Merge branch 'main' into py_Text

# Conflicts:
#	main/xiaozhi-server/core/handle/helloHandle.py
#	main/xiaozhi-server/core/providers/tts/base.py
This commit is contained in:
hrz
2025-06-07 22:48:23 +08:00
37 changed files with 1968 additions and 581 deletions
@@ -1,6 +1,4 @@
import json
import queue
from config.logger import setup_logging
TAG = __name__
@@ -35,8 +35,6 @@ async def handleHelloMessage(conn, msg_json):
format = audio_params.get("format")
conn.logger.bind(tag=TAG).info(f"客户端音频格式: {format}")
conn.audio_format = format
if conn.asr is not None:
conn.asr.set_audio_format(format)
conn.welcome_msg["audio_params"] = audio_params
features = msg_json.get("features")
if features:
@@ -68,6 +66,7 @@ async def checkWakeupWords(conn, text):
if filtered_text not in conn.config.get("wakeup_words"):
return False
conn.just_woken_up = True
await send_stt_message(conn, text)
# 获取当前音色
@@ -96,6 +96,7 @@ async def process_intent_result(conn, intent_result, original_text):
}
await send_stt_message(conn, original_text)
conn.client_abort = False
# 使用executor执行函数调用和结果处理
def process_function_call():
@@ -3,6 +3,7 @@ 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
import asyncio
from core.handle.sendAudioHandle import SentenceType
from core.utils.util import audio_to_data
@@ -10,19 +11,29 @@ TAG = __name__
async def handleAudioMessage(conn, audio):
if conn.vad is None:
return
if conn.asr is None or not hasattr(conn.asr, "conn") or conn.asr.conn is None:
return
# 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
if hasattr(conn, "just_woken_up") and conn.just_woken_up:
have_voice = False
# 设置一个短暂延迟后恢复VAD检测
conn.asr_audio.clear()
asyncio.create_task(resume_vad_detection(conn))
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
await conn.asr.receive_audio(audio, have_voice)
await conn.asr.receive_audio(conn, audio, have_voice)
async def resume_vad_detection(conn):
# 等待2秒后恢复VAD检测
await asyncio.sleep(2)
conn.just_woken_up = False
async def startToChat(conn, text):
@@ -89,8 +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
break
# 每分钟重置一次计时器
if time.perf_counter() - last_reset_time > 60:
@@ -61,6 +61,7 @@ async def handleTextMessage(conn, message):
await send_tts_message(conn, "stop", None)
conn.client_is_speaking = False
elif is_wakeup_words:
conn.just_woken_up = True
# 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", [])
await startToChat(conn, "嘿,你好呀")
@@ -78,7 +79,9 @@ async def handleTextMessage(conn, message):
elif msg_json["type"] == "mcp":
conn.logger.bind(tag=TAG).info(f"收到mcp消息:{message}")
if "payload" in msg_json:
asyncio.create_task(handle_mcp_message(conn, conn.mcp_client, msg_json["payload"]))
asyncio.create_task(
handle_mcp_message(conn, conn.mcp_client, msg_json["payload"])
)
elif msg_json["type"] == "server":
# 记录日志时过滤敏感信息
conn.logger.bind(tag=TAG).info(