merge main

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

@@ -2,6 +2,7 @@ from config.logger import setup_logging
 import json
 from core.handle.sendAudioHandle import send_stt_message
 from core.utils.dialogue import Message
+from core.utils.util import remove_punctuation_and_length
 from config.functionCallConfig import FunctionCallConfig
 import asyncio
 from enum import Enum
@@ -67,7 +68,7 @@ def handle_llm_function_call(conn, function_call_data):
             except Exception as e:
                 logger.bind(tag=TAG).error(f"处理音乐意图错误: {e}")
         else:
-            return ActionResponse(action=Action.NOTFOUND, result="没有找到对应的函数", response="")
+            return ActionResponse(action=Action.NOTFOUND, result="没有找到对应的函数", response="没有找到对应的函数处理相对于的功能呢，你可以需要添加预设的对应函数处理呢")
     except Exception as e:
         logger.bind(tag=TAG).error(f"处理function call错误: {e}")
 
@@ -93,8 +94,6 @@ async def handle_user_intent(conn, text):
         # 使用支持function calling的聊天方法,不再进行意图分析
         return False
 
-    logger.bind(tag=TAG).info(f"分析用户意图: {text}")
-
     # 使用LLM进行意图分析
     intent = await analyze_intent_with_llm(conn, text)
 
@@ -107,6 +106,7 @@ async def handle_user_intent(conn, text):
 
 async def check_direct_exit(conn, text):
     """检查是否有明确的退出命令"""
+    _, text = remove_punctuation_and_length(text)
     cmd_exit = conn.cmd_exit
     for cmd in cmd_exit:
         if text == cmd:
@@ -122,13 +122,10 @@ async def analyze_intent_with_llm(conn, text):
         logger.bind(tag=TAG).warning("意图识别服务未初始化")
         return None
 
-    # 创建对话历史记录
+    # 对话历史记录
     dialogue = conn.dialogue
-    dialogue.put(Message(role="user", content=text))
-
     try:
-        intent_result = await conn.intent.detect_intent(dialogue.dialogue)
-        logger.bind(tag=TAG).info(f"意图识别结果: {intent_result}")
+        intent_result = await conn.intent.detect_intent(conn, dialogue.dialogue, text)
 
         # 尝试解析JSON结果
         try:

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

@@ -67,8 +67,9 @@ async def no_voice_close_connect(conn):
     else:
         no_voice_time = time.time() * 1000 - conn.client_no_voice_last_time
         close_connection_no_voice_time = conn.config.get("close_connection_no_voice_time", 120)
-        if no_voice_time > 1000 * close_connection_no_voice_time:
+        if not conn.close_after_chat and no_voice_time > 1000 * close_connection_no_voice_time:
+            conn.close_after_chat = True
             conn.client_abort = False
             conn.asr_server_receive = False
-            prompt = "时间过得真快，我都好久没说话了。请你用十个字左右话跟我告别，以“再见”或“拜拜”为结尾"
+            prompt = "请你以“时间过得真快”未来头，用富有感情、依依不舍的话来结束这场对话吧。"
             await startToChat(conn, prompt)

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

@@ -75,28 +75,37 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
         logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
     await send_tts_message(conn, "sentence_start", text)
 
-    # 初始化流控参数
-    frame_duration = 60  # 毫秒
-    start_time = time.perf_counter()  # 使用高精度计时器
-    play_position = 0  # 已播放的时长（毫秒）
+    # 流控参数优化
+    original_frame_duration = 60  # 原始帧时长（毫秒）
+    adjusted_frame_duration = int(original_frame_duration * 0.8)  # 缩短20%
+    total_frames = len(audios)  # 获取总帧数
+    compensation = total_frames * (original_frame_duration - adjusted_frame_duration) / 1000  # 补偿时间（秒）
+
+    start_time = time.perf_counter()
+    play_position = 0  # 已播放时长（毫秒）
 
     for opus_packet in audios:
         if conn.client_abort:
             return
 
-        # 计算当前包的预期发送时间
+        # 计算带加速因子的预期时间
         expected_time = start_time + (play_position / 1000)
         current_time = time.perf_counter()
 
-        # 等待直到预期时间
+        # 流控等待（使用加速后的帧时长）
         delay = expected_time - current_time
         if delay > 0:
             await asyncio.sleep(delay)
 
-        # 发送音频包
         await conn.websocket.send(opus_packet)
-        play_position += frame_duration  # 更新播放位置
+        play_position += adjusted_frame_duration  # 使用调整后的帧时长
+
+    # 补偿因加速损失的时长
+    if compensation > 0:
+        await asyncio.sleep(compensation)
+
     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)