Merge branch 'xinnan-tech:main' into main

main/xiaozhi-server/config.yaml

@@ -49,7 +49,7 @@ prompt: |
   你是一个叫小智/小志的台湾女孩，说话机车，声音好听，习惯简短表达，爱用网络梗。
   请注意，要像一个人一样说话，请不要回复表情符号、代码、和xml标签。
   现在我正在和你进行语音聊天，我们开始吧。
-  如果用户希望结束对话，请在最后说“拜拜”或“再见”。
+
 # 使用完声音文件后删除文件(Delete the sound file when you are done using it)
 delete_audio: true
 
@@ -57,6 +57,14 @@ delete_audio: true
 close_connection_no_voice_time: 120
 # TTS请求超时时间(秒)
 tts_timeout: 10
+# 开启唤醒词加速
+enable_wakeup_words_response_cache: true
+# 开场是否回复唤醒词
+enable_greeting: true
+# 说完话是否开启提示音
+enable_stop_tts_notify: false
+# 说完话是否开启提示音，音效地址
+stop_tts_notify_voice: "config/assets/tts_notify.mp3"
 
 CMD_exit:
   - "退出"
@@ -99,6 +107,12 @@ Intent:
       - change_role
       - get_weather
       - get_news
+      # play_music是服务器自带的音乐播放，hass_play_music是通过home assistant控制的独立外部程序音乐播放
+      # 如果用了hass_play_music，就不要开启play_music，两者只留一个
+      - play_music
+      #- hass_get_state
+      #- hass_set_state
+      #- hass_play_music
 
 # 插件的基础配置
 plugins:
@@ -115,6 +129,20 @@ plugins:
       society: "https://www.chinanews.com.cn/rss/society.xml"
       world: "https://www.chinanews.com.cn/rss/world.xml"
       finance: "https://www.chinanews.com.cn/rss/finance.xml"
+  home_assistant:
+    devices:
+      - 客厅,玩具灯,switch.cuco_cn_460494544_cp1_on_p_2_1
+      - 卧室,台灯,switch.iot_cn_831898993_socn1_on_p_2_1
+    base_url: http://homeassistant.local:8123
+    api_key: 你的home assistant api访问令牌
+  play_music:
+    music_dir: "./music"  # 音乐文件存放路径，将从该目录及子目录下搜索音乐文件
+    music_ext: # 音乐文件类型，p3格式效率最高
+      - ".mp3"
+      - ".wav"
+      - ".p3"
+    refresh_time: 300 # 刷新音乐列表的时间间隔，单位为秒
+
 
 Memory:
   mem0ai:
@@ -165,6 +193,18 @@ LLM:
     top_p: 1         
     top_k: 50        
     frequency_penalty: 0  # 频率惩罚
+  AliAppLLM:
+    # 定义LLM API类型
+    type: AliBL
+    base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
+    app_id: 你的app_id
+    # 可在这里找到你的 api_key https://bailian.console.aliyun.com/?apiKey=1#/api-key
+    api_key: 你的api_key
+    # 是否不使用本地prompt：true|false (默不用请在百练应用中设置prompt) 
+    is_no_prompt: true
+    # Ali_memory_id：false（不使用）|你的memory_id（请在百练应用中设置中获取）
+    # Tips！：Ali_memory未实现多用户存储记忆(记忆按id调用)
+    ali_memory_id: false
   DoubaoLLM:
     # 定义LLM API类型
     type: openai
@@ -229,12 +269,6 @@ 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
@@ -489,19 +523,15 @@ module_test:
     - "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_dir: "./music"  # 音乐文件存放路径，将从该目录及子目录下搜索音乐文件
-  music_ext: # 音乐文件类型，p3格式效率最高
-    - ".mp3"
-    - ".wav"
-    - ".p3"
-  refresh_time: 300 # 刷新音乐列表的时间间隔，单位为秒
-
-# 以下配置在小于等于0.0.9版本中的docker容器中可用
-# 0.0.9以后的新版本源码部署已经无法奏效
-manager:
-  enabled: false
-  ip: 0.0.0.0
-  port: 8002
-use_private_config: false
+# 唤醒词，用于识别唤醒词还是讲话内容
+wakeup_words:
+  - "你好小智"
+  - "你好小志"
+  - "小爱同学"
+  - "你好小鑫"
+  - "你好小新"
+  - "小美同学"
+  - "小龙小龙"
+  - "喵喵同学"
+  - "小滨小滨"
+  - "小冰小冰"

main/xiaozhi-server/core/connection.py

@@ -9,7 +9,7 @@ import traceback
 import threading
 import websockets
 from typing import Dict, Any
-import plugins_func.loadplugins
+from plugins_func.loadplugins import auto_import_modules
 from config.logger import setup_logging
 from core.utils.dialogue import Message, Dialogue
 from core.handle.textHandle import handleTextMessage
@@ -25,6 +25,8 @@ from core.utils.auth_code_gen import AuthCodeGenerator
 
 TAG = __name__
 
+auto_import_modules('plugins_func.functions')
+
 
 class TTSException(RuntimeError):
     pass
@@ -109,11 +111,15 @@ class ConnectionHandler:
 
             # 进行认证
             await self.auth.authenticate(self.headers)
-
             device_id = self.headers.get("device-id", None)
-            self.memory.init_memory(device_id, self.llm)
-            self.intent.set_llm(self.llm)
 
+            # 认证通过,继续处理
+            self.websocket = ws
+            self.session_id = str(uuid.uuid4())
+
+            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)
             self.logger.bind(tag=TAG).info(f"bUsePrivateConfig: {bUsePrivateConfig}, device_id: {device_id}")
@@ -141,17 +147,8 @@ class ConnectionHandler:
                     self.private_config = None
                     raise
 
-            # 认证通过,继续处理
-            self.websocket = ws
-            self.session_id = str(uuid.uuid4())
-
-            self.welcome_msg = self.config["xiaozhi"]
-            self.welcome_msg["session_id"] = self.session_id
-            await self.websocket.send(json.dumps(self.welcome_msg))
-
             # 异步初始化
-            await self.loop.run_in_executor(None, self._initialize_components)
-
+            self.executor.submit(self._initialize_components)
             # tts 消化线程
             tts_priority = threading.Thread(target=self._tts_priority_thread, daemon=True)
             tts_priority.start()
@@ -187,16 +184,26 @@ class ConnectionHandler:
             await handleAudioMessage(self, message)
 
     def _initialize_components(self):
+        """加载插件"""
+        self.func_handler = FunctionHandler(self)
+
+        """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.client_ip_info = get_ip_info(self.client_ip)
-        self.logger.bind(tag=TAG).info(f"Client ip info: {self.client_ip_info}")
-        self.prompt = self.prompt + f"\n我在:{self.client_ip_info}"
         self.dialogue.put(Message(role="system", content=self.prompt))
 
-        self.func_handler = FunctionHandler(self.config)
+        """加载记忆"""
+        device_id = self.headers.get("device-id", None)
+        self.memory.init_memory(device_id, self.llm)
+        self.intent.set_llm(self.llm)
+
+        """加载位置信息"""
+        self.client_ip_info = get_ip_info(self.client_ip)
+        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 change_system_prompt(self, prompt):
         self.prompt = prompt

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

@@ -1,16 +1,16 @@
-import asyncio
-from enum import Enum
-
 from config.logger import setup_logging
 import json
 from plugins_func.register import FunctionRegistry, ActionResponse, Action, ToolType
+from plugins_func.functions.hass_init import append_devices_to_prompt
+
 TAG = __name__
 logger = setup_logging()
 
 
 class FunctionHandler:
-    def __init__(self, config):
-        self.config = config
+    def __init__(self, conn):
+        self.conn = conn
+        self.config = conn.config
         self.function_registry = FunctionRegistry()
         self.register_nessary_functions()
         self.register_config_functions()
@@ -26,9 +26,10 @@ class FunctionHandler:
         func_names = ",".join(surport_plugins)
         for function_desc in self.functions_desc:
             if function_desc["function"]["name"] == "plugin_loader":
-                function_desc["function"]["description"] = function_desc["function"]["description"].replace("[plugins]", func_names)
+                function_desc["function"]["description"] = function_desc["function"]["description"].replace("[plugins]",
+                                                                                                            func_names)
                 break
-        
+
     def upload_functions_desc(self):
         self.functions_desc = self.function_registry.get_all_function_desc()
 
@@ -47,7 +48,6 @@ class FunctionHandler:
     def register_nessary_functions(self):
         """注册必要的函数"""
         self.function_registry.register_function("handle_exit_intent")
-        self.function_registry.register_function("play_music")
         self.function_registry.register_function("plugin_loader")
         self.function_registry.register_function("get_time")
         self.function_registry.register_function("raise_and_lower_the_volume")
@@ -57,6 +57,9 @@ class FunctionHandler:
         for func in self.config["Intent"]["function_call"].get("functions", []):
             self.function_registry.register_function(func)
 
+        """home assistant需要初始化提示词"""
+        append_devices_to_prompt(self.conn)
+
     def get_function(self, name):
         return self.function_registry.get_function(name)
 
@@ -81,4 +84,4 @@ class FunctionHandler:
         except Exception as e:
             logger.bind(tag=TAG).error(f"处理function call错误: {e}")
 
-        return None
+        return None

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

@@ -1,8 +1,72 @@
 import json
 from config.logger import setup_logging
+from core.handle.sendAudioHandle import send_stt_message
+from core.utils.util import remove_punctuation_and_length
+import shutil
+import asyncio
+import os
+import random
+import time
 
 logger = setup_logging()
 
+WAKEUP_CONFIG = {"dir": "config/assets/", "file_name": "wakeup_words", "create_time": time.time(), "refresh_time": 10,
+                 "words": ["很高兴见到你", "你好啊", "我们又见面了", "最近可好?", "很高兴再次和你谈话", "在干嘛"]}
+
 
 async def handleHelloMessage(conn):
     await conn.websocket.send(json.dumps(conn.welcome_msg))
+
+
+async def checkWakeupWords(conn, text):
+    enable_wakeup_words_response_cache = conn.config["enable_wakeup_words_response_cache"]
+    """是否开启唤醒词加速"""
+    if not enable_wakeup_words_response_cache:
+        return False
+    """检查是否是唤醒词"""
+    _, text = remove_punctuation_and_length(text)
+    if text in conn.config.get("wakeup_words"):
+        await send_stt_message(conn, text)
+        conn.tts_first_text_index = 0
+        conn.tts_last_text_index = 0
+        conn.llm_finish_task = True
+
+        file = getWakeupWordFile(WAKEUP_CONFIG["file_name"])
+        if file is None:
+            asyncio.create_task(wakeupWordsResponse(conn))
+            return False
+        opus_packets, duration = conn.tts.audio_to_opus_data(file)
+        conn.audio_play_queue.put((opus_packets, text, 0))
+        if time.time() - WAKEUP_CONFIG["create_time"] > WAKEUP_CONFIG["refresh_time"]:
+            asyncio.create_task(wakeupWordsResponse(conn))
+        return True
+    return False
+
+
+def getWakeupWordFile(file_name):
+    for file in os.listdir(WAKEUP_CONFIG["dir"]):
+        if "my_"+file_name in file:
+            return f"config/assets/{file}"
+
+    """查找config/assets/目录下名称为wakeup_words的文件"""
+    for file in os.listdir(WAKEUP_CONFIG["dir"]):
+        if file_name in file:
+            return f"config/assets/{file}"
+    return None
+
+
+async def wakeupWordsResponse(conn):
+    """唤醒词响应"""
+    wakeup_word = random.choice(WAKEUP_CONFIG["words"])
+    result = conn.llm.response_no_stream(conn.config["prompt"], wakeup_word)
+    tts_file = await asyncio.to_thread(conn.tts.to_tts, result)
+    if tts_file is not None and os.path.exists(tts_file):
+        file_type = os.path.splitext(tts_file)[1]
+        if file_type:
+            file_type = file_type.lstrip('.')
+        old_file = getWakeupWordFile("my_" +WAKEUP_CONFIG["file_name"])
+        if old_file is not None:
+            os.remove(old_file)
+        """将文件挪到"wakeup_words.mp3"""
+        shutil.move(tts_file, WAKEUP_CONFIG["dir"] + "my_" +WAKEUP_CONFIG["file_name"] + "." + file_type)
+        WAKEUP_CONFIG["create_time"] = time.time()

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

@@ -2,6 +2,7 @@ from config.logger import setup_logging
 import json
 import uuid
 from core.handle.sendAudioHandle import send_stt_message
+from core.handle.helloHandle import checkWakeupWords
 from core.utils.util import remove_punctuation_and_length
 
 TAG = __name__
@@ -12,6 +13,10 @@ async def handle_user_intent(conn, text):
     # 检查是否有明确的退出命令
     if await check_direct_exit(conn, text):
         return True
+    # 检查是否是唤醒词
+    if await checkWakeupWords(conn, text):
+        return True
+
     if conn.use_function_call_mode:
         # 使用支持function calling的聊天方法,不再进行意图分析
         return False
@@ -35,6 +40,7 @@ async def check_direct_exit(conn, text):
     return False
 
 
+
 async def analyze_intent_with_llm(conn, text):
     """使用LLM分析用户意图"""
     if not hasattr(conn, 'intent') or not conn.intent:

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

@@ -7,12 +7,26 @@ from core.utils.util import remove_punctuation_and_length, get_string_no_punctua
 TAG = __name__
 logger = setup_logging()
 
+
 async def sendAudioMessage(conn, audios, text, text_index=0):
     # 发送句子开始消息
     if text_index == conn.tts_first_text_index:
         logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
     await send_tts_message(conn, "sentence_start", text)
 
+    # 播放音频
+    await sendAudio(conn, audios)
+
+    await send_tts_message(conn, "sentence_end", text)
+
+    # 发送结束消息（如果是最后一个文本）
+    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
+        await send_tts_message(conn, 'stop', None)
+        if conn.close_after_chat:
+            await conn.close()
+
+# 播放音频
+async def sendAudio(conn, audios):
     # 流控参数优化
     frame_duration = 62  # 帧时长（毫秒），增加余量
     start_time = time.perf_counter()
@@ -46,13 +60,6 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
         # 动态调整下次延迟，补偿发送耗时
         play_position += frame_duration  # 更新播放位置
 
-    await send_tts_message(conn, "sentence_end", text)
-
-    # 发送结束消息（如果是最后一个文本）
-    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
-        await send_tts_message(conn, 'stop', None)
-        if conn.close_after_chat:
-            await conn.close()
 
 async def send_tts_message(conn, state, text=None):
     """发送 TTS 状态消息"""
@@ -64,10 +71,20 @@ async def send_tts_message(conn, state, text=None):
     if text is not None:
         message["text"] = text
 
-    await conn.websocket.send(json.dumps(message))
+    # TTS播放结束
     if state == "stop":
+        # 播放提示音
+        tts_notify = conn.config.get("enable_stop_tts_notify", False)
+        if tts_notify:
+            stop_tts_notify_voice = conn.config.get("stop_tts_notify_voice", "config/assets/tts_notify.mp3")
+            audios, duration = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
+            await sendAudio(conn, audios)
+        # 清除服务端讲话状态
         conn.clearSpeakStatus()
 
+    # 发送消息到客户端
+    await conn.websocket.send(json.dumps(message))
+
 
 async def send_stt_message(conn, text):
     """发送 STT 状态消息"""

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

@@ -2,7 +2,9 @@ from config.logger import setup_logging
 import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
+from core.utils.util import remove_punctuation_and_length
 from core.handle.receiveAudioHandle import startToChat, handleAudioMessage
+from core.handle.sendAudioHandle import send_stt_message, send_tts_message
 from core.handle.iotHandle import handleIotDescriptors, handleIotStatus
 
 TAG = __name__
@@ -38,7 +40,21 @@ async def handleTextMessage(conn, message):
                 conn.client_have_voice = False
                 conn.asr_audio.clear()
                 if "text" in msg_json:
-                    await startToChat(conn, msg_json["text"])
+                    text = msg_json["text"]
+                    _, text = remove_punctuation_and_length(text)
+
+                    # 识别是否是唤醒词
+                    is_wakeup_words = text in conn.config.get("wakeup_words")
+                    # 是否开启唤醒词回复
+                    enable_greeting = conn.config.get("enable_greeting", True)
+
+                    if is_wakeup_words and not enable_greeting:
+                        # 如果是唤醒词，且关闭了唤醒词回复，就不用回答
+                        await send_stt_message(conn, text)
+                        await send_tts_message(conn, "stop", None)
+                    else:
+                        # 否则需要LLM对文字内容进行答复
+                        await startToChat(conn, text)
         elif msg_json["type"] == "iot":
             if "descriptors" in msg_json:
                 await handleIotDescriptors(conn, msg_json["descriptors"])

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

@@ -0,0 +1,52 @@
+from config.logger import setup_logging
+from http import HTTPStatus
+from dashscope import Application
+from core.providers.llm.base import LLMProviderBase
+
+TAG = __name__
+logger = setup_logging()
+
+class LLMProvider(LLMProviderBase):
+    def __init__(self, config):
+        self.api_key = config["api_key"]
+        self.app_id = config["app_id"]
+        self.base_url = config.get("base_url")
+        self.is_No_prompt = config.get("is_no_prompt")
+        self.memory_id = config.get("ali_memory_id")
+
+    def response(self, session_id, dialogue):
+        try:
+            # 处理dialogue
+            if self.is_No_prompt:
+                dialogue.pop(0)
+                logger.bind(tag=TAG).debug(f"【阿里百练API服务】处理后的dialogue: {dialogue}")
+
+            # 构造调用参数
+            call_params = {
+                "api_key": self.api_key,
+                "app_id": self.app_id,
+                "session_id": session_id,
+                "messages": dialogue
+            }
+            if self.memory_id != False:
+                # 百练memory需要prompt参数
+                prompt = dialogue[-1].get("content")
+                call_params["memory_id"] = self.memory_id
+                call_params["prompt"] = prompt
+                logger.bind(tag=TAG).debug(f"【阿里百练API服务】处理后的prompt: {prompt}")
+
+            responses = Application.call(**call_params)
+            if responses.status_code != HTTPStatus.OK:
+                logger.bind(tag=TAG).error(
+                    f"code={responses.status_code}, "
+                    f"message={responses.message}, "
+                    f"请参考文档：https://help.aliyun.com/zh/model-studio/developer-reference/error-code"
+                )
+                yield "【阿里百练API服务响应异常】"
+            else:
+                logger.bind(tag=TAG).debug(f"【阿里百练API服务】构造参数: {call_params}")
+                yield responses.output.text
+
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"【阿里百练API服务】响应异常: {e}")
+            yield "【LLM服务响应异常】"

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

@@ -1,62 +0,0 @@
-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):
-        print(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}")

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

@@ -36,7 +36,7 @@ class TTSProviderBase(ABC):
 
             return tmp_file
         except Exception as e:
-            logger.bind(tag=TAG).info(f"Failed to generate TTS file: {e}")
+            logger.bind(tag=TAG).error(f"Failed to generate TTS file: {e}")
             return None
 
     @abstractmethod

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

@@ -35,6 +35,15 @@ class Dialogue:
             self.getMessages(m, dialogue)
         return dialogue
 
+    def update_system_message(self, new_content: str):
+        """更新或添加系统消息"""
+        # 查找第一个系统消息
+        system_msg = next((msg for msg in self.dialogue if msg.role == "system"), None)
+        if system_msg:
+            system_msg.content = new_content
+        else:
+            self.put(Message(role="system", content=new_content))
+
     def get_llm_dialogue_with_memory(self, memory_str: str = None) -> List[Dict[str, str]]:
         if memory_str is None or len(memory_str) == 0:
             return self.get_llm_dialogue()

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

@@ -73,9 +73,7 @@ def get_ip_info(ip_addr):
         resp = requests.get(url).json()
 
         ip_info = {
-            "city": resp.get("cityName"),
-            "region": resp.get("regionName"), 
-            "country": resp.get("countryName")
+            "city": resp.get("cityName")
         }
         return ip_info
     except Exception as e:

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

@@ -0,0 +1,56 @@
+from plugins_func.register import register_function, ToolType, ActionResponse, Action
+from plugins_func.functions.hass_init import initialize_hass_handler
+from config.logger import setup_logging
+import asyncio
+import requests
+
+TAG = __name__
+logger = setup_logging()
+
+hass_get_state_function_desc = {
+    "type": "function",
+    "function": {
+        "name": "hass_get_state",
+        "description": "获取homeassistant里设备的状态,包括灯光亮度,媒体播放器的音量,设备的暂停、继续操作",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "entity_id": {
+                    "type": "string",
+                    "description": "需要操作的设备id,homeassistant里的entity_id"
+                }
+            },
+            "required": ["entity_id"]
+        }
+    }
+}
+
+
+@register_function("hass_get_state", hass_get_state_function_desc, ToolType.SYSTEM_CTL)
+def hass_get_state(conn, entity_id=''):
+    try:
+
+        future = asyncio.run_coroutine_threadsafe(
+            handle_hass_get_state(conn, entity_id),
+            conn.loop
+        )
+        ha_response = future.result()
+        return ActionResponse(action=Action.REQLLM, result="执行成功", response=ha_response)
+    except Exception as e:
+        logger.bind(tag=TAG).error(f"处理设置属性意图错误: {e}")
+
+
+async def handle_hass_get_state(conn, entity_id):
+    HASS_CACHE = initialize_hass_handler(conn)
+    api_key = HASS_CACHE['api_key']
+    base_url = HASS_CACHE['base_url']
+    url = f"{base_url}/api/states/{entity_id}"
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json"
+    }
+    response = requests.get(url, headers=headers)
+    if response.status_code == 200:
+        return response.json()['state']
+    else:
+        return f"切换失败，错误码: {response.status_code}"

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

@@ -0,0 +1,35 @@
+from config.logger import setup_logging
+from core.utils.util import check_model_key
+
+TAG = __name__
+logger = setup_logging()
+
+HASS_CACHE = {}
+
+
+def append_devices_to_prompt(conn):
+    if conn.use_function_call_mode:
+        funcs = conn.config["Intent"]["function_call"].get("functions", [])
+        if "hass_get_state" in funcs or "hass_get_state" in funcs:
+            prompt = "下面是我家智能设备，可以通过homeassistant控制\n"
+            devices = conn.config["plugins"]["home_assistant"].get("devices", [])
+            if len(devices) == 0:
+                return
+            for device in devices:
+                prompt += device + "\n"
+            conn.prompt += prompt
+            # 更新提示词
+            conn.dialogue.update_system_message(conn.prompt)
+
+
+def initialize_hass_handler(conn):
+    global HASS_CACHE
+    if HASS_CACHE == {}:
+        if conn.use_function_call_mode:
+            funcs = conn.config["Intent"]["function_call"].get("functions", [])
+            if "hass_get_state" in funcs or "hass_get_state" in funcs:
+                HASS_CACHE['base_url'] = conn.config["plugins"]["home_assistant"].get("base_url")
+                HASS_CACHE['api_key'] = conn.config["plugins"]["home_assistant"].get("api_key")
+
+                check_model_key("home_assistant", HASS_CACHE['api_key'])
+    return HASS_CACHE

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

@@ -0,0 +1,64 @@
+from plugins_func.register import register_function, ToolType, ActionResponse, Action
+from plugins_func.functions.hass_init import initialize_hass_handler
+from config.logger import setup_logging
+import asyncio
+import requests
+
+TAG = __name__
+logger = setup_logging()
+
+hass_play_music_function_desc = {
+    "type": "function",
+    "function": {
+        "name": "hass_play_music",
+        "description": "用户想听音乐、有声书的时候使用，在房间的媒体播放器（media_player）里播放对应音频",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "media_content_id": {
+                    "type": "string",
+                    "description": "可以是音乐或有声书的专辑名称、歌曲名、演唱者,如果未指定就填random"
+                },
+                "entity_id": {
+                    "type": "string",
+                    "description": "需要操作的音箱的设备id,homeassistant里的entity_id,media_player开头"
+                }
+            },
+            "required": ["media_content_id", "entity_id"]
+        }
+    }
+}
+
+
+@register_function('hass_play_music', hass_play_music_function_desc, ToolType.SYSTEM_CTL)
+def hass_play_music(conn, entity_id='', media_content_id='random'):
+    try:
+        # 执行音乐播放命令
+        future = asyncio.run_coroutine_threadsafe(
+            handle_hass_play_music(conn, entity_id, media_content_id),
+            conn.loop
+        )
+        ha_response = future.result()
+        return ActionResponse(action=Action.RESPONSE, result="退出意图已处理", response=ha_response)
+    except Exception as e:
+        logger.bind(tag=TAG).error(f"处理音乐意图错误: {e}")
+
+
+async def handle_hass_play_music(conn, entity_id, media_content_id):
+    HASS_CACHE = initialize_hass_handler(conn)
+    api_key = HASS_CACHE['api_key']
+    base_url = HASS_CACHE['base_url']
+    url = f"{base_url}/api/services/music_assistant/play_media"
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json"
+    }
+    data = {
+        "entity_id": entity_id,
+        "media_id": media_content_id
+    }
+    response = requests.post(url, headers=headers, json=data)
+    if response.status_code == 200:
+        return f"正在播放{media_content_id}的音乐"
+    else:
+        return f"音乐播放失败，错误码: {response.status_code}"

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

@@ -0,0 +1,159 @@
+from plugins_func.register import register_function, ToolType, ActionResponse, Action
+from plugins_func.functions.hass_init import initialize_hass_handler
+from config.logger import setup_logging
+import asyncio
+import requests
+
+TAG = __name__
+logger = setup_logging()
+
+hass_set_state_function_desc = {
+    "type": "function",
+    "function": {
+        "name": "hass_set_state",
+        "description": "设置homeassistant里设备的状态,包括开、关,调整灯光亮度,调整播放器的音量,设备的暂停、继续、静音操作",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "state": {
+                    "type": "object",
+                    "properties": {
+                        "type": {
+                            "type": "string",
+                            "description": "需要操作的动作,打开设备:turn_on,关闭设备:turn_off,增加亮度:brightness_up,降低亮度:brightness_down,设置亮度:brightness_value,增加>音量:,volume_up降低音量:volume_down,设置音量:volume_set,设备暂停:pause,设备继续:continue,静音/取消静音:volume_mute"
+                        },
+                        "input": {
+                            "type": "int",
+                            "description": "只有在设置音量,设置亮度时候才需要,有效值为1-100,对应音量和亮度的1%-100%"
+                        },
+                        "is_muted": {
+                            "type": "string",
+                            "description": "只有在设置静音操作时才需要,设置静音的时候该值为true,取消静音时该值为false"
+                        }
+                    },
+                    "required": ["type"]
+                },
+                "entity_id": {
+                    "type": "string",
+                    "description": "需要操作的设备id,homeassistant里的entity_id"
+                }
+            },
+            "required": ["state", "entity_id"]
+        }
+    }
+}
+
+
+@register_function('hass_set_state', hass_set_state_function_desc, ToolType.SYSTEM_CTL)
+def hass_set_state(conn, entity_id='', state={}):
+    try:
+        future = asyncio.run_coroutine_threadsafe(
+            handle_hass_set_state(conn, entity_id, state),
+            conn.loop
+        )
+        ha_response = future.result()
+        return ActionResponse(action=Action.REQLLM, result="执行成功", response=ha_response)
+    except Exception as e:
+        logger.bind(tag=TAG).error(f"处理设置属性意图错误: {e}")
+
+
+async def handle_hass_set_state(conn, entity_id, state):
+    HASS_CACHE = initialize_hass_handler(conn)
+    api_key = HASS_CACHE['api_key']
+    base_url = HASS_CACHE['base_url']
+    '''
+    state = { "type":"brightness_up","input":"80","is_muted":"true"}
+    '''
+    domains = entity_id.split(".")
+    if len(domains) > 1:
+        domain = domains[0]
+    else:
+        return "执行失败，错误的设备id"
+    action = ''
+    arg = ''
+    value = ''
+    if state['type'] == 'turn_on':
+        description = "设备已打开"
+        if domain == "cover":
+            action = "open_cover"
+        elif domain == "vacuum":
+            action = "start"
+        else:
+            action = "turn_on"
+    elif state['type'] == 'turn_off':
+        description = "设备已关闭"
+        if domain == 'cover':
+            action = "close_cover"
+        elif domain == 'vacuum':
+            action = "stop"
+        else:
+            action = "turn_off"
+    elif state['type'] == 'brightness_up':
+        description = "灯光已调亮"
+        action = 'turn_on'
+        arg = 'brightness_step_pct'
+        value = 10
+    elif state['type'] == 'brightness_down':
+        description = "灯光已调暗"
+        action = 'turn_on'
+        arg = 'brightness_step_pct'
+        value = -10
+    elif state['type'] == 'brightness_value':
+        description = f"亮度已调整到{state['input']}"
+        action = 'turn_on'
+        arg = 'brightness_pct'
+        value = state['input']
+    elif state['type'] == 'volume_up':
+        description = "音量已调大"
+        action = state['type']
+    elif state['type'] == 'volume_down':
+        description = "音量已调小"
+        action = state['type']
+    elif state['type'] == 'volume_set':
+        description = f"音量已调整到{state['input']}"
+        action = state['type']
+        arg = 'volume_level'
+        value = state['input']
+    elif state['type'] == 'volume_mute':
+        description = f"设备已静音"
+        action = state['type']
+        arg = 'is_volume_muted'
+        value = state['is_muted']
+    elif state['type'] == 'pause':
+        description = f"设备已暂停"
+        action = state['type']
+        if domain == 'media_player':
+            action = 'media_pause'
+        if domain == 'cover':
+            action = 'stop_cover'
+        if domain == 'vacuum':
+            action = 'pause'
+    elif state['type'] == 'continue':
+        description = f"设备已继续"
+        if domain == 'media_player':
+            action = 'media_play'
+        if domain == 'vacuum':
+            action = 'start'
+    else:
+        return f"{domain} {state.type}功能尚未支持"
+
+    if arg == '':
+        data = {
+            "entity_id": entity_id,
+        }
+    else:
+        data = {
+            "entity_id": entity_id,
+            arg: value
+        }
+    url = f"{base_url}/api/services/{domain}/{action}"
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json"
+    }
+    response = requests.post(url, headers=headers, json=data)
+    logger.bind(tag=TAG).info(f"设置状态:url:{url},return_code:{response.status_code}")
+    if response.status_code == 200:
+        return description
+    else:
+        return f"设置失败，错误码: {response.status_code}"

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

@@ -21,13 +21,13 @@ play_music_function_desc = {
                 "type": "function",
                 "function": {
                     "name": "play_music",
-                    "description": "唱歌、听歌、播放音乐方法。比如用户说播放音乐，参数为：random，比如用户说播放两只老虎，参数为：两只老虎",
+                    "description": "唱歌、听歌、播放音乐的方法。",
                     "parameters": {
                         "type": "object",
                         "properties": {
                             "song_name": {
                                 "type": "string",
-                                "description": "歌曲名称，如果没有指定具体歌名则为'random'"
+                                "description": "歌曲名称，如果用户没有指定具体歌名则为'random', 明确指定的时返回音乐的名字 示例: ```用户:播放两只老虎\n参数：两只老虎``` ```用户:播放音乐 \n参数：random ```"
                             }
                         },
                         "required": ["song_name"]
@@ -112,8 +112,8 @@ def get_music_files(music_dir, music_ext):
 def initialize_music_handler(conn):
     global MUSIC_CACHE
     if MUSIC_CACHE == {}:
-        if "music" in conn.config:
-            MUSIC_CACHE["music_config"] = conn.config["music"]
+        if "play_music" in conn.config["plugins"]:
+            MUSIC_CACHE["music_config"] = conn.config["plugins"]["play_music"]
             MUSIC_CACHE["music_dir"] = os.path.abspath(
                 MUSIC_CACHE["music_config"].get("music_dir", "./music")  # 默认路径修改
             )

main/xiaozhi-server/plugins_func/loadplugins.py

@@ -22,6 +22,4 @@ def auto_import_modules(package_name):
         # 导入模块
         full_module_name = f"{package_name}.{module_name}"
         importlib.import_module(full_module_name)
-        #logger.bind(tag=TAG).info(f"模块 '{full_module_name}' 已加载")
-
-auto_import_modules('plugins_func.functions')
+        #logger.bind(tag=TAG).info(f"模块 '{full_module_name}' 已加载")