Hot fix (#415)

* fix:找不到function卡住bug

* fix:客户端拾音模式日志bug

main/xiaozhi-server/config.yaml

@@ -114,10 +114,10 @@ Memory:
     # 每月有1000次免费调用
     api_key: 你的mem0ai api key
   nomem:
-    # 不想使用记忆功能，可以使用nomem 
+    # 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，不会上传到服务器
     type: mem_local_short
 
 ASR:
@@ -225,7 +225,7 @@ TTS:
     # 定义TTS API类型
     type: edge
     voice: zh-CN-XiaoxiaoNeural
-    output_file: tmp/
+    output_dir: tmp/
   DoubaoTTS:
     # 定义TTS API类型
     type: doubao
@@ -235,7 +235,7 @@ TTS:
     # 地址：https://console.volcengine.com/speech/service/8
     api_url: https://openspeech.bytedance.com/api/v1/tts
     voice: BV001_streaming
-    output_file: tmp/
+    output_dir: tmp/
     authorization: "Bearer;"
     appid: 你的火山引擎语音合成服务appid
     access_token: 你的火山引擎语音合成服务access_token
@@ -246,7 +246,7 @@ TTS:
     # token申请地址 https://cloud.siliconflow.cn/account/ak
     model: FunAudioLLM/CosyVoice2-0.5B
     voice: FunAudioLLM/CosyVoice2-0.5B:alex
-    output_file: tmp/
+    output_dir: tmp/
     access_token: 你的硅基流动API密钥
     response_format: wav
   CozeCnTTS:
@@ -254,7 +254,7 @@ TTS:
     # COZECN TTS
     # token申请地址 https://www.coze.cn/open/oauth/pats
     voice: 7426720361733046281
-    output_file: tmp/
+    output_dir: tmp/
     access_token: 你的coze web key
     response_format: wav
   FishSpeech:
@@ -267,7 +267,7 @@ TTS:
     #--decoder-config-name firefly_gan_vq
     #--compile
     type: fishspeech
-    output_file: tmp/
+    output_dir: tmp/
     response_format: wav
     reference_id: null
     reference_audio: ["/tmp/test.wav",]
@@ -291,7 +291,7 @@ TTS:
     #python api_v2.py -a 127.0.0.1 -p 9880 -c GPT_SoVITS/configs/caixukun.yaml
     type: gpt_sovits_v2
     url: "http://127.0.0.1:9880/tts"
-    output_file: tmp/
+    output_dir: tmp/
     text_lang: "auto"
     ref_audio_path: "caixukun.wav"
     prompt_text: ""
@@ -316,7 +316,7 @@ TTS:
     #python api.py
     type: gpt_sovits_v3
     url: "http://127.0.0.1:9880"
-    output_file: tmp/
+    output_dir: tmp/
     text_language: "auto"
     refer_wav_path: "caixukun.wav"
     prompt_language: "zh"
@@ -337,7 +337,7 @@ TTS:
     # api_key地址：https://platform.minimaxi.com/user-center/basic-information/interface-key
     # 定义TTS API类型
     type: minimax
-    output_file: tmp/
+    output_dir: tmp/
     group_id: 你的minimax平台groupID
     api_key: 你的minimax平台接口密钥
     model: "speech-01-turbo"
@@ -374,7 +374,7 @@ TTS:
     # token地址：https://nls-portal.console.aliyun.com/overview
     # 定义TTS API类型
     type: aliyun
-    output_file: tmp/
+    output_dir: tmp/
     appkey: 你的阿里云智能语音交互服务项目Appkey
     token: 你的阿里云智能语音交互服务AccessToken，临时的24小时，要长期用下方的access_key_id，access_key_secret
     voice: xiaoyun
@@ -397,7 +397,7 @@ TTS:
     api_url: https://api.302ai.cn/doubao/tts_hd
     authorization: "Bearer "
     voice: "zh_female_wanwanxiaohe_moon_bigtts"
-    output_file: tmp/
+    output_dir: tmp/
     access_token: "你的302API密钥"
   ACGNTTS:
     #在线网址：https://acgn.ttson.cn/
@@ -414,7 +414,7 @@ TTS:
     to_lang: ZH
     url: https://u95167-bd74-2aef8085.westx.seetacloud.com:8443/flashsummary/tts?token=
     format: mp3
-    output_file: tmp/
+    output_dir: tmp/
     emotion: 1
   OpenAITTS:
     # openai官方文本转语音服务，可支持全球大多数语种
@@ -428,7 +428,7 @@ TTS:
     voice: onyx
     # 语速范围0.25-4.0
     speed: 1
-    output_file: tmp/
+    output_dir: tmp/
   CustomTTS:
     # 自定义的TTS接口服务，请求参数可自定义
     # 要求接口使用GET方式请求，并返回音频文件
@@ -443,7 +443,7 @@ TTS:
     headers: # 自定义请求头
       # Authorization: Bearer xxxx
     format: wav # 接口返回的音频格式
-    output_file: tmp/
+    output_dir: tmp/
 # 模块测试配置
 module_test:
   test_sentences:  # 自定义测试语句
@@ -466,4 +466,4 @@ manager:
   enabled: false
   ip: 0.0.0.0
   port: 8002
-use_private_config: false
+use_private_config: false

main/xiaozhi-server/config/settings.py

@@ -7,9 +7,48 @@ from core.utils.util import read_config, get_project_dir
 default_config_file = "config.yaml"
 
 
+def ensure_directories(config):
+    """确保所有配置路径存在"""
+    dirs_to_create = set()
+    project_dir = get_project_dir()  # 获取项目根目录
+    # 日志文件目录
+    log_dir = config.get('log', {}).get('log_dir', 'tmp')
+    dirs_to_create.add(os.path.join(project_dir, log_dir))
+
+    # ASR/TTS模块输出目录
+    for module in ['ASR', 'TTS']:
+        for provider in config.get(module, {}).values():
+            output_dir = provider.get('output_dir', '')
+            if output_dir:
+                dirs_to_create.add(output_dir)
+
+    # 根据selected_module创建模型目录
+    selected_modules = config.get('selected_module', {})
+    for module_type in ['ASR', 'LLM', 'TTS']:
+        selected_provider = selected_modules.get(module_type)
+        if not selected_provider:
+            continue
+        provider_config = config.get(module_type, {}).get(selected_provider, {})
+        output_dir = provider_config.get('output_dir')
+        if output_dir:
+            full_model_dir = os.path.join(project_dir, output_dir)
+            dirs_to_create.add(full_model_dir)
+
+    # 统一创建目录（保留原data目录创建）
+    for dir_path in dirs_to_create:
+        try:
+            os.makedirs(dir_path, exist_ok=True)
+        except PermissionError:
+            print(f"警告：无法创建目录 {dir_path}，请检查写入权限")
+
+
 def get_config_file():
     global default_config_file
-    # 判断是否存在私有的配置文件
+    """获取配置文件路径，优先使用私有配置文件（若存在）。
+
+    Returns:
+       str: 配置文件路径（相对路径或默认路径）
+    """
     config_file = default_config_file
     if os.path.exists(get_project_dir() + "data/." + default_config_file):
         config_file = "data/." + default_config_file
@@ -20,9 +59,13 @@ def load_config():
     """加载配置文件"""
     parser = argparse.ArgumentParser(description="Server configuration")
     config_file = get_config_file()
+
     parser.add_argument("--config_path", type=str, default=config_file)
     args = parser.parse_args()
-    return read_config(args.config_path)
+    config = read_config(args.config_path)
+    # 初始化目录
+    ensure_directories(config)
+    return config
 
 
 def update_config(config):
@@ -67,7 +110,7 @@ def find_missing_keys(new_config, old_config, parent_key=''):
 def check_config_file():
     old_config_file = get_config_file()
     global default_config_file
-    if not old_config_file.startswith('data'):
+    if not 'data' in old_config_file:
         return
     old_config = read_config(get_project_dir() + old_config_file)
     new_config = read_config(get_project_dir() + default_config_file)

main/xiaozhi-server/core/connection.py

@@ -197,7 +197,7 @@ class ConnectionHandler:
         self.dialogue.put(Message(role="system", content=self.prompt))
 
         self.func_handler = FunctionHandler(self.config)
-    
+
     def change_system_prompt(self, prompt):
         self.prompt = prompt
         # 找到原来的role==system，替换原来的系统提示
@@ -303,7 +303,7 @@ class ConnectionHandler:
         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):
+    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"""
         if self.isNeedAuth():
@@ -311,7 +311,7 @@ class ConnectionHandler:
             future = asyncio.run_coroutine_threadsafe(self._check_and_broadcast_auth_code(), self.loop)
             future.result()
             return True
-        
+
         if not tool_call:
             self.dialogue.put(Message(role="user", content=query))
 
@@ -320,7 +320,7 @@ class ConnectionHandler:
 
         response_message = []
         processed_chars = 0  # 跟踪已处理的字符位置
-   
+
         try:
             start_time = time.time()
 
@@ -328,7 +328,7 @@ class ConnectionHandler:
             future = asyncio.run_coroutine_threadsafe(self.memory.query_memory(query), self.loop)
             memory_str = future.result()
 
-            #self.logger.bind(tag=TAG).info(f"对话记录: {self.dialogue.get_llm_dialogue_with_memory(memory_str)}")
+            # 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(
@@ -351,8 +351,8 @@ class ConnectionHandler:
         content_arguments = ""
         for response in llm_responses:
             content, tools_call = response
-            if content is not None and len(content)>0:
+            if content is not None and len(content) > 0:
-                if len(response_message)<=0 and (content=="```" or "<tool_call>" in content):
+                if len(response_message) <= 0 and (content == "```" or "<tool_call>" in content):
                     tool_call_flag = True
 
             if tools_call is not None:
@@ -366,7 +366,7 @@ class ConnectionHandler:
 
             if content is not None and len(content) > 0:
                 if tool_call_flag:
-                    content_arguments+=content
+                    content_arguments += content
                 else:
                     response_message.append(content)
 
@@ -422,16 +422,17 @@ class ConnectionHandler:
                 else:
                     function_arguments = json.loads(function_arguments)
             if not bHasError:
-                self.logger.bind(tag=TAG).info(f"function_name={function_name}, function_id={function_id}, function_arguments={function_arguments}")
+                self.logger.bind(tag=TAG).info(
+                    f"function_name={function_name}, function_id={function_id}, function_arguments={function_arguments}")
                 function_call_data = {
                     "name": function_name,
                     "id": function_id,
                     "arguments": function_arguments
                 }
                 result = self.func_handler.handle_llm_function_call(self, function_call_data)
-                self._handle_function_result(result, function_call_data, text_index+1)
+                self._handle_function_result(result, function_call_data, text_index + 1)
 
-         # 处理最后剩余的文本
+        # 处理最后剩余的文本
         full_text = "".join(response_message)
         remaining_text = full_text[processed_chars:]
         if remaining_text:
@@ -443,7 +444,7 @@ class ConnectionHandler:
                 self.tts_queue.put(future)
 
         # 存储对话内容
-        if len(response_message)>0:
+        if len(response_message) > 0:
             self.dialogue.put(Message(role="assistant", content="".join(response_message)))
 
         self.llm_finish_task = True
@@ -452,32 +453,40 @@ class ConnectionHandler:
         return True
 
     def _handle_function_result(self, result, function_call_data, text_index):
-        if result.action == Action.RESPONSE: # 直接回复前端
+        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)
             self.tts_queue.put(future)
             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
+        elif result.action == Action.REQLLM:  # 调用函数后再请求llm生成回复
-            
+
             text = result.result
             if text is not None and len(text) > 0:
                 function_id = function_call_data["id"]
                 function_name = function_call_data["name"]
                 function_arguments = function_call_data["arguments"]
                 self.dialogue.put(Message(role='assistant',
-                                            tool_calls=[{"id": function_id, 
+                                          tool_calls=[{"id": function_id,
-                                                        "function": {"arguments": function_arguments,"name": function_name},
+                                                       "function": {"arguments": function_arguments,
-                                                        "type": 'function', 
+                                                                    "name": function_name},
-                                                        "index": 0}]))
+                                                       "type": 'function',
+                                                       "index": 0}]))
 
                 self.dialogue.put(Message(role="tool", tool_call_id=function_id, content=text))
                 self.chat_with_function_calling(text, tool_call=True)
         elif result.action == Action.NOTFOUND:
-            text = result.response
+            text = result.result
+            self.recode_first_last_text(text, text_index)
+            future = self.executor.submit(self.speak_and_play, text, text_index)
+            self.tts_queue.put(future)
+            self.dialogue.put(Message(role="assistant", content=text))
         else:
-            text = result.response
+            text = result.result
-        
+            self.recode_first_last_text(text, text_index)
+            future = self.executor.submit(self.speak_and_play, text, text_index)
+            self.tts_queue.put(future)
+            self.dialogue.put(Message(role="assistant", content=text))
 
     def _tts_priority_thread(self):
         while not self.stop_event.is_set():

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

@@ -212,7 +212,7 @@ def register_device_type(descriptor):
                         },
                         "response_failure": {
                             "type": "string",
-                            "description": "查询失败时的友好回复，例如：'无法获取{device_name}的{prop_info['description']}'"
+                            "description": f"查询失败时的友好回复，例如：'无法获取{device_name}的{prop_info['description']}'"
                         }
                     },
                     "required": ["response_success", "response_failure"]

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

@@ -2,7 +2,7 @@ from config.logger import setup_logging
 import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
-from core.handle.receiveAudioHandle import startToChat
+from core.handle.receiveAudioHandle import startToChat, handleAudioMessage
 from core.handle.iotHandle import handleIotDescriptors, handleIotStatus
 
 TAG = __name__
@@ -31,6 +31,8 @@ async def handleTextMessage(conn, message):
             elif msg_json["state"] == "stop":
                 conn.client_have_voice = True
                 conn.client_voice_stop = True
+                if len(conn.asr_audio) > 0:
+                    await handleAudioMessage(conn, b'')
             elif msg_json["state"] == "detect":
                 conn.asr_server_receive = False
                 conn.client_have_voice = False
@@ -41,6 +43,6 @@ async def handleTextMessage(conn, message):
             if "descriptors" in msg_json:
                 await handleIotDescriptors(conn, msg_json["descriptors"])
             if "states" in msg_json:
-                await handleIotStatus(conn, msg_json["states"])  
+                await handleIotStatus(conn, msg_json["states"])
     except json.JSONDecodeError:
         await conn.websocket.send(message)

main/xiaozhi-server/core/providers/tts/base.py

@@ -13,7 +13,7 @@ logger = setup_logging()
 class TTSProviderBase(ABC):
     def __init__(self, config, delete_audio_file):
         self.delete_audio_file = delete_audio_file
-        self.output_file = config.get("output_file")
+        self.output_file = config.get("output_dir")
 
     @abstractmethod
     def generate_filename(self):

main/xiaozhi-server/core/providers/tts/custom.py

@@ -15,7 +15,7 @@ class TTSProvider(TTSProviderBase):
         self.headers = config.get("headers", {})
         self.params = config.get("params")
         self.format = config.get("format", "wav")
-        self.output_file = config.get("output_file", "tmp/")
+        self.output_file = config.get("output_dir", "tmp/")
 
     def generate_filename(self):
         return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}.{self.format}")

main/xiaozhi-server/core/providers/tts/openai.py

@@ -14,7 +14,7 @@ class TTSProvider(TTSProviderBase):
         self.voice = config.get("voice", "alloy")
         self.response_format = "wav"
         self.speed = config.get("speed", 1.0)
-        self.output_file = config.get("output_file", "tmp/")
+        self.output_file = config.get("output_dir", "tmp/")
         check_model_key("TTS", self.api_key)
 
     def generate_filename(self, extension=".wav"):

main/xiaozhi-server/core/providers/tts/ttson.py

@@ -17,7 +17,7 @@ class TTSProvider(TTSProviderBase):
         self.volume_change_dB = config.get("volume_change_dB", 0)
         self.speed_factor = config.get("speed_factor", 1)
         self.stream = config.get("stream", False)
-        self.output_file = config.get("output_file")
+        self.output_file = config.get("output_dir")
         self.pitch_factor = config.get("pitch_factor", 0)
         self.format = config.get("format", "mp3")
         self.emotion = config.get("emotion", 1)

main/xiaozhi-server/docker-compose.yml

@@ -21,6 +21,7 @@ services:
       - ./data:/opt/xiaozhi-esp32-server/data
       # 模型文件挂接，很重要
       - ./models/SenseVoiceSmall/model.pt:/opt/xiaozhi-esp32-server/models/SenseVoiceSmall/model.pt
+
 #  #智控台还没开发好，还不能完全使用，会报很多错误，如果是非技术人员，请不要启用智控台服务
 #  xiaozhi-esp32-server-web:
 #    image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest

main/xiaozhi-server/plugins_func/functions/raise_and_lower_the_volume.py

@@ -49,6 +49,8 @@ def raise_and_lower_the_volume(conn, action: str):
 
 async def _raise_and_lower_the_volume(conn, action):
     volume = await get_iot_status(conn, "Speaker", "volume")
+    if volume is None:
+        raise Exception("你的设备不支持音量控制")
     if action == 'raise':
         volume += 10
     elif action == 'lower':

main/xiaozhi-server/requirements.txt

@@ -19,4 +19,4 @@ loguru==0.7.3
 requests==2.32.3
 cozepy==0.12.0
 mem0ai==0.1.62
-bs4==0.0.2
+bs4==0.0.2