Merge branch 'test-mcp' into py_test_mcp

This commit is contained in:
hrz
2025-05-30 16:08:14 +08:00
committed by GitHub
15 changed files with 618 additions and 225 deletions
+18 -5
View File
@@ -141,11 +141,10 @@
本项目提供两种部署方式,请根据您的具体需求选择:
#### 🚀 部署方式选择
| 部署方式 | 特点 | 适用场景 | Docker部署文档 | 源码部署文档 | 视频教程 |
| 部署方式 | 特点 | 适用场景 | 部署文档 | 配置要求 | 视频教程 |
|---------|------|---------|---------|---------|---------|
| **最简化安装** | 智能对话、IOT功能,数据存储在配置文件 | 低配置环境,无需数据库 | [Docker只运行Server](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) | [本地源码只运行Server](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| - |
| **全模块安装** | 智能对话、IOT、OTA、智控台,数据存储在数据库 | 完整功能体验 |[Docker运行全模块](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) | [本地源码运行全模块](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) | [本地源码视频教程](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
| **最简化安装** | 智能对话、IOT功能,数据存储在配置文件 | 低配置环境,无需数据库 | [Docker](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [源码部署](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 如果使用`FunASR`要2核4G,如果全API,要2核2G | - |
| **全模块安装** | 智能对话、IOT、OTA、智控台,数据存储在数据库 | 完整功能体验 |[Docker](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [源码部署](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) | 如果使用`FunASR`要4核8G,如果全API,要2核4G| [本地源码视频教程](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
> 💡 提示:以下是按最新代码部署后的测试平台,有需要可烧录测试,并发为6个,每天会清空数据
@@ -158,9 +157,23 @@ OTA接口地址: https://2662r3426b.vicp.fun/xiaozhi/ota/
Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
```
#### 🚩 配置说明和推荐
> [!Note]
> 本项目默认的配置是`入门全免费`设置,如果想效果更优,推荐使用`全流式配置`。
>
> 本项目自`0.5.2`版本,已支持整个生命周期全流式,相比`0.5`版本以前,响应速度提升约`2.5秒`
| 模块名称 | 入门全免费设置 | 全流式配置 |
|---------|---------|------|
| ASR(语音识别) | FunASR(本地) | ✅DoubaoASR(火山流式语音识别) |
| LLM(大模型) | ChatGLMLLM(智谱glm-4-flash) | ✅DoubaoLLM(火山doubao-1-5-pro-32k-250115) |
| TTS(语音合成) | EdgeTTS(微软语音) | ✅HuoshanDoubleStreamTTS(火山双流式语音合成) |
| Intent(意图识别) | function_call(函数调用) | ✅function_call(函数调用) |
| Memory(记忆功能) | mem_local_short(本地短期记忆) | ✅mem_local_short(本地短期记忆) |
---
## 功能清单 ✨
### 已实现 ✅
| 功能模块 | 描述 |
@@ -227,7 +227,7 @@ public interface Constant {
/**
* 版本号
*/
public static final String VERSION = "0.5.1";
public static final String VERSION = "0.5.2";
/**
* 无效固件URL
+23 -7
View File
@@ -4,7 +4,7 @@ from loguru import logger
from config.config_loader import load_config
from config.settings import check_config_file
SERVER_VERSION = "0.5.1"
SERVER_VERSION = "0.5.2"
_logger_initialized = False
@@ -48,7 +48,11 @@ def setup_logging():
# 第一次初始化时配置日志
if not _logger_initialized:
logger.configure(extra={"selected_module": log_config.get("selected_module", "00000000000000")}) # 新增配置
logger.configure(
extra={
"selected_module": log_config.get("selected_module", "00000000000000")
}
) # 新增配置
log_format = log_config.get(
"log_format",
"<green>{time:YYMMDD HH:mm:ss}</green>[{version}_{extra[selected_module]}][<light-blue>{extra[tag]}</light-blue>]-<level>{level}</level>-<light-green>{message}</light-green>",
@@ -62,7 +66,9 @@ def setup_logging():
log_format = log_format.replace("{version}", SERVER_VERSION)
log_format = log_format.replace("{selected_module}", selected_module_str)
log_format_file = log_format_file.replace("{version}", SERVER_VERSION)
log_format_file = log_format_file.replace("{selected_module}", selected_module_str)
log_format_file = log_format_file.replace(
"{selected_module}", selected_module_str
)
log_level = log_config.get("log_level", "INFO")
log_dir = log_config.get("log_dir", "tmp")
@@ -116,15 +122,25 @@ def update_module_string(selected_module_str):
log_format = log_format.replace("{version}", SERVER_VERSION)
log_format = log_format.replace("{selected_module}", selected_module_str)
log_format_file = log_format_file.replace("{version}", SERVER_VERSION)
log_format_file = log_format_file.replace("{selected_module}", selected_module_str)
log_format_file = log_format_file.replace(
"{selected_module}", selected_module_str
)
logger.remove()
logger.add(sys.stdout, format=log_format, level=log_config.get("log_level", "INFO"), filter=formatter)
logger.add(
os.path.join(log_config.get("log_dir", "tmp"), log_config.get("log_file", "server.log")),
sys.stdout,
format=log_format,
level=log_config.get("log_level", "INFO"),
filter=formatter,
)
logger.add(
os.path.join(
log_config.get("log_dir", "tmp"),
log_config.get("log_file", "server.log"),
),
format=log_format_file,
level=log_config.get("log_level", "INFO"),
filter=formatter
filter=formatter,
)
except Exception as e:
+15 -7
View File
@@ -84,6 +84,7 @@ class ConnectionHandler:
# 客户端状态相关
self.client_abort = False
self.client_is_speaking = False
self.client_listen_mode = "auto"
# 线程任务相关
@@ -624,7 +625,7 @@ class ConnectionHandler:
function_arguments = ""
content_arguments = ""
text_index = 0
self.client_abort = False
for response in llm_responses:
if self.client_abort:
break
@@ -704,17 +705,23 @@ class ConnectionHandler:
"arguments": function_arguments,
}
# 处理MCP工具调用
# 处理Server端MCP工具调用
if self.mcp_manager.is_mcp_tool(function_name):
result = self._handle_mcp_tool_call(function_call_data)
elif hasattr(self, "mcp_client") and self.mcp_client.has_tool(function_name):
# 如果是MCP工具调用
# 如果是小智端MCP工具调用
self.logger.bind(tag=TAG).debug(
f"调用MCP工具: {function_name}, 参数: {function_arguments}"
f"调用小智端MCP工具: {function_name}, 参数: {function_arguments}"
)
result = asyncio.run_coroutine_threadsafe(call_mcp_tool(self, self.mcp_client, function_name, function_arguments), self.loop).result()
self.logger.bind(tag=TAG).debug(f"MCP工具调用结果: {result}")
result = ActionResponse(action=Action.REQLLM, result=result, response="")
try:
result = asyncio.run_coroutine_threadsafe(call_mcp_tool(self, self.mcp_client, function_name, function_arguments), self.loop).result()
self.logger.bind(tag=TAG).debug(f"MCP工具调用结果: {result}")
result = ActionResponse(action=Action.REQLLM, result=result, response="")
except Exception as e:
self.logger.bind(tag=TAG).error(f"MCP工具调用失败: {e}")
result = ActionResponse(
action=Action.REQLLM, result="MCP工具调用失败", response=""
)
else:
# 处理系统函数
result = self.func_handler.handle_llm_function_call(
@@ -867,6 +874,7 @@ class ConnectionHandler:
self.report_queue.task_done()
def clearSpeakStatus(self):
self.client_is_speaking = False
self.logger.bind(tag=TAG).debug(f"清除服务端讲话状态")
async def close(self, ws=None):
@@ -61,7 +61,7 @@ class FunctionHandler:
self.function_registry.register_function("plugin_loader")
self.function_registry.register_function("get_time")
self.function_registry.register_function("get_lunar")
self.function_registry.register_function("handle_speaker_volume_or_screen_brightness")
# self.function_registry.register_function("handle_speaker_volume_or_screen_brightness")
def register_config_functions(self):
"""注册配置中的函数,可以不同客户端使用不同的配置"""
@@ -104,7 +104,13 @@ 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)
question = (
"此刻用户正在和你说```"
+ wakeup_word
+ "```。\n请你根据以上用户的内容,进行简短回复,文字内容控制在15个字以内。\n"
+ "请勿对这条内容本身进行任何解释和回应,仅返回对用户的内容的回复。"
)
result = conn.llm.response_no_stream(conn.config["prompt"], question)
if result is None or result == "":
return
tts_file = await asyncio.to_thread(conn.tts.to_tts, result)
+22 -18
View File
@@ -7,33 +7,36 @@ TAG = __name__
class MCPClient:
"""MCPClient,用于管理MCP状态和工具"""
def __init__(self):
self.tools = []
self.tools = {} # Dictionary for O(1) lookup
self.ready = False
self.call_results = {} # To store Futures for tool call responses
self.next_id = 1
self.lock = asyncio.Lock()
self._cached_available_tools = None # Cache for get_available_tools
async def has_tool(self, name: str) -> bool:
async with self.lock:
for tool in self.tools:
if tool["name"] == name:
return True
return False
def has_tool(self, name: str) -> bool:
return name in self.tools
def get_available_tools(self) -> list:
# async with self.lock:
# Check if the cache is valid
if self._cached_available_tools is not None:
return self._cached_available_tools
# If cache is not valid, regenerate the list
result = []
for tool in self.tools:
for tool_name, tool_data in self.tools.items():
function_def = {
"name": tool["name"],
"description": tool["description"],
"name": tool_data["name"],
"description": tool_data["description"],
"parameters": {
"type": tool["inputSchema"].get("type", "object"),
"properties": tool["inputSchema"].get("properties", {}),
"required": tool["inputSchema"].get("required", [])
"type": tool_data["inputSchema"].get("type", "object"),
"properties": tool_data["inputSchema"].get("properties", {}),
"required": tool_data["inputSchema"].get("required", [])
}
}
result.append({"type": "function", "function": function_def})
self._cached_available_tools = result # Store the generated list in cache
return result
async def is_ready(self) -> bool:
@@ -46,8 +49,9 @@ class MCPClient:
async def add_tool(self, tool_data: dict):
async with self.lock:
self.tools.append(tool_data)
self.tools[tool_data["name"]] = tool_data
self._cached_available_tools = None # Invalidate the cache when a tool is added
async def get_next_id(self) -> int:
async with self.lock:
current_id = self.next_id
@@ -232,7 +236,7 @@ async def call_mcp_tool(conn, mcp_client: MCPClient, tool_name: str, args: str =
if not await mcp_client.is_ready():
raise RuntimeError("MCP客户端尚未准备就绪")
if not await mcp_client.has_tool(tool_name):
if not mcp_client.has_tool(tool_name):
raise ValueError(f"工具 {tool_name} 不存在")
tool_call_id = await mcp_client.get_next_id()
@@ -272,4 +276,4 @@ async def call_mcp_tool(conn, mcp_client: MCPClient, tool_name: str, args: str =
raise TimeoutError("工具调用请求超时")
except Exception as e:
await mcp_client.cleanup_call_result(tool_call_id)
raise e
raise e
@@ -1,6 +1,7 @@
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.abortHandle import handleAbortMessage
import time
from core.handle.sendAudioHandle import SentenceType
from core.utils.util import audio_to_data
@@ -12,11 +13,14 @@ async def handleAudioMessage(conn, audio):
if conn.vad is None:
conn.logger.bind(tag=TAG).warning("VAD模块未初始化,继续等待")
return
if conn.asr is None:
conn.logger.bind(tag=TAG).warning("ASR模块未初始化,继续等待")
if conn.asr is None or not hasattr(conn.asr, "conn") or conn.asr.conn is None:
conn.logger.bind(tag=TAG).warning("ASR模块未初始化或通道未就绪,继续等待")
return
# 当前片段是否有人说话
have_voice = conn.vad.is_vad(conn, audio)
if have_voice:
if conn.client_is_speaking:
await handleAbortMessage(conn)
# 设备长时间空闲检测,用于say goodbye
await no_voice_close_connect(conn, have_voice)
# 接收音频
@@ -35,6 +39,8 @@ async def startToChat(conn, text):
):
await max_out_size(conn)
return
if conn.client_is_speaking:
await handleAbortMessage(conn)
# 首先进行意图分析
intent_handled = await handle_user_intent(conn, text)
@@ -72,7 +78,7 @@ async def no_voice_close_connect(conn, have_voice):
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。!"
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)
@@ -62,6 +62,7 @@ async def sendAudioMessage(conn, sentenceType, audios, text):
# 发送结束消息(如果是最后一个文本)
if conn.llm_finish_task and sentenceType == SentenceType.LAST:
await send_tts_message(conn, "stop", None)
conn.client_is_speaking = False
if conn.close_after_chat:
await conn.close()
@@ -88,6 +89,7 @@ async def sendAudio(conn, audios, pre_buffer=True):
# 播放剩余音频帧
for opus_packet in remaining_audios:
if conn.client_abort:
conn.client_abort = False
return
# 每分钟重置一次计时器
@@ -141,4 +143,5 @@ async def send_stt_message(conn, text):
await conn.websocket.send(
json.dumps({"type": "stt", "text": stt_text, "session_id": conn.session_id})
)
conn.client_is_speaking = True
await send_tts_message(conn, "start")
@@ -59,6 +59,7 @@ async def handleTextMessage(conn, message):
# 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, original_text)
await send_tts_message(conn, "stop", None)
conn.client_is_speaking = False
elif is_wakeup_words:
# 上报纯文字数据(复用ASR上报功能,但不提供音频数据)
enqueue_asr_report(conn, "嘿,你好呀", [])
@@ -47,7 +47,7 @@ class ASRProviderBase(ABC):
if self.conn.client_voice_stop:
asr_audio_task = copy.deepcopy(self.conn.asr_audio)
self.conn.asr_audio.clear()
self.conn.client_abort = False
# 音频太短了,无法识别
self.conn.reset_vad_states()
if len(asr_audio_task) > 15:
+196 -91
View File
@@ -33,6 +33,21 @@ class ASRProvider(ASRProviderBase):
self.max_retries = 3
self.retry_delay = 2 # 重试延迟秒数
self.recv_lock = asyncio.Lock() # 添加接收锁
self.reconnect_lock = asyncio.Lock() # 添加重连锁
self.last_reconnect_time = 0 # 上次重连时间
self.reconnect_cooldown = 1 # 增加重连冷却时间到10秒
self.reconnect_count = 0 # 当前重连次数
self.max_reconnect_count = 3 # 减少最大重连次数到3次
self.asr_thread = None # ASR监听线程
self.thread_lock = threading.Lock() # 线程管理锁
self.is_reconnecting = False # 添加重连状态标志
# 添加会话管理相关属性
self._session_lock = asyncio.Lock() # 会话操作的并发锁
self._current_session_id = None # 当前会话ID
self._session_started = False # 会话是否已开始
self._session_finished = False # 会话是否已结束
self._session_close_event = asyncio.Event() # 添加会话关闭事件
self.appid = str(config.get("appid"))
self.cluster = config.get("cluster")
@@ -60,7 +75,6 @@ class ASRProvider(ASRProviderBase):
self.asr_ws = None
self.forward_task = None
self.conn = None
self.asr_thread = None
###################################################################################
# 豆包流式ASR重写父类的方法--开始
@@ -68,10 +82,18 @@ class ASRProvider(ASRProviderBase):
async def open_audio_channels(self, conn):
await super().open_audio_channels(conn)
retry_count = 0
while retry_count < self.max_retries:
try:
# 确保关闭旧的连接
async with self._session_lock:
# 如果正在重连,等待重连完成
if self.is_reconnecting:
logger.bind(tag=TAG).info("等待当前重连完成...")
await self._session_close_event.wait()
self._session_close_event.clear()
# 如果已有会话未结束,先关闭它
if self._session_started and not self._session_finished:
logger.bind(tag=TAG).warning(
f"发现未关闭的会话 {self._current_session_id},正在关闭..."
)
if self.asr_ws is not None:
try:
await self.asr_ws.close()
@@ -79,62 +101,94 @@ class ASRProvider(ASRProviderBase):
logger.bind(tag=TAG).warning(f"关闭旧连接时发生错误: {e}")
finally:
self.asr_ws = None
self._session_finished = True
self._session_close_event.set()
headers = self.token_auth() if self.auth_method == "token" else None
self.asr_ws = await websockets.connect(
self.ws_url,
additional_headers=headers,
max_size=1000000000,
ping_interval=None, # 禁用ping,因为服务器可能不支持
ping_timeout=None,
close_timeout=10,
)
# 重置会话状态
self._current_session_id = str(uuid.uuid4())
self._session_started = True
self._session_finished = False
self.is_reconnecting = True
# 发送初始化请求
request_params = self.construct_request(str(uuid.uuid4()))
try:
payload_bytes = str.encode(json.dumps(request_params))
payload_bytes = gzip.compress(payload_bytes)
full_client_request = self.generate_header()
full_client_request.extend((len(payload_bytes)).to_bytes(4, "big"))
full_client_request.extend(payload_bytes)
await self.asr_ws.send(full_client_request)
logger.bind(tag=TAG).debug(f"发送初始化请求: {request_params}")
except Exception as e:
logger.bind(tag=TAG).error(f"发送初始化请求失败: {e}")
raise e
try:
retry_count = 0
while retry_count < self.max_retries:
try:
headers = (
self.token_auth() if self.auth_method == "token" else None
)
self.asr_ws = await websockets.connect(
self.ws_url,
additional_headers=headers,
max_size=1000000000,
ping_interval=None,
ping_timeout=None,
close_timeout=10,
)
# 等待初始化响应
try:
init_res = await self.asr_ws.recv()
result = self.parse_response(init_res)
logger.bind(tag=TAG).info(f"ASR服务初始化响应: {result}")
except Exception as e:
logger.bind(tag=TAG).error(f"ASR服务初始化失败: {e}")
raise e
# 发送初始化请求
request_params = self.construct_request(
self._current_session_id
)
try:
payload_bytes = str.encode(json.dumps(request_params))
payload_bytes = gzip.compress(payload_bytes)
full_client_request = self.generate_header()
full_client_request.extend(
(len(payload_bytes)).to_bytes(4, "big")
)
full_client_request.extend(payload_bytes)
await self.asr_ws.send(full_client_request)
except Exception as e:
logger.bind(tag=TAG).error(f"发送初始化请求失败: {e}")
raise e
# 启动接收ASR结果的异步任务
asr_priority = threading.Thread(
target=self._start_monitor_asr_response_thread, daemon=True
)
asr_priority.start()
return
# 等待初始化响应
try:
init_res = await self.asr_ws.recv()
self.parse_response(init_res)
except Exception as e:
logger.bind(tag=TAG).error(f"ASR服务初始化失败: {e}")
raise e
except websockets.exceptions.WebSocketException as e:
retry_count += 1
if retry_count < self.max_retries:
logger.bind(tag=TAG).warning(
f"WebSocket连接失败,正在进行第{retry_count}次重试: {e}"
)
await asyncio.sleep(self.retry_delay)
else:
logger.bind(tag=TAG).error(
f"WebSocket连接失败,已达到最大重试次数: {e}"
)
raise
except Exception as e:
logger.bind(tag=TAG).error(f"WebSocket连接发生未知错误: {e}")
raise
# 启动接收ASR结果的异步任务
with self.thread_lock:
if (
self.asr_thread is None
or not self.asr_thread.is_alive()
):
logger.bind(tag=TAG).info("创建新的ASR监听线程...")
self.asr_thread = threading.Thread(
target=self._start_monitor_asr_response_thread,
daemon=True,
)
self.asr_thread.start()
# 等待一小段时间确保线程启动
await asyncio.sleep(0.1)
if not self.asr_thread.is_alive():
logger.bind(tag=TAG).error("ASR监听线程启动失败")
raise Exception("ASR监听线程启动失败")
logger.bind(tag=TAG).info("ASR监听线程已启动")
return
except websockets.exceptions.WebSocketException as e:
retry_count += 1
if retry_count < self.max_retries:
logger.bind(tag=TAG).warning(
f"WebSocket连接失败,正在进行第{retry_count}次重试: {e}"
)
await asyncio.sleep(self.retry_delay)
else:
logger.bind(tag=TAG).warning(
f"WebSocket连接失败,已达到最大重试次数: {e}"
)
raise
except Exception as e:
logger.bind(tag=TAG).error(f"WebSocket连接发生未知错误: {e}")
raise
finally:
self.is_reconnecting = False
self._session_close_event.set()
async def receive_audio(self, audio, _):
if not isinstance(audio, bytes):
@@ -150,7 +204,7 @@ class ASRProvider(ASRProviderBase):
if self.asr_ws:
await self.asr_ws.send(audio_request)
except Exception as e:
logger.bind(tag=TAG).error(f"发送音频数据时发生错误: {e}")
logger.bind(tag=TAG).debug(f"发送音频数据时发生错误: {e}")
###################################################################################
# 豆包流式ASR重写父类的方法--结束
@@ -246,23 +300,61 @@ class ASRProvider(ASRProviderBase):
def _start_monitor_asr_response_thread(self):
# 初始化链接
asyncio.run_coroutine_threadsafe(
self._forward_asr_results(), loop=self.conn.loop
)
try:
with self.thread_lock:
if self.conn is None or self.conn.loop is None:
logger.bind(tag=TAG).error(
"无法启动ASR监听线程:conn或loop未初始化"
)
return
try:
logger.bind(tag=TAG).info("开始启动ASR监听...")
asyncio.run_coroutine_threadsafe(
self._forward_asr_results(), loop=self.conn.loop
)
logger.bind(tag=TAG).info("ASR监听已启动")
except Exception as e:
logger.bind(tag=TAG).error(f"启动ASR监听线程失败: {e}")
except Exception as e:
logger.bind(tag=TAG).error(f"ASR监听线程发生未预期的错误: {e}")
async def _forward_asr_results(self):
try:
while not self.conn.stop_event.is_set():
try:
if self.asr_ws is None:
logger.bind(tag=TAG).info("尝试重新连接ASR服务...")
await self.open_audio_channels(self.conn)
continue
# 检查是否需要重连
async with self.reconnect_lock:
current_time = asyncio.get_event_loop().time()
if (
current_time - self.last_reconnect_time
< self.reconnect_cooldown
):
await asyncio.sleep(1)
continue
if self.reconnect_count >= self.max_reconnect_count:
logger.bind(tag=TAG).error(
"达到最大重连次数限制,停止重连"
)
await asyncio.sleep(self.reconnect_cooldown)
self.reconnect_count = 0
continue
self.last_reconnect_time = current_time
self.reconnect_count += 1
logger.bind(tag=TAG).info(
f"尝试重新连接ASR服务... (第{self.reconnect_count}次)"
)
await self.open_audio_channels(self.conn)
continue
# 使用锁来确保同一时间只有一个协程在接收数据
async with self.recv_lock:
response = await self.asr_ws.recv()
result = self.parse_response(response)
# 检查是否需要重连
if result.get("need_reconnect", False):
logger.bind(tag=TAG).info(
@@ -290,6 +382,7 @@ class ASRProvider(ASRProviderBase):
self.text = utterance["text"]
await self.handle_voice_stop(None)
break
except websockets.ConnectionClosed:
logger.bind(tag=TAG).debug("ASR服务连接已关闭,准备重连...")
# 确保关闭旧连接
@@ -301,34 +394,16 @@ class ASRProvider(ASRProviderBase):
finally:
self.asr_ws = None
retry_count = 0
while (
retry_count < self.max_retries
and not self.conn.stop_event.is_set()
):
try:
logger.bind(tag=TAG).info(
f"正在进行第{retry_count + 1}次重连尝试..."
)
await self.open_audio_channels(self.conn)
break
except Exception as e:
retry_count += 1
if retry_count < self.max_retries:
logger.bind(tag=TAG).warning(
f"重连失败,等待{self.retry_delay}秒后重试: {e}"
)
await asyncio.sleep(self.retry_delay)
else:
logger.bind(tag=TAG).error(
f"重连失败,已达到最大重试次数: {e}"
)
await asyncio.sleep(
self.retry_delay
) # 继续等待,以便后续重试
# 等待冷却时间
await asyncio.sleep(self.reconnect_cooldown)
continue
except Exception as e:
if not self.conn.stop_event.is_set():
await asyncio.sleep(2) # 增加重试延迟
logger.bind(tag=TAG).error(f"ASR监听发生错误: {e}")
await asyncio.sleep(self.retry_delay)
continue
except Exception as e:
logger.bind(tag=TAG).error(f"ASR监听线程发生错误: {e}")
# 确保在发生严重错误时也能继续尝试重连
@@ -422,8 +497,38 @@ class ASRProvider(ASRProviderBase):
f"ASR错误: {error_message} (错误码: {error_code})"
)
# 如果是识别相关错误>=1020,标记需要重连
if error_code >= 1020:
# 如果是识别相关错误,标记需要重连
if error_code >= 1020 or error_code == 1001:
result["need_reconnect"] = True
return result
async def close_session(self):
"""关闭当前会话"""
async with self._session_lock:
if not self._session_started:
logger.bind(tag=TAG).warning("尝试关闭未开始的会话")
return
if self._session_finished:
logger.bind(tag=TAG).warning(
f"会话 {self._current_session_id} 已经关闭"
)
return
try:
if self.asr_ws is not None:
await self.asr_ws.close()
except Exception as e:
logger.bind(tag=TAG).warning(f"关闭WebSocket连接时发生错误: {e}")
finally:
self.asr_ws = None
self._session_finished = True
self._session_started = False
self._current_session_id = None
# 重置重连计数
self.reconnect_count = 0
async def close(self):
"""资源清理方法"""
await self.close_session()
@@ -216,6 +216,7 @@ class TTSProviderBase(ABC):
logger.bind(tag=TAG).error(
f"处理TTS文本失败: {str(e)}, 类型: {type(e).__name__}, 堆栈: {traceback.format_exc()}"
)
continue
def _audio_play_priority_thread(self):
while not self.conn.stop_event.is_set():
@@ -6,6 +6,7 @@ import asyncio
import threading
import traceback
import websockets
import time
from config.logger import setup_logging
from core.utils import opus_encoder_utils
from core.utils.util import check_model_key
@@ -138,6 +139,7 @@ class Response:
class TTSProvider(TTSProviderBase):
def __init__(self, config, delete_audio_file):
super().__init__(config, delete_audio_file)
self.ws = None # 初始化ws属性
self.interface_type = InterfaceType.DUAL_STREAM
self.appId = config.get("appid")
self.access_token = config.get("access_token")
@@ -166,59 +168,133 @@ class TTSProvider(TTSProviderBase):
self._current_session_id = None # 当前会话ID
self._session_started = False # 会话是否已开始
self._session_finished = False # 会话是否已结束
self._connection_ready = False # 连接是否就绪
self._reconnect_attempts = 0 # 重连尝试次数
self._max_reconnect_attempts = 3 # 最大重连次数
###################################################################################
# 火山双流式TTS重写父类的方法--开始
###################################################################################
async def open_audio_channels(self, conn):
await super().open_audio_channels(conn)
ws_header = {
"X-Api-App-Key": self.appId,
"X-Api-Access-Key": self.access_token,
"X-Api-Resource-Id": self.resource_id,
"X-Api-Connect-Id": uuid.uuid4(),
}
self.ws = await websockets.connect(
self.ws_url, additional_headers=ws_header, max_size=1000000000
)
tts_priority = threading.Thread(
target=self._start_monitor_tts_response_thread, daemon=True
)
tts_priority.start()
try:
await super().open_audio_channels(conn)
await self._ensure_connection()
tts_priority = threading.Thread(
target=self._start_monitor_tts_response_thread, daemon=True
)
tts_priority.start()
except Exception as e:
logger.bind(tag=TAG).error(f"Failed to open audio channels: {str(e)}")
self.ws = None
raise
async def _ensure_connection(self):
"""确保WebSocket连接可用"""
try:
if self.ws is None:
logger.bind(tag=TAG).info("WebSocket连接不存在,开始建立新连接...")
ws_header = {
"X-Api-App-Key": self.appId,
"X-Api-Access-Key": self.access_token,
"X-Api-Resource-Id": self.resource_id,
"X-Api-Connect-Id": uuid.uuid4(),
}
self.ws = await websockets.connect(
self.ws_url, additional_headers=ws_header, max_size=1000000000
)
self._connection_ready = True
self._reconnect_attempts = 0
logger.bind(tag=TAG).info("WebSocket连接建立成功")
else:
# 尝试发送ping来检查连接是否还活着
try:
logger.bind(tag=TAG).debug("检查WebSocket连接状态...")
pong_waiter = await self.ws.ping()
await asyncio.wait_for(pong_waiter, timeout=1.0)
logger.bind(tag=TAG).debug("WebSocket连接状态正常")
except (asyncio.TimeoutError, websockets.ConnectionClosed):
# 如果ping失败,重新建立连接
logger.bind(tag=TAG).warning("WebSocket连接已断开,准备重新连接...")
try:
await self.ws.close()
except:
pass
self.ws = None
self._connection_ready = False
# 重新建立连接
await self._ensure_connection()
except Exception as e:
logger.bind(tag=TAG).error(f"确保连接失败: {str(e)}")
self._connection_ready = False
self.ws = None
raise
def tts_text_priority_thread(self):
logger.bind(tag=TAG).info("TTS文本处理线程启动")
while not self.conn.stop_event.is_set():
try:
logger.bind(tag=TAG).debug("等待TTS文本队列消息...")
message = self.tts_text_queue.get(timeout=1)
logger.bind(tag=TAG).debug(
f"TTS任务|{message.sentence_type.name} {message.content_type.name}"
logger.bind(tag=TAG).info(
f"收到TTS任务|{message.sentence_type.name} {message.content_type.name} | 会话ID: {self.conn.sentence_id}"
)
if message.sentence_type == SentenceType.FIRST:
# 初始化参数
future = asyncio.run_coroutine_threadsafe(
self.start_session(self.conn.sentence_id), loop=self.conn.loop
)
future.result()
self.tts_audio_first_sentence = True
self.before_stop_play_files.clear()
elif ContentType.TEXT == message.content_type:
if message.content_detail:
try:
logger.bind(tag=TAG).info("开始启动TTS会话...")
future = asyncio.run_coroutine_threadsafe(
self.text_to_speak(message.content_detail, None),
self.start_session(self.conn.sentence_id),
loop=self.conn.loop,
)
future.result()
self.tts_audio_first_sentence = True
self.before_stop_play_files.clear()
logger.bind(tag=TAG).info("TTS会话启动成功")
except Exception as e:
logger.bind(tag=TAG).error(f"启动TTS会话失败: {str(e)}")
# 直接跳过当前消息,不重新入队
time.sleep(1)
continue
elif ContentType.TEXT == message.content_type:
if message.content_detail:
try:
logger.bind(tag=TAG).info(
f"开始发送TTS文本: {message.content_detail}"
)
future = asyncio.run_coroutine_threadsafe(
self.text_to_speak(message.content_detail, None),
loop=self.conn.loop,
)
future.result()
logger.bind(tag=TAG).info("TTS文本发送成功")
except Exception as e:
logger.bind(tag=TAG).error(f"发送TTS文本失败: {str(e)}")
# 直接跳过当前消息,不重新入队
time.sleep(1)
continue
elif ContentType.FILE == message.content_type:
logger.bind(tag=TAG).info(
f"添加音频文件到待播放列表: {message.content_file}"
)
self.before_stop_play_files.append(
(message.content_file, message.content_detail)
)
if message.sentence_type == SentenceType.LAST:
future = asyncio.run_coroutine_threadsafe(
self.finish_session(self.conn.sentence_id), loop=self.conn.loop
)
future.result()
try:
logger.bind(tag=TAG).info("开始结束TTS会话...")
future = asyncio.run_coroutine_threadsafe(
self.finish_session(self.conn.sentence_id),
loop=self.conn.loop,
)
future.result()
logger.bind(tag=TAG).info("TTS会话结束成功")
except Exception as e:
logger.bind(tag=TAG).error(f"结束TTS会话失败: {str(e)}")
# 直接跳过当前消息,不重新入队
time.sleep(1)
continue
except queue.Empty:
continue
@@ -226,11 +302,30 @@ class TTSProvider(TTSProviderBase):
logger.bind(tag=TAG).error(
f"处理TTS文本失败: {str(e)}, 类型: {type(e).__name__}, 堆栈: {traceback.format_exc()}"
)
# 如果是WebSocket连接关闭错误,等待一段时间后继续
if "non-exist session" in str(e):
time.sleep(1)
continue
async def text_to_speak(self, text, _):
# 发送文本
await self.send_text(self.speaker, text, self.conn.sentence_id)
return
"""发送文本到TTS服务"""
try:
# 确保WebSocket连接可用
if not self._connection_ready or self.ws is None:
logger.bind(tag=TAG).warning("WebSocket连接不可用,尝试重新连接...")
await self._ensure_connection()
# 发送文本
await self.send_text(self.speaker, text, self.conn.sentence_id)
return
except Exception as e:
logger.bind(tag=TAG).error(f"发送TTS文本失败: {str(e)}")
# 如果是连接问题,尝试重新连接
if isinstance(e, websockets.ConnectionClosed):
self._connection_ready = False
self.ws = None
await self._handle_connection_error()
raise
###################################################################################
# 火山双流式TTS重写父类的方法--结束
@@ -308,14 +403,21 @@ class TTSProvider(TTSProviderBase):
async def send_event(
self, header: bytes, optional: bytes | None = None, payload: bytes = None
):
full_client_request = bytearray(header)
if optional is not None:
full_client_request.extend(optional)
if payload is not None:
payload_size = len(payload).to_bytes(4, "big", signed=True)
full_client_request.extend(payload_size)
full_client_request.extend(payload)
await self.ws.send(full_client_request)
try:
full_client_request = bytearray(header)
if optional is not None:
full_client_request.extend(optional)
if payload is not None:
payload_size = len(payload).to_bytes(4, "big", signed=True)
full_client_request.extend(payload_size)
full_client_request.extend(payload)
await self.ws.send(full_client_request)
except websockets.ConnectionClosed:
if await self._handle_connection_error():
# 重连成功后重试发送
await self.ws.send(full_client_request)
else:
raise
async def send_text(self, speaker: str, text: str, session_id):
header = Header(
@@ -450,63 +552,154 @@ class TTSProvider(TTSProviderBase):
return
async def start_session(self, session_id):
logger.bind(tag=TAG).debug(f"开始会话~~{session_id}")
async with self._session_lock:
# 如果已有会话未结束,先关闭它
if self._session_started and not self._session_finished:
logger.bind(tag=TAG).warning(
f"发现未关闭的会话 {self._current_session_id},正在关闭..."
)
await self.finish_session(self._current_session_id)
logger.bind(tag=TAG).info(f"开始会话~~{session_id}")
try:
async with self._session_lock:
try:
# 确保连接可用
logger.bind(tag=TAG).info("检查WebSocket连接状态...")
await asyncio.wait_for(self._ensure_connection(), timeout=5)
# 重置会话状态
self._current_session_id = session_id
self._session_started = True
self._session_finished = False
# 如果已有会话未结束,先关闭它
if self._session_started and not self._session_finished:
logger.bind(tag=TAG).warning(
f"发现未关闭的会话 {self._current_session_id},正在关闭..."
)
try:
await asyncio.wait_for(
self.finish_session(self._current_session_id), timeout=5
)
except Exception as e:
logger.bind(tag=TAG).error(f"关闭旧会话失败: {str(e)}")
# 强制重置会话状态
self._session_started = False
self._session_finished = True
self._current_session_id = None
header = Header(
message_type=FULL_CLIENT_REQUEST,
message_type_specific_flags=MsgTypeFlagWithEvent,
serial_method=JSON,
).as_bytes()
optional = Optional(
event=EVENT_StartSession, sessionId=session_id
).as_bytes()
payload = self.get_payload_bytes(
event=EVENT_StartSession, speaker=self.speaker
)
await self.send_event(header, optional, payload)
# 重置会话状态
self._current_session_id = session_id
self._session_started = True
self._session_finished = False
logger.bind(tag=TAG).info(
f"会话状态已更新 - 开始: {self._session_started}, 结束: {self._session_finished}"
)
header = Header(
message_type=FULL_CLIENT_REQUEST,
message_type_specific_flags=MsgTypeFlagWithEvent,
serial_method=JSON,
).as_bytes()
optional = Optional(
event=EVENT_StartSession, sessionId=session_id
).as_bytes()
payload = self.get_payload_bytes(
event=EVENT_StartSession, speaker=self.speaker
)
await asyncio.wait_for(
self.send_event(header, optional, payload), timeout=5
)
logger.bind(tag=TAG).info("会话启动请求已发送")
except Exception as e:
logger.bind(tag=TAG).error(f"启动会话失败: {str(e)}")
self._session_started = False
self._session_finished = True
self._current_session_id = None
raise
except asyncio.TimeoutError:
logger.bind(tag=TAG).error(f"启动会话超时: {session_id}")
# 超时后强制重置会话状态
self._session_started = False
self._session_finished = True
self._current_session_id = None
# 尝试关闭WebSocket连接
if self.ws:
try:
await self.ws.close()
except:
pass
self.ws = None
except Exception as e:
logger.bind(tag=TAG).error(f"启动会话时发生未知错误: {str(e)}")
# 发生未知错误时也重置会话状态
self._session_started = False
self._session_finished = True
self._current_session_id = None
async def finish_session(self, session_id):
logger.bind(tag=TAG).debug(f"关闭会话~~{session_id}")
async with self._session_lock:
# 检查会话状态
if not self._session_started:
logger.bind(tag=TAG).warning(f"尝试关闭未开始的会话 {session_id}")
return
logger.bind(tag=TAG).info(f"关闭会话~~{session_id}")
try:
async with self._session_lock:
try:
# 检查会话状态
if not self._session_started:
logger.bind(tag=TAG).warning(
f"尝试关闭未开始的会话 {session_id}"
)
return
if self._session_finished:
logger.bind(tag=TAG).warning(f"会话 {session_id} 已经关闭")
return
if self._session_finished:
logger.bind(tag=TAG).warning(f"会话 {session_id} 已经关闭")
return
if self._current_session_id != session_id:
logger.bind(tag=TAG).warning(
f"尝试关闭错误的会话 {session_id},当前会话为 {self._current_session_id}"
)
return
if self._current_session_id != session_id:
logger.bind(tag=TAG).warning(
f"尝试关闭错误的会话 {session_id},当前会话为 {self._current_session_id}"
)
# 即使会话ID不匹配,也尝试关闭当前会话
if self._current_session_id:
session_id = self._current_session_id
header = Header(
message_type=FULL_CLIENT_REQUEST,
message_type_specific_flags=MsgTypeFlagWithEvent,
serial_method=JSON,
).as_bytes()
optional = Optional(
event=EVENT_FinishSession, sessionId=session_id
).as_bytes()
payload = str.encode("{}")
await self.send_event(header, optional, payload)
# 确保WebSocket连接可用
if self.ws is None:
logger.bind(tag=TAG).warning(
"WebSocket连接不存在,尝试重新连接..."
)
await asyncio.wait_for(self._ensure_connection(), timeout=5)
# 更新会话状态
header = Header(
message_type=FULL_CLIENT_REQUEST,
message_type_specific_flags=MsgTypeFlagWithEvent,
serial_method=JSON,
).as_bytes()
optional = Optional(
event=EVENT_FinishSession, sessionId=session_id
).as_bytes()
payload = str.encode("{}")
await asyncio.wait_for(
self.send_event(header, optional, payload), timeout=5
)
logger.bind(tag=TAG).info("会话结束请求已发送")
# 更新会话状态
self._session_finished = True
self._session_started = False
self._current_session_id = None
logger.bind(tag=TAG).info(
"会话状态已更新 - 开始: False, 结束: True"
)
except Exception as e:
logger.bind(tag=TAG).error(f"关闭会话失败: {str(e)}")
# 即使发生错误,也要重置会话状态
self._session_finished = True
self._session_started = False
self._current_session_id = None
raise
except asyncio.TimeoutError:
logger.bind(tag=TAG).error(f"关闭会话超时: {session_id}")
# 超时后强制重置会话状态
self._session_finished = True
self._session_started = False
self._current_session_id = None
# 尝试关闭WebSocket连接
if self.ws:
try:
await self.ws.close()
except:
pass
self.ws = None
except Exception as e:
logger.bind(tag=TAG).error(f"关闭会话时发生未知错误: {str(e)}")
# 发生未知错误时也重置会话状态
self._session_finished = True
self._session_started = False
self._current_session_id = None
@@ -527,3 +720,20 @@ class TTSProvider(TTSProviderBase):
def wav_to_opus_data_audio_raw(self, raw_data_var, is_end=False):
opus_datas = self.opus_encoder.encode_pcm_to_opus(raw_data_var, is_end)
return opus_datas
async def _handle_connection_error(self):
"""处理连接错误"""
if self._reconnect_attempts < self._max_reconnect_attempts:
self._reconnect_attempts += 1
logger.bind(tag=TAG).warning(
f"尝试重新连接 (第{self._reconnect_attempts}次)"
)
try:
await self._ensure_connection()
return True
except Exception as e:
logger.bind(tag=TAG).error(f"重新连接失败: {str(e)}")
return False
else:
logger.bind(tag=TAG).error("达到最大重连次数,放弃重连")
return False
+21 -1
View File
@@ -1484,6 +1484,23 @@
if (message.text && message.text !== '😊') {
addMessage(message.text);
}
}else if (message.type === 'mcp') {
const payload = message.payload || {};
log(`服务器下发: ${JSON.stringify(message)}`, 'info');
if (payload) {
// 模拟小智客户端行为
if(payload.method === 'tools/list'){
const replay_message = JSON.stringify({"session_id":"","type":"mcp","payload":{"jsonrpc":"2.0","id":2,"result":{"tools":[{"name":"self.get_device_status","description":"Provides the real-time information of the device, including the current status of the audio speaker, screen, battery, network, etc.\nUse this tool for: \n1. Answering questions about current condition (e.g. what is the current volume of the audio speaker?)\n2. As the first step to control the device (e.g. turn up / down the volume of the audio speaker, etc.)","inputSchema":{"type":"object","properties":{}}},{"name":"self.audio_speaker.set_volume","description":"Set the volume of the audio speaker. If the current volume is unknown, you must call `self.get_device_status` tool first and then call this tool.","inputSchema":{"type":"object","properties":{"volume":{"type":"integer","minimum":0,"maximum":100}},"required":["volume"]}},{"name":"self.screen.set_brightness","description":"Set the brightness of the screen.","inputSchema":{"type":"object","properties":{"brightness":{"type":"integer","minimum":0,"maximum":100}},"required":["brightness"]}},{"name":"self.screen.set_theme","description":"Set the theme of the screen. The theme can be 'light' or 'dark'.","inputSchema":{"type":"object","properties":{"theme":{"type":"string"}},"required":["theme"]}}]}}})
websocket.send(replay_message);
log(`回复MCP消息: ${replay_message}`, 'info');
} else if(payload.method === 'tools/call'){
// 模拟回复
const replay_message = JSON.stringify({"session_id":"9f261599","type":"mcp","payload":{"jsonrpc":"2.0","id": payload.id,"result":{"content":[{"type":"text","text":"true"}],"isError":false}}})
websocket.send(replay_message);
log(`回复MCP消息: ${replay_message}`, 'info');
}
}
} else {
// 未知消息类型
log(`未知消息类型: ${message.type}`, 'info');
@@ -1523,7 +1540,10 @@
device_id: config.deviceId,
device_name: config.deviceName,
device_mac: config.deviceMac,
token: config.token
token: config.token,
features: {
mcp: true
}
};
log('发送hello握手消息', 'info');