Music play (#142)

* Update util.py解决返回元组报错 (#103)

解决返回元组报错

* 增加播放本地音乐功能 (#105)

* Please enter the commit message for your changes. Lines starting
 with '#' will be ignored, and an empty message aborts the commit.

 On branch Music-playback
 Your branch is up to date with 'origin/Music-playback'.

 Changes to be committed:
	modified:   core/handle/audioHandle.py
	new file:   "music/\346\234\210\344\272\256\344\273\243\350\241\250\346\210\221\347\232\204\345\277\203_\351\202\223\344\270\275\345\220\233.mp3"
	new file:   "music/\350\270\217\345\261\261\346\262\263.mp3"

* Please enter the commit message for your changes. Lines starting
with '#' will be ignored, and an empty message aborts the commit.

On branch Music-playback
Your branch is up to date with 'origin/Music-playback'.

Changes to be committed:
	modified:   config.yaml
	modified:   core/connection.py
	modified:   core/handle/abortHandle.py
	modified:   core/handle/audioHandle.py
	new file:   core/handle/musicHandler.py
	modified:   core/handle/textHandle.py
	modified:   core/websocket_server.py
	new file:   "music/\344\270\200\345\277\265\345\215\203\345\271\264_\345\233\275\351\243\216\347\211\210.mp3"
	new file:   "music/\344\270\255\347\247\213\346\234\210.mp3"
	deleted:    "music/\346\234\210\344\272\256\344\273\243\350\241\250\346\210\221\347\232\204\345\277\203_\351\202\223\344\270\275\345\220\233.mp3"
	deleted:    "music/\350\270\217\345\261\261\346\262\263.mp3"

* 增加播放本地音乐功能

* 增加播放本地音乐功能

* 让音乐配置变的优雅

On branch Music-playback
Your branch is up to date with 'origin/Music-playback'.

Changes to be committed:
	modified:   config.yaml
	modified:   core/handle/musicHandler.py
	renamed:    "music/\344\270\200\345\277\265\345\215\203\345\271\264_\345\233\275\351\243\216\347\211\210.mp3" -> "music/mp3/\344\270\200\345\277\265\345\215\203\345\271\264_\345\233\275\351\243\216\347\211\210.mp3"
	renamed:    "music/\344\270\255\347\247\213\346\234\210.mp3" -> "music/mp3/\344\270\255\347\247\213\346\234\210.mp3"
	renamed:    "music/\345\273\211\346\263\242\350\200\201\347\237\243\357\274\214\345\260\232\350\203\275\351\245\255\345\220\246.mp3" -> "music/mp3/\345\273\211\346\263\242\350\200\201\347\237\243\357\274\214\345\260\232\350\203\275\351\245\255\345\220\246.mp3"
	new file:   music/music_config.yaml

---------

Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com>

* update:优化代码

* update:流控调试

* update:优化音乐播放

* update:优化音乐配置初始化

---------

Co-authored-by: linqingping <linqingping@users.noreply.github.com>
Co-authored-by: Chris <119588753+Chris-websketch@users.noreply.github.com>
Co-authored-by: hrz <1710360675@qq.com>

README.md

@@ -58,28 +58,13 @@
     </tr>
 </table>
 
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
 ---
 
 ## 系统要求与部署前提 🖥️
 
 - **硬件**：一套兼容 `xiaozhi-esp32`
   的硬件设备（具体型号请参考 [此处](https://rcnv1t9vps13.feishu.cn/wiki/DdgIw4BUgivWDPkhMj1cGIYCnRf)）。
-- **服务器**：至少 4 核 CPU、8G 内存的电脑或服务器。
+- **服务器**：至少 4 核 CPU、8G 内存的电脑。
 - **固件编译**：请将后端服务的接口地址更新至 `xiaozhi-esp32` 项目中，再重新编译固件并烧录到设备上。
 
 ---
@@ -178,17 +163,25 @@ server:
 
 ### 一、[部署文档](./docs/Deployment.md)
 
-本项目支持以下三种部署方式，您可根据实际需求选择：
+本项目支持以下三种部署方式，您可根据实际需求选择。
+
+本项目的文档主要是`文字版本`的教程，如果你想要`视频版本`的教程，您可以学习一下[这个大佬的手把手教程](https://www.bilibili.com/video/BV1gePuejEvT)。
+
+如果你能把`文字版本的教程`和`视频版本的教程`结合起来一起看，可以让你更快上手。
 
 1. [Docker 快速部署](./docs/Deployment.md)
-   适合快速体验，不需过多环境配置。缺点是，拉取镜像有点慢。
+
+适合快速体验的普通用户，不需过多环境配置。缺点是，拉取镜像有点慢。
 
 2. [借助 Docker 环境运行部署](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E5%80%9F%E5%8A%A9docker%E7%8E%AF%E5%A2%83%E8%BF%90%E8%A1%8C%E9%83%A8%E7%BD%B2)
-   适用于已安装 Docker 且希望对代码进行自定义修改的用户。
+
+适用于已安装 Docker 且希望对代码进行自定义修改的软件工程师。
 
 3. [本地源码运行](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%89%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C)
-   适合熟悉 Conda 环境或希望从零搭建运行环境的用户。  
-   对于对响应速度要求较高的场景，推荐使用本地源码运行方式以降低额外开销。
+
+适合熟悉`Conda` 环境或希望从零搭建运行环境的用户。
+
+对于对响应速度要求较高的场景，推荐使用本地源码运行方式以降低额外开销。
 
 ### 二、[固件编译](./docs/firmware-build.md)
 
@@ -304,7 +297,6 @@ TTS 性能排行:
 ## 鸣谢 🙏
 
 - 本项目受 [百聆语音对话机器人](https://github.com/wwbin2017/bailing) 启发，并在其基础上实现。
-- 感谢 [腾讯云](https://cloud.tencent.com/) 提供免费 Docker 镜像空间。
 - 感谢 [十方融海](https://www.tenclass.com/) 对小智通讯协议提供的详尽文档支持。
 
 <a href="https://star-history.com/#xinnan-tech/xiaozhi-esp32-server&Date">

config.yaml

@@ -41,7 +41,9 @@ manager:
   enabled: false
   ip: 0.0.0.0
   port: 8002
-
+iot:
+  Speaker:
+    volume: 100
 xiaozhi:
   type: hello
   version: 1
@@ -147,6 +149,12 @@ LLM:
     user_id: 你的user_id
     base_url: "https://api.coze.cn/open_api/v2/chat" # 服务地址
     personal_access_token: 你的coze个人令牌
+  LMStudioLLM:
+    # 定义LLM API类型
+    type: openai
+    model_name: deepseek-r1-distill-llama-8b@q4_k_m # 使用的模型名称，需要预先在社区下载
+    url: http://localhost:1234/v1 # LM Studio服务地址
+    api_key: lm-studio # LM Studio服务的固定API Key
   HomeAssistant:
     # 定义LLM API类型
     type: homeassistant
@@ -304,3 +312,19 @@ module_test:
     - "你好，请介绍一下你自己"
     - "What's the weather like today?"
     - "请用100字概括量子计算的基本原理和应用前景"
+
+# 本地音乐播放配置
+music:
+  music_commands:
+    - "来一首歌"
+    - "唱一首歌"
+    - "播放音乐"
+    - "来点音乐"
+    - "背景音乐"
+    - "放首歌"
+    - "播放歌曲"
+    - "来点背景音乐"
+    - "我想听歌"
+    - "我要听歌"
+    - "放点音乐"
+  music_dir: "./music"  # 音乐文件存放路径

core/connection.py

@@ -4,6 +4,7 @@ import uuid
 import time
 import queue
 import asyncio
+import traceback
 from config.logger import setup_logging
 import threading
 import websockets
@@ -14,15 +15,18 @@ from core.utils.dialogue import Message, Dialogue
 from core.handle.textHandle import handleTextMessage
 from core.utils.util import get_string_no_punctuation_or_emoji
 from concurrent.futures import ThreadPoolExecutor, TimeoutError
-from core.handle.audioHandle import handleAudioMessage, sendAudioMessage
+from core.handle.sendAudioHandle import sendAudioMessage
+from core.handle.receiveAudioHandle import handleAudioMessage
 from config.private_config import PrivateConfig
 from core.auth import AuthMiddleware, AuthenticationError
-from core.utils.auth_code_gen import AuthCodeGenerator  # 添加导入
+from core.utils.auth_code_gen import AuthCodeGenerator
+
 
 TAG = __name__
 
+
 class ConnectionHandler:
-    def __init__(self, config: Dict[str, Any], _vad, _asr, _llm, _tts):
+    def __init__(self, config: Dict[str, Any], _vad, _asr, _llm, _tts, _music):
         self.config = config
         self.logger = setup_logging()
         self.auth = AuthMiddleware(config)
@@ -72,28 +76,33 @@ class ConnectionHandler:
         self.tts_start_speak_time = None
         self.tts_duration = 0
 
+        # iot相关变量
+        self.iot_descriptors = {}
+
         self.cmd_exit = self.config["CMD_exit"]
         self.max_cmd_length = 0
         for cmd in self.cmd_exit:
             if len(cmd) > self.max_cmd_length:
                 self.max_cmd_length = len(cmd)
-        
+
         self.private_config = None
         self.auth_code_gen = AuthCodeGenerator.get_instance()
         self.is_device_verified = False  # 添加设备验证状态标志
-
+        self.music_handler = _music
 
     async def handle_connection(self, ws):
         try:
             # 获取并验证headers
             self.headers = dict(ws.request.headers)
-            self.logger.bind(tag=TAG).info(f"New connection request - Headers: {self.headers}")
+            # 获取客户端ip地址
+            client_ip = ws.remote_address[0]
+            self.logger.bind(tag=TAG).info(f"{client_ip} conn - Headers: {self.headers}")
 
             # 进行认证
             await self.auth.authenticate(self.headers)
 
             device_id = self.headers.get("device-id", None)
-            
+
             # Load private configuration if device_id is provided
             bUsePrivateConfig = self.config.get("use_private_config", False)
             self.logger.bind(tag=TAG).info(f"bUsePrivateConfig: {bUsePrivateConfig}, device_id: {device_id}")
@@ -104,10 +113,10 @@ class ConnectionHandler:
                     # 判断是否已经绑定
                     owner = self.private_config.get_owner()
                     self.is_device_verified = owner is not None
-                    
+
                     if self.is_device_verified:
-                        await self.private_config.update_last_chat_time() 
-                    
+                        await self.private_config.update_last_chat_time()
+
                     llm, tts = self.private_config.create_private_instances()
                     if all([llm, tts]):
                         self.llm = llm
@@ -146,7 +155,8 @@ class ConnectionHandler:
             await ws.close()
             return
         except Exception as e:
-            self.logger.bind(tag=TAG).error(f"Connection error: {str(e)}")
+            stack_trace = traceback.format_exc()
+            self.logger.bind(tag=TAG).error(f"Connection error: {str(e)}-{stack_trace}")
             await ws.close()
             return
 
@@ -166,7 +176,7 @@ class ConnectionHandler:
             date_time = time.strftime("%Y-%m-%d %H:%M", time.localtime())
             self.prompt = self.prompt.replace("{date_time}", date_time)
         self.dialogue.put(Message(role="system", content=self.prompt))
-          
+
     async def _check_and_broadcast_auth_code(self):
         """检查设备绑定状态并广播认证码"""
         if not self.private_config.get_owner():
@@ -186,7 +196,7 @@ class ConnectionHandler:
             # 如果不使用私有配置，就不需要验证
             return False
         return not self.is_device_verified
-    
+
     def chat(self, query):
         # 如果设备未验证，就发送验证码
         if self.isNeedAuth():
@@ -199,7 +209,7 @@ class ConnectionHandler:
             finally:
                 loop.close()
             return True
-        
+
         self.dialogue.put(Message(role="user", content=query))
         response_message = []
         start = 0
@@ -316,6 +326,8 @@ class ConnectionHandler:
 
     async def close(self):
         """资源清理方法"""
+
+        # 清理其他资源
         self.stop_event.set()
         self.executor.shutdown(wait=False)
         if self.websocket:

core/handle/iotHandle.py

@@ -0,0 +1,152 @@
+import json
+from config.logger import setup_logging
+
+TAG = __name__
+logger = setup_logging()
+
+
+class IotDescriptor:
+    """
+    A class to represent an IoT descriptor.
+    Attributes:
+    ----------
+    name : str
+        The name of the IoT descriptor.
+    description : str
+        A brief description of the IoT descriptor.
+    properties : dict
+        A dictionary containing properties of the IoT descriptor.
+    methods : dict
+        A dictionary containing methods of the IoT descriptor.
+    -------
+    """
+
+    def __init__(self, name, description, properties, methods):
+        self.name = name
+        self.description = description
+        self.properties = []
+        self.methods = []
+
+        # 根据描述创建属性
+        for key, value in properties.items():
+            # "volume":{"description":"当前音量 值","type":"number"}
+            """
+            等价于
+            {
+                'name': 名字,
+                'description': 描述,
+                'value': 0
+            }
+            """
+            # setattr(self, key, {}) # 创建一个空字典, 名字是属性名
+            property_item = globals()[key] = {}  # 创建一个空字典, 名字是属性名
+            property_item['name'] = key
+            property_item["description"] = value["description"]
+            if value["type"] == "number":
+                property_item["value"] = 0
+            elif value["type"] == "boolean":
+                property_item["value"] = False
+            else:
+                property_item["value"] = ""
+            self.properties.append(property_item)
+
+        # 根据描述创建方法
+        for key, value in methods.items():
+            # "SetVolume": {"description":"设置音量","parameters":{"volume":{"description":"0到100之间的整数","type":"number"}}}
+            """
+            等价于
+            SetVolume = {
+                `description`: 描述,
+                `volume`: {
+                    `description`: 描述,
+                    `value`: 0
+                }
+            }
+            """
+            # setattr(self, key, {}) # 创建一个空字典, 名字是方法名
+            method = globals()[key] = {}  # 创建一个空字典, 名字是方法名
+            method["description"] = value["description"]
+            method['name'] = key
+            for k, v in value["parameters"].items():
+                # 不同的参数解析
+                method[k] = {}
+                method[k]["description"] = v["description"]
+                if v["type"] == "number":
+                    method[k]["value"] = 0
+                elif v["type"] == "boolean":
+                    method[k]["value"] = False
+                else:
+                    method[k]["value"] = ""
+
+            self.methods.append(method)
+
+
+async def handleIotDescriptors(conn, descriptors):
+    """
+    处理物联网描述
+    示例: [{
+        "name":"Speaker",
+        "description":"当前 AI 机器人的扬声器",
+        "properties":{
+            "volume":{"description":"当前音量 值","type":"number"}  可以有boolean, number, string三种类型
+        },
+        "methods":{
+            "SetVolume":{
+                "description":"设置音量","parameters":{"volume":{"description":"0到100之间的整数","type":"number"}}
+            }
+        }
+    }]
+    descriptors: 描述列表
+    """
+    for descriptor in descriptors:
+        iot_descriptor = IotDescriptor(descriptor["name"], descriptor["description"], descriptor["properties"],
+                                       descriptor["methods"])
+        conn.iot_descriptors[descriptor["name"]] = iot_descriptor
+
+    # 暂时从配置文件中设置音量，后期通过意图识别控制音量
+    default_iot_volume = 100
+    if "iot" in conn.config:
+        default_iot_volume = conn.config["iot"]["Speaker"]["volume"]
+    logger.bind(tag=TAG).info(f"服务端设置音量为{default_iot_volume}")
+    await send_iot_conn(conn, "Speaker", "SetVolume", {"volume": default_iot_volume})
+
+
+async def send_iot_conn(conn, name, method_name, parameters):
+    """
+    发送物联网指令
+    name: 设备名称 "Speaker"
+    method: 方法 "SetVolume"
+    parameters: 参数, 是一个字典 {"volume": 100}
+    发送示例:
+    {
+        "type": "iot",
+        "commands": [
+            {
+                "name" :  "Speaker",
+                "method": "SetVolume",
+                "parameters": {
+                    "volume": 100
+                    }
+            }
+        ]
+    }
+    """
+
+    for key, value in conn.iot_descriptors.items():
+        if key == name:
+            # 找到了设备
+            for method in value.methods:
+                # 找到了方法
+                if method["name"] == method_name:
+                    await conn.websocket.send(json.dumps({
+                        "type": "iot",
+                        "commands": [
+                            {
+                                "name": name,
+                                "method": method_name,
+                                "parameters": parameters
+                            }
+                        ]
+                    }))
+                    return
+    logger.bind(tag=TAG).error(f"未找到方法{method_name}")

core/handle/musicHandler.py

@@ -0,0 +1,109 @@
+from config.logger import setup_logging
+import os
+import random
+import difflib
+import re
+import traceback
+from core.handle.sendAudioHandle import sendAudioMessage, send_stt_message
+
+TAG = __name__
+logger = setup_logging()
+
+
+def _extract_song_name(text):
+    """从用户输入中提取歌名"""
+    for keyword in ["听", "播放", "放", "唱"]:
+        if keyword in text:
+            parts = text.split(keyword)
+            if len(parts) > 1:
+                return parts[1].strip()
+    return None
+
+
+def _find_best_match(potential_song, music_files):
+    """查找最匹配的歌曲"""
+    best_match = None
+    highest_ratio = 0
+
+    for music_file in music_files:
+        song_name = os.path.splitext(music_file)[0]
+        ratio = difflib.SequenceMatcher(None, potential_song, song_name).ratio()
+        if ratio > highest_ratio and ratio > 0.4:
+            highest_ratio = ratio
+            best_match = music_file
+    return best_match
+
+
+class MusicHandler:
+    def __init__(self, config):
+        self.config = config
+        self.music_related_keywords = []
+
+        if "music" in self.config:
+            self.music_config = self.config["music"]
+            self.music_dir = os.path.abspath(
+                self.music_config.get("music_dir", "./music")  # 默认路径修改
+            )
+            self.music_related_keywords = self.music_config.get("music_commands", [])
+        else:
+            self.music_dir = os.path.abspath("./music")
+            self.music_related_keywords = ["来一首歌", "唱一首歌", "播放音乐", "来点音乐", "背景音乐", "放首歌",
+                                           "播放歌曲", "来点背景音乐", "我想听歌", "我要听歌", "放点音乐"]
+
+    async def handle_music_command(self, conn, text):
+        """处理音乐播放指令"""
+        clean_text = re.sub(r'[^\w\s]', '', text).strip()
+        logger.bind(tag=TAG).debug(f"检查是否是音乐命令: {clean_text}")
+
+        # 尝试匹配具体歌名
+        if os.path.exists(self.music_dir):
+            music_files = [f for f in os.listdir(self.music_dir) if f.endswith('.mp3')]
+            logger.bind(tag=TAG).debug(f"找到的音乐文件: {music_files}")
+
+            potential_song = _extract_song_name(clean_text)
+            if potential_song:
+                best_match = _find_best_match(potential_song, music_files)
+                if best_match:
+                    logger.bind(tag=TAG).info(f"找到最匹配的歌曲: {best_match}")
+                    await self.play_local_music(conn, specific_file=best_match)
+                    return True
+
+        # 检查是否是通用播放音乐命令
+        if any(cmd in clean_text for cmd in self.music_related_keywords):
+            await self.play_local_music(conn)
+            return True
+
+        return False
+
+    async def play_local_music(self, conn, specific_file=None):
+        """播放本地音乐文件"""
+        try:
+            if not os.path.exists(self.music_dir):
+                logger.bind(tag=TAG).error(f"音乐目录不存在: {self.music_dir}")
+                return
+
+            # 确保路径正确性
+            if specific_file:
+                music_path = os.path.join(self.music_dir, specific_file)
+                if not os.path.exists(music_path):
+                    logger.bind(tag=TAG).error(f"指定的音乐文件不存在: {music_path}")
+                    return
+                selected_music = specific_file
+            else:
+                music_files = [f for f in os.listdir(self.music_dir) if f.endswith('.mp3')]
+                if not music_files:
+                    logger.bind(tag=TAG).error("未找到MP3音乐文件")
+                    return
+                selected_music = random.choice(music_files)
+                music_path = os.path.join(self.music_dir, selected_music)
+            text = f"正在播放{selected_music}"
+            await send_stt_message(conn, text)
+            conn.tts_first_text = selected_music
+            conn.tts_last_text = selected_music
+            conn.llm_finish_task = True
+            opus_packets, duration = conn.tts.wav_to_opus_data(music_path)
+            await sendAudioMessage(conn, opus_packets, duration, selected_music)
+
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"播放音乐失败: {str(e)}")
+            logger.bind(tag=TAG).error(f"详细错误: {traceback.format_exc()}")

core/handle/receiveAudioHandle.py

@@ -0,0 +1,81 @@
+from config.logger import setup_logging
+import asyncio
+import time
+from core.utils.util import remove_punctuation_and_length
+from core.handle.sendAudioHandle import schedule_with_interrupt, send_stt_message
+
+TAG = __name__
+logger = setup_logging()
+
+
+async def handleAudioMessage(conn, audio):
+    if not conn.asr_server_receive:
+        logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
+        return
+    if conn.client_listen_mode == "auto":
+        have_voice = conn.vad.is_vad(conn, audio)
+    else:
+        have_voice = conn.client_have_voice
+
+    # 如果本次没有声音，本段也没声音，就把声音丢弃了
+    if have_voice == False and conn.client_have_voice == False:
+        await no_voice_close_connect(conn)
+        conn.asr_audio.clear()
+        return
+    conn.client_no_voice_last_time = 0.0
+    conn.asr_audio.append(audio)
+    # 如果本段有声音，且已经停止了
+    if conn.client_voice_stop:
+        conn.client_abort = False
+        conn.asr_server_receive = False
+        # 音频太短了，无法识别
+        if len(conn.asr_audio) < 3:
+            conn.asr_server_receive = True
+        else:
+            text, file_path = await conn.asr.speech_to_text(conn.asr_audio, conn.session_id)
+            logger.bind(tag=TAG).info(f"识别文本: {text}")
+            text_len, text_without_punctuation = remove_punctuation_and_length(text)
+            if await conn.music_handler.handle_music_command(conn, text_without_punctuation):
+                conn.asr_server_receive = True
+                conn.asr_audio.clear()
+                return
+            if text_len <= conn.max_cmd_length and await handleCMDMessage(conn, text_without_punctuation):
+                return
+            if text_len > 0:
+                await startToChat(conn, text)
+            else:
+                conn.asr_server_receive = True
+        conn.asr_audio.clear()
+        conn.reset_vad_states()
+
+
+async def handleCMDMessage(conn, text):
+    cmd_exit = conn.cmd_exit
+    for cmd in cmd_exit:
+        if text == cmd:
+            logger.bind(tag=TAG).info("识别到明确的退出命令".format(text))
+            await conn.close()
+            return True
+    return False
+
+
+async def startToChat(conn, text):
+    # 异步发送 stt 信息
+    stt_task = asyncio.create_task(
+        schedule_with_interrupt(0, send_stt_message(conn, text))
+    )
+    conn.scheduled_tasks.append(stt_task)
+    conn.executor.submit(conn.chat, text)
+
+
+async def no_voice_close_connect(conn):
+    if conn.client_no_voice_last_time == 0.0:
+        conn.client_no_voice_last_time = time.time() * 1000
+    else:
+        no_voice_time = time.time() * 1000 - conn.client_no_voice_last_time
+        close_connection_no_voice_time = conn.config.get("close_connection_no_voice_time", 120)
+        if no_voice_time > 1000 * close_connection_no_voice_time:
+            conn.client_abort = False
+            conn.asr_server_receive = False
+            prompt = "时间过得真快，我都好久没说话了。请你用十个字左右话跟我告别，以“再见”或“拜拜”为结尾"
+            await startToChat(conn, prompt)

core/handle/sendAudioHandle.py

@@ -8,56 +8,6 @@ TAG = __name__
 logger = setup_logging()
 
 
-async def handleAudioMessage(conn, audio):
-    if not conn.asr_server_receive:
-        logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
-        return
-    if conn.client_listen_mode == "auto":
-        have_voice = conn.vad.is_vad(conn, audio)
-    else:
-        have_voice = conn.client_have_voice
-
-    # 如果本次没有声音，本段也没声音，就把声音丢弃了
-    if have_voice == False and conn.client_have_voice == False:
-        await no_voice_close_connect(conn)
-        conn.asr_audio.clear()
-        return
-    conn.client_no_voice_last_time = 0.0
-    conn.asr_audio.append(audio)
-    # 如果本段有声音，且已经停止了
-    if conn.client_voice_stop:
-        conn.client_abort = False
-        conn.asr_server_receive = False
-        # 音频太短了，无法识别
-        if len(conn.asr_audio) < 3:
-            conn.asr_server_receive = True
-        else:
-            text, file_path = await conn.asr.speech_to_text(conn.asr_audio, conn.session_id)
-            logger.bind(tag=TAG).info(f"识别文本: {text}")
-            text_len, text_without_punctuation = remove_punctuation_and_length(text)
-            if text_len <= conn.max_cmd_length and await handleCMDMessage(conn, text_without_punctuation):
-                return
-            if text_len > 0:
-                await startToChat(conn, text)
-            else:
-                conn.asr_server_receive = True
-        conn.asr_audio.clear()
-        conn.reset_vad_states()
-
-async def handleCMDMessage(conn, text):
-    cmd_exit = conn.cmd_exit
-    for cmd in cmd_exit:
-        if text == cmd:
-            logger.bind(tag=TAG).info("识别到明确的退出命令".format(text))
-            await finishToChat(conn)
-            return True
-    return False
-
-
-async def finishToChat(conn):
-    await conn.close()
-
-
 async def isLLMWantToFinish(conn):
     first_text = conn.tts_first_text
     last_text = conn.tts_last_text
@@ -70,15 +20,6 @@ async def isLLMWantToFinish(conn):
     return False
 
 
-async def startToChat(conn, text):
-    # 异步发送 stt 信息
-    stt_task = asyncio.create_task(
-        schedule_with_interrupt(0, send_stt_message(conn, text))
-    )
-    conn.scheduled_tasks.append(stt_task)
-    conn.executor.submit(conn.chat, text)
-
-
 async def sendAudioMessage(conn, audios, duration, text):
     base_delay = conn.tts_duration
 
@@ -107,7 +48,7 @@ async def sendAudioMessage(conn, audios, duration, text):
         conn.scheduled_tasks.append(stop_task)
         if await isLLMWantToFinish(conn):
             finish_task = asyncio.create_task(
-                schedule_with_interrupt(stop_duration, finishToChat(conn))
+                schedule_with_interrupt(stop_duration, await conn.close())
             )
             conn.scheduled_tasks.append(finish_task)
 
@@ -152,16 +93,3 @@ async def schedule_with_interrupt(delay, coro):
         await coro
     except asyncio.CancelledError:
         pass
-
-
-async def no_voice_close_connect(conn):
-    if conn.client_no_voice_last_time == 0.0:
-        conn.client_no_voice_last_time = time.time() * 1000
-    else:
-        no_voice_time = time.time() * 1000 - conn.client_no_voice_last_time
-        close_connection_no_voice_time = conn.config.get("close_connection_no_voice_time", 120)
-        if no_voice_time > 1000 * close_connection_no_voice_time:
-            conn.client_abort = False
-            conn.asr_server_receive = False
-            prompt = "时间过得真快，我都好久没说话了。请你用十个字左右话跟我告别，以“再见”或“拜拜拜”为结尾"
-            await startToChat(conn, prompt)

core/handle/textHandle.py

@@ -2,7 +2,8 @@ from config.logger import setup_logging
 import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
-from core.handle.audioHandle import startToChat
+from core.handle.receiveAudioHandle import startToChat
+from core.handle.iotHandle import handleIotDescriptors
 
 TAG = __name__
 logger = setup_logging()
@@ -36,5 +37,8 @@ async def handleTextMessage(conn, message):
                 conn.asr_audio.clear()
                 if "text" in msg_json:
                     await startToChat(conn, msg_json["text"])
+        elif msg_json["type"] == "iot":
+            if "descriptors" in msg_json:
+                await handleIotDescriptors(conn, msg_json["descriptors"])
     except json.JSONDecodeError:
         await conn.websocket.send(message)

core/providers/llm/openai/openai.py

@@ -25,12 +25,25 @@ class LLMProvider(LLMProviderBase):
                 messages=dialogue,
                 stream=True
             )
+            
+            is_active = True
             for chunk in responses:
-                # 检查是否存在有效的choice且content不为空
-                if chunk.choices and len(chunk.choices) > 0:
-                    delta = chunk.choices[0].delta
-                    content = getattr(delta, 'content', '')
-                    if content:  # 仅在content非空时生成
+                try:
+                    # 检查是否存在有效的choice且content不为空
+                    delta = chunk.choices[0].delta if getattr(chunk, 'choices', None) else None
+                    content = delta.content if hasattr(delta, 'content') else ''
+                except IndexError:
+                    content = ''
+                if content:
+                    # 处理标签跨多个chunk的情况
+                    if '<think>' in content:
+                        is_active = False
+                        content = content.split('<think>')[0]
+                    if '</think>' in content:
+                        is_active = True
+                        content = content.split('</think>')[-1]
+                    if is_active:
                         yield content
+
         except Exception as e:
             logger.bind(tag=TAG).error(f"Error in response generation: {e}")

core/websocket_server.py

@@ -2,6 +2,7 @@ import asyncio
 import websockets
 from config.logger import setup_logging
 from core.connection import ConnectionHandler
+from core.handle.musicHandler import MusicHandler
 from core.utils.util import get_local_ip
 from core.utils import asr, vad, llm, tts
 
@@ -12,7 +13,8 @@ class WebSocketServer:
     def __init__(self, config: dict):
         self.config = config
         self.logger = setup_logging()
-        self._vad, self._asr, self._llm, self._tts = self._create_processing_instances()
+        self._vad, self._asr, self._llm, self._tts, self._music = self._create_processing_instances()
+        self.active_connections = set()  # 添加全局连接记录
 
     def _create_processing_instances(self):
         """创建处理模块实例"""
@@ -43,7 +45,8 @@ class WebSocketServer:
                 self.config["TTS"][self.config["selected_module"]["TTS"]]["type"],
                 self.config["TTS"][self.config["selected_module"]["TTS"]],
                 self.config["delete_audio"]
-            )
+            ),
+            MusicHandler(self.config)
         )
 
     async def start(self):
@@ -62,5 +65,10 @@ class WebSocketServer:
 
     async def _handle_connection(self, websocket):
         """处理新连接，每次创建独立的ConnectionHandler"""
-        handler = ConnectionHandler(self.config, self._vad, self._asr, self._llm, self._tts)
-        await handler.handle_connection(websocket)
+        # 创建ConnectionHandler时传入当前server实例
+        handler = ConnectionHandler(self.config, self._vad, self._asr, self._llm, self._tts, self._music)
+        self.active_connections.add(handler)
+        try:
+            await handler.handle_connection(websocket)
+        finally:
+            self.active_connections.discard(handler)

docker-compose.yml

@@ -1,3 +1,4 @@
+version: '3'
 services:
   xiaozhi-esp32-server:
     image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:latest

docs/Deployment.md

@@ -117,7 +117,7 @@ docker run -it --name xiaozhi-env --restart always --security-opt seccomp:unconf
   -p 8000:8000 \
   -p 8002:8002 \
   -v ./:/app \
-  ccr.ccs.tencentyun.com/kalicyh/poetry:v3.10_latest
+  kalicyh/poetry:v3.10_xiaozhi
 ```
 
 然后就和正常开发一样了

requirements.txt

@@ -16,4 +16,4 @@ aiohttp_cors==0.7.0
 ormsgpack==1.7.0
 ruamel.yaml==0.18.10
 loguru==0.7.3
-requests>=2.0.0
+requests==2.32.3