update:websocket播报6位验证码 (#821)

main/xiaozhi-server/config/config_loader.py

@@ -4,6 +4,17 @@ import requests
 import yaml
 import time
 
+
+class DeviceNotFoundException(Exception):
+    pass
+
+
+class DeviceBindException(Exception):
+    def __init__(self, bind_code):
+        self.bind_code = bind_code
+        super().__init__(f"设备绑定异常，绑定码: {bind_code}")
+
+
 # 添加全局配置缓存
 _config_cache = None
 
@@ -83,7 +94,11 @@ def _make_api_request(api_url, secret, endpoint, json_data=None):
             response = requests.post(f"{api_url}{endpoint}", json=json_data)
             if response.status_code == 200:
                 result = response.json()
-                if result.get("code") != 0:
+                if result.get("code") == 10041:
+                    raise DeviceNotFoundException(result.get("msg"))
+                elif result.get("code") == 10042:
+                    raise DeviceBindException(result.get("msg"))
+                elif result.get("code") != 0:
                     raise Exception(f"API返回错误: {result.get('msg', '未知错误')}")
                 return result.get("data")
 

main/xiaozhi-server/core/connection.py

@@ -27,7 +27,11 @@ from core.handle.functionHandler import FunctionHandler
 from plugins_func.register import Action, ActionResponse
 from core.auth import AuthMiddleware, AuthenticationError
 from core.mcp.manager import MCPManager
-from config.config_loader import get_private_config_from_api
+from config.config_loader import (
+    get_private_config_from_api,
+    DeviceNotFoundException,
+    DeviceBindException,
+)
 
 TAG = __name__
 
@@ -46,6 +50,9 @@ class ConnectionHandler:
         self.logger = setup_logging()
         self.auth = AuthMiddleware(config)
 
+        self.need_bind = False
+        self.bind_code = None
+
         self.websocket = None
         self.headers = None
         self.client_ip = None
@@ -206,7 +213,15 @@ class ConnectionHandler:
             )
             private_config["delete_audio"] = bool(self.config.get("delete_audio", True))
             self.logger.bind(tag=TAG).info(f"获取差异化配置成功: {private_config}")
+        except DeviceNotFoundException as e:
+            self.need_bind = True
+            private_config = {}
+        except DeviceBindException as e:
+            self.need_bind = True
+            self.bind_code = e.bind_code
+            private_config = {}
         except Exception as e:
+            self.need_bind = True
             self.logger.bind(tag=TAG).error(f"获取差异化配置失败: {e}")
             private_config = {}
 
@@ -345,7 +360,6 @@ class ConnectionHandler:
         response_message = []
         processed_chars = 0  # 跟踪已处理的字符位置
         try:
-            start_time = time.time()
             # 使用带记忆的对话
             future = asyncio.run_coroutine_threadsafe(
                 self.memory.query_memory(query), self.loop
@@ -367,9 +381,6 @@ class ConnectionHandler:
             if self.client_abort:
                 break
 
-            end_time = time.time()
-            # self.logger.bind(tag=TAG).debug(f"大模型返回时间: {end_time - start_time} 秒, 生成token={content}")
-
             # 合并当前全部文本并处理未分割部分
             full_text = "".join(response_message)
             current_text = full_text[processed_chars:]  # 从未处理的位置开始

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

@@ -1,5 +1,6 @@
 from config.logger import setup_logging
 import time
+import asyncio
 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
@@ -35,9 +36,7 @@ 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
-            )
+            text, _ = await conn.asr.speech_to_text(conn.asr_audio, conn.session_id)
             logger.bind(tag=TAG).info(f"识别文本: {text}")
             text_len, _ = remove_punctuation_and_length(text)
             if text_len > 0:
@@ -49,6 +48,9 @@ async def handleAudioMessage(conn, audio):
 
 
 async def startToChat(conn, text):
+    if conn.need_bind:
+        await check_bind_device(conn)
+        return
     # 首先进行意图分析
     intent_handled = await handle_user_intent(conn, text)
 
@@ -85,3 +87,44 @@ async def no_voice_close_connect(conn):
                 "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 check_bind_device(conn):
+    if conn.bind_code:
+        # 确保bind_code是6位数字
+        if len(conn.bind_code) != 6:
+            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, _ = conn.tts.audio_to_opus_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, _ = conn.tts.audio_to_opus_data(num_path)
+                conn.audio_play_queue.put((num_packets, text, i + 1))
+            except Exception as e:
+                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, _ = conn.tts.audio_to_opus_data(music_path)
+        conn.audio_play_queue.put((opus_packets, text, 0))

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

@@ -16,7 +16,7 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("voice")
         self.response_format = config.get("response_format")
         self.sample_rate = config.get("sample_rate")
-        self.speed = float(config.get("speed"))
+        self.speed = float(config.get("speed", 1.0))
         self.gain = config.get("gain")
 
         self.host = "api.siliconflow.cn"