Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-26 09:03:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into py-test

Browse Source
This commit is contained in:
hrz
2025-05-09 09:52:26 +08:00
committed by GitHub
parent ee18fbebae 91b80f7c49
commit d0b4fa5b28
49 changed files with 798 additions and 559 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/handle/abortHandle.py
+5 -4
View File
@@ -3,15 +3,16 @@ import queue
from config.logger import setup_logging
TAG = __name__
logger = setup_logging()
async def handleAbortMessage(conn):
logger.bind(tag=TAG).info("Abort message received")
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
conn.clear_queues()
# 打断客户端说话状态
await conn.websocket.send(json.dumps({"type": "tts", "state": "stop", "session_id": conn.session_id}))
await conn.websocket.send(
json.dumps({"type": "tts", "state": "stop", "session_id": conn.session_id})
)
conn.clearSpeakStatus()
logger.bind(tag=TAG).info("Abort message received-end")
conn.logger.bind(tag=TAG).info("Abort message received-end")
main/xiaozhi-server/core/handle/functionHandler.py
+7 -4
View File
@@ -4,7 +4,6 @@ from plugins_func.register import FunctionRegistry, ActionResponse, Action, Tool
from plugins_func.functions.hass_init import append_devices_to_prompt
TAG = __name__
logger = setup_logging()
class FunctionHandler:
@@ -40,7 +39,9 @@ class FunctionHandler:
for func in self.functions_desc:
func_names.append(func["function"]["name"])
# 打印当前支持的函数列表
logger.bind(tag=TAG).info(f"当前支持的函数列表: {func_names}")
self.conn.logger.bind(tag=TAG, session_id=self.conn.session_id).info(
f"当前支持的函数列表: {func_names}"
)
return func_names
def get_functions(self):
@@ -79,7 +80,9 @@ class FunctionHandler:
func = funcItem.func
arguments = function_call_data["arguments"]
arguments = json.loads(arguments) if arguments else {}
logger.bind(tag=TAG).debug(f"调用函数: {function_name}, 参数: {arguments}")
self.conn.logger.bind(tag=TAG).debug(
f"调用函数: {function_name}, 参数: {arguments}"
)
if (
funcItem.type == ToolType.SYSTEM_CTL
or funcItem.type == ToolType.IOT_CTL
@@ -94,6 +97,6 @@ class FunctionHandler:
action=Action.NOTFOUND, result="没有找到对应的函数", response=""
)
except Exception as e:
logger.bind(tag=TAG).error(f"处理function call错误: {e}")
self.conn.logger.bind(tag=TAG).error(f"处理function call错误: {e}")
return None
main/xiaozhi-server/core/handle/helloHandle.py
+11 -4
View File
@@ -1,5 +1,4 @@
import json
from config.logger import setup_logging
from core.handle.sendAudioHandle import send_stt_message
from core.utils.util import remove_punctuation_and_length
import shutil
@@ -9,7 +8,6 @@ import random
import time
TAG = __name__
logger = setup_logging()
WAKEUP_CONFIG = {
"dir": "config/assets/",
@@ -21,7 +19,16 @@ WAKEUP_CONFIG = {
}
async def handleHelloMessage(conn):
async def handleHelloMessage(conn, msg_json):
"""处理hello消息"""
audio_params = msg_json.get("audio_params")
if audio_params:
format = audio_params.get("format")
conn.logger.bind(tag=TAG).info(f"客户端音频格式: {format}")
conn.audio_format = format
conn.asr.set_audio_format(format)
conn.welcome_msg["audio_params"] = audio_params
await conn.websocket.send(json.dumps(conn.welcome_msg))
@@ -75,7 +82,7 @@ async def wakeupWordsResponse(conn):
await asyncio.sleep(1)
wait_max_time -= 1
if wait_max_time <= 0:
logger.bind(tag=TAG).error("连接对象没有llm")
conn.logger.bind(tag=TAG).error("连接对象没有llm")
return
"""唤醒词响应"""
main/xiaozhi-server/core/handle/intentHandler.py
+6 -8
View File
@@ -5,10 +5,8 @@ from core.handle.sendAudioHandle import send_stt_message
from core.handle.helloHandle import checkWakeupWords
from core.utils.util import remove_punctuation_and_length
from core.utils.dialogue import Message
from loguru import logger
TAG = __name__
logger = setup_logging()
async def handle_user_intent(conn, text):
@@ -36,7 +34,7 @@ async def check_direct_exit(conn, text):
cmd_exit = conn.cmd_exit
for cmd in cmd_exit:
if text == cmd:
logger.bind(tag=TAG).info(f"识别到明确的退出命令: {text}")
conn.logger.bind(tag=TAG).info(f"识别到明确的退出命令: {text}")
await send_stt_message(conn, text)
await conn.close()
return True
@@ -46,7 +44,7 @@ async def check_direct_exit(conn, text):
async def analyze_intent_with_llm(conn, text):
"""使用LLM分析用户意图"""
if not hasattr(conn, "intent") or not conn.intent:
logger.bind(tag=TAG).warning("意图识别服务未初始化")
conn.logger.bind(tag=TAG).warning("意图识别服务未初始化")
return None
# 对话历史记录
@@ -55,7 +53,7 @@ async def analyze_intent_with_llm(conn, text):
intent_result = await conn.intent.detect_intent(conn, dialogue.dialogue, text)
return intent_result
except Exception as e:
logger.bind(tag=TAG).error(f"意图识别失败: {str(e)}")
conn.logger.bind(tag=TAG).error(f"意图识别失败: {str(e)}")
return None
@@ -69,7 +67,7 @@ async def process_intent_result(conn, intent_result, original_text):
# 检查是否有function_call
if "function_call" in intent_data:
# 直接从意图识别获取了function_call
logger.bind(tag=TAG).debug(
conn.logger.bind(tag=TAG).debug(
f"检测到function_call格式的意图结果: {intent_data['function_call']['name']}"
)
function_name = intent_data["function_call"]["name"]
@@ -118,7 +116,7 @@ async def process_intent_result(conn, intent_result, original_text):
conn.speak_and_play, text, text_index
)
conn.llm_finish_task = True
conn.tts_queue.put(future)
conn.tts_queue.put((future, text_index))
conn.dialogue.put(Message(role="assistant", content=text))
# 将函数执行放在线程池中
@@ -126,7 +124,7 @@ async def process_intent_result(conn, intent_result, original_text):
return True
return False
except json.JSONDecodeError as e:
logger.bind(tag=TAG).error(f"处理意图结果时出错: {e}")
conn.logger.bind(tag=TAG).error(f"处理意图结果时出错: {e}")
return False
main/xiaozhi-server/core/handle/iotHandle.py
+22 -19
View File
@@ -10,7 +10,6 @@ from plugins_func.register import (
)
TAG = __name__
logger = setup_logging()
def wrap_async_function(async_func):
@@ -21,7 +20,7 @@ def wrap_async_function(async_func):
# 获取连接对象（第一个参数）
conn = args[0]
if not hasattr(conn, "loop"):
logger.bind(tag=TAG).error("Connection对象没有loop属性")
conn.logger.bind(tag=TAG).error("Connection对象没有loop属性")
return ActionResponse(
Action.ERROR,
"Connection对象没有loop属性",
@@ -35,7 +34,7 @@ def wrap_async_function(async_func):
# 等待结果返回
return future.result()
except Exception as e:
logger.bind(tag=TAG).error(f"运行异步函数时出错: {e}")
conn.logger.bind(tag=TAG).error(f"运行异步函数时出错: {e}")
return ActionResponse(Action.ERROR, str(e), f"执行操作时出错: {e}")
return wrapper
@@ -57,7 +56,7 @@ def create_iot_function(device_name, method_name, method_info):
response_failure = "操作失败"
# 打印响应参数
logger.bind(tag=TAG).debug(
conn.logger.bind(tag=TAG).debug(
f"控制函数接收到的响应参数: success='{response_success}', failure='{response_failure}'"
)
@@ -86,7 +85,9 @@ def create_iot_function(device_name, method_name, method_info):
return ActionResponse(Action.RESPONSE, result, response)
except Exception as e:
logger.bind(tag=TAG).error(f"执行{device_name}的{method_name}操作失败: {e}")
conn.logger.bind(tag=TAG).error(
f"执行{device_name}的{method_name}操作失败: {e}"
)
# 操作失败时使用大模型提供的失败响应
response = response_failure
@@ -104,7 +105,7 @@ def create_iot_query_function(device_name, prop_name, prop_info):
async def iot_query_function(conn, response_success=None, response_failure=None):
try:
# 打印响应参数
logger.bind(tag=TAG).info(
conn.logger.bind(tag=TAG).info(
f"查询函数接收到的响应参数: success='{response_success}', failure='{response_failure}'"
)
@@ -122,7 +123,9 @@ def create_iot_query_function(device_name, prop_name, prop_info):
return ActionResponse(Action.ERROR, f"属性{prop_name}不存在", response)
except Exception as e:
logger.bind(tag=TAG).error(f"查询{device_name}的{prop_name}时出错: {e}")
conn.logger.bind(tag=TAG).error(
f"查询{device_name}的{prop_name}时出错: {e}"
)
# 查询出错时使用大模型提供的失败响应
response = response_failure
@@ -280,7 +283,7 @@ async def handleIotDescriptors(conn, descriptors):
await asyncio.sleep(1)
wait_max_time -= 1
if wait_max_time <= 0:
logger.bind(tag=TAG).debug("连接对象没有func_handler")
conn.logger.bind(tag=TAG).debug("连接对象没有func_handler")
return
"""处理物联网描述"""
functions_changed = False
@@ -323,7 +326,7 @@ async def handleIotDescriptors(conn, descriptors):
if hasattr(conn, "func_handler"):
for func_name in device_functions:
conn.func_handler.function_registry.register_function(func_name)
logger.bind(tag=TAG).info(
conn.logger.bind(tag=TAG).info(
f"注册IOT函数到function handler: {func_name}"
)
functions_changed = True
@@ -332,8 +335,8 @@ async def handleIotDescriptors(conn, descriptors):
if functions_changed and hasattr(conn, "func_handler"):
conn.func_handler.upload_functions_desc()
func_names = conn.func_handler.current_support_functions()
logger.bind(tag=TAG).info(f"设备类型: {type_id}")
logger.bind(tag=TAG).info(
conn.logger.bind(tag=TAG).info(f"设备类型: {type_id}")
conn.logger.bind(tag=TAG).info(
f"更新function描述列表完成，当前支持的函数: {func_names}"
)
@@ -347,13 +350,13 @@ async def handleIotStatus(conn, states):
for k, v in state["state"].items():
if property_item["name"] == k:
if type(v) != type(property_item["value"]):
logger.bind(tag=TAG).error(
conn.logger.bind(tag=TAG).error(
f"属性{property_item['name']}的值类型不匹配"
)
break
else:
property_item["value"] = v
logger.bind(tag=TAG).info(
conn.logger.bind(tag=TAG).info(
f"物联网状态更新: {key} , {property_item['name']} = {v}"
)
break
@@ -367,7 +370,7 @@ async def get_iot_status(conn, name, property_name):
for property_item in value.properties:
if property_item["name"] == property_name:
return property_item["value"]
logger.bind(tag=TAG).warning(f"未找到设备 {name} 的属性 {property_name}")
conn.logger.bind(tag=TAG).warning(f"未找到设备 {name} 的属性 {property_name}")
return None
@@ -378,16 +381,16 @@ async def set_iot_status(conn, name, property_name, value):
for property_item in iot_descriptor.properties:
if property_item["name"] == property_name:
if type(value) != type(property_item["value"]):
logger.bind(tag=TAG).error(
conn.logger.bind(tag=TAG).error(
f"属性{property_item['name']}的值类型不匹配"
)
return
property_item["value"] = value
logger.bind(tag=TAG).info(
conn.logger.bind(tag=TAG).info(
f"物联网状态更新: {name} , {property_name} = {value}"
)
return
logger.bind(tag=TAG).warning(f"未找到设备 {name} 的属性 {property_name}")
conn.logger.bind(tag=TAG).warning(f"未找到设备 {name} 的属性 {property_name}")
async def send_iot_conn(conn, name, method_name, parameters):
@@ -409,6 +412,6 @@ async def send_iot_conn(conn, name, method_name, parameters):
command["parameters"] = parameters
send_message = json.dumps({"type": "iot", "commands": [command]})
await conn.websocket.send(send_message)
logger.bind(tag=TAG).info(f"发送物联网指令: {send_message}")
conn.logger.bind(tag=TAG).info(f"发送物联网指令: {send_message}")
return
logger.bind(tag=TAG).error(f"未找到方法{method_name}")
conn.logger.bind(tag=TAG).error(f"未找到方法{method_name}")
main/xiaozhi-server/core/handle/receiveAudioHandle.py
+11 -11
View File
@@ -1,4 +1,3 @@
from config.logger import setup_logging
import time
import copy
from core.utils.util import remove_punctuation_and_length
@@ -6,15 +5,16 @@ 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.ttsReportHandle import enqueue_tts_report
from core.providers.tts.base import audio_to_opus_data
from core.utils.util import audio_to_data
TAG = __name__
logger = setup_logging()
async def handleAudioMessage(conn, audio):
if conn.vad is None:
return
if not conn.asr_server_receive:
logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
conn.logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
return
if conn.client_listen_mode == "auto":
have_voice = conn.vad.is_vad(conn, audio)
@@ -40,7 +40,7 @@ async def handleAudioMessage(conn, audio):
conn.asr_server_receive = True
else:
text, _ = await conn.asr.speech_to_text(conn.asr_audio, conn.session_id)
logger.bind(tag=TAG).info(f"识别文本: {text}")
conn.logger.bind(tag=TAG).info(f"识别文本: {text}")
text_len, _ = remove_punctuation_and_length(text)
if text_len > 0:
# 使用自定义模块进行上报
@@ -111,7 +111,7 @@ async def max_out_size(conn):
conn.tts_last_text_index = 0
conn.llm_finish_task = True
file_path = "config/assets/max_output_size.wav"
opus_packets, _ = audio_to_opus_data(file_path)
opus_packets, _ = audio_to_data(file_path)
conn.audio_play_queue.put((opus_packets, text, 0))
conn.close_after_chat = True
@@ -120,7 +120,7 @@ async def check_bind_device(conn):
if conn.bind_code:
# 确保bind_code是6位数字
if len(conn.bind_code) != 6:
logger.bind(tag=TAG).error(f"无效的绑定码格式: {conn.bind_code}")
conn.logger.bind(tag=TAG).error(f"无效的绑定码格式: {conn.bind_code}")
text = "绑定码格式错误，请检查配置。"
await send_stt_message(conn, text)
return
@@ -133,7 +133,7 @@ async def check_bind_device(conn):
# 播放提示音
music_path = "config/assets/bind_code.wav"
opus_packets, _ = audio_to_opus_data(music_path)
opus_packets, _ = audio_to_data(music_path)
conn.audio_play_queue.put((opus_packets, text, 0))
# 逐个播放数字
@@ -141,10 +141,10 @@ async def check_bind_device(conn):
try:
digit = conn.bind_code[i]
num_path = f"config/assets/bind_code/{digit}.wav"
num_packets, _ = audio_to_opus_data(num_path)
num_packets, _ = audio_to_data(num_path)
conn.audio_play_queue.put((num_packets, None, i + 1))
except Exception as e:
logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
continue
else:
text = f"没有找到该设备的版本信息，请正确配置 OTA地址，然后重新编译固件。"
@@ -153,5 +153,5 @@ async def check_bind_device(conn):
conn.tts_last_text_index = 0
conn.llm_finish_task = True
music_path = "config/assets/bind_not_found.wav"
opus_packets, _ = audio_to_opus_data(music_path)
opus_packets, _ = audio_to_data(music_path)
conn.audio_play_queue.put((opus_packets, text, 0))
main/xiaozhi-server/core/handle/sendAudioHandle.py
+3 -5
View File
@@ -1,11 +1,9 @@
from config.logger import setup_logging
import json
import asyncio
import time
from core.utils.util import get_string_no_punctuation_or_emoji, analyze_emotion
TAG = __name__
logger = setup_logging()
emoji_map = {
"neutral": "😶",
@@ -49,10 +47,10 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
)
if text_index == conn.tts_first_text_index:
logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
conn.logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
await send_tts_message(conn, "sentence_start", text)
is_first_audio = (text_index == conn.tts_first_text_index)
is_first_audio = text_index == conn.tts_first_text_index
await sendAudio(conn, audios, pre_buffer=is_first_audio)
await send_tts_message(conn, "sentence_end", text)
@@ -117,7 +115,7 @@ async def send_tts_message(conn, state, text=None):
stop_tts_notify_voice = conn.config.get(
"stop_tts_notify_voice", "config/assets/tts_notify.mp3"
)
audios, duration = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
audios, _ = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
await sendAudio(conn, audios)
# 清除服务端讲话状态
conn.clearSpeakStatus()
main/xiaozhi-server/core/handle/textHandle.py
+5 -5
View File
@@ -1,4 +1,3 @@
from config.logger import setup_logging
import json
from core.handle.abortHandle import handleAbortMessage
from core.handle.helloHandle import handleHelloMessage
@@ -10,25 +9,26 @@ from core.handle.ttsReportHandle import enqueue_tts_report
import asyncio
TAG = __name__
logger = setup_logging()
async def handleTextMessage(conn, message):
"""处理文本消息"""
logger.bind(tag=TAG).info(f"收到文本消息：{message}")
conn.logger.bind(tag=TAG).info(f"收到文本消息：{message}")
try:
msg_json = json.loads(message)
if isinstance(msg_json, int):
await conn.websocket.send(message)
return
if msg_json["type"] == "hello":
await handleHelloMessage(conn)
await handleHelloMessage(conn, msg_json)
elif msg_json["type"] == "abort":
await handleAbortMessage(conn)
elif msg_json["type"] == "listen":
if "mode" in msg_json:
conn.client_listen_mode = msg_json["mode"]
logger.bind(tag=TAG).debug(f"客户端拾音模式：{conn.client_listen_mode}")
conn.logger.bind(tag=TAG).debug(
f"客户端拾音模式：{conn.client_listen_mode}"
)
if msg_json["state"] == "start":
conn.client_have_voice = True
conn.client_voice_stop = False
main/xiaozhi-server/core/handle/ttsReportHandle.py
+6 -11
View File
@@ -9,16 +9,11 @@ TTS上报功能已集成到ConnectionHandler类中。
具体实现请参考core/connection.py中的相关代码。
"""
import os
import uuid
import wave
import opuslib_next
from config.logger import setup_logging
from config.manage_api_client import report
TAG = __name__
logger = setup_logging()
def report_tts(conn, type, text, opus_data):
@@ -32,7 +27,7 @@ def report_tts(conn, type, text, opus_data):
"""
try:
if opus_data:
audio_data = opus_to_wav(opus_data)
audio_data = opus_to_wav(conn, opus_data)
else:
audio_data = None
# 执行上报
@@ -44,10 +39,10 @@ def report_tts(conn, type, text, opus_data):
audio=audio_data,
)
except Exception as e:
logger.bind(tag=TAG).error(f"TTS上报失败: {e}")
conn.logger.bind(tag=TAG).error(f"TTS上报失败: {e}")
def opus_to_wav(opus_data):
def opus_to_wav(conn, opus_data):
"""将Opus数据转换为WAV格式的字节流
Args:
@@ -65,7 +60,7 @@ def opus_to_wav(opus_data):
pcm_frame = decoder.decode(opus_packet, 960) # 960 samples = 60ms
pcm_data.append(pcm_frame)
except opuslib_next.OpusError as e:
logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
conn.logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
if not pcm_data:
raise ValueError("没有有效的PCM数据")
@@ -108,8 +103,8 @@ def enqueue_tts_report(conn, type, text, opus_data):
# 使用连接对象的队列，传入文本和二进制数据而非文件路径
conn.tts_report_queue.put((type, text, opus_data))
logger.bind(tag=TAG).debug(
conn.logger.bind(tag=TAG).debug(
f"TTS数据已加入上报队列: {conn.device_id}, 音频大小: {len(opus_data)} "
)
except Exception as e:
logger.bind(tag=TAG).error(f"加入TTS上报队列失败: {text}, {e}")
conn.logger.bind(tag=TAG).error(f"加入TTS上报队列失败: {text}, {e}")