update: 增加唤醒时声纹处理 ，1秒内发送至大模型 【需优化唤醒锁机制，中途会遭受打断(偶发)，考虑忽略检测】

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

@@ -1,16 +1,5 @@
-import time
 import json
-import random
 import asyncio
-from core.utils.dialogue import Message
-from core.providers.tts.dto.dto import SentenceType
-from core.utils.wakeup_word import WakeupWordsConfig
-from core.handle.sendAudioHandle import sendAudioMessage, send_stt_message
-from core.utils.util import (
-    audio_to_data_stream,
-    remove_punctuation_and_length, 
-    opus_datas_to_wav_bytes
-)
 from core.providers.tools.device_mcp import (
     MCPClient,
     send_mcp_initialize_message,
@@ -19,18 +8,6 @@ from core.providers.tools.device_mcp import (
 
 TAG = __name__
 
-WAKEUP_CONFIG = {
-    "refresh_time": 5,
-    "words": ["你好", "你好啊", "嘿，你好", "嗨"],
-}
-
-# 创建全局的唤醒词配置管理器
-wakeup_words_config = WakeupWordsConfig()
-
-# 用于防止并发调用wakeupWordsResponse的锁
-_wakeup_response_lock = asyncio.Lock()
-
-
 async def handleHelloMessage(conn, msg_json):
     """处理hello消息"""
     audio_params = msg_json.get("audio_params")
@@ -51,100 +28,4 @@ async def handleHelloMessage(conn, msg_json):
             # 发送mcp消息，获取tools列表
             asyncio.create_task(send_mcp_tools_list_request(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"
-    ]
-
-    if not enable_wakeup_words_response_cache or not conn.tts:
-        return False
-
-    _, filtered_text = remove_punctuation_and_length(text)
-    if filtered_text not in conn.config.get("wakeup_words"):
-        return False
-
-    conn.just_woken_up = True
-    await send_stt_message(conn, text)
-
-    # 获取当前音色
-    voice = getattr(conn.tts, "voice", "default")
-    if not voice:
-        voice = "default"
-
-    # 获取唤醒词回复配置
-    response = wakeup_words_config.get_wakeup_response(voice)
-    if not response or not response.get("file_path"):
-        response = {
-            "voice": "default",
-            "file_path": "config/assets/wakeup_words.wav",
-            "time": 0,
-            "text": "哈啰啊，我是小智啦，声音好听的台湾女孩一枚，超开心认识你耶，最近在忙啥，别忘了给我来点有趣的料哦，我超爱听八卦的啦",
-        }
-    
-    # 获取音频数据
-    opus_packets = []
-    def handle_audio_frame(frame_data):
-        opus_packets.append(frame_data)
-    
-    audio_to_data_stream(response.get("file_path"), is_opus=True, callback=handle_audio_frame)
-
-    # 播放唤醒词回复
-    conn.client_abort = False
-
-    conn.logger.bind(tag=TAG).info(f"播放唤醒词回复: {response.get('text')}")
-    await sendAudioMessage(conn, SentenceType.FIRST, opus_packets, response.get("text"))
-    await sendAudioMessage(conn, SentenceType.LAST, [], None)
-
-    # 补充对话
-    conn.dialogue.put(Message(role="assistant", content=response.get("text")))
-
-    # 检查是否需要更新唤醒词回复
-    if time.time() - response.get("time", 0) > WAKEUP_CONFIG["refresh_time"]:
-        if not _wakeup_response_lock.locked():
-            asyncio.create_task(wakeupWordsResponse(conn))
-    return True
-
-
-async def wakeupWordsResponse(conn):
-    if not conn.tts or not conn.llm or not conn.llm.response_no_stream:
-        return
-
-    try:
-        # 尝试获取锁，如果获取不到就返回
-        if not await _wakeup_response_lock.acquire():
-            return
-
-        # 生成唤醒词回复
-        wakeup_word = random.choice(WAKEUP_CONFIG["words"])
-        question = (
-            "此刻用户正在和你说```"
-            + wakeup_word
-            + "```。\n请你根据以上用户的内容进行20-30字回复。要符合系统设置的角色情感和态度，不要像机器人一样说话。\n"
-            + "请勿对这条内容本身进行任何解释和回应，请勿返回表情符号，仅返回对用户的内容的回复。"
-        )
-
-        result = conn.llm.response_no_stream(conn.config["prompt"], question)
-        if not result or len(result) == 0:
-            return
-
-        # 生成TTS音频
-        tts_result = await asyncio.to_thread(conn.tts.to_tts, result)
-        if not tts_result:
-            return
-
-        # 获取当前音色
-        voice = getattr(conn.tts, "voice", "default")
-
-        wav_bytes = opus_datas_to_wav_bytes(tts_result, sample_rate=16000)
-        file_path = wakeup_words_config.generate_file_path(voice)
-        with open(file_path, "wb") as f:
-            f.write(wav_bytes)
-        # 更新配置
-        wakeup_words_config.update_wakeup_response(voice, file_path, result)
-    finally:
-        # 确保在任何情况下都释放锁
-        if _wakeup_response_lock.locked():
-            _wakeup_response_lock.release()
+    await conn.websocket.send(json.dumps(conn.welcome_msg))