合并main分支

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

@@ -1,18 +1,22 @@
-from config.logger import setup_logging
 import time
+import copy
 from core.utils.util import remove_punctuation_and_length
 from core.handle.sendAudioHandle import send_stt_message
 from core.handle.intentHandler import handle_user_intent
+from core.utils.output_counter import check_device_output_limit
+from core.handle.reportHandle import enqueue_asr_report
+from core.utils.util import audio_to_data
 
 TAG = __name__
-logger = setup_logging()
 
 
 async def handleAudioMessage(conn, audio):
-    if not conn.asr_server_receive:
-        logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
+    if conn.vad is None:
         return
-    if conn.client_listen_mode == "auto":
+    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" or conn.client_listen_mode == "realtime":
         have_voice = conn.vad.is_vad(conn, audio)
     else:
         have_voice = conn.client_have_voice
@@ -35,12 +39,13 @@ async def handleAudioMessage(conn, audio):
         if len(conn.asr_audio) < 15:
             conn.asr_server_receive = True
         else:
-            text, file_path = await conn.asr.speech_to_text(
-                conn.asr_audio, conn.session_id
-            )
-            logger.bind(tag=TAG).info(f"识别文本: {text}")
+            text, _ = await conn.asr.speech_to_text(conn.asr_audio, conn.session_id)
+            conn.logger.bind(tag=TAG).info(f"识别文本: {text}")
             text_len, _ = remove_punctuation_and_length(text)
             if text_len > 0:
+                # 使用自定义模块进行上报
+                enqueue_asr_report(conn, text, copy.deepcopy(conn.asr_audio))
+
                 await startToChat(conn, text)
             else:
                 conn.asr_server_receive = True
@@ -49,6 +54,18 @@ async def handleAudioMessage(conn, audio):
 
 
 async def startToChat(conn, text):
+    if conn.need_bind:
+        await check_bind_device(conn)
+        return
+
+    # 如果当日的输出字数大于限定的字数
+    if conn.max_output_size > 0:
+        if check_device_output_limit(
+            conn.headers.get("device-id"), conn.max_output_size
+        ):
+            await max_out_size(conn)
+            return
+
     # 首先进行意图分析
     intent_handled = await handle_user_intent(conn, text)
 
@@ -59,7 +76,7 @@ async def startToChat(conn, text):
 
     # 意图未被处理，继续常规聊天流程
     await send_stt_message(conn, text)
-    if conn.use_function_call_mode:
+    if conn.intent_type == "function_call":
         # 使用支持function calling的聊天方法
         conn.executor.submit(conn.chat_with_function_calling, text)
     else:
@@ -71,8 +88,8 @@ async def no_voice_close_connect(conn):
         conn.client_no_voice_last_time = time.time() * 1000
     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
+        close_connection_no_voice_time = int(
+            conn.config.get("close_connection_no_voice_time", 120)
         )
         if (
             not conn.close_after_chat
@@ -81,7 +98,65 @@ async def no_voice_close_connect(conn):
             conn.close_after_chat = True
             conn.client_abort = False
             conn.asr_server_receive = False
-            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。"
-            )
+            end_prompt = conn.config.get("end_prompt", {})
+            if end_prompt and end_prompt.get("enable", True) is False:
+                conn.logger.bind(tag=TAG).info("结束对话，无需发送结束提示语")
+                await conn.close()
+                return
+            prompt = end_prompt.get("prompt")
+            if not prompt:
+                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)
+
+
+async def max_out_size(conn):
+    text = "不好意思，我现在有点事情要忙，明天这个时候我们再聊，约好了哦！明天不见不散，拜拜！"
+    await send_stt_message(conn, text)
+    conn.tts_first_text_index = 0
+    conn.tts_last_text_index = 0
+    conn.llm_finish_task = True
+    file_path = "config/assets/max_output_size.wav"
+    opus_packets, _ = audio_to_data(file_path)
+    conn.audio_play_queue.put((opus_packets, text, 0))
+    conn.close_after_chat = True
+
+
+async def check_bind_device(conn):
+    if conn.bind_code:
+        # 确保bind_code是6位数字
+        if len(conn.bind_code) != 6:
+            conn.logger.bind(tag=TAG).error(f"无效的绑定码格式: {conn.bind_code}")
+            text = "绑定码格式错误，请检查配置。"
+            await send_stt_message(conn, text)
+            return
+
+        text = f"请登录控制面板，输入{conn.bind_code}，绑定设备。"
+        await send_stt_message(conn, text)
+        conn.tts_first_text_index = 0
+        conn.tts_last_text_index = 6
+        conn.llm_finish_task = True
+
+        # 播放提示音
+        music_path = "config/assets/bind_code.wav"
+        opus_packets, _ = audio_to_data(music_path)
+        conn.audio_play_queue.put((opus_packets, text, 0))
+
+        # 逐个播放数字
+        for i in range(6):  # 确保只播放6位数字
+            try:
+                digit = conn.bind_code[i]
+                num_path = f"config/assets/bind_code/{digit}.wav"
+                num_packets, _ = audio_to_data(num_path)
+                conn.audio_play_queue.put((num_packets, None, i + 1))
+            except Exception as e:
+                conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
+                continue
+    else:
+        text = f"没有找到该设备的版本信息，请正确配置 OTA地址，然后重新编译固件。"
+        await send_stt_message(conn, text)
+        conn.tts_first_text_index = 0
+        conn.tts_last_text_index = 0
+        conn.llm_finish_task = True
+        music_path = "config/assets/bind_not_found.wav"
+        opus_packets, _ = audio_to_data(music_path)
+        conn.audio_play_queue.put((opus_packets, text, 0))