_rate
+            "pitch_rate": self.pitch_rate,
         }
 
         # print(self.api_url, json.dumps(request_json, ensure_ascii=False))
         try:
-            resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
+            resp = requests.post(
+                self.api_url, json.dumps(request_json), headers=self.header
+            )
             if resp.status_code == 401:  # Token过期特殊处理
                 self._refresh_token()
-                resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
+                resp = requests.post(
+                    self.api_url, json.dumps(request_json), headers=self.header
+                )
             # 检查返回请求数据的mime类型是否是audio/***，是则保存到指定路径下；返回的是binary格式的
-            if resp.headers['Content-Type'].startswith('audio/'):
-                with open(output_file, 'wb') as f:
+            if resp.headers["Content-Type"].startswith("audio/"):
+                with open(output_file, "wb") as f:
                     f.write(resp.content)
                 return output_file
             else:
-                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+                raise Exception(
+                    f"{__name__} status_code: {resp.status_code} response: {resp.content}"
+                )
         except Exception as e:
             raise Exception(f"{__name__} error: {e}")

From be7ef08f401a60298f639f0862af4f22127b377c Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Tue, 27 May 2025 15:28:17 +0800
Subject: [PATCH 16/16] =?UTF-8?q?update:=E6=99=BA=E6=8E=A7=E5=8F=B0?=
 =?UTF-8?q?=E6=B7=BB=E5=8A=A0=E7=8B=AC=E7=AB=8B=E8=AE=B0=E5=BF=86=E6=A8=A1?=
 =?UTF-8?q?=E5=9E=8B=E9=85=8D=E7=BD=AE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../service/impl/ConfigServiceImpl.java       | 30 +++++++--
 .../resources/db/changelog/202505271412.sql   |  4 ++
 .../db/changelog/db.changelog-master.yaml     |  9 ++-
 .../core/providers/llm/coze/coze.py           |  2 +-
 .../core/providers/llm/dify/dify.py           |  2 +-
 .../core/providers/llm/fastgpt/fastgpt.py     |  2 +-
 .../core/providers/llm/gemini/gemini.py       |  2 +-
 .../llm/homeassistant/homeassistant.py        |  2 +-
 .../core/providers/llm/ollama/ollama.py       | 64 +++++++++++--------
 .../providers/llm/xinference/xinference.py    | 55 ++++++++++------
 .../memory/mem_local_short/mem_local_short.py | 12 +++-
 11 files changed, 125 insertions(+), 59 deletions(-)
 create mode 100644 main/manager-api/src/main/resources/db/changelog/202505271412.sql

diff --git a/main/manager-api/src/main/java/xiaozhi/modules/config/service/impl/ConfigServiceImpl.java b/main/manager-api/src/main/java/xiaozhi/modules/config/service/impl/ConfigServiceImpl.java
index 592b3c1d..f28c4e55 100644
--- a/main/manager-api/src/main/java/xiaozhi/modules/config/service/impl/ConfigServiceImpl.java
+++ b/main/manager-api/src/main/java/xiaozhi/modules/config/service/impl/ConfigServiceImpl.java
@@ -251,6 +251,7 @@ public class ConfigServiceImpl implements ConfigService {
         String[] modelTypes = { "VAD", "ASR", "TTS", "Memory", "Intent", "LLM" };
         String[] modelIds = { vadModelId, asrModelId, ttsModelId, memModelId, intentModelId, llmModelId };
         String intentLLMModelId = null;
+        String memLocalShortLLMModelId = null;
 
         for (int i = 0; i < modelIds.length; i++) {
             if (modelIds[i] == null) {
@@ -269,7 +270,7 @@ public class ConfigServiceImpl implements ConfigService {
                     Map<String, Object> map = (Map<String, Object>) model.getConfigJson();
                     if ("intent_llm".equals(map.get("type"))) {
                         intentLLMModelId = (String) map.get("llm");
-                        if (intentLLMModelId != null && intentLLMModelId.equals(llmModelId)) {
+                        if (StringUtils.isNotBlank(intentLLMModelId) && intentLLMModelId.equals(llmModelId)) {
                             intentLLMModelId = null;
                         }
                     }
@@ -281,10 +282,31 @@ public class ConfigServiceImpl implements ConfigService {
                         }
                     }
                 }
+                if ("Memory".equals(modelTypes[i])) {
+                    Map<String, Object> map = (Map<String, Object>) model.getConfigJson();
+                    if ("mem_local_short".equals(map.get("type"))) {
+                        memLocalShortLLMModelId = (String) map.get("llm");
+                        if (StringUtils.isNotBlank(memLocalShortLLMModelId)
+                                && memLocalShortLLMModelId.equals(llmModelId)) {
+                            memLocalShortLLMModelId = null;
+                        }
+                    }
+                }
                 // 如果是LLM类型，且intentLLMModelId不为空，则添加附加模型
-                if ("LLM".equals(modelTypes[i]) && intentLLMModelId != null) {
-                    ModelConfigEntity intentLLM = modelConfigService.getModelById(intentLLMModelId, isCache);
-                    typeConfig.put(intentLLM.getId(), intentLLM.getConfigJson());
+                if ("LLM".equals(modelTypes[i])) {
+                    if (StringUtils.isNotBlank(intentLLMModelId)) {
+                        if (!typeConfig.containsKey(intentLLMModelId)) {
+                            ModelConfigEntity intentLLM = modelConfigService.getModelById(intentLLMModelId, isCache);
+                            typeConfig.put(intentLLM.getId(), intentLLM.getConfigJson());
+                        }
+                    }
+                    if (StringUtils.isNotBlank(memLocalShortLLMModelId)) {
+                        if (!typeConfig.containsKey(memLocalShortLLMModelId)) {
+                            ModelConfigEntity memLocalShortLLM = modelConfigService
+                                    .getModelById(memLocalShortLLMModelId, isCache);
+                            typeConfig.put(memLocalShortLLM.getId(), memLocalShortLLM.getConfigJson());
+                        }
+                    }
                 }
             }
             result.put(modelTypes[i], typeConfig);
diff --git a/main/manager-api/src/main/resources/db/changelog/202505271412.sql b/main/manager-api/src/main/resources/db/changelog/202505271412.sql
new file mode 100644
index 00000000..70cd2e0d
--- /dev/null
+++ b/main/manager-api/src/main/resources/db/changelog/202505271412.sql
@@ -0,0 +1,4 @@
+-- 本地短期记忆配置可以设置独立的LLM
+
+update `ai_model_provider` set fields =  '[{"key":"llm","label":"LLM模型","type":"string"}]' where  id = 'SYSTEM_Memory_mem_local_short';
+update `ai_model_config` set config_json =  '{\"type\": \"mem_local_short\", \"llm\": \"LLM_ChatGLMLLM\"}' where  id = 'Memory_mem_local_short';
diff --git a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml
index 9d3808da..aadd2235 100755
--- a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml
+++ b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml
@@ -162,4 +162,11 @@ databaseChangeLog:
       changes:
         - sqlFile:
             encoding: utf8
-            path: classpath:db/changelog/202505151451.sql
\ No newline at end of file
+            path: classpath:db/changelog/202505151451.sql
+  - changeSet:
+      id: 202505271412
+      author: hrz
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202505271412.sql
\ No newline at end of file
diff --git a/main/xiaozhi-server/core/providers/llm/coze/coze.py b/main/xiaozhi-server/core/providers/llm/coze/coze.py
index 60a04667..19002ac8 100644
--- a/main/xiaozhi-server/core/providers/llm/coze/coze.py
+++ b/main/xiaozhi-server/core/providers/llm/coze/coze.py
@@ -25,7 +25,7 @@ class LLMProvider(LLMProviderBase):
         self.session_conversation_map = {}  # 存储session_id和conversation_id的映射
         check_model_key("CozeLLM", self.personal_access_token)
 
-    def response(self, session_id, dialogue):
+    def response(self, session_id, dialogue, **kwargs):
         coze_api_token = self.personal_access_token
         coze_api_base = COZE_CN_BASE_URL
 
diff --git a/main/xiaozhi-server/core/providers/llm/dify/dify.py b/main/xiaozhi-server/core/providers/llm/dify/dify.py
index 52ca9853..8b01261f 100644
--- a/main/xiaozhi-server/core/providers/llm/dify/dify.py
+++ b/main/xiaozhi-server/core/providers/llm/dify/dify.py
@@ -17,7 +17,7 @@ class LLMProvider(LLMProviderBase):
         self.session_conversation_map = {}  # 存储session_id和conversation_id的映射
         check_model_key("DifyLLM", self.api_key)
 
-    def response(self, session_id, dialogue):
+    def response(self, session_id, dialogue, **kwargs):
         try:
             # 取最后一条用户消息
             last_msg = next(m for m in reversed(dialogue) if m["role"] == "user")
diff --git a/main/xiaozhi-server/core/providers/llm/fastgpt/fastgpt.py b/main/xiaozhi-server/core/providers/llm/fastgpt/fastgpt.py
index b2e9d6b7..a5581541 100644
--- a/main/xiaozhi-server/core/providers/llm/fastgpt/fastgpt.py
+++ b/main/xiaozhi-server/core/providers/llm/fastgpt/fastgpt.py
@@ -16,7 +16,7 @@ class LLMProvider(LLMProviderBase):
         self.variables = config.get("variables", {})
         check_model_key("FastGPTLLM", self.api_key)
 
-    def response(self, session_id, dialogue):
+    def response(self, session_id, dialogue, **kwargs):
         try:
             # 取最后一条用户消息
             last_msg = next(m for m in reversed(dialogue) if m["role"] == "user")
diff --git a/main/xiaozhi-server/core/providers/llm/gemini/gemini.py b/main/xiaozhi-server/core/providers/llm/gemini/gemini.py
index d1cf238e..3369aa2d 100644
--- a/main/xiaozhi-server/core/providers/llm/gemini/gemini.py
+++ b/main/xiaozhi-server/core/providers/llm/gemini/gemini.py
@@ -112,7 +112,7 @@ class LLMProvider(LLMProviderBase):
         ]
 
     # Gemini文档提到，无需维护session-id，直接用dialogue拼接而成
-    def response(self, session_id, dialogue):
+    def response(self, session_id, dialogue, **kwargs):
         yield from self._generate(dialogue, None)
 
     def response_with_functions(self, session_id, dialogue, functions=None):
diff --git a/main/xiaozhi-server/core/providers/llm/homeassistant/homeassistant.py b/main/xiaozhi-server/core/providers/llm/homeassistant/homeassistant.py
index c436fc9e..f203e5f7 100644
--- a/main/xiaozhi-server/core/providers/llm/homeassistant/homeassistant.py
+++ b/main/xiaozhi-server/core/providers/llm/homeassistant/homeassistant.py
@@ -14,7 +14,7 @@ class LLMProvider(LLMProviderBase):
         self.base_url = config.get("base_url", config.get("url"))  # 默认使用 base_url
         self.api_url = f"{self.base_url}/api/conversation/process"  # 拼接完整的 API URL
 
-    def response(self, session_id, dialogue):
+    def response(self, session_id, dialogue, **kwargs):
         try:
             # home assistant语音助手自带意图，无需使用xiaozhi ai自带的，只需要把用户说的话传递给home assistant即可
 
diff --git a/main/xiaozhi-server/core/providers/llm/ollama/ollama.py b/main/xiaozhi-server/core/providers/llm/ollama/ollama.py
index aad6354f..c973cacd 100644
--- a/main/xiaozhi-server/core/providers/llm/ollama/ollama.py
+++ b/main/xiaozhi-server/core/providers/llm/ollama/ollama.py
@@ -18,13 +18,13 @@ class LLMProvider(LLMProviderBase):
 
         self.client = OpenAI(
             base_url=self.base_url,
-            api_key="ollama"  # Ollama doesn't need an API key but OpenAI client requires one
+            api_key="ollama",  # Ollama doesn't need an API key but OpenAI client requires one
         )
 
         # 检查是否是qwen3模型
         self.is_qwen3 = self.model_name and self.model_name.lower().startswith("qwen3")
 
-    def response(self, session_id, dialogue):
+    def response(self, session_id, dialogue, **kwargs):
         try:
             # 如果是qwen3模型，在用户最后一条消息中添加/no_think指令
             if self.is_qwen3:
@@ -35,7 +35,9 @@ class LLMProvider(LLMProviderBase):
                 for i in range(len(dialogue_copy) - 1, -1, -1):
                     if dialogue_copy[i]["role"] == "user":
                         # 在用户消息前添加/no_think指令
-                        dialogue_copy[i]["content"] = "/no_think " + dialogue_copy[i]["content"]
+                        dialogue_copy[i]["content"] = (
+                            "/no_think " + dialogue_copy[i]["content"]
+                        )
                         logger.bind(tag=TAG).debug(f"为qwen3模型添加/no_think指令")
                         break
 
@@ -43,9 +45,7 @@ class LLMProvider(LLMProviderBase):
                 dialogue = dialogue_copy
 
             responses = self.client.chat.completions.create(
-                model=self.model_name,
-                messages=dialogue,
-                stream=True
+                model=self.model_name, messages=dialogue, stream=True
             )
             is_active = True
             # 用于处理跨chunk的标签
@@ -53,29 +53,33 @@ class LLMProvider(LLMProviderBase):
 
             for chunk in responses:
                 try:
-                    delta = chunk.choices[0].delta if getattr(chunk, 'choices', None) else None
-                    content = delta.content if hasattr(delta, 'content') else ''
+                    delta = (
+                        chunk.choices[0].delta
+                        if getattr(chunk, "choices", None)
+                        else None
+                    )
+                    content = delta.content if hasattr(delta, "content") else ""
 
                     if content:
                         # 将内容添加到缓冲区
                         buffer += content
 
                         # 处理缓冲区中的标签
-                        while '<think>' in buffer and '</think>' in buffer:
+                        while "<think>" in buffer and "</think>" in buffer:
                             # 找到完整的<think></think>标签并移除
-                            pre = buffer.split('<think>', 1)[0]
-                            post = buffer.split('</think>', 1)[1]
+                            pre = buffer.split("<think>", 1)[0]
+                            post = buffer.split("</think>", 1)[1]
                             buffer = pre + post
 
                         # 处理只有开始标签的情况
-                        if '<think>' in buffer:
+                        if "<think>" in buffer:
                             is_active = False
-                            buffer = buffer.split('<think>', 1)[0]
+                            buffer = buffer.split("<think>", 1)[0]
 
                         # 处理只有结束标签的情况
-                        if '</think>' in buffer:
+                        if "</think>" in buffer:
                             is_active = True
-                            buffer = buffer.split('</think>', 1)[1]
+                            buffer = buffer.split("</think>", 1)[1]
 
                         # 如果当前处于活动状态且缓冲区有内容，则输出
                         if is_active and buffer:
@@ -100,7 +104,9 @@ class LLMProvider(LLMProviderBase):
                 for i in range(len(dialogue_copy) - 1, -1, -1):
                     if dialogue_copy[i]["role"] == "user":
                         # 在用户消息前添加/no_think指令
-                        dialogue_copy[i]["content"] = "/no_think " + dialogue_copy[i]["content"]
+                        dialogue_copy[i]["content"] = (
+                            "/no_think " + dialogue_copy[i]["content"]
+                        )
                         logger.bind(tag=TAG).debug(f"为qwen3模型添加/no_think指令")
                         break
 
@@ -119,9 +125,15 @@ class LLMProvider(LLMProviderBase):
 
             for chunk in stream:
                 try:
-                    delta = chunk.choices[0].delta if getattr(chunk, 'choices', None) else None
-                    content = delta.content if hasattr(delta, 'content') else None
-                    tool_calls = delta.tool_calls if hasattr(delta, 'tool_calls') else None
+                    delta = (
+                        chunk.choices[0].delta
+                        if getattr(chunk, "choices", None)
+                        else None
+                    )
+                    content = delta.content if hasattr(delta, "content") else None
+                    tool_calls = (
+                        delta.tool_calls if hasattr(delta, "tool_calls") else None
+                    )
 
                     # 如果是工具调用，直接传递
                     if tool_calls:
@@ -134,21 +146,21 @@ class LLMProvider(LLMProviderBase):
                         buffer += content
 
                         # 处理缓冲区中的标签
-                        while '<think>' in buffer and '</think>' in buffer:
+                        while "<think>" in buffer and "</think>" in buffer:
                             # 找到完整的<think></think>标签并移除
-                            pre = buffer.split('<think>', 1)[0]
-                            post = buffer.split('</think>', 1)[1]
+                            pre = buffer.split("<think>", 1)[0]
+                            post = buffer.split("</think>", 1)[1]
                             buffer = pre + post
 
                         # 处理只有开始标签的情况
-                        if '<think>' in buffer:
+                        if "<think>" in buffer:
                             is_active = False
-                            buffer = buffer.split('<think>', 1)[0]
+                            buffer = buffer.split("<think>", 1)[0]
 
                         # 处理只有结束标签的情况
-                        if '</think>' in buffer:
+                        if "</think>" in buffer:
                             is_active = True
-                            buffer = buffer.split('</think>', 1)[1]
+                            buffer = buffer.split("</think>", 1)[1]
 
                         # 如果当前处于活动状态且缓冲区有内容，则输出
                         if is_active and buffer:
diff --git a/main/xiaozhi-server/core/providers/llm/xinference/xinference.py b/main/xiaozhi-server/core/providers/llm/xinference/xinference.py
index b90b0418..a4e9a5e6 100644
--- a/main/xiaozhi-server/core/providers/llm/xinference/xinference.py
+++ b/main/xiaozhi-server/core/providers/llm/xinference/xinference.py
@@ -15,39 +15,45 @@ class LLMProvider(LLMProviderBase):
         # 如果没有v1，增加v1
         if not self.base_url.endswith("/v1"):
             self.base_url = f"{self.base_url}/v1"
-            
-        logger.bind(tag=TAG).info(f"Initializing Xinference LLM provider with model: {self.model_name}, base_url: {self.base_url}")
+
+        logger.bind(tag=TAG).info(
+            f"Initializing Xinference LLM provider with model: {self.model_name}, base_url: {self.base_url}"
+        )
 
         try:
             self.client = OpenAI(
                 base_url=self.base_url,
-                api_key="xinference"  # Xinference has a similar setup to Ollama where it doesn't need an actual key
+                api_key="xinference",  # Xinference has a similar setup to Ollama where it doesn't need an actual key
             )
             logger.bind(tag=TAG).info("Xinference client initialized successfully")
         except Exception as e:
             logger.bind(tag=TAG).error(f"Error initializing Xinference client: {e}")
             raise
 
-    def response(self, session_id, dialogue):
+    def response(self, session_id, dialogue, **kwargs):
         try:
-            logger.bind(tag=TAG).debug(f"Sending request to Xinference with model: {self.model_name}, dialogue length: {len(dialogue)}")
-            responses = self.client.chat.completions.create(
-                model=self.model_name,
-                messages=dialogue,
-                stream=True
+            logger.bind(tag=TAG).debug(
+                f"Sending request to Xinference with model: {self.model_name}, dialogue length: {len(dialogue)}"
             )
-            is_active=True
+            responses = self.client.chat.completions.create(
+                model=self.model_name, messages=dialogue, stream=True
+            )
+            is_active = True
             for chunk in responses:
                 try:
-                    delta = chunk.choices[0].delta if getattr(chunk, 'choices', None) else None
-                    content = delta.content if hasattr(delta, 'content') else ''
+                    delta = (
+                        chunk.choices[0].delta
+                        if getattr(chunk, "choices", None)
+                        else None
+                    )
+                    content = delta.content if hasattr(delta, "content") else ""
                     if content:
-                        if '<think>' in content:
+                        if "<think>" in content:
                             is_active = False
-                            content = content.split('<think>')[0]
-                        if '</think>' in content:
+                            content = content.split("<think>")[0]
+                        if "</think>" in content:
                             is_active = True
-                            content = content.split('</think>')[-1]
+                            content = content.split("</think>")[-1]
                         if is_active:
                             yield content
                 except Exception as e:
@@ -59,10 +65,14 @@ class LLMProvider(LLMProviderBase):
 
     def response_with_functions(self, session_id, dialogue, functions=None):
         try:
-            logger.bind(tag=TAG).debug(f"Sending function call request to Xinference with model: {self.model_name}, dialogue length: {len(dialogue)}")
+            logger.bind(tag=TAG).debug(
+                f"Sending function call request to Xinference with model: {self.model_name}, dialogue length: {len(dialogue)}"
+            )
             if functions:
-                logger.bind(tag=TAG).debug(f"Function calls enabled with: {[f.get('function', {}).get('name') for f in functions]}")
-                
+                logger.bind(tag=TAG).debug(
+                    f"Function calls enabled with: {[f.get('function', {}).get('name') for f in functions]}"
+                )
+
             stream = self.client.chat.completions.create(
                 model=self.model_name,
                 messages=dialogue,
@@ -74,7 +84,7 @@ class LLMProvider(LLMProviderBase):
                 delta = chunk.choices[0].delta
                 content = delta.content
                 tool_calls = delta.tool_calls
-                
+
                 if content:
                     yield content, tool_calls
                 elif tool_calls:
@@ -82,4 +92,7 @@ class LLMProvider(LLMProviderBase):
 
         except Exception as e:
             logger.bind(tag=TAG).error(f"Error in Xinference function call: {e}")
-            yield {"type": "content", "content": f"【Xinference服务响应异常: {str(e)}】"} 
+            yield {
+                "type": "content",
+                "content": f"【Xinference服务响应异常: {str(e)}】",
+            }
diff --git a/main/xiaozhi-server/core/providers/memory/mem_local_short/mem_local_short.py b/main/xiaozhi-server/core/providers/memory/mem_local_short/mem_local_short.py
index 844035bd..9f855cc6 100644
--- a/main/xiaozhi-server/core/providers/memory/mem_local_short/mem_local_short.py
+++ b/main/xiaozhi-server/core/providers/memory/mem_local_short/mem_local_short.py
@@ -167,7 +167,12 @@ class MemoryProvider(MemoryProviderBase):
         msgStr += f"当前时间：{time_str}"
 
         if self.save_to_file:
-            result = self.llm.response_no_stream(short_term_memory_prompt, msgStr)
+            result = self.llm.response_no_stream(
+                short_term_memory_prompt,
+                msgStr,
+                max_tokens=2000,
+                temperature=0.2,
+            )
             json_str = extract_json_data(result)
             try:
                 json.loads(json_str)  # 检查json格式是否正确
@@ -177,7 +182,10 @@ class MemoryProvider(MemoryProviderBase):
                 print("Error:", e)
         else:
             result = self.llm.response_no_stream(
-                short_term_memory_prompt_only_content, msgStr
+                short_term_memory_prompt_only_content,
+                msgStr,
+                max_tokens=2000,
+                temperature=0.2,
             )
             save_mem_local_short(self.role_id, result)
         logger.bind(tag=TAG).info(f"Save memory successful - Role: {self.role_id}")