Merge branch 'main' into py_test_Memory_powermem

main/xiaozhi-server/core/providers/asr/aliyun_stream.py

@@ -13,6 +13,10 @@ from datetime import datetime
 from config.logger import setup_logging
 from core.providers.asr.base import ASRProviderBase
 from core.providers.asr.dto.dto import InterfaceType
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
 
 TAG = __name__
 logger = setup_logging()
@@ -146,7 +150,7 @@ class ASRProvider(ASRProviderBase):
                 logger.bind(tag=TAG).warning(f"发送音频失败: {str(e)}")
                 await self._cleanup()
 
-    async def _start_recognition(self, conn):
+    async def _start_recognition(self, conn: "ConnectionHandler"):
         """开始识别会话"""
         if self._is_token_expired():
             self._refresh_token()
@@ -192,7 +196,7 @@ class ASRProvider(ASRProviderBase):
         await self.asr_ws.send(json.dumps(start_request, ensure_ascii=False))
         logger.bind(tag=TAG).debug("已发送开始请求，等待服务器准备...")
 
-    async def _forward_results(self, conn):
+    async def _forward_results(self, conn: "ConnectionHandler"):
         """转发识别结果"""
         try:
             while not conn.stop_event.is_set():

main/xiaozhi-server/core/providers/asr/aliyunbl_stream.py

@@ -3,7 +3,11 @@ import uuid
 import asyncio
 import websockets
 import opuslib_next
-from typing import List
+from typing import List, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
+
 from config.logger import setup_logging
 from core.providers.asr.base import ASRProviderBase
 from core.providers.asr.dto.dto import InterfaceType
@@ -74,7 +78,7 @@ class ASRProvider(ASRProviderBase):
                 logger.bind(tag=TAG).warning(f"发送音频失败: {str(e)}")
                 await self._cleanup()
 
-    async def _start_recognition(self, conn):
+    async def _start_recognition(self, conn: "ConnectionHandler"):
         """开始识别会话"""
         try:
             # 如果为手动模式,设置超时时长为最大值
@@ -154,7 +158,7 @@ class ASRProvider(ASRProviderBase):
 
         return message
 
-    async def _forward_results(self, conn):
+    async def _forward_results(self, conn: "ConnectionHandler"):
         """转发识别结果"""
         try:
             while not conn.stop_event.is_set():

main/xiaozhi-server/core/providers/asr/base.py

@@ -5,21 +5,25 @@ import uuid
 import json
 import time
 import queue
+import shutil
 import asyncio
+import tempfile
 import traceback
 import threading
-import shutil
 import opuslib_next
 
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
-from typing import Optional, Tuple, List, NamedTuple
 from core.providers.asr.dto.dto import InterfaceType
 from core.handle.receiveAudioHandle import startToChat
 from core.handle.reportHandle import enqueue_asr_report
 from core.utils.util import remove_punctuation_and_length
 from core.handle.receiveAudioHandle import handleAudioMessage
-import tempfile
+from typing import Optional, Tuple, List, NamedTuple, TYPE_CHECKING
+
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
 
 TAG = __name__
 logger = setup_logging()
@@ -30,14 +34,14 @@ class ASRProviderBase(ABC):
         pass
 
     # 打开音频通道
-    async def open_audio_channels(self, conn):
+    async def open_audio_channels(self, conn: "ConnectionHandler"):
         conn.asr_priority_thread = threading.Thread(
             target=self.asr_text_priority_thread, args=(conn,), daemon=True
         )
         conn.asr_priority_thread.start()
 
     # 有序处理ASR音频
-    def asr_text_priority_thread(self, conn):
+    def asr_text_priority_thread(self, conn: "ConnectionHandler"):
         while not conn.stop_event.is_set():
             try:
                 message = conn.asr_audio_queue.get(timeout=1)
@@ -55,7 +59,7 @@ class ASRProviderBase(ABC):
                 continue
 
     # 接收音频
-    async def receive_audio(self, conn, audio, audio_have_voice):
+    async def receive_audio(self, conn: "ConnectionHandler", audio, audio_have_voice):
         if conn.client_listen_mode == "manual":
             # 手动模式：缓存音频用于ASR识别
             conn.asr_audio.append(audio)
@@ -77,7 +81,7 @@ class ASRProviderBase(ABC):
                     await self.handle_voice_stop(conn, asr_audio_task)
 
     # 处理语音停止
-    async def handle_voice_stop(self, conn, asr_audio_task: List[bytes]):
+    async def handle_voice_stop(self, conn: "ConnectionHandler", asr_audio_task: List[bytes]):
         """并行处理ASR和声纹识别"""
         try:
             total_start_time = time.monotonic()

main/xiaozhi-server/core/providers/asr/doubao_stream.py

@@ -7,6 +7,10 @@ import opuslib_next
 from core.providers.asr.base import ASRProviderBase
 from config.logger import setup_logging
 from core.providers.asr.dto.dto import InterfaceType
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
 
 TAG = __name__
 logger = setup_logging()
@@ -34,7 +38,9 @@ class ASRProvider(ASRProviderBase):
 
         # 火山引擎ASR配置
         enable_multilingual = config.get("enable_multilingual", False)
-        self.enable_multilingual = False if str(enable_multilingual).lower() == 'false' else True
+        self.enable_multilingual = (
+            False if str(enable_multilingual).lower() == "false" else True
+        )
         if self.enable_multilingual:
             self.ws_url = "wss://openspeech.bytedance.com/api/v3/sauc/bigmodel_nostream"
         else:
@@ -59,10 +65,10 @@ class ASRProvider(ASRProviderBase):
     async def open_audio_channels(self, conn):
         await super().open_audio_channels(conn)
 
-    async def receive_audio(self, conn, audio, audio_have_voice):
+    async def receive_audio(self, conn: "ConnectionHandler", audio, audio_have_voice):
         # 先调用父类方法处理基础逻辑
         await super().receive_audio(conn, audio, audio_have_voice)
-
+        
         # 如果本次有声音，且之前没有建立连接
         if audio_have_voice and self.asr_ws is None and not self.is_processing:
             try:
@@ -151,7 +157,7 @@ class ASRProvider(ASRProviderBase):
             except Exception as e:
                 logger.bind(tag=TAG).info(f"发送音频数据时发生错误: {e}")
 
-    async def _forward_asr_results(self, conn):
+    async def _forward_asr_results(self, conn: "ConnectionHandler"):
         try:
             while self.asr_ws and not conn.stop_event.is_set():
                 # 获取当前连接的音频数据
@@ -172,8 +178,9 @@ class ASRProvider(ASRProviderBase):
                             utterances = payload["result"].get("utterances", [])
                             # 检查duration和空文本的情况
                             if (
-                                not self.enable_multilingual # 注意：多语种模式不返回中间结果，需要等待最终结果
-                                and payload.get("audio_info", {}).get("duration", 0) > 2000
+                                not self.enable_multilingual  # 注意：多语种模式不返回中间结果，需要等待最终结果
+                                and payload.get("audio_info", {}).get("duration", 0)
+                                > 2000
                                 and not utterances
                                 and not payload["result"].get("text")
                                 and conn.client_listen_mode != "manual"
@@ -218,7 +225,9 @@ class ASRProvider(ASRProviderBase):
                                         # 自动模式下直接覆盖
                                         self.text = current_text
                                         if len(audio_data) > 15:  # 确保有足够音频数据
-                                            await self.handle_voice_stop(conn, audio_data)
+                                            await self.handle_voice_stop(
+                                                conn, audio_data
+                                            )
                                     break
                         elif "error" in payload:
                             error_msg = payload.get("error", "未知错误")
@@ -260,7 +269,9 @@ class ASRProvider(ASRProviderBase):
             try:
                 # 发送结束标记的音频帧（gzip压缩的空数据）
                 empty_payload = gzip.compress(b"")
-                last_audio_request = bytearray(self.generate_last_audio_default_header())
+                last_audio_request = bytearray(
+                    self.generate_last_audio_default_header()
+                )
                 last_audio_request.extend(len(empty_payload).to_bytes(4, "big"))
                 last_audio_request.extend(empty_payload)
                 await self.asr_ws.send(last_audio_request)
@@ -406,9 +417,9 @@ class ASRProvider(ASRProviderBase):
                 pass
             self.forward_task = None
         self.is_processing = False
-        
+
         # 显式释放decoder资源
-        if hasattr(self, 'decoder') and self.decoder is not None:
+        if hasattr(self, "decoder") and self.decoder is not None:
             try:
                 del self.decoder
                 self.decoder = None

main/xiaozhi-server/core/providers/asr/xunfei_stream.py

@@ -9,7 +9,10 @@ import gc
 from time import mktime
 from datetime import datetime
 from urllib.parse import urlencode
-from typing import List
+from typing import List, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
 from config.logger import setup_logging
 from wsgiref.handlers import format_date_time
 from core.providers.asr.base import ASRProviderBase
@@ -94,10 +97,10 @@ class ASRProvider(ASRProviderBase):
         url = url + "?" + urlencode(v)
         return url
 
-    async def open_audio_channels(self, conn):
+    async def open_audio_channels(self, conn: "ConnectionHandler"):
         await super().open_audio_channels(conn)
 
-    async def receive_audio(self, conn, audio, audio_have_voice):
+    async def receive_audio(self, conn: "ConnectionHandler", audio, audio_have_voice):
         # 先调用父类方法处理基础逻辑
         await super().receive_audio(conn, audio, audio_have_voice)
 
@@ -119,7 +122,7 @@ class ASRProvider(ASRProviderBase):
                 logger.bind(tag=TAG).warning(f"发送音频数据时发生错误: {e}")
                 await self._cleanup()
 
-    async def _start_recognition(self, conn):
+    async def _start_recognition(self, conn: "ConnectionHandler"):
         """开始识别会话"""
         try:
             self.is_processing = True
@@ -189,7 +192,7 @@ class ASRProvider(ASRProviderBase):
 
         await self.asr_ws.send(json.dumps(frame_data, ensure_ascii=False))
 
-    async def _forward_results(self, conn):
+    async def _forward_results(self, conn: "ConnectionHandler"):
         """转发识别结果"""
         try:
             while not conn.stop_event.is_set():
@@ -253,7 +256,9 @@ class ASRProvider(ASRProviderBase):
             await self._cleanup()
             conn.reset_audio_states()
 
-    async def handle_voice_stop(self, conn, asr_audio_task: List[bytes]):
+    async def handle_voice_stop(
+        self, conn: "ConnectionHandler", asr_audio_task: List[bytes]
+    ):
         """处理语音停止，发送最后一帧并处理识别结果"""
         try:
             # 先发送最后一帧表示音频结束
@@ -338,7 +343,7 @@ class ASRProvider(ASRProviderBase):
         self.is_processing = False
 
         # 显式释放decoder资源
-        if hasattr(self, 'decoder') and self.decoder is not None:
+        if hasattr(self, "decoder") and self.decoder is not None:
             try:
                 del self.decoder
                 self.decoder = None

main/xiaozhi-server/core/providers/intent/intent_llm/intent_llm.py

@@ -1,4 +1,7 @@
-from typing import List, Dict
+from typing import List, Dict, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
 from ..base import IntentProviderBase
 from plugins_func.functions.play_music import initialize_music_handler
 from config.logger import setup_logging
@@ -129,7 +132,9 @@ class IntentProvider(IntentProviderBase):
             logger.bind(tag=TAG).error(f"Error in generating reply result: {e}")
             return get_system_error_response(self.config)
 
-    async def detect_intent(self, conn, dialogue_history: List[Dict], text: str) -> str:
+    async def detect_intent(
+        self, conn: "ConnectionHandler", dialogue_history: List[Dict], text: str
+    ) -> str:
         if not self.llm:
             raise ValueError("LLM provider not set")
         if conn.func_handler is None:

main/xiaozhi-server/core/providers/tools/device_iot/iot_handler.py

@@ -3,12 +3,16 @@
 import asyncio
 from config.logger import setup_logging
 from .iot_descriptor import IotDescriptor
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
 
 TAG = __name__
 logger = setup_logging()
 
 
-async def handleIotDescriptors(conn, descriptors):
+async def handleIotDescriptors(conn: "ConnectionHandler", descriptors):
     """处理物联网描述"""
     wait_max_time = 5
     while (
@@ -61,7 +65,7 @@ async def handleIotDescriptors(conn, descriptors):
         conn.func_handler.current_support_functions()
 
 
-async def handleIotStatus(conn, states):
+async def handleIotStatus(conn: "ConnectionHandler", states):
     """处理物联网状态"""
     for state in states:
         for key, value in conn.iot_descriptors.items():

main/xiaozhi-server/core/providers/tools/device_mcp/mcp_executor.py

@@ -1,6 +1,9 @@
 """设备端MCP工具执行器"""
 
-from typing import Dict, Any
+from typing import Dict, Any, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
 from ..base import ToolType, ToolDefinition, ToolExecutor
 from plugins_func.register import Action, ActionResponse
 from .mcp_handler import call_mcp_tool
@@ -13,7 +16,7 @@ class DeviceMCPExecutor(ToolExecutor):
         self.conn = conn
 
     async def execute(
-        self, conn, tool_name: str, arguments: Dict[str, Any]
+        self, conn: "ConnectionHandler", tool_name: str, arguments: Dict[str, Any]
     ) -> ActionResponse:
         """执行设备端MCP工具"""
         if not hasattr(conn, "mcp_client") or not conn.mcp_client:

main/xiaozhi-server/core/providers/tools/device_mcp/mcp_handler.py

@@ -7,6 +7,10 @@ from concurrent.futures import Future
 from core.utils.util import get_vision_url, sanitize_tool_name
 from core.utils.auth import AuthToken
 from config.logger import setup_logging
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
 
 TAG = __name__
 logger = setup_logging()
@@ -96,7 +100,7 @@ class MCPClient:
                 self.call_results.pop(id)
 
 
-async def send_mcp_message(conn, payload: dict):
+async def send_mcp_message(conn: "ConnectionHandler", payload: dict):
     """Helper to send MCP messages, encapsulating common logic."""
     if not conn.features.get("mcp"):
         logger.bind(tag=TAG).warning("客户端不支持MCP，无法发送MCP消息")
@@ -111,7 +115,9 @@ async def send_mcp_message(conn, payload: dict):
         logger.bind(tag=TAG).error(f"发送MCP消息失败: {e}")
 
 
-async def handle_mcp_message(conn, mcp_client: MCPClient, payload: dict):
+async def handle_mcp_message(
+    conn: "ConnectionHandler", mcp_client: MCPClient, payload: dict
+):
     """处理MCP消息,包括初始化、工具列表和工具调用响应等"""
     logger.bind(tag=TAG).debug(f"处理MCP消息: {str(payload)[:100]}")
 
@@ -229,7 +235,7 @@ async def handle_mcp_message(conn, mcp_client: MCPClient, payload: dict):
             )
 
 
-async def send_mcp_initialize_message(conn):
+async def send_mcp_initialize_message(conn: "ConnectionHandler"):
     """发送MCP初始化消息"""
 
     vision_url = get_vision_url(conn.config)
@@ -264,7 +270,7 @@ async def send_mcp_initialize_message(conn):
     await send_mcp_message(conn, payload)
 
 
-async def send_mcp_tools_list_request(conn):
+async def send_mcp_tools_list_request(conn: "ConnectionHandler"):
     """发送MCP工具列表请求"""
     payload = {
         "jsonrpc": "2.0",
@@ -275,7 +281,7 @@ async def send_mcp_tools_list_request(conn):
     await send_mcp_message(conn, payload)
 
 
-async def send_mcp_tools_list_continue_request(conn, cursor: str):
+async def send_mcp_tools_list_continue_request(conn: "ConnectionHandler", cursor: str):
     """发送带有cursor的MCP工具列表请求"""
     payload = {
         "jsonrpc": "2.0",
@@ -288,7 +294,11 @@ async def send_mcp_tools_list_continue_request(conn, cursor: str):
 
 
 async def call_mcp_tool(
-    conn, mcp_client: MCPClient, tool_name: str, args: str = "{}", timeout: int = 30
+    conn: "ConnectionHandler",
+    mcp_client: MCPClient,
+    tool_name: str,
+    args: str = "{}",
+    timeout: int = 30,
 ):
     """
     调用指定的工具，并等待响应

main/xiaozhi-server/core/providers/tools/server_plugins/plugin_executor.py

@@ -1,6 +1,9 @@
 """服务端插件工具执行器"""
 
-from typing import Dict, Any
+from typing import Dict, Any, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from core.connection import ConnectionHandler
 from ..base import ToolType, ToolDefinition, ToolExecutor
 from plugins_func.register import all_function_registry, Action, ActionResponse
 
@@ -8,12 +11,12 @@ from plugins_func.register import all_function_registry, Action, ActionResponse
 class ServerPluginExecutor(ToolExecutor):
     """服务端插件工具执行器"""
 
-    def __init__(self, conn):
+    def __init__(self, conn: "ConnectionHandler"):
         self.conn = conn
         self.config = conn.config
 
     async def execute(
-        self, conn, tool_name: str, arguments: Dict[str, Any]
+        self, conn: "ConnectionHandler", tool_name: str, arguments: Dict[str, Any]
     ) -> ActionResponse:
         """执行服务端插件工具"""
         func_item = all_function_registry.get(tool_name)