update:server连接api (#747)

* update:server连接manager-api

* update:读取智能体模型配置

* update:添加默认模型的按钮

* update:优化配置读取方式

* update：server兼容manager接口改造

* update:优化私有配置加载

* update:加载私有模型配置

main/xiaozhi-server/core/connection.py

@@ -1,4 +1,5 @@
 import os
+import copy
 import json
 import uuid
 import time
@@ -17,16 +18,16 @@ from core.utils.util import (
     get_string_no_punctuation_or_emoji,
     extract_json_from_string,
     get_ip_info,
+    initialize_modules,
 )
 from concurrent.futures import ThreadPoolExecutor, TimeoutError
 from core.handle.sendAudioHandle import sendAudioMessage
 from core.handle.receiveAudioHandle import handleAudioMessage
 from core.handle.functionHandler import FunctionHandler
 from plugins_func.register import Action, ActionResponse
-from config.private_config import PrivateConfig
 from core.auth import AuthMiddleware, AuthenticationError
-from core.utils.auth_code_gen import AuthCodeGenerator
 from core.mcp.manager import MCPManager
+from config.config_loader import get_private_config_from_api
 
 TAG = __name__
 
@@ -41,7 +42,7 @@ class ConnectionHandler:
     def __init__(
         self, config: Dict[str, Any], _vad, _asr, _llm, _tts, _memory, _intent
     ):
-        self.config = config
+        self.config = copy.deepcopy(config)
         self.logger = setup_logging()
         self.auth = AuthMiddleware(config)
 
@@ -95,15 +96,12 @@ class ConnectionHandler:
         self.iot_descriptors = {}
         self.func_handler = None
 
-        self.cmd_exit = self.config["CMD_exit"]
+        self.cmd_exit = self.config["exit_commands"]
         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.close_after_chat = False  # 是否在聊天结束后关闭连接
         self.use_function_call_mode = False
         if self.config["selected_module"]["Intent"] == "function_call":
@@ -121,7 +119,6 @@ class ConnectionHandler:
 
             # 进行认证
             await self.auth.authenticate(self.headers)
-            device_id = self.headers.get("device-id", None)
 
             # 认证通过,继续处理
             self.websocket = ws
@@ -130,39 +127,6 @@ class ConnectionHandler:
             self.welcome_msg = self.config["xiaozhi"]
             self.welcome_msg["session_id"] = self.session_id
             await self.websocket.send(json.dumps(self.welcome_msg))
-            # Load private configuration if device_id is provided
-            bUsePrivateConfig = self.config.get("use_private_config", False)
-            if bUsePrivateConfig and device_id:
-                try:
-                    self.private_config = PrivateConfig(
-                        device_id, self.config, self.auth_code_gen
-                    )
-                    await self.private_config.load_or_create()
-                    # 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()
-
-                    llm, tts = self.private_config.create_private_instances()
-                    if all([llm, tts]):
-                        self.llm = llm
-                        self.tts = tts
-                        self.logger.bind(tag=TAG).info(
-                            f"Loaded private config and instances for device {device_id}"
-                        )
-                    else:
-                        self.logger.bind(tag=TAG).error(
-                            f"Failed to create instances for device {device_id}"
-                        )
-                        self.private_config = None
-                except Exception as e:
-                    self.logger.bind(tag=TAG).error(
-                        f"Error initializing private config: {e}"
-                    )
-                    self.private_config = None
-                    raise
 
             # 异步初始化
             self.executor.submit(self._initialize_components)
@@ -211,10 +175,11 @@ class ConnectionHandler:
             await handleAudioMessage(self, message)
 
     def _initialize_components(self):
+        """初始化组件"""
+        self._initialize_models()
+
         """加载提示词"""
         self.prompt = self.config["prompt"]
-        if self.private_config:
-            self.prompt = self.private_config.private_config.get("prompt", self.prompt)
         self.dialogue.put(Message(role="system", content=self.prompt))
 
         """加载记忆"""
@@ -222,13 +187,100 @@ class ConnectionHandler:
         """加载意图识别"""
         self._initialize_intent()
         """加载位置信息"""
-        self.client_ip_info = get_ip_info(self.client_ip)
+        self.client_ip_info = get_ip_info(self.client_ip, self.logger)
         if self.client_ip_info is not None and "city" in self.client_ip_info:
             self.logger.bind(tag=TAG).info(f"Client ip info: {self.client_ip_info}")
             self.prompt = self.prompt + f"\nuser location:{self.client_ip_info}"
 
             self.dialogue.update_system_message(self.prompt)
 
+    def _initialize_models(self):
+        read_config_from_api = self.config.get("read_config_from_api", False)
+        """如果是从配置文件获取，则进行二次实例化"""
+        if not read_config_from_api:
+            return
+        """从接口获取差异化的配置进行二次实例化，非全量重新实例化"""
+        try:
+            private_config = get_private_config_from_api(
+                self.config,
+                self.headers.get("device-id", None),
+                self.headers.get("client-id", None),
+            )
+            private_config["delete_audio"] = self.config["delete_audio"]
+            self.logger.bind(tag=TAG).info(f"获取差异化配置成功: {private_config}")
+        except Exception as e:
+            self.logger.bind(tag=TAG).error(f"获取差异化配置失败: {e}")
+            private_config = {}
+
+        init_vad, init_asr, init_llm, init_tts, init_memory, init_intent = (
+            False,
+            False,
+            False,
+            False,
+            False,
+            False,
+        )
+        if private_config.get("VAD", None) is not None:
+            init_vad = True
+            self.config["vad"] = private_config["VAD"]
+            self.config["selected_module"]["VAD"] = private_config["selected_module"][
+                "VAD"
+            ]
+        if private_config.get("ASR", None) is not None:
+            init_asr = True
+            self.config["asr"] = private_config["ASR"]
+            self.config["selected_module"]["ASR"] = private_config["selected_module"][
+                "ASR"
+            ]
+        if private_config.get("LLM", None) is not None:
+            init_llm = True
+            self.config["llm"] = private_config["LLM"]
+            self.config["selected_module"]["LLM"] = private_config["selected_module"][
+                "LLM"
+            ]
+        if private_config.get("TTS", None) is not None:
+            init_tts = True
+            self.config["tts"] = private_config["TTS"]
+            self.config["selected_module"]["TTS"] = private_config["selected_module"][
+                "TTS"
+            ]
+        if private_config.get("Memory", None) is not None:
+            init_memory = True
+            self.config["memory"] = private_config["Memory"]
+            self.config["selected_module"]["Memory"] = private_config[
+                "selected_module"
+            ]["Memory"]
+        if private_config.get("Intent", None) is not None:
+            init_intent = True
+            self.config["intent"] = private_config["Intent"]
+            self.config["selected_module"]["Intent"] = private_config[
+                "selected_module"
+            ]["Intent"]
+        if private_config.get("prompt", None) is not None:
+            self.config["prompt"] = private_config["prompt"]
+        try:
+            modules = initialize_modules(
+                self.logger,
+                private_config,
+                init_vad,
+                init_asr,
+                init_llm,
+                init_tts,
+                init_memory,
+                init_intent,
+            )
+        except Exception as e:
+            self.logger.bind(tag=TAG).error(f"初始化组件失败: {e}")
+            modules = {}
+        if modules.get("tts", None) is not None:
+            self.tts = modules["tts"]
+        if modules.get("llm", None) is not None:
+            self.llm = modules["llm"]
+        if modules.get("intent", None) is not None:
+            self.intent = modules["intent"]
+        if modules.get("memory", None) is not None:
+            self.memory = modules["memory"]
+
     def _initialize_memory(self):
         """初始化记忆模块"""
         device_id = self.headers.get("device-id", None)
@@ -281,34 +333,7 @@ class ConnectionHandler:
             if m.role == "system":
                 m.content = 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():
-            auth_code = self.private_config.get_auth_code()
-            if auth_code:
-                # 发送验证码语音提示
-                text = f"请在后台输入验证码：{' '.join(auth_code)}"
-                self.recode_first_last_text(text)
-                future = self.executor.submit(self.speak_and_play, text)
-                self.tts_queue.put(future)
-            return False
-        return True
-
-    def isNeedAuth(self):
-        bUsePrivateConfig = self.config.get("use_private_config", False)
-        if not bUsePrivateConfig:
-            # 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):
-        if self.isNeedAuth():
-            self.llm_finish_task = True
-            future = asyncio.run_coroutine_threadsafe(
-                self._check_and_broadcast_auth_code(), self.loop
-            )
-            future.result()
-            return True
 
         self.dialogue.put(Message(role="user", content=query))
 
@@ -391,13 +416,6 @@ class ConnectionHandler:
     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():
-            self.llm_finish_task = True
-            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))

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

@@ -8,6 +8,7 @@ import os
 import random
 import time
 
+TAG = __name__
 logger = setup_logging()
 
 WAKEUP_CONFIG = {
@@ -69,6 +70,14 @@ def getWakeupWordFile(file_name):
 
 
 async def wakeupWordsResponse(conn):
+    wait_max_time = 5
+    while conn.llm is None or not conn.llm.response_no_stream:
+        await asyncio.sleep(1)
+        wait_max_time -= 1
+        if wait_max_time <= 0:
+            logger.bind(tag=TAG).error("连接对象没有llm")
+            return
+
     """唤醒词响应"""
     wakeup_word = random.choice(WAKEUP_CONFIG["words"])
     result = conn.llm.response_no_stream(conn.config["prompt"], wakeup_word)

main/xiaozhi-server/core/mcp/manager.py

@@ -1,26 +1,30 @@
 """MCP服务管理器"""
+
 import os, json
 from typing import Dict, Any, List
 from .MCPClient import MCPClient
 from config.logger import setup_logging
-from core.utils.util import get_project_dir
-from plugins_func.register import register_function, ActionResponse, Action, ToolType
+from plugins_func.register import register_function, ToolType
+from config.config_loader import get_project_dir
 
 TAG = __name__
 
+
 class MCPManager:
     """管理多个MCP服务的集中管理器"""
 
-    def __init__(self,conn) -> None:
+    def __init__(self, conn) -> None:
         """
         初始化MCP管理器
         """
         self.conn = conn
         self.logger = setup_logging()
-        self.config_path = get_project_dir() + 'data/.mcp_server_settings.json'
+        self.config_path = get_project_dir() + "data/.mcp_server_settings.json"
         if os.path.exists(self.config_path) == False:
             self.config_path = ""
-            self.logger.bind(tag=TAG).warning(f"请检查mcp服务配置文件：data/.mcp_server_settings.json")
+            self.logger.bind(tag=TAG).warning(
+                f"请检查mcp服务配置文件：data/.mcp_server_settings.json"
+            )
         self.client: Dict[str, MCPClient] = {}
         self.tools = []
 
@@ -31,13 +35,15 @@ class MCPManager:
         """
         if len(self.config_path) == 0:
             return {}
-        
+
         try:
-            with open(self.config_path, 'r', encoding='utf-8') as f:
+            with open(self.config_path, "r", encoding="utf-8") as f:
                 config = json.load(f)
-            return config.get('mcpServers', {})
+            return config.get("mcpServers", {})
         except Exception as e:
-            self.logger.bind(tag=TAG).error(f"Error loading MCP config from {self.config_path}: {e}")
+            self.logger.bind(tag=TAG).error(
+                f"Error loading MCP config from {self.config_path}: {e}"
+            )
             return {}
 
     async def initialize_servers(self) -> None:
@@ -45,7 +51,9 @@ class MCPManager:
         config = self.load_config()
         for name, srv_config in config.items():
             if not srv_config.get("command"):
-                self.logger.bind(tag=TAG).warning(f"Skipping server {name}: command not specified")
+                self.logger.bind(tag=TAG).warning(
+                    f"Skipping server {name}: command not specified"
+                )
                 continue
 
             try:
@@ -56,12 +64,18 @@ class MCPManager:
                 client_tools = client.get_available_tools()
                 self.tools.extend(client_tools)
                 for tool in client_tools:
-                    func_name = "mcp_"+tool["function"]["name"]
-                    register_function(func_name, tool, ToolType.MCP_CLIENT)(self.execute_tool)
-                    self.conn.func_handler.function_registry.register_function(func_name)
+                    func_name = "mcp_" + tool["function"]["name"]
+                    register_function(func_name, tool, ToolType.MCP_CLIENT)(
+                        self.execute_tool
+                    )
+                    self.conn.func_handler.function_registry.register_function(
+                        func_name
+                    )
 
             except Exception as e:
-                self.logger.bind(tag=TAG).error(f"Failed to initialize MCP server {name}: {e}")
+                self.logger.bind(tag=TAG).error(
+                    f"Failed to initialize MCP server {name}: {e}"
+                )
         self.conn.func_handler.upload_functions_desc()
 
     def get_all_tools(self) -> List[Dict[str, Any]]:
@@ -79,7 +93,10 @@ class MCPManager:
             bool: 是否是MCP工具
         """
         for tool in self.tools:
-            if tool.get("function") != None and tool["function"].get("name") == tool_name:
+            if (
+                tool.get("function") != None
+                and tool["function"].get("name") == tool_name
+            ):
                 return True
         return False
 
@@ -87,17 +104,19 @@ class MCPManager:
         """执行工具调用
         Args:
             tool_name: 工具名称
-            arguments: 工具参数 
+            arguments: 工具参数
         Returns:
             Any: 工具执行结果
         Raises:
             ValueError: 工具未找到时抛出
         """
-        self.logger.bind(tag=TAG).info(f"Executing tool {tool_name} with arguments: {arguments}")
+        self.logger.bind(tag=TAG).info(
+            f"Executing tool {tool_name} with arguments: {arguments}"
+        )
         for client in self.client.values():
             if client.has_tool(tool_name):
                 return await client.call_tool(tool_name, arguments)
-            
+
         raise ValueError(f"Tool {tool_name} not found in any MCP server")
 
     async def cleanup_all(self) -> None:
@@ -106,5 +125,7 @@ class MCPManager:
                 await client.cleanup()
                 self.logger.bind(tag=TAG).info(f"Cleaned up MCP client: {name}")
             except Exception as e:
-                self.logger.bind(tag=TAG).error(f"Error cleaning up MCP client {name}: {e}")
+                self.logger.bind(tag=TAG).error(
+                    f"Error cleaning up MCP client {name}: {e}"
+                )
         self.client.clear()

main/xiaozhi-server/core/providers/llm/gemini/gemini.py

@@ -4,15 +4,17 @@ from core.providers.llm.base import LLMProviderBase
 from config.logger import setup_logging
 import requests
 import json
+
 TAG = __name__
 logger = setup_logging()
 
+
 class LLMProvider(LLMProviderBase):
     def __init__(self, config):
         """初始化Gemini LLM Provider"""
         self.model_name = config.get("model_name", "gemini-1.5-pro")
         self.api_key = config.get("api_key")
-        self.http_proxy=config.get("http_proxy")
+        self.http_proxy = config.get("http_proxy")
         self.https_proxy = config.get("https_proxy")
         have_key = check_model_key("LLM", self.api_key)
 
@@ -22,7 +24,7 @@ class LLMProvider(LLMProviderBase):
         try:
             # 初始化Gemini客户端
             # 配置代理（如果提供了代理配置）
-            self.proxies=None
+            self.proxies = None
             if self.http_proxy is not "" or self.https_proxy is not "":
 
                 self.proxies = {
@@ -62,19 +64,16 @@ class LLMProvider(LLMProviderBase):
                 role = "model" if msg["role"] == "assistant" else "user"
                 content = msg["content"].strip()
                 if content:
-                    chat_history.append({
-                        "role": role,
-                        "parts": [{"text":content}]
-
-                    })
+                    chat_history.append({"role": role, "parts": [{"text": content}]})
 
             # 获取当前消息
             current_msg = dialogue[-1]["content"]
 
             # 构建请求体
             request_body = {
-                "contents": chat_history + [{"role": "user", "parts": [{"text":current_msg}]}],
-                "generationConfig": self.generation_config
+                "contents": chat_history
+                + [{"role": "user", "parts": [{"text": current_msg}]}],
+                "generationConfig": self.generation_config,
             }
 
             # 构建请求URL
@@ -87,11 +86,17 @@ class LLMProvider(LLMProviderBase):
 
             # 发送POST请求,经测试手动 request 无法使用 stream 模式
             if self.proxies:
-                response = requests.post(url, headers=headers, json=request_body, stream=False, proxies=self.proxies)
+                response = requests.post(
+                    url,
+                    headers=headers,
+                    json=request_body,
+                    stream=False,
+                    proxies=self.proxies,
+                )
                 try:
                     data = response.json()  # 直接解析JSON
-                    if 'candidates' in data and data['candidates']:
-                        yield data['candidates'][0]['content']['parts'][0]['text']
+                    if "candidates" in data and data["candidates"]:
+                        yield data["candidates"][0]["content"]["parts"][0]["text"]
                     else:
                         yield "未找到候选回复。"
                 except json.JSONDecodeError as e:
@@ -104,13 +109,11 @@ class LLMProvider(LLMProviderBase):
 
                 # 发送消息并获取流式响应
                 response = chat.send_message(
-                    current_msg,
-                    stream=True,
-                    generation_config=self.generation_config
+                    current_msg, stream=True, generation_config=self.generation_config
                 )
                 # 处理流式响应
                 for chunk in response:
-                    if hasattr(chunk, 'text') and chunk.text:
+                    if hasattr(chunk, "text") and chunk.text:
                         yield chunk.text
 
         except Exception as e:
@@ -125,9 +128,6 @@ class LLMProvider(LLMProviderBase):
             else:
                 yield f"【Gemini服务响应异常: {error_msg}】"
 
-
-
-
         except requests.exceptions.RequestException as e:
             yield f"请求失败：{e}"
         except json.JSONDecodeError as e:

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

@@ -11,7 +11,7 @@ class LLMProvider(LLMProviderBase):
     def __init__(self, config):
         self.model_name = config.get("model_name")
         self.api_key = config.get("api_key")
-        if 'base_url' in config:
+        if "base_url" in config:
             self.base_url = config.get("base_url")
         else:
             self.base_url = config.get("url")
@@ -33,18 +33,22 @@ class LLMProvider(LLMProviderBase):
             for chunk in responses:
                 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 ''
+                    delta = (
+                        chunk.choices[0].delta
+                        if getattr(chunk, "choices", None)
+                        else None
+                    )
+                    content = delta.content if hasattr(delta, "content") else ""
                 except IndexError:
-                    content = ''
+                    content = ""
                 if content:
                     # 处理标签跨多个chunk的情况
-                    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
 
@@ -54,10 +58,7 @@ class LLMProvider(LLMProviderBase):
     def response_with_functions(self, session_id, dialogue, functions=None):
         try:
             stream = self.client.chat.completions.create(
-                model=self.model_name,
-                messages=dialogue,
-                stream=True,
-                tools=functions
+                model=self.model_name, messages=dialogue, stream=True, tools=functions
             )
 
             for chunk in stream:

main/xiaozhi-server/core/providers/memory/mem0ai/mem0ai.py

@@ -6,13 +6,14 @@ from core.utils.util import check_model_key
 
 TAG = __name__
 
+
 class MemoryProvider(MemoryProviderBase):
     def __init__(self, config):
         super().__init__(config)
         self.api_key = config.get("api_key", "")
         self.api_version = config.get("api_version", "v1.1")
         have_key = check_model_key("Mem0ai", self.api_key)
-        if not have_key :
+        if not have_key:
             self.use_mem0 = False
             return
         else:
@@ -30,54 +31,55 @@ class MemoryProvider(MemoryProviderBase):
             return None
         if len(msgs) < 2:
             return None
-        
+
         try:
             # Format the content as a message list for mem0
             messages = [
                 {"role": message.role, "content": message.content}
-                for message in msgs if message.role != "system"
+                for message in msgs
+                if message.role != "system"
             ]
-            result = self.client.add(messages, user_id=self.role_id, output_format=self.api_version)
+            result = self.client.add(
+                messages, user_id=self.role_id, output_format=self.api_version
+            )
             logger.bind(tag=TAG).debug(f"Save memory result: {result}")
         except Exception as e:
             logger.bind(tag=TAG).error(f"保存记忆失败: {str(e)}")
             return None
 
-    async def query_memory(self, query: str)-> str:
+    async def query_memory(self, query: str) -> str:
         if not self.use_mem0:
             return ""
         try:
             results = self.client.search(
-                query,
-                user_id=self.role_id,
-                output_format=self.api_version
+                query, user_id=self.role_id, output_format=self.api_version
             )
-            if not results or 'results' not in results:
+            if not results or "results" not in results:
                 return ""
-                
+
             # Format each memory entry with its update time up to minutes
             memories = []
-            for entry in results['results']:
-                timestamp = entry.get('updated_at', '')
+            for entry in results["results"]:
+                timestamp = entry.get("updated_at", "")
                 if timestamp:
                     try:
                         # Parse and reformat the timestamp
-                        dt = timestamp.split('.')[0]  # Remove milliseconds
-                        formatted_time = dt.replace('T', ' ')
+                        dt = timestamp.split(".")[0]  # Remove milliseconds
+                        formatted_time = dt.replace("T", " ")
                     except:
                         formatted_time = timestamp
-                memory = entry.get('memory', '')
+                memory = entry.get("memory", "")
                 if timestamp and memory:
                     # Store tuple of (timestamp, formatted_string) for sorting
                     memories.append((timestamp, f"[{formatted_time}] {memory}"))
-            
+
             # Sort by timestamp in descending order (newest first)
             memories.sort(key=lambda x: x[0], reverse=True)
-            
+
             # Extract only the formatted strings
             memories_str = "\n".join(f"- {memory[1]}" for memory in memories)
             logger.bind(tag=TAG).debug(f"Query results: {memories_str}")
             return memories_str
         except Exception as e:
             logger.bind(tag=TAG).error(f"查询记忆失败: {str(e)}")
-            return ""
+            return ""

main/xiaozhi-server/core/providers/memory/mem_local_short/mem_local_short.py

@@ -3,7 +3,8 @@ import time
 import json
 import os
 import yaml
-from core.utils.util import get_project_dir
+from config.config_loader import get_project_dir
+
 
 short_term_memory_prompt = """
 # 时空记忆编织者
@@ -71,11 +72,12 @@ short_term_memory_prompt = """
 ```
 """
 
+
 def extract_json_data(json_code):
     start = json_code.find("```json")
     # 从start开始找到下一个```结束
-    end = json_code.find("```", start+1)
-    #print("start:", start, "end:", end)
+    end = json_code.find("```", start + 1)
+    # print("start:", start, "end:", end)
     if start == -1 or end == -1:
         try:
             jsonData = json.loads(json_code)
@@ -83,74 +85,76 @@ def extract_json_data(json_code):
         except Exception as e:
             print("Error:", e)
         return ""
-    jsonData = json_code[start+7:end]
+    jsonData = json_code[start + 7 : end]
     return jsonData
 
+
 TAG = __name__
 
+
 class MemoryProvider(MemoryProviderBase):
     def __init__(self, config):
         super().__init__(config)
         self.short_momery = ""
-        self.memory_path = get_project_dir() + 'data/.memory.yaml'
+        self.memory_path = get_project_dir() + "data/.memory.yaml"
         self.load_memory()
 
     def init_memory(self, role_id, llm):
         super().init_memory(role_id, llm)
         self.load_memory()
-    
+
     def load_memory(self):
         all_memory = {}
         if os.path.exists(self.memory_path):
-            with open(self.memory_path, 'r', encoding='utf-8') as f:
+            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]
-    
+
     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 {}
+            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
-        with open(self.memory_path, 'w', encoding='utf-8') as f:
+        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):
         if self.llm is None:
             logger.bind(tag=TAG).error("LLM is not set for memory provider")
             return None
-        
+
         if len(msgs) < 2:
             return None
-        
+
         msgStr = ""
         for msg in msgs:
             if msg.role == "user":
                 msgStr += f"User: {msg.content}\n"
-            elif msg.role== "assistant":
+            elif msg.role == "assistant":
                 msgStr += f"Assistant: {msg.content}\n"
         if len(self.short_momery) > 0:
-            msgStr+="历史记忆：\n"
-            msgStr+=self.short_momery
-        
-        #当前时间
+            msgStr += "历史记忆：\n"
+            msgStr += self.short_momery
+
+        # 当前时间
         time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
         msgStr += f"当前时间：{time_str}"
 
         result = self.llm.response_no_stream(short_term_memory_prompt, msgStr)
- 
+
         json_str = extract_json_data(result)
         try:
-            json_data = json.loads(json_str) # 检查json格式是否正确
+            json_data = json.loads(json_str)  # 检查json格式是否正确
             self.short_momery = json_str
         except Exception as e:
             print("Error:", e)
-        
+
         self.save_memory_to_file()
         logger.bind(tag=TAG).info(f"Save memory successful - Role: {self.role_id}")
 
         return self.short_momery
-    
-    async def query_memory(self, query: str)-> str:
-        return self.short_momery
+
+    async def query_memory(self, query: str) -> str:
+        return self.short_momery

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

@@ -6,6 +6,10 @@ import requests
 from datetime import datetime
 from core.utils.util import check_model_key
 from core.providers.tts.base import TTSProviderBase
+from config.logger import setup_logging
+
+TAG = __name__
+logger = setup_logging()
 
 
 class TTSProvider(TTSProviderBase):
@@ -21,18 +25,19 @@ class TTSProvider(TTSProviderBase):
         check_model_key("TTS", self.access_token)
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         request_json = {
             "app": {
                 "appid": f"{self.appid}",
                 "token": "access_token",
-                "cluster": self.cluster
-            },
-            "user": {
-                "uid": "1"
+                "cluster": self.cluster,
             },
+            "user": {"uid": "1"},
             "audio": {
                 "voice_type": self.voice,
                 "encoding": "wav",
@@ -46,17 +51,21 @@ class TTSProvider(TTSProviderBase):
                 "text_type": "plain",
                 "operation": "query",
                 "with_frontend": 1,
-                "frontend_type": "unitTson"
-            }
+                "frontend_type": "unitTson",
+            },
         }
 
         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 "data" in resp.json():
                 data = resp.json()["data"]
                 file_to_save = open(output_file, "wb")
                 file_to_save.write(base64.b64decode(data))
             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}")

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

@@ -24,7 +24,7 @@ class ServeReferenceAudio(BaseModel):
     def decode_audio(cls, values):
         audio = values.get("audio")
         if (
-                isinstance(audio, str) and len(audio) > 255
+            isinstance(audio, str) and len(audio) > 255
         ):  # Check if audio is a string (Base64)
             try:
                 values["audio"] = base64.b64decode(audio)
@@ -107,7 +107,10 @@ class TTSProvider(TTSProviderBase):
         self.api_url = config.get("api_url", "http://127.0.0.1:8080/v1/tts")
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         # Prepare reference data
@@ -117,9 +120,7 @@ class TTSProvider(TTSProviderBase):
         data = {
             "text": text,
             "references": [
-                ServeReferenceAudio(
-                    audio=audio if audio else b"", text=text
-                )
+                ServeReferenceAudio(audio=audio if audio else b"", text=text)
                 for text, audio in zip(ref_texts, byte_audios)
             ],
             "reference_id": self.reference_id,
@@ -139,7 +140,9 @@ class TTSProvider(TTSProviderBase):
 
         response = requests.post(
             self.api_url,
-            data=ormsgpack.packb(pydantic_data, option=ormsgpack.OPT_SERIALIZE_PYDANTIC),
+            data=ormsgpack.packb(
+                pydantic_data, option=ormsgpack.OPT_SERIALIZE_PYDANTIC
+            ),
             headers={
                 "Authorization": f"Bearer {self.api_key}",
                 "Content-Type": "application/msgpack",
@@ -152,8 +155,6 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as audio_file:
                 audio_file.write(audio_content)
 
-
-
         else:
             print(f"Request failed with status code {response.status_code}")
             print(response.json())

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

@@ -4,6 +4,11 @@ import requests
 from datetime import datetime
 from core.utils.util import check_model_key
 from core.providers.tts.base import TTSProviderBase
+from config.logger import setup_logging
+
+TAG = __name__
+logger = setup_logging()
+
 
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
@@ -18,23 +23,28 @@ class TTSProvider(TTSProviderBase):
         check_model_key("TTS", self.api_key)
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         headers = {
             "Authorization": f"Bearer {self.api_key}",
-            "Content-Type": "application/json"
+            "Content-Type": "application/json",
         }
         data = {
             "model": self.model,
             "input": text,
             "voice": self.voice,
             "response_format": "wav",
-            "speed": self.speed
+            "speed": self.speed,
         }
         response = requests.post(self.api_url, json=data, headers=headers)
         if response.status_code == 200:
             with open(output_file, "wb") as audio_file:
                 audio_file.write(response.content)
         else:
-            raise Exception(f"OpenAI TTS请求失败: {response.status_code} - {response.text}")
+            raise Exception(
+                f"OpenAI TTS请求失败: {response.status_code} - {response.text}"
+            )

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

@@ -0,0 +1,9 @@
+from abc import ABC, abstractmethod
+from typing import Optional
+
+
+class VADProviderBase(ABC):
+    @abstractmethod
+    def is_vad(self, conn, data) -> bool:
+        """检测音频数据中的语音活动"""
+        pass

main/xiaozhi-server/core/providers/vad/silero.py

@@ -0,0 +1,63 @@
+import time
+import numpy as np
+import torch
+import opuslib_next
+from config.logger import setup_logging
+from core.providers.vad.base import VADProviderBase
+
+TAG = __name__
+logger = setup_logging()
+
+
+class VADProvider(VADProviderBase):
+    def __init__(self, config):
+        logger.bind(tag=TAG).info("SileroVAD", config)
+        self.model, self.utils = torch.hub.load(
+            repo_or_dir=config["model_dir"],
+            source="local",
+            model="silero_vad",
+            force_reload=False,
+        )
+        (get_speech_timestamps, _, _, _, _) = self.utils
+
+        self.decoder = opuslib_next.Decoder(16000, 1)
+        self.vad_threshold = config.get("threshold")
+        self.silence_threshold_ms = config.get("min_silence_duration_ms")
+
+    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
+
+            # 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:
+                # 提取前512个采样点（1024字节）
+                chunk = conn.client_audio_buffer[: 512 * 2]
+                conn.client_audio_buffer = conn.client_audio_buffer[512 * 2 :]
+
+                # 转换为模型需要的张量格式
+                audio_int16 = np.frombuffer(chunk, dtype=np.int16)
+                audio_float32 = audio_int16.astype(np.float32) / 32768.0
+                audio_tensor = torch.from_numpy(audio_float32)
+
+                # 检测语音活动
+                speech_prob = self.model(audio_tensor, 16000).item()
+                client_have_voice = speech_prob >= self.vad_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查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:
+                    stop_duration = (
+                        time.time() * 1000 - conn.client_have_voice_last_time
+                    )
+                    if stop_duration >= self.silence_threshold_ms:
+                        conn.client_voice_stop = True
+                if client_have_voice:
+                    conn.client_have_voice = True
+                    conn.client_have_voice_last_time = time.time() * 1000
+
+            return client_have_voice
+        except opuslib_next.OpusError as e:
+            logger.bind(tag=TAG).info(f"解码错误: {e}")
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"Error processing audio packet: {e}")

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

@@ -1,97 +0,0 @@
-import random
-import threading
-import time
-from typing import Set
-
-class AuthCodeGenerator:
-    _instance = None
-    _instance_lock = threading.Lock()
-    
-    def __new__(cls):
-        if not cls._instance:
-            with cls._instance_lock:
-                if not cls._instance:
-                    cls._instance = super(AuthCodeGenerator, cls).__new__(cls)
-                    # 初始化随机种子
-                    random.seed(time.time())
-        return cls._instance
-
-    def __init__(self):
-        # 确保 __init__ 只被调用一次
-        if not hasattr(self, '_initialized'):
-            self._used_codes: Set[str] = set()
-            self._code_timestamps = {}
-            self._lock = threading.Lock()
-            self._code_timeout = 3 * 24 * 60 * 60
-            self._initialized = True
-    
-    @classmethod
-    def get_instance(cls):
-        """获取AuthCodeGenerator的单例实例"""
-        return cls()
-
-    def generate_code(self) -> str:
-        """
-        生成6位数字认证码，确保不重复
-        返回: 6位数字字符串
-        """
-        with self._lock:
-            self._clean_expired_codes()  # 清理过期code
-            while True:
-                # 使用时间戳和已用码数量作为种子，确保每次生成不同的随机数
-                seed = int(time.time() * 1000) + len(self._used_codes)
-                random.seed(seed)
-                
-                # 生成6位随机数字
-                code = ''.join(str(random.randint(0, 9)) for _ in range(6))
-                
-                # 检查是否已存在
-                if code not in self._used_codes:
-                    self._used_codes.add(code)
-                    self._code_timestamps[code] = time.time()
-                    return code
-    
-    def remove_code(self, code: str) -> bool:
-        """
-        删除已使用的认证码
-        参数:
-            code: 要删除的认证码
-        返回:
-            bool: 删除成功返回True，码不存在返回False
-        """
-        print('remove_code', code)
-        with self._lock:
-            if code in self._used_codes:
-                self._used_codes.remove(code)
-                if code in self._code_timestamps:
-                    del self._code_timestamps[code]
-                return True
-            return False
-    
-    def is_code_used(self, code: str) -> bool:
-        """
-        检查认证码是否已被使用
-        参数:
-            code: 要检查的认证码
-        返回:
-            bool: 如果码存在返回True，否则返回False
-        """
-        with self._lock:
-            return code in self._used_codes
-    
-    def clear_codes(self):
-        """清空所有已使用的认证码"""
-        with self._lock:
-            self._used_codes.clear()
-            self._code_timestamps.clear()
-    
-    def _clean_expired_codes(self):
-        """清理过期的认证码"""
-        current_time = time.time()
-        expired_codes = [
-            code for code, timestamp in self._code_timestamps.items()
-            if (current_time - timestamp) > self._code_timeout
-        ]
-        for code in expired_codes:
-            self._used_codes.remove(code)
-            del self._code_timestamps[code]

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

@@ -1,39 +0,0 @@
-import asyncio
-from typing import Dict
-from config.logger import setup_logging
-
-TAG = __name__
-logger = setup_logging()
-
-class FileLockManager:
-    _instance = None
-    _locks: Dict[str, asyncio.Lock] = {}
-
-    def __new__(cls):
-        if cls._instance is None:
-            cls._instance = super(FileLockManager, cls).__new__(cls)
-        return cls._instance
-
-    @classmethod
-    def get_lock(cls, file_path: str) -> asyncio.Lock:
-        """获取指定文件的锁"""
-        if file_path not in cls._locks:
-            cls._locks[file_path] = asyncio.Lock()
-        return cls._locks[file_path]
-
-    @classmethod
-    async def acquire_lock(cls, file_path: str):
-        """获取锁"""
-        lock = cls.get_lock(file_path)
-        await lock.acquire()
-        logger.bind(tag=TAG).debug(f"Acquired lock for {file_path}")
-
-    @classmethod
-    def release_lock(cls, file_path: str):
-        """释放锁"""
-        if file_path in cls._locks:
-            try:
-                cls._locks[file_path].release()
-                logger.bind(tag=TAG).debug(f"Released lock for {file_path}")
-            except RuntimeError as e:
-                logger.bind(tag=TAG).warning(f"Failed to release lock for {file_path}: {e}")

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

@@ -2,16 +2,17 @@ import os
 import sys
 import importlib
 from config.logger import setup_logging
-from core.utils.util import read_config, get_project_dir
 
 logger = setup_logging()
 
+
 def create_instance(class_name, *args, **kwargs):
-    if os.path.exists(os.path.join('core', 'providers', 'memory', class_name, f'{class_name}.py')):
-        lib_name = f'core.providers.memory.{class_name}.{class_name}'
+    if os.path.exists(
+        os.path.join("core", "providers", "memory", class_name, f"{class_name}.py")
+    ):
+        lib_name = f"core.providers.memory.{class_name}.{class_name}"
         if lib_name not in sys.modules:
-            sys.modules[lib_name] = importlib.import_module(f'{lib_name}')
+            sys.modules[lib_name] = importlib.import_module(f"{lib_name}")
         return sys.modules[lib_name].MemoryProvider(*args, **kwargs)
 
     raise ValueError(f"不支持的记忆服务类型: {class_name}")
-

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

@@ -1,19 +1,12 @@
-import os
 import json
-import yaml
 import socket
 import subprocess
-import logging
 import re
 import requests
+from typing import Dict, Any
+from core.utils import tts, llm, intent, memory, vad, asr
 
-
-def get_project_dir():
-    """获取项目根目录"""
-    return (
-        os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-        + "/"
-    )
+TAG = __name__
 
 
 def get_local_ip():
@@ -72,7 +65,7 @@ def is_private_ip(ip_addr):
         return False  # IP address format error or insufficient segments
 
 
-def get_ip_info(ip_addr):
+def get_ip_info(ip_addr, logger):
     try:
         if is_private_ip(ip_addr):
             ip_addr = ""
@@ -81,16 +74,10 @@ def get_ip_info(ip_addr):
         ip_info = {"city": resp.get("city")}
         return ip_info
     except Exception as e:
-        logging.error(f"Error getting client ip info: {e}")
+        logger.bind(tag=TAG).error(f"Error getting client ip info: {e}")
         return {}
 
 
-def read_config(config_path):
-    with open(config_path, "r", encoding="utf-8") as file:
-        config = yaml.safe_load(file)
-    return config
-
-
 def write_json_file(file_path, data):
     """将数据写入 JSON 文件"""
     with open(file_path, "w", encoding="utf-8") as file:
@@ -169,10 +156,8 @@ def remove_punctuation_and_length(text):
 
 def check_model_key(modelType, modelKey):
     if "你" in modelKey:
-        logging.error(
-            "你还没配置"
-            + modelType
-            + "的密钥，请在配置文件中配置密钥，否则无法正常工作"
+        raise ValueError(
+            "你还没配置" + modelType + "的密钥，请检查一下所使用的LLM是否配置了密钥"
         )
         return False
     return True
@@ -212,3 +197,105 @@ def extract_json_from_string(input_string):
     if match:
         return match.group(1)  # 返回提取的 JSON 字符串
     return None
+
+
+def initialize_modules(
+    logger,
+    config: Dict[str, Any],
+    init_vad=False,
+    init_asr=False,
+    init_llm=False,
+    init_tts=False,
+    init_memory=False,
+    init_intent=False,
+) -> Dict[str, Any]:
+    """
+    初始化所有模块组件
+
+    Args:
+        config: 配置字典
+
+    Returns:
+        Dict[str, Any]: 包含所有初始化后的模块的字典
+    """
+    modules = {}
+
+    # 初始化TTS模块
+    if init_tts:
+        tts_type = (
+            config["selected_module"]["TTS"]
+            if "type" not in config["TTS"][config["selected_module"]["TTS"]]
+            else config["TTS"][config["selected_module"]["TTS"]]["type"]
+        )
+        modules["tts"] = tts.create_instance(
+            tts_type,
+            config["TTS"][config["selected_module"]["TTS"]],
+            config["delete_audio"],
+        )
+        logger.bind(tag=TAG).info(f"初始化组件: tts成功")
+
+    # 初始化LLM模块
+    if init_llm:
+        llm_type = (
+            config["selected_module"]["LLM"]
+            if "type" not in config["LLM"][config["selected_module"]["LLM"]]
+            else config["LLM"][config["selected_module"]["LLM"]]["type"]
+        )
+        modules["llm"] = llm.create_instance(
+            llm_type,
+            config["LLM"][config["selected_module"]["LLM"]],
+        )
+        logger.bind(tag=TAG).info(f"初始化组件: llm成功")
+
+    # 初始化Intent模块
+    if init_intent:
+        intent_type = (
+            config["selected_module"]["Intent"]
+            if "type" not in config["Intent"][config["selected_module"]["Intent"]]
+            else config["Intent"][config["selected_module"]["Intent"]]["type"]
+        )
+        modules["intent"] = intent.create_instance(
+            intent_type,
+            config["Intent"][config["selected_module"]["Intent"]],
+        )
+        logger.bind(tag=TAG).info(f"初始化组件: intent成功")
+    # 初始化Memory模块
+    if init_memory:
+        memory_type = (
+            config["selected_module"]["Memory"]
+            if "type" not in config["Memory"][config["selected_module"]["Memory"]]
+            else config["Memory"][config["selected_module"]["Memory"]]["type"]
+        )
+        modules["memory"] = memory.create_instance(
+            memory_type,
+            config["Memory"][config["selected_module"]["Memory"]],
+        )
+        logger.bind(tag=TAG).info(f"初始化组件: memory成功")
+
+    # 初始化VAD模块
+    if init_vad:
+        vad_type = (
+            config["selected_module"]["VAD"]
+            if "type" not in config["VAD"][config["selected_module"]["VAD"]]
+            else config["VAD"][config["selected_module"]["VAD"]]["type"]
+        )
+        modules["vad"] = vad.create_instance(
+            vad_type,
+            config["VAD"][config["selected_module"]["VAD"]],
+        )
+        logger.bind(tag=TAG).info(f"初始化组件: vad成功")
+    # 初始化ASR模块
+    if init_asr:
+        asr_type = (
+            config["selected_module"]["ASR"]
+            if "type" not in config["ASR"][config["selected_module"]["ASR"]]
+            else config["ASR"][config["selected_module"]["ASR"]]["type"]
+        )
+        modules["asr"] = asr.create_instance(
+            asr_type,
+            config["ASR"][config["selected_module"]["ASR"]],
+            config["delete_audio"],
+        )
+        logger.bind(tag=TAG).info(f"初始化组件: asr成功")
+
+    return modules

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

@@ -1,77 +1,19 @@
-from abc import ABC, abstractmethod
+import importlib
+import os
+import sys
+from core.providers.vad.base import VADProviderBase
 from config.logger import setup_logging
-import opuslib_next
-import time
-import numpy as np
-import torch
 
 TAG = __name__
 logger = setup_logging()
 
-class VAD(ABC):
-    @abstractmethod
-    def is_vad(self, conn, data):
-        """检测音频数据中的语音活动"""
-        pass
 
+def create_instance(class_name: str, *args, **kwargs) -> VADProviderBase:
+    """工厂方法创建VAD实例"""
+    if os.path.exists(os.path.join("core", "providers", "vad", f"{class_name}.py")):
+        lib_name = f"core.providers.vad.{class_name}"
+        if lib_name not in sys.modules:
+            sys.modules[lib_name] = importlib.import_module(f"{lib_name}")
+        return sys.modules[lib_name].VADProvider(*args, **kwargs)
 
-class SileroVAD(VAD):
-    def __init__(self, config):
-        logger.bind(tag=TAG).info("SileroVAD", config)
-        self.model, self.utils = torch.hub.load(repo_or_dir=config["model_dir"],
-                                                source='local',
-                                                model='silero_vad',
-                                                force_reload=False)
-        (get_speech_timestamps, _, _, _, _) = self.utils
-
-        self.decoder = opuslib_next.Decoder(16000, 1)
-        self.vad_threshold = config.get("threshold")
-        self.silence_threshold_ms = config.get("min_silence_duration_ms")
-
-    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
-
-            # 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:
-                # 提取前512个采样点（1024字节）
-                chunk = conn.client_audio_buffer[:512 * 2]
-                conn.client_audio_buffer = conn.client_audio_buffer[512 * 2:]
-
-                # 转换为模型需要的张量格式
-                audio_int16 = np.frombuffer(chunk, dtype=np.int16)
-                audio_float32 = audio_int16.astype(np.float32) / 32768.0
-                audio_tensor = torch.from_numpy(audio_float32)
-
-                # 检测语音活动
-                speech_prob = self.model(audio_tensor, 16000).item()
-                client_have_voice = speech_prob >= self.vad_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查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:
-                    stop_duration = time.time() * 1000 - conn.client_have_voice_last_time
-                    if stop_duration >= self.silence_threshold_ms:
-                        conn.client_voice_stop = True
-                if client_have_voice:
-                    conn.client_have_voice = True
-                    conn.client_have_voice_last_time = time.time() * 1000
-
-            return client_have_voice
-        except opuslib_next.OpusError as e:
-            logger.bind(tag=TAG).info(f"解码错误: {e}")
-        except Exception as e:
-            logger.bind(tag=TAG).error(f"Error processing audio packet: {e}")
-
-
-def create_instance(class_name, *args, **kwargs) -> VAD:
-    # 获取类对象
-    cls_map = {
-        "SileroVAD": SileroVAD,
-        # 可扩展其他SileroVAD实现
-    }
-
-    if cls := cls_map.get(class_name):
-        return cls(*args, **kwargs)
-    raise ValueError(f"不支持的SileroVAD类型: {class_name}")
+    raise ValueError(f"不支持的VAD类型: {class_name}，请检查该配置的type是否设置正确")

main/xiaozhi-server/core/websocket_server.py

@@ -2,8 +2,7 @@ import asyncio
 import websockets
 from config.logger import setup_logging
 from core.connection import ConnectionHandler
-from core.utils.util import get_local_ip
-from core.utils import asr, vad, llm, tts, memory, intent
+from core.utils.util import get_local_ip, initialize_modules
 
 TAG = __name__
 
@@ -12,74 +11,16 @@ class WebSocketServer:
     def __init__(self, config: dict):
         self.config = config
         self.logger = setup_logging()
-        self._vad, self._asr, self._llm, self._tts, self._memory, self.intent = (
-            self._create_processing_instances()
-        )
-        self.active_connections = set()  # 添加全局连接记录
-
-    def _create_processing_instances(self):
-        memory_cls_name = self.config["selected_module"].get(
-            "Memory", "nomem"
-        )  # 默认使用nomem
-        has_memory_cfg = (
-            self.config.get("Memory") and memory_cls_name in self.config["Memory"]
-        )
-        memory_cfg = self.config["Memory"][memory_cls_name] if has_memory_cfg else {}
-
-        """创建处理模块实例"""
-        return (
-            vad.create_instance(
-                self.config["selected_module"]["VAD"],
-                self.config["VAD"][self.config["selected_module"]["VAD"]],
-            ),
-            asr.create_instance(
-                (
-                    self.config["selected_module"]["ASR"]
-                    if not "type"
-                    in self.config["ASR"][self.config["selected_module"]["ASR"]]
-                    else self.config["ASR"][self.config["selected_module"]["ASR"]][
-                        "type"
-                    ]
-                ),
-                self.config["ASR"][self.config["selected_module"]["ASR"]],
-                self.config["delete_audio"],
-            ),
-            llm.create_instance(
-                (
-                    self.config["selected_module"]["LLM"]
-                    if not "type"
-                    in self.config["LLM"][self.config["selected_module"]["LLM"]]
-                    else self.config["LLM"][self.config["selected_module"]["LLM"]][
-                        "type"
-                    ]
-                ),
-                self.config["LLM"][self.config["selected_module"]["LLM"]],
-            ),
-            tts.create_instance(
-                (
-                    self.config["selected_module"]["TTS"]
-                    if not "type"
-                    in self.config["TTS"][self.config["selected_module"]["TTS"]]
-                    else self.config["TTS"][self.config["selected_module"]["TTS"]][
-                        "type"
-                    ]
-                ),
-                self.config["TTS"][self.config["selected_module"]["TTS"]],
-                self.config["delete_audio"],
-            ),
-            memory.create_instance(memory_cls_name, memory_cfg),
-            intent.create_instance(
-                (
-                    self.config["selected_module"]["Intent"]
-                    if not "type"
-                    in self.config["Intent"][self.config["selected_module"]["Intent"]]
-                    else self.config["Intent"][
-                        self.config["selected_module"]["Intent"]
-                    ]["type"]
-                ),
-                self.config["Intent"][self.config["selected_module"]["Intent"]],
-            ),
+        modules = initialize_modules(
+            self.logger, self.config, True, True, True, True, True, True
         )
+        self._vad = modules["vad"]
+        self._asr = modules["asr"]
+        self._tts = modules["tts"]
+        self._llm = modules["llm"]
+        self._intent = modules["intent"]
+        self._memory = modules["memory"]
+        self.active_connections = set()
 
     async def start(self):
         server_config = self.config["server"]
@@ -111,7 +52,7 @@ class WebSocketServer:
             self._llm,
             self._tts,
             self._memory,
-            self.intent,
+            self._intent,
         )
         self.active_connections.add(handler)
         try: