Merge branch 'main' into feature/add-fun-asr-auth

main/manager-api/src/main/java/xiaozhi/modules/config/service/impl/ConfigServiceImpl.java

@@ -257,7 +257,8 @@ public class ConfigServiceImpl implements ConfigService {
                         if (intentLLMModelId != null && intentLLMModelId.equals(llmModelId)) {
                             intentLLMModelId = null;
                         }
-                    } else if ("function_call".equals(map.get("type"))) {
+                    }
+                    if (map.get("functions") != null) {
                         String functionStr = (String) map.get("functions");
                         if (StringUtils.isNotBlank(functionStr)) {
                             String[] functions = functionStr.split("\\;");

main/xiaozhi-server/app.py

@@ -7,6 +7,7 @@ from core.ota_server import SimpleOtaServer
 from core.utils.util import check_ffmpeg_installed
 from config.logger import setup_logging
 from core.utils.util import get_local_ip
+from aioconsole import ainput
 
 TAG = __name__
 logger = setup_logging()
@@ -34,10 +35,19 @@ async def wait_for_exit() -> None:
             pass
 
 
+async def monitor_stdin():
+    """监控标准输入，消费回车键"""
+    while True:
+        await ainput()  # 异步等待输入，消费回车
+
+
 async def main():
     check_ffmpeg_installed()
     config = load_config()
 
+    # 添加 stdin 监控任务
+    stdin_task = asyncio.create_task(monitor_stdin())
+
     # 启动 WebSocket 服务器
     ws_server = WebSocketServer(config)
     ws_task = asyncio.create_task(ws_server.start())
@@ -78,19 +88,22 @@ async def main():
     )
 
     try:
-        await wait_for_exit()  # 监听退出信号
+        await wait_for_exit()  # 阻塞直到收到退出信号
     except asyncio.CancelledError:
         print("任务被取消，清理资源中...")
     finally:
+        # 取消所有任务（关键修复点）
+        stdin_task.cancel()
         ws_task.cancel()
         if ota_task:
             ota_task.cancel()
-        try:
-            await ws_task
-            if ota_task:
-                await ota_task
-        except asyncio.CancelledError:
-            pass
+
+        # 等待任务终止（必须加超时）
+        await asyncio.wait(
+            [stdin_task, ws_task, ota_task] if ota_task else [stdin_task, ws_task],
+            timeout=3.0,
+            return_when=asyncio.ALL_COMPLETED
+        )
         print("服务器已关闭，程序退出。")
 
 

main/xiaozhi-server/config.yaml

@@ -389,6 +389,12 @@ LLM:
     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
+    base_url: http://homeassistant.local:8123
+    agent_id: conversation.chatgpt
+    api_key: 你的home assistant api访问令牌
   FastgptLLM:
     # 定义LLM API类型
     type: fastgpt

main/xiaozhi-server/core/connection.py

@@ -1,6 +1,8 @@
 import os
 import copy
 import json
+import subprocess
+import sys
 import uuid
 import time
 import queue
@@ -241,6 +243,44 @@ class ConnectionHandler:
         elif isinstance(message, bytes):
             await handleAudioMessage(self, message)
 
+    async def handle_restart(self, message):
+        """处理服务器重启请求"""
+        try:
+
+            self.logger.bind(tag=TAG).info("收到服务器重启指令，准备执行...")
+
+            # 发送确认响应
+            await self.websocket.send(json.dumps({
+                "type": "server_response",
+                "status": "success",
+                "message": "服务器重启中..."
+            }))
+
+            # 异步执行重启操作
+            def restart_server():
+                """实际执行重启的方法"""
+                time.sleep(1)
+                self.logger.bind(tag=TAG).info("执行服务器重启...")
+                subprocess.Popen(
+                    [sys.executable, "app.py"],
+                    stdin=sys.stdin,
+                    stdout=sys.stdout,
+                    stderr=sys.stderr,
+                    start_new_session=True
+                )
+                os._exit(0)
+
+            # 使用线程执行重启避免阻塞事件循环
+            threading.Thread(target=restart_server, daemon=True).start()
+
+        except Exception as e:
+            self.logger.bind(tag=TAG).error(f"重启失败: {str(e)}")
+            await self.websocket.send(json.dumps({
+                "type": "server_response",
+                "status": "error",
+                "message": f"Restart failed: {str(e)}"
+            }))
+
     def _initialize_components(self):
         """初始化组件"""
         if self.config.get("prompt") is not None:

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

@@ -16,7 +16,7 @@ async def handleAudioMessage(conn, audio):
     if not conn.asr_server_receive:
         conn.logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
         return
-    if conn.client_listen_mode == "auto":
+    if conn.client_listen_mode == "auto" or conn.client_listen_mode == "realtime":
         have_voice = conn.vad.is_vad(conn, audio)
     else:
         have_voice = conn.client_have_voice

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

@@ -136,5 +136,8 @@ async def handleTextMessage(conn, message):
                             }
                         )
                     )
+            # 重启服务器
+            elif msg_json["action"] == "restart":
+                await conn.handle_restart(msg_json)
     except json.JSONDecodeError:
         await conn.websocket.send(message)

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

@@ -0,0 +1,72 @@
+import requests
+from requests.exceptions import RequestException
+from config.logger import setup_logging
+from core.providers.llm.base import LLMProviderBase
+
+TAG = __name__
+logger = setup_logging()
+
+
+class LLMProvider(LLMProviderBase):
+    def __init__(self, config):
+        self.agent_id = config.get("agent_id")  # 对应 agent_id
+        self.api_key = config.get("api_key")
+        self.base_url = config.get("base_url", config.get("url"))  # 默认使用 base_url
+        self.api_url = f"{self.base_url}/api/conversation/process"  # 拼接完整的 API URL
+
+    def response(self, session_id, dialogue):
+        try:
+            # home assistant语音助手自带意图，无需使用xiaozhi ai自带的，只需要把用户说的话传递给home assistant即可
+
+            # 提取最后一个 role 为 'user' 的 content
+            input_text = None
+            if isinstance(dialogue, list):  # 确保 dialogue 是一个列表
+                # 逆序遍历，找到最后一个 role 为 'user' 的消息
+                for message in reversed(dialogue):
+                    if message.get("role") == "user":  # 找到 role 为 'user' 的消息
+                        input_text = message.get("content", "")
+                        break  # 找到后立即退出循环
+
+            # 构造请求数据
+            payload = {
+                "text": input_text,
+                "agent_id": self.agent_id,
+                "conversation_id": session_id,  # 使用 session_id 作为 conversation_id
+            }
+            # 设置请求头
+            headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Content-Type": "application/json",
+            }
+
+            # 发起 POST 请求
+            response = requests.post(self.api_url, json=payload, headers=headers)
+
+            # 检查请求是否成功
+            response.raise_for_status()
+
+            # 解析返回数据
+            data = response.json()
+            speech = (
+                data.get("response", {})
+                .get("speech", {})
+                .get("plain", {})
+                .get("speech", "")
+            )
+
+            # 返回生成的内容
+            if speech:
+                yield speech
+            else:
+                logger.bind(tag=TAG).warning("API 返回数据中没有 speech 内容")
+
+        except RequestException as e:
+            logger.bind(tag=TAG).error(f"HTTP 请求错误: {e}")
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"生成响应时出错: {e}")
+
+    def response_with_functions(self, session_id, dialogue, functions=None):
+        logger.bind(tag=TAG).info(
+            f"homeassistant不支持（function call），建议使用意图识别使用:nointent"
+        )
+        return self.response(session_id, dialogue)

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

@@ -38,9 +38,13 @@ class TTSProvider(TTSProviderBase):
             "Authorization": f"Bearer {self.access_token}",
             "Content-Type": "application/json",
         }
-        response = requests.request(
-            "POST", self.api_url, json=request_json, headers=headers
-        )
-        data = response.content
-        file_to_save = open(output_file, "wb")
-        file_to_save.write(data)
+
+        try:
+            response = requests.request(
+                "POST", self.api_url, json=request_json, headers=headers
+            )
+            data = response.content
+            file_to_save = open(output_file, "wb")
+            file_to_save.write(data)
+        except Exception as e:
+            raise Exception(f"{__name__} error: {e}")

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

@@ -32,4 +32,6 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as file:
                 file.write(resp.content)
         else:
-            logger.bind(tag=TAG).error(f"Custom TTS请求失败: {resp.status_code} - {resp.text}")
+            error_msg = f"Custom TTS请求失败: {resp.status_code} - {resp.text}"
+            logger.bind(tag=TAG).error(error_msg)
+            raise Exception(error_msg)  # 抛出异常，让调用方捕获

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

@@ -20,14 +20,18 @@ class TTSProvider(TTSProviderBase):
         )
 
     async def text_to_speak(self, text, output_file):
-        communicate = edge_tts.Communicate(text, voice=self.voice)
-        # 确保目录存在并创建空文件
-        os.makedirs(os.path.dirname(output_file), exist_ok=True)
-        with open(output_file, "wb") as f:
-            pass
+        try:
+            communicate = edge_tts.Communicate(text, voice=self.voice)
+            # 确保目录存在并创建空文件
+            os.makedirs(os.path.dirname(output_file), exist_ok=True)
+            with open(output_file, "wb") as f:
+                pass
 
-        # 流式写入音频数据
-        with open(output_file, "ab") as f:  # 改为追加模式避免覆盖
-            async for chunk in communicate.stream():
-                if chunk["type"] == "audio":  # 只处理音频数据块
-                    f.write(chunk["data"])
+            # 流式写入音频数据
+            with open(output_file, "ab") as f:  # 改为追加模式避免覆盖
+                async for chunk in communicate.stream():
+                    if chunk["type"] == "audio":  # 只处理音频数据块
+                        f.write(chunk["data"])
+        except Exception as e:
+            error_msg = f"Edge TTS请求失败: {e}"
+            raise Exception(error_msg)  # 抛出异常，让调用方捕获

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

@@ -177,5 +177,7 @@ class TTSProvider(TTSProviderBase):
                 audio_file.write(audio_content)
 
         else:
-            print(f"Request failed with status code {response.status_code}")
+            error_msg = f"Request failed with status code {response.status_code}"
+            print(error_msg)
             print(response.json())
+            raise Exception(error_msg)

main/xiaozhi-server/core/providers/tts/gpt_sovits_v2.py

@@ -105,6 +105,6 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as file:
                 file.write(resp.content)
         else:
-            logger.bind(tag=TAG).error(
-                f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}"
-            )
+            error_msg = f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}"
+            logger.bind(tag=TAG).error(error_msg)
+            raise Exception(error_msg)

main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py

@@ -64,6 +64,7 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as file:
                 file.write(resp.content)
         else:
-            logger.bind(tag=TAG).error(
-                f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}"
-            )
+            error_msg = f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}"
+            logger.bind(tag=TAG).error(error_msg)
+            raise Exception(error_msg)
+

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

@@ -39,9 +39,12 @@ class TTSProvider(TTSProviderBase):
             "Authorization": f"Bearer {self.access_token}",
             "Content-Type": "application/json",
         }
-        response = requests.request(
-            "POST", self.api_url, json=request_json, headers=headers
-        )
-        data = response.content
-        file_to_save = open(output_file, "wb")
-        file_to_save.write(data)
+        try:
+            response = requests.request(
+                "POST", self.api_url, json=request_json, headers=headers
+            )
+            data = response.content
+            file_to_save = open(output_file, "wb")
+            file_to_save.write(data)
+        except Exception as e:
+            raise Exception(f"{__name__} error: {e}")

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

@@ -58,8 +58,8 @@ class TTSProvider(TTSProviderBase):
 
         resp = requests.request("POST", url, data=payload)
         if resp.status_code != 200:
-            logger.bind(tag=TAG).error(f"TTS请求失败: {resp.text}")
-            return None
+            logger.bind(tag=TAG).error(f"TTSON 请求失败: {resp.text}")
+            raise Exception(f"{__name__}: TTS请求失败")
         resp_json = resp.json()
         try:
             result = (
@@ -71,13 +71,15 @@ class TTSProvider(TTSProviderBase):
                 + "&voice_audio_path="
                 + resp_json["voice_path"]
             )
+
+            audio_content = requests.get(result)
+            with open(output_file, "wb") as f:
+                f.write(audio_content.content)
+                return True
+            voice_path = resp_json.get("voice_path")
+            des_path = output_file
+            shutil.move(voice_path, des_path)
+
         except Exception as e:
             print("error:", e)
-
-        audio_content = requests.get(result)
-        with open(output_file, "wb") as f:
-            f.write(audio_content.content)
-            return True
-        voice_path = resp_json.get("voice_path")
-        des_path = output_file
-        shutil.move(voice_path, des_path)
+            raise Exception(f"{__name__}: TTS请求失败")

main/xiaozhi-server/mcp_server_settings.json

@@ -7,6 +7,15 @@
     "当前支持stdio/sse两种模式。"
   ],
   "mcpServers": {
+    "Home Assistant": {
+      "command": "mcp-proxy",
+      "args": [
+        "http://YOUR_HA_HOST/mcp_server/sse"
+      ],
+      "env": {
+        "API_ACCESS_TOKEN": "YOUR_API_ACCESS_TOKEN"
+      }
+    },
     "filesystem": {
       "command": "npx",
       "args": [

main/xiaozhi-server/requirements.txt

@@ -28,4 +28,5 @@ PySocks==1.7.1
 dashscope==1.23.1
 baidu-aip==4.16.13
 chardet==5.2.0
+aioconsole==0.8.1
 markitdown==0.1.1