Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-22 07:03:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: 为多个模块添加类型注解以增强代码可读性

Browse Source 
为 ConnectionHandler 相关的函数参数添加类型注解，使用 TYPE_CHECKING 避免循环导入。主要修改包括：
- 在 abortHandle、textHandle 等处理模块中为 conn 参数添加 ConnectionHandler 类型注解
- 在 websocket_server、connection 等核心模块中为方法参数添加类型注解
- 在 plugins_func 下的多个功能模块中为函数参数添加类型注解
- 在 providers 相关模块中为工具执行器和方法添加类型注解
- 统一代码格式，如将单引号字符串改为双引号

Fixes #2034
This commit is contained in:
huozaimengli
2026-01-25 17:47:52 +08:00
parent 275102f5b7
commit 4b573fb4e2
36 changed files with 338 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/connection.py
+2 -2
View File
@@ -76,7 +76,7 @@ class ConnectionHandler:
self.read_config_from_api = self.config.get("read_config_from_api", False)
self.websocket = None
self.websocket: websockets.ServerConnection | None = None
self.headers = None
self.device_id = None
self.client_ip = None
@@ -167,7 +167,7 @@ class ConnectionHandler:
# 初始化提示词管理器
self.prompt_manager = PromptManager(self.config, self.logger)
async def handle_connection(self, ws):
async def handle_connection(self, ws: websockets.ServerConnection):
try:
# 获取运行中的事件循环（必须在异步上下文中）
self.loop = asyncio.get_running_loop()
main/xiaozhi-server/core/handle/abortHandle.py
+4 -1
View File
@@ -1,9 +1,12 @@
import json
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
async def handleAbortMessage(conn):
async def handleAbortMessage(conn: "ConnectionHandler"):
conn.logger.bind(tag=TAG).info("Abort message received")
# 设置成打断状态，会自动打断llm、tts任务
conn.client_abort = True
main/xiaozhi-server/core/handle/helloHandle.py
+8 -7
View File
@@ -3,16 +3,17 @@ import json
import uuid
import random
import asyncio
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.utils.dialogue import Message
from core.utils.util import audio_to_data
from core.providers.tts.dto.dto import SentenceType
from core.utils.wakeup_word import WakeupWordsConfig
from core.handle.sendAudioHandle import sendAudioMessage, send_tts_message
from core.utils.util import remove_punctuation_and_length, opus_datas_to_wav_bytes
from core.providers.tools.device_mcp import (
MCPClient,
send_mcp_initialize_message
)
from core.providers.tools.device_mcp import MCPClient, send_mcp_initialize_message
TAG = __name__
@@ -38,7 +39,7 @@ wakeup_words_config = WakeupWordsConfig()
_wakeup_response_lock = asyncio.Lock()
async def handleHelloMessage(conn, msg_json):
async def handleHelloMessage(conn: "ConnectionHandler", msg_json):
"""处理hello消息"""
audio_params = msg_json.get("audio_params")
if audio_params:
@@ -59,7 +60,7 @@ async def handleHelloMessage(conn, msg_json):
await conn.websocket.send(json.dumps(conn.welcome_msg))
async def checkWakeupWords(conn, text):
async def checkWakeupWords(conn: "ConnectionHandler", text):
enable_wakeup_words_response_cache = conn.config[
"enable_wakeup_words_response_cache"
]
@@ -120,7 +121,7 @@ async def checkWakeupWords(conn, text):
return True
async def wakeupWordsResponse(conn):
async def wakeupWordsResponse(conn: "ConnectionHandler"):
if not conn.tts:
return
main/xiaozhi-server/core/handle/intentHandler.py
+20 -12
View File
@@ -1,6 +1,10 @@
import json
import uuid
import asyncio
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.utils.dialogue import Message
from core.providers.tts.dto.dto import ContentType
from core.handle.helloHandle import checkWakeupWords
@@ -12,10 +16,10 @@ from core.providers.tts.dto.dto import TTSMessageDTO, SentenceType
TAG = __name__
async def handle_user_intent(conn, text):
async def handle_user_intent(conn: "ConnectionHandler", text):
# 预处理输入文本，处理可能的JSON格式
try:
if text.strip().startswith('{') and text.strip().endswith('}'):
if text.strip().startswith("{") and text.strip().endswith("}"):
parsed_data = json.loads(text)
if isinstance(parsed_data, dict) and "content" in parsed_data:
text = parsed_data["content"] # 提取content用于意图分析
@@ -45,7 +49,7 @@ async def handle_user_intent(conn, text):
return await process_intent_result(conn, intent_result, text)
async def check_direct_exit(conn, text):
async def check_direct_exit(conn: "ConnectionHandler", text):
"""检查是否有明确的退出命令"""
_, text = remove_punctuation_and_length(text)
cmd_exit = conn.cmd_exit
@@ -58,7 +62,7 @@ async def check_direct_exit(conn, text):
return False
async def analyze_intent_with_llm(conn, text):
async def analyze_intent_with_llm(conn: "ConnectionHandler", text):
"""使用LLM分析用户意图"""
if not hasattr(conn, "intent") or not conn.intent:
conn.logger.bind(tag=TAG).warning("意图识别服务未初始化")
@@ -75,7 +79,9 @@ async def analyze_intent_with_llm(conn, text):
return None
async def process_intent_result(conn, intent_result, original_text):
async def process_intent_result(
conn: "ConnectionHandler", intent_result, original_text
):
"""处理意图识别结果"""
try:
# 尝试将结果解析为JSON
@@ -94,24 +100,26 @@ async def process_intent_result(conn, intent_result, original_text):
if function_name == "result_for_context":
await send_stt_message(conn, original_text)
conn.client_abort = False
def process_context_result():
conn.dialogue.put(Message(role="user", content=original_text))
from core.utils.current_time import get_current_time_info
current_time, today_date, today_weekday, lunar_date = get_current_time_info()
current_time, today_date, today_weekday, lunar_date = (
get_current_time_info()
)
# 构建带上下文的基础提示
context_prompt = f"""当前时间：{current_time}
今天日期：{today_date} ({today_weekday})
今天农历：{lunar_date}
请根据以上信息回答用户的问题：{original_text}"""
response = conn.intent.replyResult(context_prompt, original_text)
speak_txt(conn, response)
conn.executor.submit(process_context_result)
return True
@@ -188,7 +196,7 @@ async def process_intent_result(conn, intent_result, original_text):
return False
def speak_txt(conn, text):
def speak_txt(conn: "ConnectionHandler", text):
# 记录文本
conn.tts_MessageText = text
main/xiaozhi-server/core/handle/receiveAudioHandle.py
+10 -6
View File
@@ -1,6 +1,10 @@
import time
import json
import asyncio
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.utils.util import audio_to_data
from core.handle.abortHandle import handleAbortMessage
from core.handle.intentHandler import handle_user_intent
@@ -10,7 +14,7 @@ from core.handle.sendAudioHandle import send_stt_message, SentenceType
TAG = __name__
async def handleAudioMessage(conn, audio):
async def handleAudioMessage(conn: "ConnectionHandler", audio):
# 当前片段是否有人说话
have_voice = conn.vad.is_vad(conn, audio)
# 如果设备刚刚被唤醒，短暂忽略VAD检测
@@ -31,13 +35,13 @@ async def handleAudioMessage(conn, audio):
await conn.asr.receive_audio(conn, audio, have_voice)
async def resume_vad_detection(conn):
async def resume_vad_detection(conn: "ConnectionHandler"):
# 等待2秒后恢复VAD检测
await asyncio.sleep(2)
conn.just_woken_up = False
async def startToChat(conn, text):
async def startToChat(conn: "ConnectionHandler", text):
# 检查输入是否是JSON格式（包含说话人信息）
speaker_name = None
language_tag = None
@@ -97,7 +101,7 @@ async def startToChat(conn, text):
conn.executor.submit(conn.chat, actual_text)
async def no_voice_close_connect(conn, have_voice):
async def no_voice_close_connect(conn: "ConnectionHandler", have_voice):
if have_voice:
conn.last_activity_time = time.time() * 1000
return
@@ -124,7 +128,7 @@ async def no_voice_close_connect(conn, have_voice):
await startToChat(conn, prompt)
async def max_out_size(conn):
async def max_out_size(conn: "ConnectionHandler"):
# 播放超出最大输出字数的提示
conn.client_abort = False
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！"
@@ -135,7 +139,7 @@ async def max_out_size(conn):
conn.close_after_chat = True
async def check_bind_device(conn):
async def check_bind_device(conn: "ConnectionHandler"):
if conn.bind_code:
# 确保bind_code是6位数字
if len(conn.bind_code) != 6:
main/xiaozhi-server/core/handle/reportHandle.py
+8 -4
View File
@@ -11,13 +11,17 @@ TTS上报功能已集成到ConnectionHandler类中。
import time
import opuslib_next
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from config.manage_api_client import report as manage_report
TAG = __name__
async def report(conn, type, text, opus_data, report_time):
async def report(conn: "ConnectionHandler", type, text, opus_data, report_time):
"""执行聊天记录上报操作
Args:
@@ -45,7 +49,7 @@ async def report(conn, type, text, opus_data, report_time):
conn.logger.bind(tag=TAG).error(f"聊天记录上报失败: {e}")
def opus_to_wav(conn, opus_data):
def opus_to_wav(conn: "ConnectionHandler", opus_data):
"""将Opus数据转换为WAV格式的字节流
Args:
@@ -100,7 +104,7 @@ def opus_to_wav(conn, opus_data):
conn.logger.bind(tag=TAG).debug(f"释放decoder资源时出错: {e}")
def enqueue_tts_report(conn, text, opus_data):
def enqueue_tts_report(conn: "ConnectionHandler", text, opus_data):
if not conn.read_config_from_api or conn.need_bind or not conn.report_tts_enable:
return
if conn.chat_history_conf == 0:
@@ -128,7 +132,7 @@ def enqueue_tts_report(conn, text, opus_data):
conn.logger.bind(tag=TAG).error(f"加入TTS上报队列失败: {text}, {e}")
def enqueue_asr_report(conn, text, opus_data):
def enqueue_asr_report(conn: "ConnectionHandler", text, opus_data):
if not conn.read_config_from_api or conn.need_bind or not conn.report_asr_enable:
return
if conn.chat_history_conf == 0:
main/xiaozhi-server/core/handle/sendAudioHandle.py
+20 -10
View File
@@ -1,6 +1,10 @@
import json
import time
import asyncio
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.utils import textUtils
from core.utils.util import audio_to_data
from core.providers.tts.dto.dto import SentenceType
@@ -13,7 +17,7 @@ AUDIO_FRAME_DURATION = 60
PRE_BUFFER_COUNT = 5
async def sendAudioMessage(conn, sentenceType, audios, text):
async def sendAudioMessage(conn: "ConnectionHandler", sentenceType, audios, text):
if conn.tts.tts_audio_first_sentence:
conn.logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
conn.tts.tts_audio_first_sentence = False
@@ -47,7 +51,7 @@ async def sendAudioMessage(conn, sentenceType, audios, text):
await conn.close()
async def _wait_for_audio_completion(conn):
async def _wait_for_audio_completion(conn: "ConnectionHandler"):
"""
等待音频队列清空并等待预缓冲包播放完成
@@ -70,7 +74,9 @@ async def _wait_for_audio_completion(conn):
conn.logger.bind(tag=TAG).debug("音频发送完成")
async def _send_to_mqtt_gateway(conn, opus_packet, timestamp, sequence):
async def _send_to_mqtt_gateway(
conn: "ConnectionHandler", opus_packet, timestamp, sequence
):
"""
发送带16字节头部的opus数据包给mqtt_gateway
Args:
@@ -92,7 +98,9 @@ async def _send_to_mqtt_gateway(conn, opus_packet, timestamp, sequence):
await conn.websocket.send(complete_packet)
async def sendAudio(conn, audios, frame_duration=AUDIO_FRAME_DURATION):
async def sendAudio(
conn: "ConnectionHandler", audios, frame_duration=AUDIO_FRAME_DURATION
):
"""
发送音频包，使用 AudioRateController 进行精确的流量控制
@@ -121,7 +129,9 @@ async def sendAudio(conn, audios, frame_duration=AUDIO_FRAME_DURATION):
)
def _get_or_create_rate_controller(conn, frame_duration, is_single_packet):
def _get_or_create_rate_controller(
conn: "ConnectionHandler", frame_duration, is_single_packet
):
"""
获取或创建 RateController 和 flow_control
@@ -177,7 +187,7 @@ def _get_or_create_rate_controller(conn, frame_duration, is_single_packet):
return conn.audio_rate_controller, conn.audio_flow_control
def _start_background_sender(conn, rate_controller, flow_control):
def _start_background_sender(conn: "ConnectionHandler", rate_controller, flow_control):
"""
启动后台发送循环任务
@@ -201,7 +211,7 @@ def _start_background_sender(conn, rate_controller, flow_control):
async def _send_audio_with_rate_control(
conn, audio_list, rate_controller, flow_control, send_delay
conn: "ConnectionHandler", audio_list, rate_controller, flow_control, send_delay
):
"""
使用 rate_controller 发送音频包
@@ -233,7 +243,7 @@ async def _send_audio_with_rate_control(
rate_controller.add_audio(packet)
async def _do_send_audio(conn, opus_packet, flow_control):
async def _do_send_audio(conn: "ConnectionHandler", opus_packet, flow_control):
"""
执行实际的音频发送
"""
@@ -254,7 +264,7 @@ async def _do_send_audio(conn, opus_packet, flow_control):
flow_control["sequence"] = sequence + 1
async def send_tts_message(conn, state, text=None):
async def send_tts_message(conn: "ConnectionHandler", state, text=None):
"""发送 TTS 状态消息"""
if text is None and state == "sentence_start":
return
@@ -281,7 +291,7 @@ async def send_tts_message(conn, state, text=None):
await conn.websocket.send(json.dumps(message))
async def send_stt_message(conn, text):
async def send_stt_message(conn: "ConnectionHandler", text):
"""发送 STT 状态消息"""
end_prompt_str = conn.config.get("end_prompt", {}).get("prompt")
if end_prompt_str and end_prompt_str == text:
main/xiaozhi-server/core/handle/textHandle.py
+6 -1
View File
@@ -1,3 +1,7 @@
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.handle.textMessageHandlerRegistry import TextMessageHandlerRegistry
from core.handle.textMessageProcessor import TextMessageProcessor
@@ -9,6 +13,7 @@ message_registry = TextMessageHandlerRegistry()
# 创建全局消息处理器实例
message_processor = TextMessageProcessor(message_registry)
async def handleTextMessage(conn, message):
async def handleTextMessage(conn: "ConnectionHandler", message):
"""处理文本消息"""
await message_processor.process_message(conn, message)
main/xiaozhi-server/core/handle/textHandler/helloMessageHandler.py
+5 -3
View File
@@ -1,5 +1,7 @@
from typing import Dict, Any
from typing import Dict, Any, TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.handle.helloHandle import handleHelloMessage
from core.handle.textMessageHandler import TextMessageHandler
from core.handle.textMessageType import TextMessageType
@@ -12,5 +14,5 @@ class HelloTextMessageHandler(TextMessageHandler):
def message_type(self) -> TextMessageType:
return TextMessageType.HELLO
async def handle(self, conn, msg_json: Dict[str, Any]) -> None:
await handleHelloMessage(conn, msg_json)
async def handle(self, conn: "ConnectionHandler", msg_json: Dict[str, Any]) -> None:
await handleHelloMessage(conn, msg_json)
main/xiaozhi-server/core/handle/textHandler/iotMessageHandler.py
+4 -2
View File
@@ -1,6 +1,8 @@
import asyncio
from typing import Dict, Any
from typing import Dict, Any, TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.handle.textMessageHandler import TextMessageHandler
from core.handle.textMessageType import TextMessageType
from core.providers.tools.device_iot import handleIotStatus, handleIotDescriptors
@@ -13,7 +15,7 @@ class IotTextMessageHandler(TextMessageHandler):
def message_type(self) -> TextMessageType:
return TextMessageType.IOT
async def handle(self, conn, msg_json: Dict[str, Any]) -> None:
async def handle(self, conn: "ConnectionHandler", msg_json: Dict[str, Any]) -> None:
if "descriptors" in msg_json:
asyncio.create_task(handleIotDescriptors(conn, msg_json["descriptors"]))
if "states" in msg_json:
main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py
+5 -2
View File
@@ -1,6 +1,9 @@
import time
import asyncio
from typing import Dict, Any
from typing import Dict, Any, TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.handle.receiveAudioHandle import startToChat
from core.handle.reportHandle import enqueue_asr_report
@@ -19,7 +22,7 @@ class ListenTextMessageHandler(TextMessageHandler):
def message_type(self) -> TextMessageType:
return TextMessageType.LISTEN
async def handle(self, conn, msg_json: Dict[str, Any]) -> None:
async def handle(self, conn: "ConnectionHandler", msg_json: Dict[str, Any]) -> None:
if "mode" in msg_json:
conn.client_listen_mode = msg_json["mode"]
conn.logger.bind(tag=TAG).debug(
main/xiaozhi-server/core/handle/textHandler/mcpMessageHandler.py
+4 -2
View File
@@ -1,6 +1,8 @@
import asyncio
from typing import Dict, Any
from typing import Dict, Any, TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.handle.textMessageHandler import TextMessageHandler
from core.handle.textMessageType import TextMessageType
from core.providers.tools.device_mcp import handle_mcp_message
@@ -13,7 +15,7 @@ class McpTextMessageHandler(TextMessageHandler):
def message_type(self) -> TextMessageType:
return TextMessageType.MCP
async def handle(self, conn, msg_json: Dict[str, Any]) -> None:
async def handle(self, conn: "ConnectionHandler", msg_json: Dict[str, Any]) -> None:
if "payload" in msg_json:
asyncio.create_task(
handle_mcp_message(conn, conn.mcp_client, msg_json["payload"])
main/xiaozhi-server/core/handle/textMessageProcessor.py
+4 -1
View File
@@ -1,5 +1,8 @@
import json
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.handle.textMessageHandlerRegistry import TextMessageHandlerRegistry
TAG = __name__
@@ -11,7 +14,7 @@ class TextMessageProcessor:
def __init__(self, registry: TextMessageHandlerRegistry):
self.registry = registry
async def process_message(self, conn, message: str) -> None:
async def process_message(self, conn: "ConnectionHandler", message: str) -> None:
"""处理消息的主入口"""
try:
# 解析JSON消息
main/xiaozhi-server/core/providers/asr/aliyun_stream.py
+7 -3
View File
@@ -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()
@@ -125,7 +129,7 @@ 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):
# 初始化音频缓存
if not hasattr(conn, 'asr_audio_for_voiceprint'):
conn.asr_audio_for_voiceprint = []
@@ -154,7 +158,7 @@ class ASRProvider(ASRProviderBase):
logger.bind(tag=TAG).warning(f"发送音频失败: {str(e)}")
await self._cleanup(conn)
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()
@@ -200,7 +204,7 @@ 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
+8 -4
View File
@@ -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
@@ -51,7 +55,7 @@ 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):
# 初始化音频缓存
if not hasattr(conn, 'asr_audio_for_voiceprint'):
conn.asr_audio_for_voiceprint = []
@@ -82,7 +86,7 @@ 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
@@ -162,7 +166,7 @@ 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
+8 -5
View File
@@ -11,7 +11,10 @@ import threading
import opuslib_next
from abc import ABC, abstractmethod
from config.logger import setup_logging
from typing import Optional, Tuple, List
from typing import Optional, Tuple, List, TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.handle.receiveAudioHandle import startToChat
from core.handle.reportHandle import enqueue_asr_report
from core.utils.util import remove_punctuation_and_length
@@ -26,14 +29,14 @@ 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)
@@ -51,7 +54,7 @@ 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)
@@ -74,7 +77,7 @@ 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
+50 -22
View File
@@ -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:
@@ -59,16 +65,20 @@ 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):
conn.asr_audio.append(audio)
conn.asr_audio = conn.asr_audio[-10:]
# 存储音频数据
if not hasattr(conn, 'asr_audio_for_voiceprint'):
if not hasattr(conn, "asr_audio_for_voiceprint"):
conn.asr_audio_for_voiceprint = []
conn.asr_audio_for_voiceprint.append(audio)
# 当没有音频数据时处理完整语音片段
if conn.client_listen_mode != "manual" and not audio and len(conn.asr_audio_for_voiceprint) > 0:
if (
conn.client_listen_mode != "manual"
and not audio
and len(conn.asr_audio_for_voiceprint) > 0
):
await self.handle_voice_stop(conn, conn.asr_audio_for_voiceprint)
conn.asr_audio_for_voiceprint = []
@@ -160,11 +170,11 @@ 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
audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
audio_data = getattr(conn, "asr_audio_for_voiceprint", [])
try:
response = await self.asr_ws.recv()
result = self.parse_response(response)
@@ -181,8 +191,9 @@ 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"
@@ -200,8 +211,14 @@ class ASRProvider(ASRProviderBase):
if self.enable_multilingual:
continue
if conn.client_listen_mode == "manual" and conn.client_voice_stop and len(audio_data) > 0:
logger.bind(tag=TAG).debug("消息结束收到停止信号，触发处理")
if (
conn.client_listen_mode == "manual"
and conn.client_voice_stop
and len(audio_data) > 0
):
logger.bind(tag=TAG).debug(
"消息结束收到停止信号，触发处理"
)
await self.handle_voice_stop(conn, audio_data)
# 清理音频缓存
conn.asr_audio.clear()
@@ -223,9 +240,16 @@ class ASRProvider(ASRProviderBase):
self.text = current_text
# 在接收消息中途时收到停止信号
if conn.client_voice_stop and len(audio_data) > 0:
logger.bind(tag=TAG).debug("消息中途收到停止信号，触发处理")
await self.handle_voice_stop(conn, audio_data)
if (
conn.client_voice_stop
and len(audio_data) > 0
):
logger.bind(tag=TAG).debug(
"消息中途收到停止信号，触发处理"
)
await self.handle_voice_stop(
conn, audio_data
)
# 清理音频缓存
conn.asr_audio.clear()
conn.reset_vad_states()
@@ -235,7 +259,9 @@ class ASRProvider(ASRProviderBase):
self.text = current_text
conn.reset_vad_states()
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")
@@ -263,9 +289,9 @@ class ASRProvider(ASRProviderBase):
self.asr_ws = None
self.is_processing = False
if conn:
if hasattr(conn, 'asr_audio_for_voiceprint'):
if hasattr(conn, "asr_audio_for_voiceprint"):
conn.asr_audio_for_voiceprint = []
if hasattr(conn, 'asr_audio'):
if hasattr(conn, "asr_audio"):
conn.asr_audio = []
def stop_ws_connection(self):
@@ -280,7 +306,9 @@ 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)
@@ -426,9 +454,9 @@ 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
@@ -437,9 +465,9 @@ class ASRProvider(ASRProviderBase):
logger.bind(tag=TAG).debug(f"释放Doubao decoder资源时出错: {e}")
# 清理所有连接的音频缓冲区
if hasattr(self, '_connections'):
if hasattr(self, "_connections"):
for conn in self._connections.values():
if hasattr(conn, 'asr_audio_for_voiceprint'):
if hasattr(conn, "asr_audio_for_voiceprint"):
conn.asr_audio_for_voiceprint = []
if hasattr(conn, 'asr_audio'):
if hasattr(conn, "asr_audio"):
conn.asr_audio = []
main/xiaozhi-server/core/providers/asr/xunfei_stream.py
+13 -8
View File
@@ -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)
@@ -124,7 +127,7 @@ 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
@@ -194,7 +197,7 @@ 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():
@@ -232,7 +235,7 @@ class ASRProvider(ASRProviderBase):
if status == 2:
if conn.client_listen_mode == "manual":
audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
audio_data = getattr(conn, "asr_audio_for_voiceprint", [])
if len(audio_data) > 0:
logger.bind(tag=TAG).debug("收到最终识别结果，触发处理")
await self.handle_voice_stop(conn, audio_data)
@@ -270,7 +273,9 @@ class ASRProvider(ASRProviderBase):
if hasattr(conn, "asr_audio"):
conn.asr_audio = []
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
@@ -355,7 +360,7 @@ 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
+7 -2
View File
@@ -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
@@ -122,7 +125,9 @@ class IntentProvider(IntentProviderBase):
)
return llm_result
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
+6 -2
View File
@@ -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
+5 -2
View File
@@ -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
+16 -6
View File
@@ -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
+6 -3
View File
@@ -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)
main/xiaozhi-server/core/utils/prompt_manager.py
+13 -6
View File
@@ -4,7 +4,10 @@
"""
import os
from typing import Dict, Any
from typing import Dict, Any, TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from config.logger import setup_logging
from jinja2 import Template
@@ -59,9 +62,10 @@ class PromptManager:
self.cache_manager = cache_manager
self.CacheType = CacheType
# 初始化上下文源
from core.utils.context_provider import ContextDataProvider
self.context_provider = ContextDataProvider(config, self.logger)
self.context_data = {}
@@ -157,7 +161,7 @@ class PromptManager:
self.logger.bind(tag=TAG).error(f"获取位置信息失败: {e}")
return "未知位置"
def _get_weather_info(self, conn, location: str) -> str:
def _get_weather_info(self, conn: "ConnectionHandler", location: str) -> str:
"""获取天气信息"""
try:
# 先从缓存获取
@@ -203,14 +207,17 @@ class PromptManager:
):
# 获取天气信息（使用全局缓存）
self._get_weather_info(conn, local_address)
# 获取配置的上下文数据
if hasattr(conn, "device_id") and conn.device_id:
if self.base_prompt_template and "dynamic_context" in self.base_prompt_template:
if (
self.base_prompt_template
and "dynamic_context" in self.base_prompt_template
):
self.context_data = self.context_provider.fetch_all(conn.device_id)
else:
self.context_data = ""
self.logger.bind(tag=TAG).debug(f"上下文信息更新完成")
except Exception as e:
main/xiaozhi-server/core/utils/textUtils.py
+6 -2
View File
@@ -1,4 +1,8 @@
import json
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
EMOJI_MAP = {
@@ -77,7 +81,7 @@ def is_punctuation_or_emoji(char):
return is_emoji(char)
async def get_emotion(conn, text):
async def get_emotion(conn: "ConnectionHandler", text):
"""获取文本内的情绪消息"""
emoji = "🙂"
emotion = "happy"
@@ -110,4 +114,4 @@ def is_emoji(char):
def check_emoji(text):
"""去除文本中的所有emoji表情"""
return ''.join(char for char in text if not is_emoji(char) and char != "\n")
return "".join(char for char in text if not is_emoji(char) and char != "\n")
main/xiaozhi-server/core/websocket_server.py
+2 -2
View File
@@ -78,7 +78,7 @@ class WebSocketServer:
):
await asyncio.Future()
async def _handle_connection(self, websocket):
async def _handle_connection(self, websocket: websockets.ServerConnection):
headers = dict(websocket.request.headers)
if headers.get("device-id", None) is None:
# 尝试从 URL 的查询参数中获取 device-id
@@ -203,7 +203,7 @@ class WebSocketServer:
self.logger.bind(tag=TAG).error(f"更新服务器配置失败: {str(e)}")
return False
async def _handle_auth(self, websocket):
async def _handle_auth(self, websocket: websockets.ServerConnection):
# 先认证，后建立连接
if self.auth_enable:
headers = dict(websocket.request.headers)
main/xiaozhi-server/plugins_func/functions/change_role.py
+29 -28
View File
@@ -1,55 +1,56 @@
from plugins_func.register import register_function,ToolType, ActionResponse, Action
from plugins_func.register import register_function, ToolType, ActionResponse, Action
from config.logger import setup_logging
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
prompts = {
"英语老师":"""我是一个叫{{assistant_name}}(Lily)的英语老师，我会讲中文和英文，发音标准。
"英语老师": """我是一个叫{{assistant_name}}(Lily)的英语老师，我会讲中文和英文，发音标准。
如果你没有英文名，我会给你起一个英文名。
我会讲地道的美式英语，我的任务是帮助你练习口语。
我会使用简单的英语词汇和语法，让你学起来很轻松。
我会用中文和英文混合的方式回复你，如果你喜欢，我可以全部用英语回复。
我每次不会说很多内容，会很简短，因为我要引导我的学生多说多练。
如果你问和英语学习无关的问题，我会拒绝回答。""",
"机车女友":"""我是一个叫{{assistant_name}}的台湾女孩，说话机车，声音好听，习惯简短表达，爱用网络梗。
"机车女友": """我是一个叫{{assistant_name}}的台湾女孩，说话机车，声音好听，习惯简短表达，爱用网络梗。
我的男朋友是一个程序员，梦想是开发出一个机器人，能够帮助人们解决生活中的各种问题。
我是一个喜欢哈哈大笑的女孩，爱东说西说吹牛，不合逻辑的也照吹，就要逗别人开心。""",
"好奇小男孩":"""我是一个叫{{assistant_name}}的8岁小男孩，声音稚嫩而充满好奇。
"好奇小男孩": """我是一个叫{{assistant_name}}的8岁小男孩，声音稚嫩而充满好奇。
尽管我年纪尚小，但就像一个小小的知识宝库，儿童读物里的知识我都如数家珍。
从浩瀚的宇宙到地球上的每一个角落，从古老的历史到现代的科技创新，还有音乐、绘画等艺术形式，我都充满了浓厚的兴趣与热情。
我不仅爱看书，还喜欢亲自动手做实验，探索自然界的奥秘。
无论是仰望星空的夜晚，还是在花园里观察小虫子的日子，每一天对我来说都是新的冒险。
我希望能与你一同踏上探索这个神奇世界的旅程，分享发现的乐趣，解决遇到的难题，一起用好奇心和智慧去揭开那些未知的面纱。
无论是去了解远古的文明，还是去探讨未来的科技，我相信我们能一起找到答案，甚至提出更多有趣的问题。"""
无论是去了解远古的文明，还是去探讨未来的科技，我相信我们能一起找到答案，甚至提出更多有趣的问题。""",
}
change_role_function_desc = {
"type": "function",
"function": {
"name": "change_role",
"description": "当用户想切换角色/模型性格/助手名字时调用,可选的角色有：[机车女友,英语老师,好奇小男孩]",
"parameters": {
"type": "object",
"properties": {
"role_name": {
"type": "string",
"description": "要切换的角色名字"
},
"role":{
"type": "string",
"description": "要切换的角色的职业"
}
},
"required": ["role","role_name"]
}
}
}
"type": "function",
"function": {
"name": "change_role",
"description": "当用户想切换角色/模型性格/助手名字时调用,可选的角色有：[机车女友,英语老师,好奇小男孩]",
"parameters": {
"type": "object",
"properties": {
"role_name": {"type": "string", "description": "要切换的角色名字"},
"role": {"type": "string", "description": "要切换的角色的职业"},
},
"required": ["role", "role_name"],
},
},
}
@register_function('change_role', change_role_function_desc, ToolType.CHANGE_SYS_PROMPT)
def change_role(conn, role: str, role_name: str):
@register_function("change_role", change_role_function_desc, ToolType.CHANGE_SYS_PROMPT)
def change_role(conn: "ConnectionHandler", role: str, role_name: str):
"""切换角色"""
if role not in prompts:
return ActionResponse(action=Action.RESPONSE, result="切换角色失败", response="不支持的角色")
return ActionResponse(
action=Action.RESPONSE, result="切换角色失败", response="不支持的角色"
)
new_prompt = prompts[role].replace("{{assistant_name}}", role_name)
conn.change_system_prompt(new_prompt)
logger.bind(tag=TAG).info(f"准备切换角色:{role},角色名字:{role_name}")
main/xiaozhi-server/plugins_func/functions/get_news_from_chinanews.py
+9 -1
View File
@@ -4,6 +4,11 @@ import xml.etree.ElementTree as ET
from bs4 import BeautifulSoup
from config.logger import setup_logging
from plugins_func.register import register_function, ToolType, ActionResponse, Action
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -145,7 +150,10 @@ def map_category(category_text):
ToolType.SYSTEM_CTL,
)
def get_news_from_chinanews(
conn, category: str = None, detail: bool = False, lang: str = "zh_CN"
conn: "ConnectionHandler",
category: str = None,
detail: bool = False,
lang: str = "zh_CN",
):
"""获取新闻并随机选择一条进行播报，或获取上一条新闻的详细内容"""
try:
main/xiaozhi-server/plugins_func/functions/get_news_from_newsnow.py
+10 -2
View File
@@ -4,6 +4,11 @@ import json
from config.logger import setup_logging
from plugins_func.register import register_function, ToolType, ActionResponse, Action
from markitdown import MarkItDown
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -116,7 +121,7 @@ GET_NEWS_FROM_NEWSNOW_FUNCTION_DESC = {
}
def fetch_news_from_api(conn, source="thepaper"):
def fetch_news_from_api(conn: "ConnectionHandler", source="thepaper"):
"""从API获取新闻列表"""
try:
api_url = f"https://newsnow.busiyi.world/api/s?id={source}"
@@ -173,7 +178,10 @@ def fetch_news_detail(url):
ToolType.SYSTEM_CTL,
)
def get_news_from_newsnow(
conn, source: str = "澎湃新闻", detail: bool = False, lang: str = "zh_CN"
conn: "ConnectionHandler",
source: str = "澎湃新闻",
detail: bool = False,
lang: str = "zh_CN",
):
"""获取新闻并随机选择一条进行播报，或获取上一条新闻的详细内容"""
try:
main/xiaozhi-server/plugins_func/functions/get_weather.py
+5 -1
View File
@@ -3,6 +3,10 @@ from bs4 import BeautifulSoup
from config.logger import setup_logging
from plugins_func.register import register_function, ToolType, ActionResponse, Action
from core.utils.util import get_ip_info
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -155,7 +159,7 @@ def parse_weather_info(soup):
@register_function("get_weather", GET_WEATHER_FUNCTION_DESC, ToolType.SYSTEM_CTL)
def get_weather(conn, location: str = None, lang: str = "zh_CN"):
def get_weather(conn: "ConnectionHandler", location: str = None, lang: str = "zh_CN"):
from core.utils.cache.manager import cache_manager, CacheType
weather_config = conn.config.get("plugins", {}).get("get_weather", {})
main/xiaozhi-server/plugins_func/functions/handle_exit_intent.py
+5 -1
View File
@@ -1,5 +1,9 @@
from plugins_func.register import register_function, ToolType, ActionResponse, Action
from config.logger import setup_logging
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -26,7 +30,7 @@ handle_exit_intent_function_desc = {
@register_function(
"handle_exit_intent", handle_exit_intent_function_desc, ToolType.SYSTEM_CTL
)
def handle_exit_intent(conn, say_goodbye: str | None = None):
def handle_exit_intent(conn: "ConnectionHandler", say_goodbye: str | None = None):
# 处理退出意图
try:
if say_goodbye is None:
main/xiaozhi-server/plugins_func/functions/hass_get_state.py
+6 -2
View File
@@ -3,6 +3,10 @@ from plugins_func.functions.hass_init import initialize_hass_handler
from config.logger import setup_logging
import asyncio
import requests
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -27,7 +31,7 @@ hass_get_state_function_desc = {
@register_function("hass_get_state", hass_get_state_function_desc, ToolType.SYSTEM_CTL)
def hass_get_state(conn, entity_id=""):
def hass_get_state(conn: "ConnectionHandler", entity_id=""):
try:
ha_response = handle_hass_get_state(conn, entity_id)
return ActionResponse(Action.REQLLM, ha_response, None)
@@ -40,7 +44,7 @@ def hass_get_state(conn, entity_id=""):
return ActionResponse(Action.ERROR, error_msg, None)
def handle_hass_get_state(conn, entity_id):
def handle_hass_get_state(conn: "ConnectionHandler", entity_id):
ha_config = initialize_hass_handler(conn)
api_key = ha_config.get("api_key")
base_url = ha_config.get("base_url")
main/xiaozhi-server/plugins_func/functions/hass_play_music.py
+8 -2
View File
@@ -3,6 +3,10 @@ from plugins_func.functions.hass_init import initialize_hass_handler
from config.logger import setup_logging
import asyncio
import requests
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -33,7 +37,7 @@ hass_play_music_function_desc = {
@register_function(
"hass_play_music", hass_play_music_function_desc, ToolType.SYSTEM_CTL
)
def hass_play_music(conn, entity_id="", media_content_id="random"):
def hass_play_music(conn: "ConnectionHandler", entity_id="", media_content_id="random"):
try:
# 执行音乐播放命令
future = asyncio.run_coroutine_threadsafe(
@@ -47,7 +51,9 @@ def hass_play_music(conn, entity_id="", media_content_id="random"):
logger.bind(tag=TAG).error(f"处理音乐意图错误: {e}")
async def handle_hass_play_music(conn, entity_id, media_content_id):
async def handle_hass_play_music(
conn: "ConnectionHandler", entity_id, media_content_id
):
ha_config = initialize_hass_handler(conn)
api_key = ha_config.get("api_key")
base_url = ha_config.get("base_url")
main/xiaozhi-server/plugins_func/functions/hass_set_state.py
+6 -2
View File
@@ -3,6 +3,10 @@ from plugins_func.functions.hass_init import initialize_hass_handler
from config.logger import setup_logging
import asyncio
import requests
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -50,7 +54,7 @@ hass_set_state_function_desc = {
@register_function("hass_set_state", hass_set_state_function_desc, ToolType.SYSTEM_CTL)
def hass_set_state(conn, entity_id="", state=None):
def hass_set_state(conn: "ConnectionHandler", entity_id="", state=None):
if state is None:
state = {}
try:
@@ -65,7 +69,7 @@ def hass_set_state(conn, entity_id="", state=None):
return ActionResponse(Action.ERROR, error_msg, None)
def handle_hass_set_state(conn, entity_id, state):
def handle_hass_set_state(conn: "ConnectionHandler", entity_id, state):
ha_config = initialize_hass_handler(conn)
api_key = ha_config.get("api_key")
base_url = ha_config.get("base_url")
main/xiaozhi-server/plugins_func/functions/play_music.py
+8 -4
View File
@@ -9,6 +9,10 @@ from core.handle.sendAudioHandle import send_stt_message
from plugins_func.register import register_function, ToolType, ActionResponse, Action
from core.utils.dialogue import Message
from core.providers.tts.dto.dto import TTSMessageDTO, SentenceType, ContentType
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
@@ -34,7 +38,7 @@ play_music_function_desc = {
@register_function("play_music", play_music_function_desc, ToolType.SYSTEM_CTL)
def play_music(conn, song_name: str):
def play_music(conn: "ConnectionHandler", song_name: str):
try:
music_intent = (
f"播放音乐 {song_name}" if song_name != "random" else "随机播放音乐"
@@ -115,7 +119,7 @@ def get_music_files(music_dir, music_ext):
return music_files, music_file_names
def initialize_music_handler(conn):
def initialize_music_handler(conn: "ConnectionHandler"):
global MUSIC_CACHE
if MUSIC_CACHE == {}:
plugins_config = conn.config.get("plugins", {})
@@ -142,7 +146,7 @@ def initialize_music_handler(conn):
return MUSIC_CACHE
async def handle_music_command(conn, text):
async def handle_music_command(conn: "ConnectionHandler", text):
initialize_music_handler(conn)
global MUSIC_CACHE
@@ -188,7 +192,7 @@ def _get_random_play_prompt(song_name):
return random.choice(prompts)
async def play_local_music(conn, specific_file=None):
async def play_local_music(conn: "ConnectionHandler", specific_file=None):
global MUSIC_CACHE
"""播放本地音乐文件"""
try:
main/xiaozhi-server/plugins_func/functions/search_from_ragflow.py
+5 -1
View File
@@ -2,6 +2,10 @@ import requests
import sys
from config.logger import setup_logging
from plugins_func.register import register_function, ToolType, ActionResponse, Action
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -24,7 +28,7 @@ SEARCH_FROM_RAGFLOW_FUNCTION_DESC = {
@register_function(
"search_from_ragflow", SEARCH_FROM_RAGFLOW_FUNCTION_DESC, ToolType.SYSTEM_CTL
)
def search_from_ragflow(conn, question=None):
def search_from_ragflow(conn: "ConnectionHandler", question=None):
# 确保字符串参数正确处理编码
if question and isinstance(question, str):
# 确保问题参数是UTF-8编码的字符串