From 69cac9d40ab0e92533ff952c3d5e0ff7fcd32a66 Mon Sep 17 00:00:00 2001
From: Sakura-RanChen <1908198662@qq.com>
Date: Thu, 3 Jul 2025 09:16:06 +0800
Subject: [PATCH 1/7] =?UTF-8?q?update:=20TTS=E5=A4=8D=E7=94=A8=E9=93=BE?=
 =?UTF-8?q?=E6=8E=A5=EF=BC=8CVAD=E5=8F=8C=E9=98=88=E5=80=BC=E5=88=A4?=
 =?UTF-8?q?=E6=96=AD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/config.yaml               |  1 +
 main/xiaozhi-server/core/connection.py        |  6 ++++
 .../providers/tts/huoshan_double_stream.py    | 36 ++++++++++++++-----
 .../core/providers/vad/silero.py              | 28 +++++++++------
 4 files changed, 52 insertions(+), 19 deletions(-)

diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml
index 5a43c995..a7a94658 100644
--- a/main/xiaozhi-server/config.yaml
+++ b/main/xiaozhi-server/config.yaml
@@ -325,6 +325,7 @@ VAD:
   SileroVAD:
     type: silero
     threshold: 0.5
+    threshold_low: 0.3
     model_dir: models/snakers4_silero-vad
     min_silence_duration_ms: 200  # 如果说话停顿比较长，可以把这个值设置大一些
 
diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py
index 9d1949c4..375bd117 100644
--- a/main/xiaozhi-server/core/connection.py
+++ b/main/xiaozhi-server/core/connection.py
@@ -17,6 +17,7 @@ from core.utils.util import (
     filter_sensitive_info,
 )
 from typing import Dict, Any
+from collections import deque
 from core.utils.modules_initialize import (
     initialize_modules,
     initialize_tts,
@@ -112,6 +113,8 @@ class ConnectionHandler:
         self.client_have_voice = False
         self.last_activity_time = 0.0  # 统一的活动时间戳（毫秒）
         self.client_voice_stop = False
+        self.client_voice_window = deque(maxlen=5)
+        self.last_is_voice = False
 
         # asr相关变量
         # 因为实际部署时可能会用到公共的本地ASR，不能把变量暴露给公共ASR
@@ -858,6 +861,9 @@ class ConnectionHandler:
             elif self.websocket:
                 await self.websocket.close()
 
+            if self.tts:
+                await self.tts.close()
+
             # 最后关闭线程池（避免阻塞）
             if self.executor:
                 self.executor.shutdown(wait=False)
diff --git a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
index 1ebaf15a..3fe6294e 100644
--- a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
+++ b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
@@ -1,4 +1,3 @@
-import os
 import uuid
 import json
 import queue
@@ -10,7 +9,6 @@ from config.logger import setup_logging
 from core.utils import opus_encoder_utils
 from core.utils.util import check_model_key
 from core.providers.tts.base import TTSProviderBase
-from core.handle.abortHandle import handleAbortMessage
 from core.providers.tts.dto.dto import SentenceType, ContentType, InterfaceType
 from asyncio import Task
 
@@ -175,6 +173,9 @@ class TTSProvider(TTSProviderBase):
     async def _ensure_connection(self):
         """建立新的WebSocket连接"""
         try:
+            if self.ws:
+                logger.bind(tag=TAG).info(f"使用已有链接...")
+                return self.ws
             logger.bind(tag=TAG).info("开始建立新连接...")
             ws_header = {
                 "X-Api-App-Key": self.appId,
@@ -368,9 +369,17 @@ class TTSProvider(TTSProviderBase):
                 logger.bind(tag=TAG).info("会话结束请求已发送")
 
                 # 等待监听任务完成
-                if hasattr(self, "_monitor_task"):
+                if hasattr(self, "_monitor_task") and self._monitor_task is not None:
                     try:
-                        await self._monitor_task
+                        # 设置4秒超时等待监听任务结束
+                        await asyncio.wait_for(self._monitor_task, timeout=4)
+                    except asyncio.TimeoutError:
+                        logger.bind(tag=TAG).warning("等待监听任务超时，强制取消")
+                        self._monitor_task.cancel()
+                        try:
+                            await self._monitor_task
+                        except asyncio.CancelledError:
+                            pass
                     except Exception as e:
                         logger.bind(tag=TAG).error(
                             f"等待监听任务完成时发生错误: {str(e)}"
@@ -378,8 +387,6 @@ class TTSProvider(TTSProviderBase):
                     finally:
                         self._monitor_task = None
 
-                # 关闭连接
-                await self.close()
         except Exception as e:
             logger.bind(tag=TAG).error(f"关闭会话失败: {str(e)}")
             # 确保清理资源
@@ -400,6 +407,15 @@ class TTSProvider(TTSProviderBase):
 
     async def close(self):
         """资源清理方法"""
+        # 取消监听任务
+        if self._monitor_task:
+            try:
+                self._monitor_task.cancel()
+                await self._monitor_task
+            except asyncio.CancelledError:
+                pass
+            self._monitor_task = None
+
         if self.ws:
             try:
                 await self.ws.close()
@@ -413,6 +429,7 @@ class TTSProvider(TTSProviderBase):
         is_first_sentence = True
         first_sentence_segment_count = 0  # 添加计数器
         try:
+            session_finished = False  # 标记会话是否正常结束
             while not self.conn.stop_event.is_set():
                 try:
                     # 确保 `recv()` 运行在同一个 event loop
@@ -466,6 +483,7 @@ class TTSProvider(TTSProviderBase):
                     elif res.optional.event == EVENT_SessionFinished:
                         logger.bind(tag=TAG).debug(f"会话结束～～")
                         self._process_before_stop_play_files()
+                        session_finished = True
                         break
                 except websockets.ConnectionClosed:
                     logger.bind(tag=TAG).warning("WebSocket连接已关闭")
@@ -476,15 +494,15 @@ class TTSProvider(TTSProviderBase):
                     )
                     traceback.print_exc()
                     break
-        finally:
-            # 确保清理资源
-            if self.ws:
+            # 仅在连接异常时才关闭
+            if not session_finished and self.ws:
                 try:
                     await self.ws.close()
                 except:
                     pass
                 self.ws = None
             # 监听任务退出时清理引用
+        finally:
             self._monitor_task = None
 
     async def send_event(
diff --git a/main/xiaozhi-server/core/providers/vad/silero.py b/main/xiaozhi-server/core/providers/vad/silero.py
index 2c45ba8c..b516d8fb 100644
--- a/main/xiaozhi-server/core/providers/vad/silero.py
+++ b/main/xiaozhi-server/core/providers/vad/silero.py
@@ -23,22 +23,24 @@ class VADProvider(VADProviderBase):
 
         # 处理空字符串的情况
         threshold = config.get("threshold", "0.5")
+        threshold_low = config.get("threshold_low", "0.2")
         min_silence_duration_ms = config.get("min_silence_duration_ms", "1000")
 
         self.vad_threshold = float(threshold) if threshold else 0.5
+        self.vad_threshold_low = float(threshold_low) if threshold_low else 0.2
+
         self.silence_threshold_ms = (
             int(min_silence_duration_ms) if min_silence_duration_ms else 1000
         )
 
+        # 至少要多少帧才算有语音
+        self.frame_window_threshold = 3
+
     def is_vad(self, conn, opus_packet):
         try:
             pcm_frame = self.decoder.decode(opus_packet, 960)
             conn.client_audio_buffer.extend(pcm_frame)  # 将新数据加入缓冲区
 
-            # 确保帧计数器存在
-            if not hasattr(conn, "client_voice_frame_count"):
-                conn.client_voice_frame_count = 0
-
             # 处理缓冲区中的完整帧（每次处理512采样点）
             client_have_voice = False
             while len(conn.client_audio_buffer) >= 512 * 2:
@@ -54,15 +56,21 @@ class VADProvider(VADProviderBase):
                 # 检测语音活动
                 with torch.no_grad():
                     speech_prob = self.model(audio_tensor, 16000).item()
-                is_voice = speech_prob >= self.vad_threshold
 
-                if is_voice:
-                    conn.client_voice_frame_count += 1
+                # 双阈值判断
+                if speech_prob >= self.vad_threshold:
+                    is_voice = True
+                elif speech_prob <= self.vad_threshold_low:
+                    is_voice = False
                 else:
-                    conn.client_voice_frame_count = 0
+                    is_voice = conn.last_is_voice
 
-                # 只有连续4帧检测到语音才认为有语音
-                client_have_voice = conn.client_voice_frame_count >= 4
+                # 声音没低于最低值则延续前一个状态，判断为有声音
+                conn.last_is_voice = is_voice
+
+                # 更新滑动窗口
+                conn.client_voice_window.append(is_voice)
+                client_have_voice = (conn.client_voice_window.count(True) >= self.frame_window_threshold)
 
                 # 如果之前有声音，但本次没有声音，且与上次有声音的时间差已经超过了静默阈值，则认为已经说完一句话
                 if conn.client_have_voice and not client_have_voice:

From 7e5a2b4549fbd22e9727deac192fdd31179fa575 Mon Sep 17 00:00:00 2001
From: Sakura-RanChen <1908198662@qq.com>
Date: Fri, 4 Jul 2025 11:27:49 +0800
Subject: [PATCH 2/7] =?UTF-8?q?fix:=20=E6=92=AD=E6=94=BE=E9=9F=B3=E4=B9=90?=
 =?UTF-8?q?=E6=97=B6=EF=BC=8C=E5=BC=95=E5=AF=BC=E8=AF=8D=E5=8D=A1=E9=A1=BF?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/core/providers/tts/base.py         |  6 ++----
 .../core/providers/tts/huoshan_double_stream.py        | 10 +++++++---
 main/xiaozhi-server/core/providers/tts/linkerai.py     | 10 +++++++---
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/main/xiaozhi-server/core/providers/tts/base.py b/main/xiaozhi-server/core/providers/tts/base.py
index 223cb807..d196b8f9 100644
--- a/main/xiaozhi-server/core/providers/tts/base.py
+++ b/main/xiaozhi-server/core/providers/tts/base.py
@@ -362,10 +362,8 @@ class TTSProviderBase(ABC):
         return audio_datas
 
     def _process_before_stop_play_files(self):
-        for tts_file, text in self.before_stop_play_files:
-            if tts_file and os.path.exists(tts_file):
-                audio_datas = self._process_audio_file(tts_file)
-                self.tts_audio_queue.put((SentenceType.MIDDLE, audio_datas, text))
+        for audio_datas, text in self.before_stop_play_files:
+            self.tts_audio_queue.put((SentenceType.MIDDLE, audio_datas, text))
         self.before_stop_play_files.clear()
         self.tts_audio_queue.put((SentenceType.LAST, [], None))
 
diff --git a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
index 3fe6294e..6f8fcca5 100644
--- a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
+++ b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
@@ -1,3 +1,4 @@
+import os
 import uuid
 import json
 import queue
@@ -245,9 +246,12 @@ class TTSProvider(TTSProviderBase):
                     logger.bind(tag=TAG).info(
                         f"添加音频文件到待播放列表: {message.content_file}"
                     )
-                    self.before_stop_play_files.append(
-                        (message.content_file, message.content_detail)
-                    )
+                    if message.content_file and os.path.exists(message.content_file):
+                        # 先处理文件音频数据
+                        file_audio = self._process_audio_file(message.content_file)
+                        self.before_stop_play_files.append(
+                            (file_audio, message.content_detail)
+                        )
 
                 if message.sentence_type == SentenceType.LAST:
                     try:
diff --git a/main/xiaozhi-server/core/providers/tts/linkerai.py b/main/xiaozhi-server/core/providers/tts/linkerai.py
index ee108540..1046b972 100644
--- a/main/xiaozhi-server/core/providers/tts/linkerai.py
+++ b/main/xiaozhi-server/core/providers/tts/linkerai.py
@@ -1,3 +1,4 @@
+import os
 import queue
 import asyncio
 import traceback
@@ -63,9 +64,12 @@ class TTSProvider(TTSProviderBase):
                     logger.bind(tag=TAG).info(
                         f"添加音频文件到待播放列表: {message.content_file}"
                     )
-                    self.before_stop_play_files.append(
-                        (message.content_file, message.content_detail)
-                    )
+                    if message.content_file and os.path.exists(message.content_file):
+                        # 先处理文件音频数据
+                        file_audio = self._process_audio_file(message.content_file)
+                        self.before_stop_play_files.append(
+                            (file_audio, message.content_detail)
+                        )
 
                 if message.sentence_type == SentenceType.LAST:
                     # 处理剩余的文本

From 8da9dc8a3f8f761515e6b96f365cf5106ee40229 Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Mon, 7 Jul 2025 11:45:37 +0800
Subject: [PATCH 3/7] =?UTF-8?q?update:=E4=BC=98=E5=8C=96=E5=BC=95=E5=AF=BC?=
 =?UTF-8?q?=E8=AF=8D?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/plugins_func/functions/play_music.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/main/xiaozhi-server/plugins_func/functions/play_music.py b/main/xiaozhi-server/plugins_func/functions/play_music.py
index 6d184b6b..a6eb5822 100644
--- a/main/xiaozhi-server/plugins_func/functions/play_music.py
+++ b/main/xiaozhi-server/plugins_func/functions/play_music.py
@@ -181,10 +181,10 @@ def _get_random_play_prompt(song_name):
         f"正在为您播放，{clean_name}",
         f"请欣赏歌曲，{clean_name}",
         f"即将为您播放，{clean_name}",
-        f"为您带来，{clean_name}",
-        f"让我们聆听，{clean_name}",
+        f"现在为您带来，《{clean_name}》",
+        f"让我们一起聆听，《{clean_name}》",
         f"接下来请欣赏，{clean_name}",
-        f"为您献上，{clean_name}",
+        f"此刻为您献上，《{clean_name}》",
     ]
     # 直接使用random.choice，不设置seed
     return random.choice(prompts)

From 44593ff3f38a807463e74b4fae2adaa39cc49975 Mon Sep 17 00:00:00 2001
From: Sakura-RanChen <1908198662@qq.com>
Date: Tue, 8 Jul 2025 17:48:50 +0800
Subject: [PATCH 4/7] =?UTF-8?q?update:=20=E4=BC=98=E5=8C=96chat=E5=87=BD?=
 =?UTF-8?q?=E6=95=B0=E6=B5=81=E7=A8=8B=20=E4=BC=98=E5=8C=96huoshan?=
 =?UTF-8?q?=E5=A4=84=E7=90=86=20=E4=BC=9A=E8=AF=9D=E4=BF=9D=E6=8C=81?=
 =?UTF-8?q?=E4=B8=80=E8=87=B4=E6=80=A7?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/core/connection.py        | 38 +++++----
 .../core/handle/intentHandler.py              | 19 ++++-
 .../xiaozhi-server/core/providers/tts/base.py | 14 ----
 .../providers/tts/huoshan_double_stream.py    | 78 ++++++++-----------
 .../plugins_func/functions/play_music.py      | 35 ++++-----
 5 files changed, 86 insertions(+), 98 deletions(-)

diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py
index 375bd117..e0eb90bc 100644
--- a/main/xiaozhi-server/core/connection.py
+++ b/main/xiaozhi-server/core/connection.py
@@ -594,13 +594,24 @@ class ConnectionHandler:
         # 更新系统prompt至上下文
         self.dialogue.update_system_message(self.prompt)
 
-    def chat(self, query, tool_call=False):
+    def chat(self, query, tool_call=False, depth=0):
         self.logger.bind(tag=TAG).info(f"大模型收到用户消息: {query}")
         self.llm_finish_task = False
 
         if not tool_call:
             self.dialogue.put(Message(role="user", content=query))
 
+        # 为最顶层时新建会话ID和发送FIRST请求
+        if depth == 0:
+            self.sentence_id = str(uuid.uuid4().hex)
+            self.tts.tts_text_queue.put(
+                TTSMessageDTO(
+                    sentence_id=self.sentence_id,
+                    sentence_type=SentenceType.FIRST,
+                    content_type=ContentType.ACTION,
+                )
+            )
+
         # Define intent functions
         functions = None
         if self.intent_type == "function_call" and hasattr(self, "func_handler"):
@@ -616,8 +627,6 @@ class ConnectionHandler:
                 )
                 memory_str = future.result()
 
-            self.sentence_id = str(uuid.uuid4().hex)
-
             if self.intent_type == "function_call" and functions is not None:
                 # 使用支持functions的streaming接口
                 llm_responses = self.llm.response_with_functions(
@@ -640,7 +649,6 @@ class ConnectionHandler:
         function_id = None
         function_arguments = ""
         content_arguments = ""
-        text_index = 0
         self.client_abort = False
         for response in llm_responses:
             if self.client_abort:
@@ -670,14 +678,6 @@ class ConnectionHandler:
             if content is not None and len(content) > 0:
                 if not tool_call_flag:
                     response_message.append(content)
-                    if text_index == 0:
-                        self.tts.tts_text_queue.put(
-                            TTSMessageDTO(
-                                sentence_id=self.sentence_id,
-                                sentence_type=SentenceType.FIRST,
-                                content_type=ContentType.ACTION,
-                            )
-                        )
                     self.tts.tts_text_queue.put(
                         TTSMessageDTO(
                             sentence_id=self.sentence_id,
@@ -686,7 +686,6 @@ class ConnectionHandler:
                             content_detail=content,
                         )
                     )
-                    text_index += 1
         # 处理function call
         if tool_call_flag:
             bHasError = False
@@ -711,6 +710,11 @@ class ConnectionHandler:
                         f"function call error: {content_arguments}"
                     )
             if not bHasError:
+                # 如需要大模型先处理一轮，添加相关处理后的日志情况
+                if len(response_message) > 0:
+                    self.dialogue.put(
+                        Message(role="assistant", content="".join(response_message))
+                    )
                 response_message.clear()
                 self.logger.bind(tag=TAG).debug(
                     f"function_name={function_name}, function_id={function_id}, function_arguments={function_arguments}"
@@ -728,14 +732,14 @@ class ConnectionHandler:
                     ),
                     self.loop,
                 ).result()
-                self._handle_function_result(result, function_call_data)
+                self._handle_function_result(result, function_call_data, depth=depth)
 
         # 存储对话内容
         if len(response_message) > 0:
             self.dialogue.put(
                 Message(role="assistant", content="".join(response_message))
             )
-        if text_index > 0:
+        if depth == 0:
             self.tts.tts_text_queue.put(
                 TTSMessageDTO(
                     sentence_id=self.sentence_id,
@@ -750,7 +754,7 @@ class ConnectionHandler:
 
         return True
 
-    def _handle_function_result(self, result, function_call_data):
+    def _handle_function_result(self, result, function_call_data, depth):
         if result.action == Action.RESPONSE:  # 直接回复前端
             text = result.response
             self.tts.tts_one_sentence(self, ContentType.TEXT, content_detail=text)
@@ -787,7 +791,7 @@ class ConnectionHandler:
                         content=text,
                     )
                 )
-                self.chat(text, tool_call=True)
+                self.chat(text, tool_call=True, depth=depth + 1)
         elif result.action == Action.NOTFOUND or result.action == Action.ERROR:
             text = result.response if result.response else result.result
             self.tts.tts_one_sentence(self, ContentType.TEXT, content_detail=text)
diff --git a/main/xiaozhi-server/core/handle/intentHandler.py b/main/xiaozhi-server/core/handle/intentHandler.py
index 2d0baca4..a398195b 100644
--- a/main/xiaozhi-server/core/handle/intentHandler.py
+++ b/main/xiaozhi-server/core/handle/intentHandler.py
@@ -6,9 +6,8 @@ from core.handle.helloHandle import checkWakeupWords
 from core.utils.util import remove_punctuation_and_length
 from core.providers.tts.dto.dto import ContentType
 from core.utils.dialogue import Message
-from core.providers.tools.device_mcp import call_mcp_tool
 from plugins_func.register import Action, ActionResponse
-from loguru import logger
+from core.providers.tts.dto.dto import TTSMessageDTO, SentenceType
 
 TAG = __name__
 
@@ -29,6 +28,8 @@ async def handle_user_intent(conn, text):
     intent_result = await analyze_intent_with_llm(conn, text)
     if not intent_result:
         return False
+    # 会话开始时生成sentence_id
+    conn.sentence_id = str(uuid.uuid4().hex)
     # 处理各种意图
     return await process_intent_result(conn, intent_result, text)
 
@@ -158,5 +159,19 @@ async def process_intent_result(conn, intent_result, original_text):
 
 
 def speak_txt(conn, text):
+    conn.tts.tts_text_queue.put(
+        TTSMessageDTO(
+            sentence_id=conn.sentence_id,
+            sentence_type=SentenceType.FIRST,
+            content_type=ContentType.ACTION,
+        )
+    )
     conn.tts.tts_one_sentence(conn, ContentType.TEXT, content_detail=text)
+    conn.tts.tts_text_queue.put(
+        TTSMessageDTO(
+            sentence_id=conn.sentence_id,
+            sentence_type=SentenceType.LAST,
+            content_type=ContentType.ACTION,
+        )
+    )
     conn.dialogue.put(Message(role="assistant", content=text))
diff --git a/main/xiaozhi-server/core/providers/tts/base.py b/main/xiaozhi-server/core/providers/tts/base.py
index d196b8f9..c89b3247 100644
--- a/main/xiaozhi-server/core/providers/tts/base.py
+++ b/main/xiaozhi-server/core/providers/tts/base.py
@@ -161,13 +161,6 @@ class TTSProviderBase(ABC):
             else:
                 sentence_id = str(uuid.uuid4()).replace("-", "")
                 conn.sentence_id = sentence_id
-        self.tts_text_queue.put(
-            TTSMessageDTO(
-                sentence_id=sentence_id,
-                sentence_type=SentenceType.FIRST,
-                content_type=ContentType.ACTION,
-            )
-        )
         # 对于单句的文本，进行分段处理
         segments = re.split(r"([。！？!?；;\n])", content_detail)
         for seg in segments:
@@ -180,13 +173,6 @@ class TTSProviderBase(ABC):
                     content_file=content_file,
                 )
             )
-        self.tts_text_queue.put(
-            TTSMessageDTO(
-                sentence_id=sentence_id,
-                sentence_type=SentenceType.LAST,
-                content_type=ContentType.ACTION,
-            )
-        )
 
     async def open_audio_channels(self, conn):
         self.conn = conn
diff --git a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
index 6f8fcca5..49643b85 100644
--- a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
+++ b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
@@ -202,6 +202,10 @@ class TTSProvider(TTSProviderBase):
                 logger.bind(tag=TAG).debug(
                     f"收到TTS任务｜{message.sentence_type.name} ｜ {message.content_type.name} | 会话ID: {self.conn.sentence_id}"
                 )
+
+                if message.sentence_type == SentenceType.FIRST:
+                    self.conn.client_abort = False
+
                 if self.conn.client_abort:
                     logger.bind(tag=TAG).info("收到打断信息，终止TTS文本处理线程")
                     continue
@@ -300,24 +304,23 @@ class TTSProvider(TTSProviderBase):
     async def start_session(self, session_id):
         logger.bind(tag=TAG).info(f"开始会话～～{session_id}")
         try:
-            task = self._monitor_task
+            # 会话开始时检测上个会话的监听状态
             if (
-                task is not None
-                and isinstance(task, Task)
-                and not task.done()
+                self._monitor_task is not None
+                and isinstance(self._monitor_task, Task)
+                and not self._monitor_task.done()
             ):
-                logger.bind(tag=TAG).info("等待上一个监听任务结束...")
-                if self.ws is not None:
-                    logger.bind(tag=TAG).info("强制关闭上一个WebSocket连接以唤醒监听任务...")
-                    try:
-                        await self.ws.close()
-                    except Exception as e:
-                        logger.bind(tag=TAG).warning(f"关闭上一个ws异常: {e}")
-                    self.ws = None
+                logger.bind(tag=TAG).info("取消上一个监听任务...")
+                self._monitor_task.cancel()
                 try:
-                    await asyncio.wait_for(task, timeout=8)
+                    # 等待任务取消完成
+                    await asyncio.wait_for(self._monitor_task, timeout=3)
+                except asyncio.CancelledError:
+                    logger.bind(tag=TAG).info("监听任务已成功取消")
+                except asyncio.TimeoutError:
+                    logger.bind(tag=TAG).warning("取消监听任务超时，可能仍在运行")
                 except Exception as e:
-                    logger.bind(tag=TAG).warning(f"等待监听任务异常: {e}")
+                    logger.bind(tag=TAG).warning(f"取消监听任务异常: {e}")
                 self._monitor_task = None
             # 建立新连接
             await self._ensure_connection()
@@ -341,19 +344,7 @@ class TTSProvider(TTSProviderBase):
         except Exception as e:
             logger.bind(tag=TAG).error(f"启动会话失败: {str(e)}")
             # 确保清理资源
-            if hasattr(self, "_monitor_task"):
-                try:
-                    self._monitor_task.cancel()
-                    await self._monitor_task
-                except:
-                    pass
-                self._monitor_task = None
-            if self.ws:
-                try:
-                    await self.ws.close()
-                except:
-                    pass
-                self.ws = None
+            await self.close()
             raise
 
     async def finish_session(self, session_id):
@@ -379,11 +370,14 @@ class TTSProvider(TTSProviderBase):
                         await asyncio.wait_for(self._monitor_task, timeout=4)
                     except asyncio.TimeoutError:
                         logger.bind(tag=TAG).warning("等待监听任务超时，强制取消")
-                        self._monitor_task.cancel()
-                        try:
-                            await self._monitor_task
-                        except asyncio.CancelledError:
-                            pass
+                        if not self._monitor_task.done():
+                            self._monitor_task.cancel()
+                            try:
+                                await self._monitor_task
+                            except asyncio.CancelledError:
+                                pass
+                            except Exception as e:
+                                logger.bind(tag=TAG).warning(f"监听任务取消时发生错误: {e}")
                     except Exception as e:
                         logger.bind(tag=TAG).error(
                             f"等待监听任务完成时发生错误: {str(e)}"
@@ -394,31 +388,21 @@ class TTSProvider(TTSProviderBase):
         except Exception as e:
             logger.bind(tag=TAG).error(f"关闭会话失败: {str(e)}")
             # 确保清理资源
-            if hasattr(self, "_monitor_task"):
-                try:
-                    self._monitor_task.cancel()
-                    await self._monitor_task
-                except:
-                    pass
-                self._monitor_task = None
-            if self.ws:
-                try:
-                    await self.ws.close()
-                except:
-                    pass
-                self.ws = None
+            await self.close()
             raise
 
     async def close(self):
         """资源清理方法"""
         # 取消监听任务
-        if self._monitor_task:
+        if self._monitor_task and not self._monitor_task.done():
             try:
                 self._monitor_task.cancel()
                 await self._monitor_task
             except asyncio.CancelledError:
                 pass
-            self._monitor_task = None
+            except Exception as e:
+                logger.bind(tag=TAG).warning(f"关闭时取消监听任务错误: {e}")
+        self._monitor_task = None
 
         if self.ws:
             try:
diff --git a/main/xiaozhi-server/plugins_func/functions/play_music.py b/main/xiaozhi-server/plugins_func/functions/play_music.py
index a6eb5822..6451e526 100644
--- a/main/xiaozhi-server/plugins_func/functions/play_music.py
+++ b/main/xiaozhi-server/plugins_func/functions/play_music.py
@@ -1,13 +1,10 @@
-from config.logger import setup_logging
 import os
 import re
 import time
 import random
-import asyncio
 import difflib
 import traceback
 from pathlib import Path
-from core.utils import p3
 from core.handle.sendAudioHandle import send_stt_message
 from plugins_func.register import register_function, ToolType, ActionResponse, Action
 from core.utils.dialogue import Message
@@ -51,8 +48,8 @@ def play_music(conn, song_name: str):
             )
 
         # 提交异步任务
-        future = asyncio.run_coroutine_threadsafe(
-            handle_music_command(conn, music_intent), conn.loop
+        task = conn.loop.create_task(
+            handle_music_command(conn, music_intent)  # 封装异步逻辑
         )
 
         # 非阻塞回调处理
@@ -63,7 +60,7 @@ def play_music(conn, song_name: str):
             except Exception as e:
                 conn.logger.bind(tag=TAG).error(f"播放失败: {e}")
 
-        future.add_done_callback(handle_done)
+        task.add_done_callback(handle_done)
 
         return ActionResponse(
             action=Action.NONE, result="指令已接收", response="正在为您播放音乐"
@@ -218,13 +215,14 @@ async def play_local_music(conn, specific_file=None):
         await send_stt_message(conn, text)
         conn.dialogue.put(Message(role="assistant", content=text))
 
-        conn.tts.tts_text_queue.put(
-            TTSMessageDTO(
-                sentence_id=conn.sentence_id,
-                sentence_type=SentenceType.FIRST,
-                content_type=ContentType.ACTION,
+        if conn.intent_type == "intent_llm":
+            conn.tts.tts_text_queue.put(
+                TTSMessageDTO(
+                    sentence_id=conn.sentence_id,
+                    sentence_type=SentenceType.FIRST,
+                    content_type=ContentType.ACTION,
+                )
             )
-        )
         conn.tts.tts_text_queue.put(
             TTSMessageDTO(
                 sentence_id=conn.sentence_id,
@@ -241,13 +239,14 @@ async def play_local_music(conn, specific_file=None):
                 content_file=music_path,
             )
         )
-        conn.tts.tts_text_queue.put(
-            TTSMessageDTO(
-                sentence_id=conn.sentence_id,
-                sentence_type=SentenceType.LAST,
-                content_type=ContentType.ACTION,
+        if conn.intent_type == "intent_llm":
+            conn.tts.tts_text_queue.put(
+                TTSMessageDTO(
+                    sentence_id=conn.sentence_id,
+                    sentence_type=SentenceType.LAST,
+                    content_type=ContentType.ACTION,
+                )
             )
-        )
 
     except Exception as e:
         conn.logger.bind(tag=TAG).error(f"播放音乐失败: {str(e)}")

From 62e39dd0e248be0d89689709d3c0caaaf930a626 Mon Sep 17 00:00:00 2001
From: Sakura-RanChen <1908198662@qq.com>
Date: Wed, 9 Jul 2025 11:18:26 +0800
Subject: [PATCH 5/7] =?UTF-8?q?fix:=20=E7=AD=89=E5=BE=85=E6=97=B6=E5=8F=AF?=
 =?UTF-8?q?=E8=83=BD=E5=B7=B2=E7=BB=8F=E5=AE=8C=E6=88=90=EF=BC=88=E8=AE=BE?=
 =?UTF-8?q?=E7=BD=AE=E4=B8=BANone=EF=BC=89=EF=BC=8C=E5=90=8E=E7=BB=AD?=
 =?UTF-8?q?=E5=AF=B9None=E9=94=99=E8=AF=AF=E8=AE=BF=E9=97=AE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../providers/tts/huoshan_double_stream.py    | 19 ++++---------------
 1 file changed, 4 insertions(+), 15 deletions(-)

diff --git a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
index 49643b85..e6e4d2fa 100644
--- a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
+++ b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
@@ -364,20 +364,9 @@ class TTSProvider(TTSProviderBase):
                 logger.bind(tag=TAG).info("会话结束请求已发送")
 
                 # 等待监听任务完成
-                if hasattr(self, "_monitor_task") and self._monitor_task is not None:
+                if self._monitor_task:
                     try:
-                        # 设置4秒超时等待监听任务结束
-                        await asyncio.wait_for(self._monitor_task, timeout=4)
-                    except asyncio.TimeoutError:
-                        logger.bind(tag=TAG).warning("等待监听任务超时，强制取消")
-                        if not self._monitor_task.done():
-                            self._monitor_task.cancel()
-                            try:
-                                await self._monitor_task
-                            except asyncio.CancelledError:
-                                pass
-                            except Exception as e:
-                                logger.bind(tag=TAG).warning(f"监听任务取消时发生错误: {e}")
+                        await self._monitor_task
                     except Exception as e:
                         logger.bind(tag=TAG).error(
                             f"等待监听任务完成时发生错误: {str(e)}"
@@ -394,7 +383,7 @@ class TTSProvider(TTSProviderBase):
     async def close(self):
         """资源清理方法"""
         # 取消监听任务
-        if self._monitor_task and not self._monitor_task.done():
+        if self._monitor_task:
             try:
                 self._monitor_task.cancel()
                 await self._monitor_task
@@ -402,7 +391,7 @@ class TTSProvider(TTSProviderBase):
                 pass
             except Exception as e:
                 logger.bind(tag=TAG).warning(f"关闭时取消监听任务错误: {e}")
-        self._monitor_task = None
+            self._monitor_task = None
 
         if self.ws:
             try:

From 7f67459c6eb95e3f49d048e400f0b533468da2c7 Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Wed, 9 Jul 2025 16:26:26 +0800
Subject: [PATCH 6/7] =?UTF-8?q?update:=E5=A2=9E=E5=8A=A0=E4=B9=A6=E5=90=8D?=
 =?UTF-8?q?=E5=8F=B7?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/plugins_func/functions/play_music.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/main/xiaozhi-server/plugins_func/functions/play_music.py b/main/xiaozhi-server/plugins_func/functions/play_music.py
index 6451e526..2cbc4018 100644
--- a/main/xiaozhi-server/plugins_func/functions/play_music.py
+++ b/main/xiaozhi-server/plugins_func/functions/play_music.py
@@ -175,12 +175,12 @@ def _get_random_play_prompt(song_name):
     # 移除文件扩展名
     clean_name = os.path.splitext(song_name)[0]
     prompts = [
-        f"正在为您播放，{clean_name}",
-        f"请欣赏歌曲，{clean_name}",
-        f"即将为您播放，{clean_name}",
+        f"正在为您播放，《{clean_name}》",
+        f"请欣赏歌曲，《{clean_name}》",
+        f"即将为您播放，《{clean_name}》",
         f"现在为您带来，《{clean_name}》",
         f"让我们一起聆听，《{clean_name}》",
-        f"接下来请欣赏，{clean_name}",
+        f"接下来请欣赏，《{clean_name}》",
         f"此刻为您献上，《{clean_name}》",
     ]
     # 直接使用random.choice，不设置seed

From 2625133f407125b77bfa3d2c940154655b43e519 Mon Sep 17 00:00:00 2001
From: Sakura-RanChen <1908198662@qq.com>
Date: Wed, 9 Jul 2025 17:04:42 +0800
Subject: [PATCH 7/7] =?UTF-8?q?fix:=20=E6=89=93=E6=96=AD=E7=8A=B6=E6=80=81?=
 =?UTF-8?q?=E6=9C=AA=E9=87=8D=E7=BD=AE=20=E7=9B=91=E5=90=AC=E6=9C=AA?=
 =?UTF-8?q?=E5=AE=8C=E6=88=90=E6=97=B6=E6=9C=8D=E5=8A=A1=E7=AB=AF=E5=8F=AF?=
 =?UTF-8?q?=E8=83=BD=E8=BF=98=E5=9C=A8=E5=8F=91=E9=80=81=E6=95=B0=E6=8D=AE?=
 =?UTF-8?q?=20=E6=AD=A4=E6=97=B6=E5=A4=8D=E7=94=A8=E9=93=BE=E6=8E=A5?=
 =?UTF-8?q?=E4=BC=9A=E6=8E=A5=E6=94=B6=E4=B8=8A=E4=B8=AA=E8=AF=AD=E9=9F=B3?=
 =?UTF-8?q?=E7=9A=84=E6=AE=8B=E4=BD=99=20=E9=9C=80=E8=A6=81=E4=B8=A4?=
 =?UTF-8?q?=E8=80=85=E4=B8=80=E5=90=8C=E5=85=B3=E9=97=AD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/core/providers/tts/base.py    |  2 ++
 .../core/providers/tts/huoshan_double_stream.py   | 15 +++------------
 2 files changed, 5 insertions(+), 12 deletions(-)

diff --git a/main/xiaozhi-server/core/providers/tts/base.py b/main/xiaozhi-server/core/providers/tts/base.py
index c89b3247..9127ec12 100644
--- a/main/xiaozhi-server/core/providers/tts/base.py
+++ b/main/xiaozhi-server/core/providers/tts/base.py
@@ -195,6 +195,8 @@ class TTSProviderBase(ABC):
         while not self.conn.stop_event.is_set():
             try:
                 message = self.tts_text_queue.get(timeout=1)
+                if message.sentence_type == SentenceType.FIRST:
+                    self.conn.client_abort = False
                 if self.conn.client_abort:
                     logger.bind(tag=TAG).info("收到打断信息，终止TTS文本处理线程")
                     continue
diff --git a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
index e6e4d2fa..0eb7c72d 100644
--- a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
+++ b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
@@ -310,18 +310,9 @@ class TTSProvider(TTSProviderBase):
                 and isinstance(self._monitor_task, Task)
                 and not self._monitor_task.done()
             ):
-                logger.bind(tag=TAG).info("取消上一个监听任务...")
-                self._monitor_task.cancel()
-                try:
-                    # 等待任务取消完成
-                    await asyncio.wait_for(self._monitor_task, timeout=3)
-                except asyncio.CancelledError:
-                    logger.bind(tag=TAG).info("监听任务已成功取消")
-                except asyncio.TimeoutError:
-                    logger.bind(tag=TAG).warning("取消监听任务超时，可能仍在运行")
-                except Exception as e:
-                    logger.bind(tag=TAG).warning(f"取消监听任务异常: {e}")
-                self._monitor_task = None
+                logger.bind(tag=TAG).info("检测到未完成的上个会话，关闭监听任务和连接...")
+                await self.close()
+
             # 建立新连接
             await self._ensure_connection()