From 60521b0a7ef6fc2d9ec7cdfd96a4d6688fb0f582 Mon Sep 17 00:00:00 2001 From: FAN-yeB <1442100690@qq.com> Date: Tue, 9 Dec 2025 14:42:50 +0800 Subject: [PATCH 01/39] =?UTF-8?q?update:=E9=95=BF=E6=8C=89=E8=AF=B4?= =?UTF-8?q?=E8=AF=9D=E4=B8=8D=E8=B5=B0VAD=E7=9B=B4=E6=8E=A5=E8=A7=A6?= =?UTF-8?q?=E5=8F=91ASR=E8=AF=86=E5=88=AB?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../textHandler/listenMessageHandler.py | 8 ++++++- .../xiaozhi-server/core/providers/asr/base.py | 23 ++++++++++++------- .../core/providers/vad/silero.py | 4 ++++ 3 files changed, 26 insertions(+), 9 deletions(-) diff --git a/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py b/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py index 97286dfe..65b442ad 100644 --- a/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py +++ b/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py @@ -30,7 +30,13 @@ class ListenTextMessageHandler(TextMessageHandler): conn.client_have_voice = True conn.client_voice_stop = True if len(conn.asr_audio) > 0: - await handleAudioMessage(conn, b"") + # 手动模式下直接触发ASR识别，不需要再调用handleAudioMessage + asr_audio_task = conn.asr_audio.copy() + conn.asr_audio.clear() + conn.reset_vad_states() + + if len(asr_audio_task) > 0: + await conn.asr.handle_voice_stop(conn, asr_audio_task) elif msg_json["state"] == "detect": conn.client_have_voice = False conn.asr_audio.clear() diff --git a/main/xiaozhi-server/core/providers/asr/base.py b/main/xiaozhi-server/core/providers/asr/base.py index 7e36de5c..6c3c2d25 100644 --- a/main/xiaozhi-server/core/providers/asr/base.py +++ b/main/xiaozhi-server/core/providers/asr/base.py @@ -56,21 +56,28 @@ class ASRProviderBase(ABC): async def receive_audio(self, conn, audio, audio_have_voice): if conn.client_listen_mode == "auto" or conn.client_listen_mode == "realtime": have_voice = audio_have_voice + + conn.asr_audio.append(audio) + if not have_voice and not conn.client_have_voice: + conn.asr_audio = conn.asr_audio[-10:] + return else: - have_voice = conn.client_have_voice - - conn.asr_audio.append(audio) - if not have_voice and not conn.client_have_voice: - conn.asr_audio = conn.asr_audio[-10:] - return + # 手动模式：总是缓存音频，忽略VAD检测结果 + conn.asr_audio.append(audio) if conn.client_voice_stop: asr_audio_task = conn.asr_audio.copy() conn.asr_audio.clear() conn.reset_vad_states() - if len(asr_audio_task) > 15: - await self.handle_voice_stop(conn, asr_audio_task) + # 手动模式下允许短语音识别，自动模式保持原有限制 + if conn.client_listen_mode == "auto" or conn.client_listen_mode == "realtime": + if len(asr_audio_task) > 15: + await self.handle_voice_stop(conn, asr_audio_task) + else: + # 手动模式：只要有音频就进行识别 + if len(asr_audio_task) > 0: + 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]): diff --git a/main/xiaozhi-server/core/providers/vad/silero.py b/main/xiaozhi-server/core/providers/vad/silero.py index ae51b88f..28a3e61e 100644 --- a/main/xiaozhi-server/core/providers/vad/silero.py +++ b/main/xiaozhi-server/core/providers/vad/silero.py @@ -45,6 +45,10 @@ class VADProvider(VADProviderBase): pass def is_vad(self, conn, opus_packet): + # 手动模式：直接返回True，不进行实时VAD检测，所有音频都缓存 + if conn.client_listen_mode not in ["auto", "realtime"]: + return True + try: pcm_frame = self.decoder.decode(opus_packet, 960) conn.client_audio_buffer.extend(pcm_frame) # 将新数据加入缓冲区 From 48094f7e376324d893773f667500b5eb14293404 Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Tue, 9 Dec 2025 18:06:56 +0800 Subject: [PATCH 02/39] =?UTF-8?q?update:=20=E9=9F=B3=E9=A2=91=E5=90=8E?= =?UTF-8?q?=E5=8F=B0=E9=98=9F=E5=88=97=E7=A8=B3=E5=AE=9A=E5=8F=91=E9=80=81?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/core/connection.py | 5 + .../core/handle/sendAudioHandle.py | 199 ++++++++++-------- .../core/utils/audioRateController.py | 84 +++++--- .../core/utils/opus_encoder_utils.py | 3 + 4 files changed, 166 insertions(+), 125 deletions(-) diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py index 6b34e32f..b37745c7 100644 --- a/main/xiaozhi-server/core/connection.py +++ b/main/xiaozhi-server/core/connection.py @@ -1171,6 +1171,11 @@ class ConnectionHandler: except queue.Empty: break + # 重置音频流控器（取消后台任务并清空队列） + if hasattr(self, "audio_rate_controller") and self.audio_rate_controller: + self.audio_rate_controller.reset() + self.logger.bind(tag=TAG).debug("已重置音频流控器") + self.logger.bind(tag=TAG).debug( f"清理结束: TTS队列大小={self.tts.tts_text_queue.qsize()}, 音频队列大小={self.tts.tts_audio_queue.qsize()}" ) diff --git a/main/xiaozhi-server/core/handle/sendAudioHandle.py b/main/xiaozhi-server/core/handle/sendAudioHandle.py index ea952fbe..f662b6c6 100644 --- a/main/xiaozhi-server/core/handle/sendAudioHandle.py +++ b/main/xiaozhi-server/core/handle/sendAudioHandle.py @@ -16,7 +16,14 @@ async def sendAudioMessage(conn, sentenceType, audios, text): await send_tts_message(conn, "start", None) if sentenceType == SentenceType.FIRST: - await send_tts_message(conn, "sentence_start", text) + # 同一句子的后续消息加入流控队列，其他情况立即发送 + if hasattr(conn, "audio_rate_controller") and conn.audio_rate_controller and getattr(conn, "audio_flow_control", {}).get("sentence_id") == conn.sentence_id: + conn.audio_rate_controller.add_message( + lambda: send_tts_message(conn, "sentence_start", text) + ) + else: + # 新句子或流控器未初始化，立即发送 + await send_tts_message(conn, "sentence_start", text) await sendAudio(conn, audios) # 发送句子开始消息 @@ -31,6 +38,22 @@ async def sendAudioMessage(conn, sentenceType, audios, text): await conn.close() +async def _wait_for_audio_completion(conn): + """ + 等待音频队列清空 + + Args: + conn: 连接对象 + """ + if hasattr(conn, "audio_rate_controller") and conn.audio_rate_controller: + rate_controller = conn.audio_rate_controller + conn.logger.bind(tag=TAG).debug( + f"等待音频发送完成，队列中还有 {len(rate_controller.queue)} 个包" + ) + await rate_controller.queue_empty_event.wait() + conn.logger.bind(tag=TAG).debug("音频发送完成") + + async def _send_to_mqtt_gateway(conn, opus_packet, timestamp, sequence): """ 发送带16字节头部的opus数据包给mqtt_gateway @@ -53,7 +76,6 @@ async def _send_to_mqtt_gateway(conn, opus_packet, timestamp, sequence): await conn.websocket.send(complete_packet) -# 播放音频 - 使用 AudioRateController 进行精确流控 async def sendAudio(conn, audios, frame_duration=60): """ 发送音频包，使用 AudioRateController 进行精确的流量控制 @@ -62,130 +84,121 @@ async def sendAudio(conn, audios, frame_duration=60): conn: 连接对象 audios: 单个opus包(bytes) 或 opus包列表 frame_duration: 帧时长（毫秒），默认60ms - - 改进点： - 1. 使用单一时间基准，避免累积误差 - 2. 每次检查队列时重新计算 elapsed_ms，更精准 - 3. 支持高并发而不产生时间偏差 """ if audios is None or len(audios) == 0: return - # 获取发送延迟配置 send_delay = conn.config.get("tts_audio_send_delay", -1) / 1000.0 + is_single_packet = isinstance(audios, bytes) - if isinstance(audios, bytes): - # 单个 opus 包处理 - await _sendAudio_single(conn, audios, send_delay, frame_duration) - else: - # 音频列表处理（如文件型音频） - await _sendAudio_list(conn, audios, send_delay, frame_duration) + # 初始化或获取 RateController + rate_controller, flow_control = _get_or_create_rate_controller( + conn, frame_duration, is_single_packet + ) + + # 统一转换为列表处理 + audio_list = [audios] if is_single_packet else audios + + # 发送音频包 + await _send_audio_with_rate_control( + conn, audio_list, rate_controller, flow_control, send_delay + ) -async def _sendAudio_single(conn, opus_packet, send_delay, frame_duration=60): +def _get_or_create_rate_controller(conn, frame_duration, is_single_packet): """ - 发送单个 opus 包 - 使用 AudioRateController 进行流控 + 获取或创建 RateController 和 flow_control + + Args: + conn: 连接对象 + frame_duration: 帧时长 + is_single_packet: 是否单包模式（True: TTS流式单包, False: 批量包） + + Returns: + (rate_controller, flow_control) """ - # 重置流控状态，第一次读取和会话发生转变时 - if not hasattr(conn, "audio_rate_controller") or conn.audio_flow_control.get("sentence_id") != conn.sentence_id: - if hasattr(conn, "audio_rate_controller"): - conn.audio_rate_controller.reset() - else: + # 判断是否需要重置：单包模式且 sentence_id 变化，或者控制器不存在 + need_reset = ( + is_single_packet + and getattr(conn, "audio_flow_control", {}).get("sentence_id") != conn.sentence_id + ) or not hasattr(conn, "audio_rate_controller") + + if need_reset: + # 创建或获取 rate_controller + if not hasattr(conn, "audio_rate_controller"): conn.audio_rate_controller = AudioRateController(frame_duration) + else: conn.audio_rate_controller.reset() + # 初始化 flow_control conn.audio_flow_control = { "packet_count": 0, "sequence": 0, "sentence_id": conn.sentence_id, } - if conn.client_abort: - return + # 启动后台发送循环 + _start_background_sender(conn, conn.audio_rate_controller, conn.audio_flow_control) - conn.last_activity_time = time.time() * 1000 + return conn.audio_rate_controller, conn.audio_flow_control - rate_controller = conn.audio_rate_controller - flow_control = conn.audio_flow_control - packet_count = flow_control["packet_count"] - # 预缓冲：前5个包直接发送，不做延迟 +def _start_background_sender(conn, rate_controller, flow_control): + """ + 启动后台发送循环任务 + + Args: + conn: 连接对象 + rate_controller: 速率控制器 + flow_control: 流控状态 + """ + async def send_callback(packet): + # 检查是否应该中止 + if conn.client_abort: + raise asyncio.CancelledError("客户端已中止") + + conn.last_activity_time = time.time() * 1000 + await _do_send_audio(conn, packet, flow_control) + conn.client_is_speaking = True + + # 使用 start_sending 启动后台循环 + rate_controller.start_sending(send_callback) + + +async def _send_audio_with_rate_control(conn, audio_list, rate_controller, flow_control, send_delay): + """ + 使用 rate_controller 发送音频包 + + Args: + conn: 连接对象 + audio_list: 音频包列表 + rate_controller: 速率控制器 + flow_control: 流控状态 + send_delay: 固定延迟（秒），-1表示使用动态流控 + """ pre_buffer_count = 5 - if packet_count < pre_buffer_count or send_delay > 0: - # 预缓冲阶段或固定延迟模式，直接发送 - await _do_send_audio(conn, opus_packet, flow_control, frame_duration) - conn.client_is_speaking = True - - if send_delay > 0 and packet_count >= pre_buffer_count: - await asyncio.sleep(send_delay) - else: - # 使用流控器进行精确的速率控制 - rate_controller.add_audio(opus_packet) - - async def send_callback(packet): - await _do_send_audio(conn, packet, flow_control, frame_duration) - - await rate_controller.check_queue(send_callback) - conn.client_is_speaking = True - - # 更新流控状态 - flow_control["packet_count"] += 1 - flow_control["sequence"] += 1 - - -async def _sendAudio_list(conn, audios, send_delay, frame_duration=60): - """ - 发送音频列表（如文件型音频） - """ - if not audios: - return - - rate_controller = AudioRateController(frame_duration) - rate_controller.reset() - - flow_control = { - "packet_count": 0, - "sequence": 0, - } - - # 预缓冲：前5个包直接发送 - pre_buffer_frames = min(5, len(audios)) - for i in range(pre_buffer_frames): + for packet in audio_list: if conn.client_abort: return - await _do_send_audio(conn, audios[i], flow_control, frame_duration) - conn.client_is_speaking = True - - remaining_audios = audios[pre_buffer_frames:] - - # 处理剩余音频帧 - for i, opus_packet in enumerate(remaining_audios): - if conn.client_abort: - break conn.last_activity_time = time.time() * 1000 - if send_delay > 0: + # 预缓冲：前5个包直接发送 + if flow_control["packet_count"] < pre_buffer_count: + await _do_send_audio(conn, packet, flow_control) + conn.client_is_speaking = True + elif send_delay > 0: # 固定延迟模式 await asyncio.sleep(send_delay) - else: - # 使用流控器进行精确延迟 - rate_controller.add_audio(opus_packet) - - async def send_callback(packet): - await _do_send_audio(conn, packet, flow_control, frame_duration) - - await rate_controller.check_queue(send_callback) + await _do_send_audio(conn, packet, flow_control) conn.client_is_speaking = True - continue - - await _do_send_audio(conn, opus_packet, flow_control, frame_duration) - conn.client_is_speaking = True + else: + # 动态流控模式：仅添加到队列，由后台循环负责发送 + rate_controller.add_audio(packet) -async def _do_send_audio(conn, opus_packet, flow_control, frame_duration=60): +async def _do_send_audio(conn, opus_packet, flow_control): """ 执行实际的音频发送 """ @@ -224,6 +237,8 @@ async def send_tts_message(conn, state, text=None): ) audios = audio_to_data(stop_tts_notify_voice, is_opus=True) await sendAudio(conn, audios) + # 等待所有音频包发送完成 + await _wait_for_audio_completion(conn) # 清除服务端讲话状态 conn.clearSpeakStatus() diff --git a/main/xiaozhi-server/core/utils/audioRateController.py b/main/xiaozhi-server/core/utils/audioRateController.py index b404e6f1..e6d883f1 100644 --- a/main/xiaozhi-server/core/utils/audioRateController.py +++ b/main/xiaozhi-server/core/utils/audioRateController.py @@ -10,12 +10,6 @@ class AudioRateController: """ 音频速率控制器 - 按照60ms帧时长精确控制音频发送 解决高并发下的时间累积误差问题 - - 关键改进： - 1. 单一时间基准（start_timestamp 只初始化一次） - 2. 每次检查队列时重新计算 elapsed_ms，避免累积误差 - 3. 分离"检查时间"和"发送"两个操作 - 4. 支持高并发而不产生延迟 """ def __init__(self, frame_duration=60): @@ -29,24 +23,34 @@ class AudioRateController: self.start_timestamp = None # 开始时间戳（只读，不修改） self.pending_send_task = None self.logger = logger + self.queue_empty_event = asyncio.Event() # 队列清空事件 + self.queue_empty_event.set() # 初始为空状态 def reset(self): """重置控制器状态""" if self.pending_send_task and not self.pending_send_task.done(): self.pending_send_task.cancel() - try: - # 等待任务取消完成 - asyncio.get_event_loop().run_until_complete(self.pending_send_task) - except asyncio.CancelledError: - pass + # 取消任务后，任务会在下次事件循环时清理，无需阻塞等待 self.queue.clear() self.play_position = 0 self.start_timestamp = time.time() + self.queue_empty_event.set() # 队列已清空 def add_audio(self, opus_packet): """添加音频包到队列""" self.queue.append(("audio", opus_packet)) + self.queue_empty_event.clear() # 队列非空，清除事件 + + def add_message(self, message_callback): + """ + 添加消息到队列（立即发送，不占用播放时间） + + Args: + message_callback: 消息发送回调函数 async def() + """ + self.queue.append(("message", message_callback)) + self.queue_empty_event.clear() # 队列非空，清除事件 def _get_elapsed_ms(self): """获取已经过的时间（毫秒）""" @@ -62,34 +66,47 @@ class AudioRateController: send_audio_callback: 发送音频的回调函数 async def(opus_packet) """ if self.start_timestamp is None: - self.reset() + self.start_timestamp = time.time() while self.queue: item = self.queue[0] item_type = item[0] - if item_type == "audio": + if item_type == "message": + # 消息类型：立即发送，不占用播放时间 + _, message_callback = item + self.queue.pop(0) + try: + await message_callback() + except Exception as e: + self.logger.bind(tag=TAG).error(f"发送消息失败: {e}") + raise + + elif item_type == "audio": _, opus_packet = item - # 计算时间差 - elapsed_ms = self._get_elapsed_ms() - output_ms = self.play_position + # 循环等待直到时间到达 + while True: + # 计算时间差 + elapsed_ms = self._get_elapsed_ms() + output_ms = self.play_position - if elapsed_ms < output_ms: - # 还不到发送时间，计算等待时长 - wait_ms = output_ms - elapsed_ms + if elapsed_ms < output_ms: + # 还不到发送时间，计算等待时长 + wait_ms = output_ms - elapsed_ms - # 等待后继续检查（允许被中断） - try: - await asyncio.sleep(wait_ms / 1000) - except asyncio.CancelledError: - self.logger.bind(tag=TAG).debug("音频发送任务被取消") - raise + # 等待后继续检查（允许被中断） + try: + await asyncio.sleep(wait_ms / 1000) + except asyncio.CancelledError: + self.logger.bind(tag=TAG).debug("音频发送任务被取消") + raise + # 等待结束后重新检查时间（循环回到 while True） + else: + # 时间已到，跳出等待循环 + break - # 继续循环检查（时间可能已到） - continue - - # 时间已到，发送音频 + # 时间已到，从队列移除并发送 self.queue.pop(0) self.play_position += self.frame_duration @@ -99,14 +116,15 @@ class AudioRateController: self.logger.bind(tag=TAG).error(f"发送音频失败: {e}") raise + self.queue_empty_event.set() - async def start_sending(self, send_audio_callback, send_message_callback=None): + + def start_sending(self, send_audio_callback): """ 启动异步发送任务 Args: send_audio_callback: 发送音频的回调函数 - send_message_callback: 发送消息的回调函数 Returns: asyncio.Task: 发送任务 @@ -114,11 +132,11 @@ class AudioRateController: async def _send_loop(): try: while True: - await self.check_queue(send_audio_callback, send_message_callback) + await self.check_queue(send_audio_callback) # 如果队列空了，短暂等待后再检查（避免 busy loop） await asyncio.sleep(0.01) except asyncio.CancelledError: - self.logger.bind(tag=TAG).info("音频发送循环已停止") + self.logger.bind(tag=TAG).debug("音频发送循环已停止") except Exception as e: self.logger.bind(tag=TAG).error(f"音频发送循环异常: {e}") diff --git a/main/xiaozhi-server/core/utils/opus_encoder_utils.py b/main/xiaozhi-server/core/utils/opus_encoder_utils.py index 300b2422..f2fcc266 100644 --- a/main/xiaozhi-server/core/utils/opus_encoder_utils.py +++ b/main/xiaozhi-server/core/utils/opus_encoder_utils.py @@ -103,6 +103,9 @@ class OpusEncoderUtils: def _encode(self, frame: np.ndarray) -> Optional[bytes]: """编码一帧音频数据""" try: + # 编码器已释放，跳过编码 + if not hasattr(self, 'encoder') or self.encoder is None: + return None # 将numpy数组转换为bytes frame_bytes = frame.tobytes() # opuslib要求输入字节数必须是channels*2的倍数 From 3a74b30a0e5669e7e1d8e69bdd4ba0a892c54497 Mon Sep 17 00:00:00 2001 From: FAN-yeB <1442100690@qq.com> Date: Wed, 10 Dec 2025 17:57:26 +0800 Subject: [PATCH 03/39] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20qwen3=5Fasr=5Fflash.?= =?UTF-8?q?py?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../core/providers/asr/qwen3_asr_flash.py | 23 ++----------------- 1 file changed, 2 insertions(+), 21 deletions(-) diff --git a/main/xiaozhi-server/core/providers/asr/qwen3_asr_flash.py b/main/xiaozhi-server/core/providers/asr/qwen3_asr_flash.py index 84fe1979..7101448d 100644 --- a/main/xiaozhi-server/core/providers/asr/qwen3_asr_flash.py +++ b/main/xiaozhi-server/core/providers/asr/qwen3_asr_flash.py @@ -1,8 +1,5 @@ import os -import json -import asyncio import tempfile -import difflib from typing import Optional, Tuple, List import dashscope from config.logger import setup_logging @@ -130,27 +127,11 @@ class ASRProvider(ASRProviderBase): # 处理流式响应 full_text = "" - last_text = "" # 用于存储上一个文本片段 for chunk in response: try: text = chunk["output"]["choices"][0]["message"].content[0]["text"] - # 标准化文本片段（去除首尾空格） - normalized_text = text.strip() - # 只有当新文本片段与上一个不同时才处理 - if normalized_text != last_text: - # 提取新增的文本部分 - # 通过比较当前文本和上一个文本，找到新增的部分 - if normalized_text.startswith(last_text): - # 如果当前文本以最后一个文本开头，则新增部分是两者的差集 - new_part = normalized_text[len(last_text):] - else: - # 如果不以最后一个文本开头，说明识别结果发生了较大变化，直接使用当前文本 - new_part = normalized_text - - # 将新增部分添加到完整文本中 - full_text += new_part - last_text = normalized_text - # 这里可以实时处理文本片段，例如通过回调函数 + # 更新为最新的完整文本 + full_text = text.strip() except: pass From 5ac1a1d6a597c6cd02bb460074134c4369e066c8 Mon Sep 17 00:00:00 2001 From: panjingpeng Date: Thu, 11 Dec 2025 16:08:45 +0800 Subject: [PATCH 04/39] =?UTF-8?q?fix:=20=E4=B8=BAJava=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=E7=9A=84OTA=E6=8E=A5=E5=8F=A3=E5=AE=9E=E7=8E=B0WebSocket?= =?UTF-8?q?=E8=AE=A4=E8=AF=81token=E7=94=9F=E6=88=90=E5=8A=9F=E8=83=BD?= =?UTF-8?q?=EF=BC=8C=E7=A1=AE=E4=BF=9D=E4=B8=8EPython=E7=AB=AF=E5=AE=8C?= =?UTF-8?q?=E5=85=A8=E5=85=BC=E5=AE=B9=E3=80=82?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../xiaozhi/common/constant/Constant.java | 5 ++ .../service/impl/DeviceServiceImpl.java | 53 ++++++++++++++++++- main/xiaozhi-server/config/config_loader.py | 2 + 3 files changed, 59 insertions(+), 1 deletion(-) diff --git a/main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java b/main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java index 1ea19355..13084f9b 100644 --- a/main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java +++ b/main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java @@ -141,6 +141,11 @@ public interface Constant { */ String SERVER_MQTT_SECRET = "server.mqtt_signature_key"; + /** + * WebSocket认证开关 + */ + String SERVER_AUTH_ENABLED = "server.auth.enabled"; + /** * 无记忆 */ diff --git a/main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java b/main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java index 5c3f854d..b00af2cf 100644 --- a/main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java +++ b/main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java @@ -1,6 +1,8 @@ package xiaozhi.modules.device.service.impl; import java.nio.charset.StandardCharsets; +import java.security.InvalidKeyException; +import java.security.NoSuchAlgorithmException; import java.time.Instant; import java.util.Base64; import java.util.Date; @@ -169,7 +171,22 @@ public class DeviceServiceImpl extends BaseServiceImpl DeviceReportRespDTO.Websocket websocket = new DeviceReportRespDTO.Websocket(); // 从系统参数获取WebSocket URL，如果未配置则使用默认值 String wsUrl = sysParamsService.getValue(Constant.SERVER_WEBSOCKET, true); - websocket.setToken(""); + + // 检查是否启用认证并生成token + String authEnabled = sysParamsService.getValue(Constant.SERVER_AUTH_ENABLED, false); + if ("true".equalsIgnoreCase(authEnabled)) { + try { + // 生成token + String token = generateWebSocketToken(clientId, macAddress); + websocket.setToken(token); + } catch (Exception e) { + log.error("生成WebSocket token失败: {}", e.getMessage()); + websocket.setToken(""); + } + } else { + websocket.setToken(""); + } + if (StringUtils.isBlank(wsUrl) || wsUrl.equals("null")) { log.error("WebSocket地址未配置，请登录智控台，在参数管理找到【server.websocket】配置"); wsUrl = "ws://xiaozhi.server.com:8000/xiaozhi/v1/"; @@ -494,6 +511,40 @@ public class DeviceServiceImpl extends BaseServiceImpl return Base64.getEncoder().encodeToString(signature); } + /** + * 生成WebSocket认证token 遵循Python端AuthManager的实现逻辑：token = signature.timestamp + * + * @param clientId 客户端ID + * @param username 用户名 (通常为deviceId/macAddress) + * @return 认证token字符串 + */ + private String generateWebSocketToken(String clientId, String username) + throws NoSuchAlgorithmException, InvalidKeyException { + // 从系统参数获取密钥 + String secretKey = sysParamsService.getValue(Constant.SERVER_SECRET, false); + if (StringUtils.isBlank(secretKey)) { + throw new IllegalStateException("WebSocket认证密钥未配置(server.secret)"); + } + + // 获取当前时间戳(秒) + long timestamp = System.currentTimeMillis() / 1000; + + // 构建签名内容: clientId|username|timestamp + String content = String.format("%s|%s|%d", clientId, username, timestamp); + + // 生成HMAC-SHA256签名 + Mac hmac = Mac.getInstance("HmacSHA256"); + SecretKeySpec keySpec = new SecretKeySpec(secretKey.getBytes(StandardCharsets.UTF_8), "HmacSHA256"); + hmac.init(keySpec); + byte[] signature = hmac.doFinal(content.getBytes(StandardCharsets.UTF_8)); + + // Base64 URL-safe编码签名(去除填充符=) + String signatureBase64 = Base64.getUrlEncoder().withoutPadding().encodeToString(signature); + + // 返回格式: signature.timestamp + return String.format("%s.%d", signatureBase64, timestamp); + } + /** * 构建MQTT配置信息 * diff --git a/main/xiaozhi-server/config/config_loader.py b/main/xiaozhi-server/config/config_loader.py index c85510b8..e0220e33 100644 --- a/main/xiaozhi-server/config/config_loader.py +++ b/main/xiaozhi-server/config/config_loader.py @@ -68,6 +68,7 @@ async def get_config_from_api_async(config): "url": config["manager-api"].get("url", ""), "secret": config["manager-api"].get("secret", ""), } + auth_enabled = config_data.get("server", {}).get("auth", {}).get("enabled", False) # server的配置以本地为准 if config.get("server"): config_data["server"] = { @@ -77,6 +78,7 @@ async def get_config_from_api_async(config): "vision_explain": config["server"].get("vision_explain", ""), "auth_key": config["server"].get("auth_key", ""), } + config_data["server"]["auth"] = {"enabled": auth_enabled} # 如果服务器没有prompt_template，则从本地配置读取 if not config_data.get("prompt_template"): config_data["prompt_template"] = config.get("prompt_template") From fbfc408e94427e70075724ae389fc46e7c6e0cd4 Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Thu, 11 Dec 2025 17:12:56 +0800 Subject: [PATCH 05/39] =?UTF-8?q?update:=20=E9=95=BF=E6=8C=89=E8=AE=BE?= =?UTF-8?q?=E5=A4=87ASR=E9=80=82=E9=85=8D?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/config.yaml | 1 - .../core/handle/reportHandle.py | 1 - .../textHandler/listenMessageHandler.py | 24 +- .../core/providers/asr/aliyun_stream.py | 141 +++++----- .../xiaozhi-server/core/providers/asr/base.py | 27 +- .../core/providers/asr/doubao_stream.py | 66 +++-- .../core/providers/asr/qwen3_asr_flash.py | 3 +- .../core/providers/asr/xunfei_stream.py | 250 +++--------------- .../core/providers/vad/silero.py | 3 +- .../core/utils/opus_encoder_utils.py | 1 - main/xiaozhi-server/core/utils/util.py | 1 - 11 files changed, 195 insertions(+), 323 deletions(-) diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml index 2c005356..e7b61dcd 100644 --- a/main/xiaozhi-server/config.yaml +++ b/main/xiaozhi-server/config.yaml @@ -471,7 +471,6 @@ ASR: domain: slm # 识别领域，iat:日常用语，medical:医疗，finance:金融等 language: zh_cn # 语言，zh_cn:中文，en_us:英文 accent: mandarin # 方言，mandarin:普通话 - dwa: wpgs # 动态修正，wpgs:实时返回中间结果 # 调整音频处理参数以提高长语音识别质量 output_dir: tmp/ diff --git a/main/xiaozhi-server/core/handle/reportHandle.py b/main/xiaozhi-server/core/handle/reportHandle.py index 973ebb38..053e8f2e 100644 --- a/main/xiaozhi-server/core/handle/reportHandle.py +++ b/main/xiaozhi-server/core/handle/reportHandle.py @@ -10,7 +10,6 @@ TTS上报功能已集成到ConnectionHandler类中。 """ import time -import gc import opuslib_next from config.manage_api_client import report as manage_report diff --git a/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py b/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py index 65b442ad..a2c96836 100644 --- a/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py +++ b/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py @@ -1,12 +1,14 @@ import time +import asyncio from typing import Dict, Any -from core.handle.receiveAudioHandle import handleAudioMessage, startToChat +from core.handle.receiveAudioHandle import startToChat from core.handle.reportHandle import enqueue_asr_report from core.handle.sendAudioHandle import send_stt_message, send_tts_message from core.handle.textMessageHandler import TextMessageHandler from core.handle.textMessageType import TextMessageType from core.utils.util import remove_punctuation_and_length +from core.providers.asr.dto.dto import InterfaceType TAG = __name__ @@ -29,14 +31,18 @@ class ListenTextMessageHandler(TextMessageHandler): elif msg_json["state"] == "stop": conn.client_have_voice = True conn.client_voice_stop = True - if len(conn.asr_audio) > 0: - # 手动模式下直接触发ASR识别，不需要再调用handleAudioMessage - asr_audio_task = conn.asr_audio.copy() - conn.asr_audio.clear() - conn.reset_vad_states() - - if len(asr_audio_task) > 0: - await conn.asr.handle_voice_stop(conn, asr_audio_task) + if conn.asr.interface_type == InterfaceType.STREAM: + # 流式模式下，发送结束请求 + asyncio.create_task(conn.asr._send_stop_request()) + else: + # 非流式模式：直接触发ASR识别 + if len(conn.asr_audio) > 0: + asr_audio_task = conn.asr_audio.copy() + conn.asr_audio.clear() + conn.reset_vad_states() + + if len(asr_audio_task) > 0: + await conn.asr.handle_voice_stop(conn, asr_audio_task) elif msg_json["state"] == "detect": conn.client_have_voice = False conn.asr_audio.clear() diff --git a/main/xiaozhi-server/core/providers/asr/aliyun_stream.py b/main/xiaozhi-server/core/providers/asr/aliyun_stream.py index 179685bd..4ce588a7 100644 --- a/main/xiaozhi-server/core/providers/asr/aliyun_stream.py +++ b/main/xiaozhi-server/core/providers/asr/aliyun_stream.py @@ -5,12 +5,9 @@ import hmac import base64 import hashlib import asyncio -import gc import requests import websockets import opuslib_next -import random -from typing import Optional, Tuple, List from urllib import parse from datetime import datetime from config.logger import setup_logging @@ -140,13 +137,13 @@ class ASRProvider(ASRProviderBase): conn.asr_audio.append(audio) conn.asr_audio = conn.asr_audio[-10:] - # 只在有声音且没有连接时建立连接 - if audio_have_voice and not self.is_processing: + # 只在有声音且没有连接时建立连接（排除正在停止的情况） + if audio_have_voice and not self.is_processing and not self.asr_ws: try: await self._start_recognition(conn) except Exception as e: logger.bind(tag=TAG).error(f"开始识别失败: {str(e)}") - await self._cleanup(conn) + await self._cleanup() return if self.asr_ws and self.is_processing and self.server_ready: @@ -186,10 +183,8 @@ class ASRProvider(ASRProviderBase): "header": { "namespace": "SpeechTranscriber", "name": "StartTranscription", - "status": 20000000, "message_id": uuid.uuid4().hex, "task_id": self.task_id, - "status_text": "Gateway:SUCCESS:Success.", "appkey": self.appkey }, "payload": { @@ -208,18 +203,21 @@ class ASRProvider(ASRProviderBase): async def _forward_results(self, conn): """转发识别结果""" try: - while self.asr_ws and not conn.stop_event.is_set(): + while not conn.stop_event.is_set(): try: response = await asyncio.wait_for(self.asr_ws.recv(), timeout=1.0) result = json.loads(response) - + header = result.get("header", {}) payload = result.get("payload", {}) message_name = header.get("name", "") status = header.get("status", 0) - + if status != 20000000: - if status in [40000004, 40010004]: # 连接超时或客户端断开 + if status == 40010004: + logger.bind(tag=TAG).warning(f"请在服务端响应完成后再关闭链接，状态码: {status}") + break + if status in [40000004, 40010003]: # 连接超时或客户端断开 logger.bind(tag=TAG).warning(f"连接问题，状态码: {status}") break elif status in [40270002, 40270003]: # 音频问题 @@ -228,12 +226,12 @@ class ASRProvider(ASRProviderBase): else: logger.bind(tag=TAG).error(f"识别错误，状态码: {status}, 消息: {header.get('status_text', '')}") continue - + # 收到TranscriptionStarted表示服务器准备好接收音频数据 if message_name == "TranscriptionStarted": self.server_ready = True logger.bind(tag=TAG).debug("服务器已准备，开始发送缓存音频...") - + # 发送缓存音频 if conn.asr_audio: for cached_audio in conn.asr_audio[-10:]: @@ -244,89 +242,89 @@ class ASRProvider(ASRProviderBase): logger.bind(tag=TAG).warning(f"发送缓存音频失败: {e}") break continue - - if message_name == "TranscriptionResultChanged": - # 中间结果 - text = payload.get("result", "") - if text: - self.text = text elif message_name == "SentenceEnd": - # 最终结果 + # 句子结束（每个句子都会触发） text = payload.get("result", "") if text: - self.text = text - conn.reset_vad_states() - # 传递缓存的音频数据 - audio_data = getattr(conn, 'asr_audio_for_voiceprint', []) - await self.handle_voice_stop(conn, audio_data) - # 清空缓存 - conn.asr_audio_for_voiceprint = [] - break - elif message_name == "TranscriptionCompleted": - # 识别完成 - self.is_processing = False - break - + logger.bind(tag=TAG).info(f"识别到文本: {text}") + + # 手动模式下累积识别结果 + if conn.client_listen_mode == "manual": + if self.text: + self.text += text + else: + self.text = text + + # 手动模式下，只有在收到stop信号后才触发处理（仅处理一次） + if conn.client_voice_stop: + 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) + # 清理音频缓存 + conn.asr_audio.clear() + conn.reset_vad_states() + break + else: + # 自动模式下直接覆盖 + self.text = text + conn.reset_vad_states() + audio_data = getattr(conn, 'asr_audio_for_voiceprint', []) + await self.handle_voice_stop(conn, audio_data) + break + except asyncio.TimeoutError: - continue - except websockets.exceptions.ConnectionClosed: + logger.bind(tag=TAG).error("接收结果超时") + break + except websockets.ConnectionClosed: + logger.bind(tag=TAG).info("ASR服务连接已关闭") + self.is_processing = False break except Exception as e: logger.bind(tag=TAG).error(f"处理结果失败: {str(e)}") break - + except Exception as e: logger.bind(tag=TAG).error(f"结果转发失败: {str(e)}") finally: - await self._cleanup(conn) + # 清理连接的音频缓存 + await self._cleanup() + if conn: + if hasattr(conn, 'asr_audio_for_voiceprint'): + conn.asr_audio_for_voiceprint = [] + if hasattr(conn, 'asr_audio'): + conn.asr_audio = [] - async def _cleanup(self, conn): - """清理资源""" - logger.bind(tag=TAG).debug(f"开始ASR会话清理 | 当前状态: processing={self.is_processing}, server_ready={self.server_ready}") - - # 清理连接的音频缓存 - if conn and hasattr(conn, 'asr_audio_for_voiceprint'): - conn.asr_audio_for_voiceprint = [] - - # 判断是否需要发送终止请求 - should_stop = self.is_processing or self.server_ready - - # 发送停止识别请求 - if self.asr_ws and should_stop: + async def _send_stop_request(self): + """发送停止识别请求（不关闭连接）""" + if self.asr_ws: try: + # 先停止音频发送 + self.is_processing = False + stop_msg = { "header": { "namespace": "SpeechTranscriber", "name": "StopTranscription", - "status": 20000000, "message_id": uuid.uuid4().hex, "task_id": self.task_id, - "status_text": "Client:Stop", "appkey": self.appkey } } - logger.bind(tag=TAG).debug("正在发送ASR终止请求") + logger.bind(tag=TAG).debug("停止识别请求已发送") await self.asr_ws.send(json.dumps(stop_msg, ensure_ascii=False)) - await asyncio.sleep(0.1) - logger.bind(tag=TAG).debug("ASR终止请求已发送") except Exception as e: - logger.bind(tag=TAG).error(f"ASR终止请求发送失败: {e}") - - # 状态重置（在终止请求发送后） + logger.bind(tag=TAG).error(f"发送停止识别请求失败: {e}") + + async def _cleanup(self): + """清理资源（关闭连接）""" + logger.bind(tag=TAG).debug(f"开始ASR会话清理 | 当前状态: processing={self.is_processing}, server_ready={self.server_ready}") + + # 状态重置 self.is_processing = False self.server_ready = False logger.bind(tag=TAG).debug("ASR状态已重置") - # 清理任务 - if self.forward_task and not self.forward_task.done(): - self.forward_task.cancel() - try: - await asyncio.wait_for(self.forward_task, timeout=1.0) - except Exception as e: - logger.bind(tag=TAG).debug(f"forward_task取消异常: {e}") - finally: - self.forward_task = None - # 关闭连接 if self.asr_ws: try: @@ -337,7 +335,10 @@ class ASRProvider(ASRProviderBase): logger.bind(tag=TAG).error(f"关闭WebSocket连接失败: {e}") finally: self.asr_ws = None - + + # 清理任务引用 + self.forward_task = None + logger.bind(tag=TAG).debug("ASR会话清理完成") async def speech_to_text(self, opus_data, session_id, audio_format): diff --git a/main/xiaozhi-server/core/providers/asr/base.py b/main/xiaozhi-server/core/providers/asr/base.py index 6c3c2d25..671484e9 100644 --- a/main/xiaozhi-server/core/providers/asr/base.py +++ b/main/xiaozhi-server/core/providers/asr/base.py @@ -10,7 +10,6 @@ import traceback import threading import opuslib_next import concurrent.futures -import gc from abc import ABC, abstractmethod from config.logger import setup_logging from typing import Optional, Tuple, List @@ -54,30 +53,26 @@ class ASRProviderBase(ABC): # 接收音频 async def receive_audio(self, conn, audio, audio_have_voice): - if conn.client_listen_mode == "auto" or conn.client_listen_mode == "realtime": + if conn.client_listen_mode == "manual": + # 手动模式：缓存音频用于ASR识别 + conn.asr_audio.append(audio) + else: + # 自动/实时模式：使用VAD检测 have_voice = audio_have_voice - + conn.asr_audio.append(audio) if not have_voice and not conn.client_have_voice: conn.asr_audio = conn.asr_audio[-10:] return - else: - # 手动模式：总是缓存音频，忽略VAD检测结果 - conn.asr_audio.append(audio) - if conn.client_voice_stop: - asr_audio_task = conn.asr_audio.copy() - conn.asr_audio.clear() - conn.reset_vad_states() + # 自动模式下通过VAD检测到语音停止时触发识别 + if conn.client_voice_stop: + asr_audio_task = conn.asr_audio.copy() + conn.asr_audio.clear() + conn.reset_vad_states() - # 手动模式下允许短语音识别，自动模式保持原有限制 - if conn.client_listen_mode == "auto" or conn.client_listen_mode == "realtime": if len(asr_audio_task) > 15: await self.handle_voice_stop(conn, asr_audio_task) - else: - # 手动模式：只要有音频就进行识别 - if len(asr_audio_task) > 0: - 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]): diff --git a/main/xiaozhi-server/core/providers/asr/doubao_stream.py b/main/xiaozhi-server/core/providers/asr/doubao_stream.py index 2d179b86..e141e25d 100644 --- a/main/xiaozhi-server/core/providers/asr/doubao_stream.py +++ b/main/xiaozhi-server/core/providers/asr/doubao_stream.py @@ -4,7 +4,6 @@ import uuid import asyncio import websockets import opuslib_next -import gc from core.providers.asr.base import ASRProviderBase from config.logger import setup_logging from core.providers.asr.dto.dto import InterfaceType @@ -19,8 +18,6 @@ class ASRProvider(ASRProviderBase): self.interface_type = InterfaceType.STREAM self.config = config self.text = "" - self.max_retries = 3 - self.retry_delay = 2 self.decoder = opuslib_next.Decoder(16000, 1) self.asr_ws = None self.forward_task = None @@ -57,14 +54,13 @@ class ASRProvider(ASRProviderBase): async def receive_audio(self, conn, 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'): 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 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 = [] @@ -180,6 +176,7 @@ class ASRProvider(ASRProviderBase): payload.get("audio_info", {}).get("duration", 0) > 2000 and not utterances and not payload["result"].get("text") + and conn.client_listen_mode != "manual" ): logger.bind(tag=TAG).error(f"识别文本：空") self.text = "" @@ -188,15 +185,44 @@ class ASRProvider(ASRProviderBase): await self.handle_voice_stop(conn, audio_data) break + # 专门处理没有文本的识别结果（手动模式下可能已经识别完成但是没松按键） + elif not payload["result"].get("text") and not utterances: + if 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() + conn.reset_vad_states() + break + for utterance in utterances: if utterance.get("definite", False): - self.text = utterance["text"] + current_text = utterance["text"] logger.bind(tag=TAG).info( - f"识别到文本: {self.text}" + f"识别到文本: {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) + + # 手动模式下累积识别结果 + if conn.client_listen_mode == "manual": + if self.text: + self.text += current_text + else: + 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) + # 清理音频缓存 + conn.asr_audio.clear() + conn.reset_vad_states() + break + else: + # 自动模式下直接覆盖 + 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) break elif "error" in payload: error_msg = payload.get("error", "未知错误") @@ -228,8 +254,6 @@ class ASRProvider(ASRProviderBase): conn.asr_audio_for_voiceprint = [] if hasattr(conn, 'asr_audio'): conn.asr_audio = [] - if hasattr(conn, 'has_valid_voice'): - conn.has_valid_voice = False def stop_ws_connection(self): if self.asr_ws: @@ -237,6 +261,20 @@ class ASRProvider(ASRProviderBase): self.asr_ws = None self.is_processing = False + async def _send_stop_request(self): + """发送最后一个音频帧以通知服务器结束""" + if self.asr_ws: + 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.extend(len(empty_payload).to_bytes(4, "big")) + last_audio_request.extend(empty_payload) + await self.asr_ws.send(last_audio_request) + logger.bind(tag=TAG).debug("已发送结束音频帧") + except Exception as e: + logger.bind(tag=TAG).debug(f"发送结束音频帧时出错: {e}") + def construct_request(self, reqid): req = { "app": { @@ -388,5 +426,3 @@ class ASRProvider(ASRProviderBase): conn.asr_audio_for_voiceprint = [] if hasattr(conn, 'asr_audio'): conn.asr_audio = [] - if hasattr(conn, 'has_valid_voice'): - conn.has_valid_voice = False diff --git a/main/xiaozhi-server/core/providers/asr/qwen3_asr_flash.py b/main/xiaozhi-server/core/providers/asr/qwen3_asr_flash.py index 7101448d..51c84a37 100644 --- a/main/xiaozhi-server/core/providers/asr/qwen3_asr_flash.py +++ b/main/xiaozhi-server/core/providers/asr/qwen3_asr_flash.py @@ -13,7 +13,8 @@ logger = setup_logging() class ASRProvider(ASRProviderBase): def __init__(self, config: dict, delete_audio_file: bool): super().__init__() - self.interface_type = InterfaceType.STREAM + # 音频文件上传类型，流式文本识别输出 + self.interface_type = InterfaceType.NON_STREAM """Qwen3-ASR-Flash ASR初始化""" # 配置参数 diff --git a/main/xiaozhi-server/core/providers/asr/xunfei_stream.py b/main/xiaozhi-server/core/providers/asr/xunfei_stream.py index 6a895ebc..b7e7886e 100644 --- a/main/xiaozhi-server/core/providers/asr/xunfei_stream.py +++ b/main/xiaozhi-server/core/providers/asr/xunfei_stream.py @@ -35,9 +35,6 @@ class ASRProvider(ASRProviderBase): self.forward_task = None self.is_processing = False self.server_ready = False - self.last_frame_sent = False # 标记是否已发送最终帧 - self.best_text = "" # 保存最佳识别结果 - self.has_final_result = False # 标记是否收到最终识别结果 # 讯飞配置 self.app_id = config.get("app_id") @@ -52,7 +49,6 @@ class ASRProvider(ASRProviderBase): "domain": config.get("domain", "slm"), "language": config.get("language", "zh_cn"), "accent": config.get("accent", "mandarin"), - "dwa": config.get("dwa", "wpgs"), "result": {"encoding": "utf8", "compress": "raw", "format": "plain"}, } @@ -116,7 +112,7 @@ class ASRProvider(ASRProviderBase): await self._start_recognition(conn) except Exception as e: logger.bind(tag=TAG).error(f"建立ASR连接失败: {str(e)}") - await self._cleanup(conn) + await self._cleanup() return # 发送当前音频数据 @@ -126,7 +122,7 @@ class ASRProvider(ASRProviderBase): await self._send_audio_frame(pcm_frame, STATUS_CONTINUE_FRAME) except Exception as e: logger.bind(tag=TAG).warning(f"发送音频数据时发生错误: {e}") - await self._cleanup(conn) + await self._cleanup() async def _start_recognition(self, conn): """开始识别会话""" @@ -136,6 +132,10 @@ class ASRProvider(ASRProviderBase): ws_url = self.create_url() logger.bind(tag=TAG).info(f"正在连接ASR服务: {ws_url[:50]}...") + # 如果为手动模式,设置超时时长为一分钟 + if conn.client_listen_mode == "manual": + self.iat_params["eos"] = 60000 + self.asr_ws = await websockets.connect( ws_url, max_size=1000000000, @@ -146,8 +146,6 @@ class ASRProvider(ASRProviderBase): logger.bind(tag=TAG).info("ASR WebSocket连接已建立") self.server_ready = False - self.last_frame_sent = False - self.best_text = "" self.forward_task = asyncio.create_task(self._forward_results(conn)) # 发送首帧音频 @@ -196,23 +194,12 @@ class ASRProvider(ASRProviderBase): await self.asr_ws.send(json.dumps(frame_data, ensure_ascii=False)) - # 标记是否发送了最终帧 - if status == STATUS_LAST_FRAME: - self.last_frame_sent = True - logger.bind(tag=TAG).info("标记最终帧已发送") - async def _forward_results(self, conn): """转发识别结果""" 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", []) + while not conn.stop_event.is_set(): try: - # 如果已发送最终帧，增加超时时间等待完整结果 - timeout = 3.0 if self.last_frame_sent else 30.0 - response = await asyncio.wait_for( - self.asr_ws.recv(), timeout=timeout - ) + response = await asyncio.wait_for(self.asr_ws.recv(), timeout=60) result = json.loads(response) logger.bind(tag=TAG).debug(f"收到ASR结果: {result}") @@ -236,144 +223,27 @@ class ASRProvider(ASRProviderBase): # 解码base64文本 decoded_text = base64.b64decode(text_data).decode("utf-8") text_json = json.loads(decoded_text) - # 提取文本内容 text_ws = text_json.get("ws", []) - result_text = "" for i in text_ws: for j in i.get("cw", []): w = j.get("w", "") - result_text += w + self.text += w - # 更新识别文本 - 实时更新策略 - # 只检查是否为空字符串，不再过滤任何标点符号 - # 这样可以确保所有识别到的内容，包括标点符号都能被实时更新 - if result_text and result_text.strip(): - # 实时更新：正常情况下都更新，提高响应速度 - should_update = True - - # 保存最佳文本 - # 1. 如果是识别完成状态或最终帧后收到的结果，优先保存 - # 2. 否则保存最长的有意义文本 - # 取消对标点符号的过滤，只检查是否为空 - # 这样可以保留所有识别到的内容，包括各种标点符号 - is_valid_text = len(result_text.strip()) > 0 - - if ( - self.last_frame_sent or status == 2 - ) and is_valid_text: - self.best_text = result_text - self.has_final_result = True # 标记已收到最终结果 - logger.bind(tag=TAG).debug( - f"保存最终识别结果: {self.best_text}" - ) - elif ( - len(result_text) > len(self.best_text) - and is_valid_text - and not self.has_final_result - ): - self.best_text = result_text - logger.bind(tag=TAG).debug( - f"保存中间最佳文本: {self.best_text}" - ) - - # 如果已发送最终帧，只过滤空文本 - if self.last_frame_sent: - # 只拒绝完全空的结果 - if not result_text.strip(): - should_update = False - logger.bind(tag=TAG).warning( - f"最终帧后拒绝空文本" - ) - - if should_update: - # 处理流式识别结果，避免简单替换导致内容丢失 - # 1. 如果是中间状态（非最终帧后），可能需要替换为更完整的识别 - # 2. 如果是最终帧后收到的结果，可能是对前面文本的补充 - if self.last_frame_sent: - # 最终帧后收到的结果可能是标点符号等补充内容 - # 检查是否需要合并文本而不是替换 - # 如果当前文本是纯标点而前面已有内容，应该追加而不是替换 - if len( - self.text - ) > 0 and result_text.strip() in [ - "。", - ".", - "?", - "？", - "!", - "！", - ",", - "，", - ";", - "；", - ]: - # 对于标点符号，追加到现有文本后 - self.text = ( - self.text.rstrip().rstrip("。.") - + result_text - ) - else: - # 其他情况保持替换逻辑 - self.text = result_text - else: - # 中间状态替换为新的识别结果 - self.text = result_text - - logger.bind(tag=TAG).info( - f"实时更新识别文本: {self.text} (最终帧已发送: {self.last_frame_sent})" - ) - - # 识别完成，但如果还没发送最终帧，继续等待 if status == 2: - logger.bind(tag=TAG).info( - f"识别完成状态已到达，当前识别文本: {self.text}" - ) - - # 如果还没发送最终帧，继续等待 - if not self.last_frame_sent: - logger.bind(tag=TAG).info( - "识别完成但最终帧未发送，继续等待..." - ) - continue - - # 已发送最终帧且收到完成状态，使用最佳策略选择最终结果 - # 优先使用识别完成状态下的最新结果，而不是仅仅基于长度 - if self.best_text: - # 如果当前文本是在最终帧发送后或识别完成状态下收到的，优先使用 - if ( - self.last_frame_sent or status == 2 - ) and self.text.strip(): - logger.bind(tag=TAG).info( - f"使用完成状态下的最新识别结果: {self.text}" - ) - elif len(self.best_text) > len(self.text): - logger.bind(tag=TAG).info( - f"使用更长的最佳文本作为最终结果: {self.text} -> {self.best_text}" - ) - self.text = self.best_text - - logger.bind(tag=TAG).info(f"获取到最终完整文本: {self.text}") + if conn.client_listen_mode == "manual": + 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) + # 清理音频缓存 + conn.asr_audio.clear() conn.reset_vad_states() - if len(audio_data) > 15: # 确保有足够音频数据 - # 准备处理结果 - pass break except asyncio.TimeoutError: - if self.last_frame_sent: - # 超时时也使用最佳文本 - if self.best_text and len(self.best_text) > len(self.text): - logger.bind(tag=TAG).info( - f"超时，使用最佳文本: {self.text} -> {self.best_text}" - ) - self.text = self.best_text - logger.bind(tag=TAG).info( - f"最终帧后超时，使用结果: {self.text}" - ) - break - # 如果还没发送最终帧，继续等待 - continue + logger.bind(tag=TAG).error("接收结果超时") + break except websockets.ConnectionClosed: logger.bind(tag=TAG).info("ASR服务连接已关闭") self.is_processing = False @@ -390,17 +260,15 @@ class ASRProvider(ASRProviderBase): if hasattr(e, "__cause__") and e.__cause__: logger.bind(tag=TAG).error(f"错误原因: {str(e.__cause__)}") finally: - if self.asr_ws: - await self.asr_ws.close() - self.asr_ws = None - self.is_processing = False + # 清理连接资源 + await self._cleanup() + + # 清理连接的音频缓存 if conn: if hasattr(conn, "asr_audio_for_voiceprint"): conn.asr_audio_for_voiceprint = [] if hasattr(conn, "asr_audio"): conn.asr_audio = [] - if hasattr(conn, "has_valid_voice"): - conn.has_valid_voice = False async def handle_voice_stop(self, conn, asr_audio_task: List[bytes]): """处理语音停止，发送最后一帧并处理识别结果""" @@ -408,22 +276,13 @@ class ASRProvider(ASRProviderBase): # 先发送最后一帧表示音频结束 if self.asr_ws and self.is_processing: try: - # 取最后一个有效的音频帧作为最后一帧数据 - last_frame = b"" - if asr_audio_task: - last_audio = asr_audio_task[-1] - last_frame = self.decoder.decode(last_audio, 960) - await self._send_audio_frame(last_frame, STATUS_LAST_FRAME) - logger.bind(tag=TAG).info("已发送最后一帧") + await self._send_audio_frame(b"", STATUS_LAST_FRAME) + logger.bind(tag=TAG).debug(f"已发送停止请求") - # 发送最终帧后，给_forward_results适当时间处理最终结果 await asyncio.sleep(0.25) - - logger.bind(tag=TAG).info(f"准备处理最终识别结果: {self.text}") except Exception as e: - logger.bind(tag=TAG).error(f"发送最后一帧失败: {e}") + logger.bind(tag=TAG).error(f"发送停止请求失败: {e}") - # 调用父类的handle_voice_stop方法处理识别结果 await super().handle_voice_stop(conn, asr_audio_task) except Exception as e: logger.bind(tag=TAG).error(f"处理语音停止失败: {e}") @@ -437,40 +296,27 @@ class ASRProvider(ASRProviderBase): self.asr_ws = None self.is_processing = False - async def _cleanup(self, conn): - """清理资源""" - logger.bind(tag=TAG).info( + async def _send_stop_request(self): + """发送停止识别请求（不关闭连接）""" + if self.asr_ws: + try: + # 先停止音频发送 + self.is_processing = False + await self._send_audio_frame(b"", STATUS_LAST_FRAME) + logger.bind(tag=TAG).debug("已发送停止请求") + except Exception as e: + logger.bind(tag=TAG).error(f"发送停止请求失败: {e}") + + async def _cleanup(self): + """清理资源（关闭连接）""" + logger.bind(tag=TAG).debug( f"开始ASR会话清理 | 当前状态: processing={self.is_processing}, server_ready={self.server_ready}" ) - # 发送最后一帧 - if self.asr_ws and self.is_processing: - try: - await self._send_audio_frame(b"", STATUS_LAST_FRAME) - await asyncio.sleep(0.1) - logger.bind(tag=TAG).info("已发送最后一帧") - except Exception as e: - logger.bind(tag=TAG).error(f"发送最后一帧失败: {e}") - # 状态重置 self.is_processing = False self.server_ready = False - self.last_frame_sent = False - self.best_text = "" - self.has_final_result = False - logger.bind(tag=TAG).info("ASR状态已重置") - - # 清理任务 - if self.forward_task and not self.forward_task.done(): - self.forward_task.cancel() - try: - await asyncio.wait_for(self.forward_task, timeout=1.0) - except asyncio.CancelledError: - pass - except Exception as e: - logger.bind(tag=TAG).debug(f"forward_task取消异常: {e}") - finally: - self.forward_task = None + logger.bind(tag=TAG).debug("ASR状态已重置") # 关闭连接 if self.asr_ws: @@ -483,16 +329,10 @@ class ASRProvider(ASRProviderBase): finally: self.asr_ws = None - # 清理连接的音频缓存 - if conn: - if hasattr(conn, "asr_audio_for_voiceprint"): - conn.asr_audio_for_voiceprint = [] - if hasattr(conn, "asr_audio"): - conn.asr_audio = [] - if hasattr(conn, "has_valid_voice"): - conn.has_valid_voice = False + # 清理任务引用 + self.forward_task = None - logger.bind(tag=TAG).info("ASR会话清理完成") + logger.bind(tag=TAG).debug("ASR会话清理完成") async def speech_to_text(self, opus_data, session_id, audio_format): """获取识别结果""" @@ -513,7 +353,7 @@ 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: try: @@ -530,5 +370,3 @@ class ASRProvider(ASRProviderBase): conn.asr_audio_for_voiceprint = [] if hasattr(conn, "asr_audio"): conn.asr_audio = [] - if hasattr(conn, "has_valid_voice"): - conn.has_valid_voice = False diff --git a/main/xiaozhi-server/core/providers/vad/silero.py b/main/xiaozhi-server/core/providers/vad/silero.py index 28a3e61e..81215681 100644 --- a/main/xiaozhi-server/core/providers/vad/silero.py +++ b/main/xiaozhi-server/core/providers/vad/silero.py @@ -2,7 +2,6 @@ import time import numpy as np import torch import opuslib_next -import gc from config.logger import setup_logging from core.providers.vad.base import VADProviderBase @@ -46,7 +45,7 @@ class VADProvider(VADProviderBase): def is_vad(self, conn, opus_packet): # 手动模式：直接返回True，不进行实时VAD检测，所有音频都缓存 - if conn.client_listen_mode not in ["auto", "realtime"]: + if conn.client_listen_mode == "manual": return True try: diff --git a/main/xiaozhi-server/core/utils/opus_encoder_utils.py b/main/xiaozhi-server/core/utils/opus_encoder_utils.py index f2fcc266..8d603e22 100644 --- a/main/xiaozhi-server/core/utils/opus_encoder_utils.py +++ b/main/xiaozhi-server/core/utils/opus_encoder_utils.py @@ -6,7 +6,6 @@ Opus编码工具类 import logging import traceback import numpy as np -import gc from opuslib_next import Encoder from opuslib_next import constants from typing import Optional, Callable, Any diff --git a/main/xiaozhi-server/core/utils/util.py b/main/xiaozhi-server/core/utils/util.py index 37388be8..f72dda2c 100644 --- a/main/xiaozhi-server/core/utils/util.py +++ b/main/xiaozhi-server/core/utils/util.py @@ -8,7 +8,6 @@ import requests import subprocess import numpy as np import opuslib_next -import gc from io import BytesIO from core.utils import p3 from pydub import AudioSegment From f88abd7638acb6724531fe4b9f09f4afc53194aa Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Fri, 12 Dec 2025 09:46:15 +0800 Subject: [PATCH 06/39] =?UTF-8?q?fix:=20=E8=81=86=E5=90=AC=E8=AE=BE?= =?UTF-8?q?=E5=A4=87=E8=AF=AF=E8=A7=A6=E5=8F=91?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/core/providers/asr/doubao_stream.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/main/xiaozhi-server/core/providers/asr/doubao_stream.py b/main/xiaozhi-server/core/providers/asr/doubao_stream.py index e141e25d..0c1cf727 100644 --- a/main/xiaozhi-server/core/providers/asr/doubao_stream.py +++ b/main/xiaozhi-server/core/providers/asr/doubao_stream.py @@ -187,7 +187,7 @@ class ASRProvider(ASRProviderBase): # 专门处理没有文本的识别结果（手动模式下可能已经识别完成但是没松按键） elif not payload["result"].get("text") and not utterances: - if conn.client_voice_stop and len(audio_data) > 0: + 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 From c8d2d2255db5ceb16c8256f16d00d62c41926a09 Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Fri, 12 Dec 2025 15:08:40 +0800 Subject: [PATCH 07/39] =?UTF-8?q?fix:=20=E9=9F=B3=E9=A2=91=E5=BD=B1?= =?UTF-8?q?=E5=93=8D=E7=BA=BF=E7=A8=8B=E9=97=AE=E9=A2=98?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../xiaozhi-server/core/providers/asr/base.py | 102 ++++++------------ 1 file changed, 33 insertions(+), 69 deletions(-) diff --git a/main/xiaozhi-server/core/providers/asr/base.py b/main/xiaozhi-server/core/providers/asr/base.py index 671484e9..6c6969fd 100644 --- a/main/xiaozhi-server/core/providers/asr/base.py +++ b/main/xiaozhi-server/core/providers/asr/base.py @@ -9,7 +9,6 @@ import asyncio import traceback import threading import opuslib_next -import concurrent.futures from abc import ABC, abstractmethod from config.logger import setup_logging from typing import Optional, Tuple, List @@ -79,98 +78,63 @@ class ASRProviderBase(ABC): """并行处理ASR和声纹识别""" try: total_start_time = time.monotonic() - + # 准备音频数据 if conn.audio_format == "pcm": pcm_data = asr_audio_task else: pcm_data = self.decode_opus(asr_audio_task) - + combined_pcm_data = b"".join(pcm_data) - + # 预先准备WAV数据 wav_data = None if conn.voiceprint_provider and combined_pcm_data: wav_data = self._pcm_to_wav(combined_pcm_data) - + # 定义ASR任务 - def run_asr(): - start_time = time.monotonic() - try: - loop = asyncio.new_event_loop() - asyncio.set_event_loop(loop) - try: - result = loop.run_until_complete( - self.speech_to_text(asr_audio_task, conn.session_id, conn.audio_format) - ) - end_time = time.monotonic() - logger.bind(tag=TAG).debug(f"ASR耗时: {end_time - start_time:.3f}s") - return result - finally: - loop.close() - except Exception as e: - end_time = time.monotonic() - logger.bind(tag=TAG).error(f"ASR失败: {e}") - return ("", None) - - # 定义声纹识别任务 - def run_voiceprint(): - if not wav_data: - return None - try: - loop = asyncio.new_event_loop() - asyncio.set_event_loop(loop) - try: - # 使用连接的声纹识别提供者 - result = loop.run_until_complete( - conn.voiceprint_provider.identify_speaker(wav_data, conn.session_id) - ) - return result - finally: - loop.close() - except Exception as e: - logger.bind(tag=TAG).error(f"声纹识别失败: {e}") - return None - - # 使用线程池执行器并行运行 - with concurrent.futures.ThreadPoolExecutor(max_workers=2) as thread_executor: - asr_future = thread_executor.submit(run_asr) - - if conn.voiceprint_provider and wav_data: - voiceprint_future = thread_executor.submit(run_voiceprint) - - # 等待两个线程都完成 - asr_result = asr_future.result(timeout=15) - voiceprint_result = voiceprint_future.result(timeout=15) - - results = {"asr": asr_result, "voiceprint": voiceprint_result} - else: - asr_result = asr_future.result(timeout=15) - results = {"asr": asr_result, "voiceprint": None} - - - # 处理结果 - raw_text, _ = results.get("asr", ("", None)) - speaker_name = results.get("voiceprint", None) - - # 记录识别结果 + asr_task = self.speech_to_text(asr_audio_task, conn.session_id, conn.audio_format) + + if conn.voiceprint_provider and wav_data: + voiceprint_task = conn.voiceprint_provider.identify_speaker(wav_data, conn.session_id) + # 并发等待两个结果 + asr_result, voiceprint_result = await asyncio.gather( + asr_task, voiceprint_task, return_exceptions=True + ) + else: + asr_result = await asr_task + voiceprint_result = None + + # 记录识别结果 - 检查是否为异常 + if isinstance(asr_result, Exception): + logger.bind(tag=TAG).error(f"ASR识别失败: {asr_result}") + raw_text = "" + else: + raw_text, _ = asr_result + + if isinstance(voiceprint_result, Exception): + logger.bind(tag=TAG).error(f"声纹识别失败: {voiceprint_result}") + speaker_name = "" + else: + speaker_name = voiceprint_result + if raw_text: logger.bind(tag=TAG).info(f"识别文本: {raw_text}") if speaker_name: logger.bind(tag=TAG).info(f"识别说话人: {speaker_name}") - + # 性能监控 total_time = time.monotonic() - total_start_time logger.bind(tag=TAG).debug(f"总处理耗时: {total_time:.3f}s") - + # 检查文本长度 text_len, _ = remove_punctuation_and_length(raw_text) self.stop_ws_connection() - + if text_len > 0: # 构建包含说话人信息的JSON字符串 enhanced_text = self._build_enhanced_text(raw_text, speaker_name) - + # 使用自定义模块进行上报 await startToChat(conn, enhanced_text) enqueue_asr_report(conn, enhanced_text, asr_audio_task) From 20f601e6071641aae574da0ea3d08ea1d93881ff Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Fri, 12 Dec 2025 15:39:30 +0800 Subject: [PATCH 08/39] =?UTF-8?q?fix:=20=E5=90=8C=E6=AD=A5=E6=96=B9?= =?UTF-8?q?=E6=B3=95=E4=BD=BF=E7=94=A8=E7=BA=BF=E7=A8=8B=E6=B1=A0=E9=81=BF?= =?UTF-8?q?=E5=85=8D=E9=98=BB=E5=A1=9E?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../core/providers/asr/fun_local.py | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/main/xiaozhi-server/core/providers/asr/fun_local.py b/main/xiaozhi-server/core/providers/asr/fun_local.py index 217f17ff..2fd49c36 100644 --- a/main/xiaozhi-server/core/providers/asr/fun_local.py +++ b/main/xiaozhi-server/core/providers/asr/fun_local.py @@ -1,14 +1,16 @@ -import time import os -import sys import io +import sys +import time +import shutil import psutil +import asyncio + from config.logger import setup_logging from typing import Optional, Tuple, List -from core.providers.asr.base import ASRProviderBase from funasr import AutoModel from funasr.utils.postprocess_utils import rich_transcription_postprocess -import shutil +from core.providers.asr.base import ASRProviderBase from core.providers.asr.dto.dto import InterfaceType TAG = __name__ @@ -90,16 +92,17 @@ class ASRProvider(ASRProviderBase): else: file_path = self.save_audio_to_file(pcm_data, session_id) - # 语音识别 + # 语音识别 - 使用线程池避免阻塞事件循环 start_time = time.time() - result = self.model.generate( + result = await asyncio.to_thread( + self.model.generate, input=combined_pcm_data, cache={}, language="auto", use_itn=True, batch_size_s=60, ) - text = rich_transcription_postprocess(result[0]["text"]) + text = await asyncio.to_thread(rich_transcription_postprocess, result[0]["text"]) logger.bind(tag=TAG).debug( f"语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text}" ) From 5dbf796fa931efe15ec217a7ab170fdda9fde676 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Fri, 12 Dec 2025 16:33:50 +0800 Subject: [PATCH 09/39] =?UTF-8?q?update:=E6=9B=B4=E6=96=B0=E7=89=88?= =?UTF-8?q?=E6=9C=AC=E5=8F=B7?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../src/main/java/xiaozhi/common/constant/Constant.java | 2 +- main/manager-mobile/src/pages/settings/index.vue | 2 +- main/xiaozhi-server/config/logger.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java b/main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java index 1ea19355..917f1e50 100644 --- a/main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java +++ b/main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java @@ -299,7 +299,7 @@ public interface Constant { /** * 版本号 */ - public static final String VERSION = "0.8.9"; + public static final String VERSION = "0.8.10"; /** * 无效固件URL diff --git a/main/manager-mobile/src/pages/settings/index.vue b/main/manager-mobile/src/pages/settings/index.vue index 2f7be6b4..b1fa487b 100644 --- a/main/manager-mobile/src/pages/settings/index.vue +++ b/main/manager-mobile/src/pages/settings/index.vue @@ -235,7 +235,7 @@ function showAbout() { title: t('settings.aboutApp', { appName: import.meta.env.VITE_APP_TITLE }), content: t('settings.aboutContent', { appName: import.meta.env.VITE_APP_TITLE, - version: '0.8.9' + version: '0.8.10' }), showCancel: false, confirmText: t('common.confirm'), diff --git a/main/xiaozhi-server/config/logger.py b/main/xiaozhi-server/config/logger.py index a0b64dd7..bf64893c 100644 --- a/main/xiaozhi-server/config/logger.py +++ b/main/xiaozhi-server/config/logger.py @@ -5,7 +5,7 @@ from config.config_loader import load_config from config.settings import check_config_file from datetime import datetime -SERVER_VERSION = "0.8.9" +SERVER_VERSION = "0.8.10" _logger_initialized = False From 85e65cf9e8f9363dac1f244dbef3d21b10766590 Mon Sep 17 00:00:00 2001 From: shiyin Date: Fri, 12 Dec 2025 18:28:46 +0800 Subject: [PATCH 10/39] =?UTF-8?q?fix:=E5=88=9D=E5=A7=8B=E5=8C=96ASR?= =?UTF-8?q?=E6=97=B6,=E5=88=A4=E6=96=ADASR=E7=B1=BB=E5=9E=8B=E5=8F=96?= =?UTF-8?q?=E5=80=BC=E9=94=99=E8=AF=AF=E4=BF=AE=E5=A4=8D?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/core/connection.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py index b37745c7..9805fb5e 100644 --- a/main/xiaozhi-server/core/connection.py +++ b/main/xiaozhi-server/core/connection.py @@ -496,7 +496,7 @@ class ConnectionHandler: def _initialize_asr(self): """初始化ASR""" - if self._asr.interface_type == InterfaceType.LOCAL: + if self._asr is not None and hasattr(self._asr, "interface_type") and self._asr.interface_type == InterfaceType.LOCAL: # 如果公共ASR是本地服务，则直接返回 # 因为本地一个实例ASR，可以被多个连接共享 asr = self._asr From dc170edbc18e2d0b36dcc130a18b5a2a0544329c Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Fri, 12 Dec 2025 18:58:24 +0800 Subject: [PATCH 11/39] =?UTF-8?q?update:=20=E6=9C=AA=E7=BB=91=E5=AE=9A?= =?UTF-8?q?=E8=AE=BE=E5=A4=87=E7=AD=96=E7=95=A5=E4=BC=98=E5=8C=96=20fix:?= =?UTF-8?q?=20=E9=9F=B3=E9=A2=91=E9=98=9F=E5=88=97=E7=AB=9E=E6=80=81?= =?UTF-8?q?=E9=97=AE=E9=A2=98?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/core/connection.py | 48 +++++++++++-------- .../core/utils/audioRateController.py | 29 ++++------- 2 files changed, 38 insertions(+), 39 deletions(-) diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py index b37745c7..2a6a8168 100644 --- a/main/xiaozhi-server/core/connection.py +++ b/main/xiaozhi-server/core/connection.py @@ -68,7 +68,8 @@ class ConnectionHandler: self.logger = setup_logging() self.server = server # 保存server实例的引用 - self.need_bind = False # 是否需要绑定设备 + self.need_bind = True # 是否需要绑定设备 + self.bind_completed_event = asyncio.Event() self.bind_code = None # 绑定设备的验证码 self.last_bind_prompt_time = 0 # 上次播放绑定提示的时间戳(秒) self.bind_prompt_interval = 60 # 绑定提示播放间隔(秒) @@ -268,28 +269,30 @@ class ConnectionHandler: async def _route_message(self, message): """消息路由""" + try: + await asyncio.wait_for(self.bind_completed_event.wait(), timeout=1) + except asyncio.TimeoutError: + # 未绑定设备直接丢弃所有消息 + current_time = time.time() + # 检查是否需要播放绑定提示 + if ( + current_time - self.last_bind_prompt_time + >= self.bind_prompt_interval + ): + self.last_bind_prompt_time = current_time + # 复用现有的绑定提示逻辑 + from core.handle.receiveAudioHandle import check_bind_device + + asyncio.create_task(check_bind_device(self)) + # 直接丢弃音频，不进行ASR处理 + return + if isinstance(message, str): await handleTextMessage(self, message) elif isinstance(message, bytes): if self.vad is None or self.asr is None: return - # 未绑定设备直接丢弃所有音频，不进行ASR处理 - if self.need_bind: - current_time = time.time() - # 检查是否需要播放绑定提示 - if ( - current_time - self.last_bind_prompt_time - >= self.bind_prompt_interval - ): - self.last_bind_prompt_time = current_time - # 复用现有的绑定提示逻辑 - from core.handle.receiveAudioHandle import check_bind_device - - asyncio.create_task(check_bind_device(self)) - # 直接丢弃音频，不进行ASR处理 - return - # 处理来自MQTT网关的音频包 if self.conn_from_mqtt_gateway and len(message) >= 16: handled = await self._process_mqtt_audio_message(message) @@ -461,6 +464,9 @@ class ConnectionHandler: self.logger.bind(tag=TAG).error(f"实例化组件失败: {e}") def _init_prompt_enhancement(self): + if self.need_bind: + return + # 更新上下文信息 self.prompt_manager.update_context_info(self, self.client_ip) enhanced_prompt = self.prompt_manager.build_enhanced_prompt( @@ -509,6 +515,9 @@ class ConnectionHandler: def _initialize_voiceprint(self): """为当前连接初始化声纹识别""" + if self.need_bind: + return + try: voiceprint_config = self.config.get("voiceprint", {}) if voiceprint_config: @@ -548,15 +557,14 @@ class ConnectionHandler: self.logger.bind(tag=TAG).info( f"{time.time() - begin_time} 秒，异步获取差异化配置成功: {json.dumps(filter_sensitive_info(private_config), ensure_ascii=False)}" ) + self.need_bind = False + self.bind_completed_event.set() except DeviceNotFoundException as e: - self.need_bind = True private_config = {} except DeviceBindException as e: - self.need_bind = True self.bind_code = e.bind_code private_config = {} except Exception as e: - self.need_bind = True self.logger.bind(tag=TAG).error(f"异步获取差异化配置失败: {e}") private_config = {} diff --git a/main/xiaozhi-server/core/utils/audioRateController.py b/main/xiaozhi-server/core/utils/audioRateController.py index e6d883f1..612dcba0 100644 --- a/main/xiaozhi-server/core/utils/audioRateController.py +++ b/main/xiaozhi-server/core/utils/audioRateController.py @@ -85,26 +85,13 @@ class AudioRateController: elif item_type == "audio": _, opus_packet = item - # 循环等待直到时间到达 - while True: - # 计算时间差 - elapsed_ms = self._get_elapsed_ms() - output_ms = self.play_position + # 计算时间差 + elapsed_ms = self._get_elapsed_ms() + output_ms = self.play_position - if elapsed_ms < output_ms: - # 还不到发送时间，计算等待时长 - wait_ms = output_ms - elapsed_ms - - # 等待后继续检查（允许被中断） - try: - await asyncio.sleep(wait_ms / 1000) - except asyncio.CancelledError: - self.logger.bind(tag=TAG).debug("音频发送任务被取消") - raise - # 等待结束后重新检查时间（循环回到 while True） - else: - # 时间已到，跳出等待循环 - break + if elapsed_ms < output_ms: + # 还不到发送时间，返回让出控制权（非阻塞） + break # 时间已到，从队列移除并发送 self.queue.pop(0) @@ -132,6 +119,10 @@ class AudioRateController: async def _send_loop(): try: while True: + # 只有当队列非空时才处理，否则等待队列事件 + if not self.queue: + await self.queue_empty_event.wait() + await self.check_queue(send_audio_callback) # 如果队列空了，短暂等待后再检查（避免 busy loop） await asyncio.sleep(0.01) From 7fc2eeaaa5d743c964806bbc768176733dcdc85c Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sat, 13 Dec 2025 00:19:38 +0800 Subject: [PATCH 12/39] =?UTF-8?q?update:=E5=8F=91=E9=80=81=E8=AF=AD?= =?UTF-8?q?=E9=9F=B3=E6=B6=88=E6=81=AF=E6=97=B6=E6=89=93=E6=96=AD=E6=9C=BA?= =?UTF-8?q?=E5=99=A8=E4=BA=BA=E8=AF=B4=E8=AF=9D?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../test/js/core/audio/recorder.js | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/main/xiaozhi-server/test/js/core/audio/recorder.js b/main/xiaozhi-server/test/js/core/audio/recorder.js index 9f94f895..3fe785f0 100644 --- a/main/xiaozhi-server/test/js/core/audio/recorder.js +++ b/main/xiaozhi-server/test/js/core/audio/recorder.js @@ -240,6 +240,24 @@ export class AudioRecorder { if (this.isRecording) return false; try { + // 检查是否有WebSocketHandler实例 + const { getWebSocketHandler } = await import('../network/websocket.js'); + const wsHandler = getWebSocketHandler(); + + // 如果机器正在说话，发送打断消息 + if (wsHandler && wsHandler.isRemoteSpeaking && wsHandler.currentSessionId) { + const abortMessage = { + session_id: wsHandler.currentSessionId, + type: 'abort', + reason: 'wake_word_detected' + }; + + if (this.websocket && this.websocket.readyState === WebSocket.OPEN) { + this.websocket.send(JSON.stringify(abortMessage)); + log('发送打断消息', 'info'); + } + } + if (!this.initEncoder()) { log('无法启动录音: Opus编码器初始化失败', 'error'); return false; From d33cdd978d62cfae0392344eff2c4e6e42b96fa1 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sat, 13 Dec 2025 00:25:54 +0800 Subject: [PATCH 13/39] fix:edge_tts bug --- main/xiaozhi-server/requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/main/xiaozhi-server/requirements.txt b/main/xiaozhi-server/requirements.txt index 3f62ef4c..919c0f6d 100644 --- a/main/xiaozhi-server/requirements.txt +++ b/main/xiaozhi-server/requirements.txt @@ -13,7 +13,7 @@ pydub==0.25.1 funasr==1.2.7 openai==2.8.1 google-generativeai==0.8.5 -edge_tts==7.2.3 +edge_tts==7.2.6 httpx==0.28.1 aiohttp==3.13.2 aiohttp_cors==0.8.1 From 7699596597d211fa581d37af137f4ac8d296f62f Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sat, 13 Dec 2025 14:35:55 +0800 Subject: [PATCH 14/39] =?UTF-8?q?update:=E4=BC=98=E5=8C=96?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/core/connection.py | 30 +++++++++++--------------- 1 file changed, 12 insertions(+), 18 deletions(-) diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py index 2a6a8168..dbb2bf7a 100644 --- a/main/xiaozhi-server/core/connection.py +++ b/main/xiaozhi-server/core/connection.py @@ -68,7 +68,7 @@ class ConnectionHandler: self.logger = setup_logging() self.server = server # 保存server实例的引用 - self.need_bind = True # 是否需要绑定设备 + self.need_bind = False # 是否需要绑定设备 self.bind_completed_event = asyncio.Event() self.bind_code = None # 绑定设备的验证码 self.last_bind_prompt_time = 0 # 上次播放绑定提示的时间戳(秒) @@ -270,15 +270,12 @@ class ConnectionHandler: async def _route_message(self, message): """消息路由""" try: - await asyncio.wait_for(self.bind_completed_event.wait(), timeout=1) + await asyncio.wait_for(self.bind_completed_event.wait(), timeout=2) except asyncio.TimeoutError: # 未绑定设备直接丢弃所有消息 current_time = time.time() # 检查是否需要播放绑定提示 - if ( - current_time - self.last_bind_prompt_time - >= self.bind_prompt_interval - ): + if current_time - self.last_bind_prompt_time >= self.bind_prompt_interval: self.last_bind_prompt_time = current_time # 复用现有的绑定提示逻辑 from core.handle.receiveAudioHandle import check_bind_device @@ -416,6 +413,14 @@ class ConnectionHandler: def _initialize_components(self): try: + if self.tts is None: + self.tts = self._initialize_tts() + # 打开语音合成通道 + asyncio.run_coroutine_threadsafe( + self.tts.open_audio_channels(self), self.loop + ) + if self.need_bind: + return self.selected_module_str = build_module_string( self.config.get("selected_module", {}) ) @@ -439,17 +444,10 @@ class ConnectionHandler: # 初始化声纹识别 self._initialize_voiceprint() - # 打开语音识别通道 asyncio.run_coroutine_threadsafe( self.asr.open_audio_channels(self), self.loop ) - if self.tts is None: - self.tts = self._initialize_tts() - # 打开语音合成通道 - asyncio.run_coroutine_threadsafe( - self.tts.open_audio_channels(self), self.loop - ) """加载记忆""" self._initialize_memory() @@ -464,8 +462,6 @@ class ConnectionHandler: self.logger.bind(tag=TAG).error(f"实例化组件失败: {e}") def _init_prompt_enhancement(self): - if self.need_bind: - return # 更新上下文信息 self.prompt_manager.update_context_info(self, self.client_ip) @@ -515,9 +511,6 @@ class ConnectionHandler: def _initialize_voiceprint(self): """为当前连接初始化声纹识别""" - if self.need_bind: - return - try: voiceprint_config = self.config.get("voiceprint", {}) if voiceprint_config: @@ -545,6 +538,7 @@ class ConnectionHandler: async def _initialize_private_config_async(self): """从接口异步获取差异化配置（异步版本，不阻塞主循环）""" if not self.read_config_from_api: + self.bind_completed_event.set() return try: begin_time = time.time() From 2e092a78801f2ee14a5ee2c3b5e9843b2c48098c Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sat, 13 Dec 2025 15:34:11 +0800 Subject: [PATCH 15/39] =?UTF-8?q?update=EF=BC=9A=E9=BB=98=E8=AE=A4?= =?UTF-8?q?=E5=BC=80=E5=90=AFserver.auth.enabled?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../modules/device/service/impl/DeviceServiceImpl.java | 6 +++--- .../modules/security/controller/LoginController.java | 8 ++++---- .../src/main/resources/db/changelog/202512131453.sql | 6 ++++++ .../main/resources/db/changelog/db.changelog-master.yaml | 7 +++++++ main/manager-web/src/i18n/de.js | 4 ++-- main/manager-web/src/i18n/en.js | 4 ++-- main/manager-web/src/i18n/vi.js | 4 ++-- main/manager-web/src/i18n/zh_CN.js | 4 ++-- main/manager-web/src/i18n/zh_TW.js | 4 ++-- 9 files changed, 30 insertions(+), 17 deletions(-) create mode 100644 main/manager-api/src/main/resources/db/changelog/202512131453.sql diff --git a/main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java b/main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java index b00af2cf..44977730 100644 --- a/main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java +++ b/main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java @@ -173,7 +173,7 @@ public class DeviceServiceImpl extends BaseServiceImpl String wsUrl = sysParamsService.getValue(Constant.SERVER_WEBSOCKET, true); // 检查是否启用认证并生成token - String authEnabled = sysParamsService.getValue(Constant.SERVER_AUTH_ENABLED, false); + String authEnabled = sysParamsService.getValue(Constant.SERVER_AUTH_ENABLED, true); if ("true".equalsIgnoreCase(authEnabled)) { try { // 生成token @@ -206,7 +206,7 @@ public class DeviceServiceImpl extends BaseServiceImpl // 添加MQTT UDP配置 // 从系统参数获取MQTT Gateway地址，仅在配置有效时使用 - String mqttUdpConfig = sysParamsService.getValue(Constant.SERVER_MQTT_GATEWAY, false); + String mqttUdpConfig = sysParamsService.getValue(Constant.SERVER_MQTT_GATEWAY, true); if (mqttUdpConfig != null && !mqttUdpConfig.equals("null") && !mqttUdpConfig.isEmpty()) { try { String groupId = deviceById != null && deviceById.getBoard() != null ? deviceById.getBoard() @@ -555,7 +555,7 @@ public class DeviceServiceImpl extends BaseServiceImpl private DeviceReportRespDTO.MQTT buildMqttConfig(String macAddress, String groupId) throws Exception { // 从环境变量或系统参数获取签名密钥 - String signatureKey = sysParamsService.getValue("server.mqtt_signature_key", false); + String signatureKey = sysParamsService.getValue("server.mqtt_signature_key", true); if (StringUtils.isBlank(signatureKey)) { log.warn("缺少MQTT_SIGNATURE_KEY，跳过MQTT配置生成"); return null; diff --git a/main/manager-api/src/main/java/xiaozhi/modules/security/controller/LoginController.java b/main/manager-api/src/main/java/xiaozhi/modules/security/controller/LoginController.java index 2c7bab4a..1ab9809d 100644 --- a/main/manager-api/src/main/java/xiaozhi/modules/security/controller/LoginController.java +++ b/main/manager-api/src/main/java/xiaozhi/modules/security/controller/LoginController.java @@ -6,6 +6,7 @@ import java.util.HashMap; import java.util.List; import java.util.Map; +import org.apache.commons.lang3.StringUtils; import org.springframework.web.bind.annotation.GetMapping; import org.springframework.web.bind.annotation.PostMapping; import org.springframework.web.bind.annotation.PutMapping; @@ -23,7 +24,9 @@ import xiaozhi.common.exception.ErrorCode; import xiaozhi.common.exception.RenException; import xiaozhi.common.page.TokenDTO; import xiaozhi.common.user.UserDetail; +import xiaozhi.common.utils.JsonUtils; import xiaozhi.common.utils.Result; +import xiaozhi.common.utils.Sm2DecryptUtil; import xiaozhi.common.validator.AssertUtils; import xiaozhi.common.validator.ValidatorUtils; import xiaozhi.modules.security.dto.LoginDTO; @@ -32,8 +35,6 @@ import xiaozhi.modules.security.password.PasswordUtils; import xiaozhi.modules.security.service.CaptchaService; import xiaozhi.modules.security.service.SysUserTokenService; import xiaozhi.modules.security.user.SecurityUser; -import xiaozhi.common.utils.Sm2DecryptUtil; -import org.apache.commons.lang3.StringUtils; import xiaozhi.modules.sys.dto.PasswordDTO; import xiaozhi.modules.sys.dto.RetrievePasswordDTO; import xiaozhi.modules.sys.dto.SysUserDTO; @@ -41,7 +42,6 @@ import xiaozhi.modules.sys.service.SysDictDataService; import xiaozhi.modules.sys.service.SysParamsService; import xiaozhi.modules.sys.service.SysUserService; import xiaozhi.modules.sys.vo.SysDictDataItem; -import xiaozhi.common.utils.JsonUtils; /** * 登录控制层 @@ -237,7 +237,7 @@ public class LoginController { config.put("sm2PublicKey", publicKey); // 获取system-web.menu参数配置 - String menuConfig = sysParamsService.getValue("system-web.menu", false); + String menuConfig = sysParamsService.getValue("system-web.menu", true); if (StringUtils.isNotBlank(menuConfig)) { config.put("systemWebMenu", JsonUtils.parseObject(menuConfig, Object.class)); } diff --git a/main/manager-api/src/main/resources/db/changelog/202512131453.sql b/main/manager-api/src/main/resources/db/changelog/202512131453.sql new file mode 100644 index 00000000..27ea4a1b --- /dev/null +++ b/main/manager-api/src/main/resources/db/changelog/202512131453.sql @@ -0,0 +1,6 @@ +-- 删除server模块是否开启token认证参数 +delete from `sys_params` where param_code = 'server.auth.enabled'; + +-- 添加server模块是否开启token认证参数 +INSERT INTO `sys_params` (id, param_code, param_value, value_type, param_type, remark) VALUES +(122, 'server.auth.enabled', 'true', 'boolean', 1, 'server模块是否开启token认证'); \ No newline at end of file diff --git a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml index b0cdbc63..dd6dff55 100755 --- a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml +++ b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml @@ -438,3 +438,10 @@ databaseChangeLog: - sqlFile: encoding: utf8 path: classpath:db/changelog/202512041515.sql + - changeSet: + id: 202512131453 + author: hrz + changes: + - sqlFile: + encoding: utf8 + path: classpath:db/changelog/202512131453.sql diff --git a/main/manager-web/src/i18n/de.js b/main/manager-web/src/i18n/de.js index 4a9ab40c..1d8704be 100644 --- a/main/manager-web/src/i18n/de.js +++ b/main/manager-web/src/i18n/de.js @@ -713,7 +713,7 @@ export default { 'paramManagement.deleteFailed': 'Löschen fehlgeschlagen, bitte versuchen Sie es erneut', 'paramManagement.operationCancelled': 'Löschen abgebrochen', 'paramManagement.operationClosed': 'Operation geschlossen', - 'paramManagement.updateSuccess': 'Aktualisierung erfolgreich', + 'paramManagement.updateSuccess': 'Aktualisierung erfolgreich. Einige Konfigurationen werden erst nach Neustart des xiaozhi-server-Moduls wirksam.', 'paramManagement.addSuccess': 'Hinzufügen erfolgreich', 'paramManagement.updateFailed': 'Aktualisierung fehlgeschlagen', 'paramManagement.addFailed': 'Hinzufügen fehlgeschlagen', @@ -852,7 +852,7 @@ export default { 'modelConfig.enableSuccess': 'Aktivieren erfolgreich', 'modelConfig.disableSuccess': 'Deaktivieren erfolgreich', 'modelConfig.operationFailed': 'Operation fehlgeschlagen', - 'modelConfig.setDefaultSuccess': 'Standardmodell erfolgreich gesetzt', + 'modelConfig.setDefaultSuccess': 'Standardmodell erfolgreich gesetzt, bitte starten Sie das xiaozhi-server-Modul zeitnah manuell neu', 'modelConfig.itemsPerPage': '{items} Einträge/Seite', 'modelConfig.firstPage': 'Erste Seite', 'modelConfig.prevPage': 'Vorherige Seite', diff --git a/main/manager-web/src/i18n/en.js b/main/manager-web/src/i18n/en.js index 298d1e17..f57f8ab3 100644 --- a/main/manager-web/src/i18n/en.js +++ b/main/manager-web/src/i18n/en.js @@ -713,7 +713,7 @@ export default { 'paramManagement.deleteFailed': 'Deletion failed, please try again', 'paramManagement.operationCancelled': 'Deletion cancelled', 'paramManagement.operationClosed': 'Operation closed', - 'paramManagement.updateSuccess': 'Update successful', + 'paramManagement.updateSuccess': 'Update successful. Some configurations will take effect only after restarting the xiaozhi-server module.', 'paramManagement.addSuccess': 'Add successful', 'paramManagement.updateFailed': 'Update failed', 'paramManagement.addFailed': 'Add failed', @@ -852,7 +852,7 @@ export default { 'modelConfig.enableSuccess': 'Enable successful', 'modelConfig.disableSuccess': 'Disable successful', 'modelConfig.operationFailed': 'Operation failed', - 'modelConfig.setDefaultSuccess': 'Set default model successful', + 'modelConfig.setDefaultSuccess': 'Set default model successful, please restart the xiaozhi-server module manually in time', 'modelConfig.itemsPerPage': '{items} items/page', 'modelConfig.firstPage': 'First Page', 'modelConfig.prevPage': 'Previous Page', diff --git a/main/manager-web/src/i18n/vi.js b/main/manager-web/src/i18n/vi.js index 9ca108ef..a96ccfaa 100644 --- a/main/manager-web/src/i18n/vi.js +++ b/main/manager-web/src/i18n/vi.js @@ -713,7 +713,7 @@ export default { 'paramManagement.deleteFailed': 'Xóa thất bại, vui lòng thử lại', 'paramManagement.operationCancelled': 'Đã hủy xóa', 'paramManagement.operationClosed': 'Đã đóng thao tác', - 'paramManagement.updateSuccess': 'Cập nhật thành công', + 'paramManagement.updateSuccess': 'Cập nhật thành công. Một số cấu hình chỉ có hiệu lực sau khi khởi động lại mô-đun xiaozhi-server.', 'paramManagement.addSuccess': 'Thêm thành công', 'paramManagement.updateFailed': 'Cập nhật thất bại', 'paramManagement.addFailed': 'Thêm thất bại', @@ -852,7 +852,7 @@ export default { 'modelConfig.enableSuccess': 'Bật thành công', 'modelConfig.disableSuccess': 'Tắt thành công', 'modelConfig.operationFailed': 'Thao tác thất bại', - 'modelConfig.setDefaultSuccess': 'Đặt mô hình mặc định thành công', + 'modelConfig.setDefaultSuccess': 'Đặt mô hình mặc định thành công, vui lòng khởi động lại module xiaozhi-server thủ công kịp thời', 'modelConfig.itemsPerPage': '{items} mục/trang', 'modelConfig.firstPage': 'Trang đầu', 'modelConfig.prevPage': 'Trang trước', diff --git a/main/manager-web/src/i18n/zh_CN.js b/main/manager-web/src/i18n/zh_CN.js index 392b9a8b..6a3c6d80 100644 --- a/main/manager-web/src/i18n/zh_CN.js +++ b/main/manager-web/src/i18n/zh_CN.js @@ -713,7 +713,7 @@ export default { 'paramManagement.deleteFailed': '删除失败，请重试', 'paramManagement.operationCancelled': '已取消删除操作', 'paramManagement.operationClosed': '操作已关闭', - 'paramManagement.updateSuccess': '修改成功', + 'paramManagement.updateSuccess': '修改成功，部分配置需重启xiaozhi-server模块才生效', 'paramManagement.addSuccess': '新增成功', 'paramManagement.updateFailed': '更新失败', 'paramManagement.addFailed': '新增失败', @@ -852,7 +852,7 @@ export default { 'modelConfig.enableSuccess': '启用成功', 'modelConfig.disableSuccess': '禁用成功', 'modelConfig.operationFailed': '操作失败', - 'modelConfig.setDefaultSuccess': '设置默认模型成功', + 'modelConfig.setDefaultSuccess': '设置默认模型成功，请及时手动重启xiaozhi-server模块', 'modelConfig.itemsPerPage': '{items}条/页', 'modelConfig.firstPage': '首页', 'modelConfig.prevPage': '上一页', diff --git a/main/manager-web/src/i18n/zh_TW.js b/main/manager-web/src/i18n/zh_TW.js index 69bacd67..ff5fdb47 100644 --- a/main/manager-web/src/i18n/zh_TW.js +++ b/main/manager-web/src/i18n/zh_TW.js @@ -713,7 +713,7 @@ export default { 'paramManagement.deleteFailed': '刪除失敗，請重試', 'paramManagement.operationCancelled': '已取消刪除操作', 'paramManagement.operationClosed': '操作已關閉', - 'paramManagement.updateSuccess': '修改成功', + 'paramManagement.updateSuccess': '修改成功，部分配置需重啟xiaozhi-server模組才生效', 'paramManagement.addSuccess': '新增成功', 'paramManagement.updateFailed': '更新失敗', 'paramManagement.addFailed': '新增失敗', @@ -852,7 +852,7 @@ export default { 'modelConfig.enableSuccess': '啟用成功', 'modelConfig.disableSuccess': '禁用成功', 'modelConfig.operationFailed': '操作失敗', - 'modelConfig.setDefaultSuccess': '設置默認模型成功', + 'modelConfig.setDefaultSuccess': '設置默認模型成功，請及時手動重啟xiaozhi-server模組', 'modelConfig.itemsPerPage': '{items}條/頁', 'modelConfig.firstPage': '首頁', 'modelConfig.prevPage': '上一頁', From 06a90d6266354db869bcb37e0240abbe22994f46 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sat, 13 Dec 2025 20:27:11 +0800 Subject: [PATCH 16/39] =?UTF-8?q?update=EF=BC=9A=E6=81=A2=E5=A4=8DaudioRat?= =?UTF-8?q?eController=E6=97=A7=E7=89=88=E6=9C=AC?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../core/utils/audioRateController.py | 31 ++++++++++++------- 1 file changed, 20 insertions(+), 11 deletions(-) diff --git a/main/xiaozhi-server/core/utils/audioRateController.py b/main/xiaozhi-server/core/utils/audioRateController.py index 612dcba0..35038d27 100644 --- a/main/xiaozhi-server/core/utils/audioRateController.py +++ b/main/xiaozhi-server/core/utils/audioRateController.py @@ -85,13 +85,26 @@ class AudioRateController: elif item_type == "audio": _, opus_packet = item - # 计算时间差 - elapsed_ms = self._get_elapsed_ms() - output_ms = self.play_position + # 循环等待直到时间到达 + while True: + # 计算时间差 + elapsed_ms = self._get_elapsed_ms() + output_ms = self.play_position - if elapsed_ms < output_ms: - # 还不到发送时间，返回让出控制权（非阻塞） - break + if elapsed_ms < output_ms: + # 还不到发送时间，计算等待时长 + wait_ms = output_ms - elapsed_ms + + # 等待后继续检查（允许被中断） + try: + await asyncio.sleep(wait_ms / 1000) + except asyncio.CancelledError: + self.logger.bind(tag=TAG).debug("音频发送任务被取消") + raise + # 等待结束后重新检查时间（循环回到 while True） + else: + # 时间已到，跳出等待循环 + break # 时间已到，从队列移除并发送 self.queue.pop(0) @@ -105,7 +118,6 @@ class AudioRateController: self.queue_empty_event.set() - def start_sending(self, send_audio_callback): """ 启动异步发送任务 @@ -116,13 +128,10 @@ class AudioRateController: Returns: asyncio.Task: 发送任务 """ + async def _send_loop(): try: while True: - # 只有当队列非空时才处理，否则等待队列事件 - if not self.queue: - await self.queue_empty_event.wait() - await self.check_queue(send_audio_callback) # 如果队列空了，短暂等待后再检查（避免 busy loop） await asyncio.sleep(0.01) From 8b3a4ad1634ad4003cb024a18e182d4979fcfce9 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sat, 13 Dec 2025 21:45:31 +0800 Subject: [PATCH 17/39] =?UTF-8?q?update=EF=BC=9A=E4=BC=98=E5=8C=96?= =?UTF-8?q?=E4=B8=A2=E5=BC=83=E6=B6=88=E6=81=AF=E9=80=BB=E8=BE=91?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/core/connection.py | 51 +++++++++++++++++++------- 1 file changed, 38 insertions(+), 13 deletions(-) diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py index 70489036..236d4e51 100644 --- a/main/xiaozhi-server/core/connection.py +++ b/main/xiaozhi-server/core/connection.py @@ -267,23 +267,37 @@ class ConnectionHandler: f"保存记忆后关闭连接失败: {close_error}" ) + async def _discard_message_with_bind_prompt(self): + """丢弃消息并检查是否需要播放绑定提示""" + current_time = time.time() + # 检查是否需要播放绑定提示 + if current_time - self.last_bind_prompt_time >= self.bind_prompt_interval: + self.last_bind_prompt_time = current_time + # 复用现有的绑定提示逻辑 + from core.handle.receiveAudioHandle import check_bind_device + + asyncio.create_task(check_bind_device(self)) + async def _route_message(self, message): """消息路由""" - try: - await asyncio.wait_for(self.bind_completed_event.wait(), timeout=2) - except asyncio.TimeoutError: - # 未绑定设备直接丢弃所有消息 - current_time = time.time() - # 检查是否需要播放绑定提示 - if current_time - self.last_bind_prompt_time >= self.bind_prompt_interval: - self.last_bind_prompt_time = current_time - # 复用现有的绑定提示逻辑 - from core.handle.receiveAudioHandle import check_bind_device + # 检查是否已经获取到真实的绑定状态 + if not self.bind_completed_event.is_set(): + # 还没有获取到真实状态，等待直到获取到真实状态或超时 + try: + await asyncio.wait_for(self.bind_completed_event.wait(), timeout=1) + except asyncio.TimeoutError: + # 超时仍未获取到真实状态，丢弃消息 + await self._discard_message_with_bind_prompt() + return - asyncio.create_task(check_bind_device(self)) - # 直接丢弃音频，不进行ASR处理 + # 已经获取到真实状态，检查是否需要绑定 + if self.need_bind: + # 需要绑定，丢弃消息 + await self._discard_message_with_bind_prompt() return + # 不需要绑定，继续处理消息 + if isinstance(message, str): await handleTextMessage(self, message) elif isinstance(message, bytes): @@ -498,7 +512,11 @@ class ConnectionHandler: def _initialize_asr(self): """初始化ASR""" - if self._asr is not None and hasattr(self._asr, "interface_type") and self._asr.interface_type == InterfaceType.LOCAL: + if ( + self._asr is not None + and hasattr(self._asr, "interface_type") + and self._asr.interface_type == InterfaceType.LOCAL + ): # 如果公共ASR是本地服务，则直接返回 # 因为本地一个实例ASR，可以被多个连接共享 asr = self._asr @@ -538,6 +556,7 @@ class ConnectionHandler: async def _initialize_private_config_async(self): """从接口异步获取差异化配置（异步版本，不阻塞主循环）""" if not self.read_config_from_api: + self.need_bind = False self.bind_completed_event.set() return try: @@ -554,11 +573,17 @@ class ConnectionHandler: self.need_bind = False self.bind_completed_event.set() except DeviceNotFoundException as e: + self.need_bind = True + self.bind_completed_event.set() # 状态已确定，设置事件 private_config = {} except DeviceBindException as e: + self.need_bind = True self.bind_code = e.bind_code + self.bind_completed_event.set() # 状态已确定，设置事件 private_config = {} except Exception as e: + self.need_bind = True + self.bind_completed_event.set() # 状态已确定，设置事件 self.logger.bind(tag=TAG).error(f"异步获取差异化配置失败: {e}") private_config = {} From 8b2bbec0b9bf458e3bebd39b0f6ca76a1418c20b Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sat, 13 Dec 2025 22:29:10 +0800 Subject: [PATCH 18/39] =?UTF-8?q?update:audio=5Fto=5Fdata=E6=94=B9?= =?UTF-8?q?=E6=88=90=E5=BC=82=E6=AD=A5=E6=96=B9=E6=B3=95?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../xiaozhi-server/core/handle/helloHandle.py | 2 +- .../core/handle/receiveAudioHandle.py | 8 +- .../core/handle/sendAudioHandle.py | 21 +++-- main/xiaozhi-server/core/utils/util.py | 77 ++++++++++--------- 4 files changed, 63 insertions(+), 45 deletions(-) diff --git a/main/xiaozhi-server/core/handle/helloHandle.py b/main/xiaozhi-server/core/handle/helloHandle.py index 248c5f73..efe66b59 100644 --- a/main/xiaozhi-server/core/handle/helloHandle.py +++ b/main/xiaozhi-server/core/handle/helloHandle.py @@ -101,7 +101,7 @@ async def checkWakeupWords(conn, text): } # 获取音频数据 - opus_packets = audio_to_data(response.get("file_path")) + opus_packets = await audio_to_data(response.get("file_path")) # 播放唤醒词回复 conn.client_abort = False diff --git a/main/xiaozhi-server/core/handle/receiveAudioHandle.py b/main/xiaozhi-server/core/handle/receiveAudioHandle.py index 4eaf9ab1..8879564f 100644 --- a/main/xiaozhi-server/core/handle/receiveAudioHandle.py +++ b/main/xiaozhi-server/core/handle/receiveAudioHandle.py @@ -123,7 +123,7 @@ async def max_out_size(conn): 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！" await send_stt_message(conn, text) file_path = "config/assets/max_output_size.wav" - opus_packets = audio_to_data(file_path) + opus_packets = await audio_to_data(file_path) conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text)) conn.close_after_chat = True @@ -142,7 +142,7 @@ async def check_bind_device(conn): # 播放提示音 music_path = "config/assets/bind_code.wav" - opus_packets = audio_to_data(music_path) + opus_packets = await audio_to_data(music_path) conn.tts.tts_audio_queue.put((SentenceType.FIRST, opus_packets, text)) # 逐个播放数字 @@ -150,7 +150,7 @@ 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_data(num_path) + num_packets = await audio_to_data(num_path) conn.tts.tts_audio_queue.put((SentenceType.MIDDLE, num_packets, None)) except Exception as e: conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}") @@ -162,5 +162,5 @@ async def check_bind_device(conn): 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。" await send_stt_message(conn, text) music_path = "config/assets/bind_not_found.wav" - opus_packets = audio_to_data(music_path) + opus_packets = await audio_to_data(music_path) conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text)) diff --git a/main/xiaozhi-server/core/handle/sendAudioHandle.py b/main/xiaozhi-server/core/handle/sendAudioHandle.py index f662b6c6..d0167498 100644 --- a/main/xiaozhi-server/core/handle/sendAudioHandle.py +++ b/main/xiaozhi-server/core/handle/sendAudioHandle.py @@ -17,7 +17,12 @@ async def sendAudioMessage(conn, sentenceType, audios, text): if sentenceType == SentenceType.FIRST: # 同一句子的后续消息加入流控队列，其他情况立即发送 - if hasattr(conn, "audio_rate_controller") and conn.audio_rate_controller and getattr(conn, "audio_flow_control", {}).get("sentence_id") == conn.sentence_id: + if ( + hasattr(conn, "audio_rate_controller") + and conn.audio_rate_controller + and getattr(conn, "audio_flow_control", {}).get("sentence_id") + == conn.sentence_id + ): conn.audio_rate_controller.add_message( lambda: send_tts_message(conn, "sentence_start", text) ) @@ -120,7 +125,8 @@ def _get_or_create_rate_controller(conn, frame_duration, is_single_packet): # 判断是否需要重置：单包模式且 sentence_id 变化，或者控制器不存在 need_reset = ( is_single_packet - and getattr(conn, "audio_flow_control", {}).get("sentence_id") != conn.sentence_id + and getattr(conn, "audio_flow_control", {}).get("sentence_id") + != conn.sentence_id ) or not hasattr(conn, "audio_rate_controller") if need_reset: @@ -138,7 +144,9 @@ def _get_or_create_rate_controller(conn, frame_duration, is_single_packet): } # 启动后台发送循环 - _start_background_sender(conn, conn.audio_rate_controller, conn.audio_flow_control) + _start_background_sender( + conn, conn.audio_rate_controller, conn.audio_flow_control + ) return conn.audio_rate_controller, conn.audio_flow_control @@ -152,6 +160,7 @@ def _start_background_sender(conn, rate_controller, flow_control): rate_controller: 速率控制器 flow_control: 流控状态 """ + async def send_callback(packet): # 检查是否应该中止 if conn.client_abort: @@ -165,7 +174,9 @@ def _start_background_sender(conn, rate_controller, flow_control): rate_controller.start_sending(send_callback) -async def _send_audio_with_rate_control(conn, audio_list, rate_controller, flow_control, send_delay): +async def _send_audio_with_rate_control( + conn, audio_list, rate_controller, flow_control, send_delay +): """ 使用 rate_controller 发送音频包 @@ -235,7 +246,7 @@ 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 = audio_to_data(stop_tts_notify_voice, is_opus=True) + audios = await audio_to_data(stop_tts_notify_voice, is_opus=True) await sendAudio(conn, audios) # 等待所有音频包发送完成 await _wait_for_audio_completion(conn) diff --git a/main/xiaozhi-server/core/utils/util.py b/main/xiaozhi-server/core/utils/util.py index f72dda2c..2baedf68 100644 --- a/main/xiaozhi-server/core/utils/util.py +++ b/main/xiaozhi-server/core/utils/util.py @@ -4,6 +4,7 @@ import json import copy import wave import socket +import asyncio import requests import subprocess import numpy as np @@ -268,56 +269,62 @@ def audio_to_data_stream( pcm_to_data_stream(raw_data, is_opus, callback) -def audio_to_data(audio_file_path: str, is_opus: bool = True) -> list[bytes]: +async def audio_to_data(audio_file_path: str, is_opus: bool = True) -> list[bytes]: """ 将音频文件转换为Opus/PCM编码的帧列表 Args: audio_file_path: 音频文件路径 is_opus: 是否进行Opus编码 """ - # 获取文件后缀名 - file_type = os.path.splitext(audio_file_path)[1] - if file_type: - file_type = file_type.lstrip(".") - # 读取音频文件，-nostdin 参数：不要从标准输入读取数据，否则FFmpeg会阻塞 - audio = AudioSegment.from_file( - audio_file_path, format=file_type, parameters=["-nostdin"] - ) - # 转换为单声道/16kHz采样率/16位小端编码（确保与编码器匹配） - audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2) + def _sync_audio_to_data(): + # 获取文件后缀名 + file_type = os.path.splitext(audio_file_path)[1] + if file_type: + file_type = file_type.lstrip(".") + # 读取音频文件，-nostdin 参数：不要从标准输入读取数据，否则FFmpeg会阻塞 + audio = AudioSegment.from_file( + audio_file_path, format=file_type, parameters=["-nostdin"] + ) - # 获取原始PCM数据（16位小端） - raw_data = audio.raw_data + # 转换为单声道/16kHz采样率/16位小端编码（确保与编码器匹配） + audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2) - # 初始化Opus编码器 - encoder = opuslib_next.Encoder(16000, 1, opuslib_next.APPLICATION_AUDIO) + # 获取原始PCM数据（16位小端） + raw_data = audio.raw_data - # 编码参数 - frame_duration = 60 # 60ms per frame - frame_size = int(16000 * frame_duration / 1000) # 960 samples/frame + # 初始化Opus编码器 + encoder = opuslib_next.Encoder(16000, 1, opuslib_next.APPLICATION_AUDIO) - datas = [] - # 按帧处理所有音频数据（包括最后一帧可能补零） - for i in range(0, len(raw_data), frame_size * 2): # 16bit=2bytes/sample - # 获取当前帧的二进制数据 - chunk = raw_data[i : i + frame_size * 2] + # 编码参数 + frame_duration = 60 # 60ms per frame + frame_size = int(16000 * frame_duration / 1000) # 960 samples/frame - # 如果最后一帧不足，补零 - if len(chunk) < frame_size * 2: - chunk += b"\x00" * (frame_size * 2 - len(chunk)) + datas = [] + # 按帧处理所有音频数据（包括最后一帧可能补零） + for i in range(0, len(raw_data), frame_size * 2): # 16bit=2bytes/sample + # 获取当前帧的二进制数据 + chunk = raw_data[i : i + frame_size * 2] - if is_opus: - # 转换为numpy数组处理 - np_frame = np.frombuffer(chunk, dtype=np.int16) - # 编码Opus数据 - frame_data = encoder.encode(np_frame.tobytes(), frame_size) - else: - frame_data = chunk if isinstance(chunk, bytes) else bytes(chunk) + # 如果最后一帧不足，补零 + if len(chunk) < frame_size * 2: + chunk += b"\x00" * (frame_size * 2 - len(chunk)) - datas.append(frame_data) + if is_opus: + # 转换为numpy数组处理 + np_frame = np.frombuffer(chunk, dtype=np.int16) + # 编码Opus数据 + frame_data = encoder.encode(np_frame.tobytes(), frame_size) + else: + frame_data = chunk if isinstance(chunk, bytes) else bytes(chunk) - return datas + datas.append(frame_data) + + return datas + + loop = asyncio.get_running_loop() + # 在单独的线程中执行同步的音频处理操作 + return await loop.run_in_executor(None, _sync_audio_to_data) def audio_bytes_to_data_stream( From 5c261528d026cc1489b030c58406ad172c7affd1 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sat, 13 Dec 2025 23:10:40 +0800 Subject: [PATCH 19/39] =?UTF-8?q?update:=E5=B8=B8=E7=94=A8=E9=9F=B3?= =?UTF-8?q?=E9=A2=91=E5=A2=9E=E5=8A=A0=E7=BC=93=E5=AD=98=EF=BC=8C=E6=8A=B5?= =?UTF-8?q?=E5=BE=A1=E9=AB=98=E5=B9=B6=E5=8F=91=E6=9C=AA=E6=8E=88=E6=9D=83?= =?UTF-8?q?=E8=AE=BE=E5=A4=87=E8=AE=BF=E9=97=AE?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../xiaozhi-server/core/handle/helloHandle.py | 2 +- .../xiaozhi-server/core/utils/cache/config.py | 4 ++++ main/xiaozhi-server/core/utils/util.py | 24 +++++++++++++++++-- 3 files changed, 27 insertions(+), 3 deletions(-) diff --git a/main/xiaozhi-server/core/handle/helloHandle.py b/main/xiaozhi-server/core/handle/helloHandle.py index efe66b59..a4220d5a 100644 --- a/main/xiaozhi-server/core/handle/helloHandle.py +++ b/main/xiaozhi-server/core/handle/helloHandle.py @@ -101,7 +101,7 @@ async def checkWakeupWords(conn, text): } # 获取音频数据 - opus_packets = await audio_to_data(response.get("file_path")) + opus_packets = await audio_to_data(response.get("file_path"), use_cache=False) # 播放唤醒词回复 conn.client_abort = False diff --git a/main/xiaozhi-server/core/utils/cache/config.py b/main/xiaozhi-server/core/utils/cache/config.py index 248c2af7..f85e40bb 100644 --- a/main/xiaozhi-server/core/utils/cache/config.py +++ b/main/xiaozhi-server/core/utils/cache/config.py @@ -19,6 +19,7 @@ class CacheType(Enum): CONFIG = "config" DEVICE_PROMPT = "device_prompt" VOICEPRINT_HEALTH = "voiceprint_health" # 声纹识别健康检查 + AUDIO_DATA = "audio_data" # 音频数据缓存 @dataclass @@ -58,5 +59,8 @@ class CacheConfig: CacheType.VOICEPRINT_HEALTH: cls( strategy=CacheStrategy.TTL, ttl=600, max_size=100 # 10分钟过期 ), + CacheType.AUDIO_DATA: cls( + strategy=CacheStrategy.TTL, ttl=600, max_size=100 # 10分钟过期 + ), } return configs.get(cache_type, cls()) diff --git a/main/xiaozhi-server/core/utils/util.py b/main/xiaozhi-server/core/utils/util.py index 2baedf68..4547ad8f 100644 --- a/main/xiaozhi-server/core/utils/util.py +++ b/main/xiaozhi-server/core/utils/util.py @@ -269,13 +269,27 @@ def audio_to_data_stream( pcm_to_data_stream(raw_data, is_opus, callback) -async def audio_to_data(audio_file_path: str, is_opus: bool = True) -> list[bytes]: +async def audio_to_data( + audio_file_path: str, is_opus: bool = True, use_cache: bool = True +) -> list[bytes]: """ 将音频文件转换为Opus/PCM编码的帧列表 Args: audio_file_path: 音频文件路径 is_opus: 是否进行Opus编码 + use_cache: 是否使用缓存 """ + from core.utils.cache.manager import cache_manager + from core.utils.cache.config import CacheType + + # 生成缓存键，包含文件路径和编码类型 + cache_key = f"{audio_file_path}:{is_opus}" + + # 尝试从缓存获取结果 + if use_cache: + cached_result = cache_manager.get(CacheType.AUDIO_DATA, cache_key) + if cached_result is not None: + return cached_result def _sync_audio_to_data(): # 获取文件后缀名 @@ -324,7 +338,13 @@ async def audio_to_data(audio_file_path: str, is_opus: bool = True) -> list[byte loop = asyncio.get_running_loop() # 在单独的线程中执行同步的音频处理操作 - return await loop.run_in_executor(None, _sync_audio_to_data) + result = await loop.run_in_executor(None, _sync_audio_to_data) + + # 将结果存入缓存，使用配置中定义的TTL（10分钟） + if use_cache: + cache_manager.set(CacheType.AUDIO_DATA, cache_key, result) + + return result def audio_bytes_to_data_stream( From d2e3a63418700180b85bde7aafec62c3f17e0ba5 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sun, 14 Dec 2025 14:24:39 +0800 Subject: [PATCH 20/39] =?UTF-8?q?update:=E4=BC=98=E5=8C=96=E6=B5=8B?= =?UTF-8?q?=E8=AF=95=E9=A1=B5=E9=9D=A2=E7=BC=93=E5=86=B2=E9=9F=B3=E9=A2=91?= =?UTF-8?q?=E6=92=AD=E6=94=BE?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/test/css/test_page.css | 3 +- .../test/js/core/audio/player.js | 35 +++++++++ .../test/js/core/audio/stream-context.js | 72 ++++++++++++++--- .../test/js/core/network/websocket.js | 7 +- main/xiaozhi-server/test/js/ui/controller.js | 78 ++++++++++++++++++- .../test/js/utils/blocking-queue.js | 5 ++ main/xiaozhi-server/test/test_page.html | 8 +- 7 files changed, 191 insertions(+), 17 deletions(-) diff --git a/main/xiaozhi-server/test/css/test_page.css b/main/xiaozhi-server/test/css/test_page.css index c0564191..b197c60d 100644 --- a/main/xiaozhi-server/test/css/test_page.css +++ b/main/xiaozhi-server/test/css/test_page.css @@ -267,6 +267,7 @@ span.connection-status.llm-emoji { .llm-emoji .status { font-size: 14px !important; padding: 8px 20px !important; + line-height: 1.2 !important; } .emoji-large { @@ -393,7 +394,7 @@ span.connection-status.llm-emoji { /* ==================== 会话记录和日志 ==================== */ .flex-container { display: flex; - margin-top: 10px; + margin-top: 20px; background-color: #f9fafb; } diff --git a/main/xiaozhi-server/test/js/core/audio/player.js b/main/xiaozhi-server/test/js/core/audio/player.js index 459fbb54..bc89d58a 100644 --- a/main/xiaozhi-server/test/js/core/audio/player.js +++ b/main/xiaozhi-server/test/js/core/audio/player.js @@ -249,6 +249,41 @@ export class AudioPlayer { this.playBufferedAudio(); this.startAudioBuffering(); } + + // 获取音频包统计信息 + getAudioStats() { + if (!this.streamingContext) { + return { + pendingDecode: 0, + pendingPlay: 0, + totalPending: 0 + }; + } + + const pendingDecode = this.streamingContext.getPendingDecodeCount(); + const pendingPlay = this.streamingContext.getPendingPlayCount(); + + return { + pendingDecode, // 待解码包数 + pendingPlay, // 待播放包数 + totalPending: pendingDecode + pendingPlay // 总待处理包数 + }; + } + + // 清空所有音频缓冲并停止播放 + clearAllAudio() { + log('AudioPlayer: 清空所有音频', 'info'); + + // 清空接收队列（使用clear方法保持对象引用） + this.queue.clear(); + + // 清空流上下文的所有缓冲 + if (this.streamingContext) { + this.streamingContext.clearAllBuffers(); + } + + log('AudioPlayer: 音频已清空', 'success'); + } } // 创建单例 diff --git a/main/xiaozhi-server/test/js/core/audio/stream-context.js b/main/xiaozhi-server/test/js/core/audio/stream-context.js index 9c722505..05b8c1db 100644 --- a/main/xiaozhi-server/test/js/core/audio/stream-context.js +++ b/main/xiaozhi-server/test/js/core/audio/stream-context.js @@ -22,6 +22,7 @@ export class StreamingContext { this.source = null; // 当前音频源 this.totalSamples = 0; // 累积的总样本数 this.lastPlayTime = 0; // 上次播放的时间戳 + this.scheduledEndTime = 0; // 已调度音频的结束时间 } // 缓存音频数组 @@ -31,17 +32,19 @@ export class StreamingContext { // 获取需要处理缓存队列，单线程：在audioBufferQueue一直更新的状态下不会出现安全问题 async getPendingAudioBufferQueue() { - // 原子交换 + 清空 - [this.pendingAudioBufferQueue, this.audioBufferQueue] = [await this.audioBufferQueue.dequeue(), new BlockingQueue()]; + // 等待数据到达并获取 + const data = await this.audioBufferQueue.dequeue(); + // 赋值给待处理队列 + this.pendingAudioBufferQueue = data; } // 获取正在播放已解码的PCM队列，单线程：在activeQueue一直更新的状态下不会出现安全问题 async getQueue(minSamples) { - let TepArray = []; const num = minSamples - this.queue.length > 0 ? minSamples - this.queue.length : 1; - // 原子交换 + 清空 - [TepArray, this.activeQueue] = [await this.activeQueue.dequeue(num), new BlockingQueue()]; - this.queue.push(...TepArray); + + // 等待数据并获取 + const tempArray = await this.activeQueue.dequeue(num); + this.queue.push(...tempArray); } // 将Int16音频数据转换为Float32音频数据 @@ -54,6 +57,57 @@ export class StreamingContext { return float32Data; } + // 获取待解码包数 + getPendingDecodeCount() { + return this.audioBufferQueue.length + this.pendingAudioBufferQueue.length; + } + + // 获取待播放样本数（转换为包数，每包960样本） + getPendingPlayCount() { + // 计算已在队列中的样本 + const queuedSamples = this.activeQueue.length + this.queue.length; + + // 计算已调度但未播放的样本（在Web Audio缓冲区中） + let scheduledSamples = 0; + if (this.playing && this.scheduledEndTime) { + const currentTime = this.audioContext.currentTime; + const remainingTime = Math.max(0, this.scheduledEndTime - currentTime); + scheduledSamples = Math.floor(remainingTime * this.sampleRate); + } + + const totalSamples = queuedSamples + scheduledSamples; + return Math.ceil(totalSamples / 960); + } + + // 清空所有音频缓冲 + clearAllBuffers() { + log('清空所有音频缓冲', 'info'); + + // 清空所有队列（使用clear方法保持对象引用） + this.audioBufferQueue.clear(); + this.pendingAudioBufferQueue = []; + this.activeQueue.clear(); + this.queue = []; + + // 停止当前播放的音频源 + if (this.source) { + try { + this.source.stop(); + this.source.disconnect(); + } catch (e) { + // 忽略已经停止的错误 + } + this.source = null; + } + + // 重置状态 + this.playing = false; + this.scheduledEndTime = this.audioContext.currentTime; + this.totalSamples = 0; + + log('音频缓冲已清空', 'success'); + } + // 将Opus数据解码为PCM async decodeOpusFrames() { if (!this.opusDecoder) { @@ -97,7 +151,7 @@ export class StreamingContext { // 开始播放音频 async startPlaying() { - let scheduledEndTime = this.audioContext.currentTime; // 跟踪已调度音频的结束时间 + this.scheduledEndTime = this.audioContext.currentTime; // 跟踪已调度音频的结束时间 while (true) { // 初始缓冲：等待足够的样本再开始播放 @@ -126,7 +180,7 @@ export class StreamingContext { // 精确调度播放时间 const currentTime = this.audioContext.currentTime; - const startTime = Math.max(scheduledEndTime, currentTime); + const startTime = Math.max(this.scheduledEndTime, currentTime); // 直接连接到输出 this.source.connect(this.audioContext.destination); @@ -136,7 +190,7 @@ export class StreamingContext { // 更新下一个音频块的调度时间 const duration = audioBuffer.duration; - scheduledEndTime = startTime + duration; + this.scheduledEndTime = startTime + duration; this.lastPlayTime = startTime; // 如果队列中数据不足，等待新数据 diff --git a/main/xiaozhi-server/test/js/core/network/websocket.js b/main/xiaozhi-server/test/js/core/network/websocket.js index b62c710b..a605e6f1 100644 --- a/main/xiaozhi-server/test/js/core/network/websocket.js +++ b/main/xiaozhi-server/test/js/core/network/websocket.js @@ -123,7 +123,12 @@ export class WebSocketHandler { } else if (message.state === 'sentence_end') { log(`语音段结束: ${message.text}`, 'info'); } else if (message.state === 'stop') { - log('服务器语音传输结束', 'info'); + log('服务器语音传输结束，清空所有音频缓冲', 'info'); + + // 清空所有音频缓冲并停止播放 + const audioPlayer = getAudioPlayer(); + audioPlayer.clearAllAudio(); + this.isRemoteSpeaking = false; if (this.onRecordButtonStateChange) { this.onRecordButtonStateChange(false); diff --git a/main/xiaozhi-server/test/js/ui/controller.js b/main/xiaozhi-server/test/js/ui/controller.js index 8fc9dd31..3e4f6563 100644 --- a/main/xiaozhi-server/test/js/ui/controller.js +++ b/main/xiaozhi-server/test/js/ui/controller.js @@ -2,6 +2,7 @@ import { loadConfig, saveConfig } from '../config/manager.js'; import { getAudioRecorder } from '../core/audio/recorder.js'; import { getWebSocketHandler } from '../core/network/websocket.js'; +import { getAudioPlayer } from '../core/audio/player.js'; // UI控制器类 export class UIController { @@ -9,6 +10,7 @@ export class UIController { this.isEditing = false; this.visualizerCanvas = null; this.visualizerContext = null; + this.audioStatsTimer = null; } // 初始化 @@ -18,6 +20,7 @@ export class UIController { this.initVisualizer(); this.initEventListeners(); + this.startAudioStatsMonitor(); loadConfig(); } @@ -86,17 +89,20 @@ export class UIController { const sessionStatus = document.getElementById('sessionStatus'); if (!sessionStatus) return; + // 保留背景元素 + const bgHtml = ''; + if (isSpeaking === null) { // 离线状态 - sessionStatus.innerHTML = '😶 小智离线中'; + sessionStatus.innerHTML = bgHtml + '😶 小智离线中'; sessionStatus.className = 'status offline'; } else if (isSpeaking) { // 说话中 - sessionStatus.innerHTML = '😶 小智说话中'; + sessionStatus.innerHTML = bgHtml + '😶 小智说话中'; sessionStatus.className = 'status speaking'; } else { // 聆听中 - sessionStatus.innerHTML = '😶 小智聆听中'; + sessionStatus.innerHTML = bgHtml + '😶 小智聆听中'; sessionStatus.className = 'status listening'; } } @@ -110,8 +116,72 @@ export class UIController { let currentText = sessionStatus.textContent; // 移除现有的表情符号 currentText = currentText.replace(/[\u{1F300}-\u{1F9FF}]|[\u{2600}-\u{26FF}]|[\u{2700}-\u{27BF}]/gu, '').trim(); + + // 保留背景元素 + const bgHtml = ''; + // 使用 innerHTML 添加带样式的表情 - sessionStatus.innerHTML = `${emoji} ${currentText}`; + sessionStatus.innerHTML = bgHtml + `${emoji} ${currentText}`; + } + + // 更新音频统计信息 + updateAudioStats() { + const audioPlayer = getAudioPlayer(); + const stats = audioPlayer.getAudioStats(); + + const sessionStatus = document.getElementById('sessionStatus'); + const sessionStatusBg = document.getElementById('sessionStatusBg'); + + // 只在说话状态下显示背景进度 + if (sessionStatus && sessionStatus.classList.contains('speaking') && sessionStatusBg) { + if (stats.pendingPlay > 0) { + // 计算进度：5包=50%，10包及以上=100% + let percentage; + if (stats.pendingPlay >= 10) { + percentage = 100; + } else { + percentage = (stats.pendingPlay / 10) * 100; + } + + sessionStatusBg.style.width = `${percentage}%`; + + // 根据缓冲量改变背景颜色 + if (stats.pendingPlay < 5) { + // 缓冲不足：橙红色半透明 + sessionStatusBg.style.background = 'linear-gradient(90deg, rgba(255, 152, 0, 0.25), rgba(255, 87, 34, 0.25))'; + } else if (stats.pendingPlay < 10) { + // 一般：黄绿色半透明 + sessionStatusBg.style.background = 'linear-gradient(90deg, rgba(205, 220, 57, 0.25), rgba(76, 175, 80, 0.25))'; + } else { + // 充足：绿蓝色半透明 + sessionStatusBg.style.background = 'linear-gradient(90deg, rgba(76, 175, 80, 0.25), rgba(33, 150, 243, 0.25))'; + } + } else { + // 没有缓冲，隐藏背景 + sessionStatusBg.style.width = '0%'; + } + } else { + // 非说话状态，隐藏背景 + if (sessionStatusBg) { + sessionStatusBg.style.width = '0%'; + } + } + } + + // 启动音频统计监控 + startAudioStatsMonitor() { + // 每100ms更新一次音频统计 + this.audioStatsTimer = setInterval(() => { + this.updateAudioStats(); + }, 100); + } + + // 停止音频统计监控 + stopAudioStatsMonitor() { + if (this.audioStatsTimer) { + clearInterval(this.audioStatsTimer); + this.audioStatsTimer = null; + } } // 绘制音频可视化效果 diff --git a/main/xiaozhi-server/test/js/utils/blocking-queue.js b/main/xiaozhi-server/test/js/utils/blocking-queue.js index 31a43872..738a3e75 100644 --- a/main/xiaozhi-server/test/js/utils/blocking-queue.js +++ b/main/xiaozhi-server/test/js/utils/blocking-queue.js @@ -95,4 +95,9 @@ export default class BlockingQueue { get length() { return this.#items.length; } + + /* 清空队列（保持对象引用，不影响等待者） */ + clear() { + this.#items.length = 0; + } } \ No newline at end of file diff --git a/main/xiaozhi-server/test/test_page.html b/main/xiaozhi-server/test/test_page.html index 97af77ac..f3f583c9 100644 --- a/main/xiaozhi-server/test/test_page.html +++ b/main/xiaozhi-server/test/test_page.html @@ -91,6 +91,7 @@ +
@@ -113,9 +114,12 @@
-
+
- 😶 小智离线中 + + + 😶 小智离线中 +
From 4a4dbf123e9a6aace8c871b4373b71bf32cc6fc5 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Sun, 14 Dec 2025 15:29:13 +0800 Subject: [PATCH 21/39] =?UTF-8?q?update:mqtt=E9=83=A8=E7=BD=B2=E6=9B=B4?= =?UTF-8?q?=E6=96=B0?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- docs/mqtt-gateway-integration.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/docs/mqtt-gateway-integration.md b/docs/mqtt-gateway-integration.md index b2f3068c..2b96255f 100644 --- a/docs/mqtt-gateway-integration.md +++ b/docs/mqtt-gateway-integration.md @@ -76,6 +76,7 @@ MQTT_PORT=1883 # MQTT服务器端口 UDP_PORT=8884 # UDP服务器端口 API_PORT=8007 # 管理API端口 MQTT_SIGNATURE_KEY=test # MQTT签名密钥 +SERVER_SECRET=Te1st12134 # 服务器密钥，请保持和智控台（server.secret）一致或者和xiaozhi-server里（server.auth_key）保持一致 ``` 请注意`PUBLIC_IP`配置，确保其与实际公网IP一致，如果有域名就填域名。 @@ -85,6 +86,13 @@ MQTT_SIGNATURE_KEY=test # MQTT签名密钥 - 注意不要用简单的密码，比如`123456`、`test`等。 - 注意不要用简单的密码，比如`123456`、`test`等。 +`SERVER_SECRET` 是用生成websocket连接的认证信息。 + +1、如果你是全模块部署，且你的智控台的参数管理里`server.auth.enabled`设置成了`true`，那么，`SERVER_SECRET`需要和智控台（`server.secret`）保持一致。 + +2、如果你是单模块部署，且你在配置文件里把`server.auth.enabled`设置成了`true`，那么，`SERVER_SECRET`需要和配置文件里（`server.auth_key`）保持一致。 + + 6. 启动MQTT网关 ``` # 启动服务 From 33b4794e83fae676a08d27d608804714bed26d39 Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Mon, 15 Dec 2025 16:34:50 +0800 Subject: [PATCH 22/39] =?UTF-8?q?=E4=BC=98=E5=8C=96?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../core/utils/audioRateController.py | 38 ++++++++++++------- 1 file changed, 24 insertions(+), 14 deletions(-) diff --git a/main/xiaozhi-server/core/utils/audioRateController.py b/main/xiaozhi-server/core/utils/audioRateController.py index 35038d27..01d71b05 100644 --- a/main/xiaozhi-server/core/utils/audioRateController.py +++ b/main/xiaozhi-server/core/utils/audioRateController.py @@ -1,5 +1,6 @@ import time import asyncio +from collections import deque from config.logger import setup_logging TAG = __name__ @@ -18,13 +19,14 @@ class AudioRateController: frame_duration: 单个音频帧时长（毫秒），默认60ms """ self.frame_duration = frame_duration - self.queue = [] + self.queue = deque() self.play_position = 0 # 虚拟播放位置（毫秒） self.start_timestamp = None # 开始时间戳（只读，不修改） self.pending_send_task = None self.logger = logger self.queue_empty_event = asyncio.Event() # 队列清空事件 self.queue_empty_event.set() # 初始为空状态 + self.queue_has_data_event = asyncio.Event() # 队列数据事件 def reset(self): """重置控制器状态""" @@ -34,13 +36,17 @@ class AudioRateController: self.queue.clear() self.play_position = 0 - self.start_timestamp = time.time() - self.queue_empty_event.set() # 队列已清空 + self.start_timestamp = None # 由首个音频包设置 + # 相关事件处理 + self.queue_empty_event.set() + self.queue_has_data_event.clear() def add_audio(self, opus_packet): """添加音频包到队列""" self.queue.append(("audio", opus_packet)) - self.queue_empty_event.clear() # 队列非空，清除事件 + # 相关事件处理 + self.queue_empty_event.clear() + self.queue_has_data_event.set() def add_message(self, message_callback): """ @@ -50,13 +56,15 @@ class AudioRateController: message_callback: 消息发送回调函数 async def() """ self.queue.append(("message", message_callback)) - self.queue_empty_event.clear() # 队列非空，清除事件 + # 相关事件处理 + self.queue_empty_event.clear() + self.queue_has_data_event.set() def _get_elapsed_ms(self): """获取已经过的时间（毫秒）""" if self.start_timestamp is None: return 0 - return (time.time() - self.start_timestamp) * 1000 + return (time.monotonic() - self.start_timestamp) * 1000 async def check_queue(self, send_audio_callback): """ @@ -65,9 +73,6 @@ class AudioRateController: Args: send_audio_callback: 发送音频的回调函数 async def(opus_packet) """ - if self.start_timestamp is None: - self.start_timestamp = time.time() - while self.queue: item = self.queue[0] item_type = item[0] @@ -75,7 +80,7 @@ class AudioRateController: if item_type == "message": # 消息类型：立即发送，不占用播放时间 _, message_callback = item - self.queue.pop(0) + self.queue.popleft() try: await message_callback() except Exception as e: @@ -83,6 +88,9 @@ class AudioRateController: raise elif item_type == "audio": + if self.start_timestamp is None: + self.start_timestamp = time.monotonic() + _, opus_packet = item # 循环等待直到时间到达 @@ -107,16 +115,17 @@ class AudioRateController: break # 时间已到，从队列移除并发送 - self.queue.pop(0) + self.queue.popleft() self.play_position += self.frame_duration - try: await send_audio_callback(opus_packet) except Exception as e: self.logger.bind(tag=TAG).error(f"发送音频失败: {e}") raise + # 队列处理完后清除事件 self.queue_empty_event.set() + self.queue_has_data_event.clear() def start_sending(self, send_audio_callback): """ @@ -132,9 +141,10 @@ class AudioRateController: async def _send_loop(): try: while True: + # 等待队列数据事件，不轮询等待占用CPU + await self.queue_has_data_event.wait() + await self.check_queue(send_audio_callback) - # 如果队列空了，短暂等待后再检查（避免 busy loop） - await asyncio.sleep(0.01) except asyncio.CancelledError: self.logger.bind(tag=TAG).debug("音频发送循环已停止") except Exception as e: From 43ead841a4714867cc315e865e47661ea18fe96f Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Mon, 15 Dec 2025 17:31:13 +0800 Subject: [PATCH 23/39] =?UTF-8?q?fix:=20=E7=AD=89=E5=BE=85=E5=88=9D?= =?UTF-8?q?=E5=A7=8B=E5=8C=96=E6=88=90=E5=8A=9F=E8=AE=BE=E7=BD=AE=E4=BA=8B?= =?UTF-8?q?=E4=BB=B6?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/core/connection.py | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/main/xiaozhi-server/core/connection.py b/main/xiaozhi-server/core/connection.py index 236d4e51..0d3e4090 100644 --- a/main/xiaozhi-server/core/connection.py +++ b/main/xiaozhi-server/core/connection.py @@ -434,6 +434,7 @@ class ConnectionHandler: self.tts.open_audio_channels(self), self.loop ) if self.need_bind: + self.bind_completed_event.set() return self.selected_module_str = build_module_string( self.config.get("selected_module", {}) @@ -574,16 +575,13 @@ class ConnectionHandler: self.bind_completed_event.set() except DeviceNotFoundException as e: self.need_bind = True - self.bind_completed_event.set() # 状态已确定，设置事件 private_config = {} except DeviceBindException as e: self.need_bind = True self.bind_code = e.bind_code - self.bind_completed_event.set() # 状态已确定，设置事件 private_config = {} except Exception as e: self.need_bind = True - self.bind_completed_event.set() # 状态已确定，设置事件 self.logger.bind(tag=TAG).error(f"异步获取差异化配置失败: {e}") private_config = {} From b2123ff01a6cb02d48504d38fbb389682a82b62b Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Mon, 15 Dec 2025 18:15:35 +0800 Subject: [PATCH 24/39] =?UTF-8?q?update:=E4=BC=98=E5=8C=96=E6=96=87?= =?UTF-8?q?=E6=A1=A3=E8=AF=B4=E6=98=8E?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- README.md | 10 +++++----- README_de.md | 10 +++++----- README_en.md | 10 +++++----- README_vi.md | 10 +++++----- docs/FAQ.md | 8 ++++---- 5 files changed, 24 insertions(+), 24 deletions(-) diff --git a/README.md b/README.md index 943501a7..7602db54 100644 --- a/README.md +++ b/README.md @@ -211,10 +211,10 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/ | 模块名称 | 入门全免费设置 | 流式配置 | |:---:|:---:|:---:| -| ASR(语音识别) | FunASR(本地) | 👍FunASR(本地GPU模式) | -| LLM(大模型) | ChatGLMLLM(智谱glm-4-flash) | 👍AliLLM(qwen3-235b-a22b-instruct-2507) 或 👍DoubaoLLM(doubao-1-5-pro-32k-250115) | -| VLLM(视觉大模型) | ChatGLMVLLM(智谱glm-4v-flash) | 👍QwenVLVLLM(千问qwen2.5-vl-3b-instructh) | -| TTS(语音合成) | ✅LinkeraiTTS(灵犀流式) | 👍HuoshanDoubleStreamTTS(火山双流式语音合成) 或 👍AliyunStreamTTS(阿里云流式语音合成) | +| ASR(语音识别) | FunASR(本地) | 👍XunfeiStreamASR(讯飞流式) | +| LLM(大模型) | glm-4-flash(智谱) | 👍qwen-flash(阿里百炼) | +| VLLM(视觉大模型) | glm-4v-flash(智谱) | 👍qwen2.5-vl-3b-instructh(阿里百炼) | +| TTS(语音合成) | ✅LinkeraiTTS(灵犀流式) | 👍HuoshanDoubleStreamTTS(火山流式) | | 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） | @@ -260,7 +260,7 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/ --- ## 产品生态 👬 -小智是一个生态，当你使用这个产品时，也可以看看其他在这个生态圈的[优秀项目](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE) +小智是一个生态，当你使用这个产品时，也可以看看其他在这个生态圈的[优秀项目](https://github.com/78/xiaozhi-esp32/blob/main/README_zh.md#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE) --- diff --git a/README_de.md b/README_de.md index c3578fec..53609462 100644 --- a/README_de.md +++ b/README_de.md @@ -209,10 +209,10 @@ Websocket-Schnittstellenadresse: wss://2662r3426b.vicp.fun/xiaozhi/v1/ | Modulname | Einstiegslevel Kostenlose Einstellungen | Streaming-Konfiguration | |:---:|:---:|:---:| -| ASR (Spracherkennung) | FunASR (Lokal) | 👍FunASR (Lokaler GPU-Modus) | -| LLM (Großes Modell) | ChatGLMLLM (Zhipu glm-4-flash) | 👍AliLLM (qwen3-235b-a22b-instruct-2507) oder 👍DoubaoLLM (doubao-1-5-pro-32k-250115) | -| VLLM (Vision Large Model) | ChatGLMVLLM (Zhipu glm-4v-flash) | 👍QwenVLVLLM (Qwen qwen2.5-vl-3b-instructh) | -| TTS (Sprachsynthese) | ✅LinkeraiTTS (Lingxi-Streaming) | 👍HuoshanDoubleStreamTTS (Volcano Dual-Stream-Sprachsynthese) oder 👍AliyunStreamTTS (Alibaba Cloud Streaming-Sprachsynthese) | +| ASR (Spracherkennung) | FunASR (Lokal) | 👍XunfeiStreamASR (Xunfei-Streaming) | +| LLM (Großes Modell) | glm-4-flash (Zhipu) | 👍qwen-flash (Alibaba Bailian) | +| VLLM (Vision Large Model) | glm-4v-flash (Zhipu) | 👍qwen2.5-vl-3b-instructh (Alibaba Bailian) | +| TTS (Sprachsynthese) | ✅LinkeraiTTS (Lingxi-Streaming) | 👍HuoshanDoubleStreamTTS (Volcano-Streaming) | | Intent (Absichtserkennung) | function_call (Funktionsaufruf) | function_call (Funktionsaufruf) | | Memory (Gedächtnisfunktion) | mem_local_short (Lokales Kurzzeitgedächtnis) | mem_local_short (Lokales Kurzzeitgedächtnis) | @@ -258,7 +258,7 @@ Wenn Sie ein Softwareentwickler sind, finden Sie hier einen [Offenen Brief an En --- ## Produktökosystem 👬 -Xiaozhi ist ein Ökosystem. Wenn Sie dieses Produkt verwenden, können Sie sich auch andere [hervorragende Projekte](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE) in diesem Ökosystem ansehen +Xiaozhi ist ein Ökosystem. Wenn Sie dieses Produkt verwenden, können Sie sich auch andere [hervorragende Projekte](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#related-open-source-projects) in diesem Ökosystem ansehen --- diff --git a/README_en.md b/README_en.md index e8437832..cc0f170c 100644 --- a/README_en.md +++ b/README_en.md @@ -208,10 +208,10 @@ Websocket Interface Address: wss://2662r3426b.vicp.fun/xiaozhi/v1/ | Module Name | Entry Level Free Settings | Streaming Configuration | |:---:|:---:|:---:| -| ASR(Speech Recognition) | FunASR(Local) | 👍FunASRServer or 👍DoubaoStreamASR | -| LLM(Large Model) | ChatGLMLLM(Zhipu glm-4-flash) | 👍DoubaoLLM(Volcano doubao-1-5-pro-32k-250115) | -| VLLM(Vision Large Model) | ChatGLMVLLM(Zhipu glm-4v-flash) | 👍QwenVLVLLM(Qwen qwen2.5-vl-3b-instructh) | -| TTS(Speech Synthesis) | ✅LinkeraiTTS(Lingxi streaming) | 👍HuoshanDoubleStreamTTS(Volcano dual-stream speech synthesis) | +| ASR(Speech Recognition) | FunASR(Local) | 👍XunfeiStreamASR(Xunfei Streaming) | +| LLM(Large Model) | glm-4-flash(Zhipu) | 👍qwen-flash(Alibaba Bailian) | +| VLLM(Vision Large Model) | glm-4v-flash(Zhipu) | 👍qwen2.5-vl-3b-instructh(Alibaba Bailian) | +| TTS(Speech Synthesis) | ✅LinkeraiTTS(Lingxi streaming) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) | | Intent(Intent Recognition) | function_call(Function calling) | function_call(Function calling) | | Memory(Memory function) | mem_local_short(Local short-term memory) | mem_local_short(Local short-term memory) | @@ -256,7 +256,7 @@ If you are a software developer, here is an [Open Letter to Developers](docs/con --- ## Product Ecosystem 👬 -Xiaozhi is an ecosystem. When using this product, you can also check out other [excellent projects](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE) in this ecosystem +Xiaozhi is an ecosystem. When using this product, you can also check out other [excellent projects](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#related-open-source-projects) in this ecosystem | Project Name | Project Address | Project Description | |:---------------------|:--------|:--------| diff --git a/README_vi.md b/README_vi.md index 92697551..83557ce5 100644 --- a/README_vi.md +++ b/README_vi.md @@ -210,10 +210,10 @@ Công cụ kiểm tra dịch vụ: https://2662r3426b.vicp.fun/test/ | Tên module | Cài đặt miễn phí cho người mới | Cấu hình streaming | |:---:|:---:|:---:| -| ASR(Nhận dạng giọng nói) | FunASR(Local) | 👍FunASR(Chế độ GPU cục bộ) | -| LLM(Mô hình lớn) | ChatGLMLLM(Zhipu glm-4-flash) | 👍AliLLM(qwen3-235b-a22b-instruct-2507) hoặc 👍DoubaoLLM(doubao-1-5-pro-32k-250115) | -| VLLM(Mô hình lớn thị giác) | ChatGLMVLLM(Zhipu glm-4v-flash) | 👍QwenVLVLLM(Qwen qwen2.5-vl-3b-instructh) | -| TTS(Tổng hợp giọng nói) | ✅LinkeraiTTS(Lingxi streaming) | 👍HuoshanDoubleStreamTTS(Tổng hợp giọng nói streaming kép Volcano) hoặc 👍AliyunStreamTTS(Tổng hợp giọng nói streaming Alibaba Cloud) | +| ASR(Nhận dạng giọng nói) | FunASR(Local) | 👍XunfeiStreamASR(Xunfei Streaming) | +| LLM(Mô hình lớn) | glm-4-flash(Zhipu) | 👍qwen-flash(Alibaba Bailian) | +| VLLM(Mô hình lớn thị giác) | glm-4v-flash(Zhipu) | 👍qwen2.5-vl-3b-instructh(Alibaba Bailian) | +| TTS(Tổng hợp giọng nói) | ✅LinkeraiTTS(Lingxi streaming) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) | | Intent(Nhận dạng ý định) | function_call(Gọi hàm) | function_call(Gọi hàm) | | Memory(Chức năng bộ nhớ) | mem_local_short(Bộ nhớ ngắn hạn cục bộ) | mem_local_short(Bộ nhớ ngắn hạn cục bộ) | @@ -259,7 +259,7 @@ Nếu bạn là một nhà phát triển phần mềm, đây có một [Lá thư --- ## Hệ sinh thái sản phẩm 👬 -Xiaozhi là một hệ sinh thái, khi bạn sử dụng sản phẩm này, bạn cũng có thể xem các [dự án xuất sắc](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE) khác trong hệ sinh thái này +Xiaozhi là một hệ sinh thái, khi bạn sử dụng sản phẩm này, bạn cũng có thể xem các [dự án xuất sắc](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#related-open-source-projects) khác trong hệ sinh thái này --- diff --git a/docs/FAQ.md b/docs/FAQ.md index c40e7784..f1e12d84 100644 --- a/docs/FAQ.md +++ b/docs/FAQ.md @@ -38,10 +38,10 @@ conda install conda-forge::ffmpeg | 模块名称 | 入门全免费设置 | 流式配置 | |:---:|:---:|:---:| -| ASR(语音识别) | FunASR(本地) | 👍FunASR(本地GPU模式) | -| LLM(大模型) | ChatGLMLLM(智谱glm-4-flash) | 👍AliLLM(qwen3-235b-a22b-instruct-2507) 或 👍DoubaoLLM(doubao-1-5-pro-32k-250115) | -| VLLM(视觉大模型) | ChatGLMVLLM(智谱glm-4v-flash) | 👍QwenVLVLLM(千问qwen2.5-vl-3b-instructh) | -| TTS(语音合成) | ✅LinkeraiTTS(灵犀流式) | 👍HuoshanDoubleStreamTTS(火山双流式语音合成) 或 👍AliyunStreamTTS(阿里云流式语音合成) | +| ASR(语音识别) | FunASR(本地) | 👍XunfeiStreamASR(讯飞流式) | +| LLM(大模型) | glm-4-flash(智谱) | 👍qwen-flash(阿里百炼) | +| VLLM(视觉大模型) | glm-4v-flash(智谱) | 👍qwen2.5-vl-3b-instructh(阿里百炼) | +| TTS(语音合成) | ✅LinkeraiTTS(灵犀流式) | 👍HuoshanDoubleStreamTTS(火山流式) | | 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） | From 1a7c06eb810bc54abd9888c4721ef85b0982e4a8 Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Tue, 16 Dec 2025 16:39:13 +0800 Subject: [PATCH 25/39] =?UTF-8?q?update:=20=E5=A2=9E=E5=8A=A0websocket?= =?UTF-8?q?=E5=BF=83=E8=B7=B3=E6=9C=BA=E5=88=B6?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../resources/db/changelog/202512161529.sql | 1 + .../db/changelog/db.changelog-master.yaml | 7 +++ main/xiaozhi-server/config.yaml | 3 ++ .../handle/textHandler/pingMessageHandler.py | 45 +++++++++++++++++++ .../core/handle/textMessageHandlerRegistry.py | 2 + .../core/handle/textMessageType.py | 1 + 6 files changed, 59 insertions(+) create mode 100644 main/manager-api/src/main/resources/db/changelog/202512161529.sql create mode 100644 main/xiaozhi-server/core/handle/textHandler/pingMessageHandler.py diff --git a/main/manager-api/src/main/resources/db/changelog/202512161529.sql b/main/manager-api/src/main/resources/db/changelog/202512161529.sql new file mode 100644 index 00000000..40f154c7 --- /dev/null +++ b/main/manager-api/src/main/resources/db/changelog/202512161529.sql @@ -0,0 +1 @@ +INSERT INTO `sys_params` (id, param_code, param_value, value_type, param_type, remark) VALUES (311, 'enable_websocket_ping', 'false', 'boolean', 1, '是否启用WebSocket心跳保活机制'); \ No newline at end of file diff --git a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml index dd6dff55..67d912a1 100755 --- a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml +++ b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml @@ -445,3 +445,10 @@ databaseChangeLog: - sqlFile: encoding: utf8 path: classpath:db/changelog/202512131453.sql + - changeSet: + id: 202512161529 + author: RanChen + changes: + - sqlFile: + encoding: utf8 + path: classpath:db/changelog/202512161529.sql diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml index e7b61dcd..f2bbe9be 100644 --- a/main/xiaozhi-server/config.yaml +++ b/main/xiaozhi-server/config.yaml @@ -69,6 +69,9 @@ enable_greeting: true enable_stop_tts_notify: false # 说完话是否开启提示音，音效地址 stop_tts_notify_voice: "config/assets/tts_notify.mp3" +# 是否启用WebSocket心跳保活机制 +enable_websocket_ping: false + # TTS音频发送延迟配置 # tts_audio_send_delay: 控制音频包发送间隔 diff --git a/main/xiaozhi-server/core/handle/textHandler/pingMessageHandler.py b/main/xiaozhi-server/core/handle/textHandler/pingMessageHandler.py new file mode 100644 index 00000000..f3af85eb --- /dev/null +++ b/main/xiaozhi-server/core/handle/textHandler/pingMessageHandler.py @@ -0,0 +1,45 @@ +import json +import time +from typing import Dict, Any + +from core.handle.textMessageHandler import TextMessageHandler +from core.handle.textMessageType import TextMessageType + +TAG = __name__ + + +class PingMessageHandler(TextMessageHandler): + """Ping消息处理器，用于保持WebSocket连接""" + + @property + def message_type(self) -> TextMessageType: + return TextMessageType.PING + + async def handle(self, conn, msg_json: Dict[str, Any]) -> None: + """ + 处理PING消息，发送PONG响应 + 消息格式：{"type": "ping"} + Args: + conn: WebSocket连接对象 + msg_json: PING消息的JSON数据 + """ + # 检查是否启用了WebSocket心跳功能 + enable_websocket_ping = conn.config.get("enable_websocket_ping", False) + if not enable_websocket_ping: + conn.logger.debug(f"WebSocket心跳功能未启用，忽略PING消息") + return + + try: + conn.logger.debug(f"收到PING消息，发送PONG响应") + conn.last_activity_time = time.time() * 1000 + # 构造PONG响应消息 + pong_message = { + "type": "pong", + "timestamp": time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()), + } + + # 发送PONG响应 + await conn.websocket.send(json.dumps(pong_message)) + + except Exception as e: + conn.logger.error(f"处理PING消息时发生错误: {e}") diff --git a/main/xiaozhi-server/core/handle/textMessageHandlerRegistry.py b/main/xiaozhi-server/core/handle/textMessageHandlerRegistry.py index e90d7231..65e9474f 100644 --- a/main/xiaozhi-server/core/handle/textMessageHandlerRegistry.py +++ b/main/xiaozhi-server/core/handle/textMessageHandlerRegistry.py @@ -7,6 +7,7 @@ from core.handle.textHandler.listenMessageHandler import ListenTextMessageHandle from core.handle.textHandler.mcpMessageHandler import McpTextMessageHandler from core.handle.textMessageHandler import TextMessageHandler from core.handle.textHandler.serverMessageHandler import ServerTextMessageHandler +from core.handle.textHandler.pingMessageHandler import PingMessageHandler TAG = __name__ @@ -27,6 +28,7 @@ class TextMessageHandlerRegistry: IotTextMessageHandler(), McpTextMessageHandler(), ServerTextMessageHandler(), + PingMessageHandler(), ] for handler in handlers: diff --git a/main/xiaozhi-server/core/handle/textMessageType.py b/main/xiaozhi-server/core/handle/textMessageType.py index 53e71b71..bd04d289 100644 --- a/main/xiaozhi-server/core/handle/textMessageType.py +++ b/main/xiaozhi-server/core/handle/textMessageType.py @@ -9,3 +9,4 @@ class TextMessageType(Enum): IOT = "iot" MCP = "mcp" SERVER = "server" + PING = "ping" From 53e26821ade9adc3bad1482dd7ecdb2b4e80b9a5 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Tue, 16 Dec 2025 22:03:12 +0800 Subject: [PATCH 26/39] =?UTF-8?q?update:=E8=A1=A5=E5=9B=9E=E5=89=8D5?= =?UTF-8?q?=E4=B8=AA=E5=8C=85=E6=8F=90=E5=89=8D=E5=8F=91=E9=80=81=E7=9A=84?= =?UTF-8?q?=E6=97=B6=E9=97=B4=EF=BC=8C=E5=9B=A0=E4=B8=BA=E5=8F=91=E9=80=81?= =?UTF-8?q?=E5=AE=8C=E4=B8=8D=E7=AD=89=E4=BA=8E=E6=92=AD=E6=94=BE=E5=AE=8C?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../core/handle/sendAudioHandle.py | 23 +++++++++++++------ 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/main/xiaozhi-server/core/handle/sendAudioHandle.py b/main/xiaozhi-server/core/handle/sendAudioHandle.py index d0167498..8198dfb0 100644 --- a/main/xiaozhi-server/core/handle/sendAudioHandle.py +++ b/main/xiaozhi-server/core/handle/sendAudioHandle.py @@ -7,6 +7,10 @@ from core.providers.tts.dto.dto import SentenceType from core.utils.audioRateController import AudioRateController TAG = __name__ +# 音频帧时长（毫秒） +AUDIO_FRAME_DURATION = 60 +# 预缓冲包数量，直接发送以减少延迟 +PRE_BUFFER_COUNT = 5 async def sendAudioMessage(conn, sentenceType, audios, text): @@ -45,7 +49,7 @@ async def sendAudioMessage(conn, sentenceType, audios, text): async def _wait_for_audio_completion(conn): """ - 等待音频队列清空 + 等待音频队列清空并等待预缓冲包播放完成 Args: conn: 连接对象 @@ -56,6 +60,13 @@ async def _wait_for_audio_completion(conn): f"等待音频发送完成，队列中还有 {len(rate_controller.queue)} 个包" ) await rate_controller.queue_empty_event.wait() + + # 等待预缓冲包播放完成 + # 前N个包直接发送，增加2个网络抖动包，需要额外等待它们在客户端播放完成 + frame_duration_ms = rate_controller.frame_duration + pre_buffer_playback_time = (PRE_BUFFER_COUNT + 2) * frame_duration_ms / 1000.0 + await asyncio.sleep(pre_buffer_playback_time) + conn.logger.bind(tag=TAG).debug("音频发送完成") @@ -81,14 +92,14 @@ async def _send_to_mqtt_gateway(conn, opus_packet, timestamp, sequence): await conn.websocket.send(complete_packet) -async def sendAudio(conn, audios, frame_duration=60): +async def sendAudio(conn, audios, frame_duration=AUDIO_FRAME_DURATION): """ 发送音频包，使用 AudioRateController 进行精确的流量控制 Args: conn: 连接对象 audios: 单个opus包(bytes) 或 opus包列表 - frame_duration: 帧时长（毫秒），默认60ms + frame_duration: 帧时长（毫秒），默认使用全局常量AUDIO_FRAME_DURATION """ if audios is None or len(audios) == 0: return @@ -187,16 +198,14 @@ async def _send_audio_with_rate_control( flow_control: 流控状态 send_delay: 固定延迟（秒），-1表示使用动态流控 """ - pre_buffer_count = 5 - for packet in audio_list: if conn.client_abort: return conn.last_activity_time = time.time() * 1000 - # 预缓冲：前5个包直接发送 - if flow_control["packet_count"] < pre_buffer_count: + # 预缓冲：前N个包直接发送 + if flow_control["packet_count"] < PRE_BUFFER_COUNT: await _do_send_audio(conn, packet, flow_control) conn.client_is_speaking = True elif send_delay > 0: From 3fb40677a40a98743ba7a1869a46f410e9cf853f Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Wed, 17 Dec 2025 11:58:40 +0800 Subject: [PATCH 27/39] =?UTF-8?q?update=EF=BC=9A=E7=BA=A0=E6=AD=A3?= =?UTF-8?q?=E6=98=BE=E7=A4=BA=E5=90=8D=E7=A7=B0?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/manager-web/src/i18n/de.js | 2 +- main/manager-web/src/i18n/en.js | 2 +- main/manager-web/src/i18n/vi.js | 2 +- main/manager-web/src/i18n/zh_CN.js | 2 +- main/manager-web/src/i18n/zh_TW.js | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/main/manager-web/src/i18n/de.js b/main/manager-web/src/i18n/de.js index 1d8704be..22512e8c 100644 --- a/main/manager-web/src/i18n/de.js +++ b/main/manager-web/src/i18n/de.js @@ -821,7 +821,7 @@ export default { 'modelConfig.rag': 'RAG', 'modelConfig.modelId': 'Modell-ID', 'modelConfig.modelName': 'Modellname', - 'modelConfig.provider': 'Anbieter', + 'modelConfig.provider': 'Schnittstellentyp', 'modelConfig.unknown': 'Unbekannt', 'modelConfig.isEnabled': 'Aktiviert', 'modelConfig.isDefault': 'Standard', diff --git a/main/manager-web/src/i18n/en.js b/main/manager-web/src/i18n/en.js index f57f8ab3..9bcc1f7d 100644 --- a/main/manager-web/src/i18n/en.js +++ b/main/manager-web/src/i18n/en.js @@ -821,7 +821,7 @@ export default { 'modelConfig.rag': 'RAG', 'modelConfig.modelId': 'Model ID', 'modelConfig.modelName': 'Model Name', - 'modelConfig.provider': 'Provider', + 'modelConfig.provider': 'Interface Type', 'modelConfig.unknown': 'Unknown', 'modelConfig.isEnabled': 'Enabled', 'modelConfig.isDefault': 'Default', diff --git a/main/manager-web/src/i18n/vi.js b/main/manager-web/src/i18n/vi.js index a96ccfaa..c9d9e1cf 100644 --- a/main/manager-web/src/i18n/vi.js +++ b/main/manager-web/src/i18n/vi.js @@ -821,7 +821,7 @@ export default { 'modelConfig.rag': 'RAG', 'modelConfig.modelId': 'ID mô hình', 'modelConfig.modelName': 'Tên mô hình', - 'modelConfig.provider': 'Nhà cung cấp', + 'modelConfig.provider': 'Loại giao diện', 'modelConfig.unknown': 'Không xác định', 'modelConfig.isEnabled': 'Đã bật', 'modelConfig.isDefault': 'Mặc định', diff --git a/main/manager-web/src/i18n/zh_CN.js b/main/manager-web/src/i18n/zh_CN.js index 6a3c6d80..44d8e400 100644 --- a/main/manager-web/src/i18n/zh_CN.js +++ b/main/manager-web/src/i18n/zh_CN.js @@ -821,7 +821,7 @@ export default { 'modelConfig.rag': '知识库', 'modelConfig.modelId': '模型ID', 'modelConfig.modelName': '模型名称', - 'modelConfig.provider': '提供商', + 'modelConfig.provider': '接口类型', 'modelConfig.unknown': '未知', 'modelConfig.isEnabled': '是否启用', 'modelConfig.isDefault': '是否默认', diff --git a/main/manager-web/src/i18n/zh_TW.js b/main/manager-web/src/i18n/zh_TW.js index ff5fdb47..ca5a5221 100644 --- a/main/manager-web/src/i18n/zh_TW.js +++ b/main/manager-web/src/i18n/zh_TW.js @@ -821,7 +821,7 @@ export default { 'modelConfig.rag': '知識庫', 'modelConfig.modelId': '模型ID', 'modelConfig.modelName': '模型名稱', - 'modelConfig.provider': '提供商', + 'modelConfig.provider': '接口類型', 'modelConfig.unknown': '未知', 'modelConfig.isEnabled': '是否啟用', 'modelConfig.isDefault': '是否默認', From 33a385cfa8b4f4bae0a7155326d1a2bee8b0a506 Mon Sep 17 00:00:00 2001 From: rui chen Date: Wed, 17 Dec 2025 16:26:35 +0800 Subject: [PATCH 28/39] add basic OTA support for single server deployment Committer: rxchen --- main/xiaozhi-server/core/api/ota_handler.py | 219 ++++++++++++++++++-- main/xiaozhi-server/core/http_server.py | 5 +- 2 files changed, 209 insertions(+), 15 deletions(-) diff --git a/main/xiaozhi-server/core/api/ota_handler.py b/main/xiaozhi-server/core/api/ota_handler.py index b6c88dff..a521332e 100644 --- a/main/xiaozhi-server/core/api/ota_handler.py +++ b/main/xiaozhi-server/core/api/ota_handler.py @@ -3,6 +3,10 @@ import time import base64 import hashlib import hmac +import os +import re +import glob +from typing import Dict, List, Tuple from aiohttp import web from core.auth import AuthManager @@ -12,6 +16,33 @@ from core.api.base_handler import BaseHandler TAG = __name__ +def _safe_basename(filename: str) -> str: + # Prevent directory traversal + return os.path.basename(filename) + + +def _parse_version(ver: str) -> Tuple[int, ...]: + # conservative parser: split by non-digit, keep numeric parts + parts = re.findall(r"\d+", ver) + return tuple(int(p) for p in parts) if parts else (0,) + + +def _is_higher_version(a: str, b: str) -> bool: + """Return True if version string a > b (semver-like numeric compare).""" + ta = _parse_version(a) + tb = _parse_version(b) + # compare tuple lexicographically, but allow different lengths + maxlen = max(len(ta), len(tb)) + for i in range(maxlen): + ai = ta[i] if i < len(ta) else 0 + bi = tb[i] if i < len(tb) else 0 + if ai > bi: + return True + if ai < bi: + return False + return False + + class OTAHandler(BaseHandler): def __init__(self, config: dict): super().__init__(config) @@ -23,6 +54,46 @@ class OTAHandler(BaseHandler): expire_seconds = auth_config.get("expire_seconds") self.auth = AuthManager(secret_key=secret_key, expire_seconds=expire_seconds) + # firmware storage + self.bin_dir = os.path.join(os.getcwd(), "data", "bin") + # cache structure: { 'updated_at': timestamp, 'ttl': seconds, 'files_by_model': { model: [(version, filename), ...] } } + self._bin_cache: Dict = {"updated_at": 0, "ttl": config.get("firmware_cache_ttl", 30), "files_by_model": {}} + + def _refresh_bin_cache_if_needed(self): + now = int(time.time()) + ttl = int(self._bin_cache.get("ttl", 30)) + if now - int(self._bin_cache.get("updated_at", 0)) < ttl and self._bin_cache.get("files_by_model"): + return + + files_by_model: Dict[str, List[Tuple[str, str]]] = {} + try: + if not os.path.isdir(self.bin_dir): + os.makedirs(self.bin_dir, exist_ok=True) + + # match files like model_1.2.3.bin (allow dots, dashes, underscores in model and version) + pattern = os.path.join(self.bin_dir, "*.bin") + for path in glob.glob(pattern): + fname = os.path.basename(path) + # filename format: {model}_{version}.bin + m = re.match(r"^(.+?)_([0-9][A-Za-z0-9\.\-_]*)\.bin$", fname) + if not m: + # skip files not conforming to naming rule + continue + model = m.group(1) + version = m.group(2) + files_by_model.setdefault(model, []).append((version, fname)) + + # sort versions for each model descending + for model, items in files_by_model.items(): + items.sort(key=lambda it: _parse_version(it[0]), reverse=True) + + self._bin_cache["files_by_model"] = files_by_model + self._bin_cache["updated_at"] = now + self.logger.bind(tag=TAG).info(f"Firmware cache refreshed: {len(files_by_model)} models") + except Exception as e: + self.logger.bind(tag=TAG).error(f"刷新固件缓存失败: {e}") + # keep previous cache if any + def generate_password_signature(self, content: str, secret_key: str) -> str: """生成MQTT密码签名 @@ -62,7 +133,14 @@ class OTAHandler(BaseHandler): return f"ws://{local_ip}:{port}/xiaozhi/v1/" async def handle_post(self, request): - """处理 OTA POST 请求""" + """处理 OTA POST 请求 + + This handler will: + - read device id/client id (as before) + - attempt to determine device model and current firmware version (prefer headers, fallback to body) + - check data/bin for newer firmware for that model + - if found a newer firmware, set firmware.url to the download endpoint + """ try: data = await request.text() self.logger.bind(tag=TAG).debug(f"OTA请求方法: {request.method}") @@ -81,11 +159,54 @@ class OTAHandler(BaseHandler): else: raise Exception("OTA请求ClientID为空") - data_json = json.loads(data) + data_json = {} + try: + data_json = json.loads(data) if data else {} + self.logger.bind(tag=TAG).info(f"data json:{data_json}") + except Exception: + data_json = {} server_config = self.config["server"] - port = int(server_config.get("port", 8000)) + # Distinguish ports: + # - websocket_port is used to construct websocket URL (server["port"]) + # - http_port is used to construct OTA download URLs (server["http_port"]) + websocket_port = int(server_config.get("port", 8000)) + http_port = int(server_config.get("http_port", 8003)) local_ip = get_local_ip() + ota_addr = server_config.get("ota_addr", "") + + # Determine device model (prefer headers) + device_model = "" + # header candidates + for h in ("device-model", "device_model", "model"): + if h in request.headers: + device_model = request.headers.get(h, "").strip() + break + # body fallback + if not device_model: + try: + if "board" in data_json and isinstance(data_json["board"], dict): + device_model = data_json["board"].get("type", "") + elif "model" in data_json: + device_model = data_json.get("model", "") + except Exception: + device_model = "" + if not device_model: + device_model = "default" + + # Determine device current version (prefer headers) + device_version = "" + for h in ("device-version", "device_version", "firmware-version", "app-version", "application-version"): + if h in request.headers: + device_version = request.headers.get(h, "").strip() + break + if not device_version: + try: + device_version = data_json.get("application", {}).get("version", "") + except Exception: + device_version = "" + if not device_version: + device_version = "0.0.0" return_json = { "server_time": { @@ -93,21 +214,17 @@ class OTAHandler(BaseHandler): "timezone_offset": server_config.get("timezone_offset", 8) * 60, }, "firmware": { - "version": data_json["application"].get("version", "1.0.0"), + "version": device_version, "url": "", }, } + # existing mqtt/websocket logic (unchanged) mqtt_gateway_endpoint = server_config.get("mqtt_gateway") if mqtt_gateway_endpoint: # 如果配置了非空字符串 - # 尝试从请求数据中获取设备型号 - device_model = "default" + # 尝试从请求数据中获取设备型号（已解析 above） try: - if "device" in data_json and isinstance(data_json["device"], dict): - device_model = data_json["device"].get("model", "default") - elif "model" in data_json: - device_model = data_json["model"] group_id = f"GID_{device_model}".replace(":", "_").replace(" ", "_") except Exception as e: self.logger.bind(tag=TAG).error(f"获取设备型号失败: {e}") @@ -159,20 +276,51 @@ class OTAHandler(BaseHandler): token = self.auth.generate_token(client_id, device_id) else: token = self.auth.generate_token(client_id, device_id) + # NOTE: use websocket_port here return_json["websocket"] = { - "url": self._get_websocket_url(local_ip, port), + "url": self._get_websocket_url(local_ip, websocket_port), "token": token, } self.logger.bind(tag=TAG).info( f"未配置MQTT网关，为设备 {device_id} 下发WebSocket配置" ) - self.logger.bind(tag=TAG).info(f"{return_json}") + + # Now check firmware files for updates + try: + self._refresh_bin_cache_if_needed() + files_by_model = self._bin_cache.get("files_by_model", {}) + candidates = files_by_model.get(device_model, []) + + self.logger.bind(tag=TAG).info(f"查找型号 {device_model} 的固件，找到 {len(candidates)} 个候选") + + chosen_url = "" + chosen_version = device_version + + # candidates are sorted descending by version + for ver, fname in candidates: + if _is_higher_version(ver, device_version): + # build download url (only allow download via our download endpoint) + chosen_version = ver + # use local_ip and http_port to construct url + chosen_url = f"http://{ota_addr}:{http_port}/xiaozhi/ota/download/{fname}" + break + + if chosen_url: + return_json["firmware"]["version"] = chosen_version + return_json["firmware"]["url"] = chosen_url + self.logger.bind(tag=TAG).info(f"为设备 {device_id} 下发固件 {chosen_version} -> {chosen_url}") + else: + self.logger.bind(tag=TAG).info(f"设备 {device_id} 固件已是最新: {device_version}") + + except Exception as e: + self.logger.bind(tag=TAG).error(f"检查固件版本时出错: {e}") response = web.Response( text=json.dumps(return_json, separators=(",", ":")), content_type="application/json", ) except Exception as e: + self.logger.bind(tag=TAG).error(f"OTA POST处理异常: {e}") return_json = {"success": False, "message": "request error."} response = web.Response( text=json.dumps(return_json, separators=(",", ":")), @@ -187,8 +335,9 @@ class OTAHandler(BaseHandler): try: server_config = self.config["server"] local_ip = get_local_ip() - port = int(server_config.get("port", 8000)) - websocket_url = self._get_websocket_url(local_ip, port) + # use websocket port for websocket URL + websocket_port = int(server_config.get("port", 8000)) + websocket_url = self._get_websocket_url(local_ip, websocket_port) message = f"OTA接口运行正常，向设备发送的websocket地址是：{websocket_url}" response = web.Response(text=message, content_type="text/plain") except Exception as e: @@ -197,3 +346,45 @@ class OTAHandler(BaseHandler): finally: self._add_cors_headers(response) return response + + async def handle_download(self, request): + """ + 下载固件接口 + URL: /xiaozhi/ota/download/{filename} + - 只允许下载 data/bin 目录下的 .bin 文件 + - filename 必须是 basename 且匹配安全的模式 + """ + try: + fname = request.match_info.get("filename", "") + if not fname: + raise web.HTTPBadRequest(text="filename required") + + # sanitize + fname = _safe_basename(fname) + # pattern: allow letters, numbers, dot, underscore, dash + if not re.match(r"^[A-Za-z0-9\.\-_]+\.bin$", fname): + raise web.HTTPBadRequest(text="invalid filename") + + file_path = os.path.join(self.bin_dir, fname) + # ensure realpath is under bin_dir + file_real = os.path.realpath(file_path) + bin_dir_real = os.path.realpath(self.bin_dir) + if not file_real.startswith(bin_dir_real + os.sep) and file_real != bin_dir_real: + raise web.HTTPForbidden(text="forbidden") + + if not os.path.isfile(file_real): + raise web.HTTPNotFound(text="file not found") + + # use FileResponse to stream file + resp = web.FileResponse(path=file_real) + except web.HTTPError as e: + resp = e + except Exception as e: + self.logger.bind(tag=TAG).error(f"固件下载异常: {e}") + resp = web.Response(text="download error", status=500) + finally: + try: + self._add_cors_headers(resp) + except Exception: + pass + return resp diff --git a/main/xiaozhi-server/core/http_server.py b/main/xiaozhi-server/core/http_server.py index edbdf1fe..ecc80efb 100644 --- a/main/xiaozhi-server/core/http_server.py +++ b/main/xiaozhi-server/core/http_server.py @@ -48,6 +48,9 @@ class SimpleHttpServer: web.get("/xiaozhi/ota/", self.ota_handler.handle_get), web.post("/xiaozhi/ota/", self.ota_handler.handle_post), web.options("/xiaozhi/ota/", self.ota_handler.handle_post), + # 下载接口，仅提供 data/bin/*.bin 下载 + web.get("/xiaozhi/ota/download/{filename}", self.ota_handler.handle_download), + web.options("/xiaozhi/ota/download/{filename}", self.ota_handler.handle_download), ] ) # 添加路由 @@ -67,4 +70,4 @@ class SimpleHttpServer: # 保持服务运行 while True: - await asyncio.sleep(3600) # 每隔 1 小时检查一次 + await asyncio.sleep(3600) # 每隔 1 小时检查一次 \ No newline at end of file From d5f804bbb36c736edd5b8e1e7c5d6b13793acb9f Mon Sep 17 00:00:00 2001 From: rui chen Date: Wed, 17 Dec 2025 16:44:54 +0800 Subject: [PATCH 29/39] add basic OTA support for single server deployment, remove debug --- main/xiaozhi-server/core/api/ota_handler.py | 1 - 1 file changed, 1 deletion(-) diff --git a/main/xiaozhi-server/core/api/ota_handler.py b/main/xiaozhi-server/core/api/ota_handler.py index a521332e..b20ba60b 100644 --- a/main/xiaozhi-server/core/api/ota_handler.py +++ b/main/xiaozhi-server/core/api/ota_handler.py @@ -162,7 +162,6 @@ class OTAHandler(BaseHandler): data_json = {} try: data_json = json.loads(data) if data else {} - self.logger.bind(tag=TAG).info(f"data json:{data_json}") except Exception: data_json = {} From 7d9895cf5b3798868cf53e510a4276500e799f99 Mon Sep 17 00:00:00 2001 From: FAN-yeB <1442100690@qq.com> Date: Thu, 18 Dec 2025 10:11:13 +0800 Subject: [PATCH 30/39] =?UTF-8?q?=E4=BF=AE=E5=A4=8D=E5=94=A4=E9=86=92?= =?UTF-8?q?=E7=8A=B6=E6=80=81?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../core/handle/textHandler/listenMessageHandler.py | 1 + 1 file changed, 1 insertion(+) diff --git a/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py b/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py index a2c96836..c71649ed 100644 --- a/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py +++ b/main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py @@ -69,6 +69,7 @@ class ListenTextMessageHandler(TextMessageHandler): enqueue_asr_report(conn, "嘿，你好呀", []) await startToChat(conn, "嘿，你好呀") else: + 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, original_text, []) # 否则需要LLM对文字内容进行答复 From 19736e66ad46b0542450ebc779596009e2a149d9 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Thu, 18 Dec 2025 11:18:49 +0800 Subject: [PATCH 31/39] =?UTF-8?q?fix=EF=BC=9A=E6=97=A0=E6=84=8F=E5=9B=BE?= =?UTF-8?q?=E8=AF=86=E5=88=AB=E6=97=B6=EF=BC=8C=E6=97=A0"plugins"=E9=85=8D?= =?UTF-8?q?=E7=BD=AE=E6=8A=A5=E9=94=99=E7=9A=84bug?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../functions/get_news_from_chinanews.py | 2 +- .../functions/get_news_from_newsnow.py | 8 ++++---- .../plugins_func/functions/get_weather.py | 11 ++++------- .../plugins_func/functions/hass_init.py | 16 +++++++++------- .../plugins_func/functions/play_music.py | 5 +++-- .../functions/search_from_ragflow.py | 7 ++++--- 6 files changed, 25 insertions(+), 24 deletions(-) diff --git a/main/xiaozhi-server/plugins_func/functions/get_news_from_chinanews.py b/main/xiaozhi-server/plugins_func/functions/get_news_from_chinanews.py index e5ca0d1f..2267c83c 100644 --- a/main/xiaozhi-server/plugins_func/functions/get_news_from_chinanews.py +++ b/main/xiaozhi-server/plugins_func/functions/get_news_from_chinanews.py @@ -195,7 +195,7 @@ def get_news_from_chinanews( # 否则，获取新闻列表并随机选择一条 # 从配置中获取RSS URL - rss_config = conn.config["plugins"]["get_news_from_chinanews"] + rss_config = conn.config.get("plugins", {}).get("get_news_from_chinanews", {}) default_rss_url = rss_config.get( "default_rss_url", "https://www.chinanews.com.cn/rss/society.xml" ) diff --git a/main/xiaozhi-server/plugins_func/functions/get_news_from_newsnow.py b/main/xiaozhi-server/plugins_func/functions/get_news_from_newsnow.py index 1d60aefd..2bcd9193 100644 --- a/main/xiaozhi-server/plugins_func/functions/get_news_from_newsnow.py +++ b/main/xiaozhi-server/plugins_func/functions/get_news_from_newsnow.py @@ -120,10 +120,10 @@ def fetch_news_from_api(conn, source="thepaper"): """从API获取新闻列表""" try: api_url = f"https://newsnow.busiyi.world/api/s?id={source}" - if conn.config["plugins"].get("get_news_from_newsnow") and conn.config[ - "plugins" - ]["get_news_from_newsnow"].get("url"): - api_url = conn.config["plugins"]["get_news_from_newsnow"]["url"] + source + + news_config = conn.config.get("plugins", {}).get("get_news_from_newsnow", {}) + if news_config.get("url"): + api_url = news_config["url"] + source headers = {"User-Agent": "Mozilla/5.0"} response = requests.get(api_url, headers=headers, timeout=10) diff --git a/main/xiaozhi-server/plugins_func/functions/get_weather.py b/main/xiaozhi-server/plugins_func/functions/get_weather.py index 38770a3f..e95a40d8 100644 --- a/main/xiaozhi-server/plugins_func/functions/get_weather.py +++ b/main/xiaozhi-server/plugins_func/functions/get_weather.py @@ -158,13 +158,10 @@ def parse_weather_info(soup): def get_weather(conn, location: str = None, lang: str = "zh_CN"): from core.utils.cache.manager import cache_manager, CacheType - api_host = conn.config["plugins"]["get_weather"].get( - "api_host", "mj7p3y7naa.re.qweatherapi.com" - ) - api_key = conn.config["plugins"]["get_weather"].get( - "api_key", "a861d0d5e7bf4ee1a83d9a9e4f96d4da" - ) - default_location = conn.config["plugins"]["get_weather"]["default_location"] + weather_config = conn.config.get("plugins", {}).get("get_weather", {}) + api_host = weather_config.get("api_host", "mj7p3y7naa.re.qweatherapi.com") + api_key = weather_config.get("api_key", "a861d0d5e7bf4ee1a83d9a9e4f96d4da") + default_location = weather_config.get("default_location", "广州") client_ip = conn.client_ip # 优先使用用户提供的location参数 diff --git a/main/xiaozhi-server/plugins_func/functions/hass_init.py b/main/xiaozhi-server/plugins_func/functions/hass_init.py index 11cbb7a0..dadb190b 100644 --- a/main/xiaozhi-server/plugins_func/functions/hass_init.py +++ b/main/xiaozhi-server/plugins_func/functions/hass_init.py @@ -11,15 +11,17 @@ def append_devices_to_prompt(conn): "functions", [] ) + # 安全地获取插件配置 + plugins_config = conn.config.get("plugins", {}) config_source = ( "home_assistant" - if conn.config["plugins"].get("home_assistant") + if plugins_config.get("home_assistant") else "hass_get_state" ) if "hass_get_state" in funcs or "hass_set_state" in funcs: prompt = "\n下面是我家智能设备列表（位置，设备名，entity_id），可以通过homeassistant控制\n" - deviceStr = conn.config["plugins"].get(config_source, {}).get("devices", "") + deviceStr = plugins_config.get(config_source, {}).get("devices", "") conn.prompt += prompt + deviceStr + "\n" # 更新提示词 conn.dialogue.update_system_message(conn.prompt) @@ -30,17 +32,17 @@ def initialize_hass_handler(conn): if not conn.load_function_plugin: return ha_config + # 安全地获取插件配置 + plugins_config = conn.config.get("plugins", {}) # 确定配置来源 config_source = ( - "home_assistant" - if conn.config["plugins"].get("home_assistant") - else "hass_get_state" + "home_assistant" if plugins_config.get("home_assistant") else "hass_get_state" ) - if not conn.config["plugins"].get(config_source): + if not plugins_config.get(config_source): return ha_config # 统一获取配置 - plugin_config = conn.config["plugins"][config_source] + plugin_config = plugins_config[config_source] ha_config["base_url"] = plugin_config.get("base_url") ha_config["api_key"] = plugin_config.get("api_key") diff --git a/main/xiaozhi-server/plugins_func/functions/play_music.py b/main/xiaozhi-server/plugins_func/functions/play_music.py index 2cbc4018..be4cf618 100644 --- a/main/xiaozhi-server/plugins_func/functions/play_music.py +++ b/main/xiaozhi-server/plugins_func/functions/play_music.py @@ -118,8 +118,9 @@ def get_music_files(music_dir, music_ext): def initialize_music_handler(conn): global MUSIC_CACHE if MUSIC_CACHE == {}: - if "play_music" in conn.config["plugins"]: - MUSIC_CACHE["music_config"] = conn.config["plugins"]["play_music"] + plugins_config = conn.config.get("plugins", {}) + if "play_music" in plugins_config: + MUSIC_CACHE["music_config"] = plugins_config["play_music"] MUSIC_CACHE["music_dir"] = os.path.abspath( MUSIC_CACHE["music_config"].get("music_dir", "./music") # 默认路径修改 ) diff --git a/main/xiaozhi-server/plugins_func/functions/search_from_ragflow.py b/main/xiaozhi-server/plugins_func/functions/search_from_ragflow.py index d585a762..ec6ac426 100644 --- a/main/xiaozhi-server/plugins_func/functions/search_from_ragflow.py +++ b/main/xiaozhi-server/plugins_func/functions/search_from_ragflow.py @@ -32,9 +32,10 @@ def search_from_ragflow(conn, question=None): else: question = str(question) if question is not None else "" - base_url = conn.config["plugins"]["search_from_ragflow"].get("base_url", "") - api_key = conn.config["plugins"]["search_from_ragflow"].get("api_key", "") - dataset_ids = conn.config["plugins"]["search_from_ragflow"].get("dataset_ids", []) + ragflow_config = conn.config.get("plugins", {}).get("search_from_ragflow", {}) + base_url = ragflow_config.get("base_url", "") + api_key = ragflow_config.get("api_key", "") + dataset_ids = ragflow_config.get("dataset_ids", []) url = base_url + "/api/v1/retrieval" headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"} From 33d70ccc96c54ac2a6ef044bfc7d3b43be77a427 Mon Sep 17 00:00:00 2001 From: rui chen Date: Thu, 18 Dec 2025 15:48:25 +0800 Subject: [PATCH 32/39] get OTA address from websocket address config, if failed find ota_addr, if failed again, use local address. --- main/xiaozhi-server/core/api/ota_handler.py | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/main/xiaozhi-server/core/api/ota_handler.py b/main/xiaozhi-server/core/api/ota_handler.py index b20ba60b..1fe339c2 100644 --- a/main/xiaozhi-server/core/api/ota_handler.py +++ b/main/xiaozhi-server/core/api/ota_handler.py @@ -9,6 +9,8 @@ import glob from typing import Dict, List, Tuple from aiohttp import web +from urllib.parse import urlparse + from core.auth import AuthManager from core.utils.util import get_local_ip from core.api.base_handler import BaseHandler @@ -172,7 +174,18 @@ class OTAHandler(BaseHandler): websocket_port = int(server_config.get("port", 8000)) http_port = int(server_config.get("http_port", 8003)) local_ip = get_local_ip() - ota_addr = server_config.get("ota_addr", "") + + ota_addr = "" + websocket_addr = self._get_websocket_url(local_ip, websocket_port) + parsedurl = urlparse(websocket_addr) + netloc = parsedurl.netloc + if netloc: + host_part = netloc.split(":")[0] + ota_addr = host_part if host_part else "" + if ota_addr == "": + ota_addr = server_config.get("ota_addr", "") + if ota_addr == "": + ota_addr = local_ip # Determine device model (prefer headers) device_model = "" From e8d0bb0c5485f63d0d30604c0c028d3956d23d3b Mon Sep 17 00:00:00 2001 From: 3030332422 <3030332422@qq.com> Date: Thu, 18 Dec 2025 16:34:37 +0800 Subject: [PATCH 33/39] =?UTF-8?q?update=EF=BC=9A=E6=8F=90=E7=A4=BA?= =?UTF-8?q?=E8=AF=8D=E4=B8=8A=E4=B8=8B=E6=96=87=E6=8C=89=E6=A8=A1=E6=9D=BF?= =?UTF-8?q?=E6=8C=89=E9=9C=80=E8=8E=B7=E5=8F=96=EF=BC=88=E4=BD=8D=E7=BD=AE?= =?UTF-8?q?/=E5=A4=A9=E6=B0=94/=E5=8A=A8=E6=80=81=E4=B8=8A=E4=B8=8B?= =?UTF-8?q?=E6=96=87=EF=BC=89?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../core/utils/prompt_manager.py | 23 +++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/main/xiaozhi-server/core/utils/prompt_manager.py b/main/xiaozhi-server/core/utils/prompt_manager.py index 78c63483..70f14d92 100644 --- a/main/xiaozhi-server/core/utils/prompt_manager.py +++ b/main/xiaozhi-server/core/utils/prompt_manager.py @@ -184,10 +184,25 @@ class PromptManager: def update_context_info(self, conn, client_ip: str): """同步更新上下文信息""" try: - # 获取位置信息（使用全局缓存） - local_address = self._get_location_info(client_ip) - # 获取天气信息（使用全局缓存） - self._get_weather_info(conn, local_address) + local_address = "" + if ( + client_ip + and self.base_prompt_template + and ( + "local_address" in self.base_prompt_template + or "weather_info" in self.base_prompt_template + ) + ): + # 获取位置信息（使用全局缓存） + local_address = self._get_location_info(client_ip) + + if ( + self.base_prompt_template + and "weather_info" in self.base_prompt_template + and local_address + ): + # 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: From 6e7c86e159ffa8e51fdba92d47f47a036e4f346a Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Thu, 18 Dec 2025 17:37:20 +0800 Subject: [PATCH 34/39] =?UTF-8?q?update:=E4=BB=8Evision=5Furl=E9=85=8D?= =?UTF-8?q?=E7=BD=AE=E9=87=8C=E8=AF=BB=E5=8F=96=E5=9F=9F=E5=90=8D=E5=92=8C?= =?UTF-8?q?=E7=AB=AF=E5=8F=A3=E5=8F=B7?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/core/api/base_handler.py | 10 ++- main/xiaozhi-server/core/api/ota_handler.py | 63 +++++++++------ .../xiaozhi-server/core/api/vision_handler.py | 14 +--- main/xiaozhi-server/core/http_server.py | 79 ++++++++++++------- 4 files changed, 99 insertions(+), 67 deletions(-) diff --git a/main/xiaozhi-server/core/api/base_handler.py b/main/xiaozhi-server/core/api/base_handler.py index 7330185e..db277543 100644 --- a/main/xiaozhi-server/core/api/base_handler.py +++ b/main/xiaozhi-server/core/api/base_handler.py @@ -10,7 +10,15 @@ class BaseHandler: def _add_cors_headers(self, response): """添加CORS头信息""" response.headers["Access-Control-Allow-Headers"] = ( - "client-id, content-type, device-id" + "client-id, content-type, device-id, authorization" ) response.headers["Access-Control-Allow-Credentials"] = "true" response.headers["Access-Control-Allow-Origin"] = "*" + + async def handle_options(self, request): + """处理OPTIONS请求，添加CORS头信息""" + response = web.Response(body=b"", content_type="text/plain") + self._add_cors_headers(response) + # 添加允许的方法 + response.headers["Access-Control-Allow-Methods"] = "GET, POST, OPTIONS" + return response diff --git a/main/xiaozhi-server/core/api/ota_handler.py b/main/xiaozhi-server/core/api/ota_handler.py index 1fe339c2..1e3b3bd0 100644 --- a/main/xiaozhi-server/core/api/ota_handler.py +++ b/main/xiaozhi-server/core/api/ota_handler.py @@ -9,10 +9,8 @@ import glob from typing import Dict, List, Tuple from aiohttp import web -from urllib.parse import urlparse - from core.auth import AuthManager -from core.utils.util import get_local_ip +from core.utils.util import get_local_ip, get_vision_url from core.api.base_handler import BaseHandler TAG = __name__ @@ -59,12 +57,18 @@ class OTAHandler(BaseHandler): # firmware storage self.bin_dir = os.path.join(os.getcwd(), "data", "bin") # cache structure: { 'updated_at': timestamp, 'ttl': seconds, 'files_by_model': { model: [(version, filename), ...] } } - self._bin_cache: Dict = {"updated_at": 0, "ttl": config.get("firmware_cache_ttl", 30), "files_by_model": {}} + self._bin_cache: Dict = { + "updated_at": 0, + "ttl": config.get("firmware_cache_ttl", 30), + "files_by_model": {}, + } def _refresh_bin_cache_if_needed(self): now = int(time.time()) ttl = int(self._bin_cache.get("ttl", 30)) - if now - int(self._bin_cache.get("updated_at", 0)) < ttl and self._bin_cache.get("files_by_model"): + if now - int( + self._bin_cache.get("updated_at", 0) + ) < ttl and self._bin_cache.get("files_by_model"): return files_by_model: Dict[str, List[Tuple[str, str]]] = {} @@ -91,7 +95,9 @@ class OTAHandler(BaseHandler): self._bin_cache["files_by_model"] = files_by_model self._bin_cache["updated_at"] = now - self.logger.bind(tag=TAG).info(f"Firmware cache refreshed: {len(files_by_model)} models") + self.logger.bind(tag=TAG).info( + f"Firmware cache refreshed: {len(files_by_model)} models" + ) except Exception as e: self.logger.bind(tag=TAG).error(f"刷新固件缓存失败: {e}") # keep previous cache if any @@ -175,18 +181,6 @@ class OTAHandler(BaseHandler): http_port = int(server_config.get("http_port", 8003)) local_ip = get_local_ip() - ota_addr = "" - websocket_addr = self._get_websocket_url(local_ip, websocket_port) - parsedurl = urlparse(websocket_addr) - netloc = parsedurl.netloc - if netloc: - host_part = netloc.split(":")[0] - ota_addr = host_part if host_part else "" - if ota_addr == "": - ota_addr = server_config.get("ota_addr", "") - if ota_addr == "": - ota_addr = local_ip - # Determine device model (prefer headers) device_model = "" # header candidates @@ -208,7 +202,13 @@ class OTAHandler(BaseHandler): # Determine device current version (prefer headers) device_version = "" - for h in ("device-version", "device_version", "firmware-version", "app-version", "application-version"): + for h in ( + "device-version", + "device_version", + "firmware-version", + "app-version", + "application-version", + ): if h in request.headers: device_version = request.headers.get(h, "").strip() break @@ -303,7 +303,9 @@ class OTAHandler(BaseHandler): files_by_model = self._bin_cache.get("files_by_model", {}) candidates = files_by_model.get(device_model, []) - self.logger.bind(tag=TAG).info(f"查找型号 {device_model} 的固件，找到 {len(candidates)} 个候选") + self.logger.bind(tag=TAG).info( + f"查找型号 {device_model} 的固件，找到 {len(candidates)} 个候选" + ) chosen_url = "" chosen_version = device_version @@ -313,16 +315,24 @@ class OTAHandler(BaseHandler): if _is_higher_version(ver, device_version): # build download url (only allow download via our download endpoint) chosen_version = ver - # use local_ip and http_port to construct url - chosen_url = f"http://{ota_addr}:{http_port}/xiaozhi/ota/download/{fname}" + # Use get_vision_url to get the base URL and replace the path + vision_url = get_vision_url(self.config) + # Replace the path from "/mcp/vision/explain" to "/xiaozhi/ota/download/{fname}" + chosen_url = vision_url.replace( + "/mcp/vision/explain", f"/xiaozhi/ota/download/{fname}" + ) break if chosen_url: return_json["firmware"]["version"] = chosen_version return_json["firmware"]["url"] = chosen_url - self.logger.bind(tag=TAG).info(f"为设备 {device_id} 下发固件 {chosen_version} -> {chosen_url}") + self.logger.bind(tag=TAG).info( + f"为设备 {device_id} 下发固件 {chosen_version} [如果地址前缀有误，请检查配置文件中的server.vision_explain]-> {chosen_url} " + ) else: - self.logger.bind(tag=TAG).info(f"设备 {device_id} 固件已是最新: {device_version}") + self.logger.bind(tag=TAG).info( + f"设备 {device_id} 固件已是最新: {device_version}" + ) except Exception as e: self.logger.bind(tag=TAG).error(f"检查固件版本时出错: {e}") @@ -381,7 +391,10 @@ class OTAHandler(BaseHandler): # ensure realpath is under bin_dir file_real = os.path.realpath(file_path) bin_dir_real = os.path.realpath(self.bin_dir) - if not file_real.startswith(bin_dir_real + os.sep) and file_real != bin_dir_real: + if ( + not file_real.startswith(bin_dir_real + os.sep) + and file_real != bin_dir_real + ): raise web.HTTPForbidden(text="forbidden") if not os.path.isfile(file_real): diff --git a/main/xiaozhi-server/core/api/vision_handler.py b/main/xiaozhi-server/core/api/vision_handler.py index a4817a84..28f48753 100644 --- a/main/xiaozhi-server/core/api/vision_handler.py +++ b/main/xiaozhi-server/core/api/vision_handler.py @@ -2,6 +2,7 @@ import json import copy from aiohttp import web from config.logger import setup_logging +from core.api.base_handler import BaseHandler from core.utils.util import get_vision_url, is_valid_image_file from core.utils.vllm import create_instance from config.config_loader import get_private_config_from_api @@ -16,10 +17,9 @@ TAG = __name__ MAX_FILE_SIZE = 5 * 1024 * 1024 -class VisionHandler: +class VisionHandler(BaseHandler): def __init__(self, config: dict): - self.config = config - self.logger = setup_logging() + super().__init__(config) # 初始化认证工具 self.auth = AuthToken(config["server"]["auth_key"]) @@ -172,11 +172,3 @@ class VisionHandler: finally: self._add_cors_headers(response) return response - - def _add_cors_headers(self, response): - """添加CORS头信息""" - response.headers["Access-Control-Allow-Headers"] = ( - "client-id, content-type, device-id" - ) - response.headers["Access-Control-Allow-Credentials"] = "true" - response.headers["Access-Control-Allow-Origin"] = "*" diff --git a/main/xiaozhi-server/core/http_server.py b/main/xiaozhi-server/core/http_server.py index ecc80efb..feb96f3b 100644 --- a/main/xiaozhi-server/core/http_server.py +++ b/main/xiaozhi-server/core/http_server.py @@ -33,41 +33,60 @@ class SimpleHttpServer: return f"ws://{local_ip}:{port}/xiaozhi/v1/" async def start(self): - server_config = self.config["server"] - read_config_from_api = self.config.get("read_config_from_api", False) - host = server_config.get("ip", "0.0.0.0") - port = int(server_config.get("http_port", 8003)) + try: + server_config = self.config["server"] + read_config_from_api = self.config.get("read_config_from_api", False) + host = server_config.get("ip", "0.0.0.0") + port = int(server_config.get("http_port", 8003)) - if port: - app = web.Application() + if port: + app = web.Application() - if not read_config_from_api: - # 如果没有开启智控台，只是单模块运行，就需要再添加简单OTA接口，用于下发websocket接口 + if not read_config_from_api: + # 如果没有开启智控台，只是单模块运行，就需要再添加简单OTA接口，用于下发websocket接口 + app.add_routes( + [ + web.get("/xiaozhi/ota/", self.ota_handler.handle_get), + web.post("/xiaozhi/ota/", self.ota_handler.handle_post), + web.options( + "/xiaozhi/ota/", self.ota_handler.handle_options + ), + # 下载接口，仅提供 data/bin/*.bin 下载 + web.get( + "/xiaozhi/ota/download/{filename}", + self.ota_handler.handle_download, + ), + web.options( + "/xiaozhi/ota/download/{filename}", + self.ota_handler.handle_options, + ), + ] + ) + # 添加路由 app.add_routes( [ - web.get("/xiaozhi/ota/", self.ota_handler.handle_get), - web.post("/xiaozhi/ota/", self.ota_handler.handle_post), - web.options("/xiaozhi/ota/", self.ota_handler.handle_post), - # 下载接口，仅提供 data/bin/*.bin 下载 - web.get("/xiaozhi/ota/download/{filename}", self.ota_handler.handle_download), - web.options("/xiaozhi/ota/download/{filename}", self.ota_handler.handle_download), + web.get("/mcp/vision/explain", self.vision_handler.handle_get), + web.post( + "/mcp/vision/explain", self.vision_handler.handle_post + ), + web.options( + "/mcp/vision/explain", self.vision_handler.handle_options + ), ] ) - # 添加路由 - app.add_routes( - [ - web.get("/mcp/vision/explain", self.vision_handler.handle_get), - web.post("/mcp/vision/explain", self.vision_handler.handle_post), - web.options("/mcp/vision/explain", self.vision_handler.handle_post), - ] - ) - # 运行服务 - runner = web.AppRunner(app) - await runner.setup() - site = web.TCPSite(runner, host, port) - await site.start() + # 运行服务 + runner = web.AppRunner(app) + await runner.setup() + site = web.TCPSite(runner, host, port) + await site.start() - # 保持服务运行 - while True: - await asyncio.sleep(3600) # 每隔 1 小时检查一次 \ No newline at end of file + # 保持服务运行 + while True: + await asyncio.sleep(3600) # 每隔 1 小时检查一次 + except Exception as e: + self.logger.bind(tag=TAG).error(f"HTTP服务器启动失败: {e}") + import traceback + + self.logger.bind(tag=TAG).error(f"错误堆栈: {traceback.format_exc()}") + raise From f3f0d62f1269102c4af5a7bfcf4ffa85355ad0ee Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Thu, 18 Dec 2025 17:38:58 +0800 Subject: [PATCH 35/39] =?UTF-8?q?add:=E6=B7=BB=E5=8A=A0=E5=8D=95=E6=A8=A1?= =?UTF-8?q?=E5=9D=97=E9=83=A8=E7=BD=B2=E6=97=B6=EF=BC=8C=E4=BD=BF=E7=94=A8?= =?UTF-8?q?ota=E6=8E=A5=E5=8F=A3=E8=87=AA=E5=8A=A8=E5=8D=87=E7=BA=A7?= =?UTF-8?q?=E5=9B=BA=E4=BB=B6=E7=9A=84=E6=95=99=E7=A8=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- docs/FAQ.md | 1 + docs/ota-upgrade-guide.md | 264 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 265 insertions(+) create mode 100644 docs/ota-upgrade-guide.md diff --git a/docs/FAQ.md b/docs/FAQ.md index f1e12d84..69494c3d 100644 --- a/docs/FAQ.md +++ b/docs/FAQ.md @@ -69,6 +69,7 @@ VAD: ### 9、编译固件相关教程 1、[如何自己编译小智固件](./firmware-build.md)
2、[如何基于虾哥编译好的固件修改OTA地址](./firmware-setting.md)
+3、[单模块部署如何配置固件OTA自动升级](./ota-upgrade-guide.md)
### 10、拓展相关教程 1、[如何开启手机号码注册智控台](./ali-sms-integration.md)
diff --git a/docs/ota-upgrade-guide.md b/docs/ota-upgrade-guide.md new file mode 100644 index 00000000..157a80ba --- /dev/null +++ b/docs/ota-upgrade-guide.md @@ -0,0 +1,264 @@ +# 单模块部署固件OTA自动升级配置指南 + +本教程将指导你如何在**单模块部署**场景下配置固件OTA自动升级功能，实现设备固件的自动更新。 + +## 功能介绍 + +在单模块部署中，xiaozhi-server内置了OTA固件管理功能，可以自动检测设备版本并下发升级固件。系统会根据设备型号和当前版本，自动匹配并推送最新的固件版本。 + +## 前提条件 + +- 你已经成功进行**单模块部署**并运行xiaozhi-server +- 设备能够正常连接到服务器 + +## 第一步 准备固件文件 + +### 1. 创建固件存放目录 + +固件文件需要放在`data/bin/`目录下。如果该目录不存在，请手动创建： + +```bash +mkdir -p data/bin +``` + +### 2. 固件文件命名规则 + +固件文件必须遵循以下命名格式： + +``` +{设备型号}_{版本号}.bin +``` + +**命名规则说明：** +- `设备型号`：设备的型号名称，例如 `lichuang-dev`、`bread-compact-wifi` 等 +- `版本号`：固件版本号，必须以数字开头，支持数字、字母、点号、下划线和短横线，例如 `1.6.6`、`2.0.0` 等 +- 文件扩展名必须是 `.bin` + +**命名示例：** +``` +bread-compact-wifi_1.6.6.bin +lichuang-dev_2.0.0.bin +``` + +### 3. 放置固件文件 + +将准备好的固件文件（.bin文件）复制到`data/bin/`目录下： + +```bash +cp your_firmware.bin data/bin/设备型号_版本号.bin +``` + +例如： +```bash +cp xiaozhi_firmware.bin data/bin/esp32s3_1.6.6.bin +``` + +## 第二步 配置公网访问地址（仅公网部署需要） + +**注意：此步骤仅适用于单模块公网部署的场景。** + +如果你的xiaozhi-server是公网部署（使用公网IP或域名），**必须**配置`server.vision_explain`参数，因为OTA固件下载地址会使用该配置的域名和端口。 + +如果你是局域网部署，可以跳过此步骤。 + +### 为什么要配置这个参数？ + +在单模块部署中，系统生成固件下载地址时，会使用`vision_explain`配置的域名和端口作为基础地址。如果不配置或配置错误，设备将无法访问固件下载地址。 + +### 配置方法 + +打开`data/.config.yaml`文件，找到`server`配置段，设置`vision_explain`参数： + +```yaml +server: + vision_explain: http://你的域名或IP:端口号/mcp/vision/explain +``` + +**配置示例：** + +局域网部署（默认）： +```yaml +server: + vision_explain: http://192.168.1.100:8003/mcp/vision/explain +``` + +公网域名部署： +```yaml +server: + vision_explain: http://yourdomain.com:8003/mcp/vision/explain +``` + +公网IP部署： +```yaml +server: + vision_explain: http://111.111.111.111:8003/mcp/vision/explain +``` + +使用HTTPS（推荐公网部署使用）： +```yaml +server: + vision_explain: https://yourdomain.com:8003/mcp/vision/explain +``` + +### 注意事项 + +- 域名或IP必须是设备能够访问的地址 +- 如果使用Docker部署，不能使用Docker内部地址（如127.0.0.1或localhost） +- 端口号默认是8003，如果你修改了`server.http_port`配置，需要同步修改这里的端口号 + +## 第三步 启动或重启服务 + +### 源码运行 + +```bash +python app.py +``` + +### Docker运行 + +```bash +docker restart xiaozhi-esp32-server +``` + +### 验证服务启动 + +启动后，查看日志输出，应该能看到类似以下内容： + +``` +2025-12-18 **** - OTA接口是 http://192.168.1.100:8003/xiaozhi/ota/ +2025-12-18 **** - 视觉分析接口是 http://192.168.1.100:8003/mcp/vision/explain +``` + +使用浏览器访问OTA接口地址，如果显示以下内容说明服务正常： + +``` +OTA接口运行正常，向设备发送的websocket地址是：ws://xxx.xxx.xxx.xxx:8000/xiaozhi/v1/ +``` + +## 第四步 设备自动检测升级 + +### 升级原理 + +当设备连接到服务器时（每次开机或定时检查），会自动发送OTA请求。服务器会： + +1. 读取设备的型号和当前固件版本 +2. 扫描`data/bin/`目录，查找匹配该型号的所有固件文件 +3. 比较版本号，如果有更高版本，则返回固件下载地址 +4. 设备收到下载地址后，会自动下载并安装新固件 + +### 版本比较规则 + +系统使用语义化版本比较方式，按数字段从左到右依次比较： + +- `1.6.6` < `1.6.7` +- `1.6.9` < `1.7.0` +- `2.0.0` > `1.9.9` + +### 查看升级日志 + +在xiaozhi-server的日志中，你可以看到OTA相关的日志输出： + +``` +[ota_handler] - OTA请求设备ID: AA:BB:CC:DD:EE:FF +[ota_handler] - 查找型号 esp32s3 的固件，找到 3 个候选 +[ota_handler] - 为设备 AA:BB:CC:DD:EE:FF 下发固件 1.6.6 [如果地址前缀有误，请检查配置文件中的server.vision_explain]-> http://yourdomain.com:8003/xiaozhi/ota/download/esp32s3_1.6.6.bin +``` + +或者如果设备已是最新版本： + +``` +[ota_handler] - 设备 AA:BB:CC:DD:EE:FF 固件已是最新: 1.6.6 +``` + +## 高级配置 + +### 固件缓存时间（可选） + +系统会缓存`data/bin/`目录的扫描结果以提高性能。默认缓存时间为30秒。你可以在配置文件中调整： + +```yaml +firmware_cache_ttl: 60 # 单位：秒，设置为60秒缓存时间 +``` + +### 多版本固件管理 + +你可以同时放置多个版本的固件，系统会自动选择最新版本： + +``` +data/bin/ + ├── esp32s3_1.6.5.bin + ├── esp32s3_1.6.6.bin + ├── esp32s3_1.7.0-beta.bin + └── xiaozhi-v2_2.0.0.bin +``` + +系统会为`esp32s3`型号的设备推送`1.7.0-beta`版本（最高版本）。 + +### 多型号固件管理 + +不同型号的设备会自动匹配对应型号的固件： + +``` +data/bin/ + ├── esp32s3_1.6.6.bin # 仅供 esp32s3 型号设备使用 + ├── xiaozhi-v2_2.0.0.bin # 仅供 xiaozhi-v2 型号设备使用 + └── default_1.0.0.bin # 供未识别型号的设备使用 +``` + +## 常见问题 + +### 1. 设备收不到固件更新 + +**可能原因和解决方法：** + +- 检查固件文件命名是否符合规则：`{型号}_{版本号}.bin` +- 检查固件文件是否正确放置在`data/bin/`目录 +- 检查设备型号是否与固件文件名中的型号匹配 +- 检查固件版本号是否高于设备当前版本 +- 查看服务器日志，确认OTA请求是否正常处理 + +### 2. 设备报告下载地址无法访问 + +**可能原因和解决方法：** + +- 检查`server.vision_explain`配置的域名或IP是否正确 +- 确认端口号配置正确（默认8003） +- 如果是公网部署，确保设备能够访问该公网地址 +- 如果是Docker部署，确保不是使用了内部地址（127.0.0.1） +- 检查防火墙是否开放了对应端口 + +### 3. 如何确认设备当前版本 + +查看OTA请求日志，日志中会显示设备上报的版本号： + +``` +[ota_handler] - 设备 AA:BB:CC:DD:EE:FF 固件已是最新: 1.6.6 +``` + +### 4. 固件文件放置后没有生效 + +系统有30秒的缓存时间（默认），可以： +- 等待30秒后再让设备发起OTA请求 +- 重启xiaozhi-server服务 +- 调整`firmware_cache_ttl`配置为更短的时间 + +### 5. 如何回滚到旧版本 + +系统只会推送更高版本的固件。如果需要回滚： +1. 删除或重命名`data/bin/`目录中高于目标版本的固件文件 +2. 等待缓存过期或重启服务 +3. 设备下次检查时会收到目标版本 + +## 安全说明 + +- 系统会验证固件文件路径，防止目录穿越攻击 +- 固件下载接口只允许访问`data/bin/`目录下的`.bin`文件 +- 建议在生产环境使用HTTPS协议传输固件 + +## 相关教程 + +如需了解更多，请参考以下教程： + +1. [如何自己编译小智固件](./firmware-build.md) +2. [如何基于虾哥编译好的固件修改OTA地址](./firmware-setting.md) +3. [如何进行全模块部署](./Deployment_all.md) From 7222f68d4d994c06acdb9443ba1fb7ee4c82f7b9 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Thu, 18 Dec 2025 17:57:05 +0800 Subject: [PATCH 36/39] =?UTF-8?q?update:=E6=B7=BB=E5=8A=A0=E9=87=8D?= =?UTF-8?q?=E8=A6=81=E8=AF=B4=E6=98=8E?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- docs/ota-upgrade-guide.md | 146 ++++---------------------------------- 1 file changed, 12 insertions(+), 134 deletions(-) diff --git a/docs/ota-upgrade-guide.md b/docs/ota-upgrade-guide.md index 157a80ba..0df4a2ff 100644 --- a/docs/ota-upgrade-guide.md +++ b/docs/ota-upgrade-guide.md @@ -2,6 +2,8 @@ 本教程将指导你如何在**单模块部署**场景下配置固件OTA自动升级功能，实现设备固件的自动更新。 +如果你已经使用**全模块部署**，请忽略本教程。 + ## 功能介绍 在单模块部署中，xiaozhi-server内置了OTA固件管理功能，可以自动检测设备版本并下发升级固件。系统会根据设备型号和当前版本，自动匹配并推送最新的固件版本。 @@ -44,13 +46,19 @@ lichuang-dev_2.0.0.bin 将准备好的固件文件（.bin文件）复制到`data/bin/`目录下： +重要的事情说三遍：升级的bin文件是`xiaozhi.bin`，不是全量固件文件`merged-binary.bin`! + +重要的事情说三遍：升级的bin文件是`xiaozhi.bin`，不是全量固件文件`merged-binary.bin`! + +重要的事情说三遍：升级的bin文件是`xiaozhi.bin`，不是全量固件文件`merged-binary.bin`! + ```bash -cp your_firmware.bin data/bin/设备型号_版本号.bin +cp xiaozhi.bin data/bin/设备型号_版本号.bin ``` 例如： ```bash -cp xiaozhi_firmware.bin data/bin/esp32s3_1.6.6.bin +cp xiaozhi.bin data/bin/bread-compact-wifi_1.6.6.bin ``` ## 第二步 配置公网访问地址（仅公网部署需要） @@ -88,122 +96,12 @@ server: vision_explain: http://yourdomain.com:8003/mcp/vision/explain ``` -公网IP部署： -```yaml -server: - vision_explain: http://111.111.111.111:8003/mcp/vision/explain -``` - -使用HTTPS（推荐公网部署使用）： -```yaml -server: - vision_explain: https://yourdomain.com:8003/mcp/vision/explain -``` - ### 注意事项 - 域名或IP必须是设备能够访问的地址 - 如果使用Docker部署，不能使用Docker内部地址（如127.0.0.1或localhost） -- 端口号默认是8003，如果你修改了`server.http_port`配置，需要同步修改这里的端口号 +- 如果你使用了nginx反向代理，请填写对外的地址和端口号，不是本项目运行的端口号 -## 第三步 启动或重启服务 - -### 源码运行 - -```bash -python app.py -``` - -### Docker运行 - -```bash -docker restart xiaozhi-esp32-server -``` - -### 验证服务启动 - -启动后，查看日志输出，应该能看到类似以下内容： - -``` -2025-12-18 **** - OTA接口是 http://192.168.1.100:8003/xiaozhi/ota/ -2025-12-18 **** - 视觉分析接口是 http://192.168.1.100:8003/mcp/vision/explain -``` - -使用浏览器访问OTA接口地址，如果显示以下内容说明服务正常： - -``` -OTA接口运行正常，向设备发送的websocket地址是：ws://xxx.xxx.xxx.xxx:8000/xiaozhi/v1/ -``` - -## 第四步 设备自动检测升级 - -### 升级原理 - -当设备连接到服务器时（每次开机或定时检查），会自动发送OTA请求。服务器会： - -1. 读取设备的型号和当前固件版本 -2. 扫描`data/bin/`目录，查找匹配该型号的所有固件文件 -3. 比较版本号，如果有更高版本，则返回固件下载地址 -4. 设备收到下载地址后，会自动下载并安装新固件 - -### 版本比较规则 - -系统使用语义化版本比较方式，按数字段从左到右依次比较： - -- `1.6.6` < `1.6.7` -- `1.6.9` < `1.7.0` -- `2.0.0` > `1.9.9` - -### 查看升级日志 - -在xiaozhi-server的日志中，你可以看到OTA相关的日志输出： - -``` -[ota_handler] - OTA请求设备ID: AA:BB:CC:DD:EE:FF -[ota_handler] - 查找型号 esp32s3 的固件，找到 3 个候选 -[ota_handler] - 为设备 AA:BB:CC:DD:EE:FF 下发固件 1.6.6 [如果地址前缀有误，请检查配置文件中的server.vision_explain]-> http://yourdomain.com:8003/xiaozhi/ota/download/esp32s3_1.6.6.bin -``` - -或者如果设备已是最新版本： - -``` -[ota_handler] - 设备 AA:BB:CC:DD:EE:FF 固件已是最新: 1.6.6 -``` - -## 高级配置 - -### 固件缓存时间（可选） - -系统会缓存`data/bin/`目录的扫描结果以提高性能。默认缓存时间为30秒。你可以在配置文件中调整： - -```yaml -firmware_cache_ttl: 60 # 单位：秒，设置为60秒缓存时间 -``` - -### 多版本固件管理 - -你可以同时放置多个版本的固件，系统会自动选择最新版本： - -``` -data/bin/ - ├── esp32s3_1.6.5.bin - ├── esp32s3_1.6.6.bin - ├── esp32s3_1.7.0-beta.bin - └── xiaozhi-v2_2.0.0.bin -``` - -系统会为`esp32s3`型号的设备推送`1.7.0-beta`版本（最高版本）。 - -### 多型号固件管理 - -不同型号的设备会自动匹配对应型号的固件： - -``` -data/bin/ - ├── esp32s3_1.6.6.bin # 仅供 esp32s3 型号设备使用 - ├── xiaozhi-v2_2.0.0.bin # 仅供 xiaozhi-v2 型号设备使用 - └── default_1.0.0.bin # 供未识别型号的设备使用 -``` ## 常见问题 @@ -226,6 +124,7 @@ data/bin/ - 如果是公网部署，确保设备能够访问该公网地址 - 如果是Docker部署，确保不是使用了内部地址（127.0.0.1） - 检查防火墙是否开放了对应端口 +- 如果你使用了nginx反向代理，请填写对外的地址和端口号，不是本项目运行的端口号 ### 3. 如何确认设备当前版本 @@ -241,24 +140,3 @@ data/bin/ - 等待30秒后再让设备发起OTA请求 - 重启xiaozhi-server服务 - 调整`firmware_cache_ttl`配置为更短的时间 - -### 5. 如何回滚到旧版本 - -系统只会推送更高版本的固件。如果需要回滚： -1. 删除或重命名`data/bin/`目录中高于目标版本的固件文件 -2. 等待缓存过期或重启服务 -3. 设备下次检查时会收到目标版本 - -## 安全说明 - -- 系统会验证固件文件路径，防止目录穿越攻击 -- 固件下载接口只允许访问`data/bin/`目录下的`.bin`文件 -- 建议在生产环境使用HTTPS协议传输固件 - -## 相关教程 - -如需了解更多，请参考以下教程： - -1. [如何自己编译小智固件](./firmware-build.md) -2. [如何基于虾哥编译好的固件修改OTA地址](./firmware-setting.md) -3. [如何进行全模块部署](./Deployment_all.md) From ce49b409ac5520d38eb146cd5b25309536a76537 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Thu, 18 Dec 2025 18:11:53 +0800 Subject: [PATCH 37/39] =?UTF-8?q?update:=E4=BC=98=E5=8C=96=E8=AF=B4?= =?UTF-8?q?=E6=98=8E?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- README.md | 4 ++-- README_de.md | 4 ++-- README_en.md | 4 ++-- README_vi.md | 4 ++-- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 7602db54..eb718c24 100644 --- a/README.md +++ b/README.md @@ -183,8 +183,8 @@ Spearheaded by Professor Siyuan Liu's Team (South China University of Technology #### 🚀 部署方式选择 | 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、MCP、视觉感知 | 低配置环境，数据存储在配置文件，无需数据库 | [①Docker版](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②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、MCP接入点、声纹识别、视觉感知、OTA、智控台 | 完整功能体验，数据存储在数据库 |[①Docker版](./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) / [②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) / [③源码部署自动更新教程](./docs/dev-ops-integration.md) | 如果使用`FunASR`要4核8G，如果全API，要2核4G| [本地源码启动视频教程](https://www.bilibili.com/video/BV1wBJhz4Ewe) | +| **最简化安装** | 智能对话、单智能体管理 | 低配置环境，数据存储在配置文件，无需数据库 | [①Docker版](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②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、多用户管理、多智能体管理、智控台界面操作 | 完整功能体验，数据存储在数据库 |[①Docker版](./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) / [②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) / [③源码部署自动更新教程](./docs/dev-ops-integration.md) | 如果使用`FunASR`要4核8G，如果全API，要2核4G| [本地源码启动视频教程](https://www.bilibili.com/video/BV1wBJhz4Ewe) | 常见问题及相关教程，可参考[这个链接](./docs/FAQ.md) diff --git a/README_de.md b/README_de.md index 53609462..0e4c74d5 100644 --- a/README_de.md +++ b/README_de.md @@ -181,8 +181,8 @@ Dieses Projekt bietet zwei Bereitstellungsmethoden. Bitte wählen Sie basierend #### 🚀 Auswahl der Bereitstellungsmethode | Bereitstellungsmethode | Funktionen | Anwendungsszenarien | Deployment-Dokumente | Konfigurationsanforderungen | Video-Tutorials | |---------|------|---------|---------|---------|---------| -| **Vereinfachte Installation** | Intelligenter Dialog, IOT, MCP, visuelle Wahrnehmung | Umgebungen mit geringer Konfiguration, Daten in Konfigurationsdateien gespeichert, keine Datenbank erforderlich | [①Docker-Version](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Quellcode-Deployment](./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)| 2 Kerne 4GB bei Verwendung von `FunASR`, 2 Kerne 2GB bei allen APIs | - | -| **Vollständige Modulinstallation** | Intelligenter Dialog, IOT, MCP-Endpunkte, Stimmabdruckerkennung, visuelle Wahrnehmung, OTA, intelligente Steuerkonsole | Vollständige Funktionserfahrung, Daten in Datenbank gespeichert |[①Docker-Version](./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) / [②Quellcode-Deployment](./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) / [③Quellcode-Deployment Auto-Update-Tutorial](./docs/dev-ops-integration.md) | 4 Kerne 8GB bei Verwendung von `FunASR`, 2 Kerne 4GB bei allen APIs| [Video-Tutorial für lokalen Quellcode-Start](https://www.bilibili.com/video/BV1wBJhz4Ewe) | +| **Vereinfachte Installation** | Intelligenter Dialog, Einzel-Agenten-Verwaltung | Umgebungen mit geringer Konfiguration, Daten in Konfigurationsdateien gespeichert, keine Datenbank erforderlich | [①Docker-Version](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Quellcode-Deployment](./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)| 2 Kerne 4GB bei Verwendung von `FunASR`, 2 Kerne 2GB bei allen APIs | - | +| **Vollständige Modulinstallation** | Intelligenter Dialog, Mehrbenutzerverwaltung, Mehr-Agenten-Verwaltung, Intelligente Steuerkonsole-Bedienung | Vollständige Funktionserfahrung, Daten in Datenbank gespeichert |[①Docker-Version](./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) / [②Quellcode-Deployment](./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) / [③Quellcode-Deployment Auto-Update-Tutorial](./docs/dev-ops-integration.md) | 4 Kerne 8GB bei Verwendung von `FunASR`, 2 Kerne 4GB bei allen APIs| [Video-Tutorial für lokalen Quellcode-Start](https://www.bilibili.com/video/BV1wBJhz4Ewe) | Häufige Fragen und entsprechende Tutorials finden Sie unter [diesem Link](./docs/FAQ.md) diff --git a/README_en.md b/README_en.md index cc0f170c..196cf16f 100644 --- a/README_en.md +++ b/README_en.md @@ -181,8 +181,8 @@ This project provides two deployment methods. Please choose based on your specif #### 🚀 Deployment Method Selection | Deployment Method | Features | Applicable Scenarios | Deployment Docs | Configuration Requirements | Video Tutorials | |---------|------|---------|---------|---------|---------| -| **Simplified Installation** | Intelligent dialogue, IOT, MCP, visual perception | Low-configuration environments, data stored in config files, no database required | [①Docker Version](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Source Code Deployment](./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)| 2 cores 4GB if using `FunASR`, 2 cores 2GB if all APIs | - | -| **Full Module Installation** | Intelligent dialogue, IOT, MCP endpoints, voiceprint recognition, visual perception, OTA, intelligent control console | Complete functionality experience, data stored in database |[①Docker Version](./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) / [②Source Code Deployment](./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) / [③Source Code Deployment Auto-Update Tutorial](./docs/dev-ops-integration.md) | 4 cores 8GB if using `FunASR`, 2 cores 4GB if all APIs| [Local Source Code Startup Video Tutorial](https://www.bilibili.com/video/BV1wBJhz4Ewe) | +| **Simplified Installation** | Intelligent dialogue, single agent management | Low-configuration environments, data stored in config files, no database required | [①Docker Version](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Source Code Deployment](./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)| 2 cores 4GB if using `FunASR`, 2 cores 2GB if all APIs | - | +| **Full Module Installation** | Intelligent dialogue, multi-user management, multi-agent management, intelligent console interface operation | Complete functionality experience, data stored in database |[①Docker Version](./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) / [②Source Code Deployment](./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) / [③Source Code Deployment Auto-Update Tutorial](./docs/dev-ops-integration.md) | 4 cores 8GB if using `FunASR`, 2 cores 4GB if all APIs| [Local Source Code Startup Video Tutorial](https://www.bilibili.com/video/BV1wBJhz4Ewe) | > 💡 Note: Below is a test platform deployed with the latest code. You can burn and test if needed. Concurrent users: 6, data will be cleared daily. diff --git a/README_vi.md b/README_vi.md index 83557ce5..e6d5f489 100644 --- a/README_vi.md +++ b/README_vi.md @@ -182,8 +182,8 @@ Dự án này cung cấp hai phương pháp triển khai, vui lòng chọn theo #### 🚀 Lựa chọn phương pháp triển khai | Phương pháp triển khai | Đặc điểm | Tình huống áp dụng | Tài liệu triển khai | Yêu cầu cấu hình | Video hướng dẫn | |---------|------|---------|---------|---------|---------| -| **Cài đặt tối giản** | Đối thoại thông minh, IOT, MCP, cảm nhận thị giác | Môi trường cấu hình thấp, dữ liệu lưu trong tệp cấu hình, không cần cơ sở dữ liệu | [①Phiên bản Docker](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Triển khai mã nguồn](./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)| 2 nhân 4GB nếu dùng `FunASR`, 2 nhân 2GB nếu toàn API | - | -| **Cài đặt toàn bộ module** | Đối thoại thông minh, IOT, điểm truy cập MCP, nhận dạng giọng nói, cảm nhận thị giác, OTA, bảng điều khiển thông minh | Trải nghiệm đầy đủ tính năng, dữ liệu lưu trong cơ sở dữ liệu |[①Phiên bản 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) / [②Triển khai mã nguồn](./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) / [③Hướng dẫn tự động cập nhật triển khai mã nguồn](./docs/dev-ops-integration.md) | 4 nhân 8GB nếu dùng `FunASR`, 2 nhân 4GB nếu toàn API| [Video hướng dẫn khởi động mã nguồn cục bộ](https://www.bilibili.com/video/BV1wBJhz4Ewe) | +| **Cài đặt tối giản** | Đối thoại thông minh, quản lý đơn tác nhân | Môi trường cấu hình thấp, dữ liệu lưu trong tệp cấu hình, không cần cơ sở dữ liệu | [①Phiên bản Docker](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Triển khai mã nguồn](./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)| 2 nhân 4GB nếu dùng `FunASR`, 2 nhân 2GB nếu toàn API | - | +| **Cài đặt toàn bộ module** | Đối thoại thông minh, quản lý đa người dùng, quản lý đa tác nhân, bảng điều khiển thông minh | Trải nghiệm đầy đủ tính năng, dữ liệu lưu trong cơ sở dữ liệu |[①Phiên bản 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) / [②Triển khai mã nguồn](./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) / [③Hướng dẫn tự động cập nhật triển khai mã nguồn](./docs/dev-ops-integration.md) | 4 nhân 8GB nếu dùng `FunASR`, 2 nhân 4GB nếu toàn API| [Video hướng dẫn khởi động mã nguồn cục bộ](https://www.bilibili.com/video/BV1wBJhz4Ewe) | Câu hỏi thường gặp và hướng dẫn liên quan, vui lòng tham khảo [liên kết này](./docs/FAQ.md) From 0dda4f56461a9ed6fd561cca1f382dca7b3e29e2 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Fri, 19 Dec 2025 12:12:10 +0800 Subject: [PATCH 38/39] Update huoshan-streamTTS-voice-cloning.md --- docs/huoshan-streamTTS-voice-cloning.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/huoshan-streamTTS-voice-cloning.md b/docs/huoshan-streamTTS-voice-cloning.md index c2d261d9..304a8c90 100644 --- a/docs/huoshan-streamTTS-voice-cloning.md +++ b/docs/huoshan-streamTTS-voice-cloning.md @@ -23,6 +23,8 @@ ### 2.将音色资源ID分配给系统账号 +使用超级管理员账号登录智控台，点击顶部`参数字典`，在下拉菜单中，点击`系统功能配置`页面。在页面上勾选`音色克隆`，点击保存配置。即可在顶部菜单看到`音色克隆`按钮。 + 使用超级管理员账号登录智控台，点击顶部【音色克隆】、【音色资源】。 点击新增按钮，在【平台名称】选择“火山双流式语音合成”； From 96991ae5ef3153f6bb10d59fc3c3a58cd46671c8 Mon Sep 17 00:00:00 2001 From: hrz <1710360675@qq.com> Date: Fri, 19 Dec 2025 13:29:06 +0800 Subject: [PATCH 39/39] =?UTF-8?q?add:=E5=A4=9A=E8=AF=AD=E8=A8=80logo?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/manager-web/src/assets/xiaozhi-ai.png | Bin 1946 -> 1941 bytes main/manager-web/src/assets/xiaozhi-ai_de.png | Bin 0 -> 6957 bytes main/manager-web/src/assets/xiaozhi-ai_en.png | Bin 0 -> 7354 bytes main/manager-web/src/assets/xiaozhi-ai_vi.png | Bin 0 -> 7171 bytes .../src/assets/xiaozhi-ai_zh_CN.png | Bin 0 -> 1946 bytes .../src/assets/xiaozhi-ai_zh_TW.png | Bin 0 -> 1828 bytes 6 files changed, 0 insertions(+), 0 deletions(-) create mode 100644 main/manager-web/src/assets/xiaozhi-ai_de.png create mode 100644 main/manager-web/src/assets/xiaozhi-ai_en.png create mode 100644 main/manager-web/src/assets/xiaozhi-ai_vi.png create mode 100644 main/manager-web/src/assets/xiaozhi-ai_zh_CN.png create mode 100644 main/manager-web/src/assets/xiaozhi-ai_zh_TW.png diff --git a/main/manager-web/src/assets/xiaozhi-ai.png b/main/manager-web/src/assets/xiaozhi-ai.png index ef3834afc08b6e3c1ffa652275e4a2d3d455facc..8a59549341b7c1ed522b30c6611849681efb6ab9 100644 GIT binary patch delta 1905 zcmV-%2afof50wv)Ie$k>dEz`2g-^ccYalH!B`{m>Pzgy1rUX&~lz>Y} zN-#TbLkZ&&h7x8Lx}G>-z_PAnW1V-G0LFlHbansq^ykkX5JJ-Bzp-zC5HcdxdV{*=HvIS(U{}>3*DX5doJ$v&~FC zbda}MS7lLTCVyW6C>5^fL{%2uX3+%5Ox{=h-n9gvZd<%( z7TyMS^50_tD@w0Q_vB135ooCynGQKTOnMJ|tQY_|!des25mVepz|PspHMjUO@rUq| znS3+WHmk2=Q1go;WGuGOTg;ACSrlT`Xk2qEzMAOV6@LM-0>)Tz2vI{OnC2vF`@L@Z z1svFm(=sZ3wga>RJn4uA_^ceO%;dh;NDBG>HGEVJhqgz*DvLTZd4b{1)`n*Q@0rO> zOuxxZ5ug>IhUOr==4B?=*+6$3ckSKZU@Z+_ab5r@V@3?FZU;m?X$6pnM$Bu?aa?r8 z^<~0pIe+#VA&6q_-SP=&t0y62uvfm`)rl_N{iD+RED=cvI=2JjL~&Km#!>Qu{&CnN zfR8(m6EX@Cc+AKd$86h zL#7C%#U8g;?;*}K*Z8=`1ZLFeE0^HS*SS7t5mz!;Gx-=N*rdKCc+=|RIoJ{qGgE7&X}r@-mR~Vu&wsV4 zBa>b`C;rh$d3+R_nYPX?$1{^}GL!#C7*n&^$N$bu{z=DPH?jg~HL{3})(W1gC2*|D zLiM-r+hgzrejRFuu!K!3-hv^a3#0+7c78lyzw2ge5dy6hJVg;WAwWaYYgL2`*h#P5 zm~jZr79n->x1rt1xrVg}w7#1fc7KqC?Cd-@OW?dv?dtQ+^ZrG|Kha-s*CDD2uUP^o zSP{^QD>t58*DzJ1d{fR|yNP(}wMt7b5Q_lt7lI>fDrzm6gP~9T_~>2jiYwaP@AXo}bboNp7$k(u3yMG- zQqFTH6Ne%YhpA+@5pn@VfRMzA=@|SGWq)p-+I2#Gwd8CQu^~LI%U_Kw!l5zf~qW zm_E&5uiVoL!yAXprhmHgjJ+JmmK+p;z(~Eg>nYDSQ7E1DaVV}l9lUHJJ24m{jDw~K zoG@=_Q+3J`T%^8|cWqA2O2o+-7V6MFi7{`QG8A2Bj5NxG%P7l)4!LehfU0YVaoB0xyu rPy`4`9Et!Ti9-<}BylJLge1;iVFt3b!d7pB00000NkvXXu0mjfX9#%K delta 1910 zcmV-+2Z{KV51J2Y} zN-#TbLkZ&&#wE-wBo7|OfF4(}LFd0q0Go$&bah{P`St4;2qF3M-_&n_5Hc+k0YWl| zB0xyyPy`6cod0c}^z!mD`u{?eO8_g&dv#4+RhG}qf z`lhb-A@@&><9NM`%jYjtxd5;>f9?RN(BBULBpmxzB5;E>fUV_o-vjUUjJ!e*2p`@7 zgbtz={6(k*@K7QE-~eDLbgj*;2Mbk}(7*2rvD72z>LCd6yty+50}Y6D*Hgn6%00?-bv+6#+r z3qASov49q(H=+0BjkgF4l#WbGi2##6fDkJN08Y@>M0AWP9wJzm?9DZIIGgxBtP53c zr`}eDI0hxZR6=61gWQ63YU-*oR*b|ocg8m}8D1h_tbc$hRv$u~FcVC2k_~-ZH~j(* z9E{U)5`4DFJ^D>uwS_7x_&Zm7UIBa*s#Gcc zBt6a|Kr0{!$w7I|>rBpUAv;#b_U`Y{mPV);F96h2L=2p^14dbC1(4Ze%xlT9T8+i^ z&4iV5?0@w_kkqwAd9%#pq;;urKHPS>XT(*_Z#7CjZeN$Ia>Tg182grkByyyM$wl;#W#~>E& zP=6bc%2|9wo+1DMTl1T}NrwY!~xh+)r6LHMWejop{P~{gLduPmwAl29+HNGo)u9m>5sjDcz zbx4oFHNv{p`mlsfE8cOM^peMa_(?%cq zEkbUl@Q`8m<`&u_korDa=s_2=n}748TLPEGXjh+infGr*`wR90yNOv%=wb|oe zWA44Yt|6;l73Y-6b{FHRmnt>=2V)Tc;X-hNPEBo1=3p$m3St7ngto~{(GSTnpFu&3 z?7h#ik6AnfIEa98%Do9W|5^YFCi@9)6Iz+F%}0w4#9YBzKxAw13BBrcgMYtc!J`)xEph#~s&HOBMvtAF>=-h$5`Tv_ zJzWM{KLGx$iso82rcspeNPl8lq#3ju*wxjy(B|f-`D-kKZ-Uu|H*-HcSYjTDP_Y;~ z-6f8l8^y~K7*eS62cA2FOU(N4SfOqCCvEsn4#8g~!;gw^Udr4V9fxx`kd(L)%P(;4 zT)+;0uii(TSCi#L2VMl9rc7j^2&5&Jx82qmIES+eqM5bC50Q*PLVw8PLJ>$y&Ux=- zrceaZGM8*OLjFJzAS839b_{+?al*=sLP?U_f!@=9g0?Vxo0E{tnOX#|p-+I2%%KQOM5IO_ggC?PKq8Fkf2(ZN8=D5O zSKiYK{*6N(x}tNy!G9dVmMs*4M40+<*OQ%ZB2Y>j;!s=#I(6ANb|y?M0=b0S5L5lD>jh)YahiU1LTA}|f16ZpjN8j*q`Fb$z15cMz$l5ZCjfoTX40o&uR2(f}9 z@K_w7&u!pVfQTWHClInKB}p9(Os|cR+++KhhbPc{rpT_$knBr|tqva{ggh_Y4iJ(# w6ahjqhax~o=1>F($sCFRA(=xFAS82s1LfGVwb@@<$p8QV07*qoM6N<$g8H(4pa1{> diff --git a/main/manager-web/src/assets/xiaozhi-ai_de.png b/main/manager-web/src/assets/xiaozhi-ai_de.png new file mode 100644 index 0000000000000000000000000000000000000000..f2c54d80c00fe5bf9e577af81f358fb56b1d32ac GIT binary patch literal 6957 zcmXYW1yoes`}NQ;v~&!J)DR*glEWY^-8E7}BOp?e5|V;+gOoIaFn|&cDZ)?!3epWj z=O7(^^Zvg7TIb$-?pk-9b05Lk;c?0FcxDci{nY^Oyku)+Kdi1tb5w{d{e&xo-{Ve*vc(B(I2K;N1?4T|lvA zsX?Hyt`zJH=vLP?c;s@=fyktfHB#W=eOV#WLm<^55KHU~{~~-$uy7xY3N;p)OC1BK z;5!3uk2lT_m-OgW^l>BIdpT55QvSawZd?@)Ru_ZgaKlUDrYtkb1s7R=UIHF;4VS2W5dChaEQj{W$V$b{D&v_uvjg{Z ztRL4e8kKEz!bNXX2~F}!eAvAZg8iVl;+Dq7dcQINGS#`?RlbC>|FKo-@m~iZ zv|MpG8$&4_fZH#a?pcN@SE_K*uTh2SgzNAiY0yd&>@Y7va{;(M1% z=_Wa3KE1qTFq|sf>Ge2P|=Upzq}{QfI?7Lm_s$D^@6{W%-{~O zdVvgRj|5SawNxks(Ig-+1{2N@yCN+ZLt~vPRBrKYm@d{)P?XQ4?kpYqXivw2H0b`lBf z(BX-D(1pWTq$Q~dOwOw7tUUwGC!J;=5QoRF0~7eTmQW0K8e!hHd1RAxYsVEpt)AHl zgIt9#xkf#Q|4dQy!Z$$$y(|;+wR=< zgE+96x}eq-+5fjErf@&ZYZQD^J<}Thf{I0VhSWqo*lYNpd*o|Ugo)4-^%@>l9D+qF z|79w!3id;_K)eH3Qm-{k;{S|}Rb=Lc32Q%?3V%>I-5H4V-rp@M0}t*Nv6kG^<*L{C zpRLGk=`jp|{#rLKFjj5=I~|el`ikTs&fNu^g|De*ChB;NJdNowQIP1LyWDd>vAMqL zhFmGs$Ovy9o;rMPdn(HhD^I$zro=!heSaGpJBe;zv2s4FPs-H$KD)^X7!=S7d(w?Y zj_RGr_|{1Zu!jB%Yp*r9g1UcsF=&*oX6Lgt^8xSTUB!77;Q}4tsZ<3>@%;X}pZyU& z!&HRlruB4^IBh}VocI|Zhj`6PFQPeXO;W{|ae#?nd+J-+jGXRSINCq(GtuoG9!meW zW&vTsuG)6lc|tQ~!P6k#Gw<%Ti&(N@q9;>*$f@zRL}uO1M&Pw!8n7!A*%=Ld#O`$! zZ_}B!ah}fc=F5-qAj@v0r8IjZOvVM_GQU0jh?*J|;?+FAV@3Kq^hGrMj&^66X&Rbv z%H@8O|ND?F)$}``ty$8{F{qBfKkyO9Kb;14q`qhfz>JLI2eHX<_G3SQJGv&Bc!VwQ zfDUr2gJ;1Dw<5TpK&*J^+8!NtZ!PIZ1hvuhX3#e$A#eZu6?Q!OE1e_0{-@|pkeyxDD&^j}SVbhI5TKC7PIuc( zMDA3z=gmV9SPcIN2Uc=3{*}ScFLY;9zl)r0TEHLv`0K6my4D6g_SK%ZG=8CL^s6#* zzw?30nV7wVm}&)D^{o)`=%$9w5}n@6+AktQ7(VH8fO!n$d~|H#-9xXvsV z*t_a@h7Lgn=S_-J$K+Un5M2n#5o`cU!Ya)0j1|3PN&%tWyUnHs8$x!-`^fbz>Hs(4 z`LYR{I~043r$Pf*b98-$@8`Vq$etD|z?MSua|>D+3zUy6M|y8Wf!^qr*Bm)kUBYtxbttmTBI*N5Rau@+OIdG zFaHpk*1=LTLg0?Lc9pTs_dF@=v;9fhFM+gsF@N0Zr1x}1aO|Ek@*I=3E2S~@j}DuI zxk4b&`GT>;eTpqrfA|B;T@XDX>`2_HVoL-LEs$9*mX+*B@+uITvTg7%%v6oeK`;7sCpWDjEe&Lnl z@7g@xe2hl!R<(Uyr*NJwSGN;wkIjjSacY-m?iJ@K=_r^VKi~P_e@>!3Ta_f^%r#9W zu)0rNw+s)9V% zUKNhsSX*+ct*4z_6rWtuOLQi03>o!t&XN_Ru70!gA(Cjp0tr2rQ@zH3-w92vv}>c; zPbAuSDh6u~Mf!y{bT6#m_~>jnb-~sdOgCF5MEoC9rmT1DR%W4IC{UGoU%-wZ!_wb+ z>sefv!wY9shq-J+K(#zrvYb*DaW9BRcE%gayOE-21jV+?wQbIK0C>D2={y3{**dQXrw@t<_`IOudO5q6La6g7lM! zl)Gz695Xr7WaRTVi(2rnFY-Gs-gyr5IX*lr3qPGe25%l!*!J(0wcOjpTKrU$_V{J% zAOda(-@9F;O~S~sJm@iDN@Z!uoyhKpm|S}K%3X5k@c?%8h>p}Em&Hx=SYpIs48LZ< z;p#d5rfxdv0p12wT8!z_u2K}(YJ`ks)^Y4Fr3_~~(iy+|PFk^*W@yF6(h>rE zFXu|~8H7t<5(8MG`Nzy4gKj~B7>yH7=7PA>uh{6_6iU7+LoQu zTPK(PZ)x)kSwc0D8W&g82|haGf(u$32KvxC;eTaejFQ|U6zvP4dYApWOg-}%-eaww z*%(u#jNZZ-*G^htc8IusDn@ME%{4|#CxCZ2r=J2J7B+QM9TNJwU)=4ssTe;b z_2Ka6jQp41Jkn7m(ID_tg`7O7o)B4_&t04KmqLCn%zEu&WI2huF2nihRffi?X?KWj zR9H<%4Wh0!ygiycZ|Y#M6@j?kVy^$xdizy5=0wL({eep6?vL?rVT`5afgRmV=deAI zuPh(k`K8W&m*ySxO*rmMD#Qs1WQtAs(zt$VmOJBXw;CH22fgst?s8;?bltft2C%@11%9|yTjatN$mb!abH)TZI|wgG%ji7WGR;fY+s$e& zg{jMM*k$@i$YBW|mtr&;ZV3F31%3*QzukAd?AG6)Bc30UtNHa98C2AFa%});$w#m+ zWqlVOz~WrE^~hMk?tC!g9>Lle4r#@|tP||o#n4_#;NzRw$uAe@Eac6Eb`<-}AA%G< zaAx^@uJ6$?AFSeZ*O+-QfMu0kN=agtgo2&2+I=i5$NWxd-Opb{pCxce;P$>EIXQPu zn>3>uVWRGuw3zK1v%GvZQ`%G zP_!*6=2__B3UAGi`HUFp4yFxAW7{}>oZHRQ?h!H_|0csa4@H4j@#1nfl7J9FEDm0r z+S|@d;x284XUY1%bho7@e^5E(zJ{t$7GFLNM}c1Kn2ls)>o?g(2iAawSgsOc%G(Cm+fx7~X3F6Qb zp%;_OpwJ5Bwyp{*uKFcvfP#=_%X{DuN4Z^cQTD<#;iPA>z1l1ePNb3>sz;S=I($Zq zpsbN+m4Y~u!W#qogn$7*+~By2WLPL7|HWSiI6C{$rE)2GydwXZ^&Q zJO0Nq@=ax+_qEhx5W8&@S6w>kIK}3fwtSzdDx6#IALLWPS-vZ0hM~3Kn|@!O@O;S* ze)!#c3H>(>8}#LnRPG*+9n%Xf#Q@6WjRO~#%Q#E*hIt;ioNmJn*8nyYkyMq7isRE7 zdcG@n8pzp#c0j#d%E&fb$N)4>ai>j?d(dzFRU zN;jpEX6KhQr|*9ovX$q$@rT36wlo-jommMfF5cy}@-S9*rj5bdvrFZoNKCERsGd8n ze>xnMb~Q-F(B{BzBHBM!lg*Ul{fKY)s>h~*_KG%#$2Zu}uyAtG-ELchVrkg`Ep{4fe;)*Y~9&l6@ zG;-rIQ+10f-j4WDq3Rg9&%_Pg-A`e`QLK`!qLBul&^?`4TpjJ|wAVpPYWYv|BV)3S zNBP=way}n|M7

<)eghB1R)i@w*P(HJ%N>`u%@Y4j^P^{yKJD7*Zo0H&HuJ-I6qp zGwwV6Ci=>M%o+Tx5g$R*&GwJ6Oy$kyeu8swyyne8(YZ!$+w_M~vtvMM;ctv}U5!ke z2AA|4S^>Nf2Lh!e`MmHD)PnFUCCO6qSmMsNhntNZvZ4*sI}f=^C<#{Foc?FjQpZUcvA%!%#?m4WiM|yZO3!d5dX-*l{^oqHaQoJ(RiJx1` zi*U~br(#BbRwS=YiAi#i;u=&4)x+%EA}~L-7>8HdPeWavWnTk zawpCL$Oo4z?82WUFPUpgHJFH3l40Q3dRrhk0@+3=f!len`*lW-`e1ROT~`&v)b{|I zvZ(PqeZNQ4#xmcp$yj<%aZI|yu=lk0SXhbXRJ&>|gn;FGDo$TwBX4=EO65mor)@e+ zh;@bU5LZYK#8(9O$HC=fu&n60(2=}4_^$-j#Q+=>XV~=USvH+gG0lbzWz;Lk*VNKw zmEjibFoNnXR<3~GrHPn9u4)g1gN~k1#9Fxiq`(ARNnjIsP|1x8>QH+|X9hRY8uM~? zhrm3om+JiTt{($!MGFJo(p5bYDVH&d7Q37@l+#XIS8Ewyme|58Lh`1g4y7-h%XW}((yc{Dp-fdT=eWVuVQ%Xym2C4)b7U7K;Me|bCw@({-7 zt*B#Fmm?=VQ^zG)`xB>_*mCgJt;nsgnW^l28>MwDdF1Jr0Cc?cUY)R&CQ44lZ;UpM zoK)(=!%O>Gk}PIGdF~|Jch@TTO-^gdllrcY;#rQ*M?_|)Mgu!8H|kj|bI-^qgpS(y zb&vzBm2!CF%i99gls%e*5UrPW)Y)+*J>0{_I$GUFPfKieHJ)h@2ie_Z>&KA09u>y0 zndwf7*OVv(9EA|Nraz5{r(F4lX}7GgBy*X*K9(;irzM=NgSMm2%!%v( zUEkX>yUSP0uq9&O?f`vzXle5xXh`NieXCLjrdPe@tzO1R^nr`AVgK~eCXIV zA7z~dp}fGXYs;;+k@h=1^;7`&pkqQsN;Cka2JyJ2 zqC7*@Gwi`m?_dcICxW!;!Os%7J>lv(47H|C*j&aF=hk**0t{Jyz%K(W$xSoX+8F!l#Qm6L+y0E z(LX@1l~#(H2hf;>Bh=gZZC7P1kM2y;s%5}_Kq(|r_aT%dE4jT}iR9`X+-X?&kvd*S z#X-%!whfxTa6;2_g}+KKeeT%4QCYfqndQ&sWVF(|BMurJW4?<#L#m% zaIUewiQ?C2XcHpLQHFK2LQgEGM1Irm#=!;?We2HZeK=b^$*fiAwxq$VhTbg+Wkfpn zp%|LyetQG5uOJ$l^HpP?W&7mVae068sjX>*TYA?O$@vY`41uzb z*2$~`-QNp|&+5KGuhW&c&or_QL8jkhHJa?GkK8r`fz+Utf*b>*aE87BXHD6Bu;voO z??@>XBH!eQgyM^EM!m8kH3Bpt@so~P!np^%m>lNFrp^nBOAey zxxbbnT~8RM^*1%Gp>@{xgChO5k(3Wx6(Pw3Mr*@rRCMA6)Dj{(d}#38VyU{5MqIIA z?Jb1+&q+vWV0ql%lwb<J4+f^{7 zDhOBaYm%={F2KF5ld=}vL8QbKQrl$5>@UVrgt~O&8CEN#k6RA6ywWZ9zejWit?6&BHwl;f0fQ?@haxv4tis&0W$gDj1}y;48>%x z3o^`H-O6*#6#` z0fJY?H!AoUOyK?AexDJ-^;=*5J@cTN+H#picS%jAlXUNuPPA2?VxkLKWG%NG7nC9S zAwH~7Za5~7y#;_GS4L0U?PVKJ>*h8m0#$itimK!{2(tip)V`9wFoQn~7w79NB+#L< z$YDl}>DHtD)|XaeH#dwXQ&qC2rrka5z6v}&nIt3+0WFz&JWU@Q^6f8q!wPTsU|3v# zqn`Ur4Vh@-{I#(>_LTdIgryeYr`|ychrE;=n&TNVMM8JQC{R7v z1A`e=5iD!^L^`zv%a>OZ2UG@5jFJ%}=(2 zxFqLLEEVd1^k&eeAU+ld{6kf}}j={0xD zfr>t6B}t#8PajHUZc$}^2FHme)ITW8y6ZYtKYg}#h~LzixyX8^@nSxSd4J6*A^7wKK*R*G&zYG24`2S=diO1tTw4#{p9qecnQiB1p(QKEOE zci-fG_m8{QdD~gd8vsX4_E)4chkMtzrcN z{qyV`yqDcEXhg@yRb4yH>ah*jcpf6jMLh~W78s9vn?b7XfnB_JZ&;SCri4uj&j0z= zBlz;}Mx0z(@84J_zih9e%jb?M{5Jyi)(!t>T3M3jzL(>jjMU9grX<; zv5o-DdkA09vR?}n_4})u-Xd=O+W@(n(3<#Ouew&RX=Y`;6z>GyDlPyIs{LqgZnC$8 zw>rj>81n^C!j45XWUZI@y!$7vp@nXU#7OSXv6Z>LS|zEQvusA4 zA16zU9KavUQH@#a3MjFd!dBH4(X4I@TmbU8lBU*-r^+$UxR?28d=YTTKS8a$t%`T@ z8!-T~e$AF2wgh;sR{u|!kpg$YzyV+dJMHl_Mkfin!^d?JBUsWMC6|^h&<#Xp{K8|f z?eH;10d@Pf&6ICr#n!yYJ;Q)n%pB1zIWGt zEt8MPTnG(jE*ZG4lr-RrVb$#>z96us8Z&1<{T4gP|Km?@Lm~Iz0BaiDp#{3A;5F|= zSvs5Q1h0Lh$vX)`TCsR)bbcdO-qw}$!u}6~ffdmf?4!pb_hD?$xPY!qrL!Uo+=iHq z$<#_CzlZ4^7dNqScsz-Rt?R$q^0Ml0_WV4SS@`-dH?!3Ug!tXeJC0^ugw}9=UH!4c(DNVnb^vCvYH6j3rKZj-WPZ7-#oknk$S5s{Op`xg1Dt z@)fVu%Y+4hVExL3o&8;5$dy>4PKo(E`lOtA@`4~B{ZRrP!wMkKyHxHPI$KT z<3sto&$tf9>-(|s^Gcv)1uJph80i!i2OGW9iD~o54@qA5N`PFa-?bP>_Vq;{<4Z_( zcuqb13dwT_38Bo`w}m>14~bCse&5lv25A$NbF(^%4{4_3aoD^ca!*%Y9sGnMGd6R; zq81N*yXJ*4yvJRhNuiqQP7i8oi;CH{cDNNONkJ$IYJ{yiqP^rYfdm;mxkTC#yyb#I zP*W&V&YeM%6`mC}j=`@_WlzPaUPBgF>nUb30UMBy2lw1DZo(3V78rA&D4peq3uk@u zgr-Z2R%oSN>d1ZHU9LRYk9B5Xt4SJ@D`$wJ0xce@7x=3NG&1p`1CXox0?nZK+3=9=c(LES1*~fhOw2v5&wT(Acda ztc`ne0Hb6JLw!`dl;CdR-m$z(ae$|K^f|U&^s1l30n46DwfOyQ{6ad}%6d8!zPY2< zdCC0|64-!bj{p13c!}CiIyIy7(p1&w%G~|>2G0tz&7m9GccHdbdD8a-XmL@5)q*%B zY4I1m&X&7Y!Z``dTw?1Q@~!Ma>83(9b@0;C=ip znPI~9O@as>?hyyF>-k$jSztw2TdarvV|zEBb369%`$v(fsHl5R2tt()umt4izlP(i z8jt;nFkv{pGNr zQq_4p693^EI^u{FK0r1@3sV0tqb6at=>1}ky-`!J0Ff2D?O)ZOvMC?9i zZ$J>%m!_JonE306^1Sq~`OfASAr_(lm+So*$emE5^Y5^?!*}3_kqq_KrMie#(hV8! z1U;F*Us@-CsIkQ79UQ%9reI@b>`mkTys(5VPpZ;ceA{Y)@ZC#A;`K;HrK&865jTKr zI+<#;Jzv#gK6v9%w?XmrdRvdZErb6riqr2KU6$=|WUbC!Wmtw|mAZTd)n_x_q?-jV z{^F%AeA`esdN~g1H68*`_3p6%L7tCz@VQ`RjX7`XB9--g!P3*$qO+uyGZz|KYvRW% zCv!cWKtVx*0ty!%=I%_1kt9qkTILEHqv!0n%JE3cl^E%g7zyg+cO_My#Z`lGCX|w) z@AE|C(WS3;4dd7tLjLBsNRoAU)tR}74~;?6I)3YG0apdj5G_y> zRcL`?{n*he8GXkKt1*llH%X9Bby{~?#eufucGA_60(7&RTKrcxvwu?3*+TyCOJ1xK zr+8fvZFuLLWX-7KxnJJ+E?JvF6!^e(MA_AV16dubDr15b^tb=y9^``&xytvqPbQK2 z|FzVO|M1*L8wUtVd$i~ucc|kAItlFhFptn5XU@cn{hl=*m<}EwiDp@Nq^u$7wN)Rg zXX3!;Fj`hsP|raxi4_J3JRdX&3_iSj0M@P=0YoUzId$r83T$3H={Wr(A4`xq)AzFf zTzxqhK1KI!(<*Xbv*WiwwTQ>gEUMBu6wn>q~y|cmAGQc3ji5q3W(p60am2wyW zFGJ4lk>D3pp~*9IXCaZ;EhZFkh7Cq0n$FUHMJHDme})}oe!js5=$u6C@t8DAW4ulY1rQc z#;3xdx4I;lcUNUj)pM-wXZABA=r#IIA@c?trwF*;a~n~0?vnw&;H$PWwfG^?!Qmb{ZfSbQ48NHA;PZKv`U5g94@=ljF|vu*zM05eskqtuMYPIM-DfG; zQ{X~uk0PCf+4)mSNssnK_KwSwL-d(9N!R2h1iVgh&7<0LhzJZF(pX`?GOvX z8umj`v6iy4F~v4qXVTLy}{0IFuIt2PNxF9o{y(4&{@5|Ne8aK%qj zQ5x#2a`A>k(N?H8RU&oszh~1xLEN-^tg1tA4(5x&$Q$J0V^ecA+vWfC;n%qJF;+~@ z;zO)Db%(BG0JBV*;j#^@>_Hf4Z$)DdLr9EB_S~@XlGNj9rW=$Gsr1cZQ5wzOo!0t{F;! zel?eS-YUKv@Baqz;uxHz&Qlft*i5&pQ1=>XG=j;Y<0l<~Ess@hQXqpJvi^q;bhlH< zdE=F>qtwR^8ZZBo-CLha@GcXL{Pg)n4^=km*aVXj0a?@ir5^!}J6@fc-tOPw{TO-eCNi@{BS$iOopdTgdy#y}6Q3SN%aglI*Bq zz5K{OQaW`^5SgL@cg9$j2)*Dxye$Gj3>ONYMKh{tcFOcZMN+Ur2SX6 z-W%#t=u{2fpy?tX;MV2v`!}b^OPmaWG5ig06TJSNA$-mmU+@WiK&L&_Fr_;Ho+dPo z@F^{0|G+vV-7{&&A|S7Pb{l4YC^_sy=JRoY#)aLZ$UqnU!Se3OO>aczx=ZJ^iQ>|F zs8L5Ck&FP0JmX8`UQEhrhRsQWlP54BwlhCLZNDjQ^6@fHwMf0Ac`|9>P$I$d*v>Uj zc+dhE3H)pN`AEwB716SnAXbf*B@+hj>SkRCP5>#3GJ>z36i3D-S%lkQCG;0+)j5}M$&0!~R9~=Z z^AF9EBJeM?eGtfr+Mq1q?-_B&8q*p5a0=isz-Oa6LGN?2w5WnT=u{7+&+BKR!$UJl_fIwq;tU~*h4&)96d*x18`_t3^fPKI% zMrUhQJSFia(zg+W1)6`7@lusdm)waBl@Xaa3NP(UH2_N&i~cc_d*aB4F7Cr07TyqI zKko4~HMu?+4)5xG`LFf-jIKM2k&jBa`nf&%0CsH6ef-}9^Y?qZJQeBn!2O95DHE9F zrw|;X?+D*anIpy`KQa7qv0Wf^y{ToE4bn??)4hJ2$et@Jfmd+ji z`=6;ZBop)I+5);Y0*FiyB6DO_)E`p-wnJiGy3?^!m)b<`+Uk7fD5{8}FT3=tk3S)} z4OakJIenc=qhMxw>2grbAXtWDt)y5x26n|>mei>;W#KqqimNS=yQ8NGCYW04`!=RL zC5x}>l>XmD&XYcY0zPO@%~%5Kn&K$pdlb&jq2h8GBf_k&hr!U-iGCdag>j&G>WkiI zJ@%AIS-rtE^KL|aj*|dZm069?grFkFjdd4hU<7sdQ{?SDT*AmJGtrbFj6GiwY&WU%-JJob(06^f83?AX*Q?YGza3V z%*uTxG*`;qk>u%XXw}H6VAKFyY-8uh;riz;FOC#?@CR#!KIP?zeIT=bROB*0a%_pk zg)aZFdm+!lZg;@*eC%Gw2;i$(;esiz#}&l9u#vLx@=?gb)903q)Nbk!FYHBOB4UjM zZ&)njhIPd?oIJ{3LW_nkJ~B}euVA4J~a9tdkb|_rp|#pd0#dZjHJ@(N#FEu=Ux*`}h%low|9FE_}iW zev~^4fWeigy|V6JEp_3=tr|z8%9gv~wCqPB9Uv2L!=2 z>7hUaW9I=Iun|MWXbPtxMv}|>QIetxGVfIIo?ok_kZ;H1z9n&`#?bW1CH#G7;Z134 zdN!o%xL?8KJ$>+2478C-N4~wLv*lQ$?UP_v1lmmz{P?(r&JEA@h19Yd?Jw*z(D3zj zJy$(9Rge9%)k~iw8`f%m3!=|lNG;ko9jr!GtfRDUEOuDbAS3o08iB+ESn2Wz{5Opo zHHTN=^0x^EuMw&v>~HQXIv>EfI8+_L3B-+O6Fo^(lC@KtdrE>b}%@(4joX-Rt1 z#?p%hv)5haV-8j~qDN2{V#XJFIE*o#{8H%weN32!(3w}=-V2(=Ce;r%fq~pKHkG)# zz>?NIs4mv38>07fxh>&x5ihE!8~kfZ1>o*_im`|Cf>m9%2{ncdLCXfN5E|S(VtQKv znp(C|9in}y@VIMDmD%J%60d(nFc+L@7n5J0j~O@XAF?G~>I&(v^zq7aV^~6+q6)|T z#|&bo*5;4@b6|K|6bAJi!LbIRuL=#Zj*Hd#hbR<{mI%vztf6n-NZh;YW!qk)`8FSR zWZ}H;EBAmoeYY(>Gr%cOVgjw*sNkKLEq-uN2wD9}xZ?!d_L{wu6*pelDRS z60e>;(3p9Q%48RSbFonq1QRVscDyEiI@I`~`~Ln>b#|jVI14&WAQ7|RA4Y$^pYy~1 zd~zC~FlLx@cPgV(N0;6kkVRZ4-pW(eC6k2&6YF=#93IG!X#L2uM1SZnIf^jt`fVdk zIK8Z`=B`g(byE?PG5-s-*T z3?h18?TY%`4M=??W{XpP1Z`FEP(kQTAH65geo z7sxA%Jm!--B9r*HaL$~!tGWEhsp6_ucHS~fL8zb0n0oFO*S0UNn_MXN~8ZF+a=yp?Lj19}w~UU)?f-wFb*Ui})^`d~KB0##%j@cbCcY-Y^L zulr$@mPnyrJ8YN8;Ww=<7Ge5X*io{}cbDtw`pv+eGtZaSXqBkWGK=N8;5Ys|c>C>!XA`s*|6-E4Y-XHoVbLds)CC z$j4LH{E`6)?FEG%UyqwCMctb$WvsVMs0+HX7N{IOS~>F9uUTr< z_NBSh0Jz5XOQ#zN1B-3IP-=d^%MZpNzkGIL(_cgffnd7lYd>uN0w>4n5K|SVUS8$=mULv*gG!(jNjBhGxx@i>6;>2RGGlyN-S~1Q>~0x z`_y;qS7y~x)CLWxf<{YmRYFp2aUKnS1T>v!p_>jc*g)?;b(=@x?nq z@Nh5>O6)XSS3Bfv?m;Ql__#9z9Ak#Qq)V#h+x|!aUn9#|dsgGd-lpJ>Yc4NWuqUGa zj2wOU?9vva$gx+5eQi-M>`#ERF%hj9TBA;GbYWS9dI*ClLI{|BWn{)x%@&F2>n}Q| zF~P|*+}1WkdEmafwD@}_^~&7?@N3PdZqH2$mb~y)^03%WWuLC6T8^k+FO%1c*?{g6 z`D&)qk(Z63#}+?r7Cf!D`{9hOg(YqHj9i?@Un?tLr&jqz)2oEYhIex-^7J`(fSLwX!rbGKCAr~mv7 zm|N%BpIkGNgz-yz{vK5ML|ex1637E1^7YdMn;mA4%NJI;X00^f$Ts?M|4Qfi>2r>P zA9QkEs*9U-$+!8>alD@Fw4a&X$4_sDtydEvcJP=HnSqg4@f)r!)x409rRd6kxCfmM zLzgh5Pz8o-z&Yx1nP6gE5p|fiBnItDXcQ@OLEagJ2IYJU(@O{@nw4U=aRU`~j6(J- zHnCAo(@$5(sTphI!BOO+jWj*p;tcq3%Y74PIWS5b!SWrBI;n3?5X zy^Ss+4?g39{b`H7MaC3j17yt0cuE;9imKc)ROM2u_P@unrJ(SNE&hGRTDGXpVH{86 zHAWGMFO*lF#N+ac_8@6S)NcBld_TE4JhXi>a;ZJ|1SjB6@d zxU`)S`c8)*=xoAByjlFNVJPH?I@%fP3j$<|^}t Sc^5-Q0@Rgtlu!z=(EkV1BkfrL literal 0 HcmV?d00001 diff --git a/main/manager-web/src/assets/xiaozhi-ai_vi.png b/main/manager-web/src/assets/xiaozhi-ai_vi.png new file mode 100644 index 0000000000000000000000000000000000000000..a54913ad3edf5c7f3794e062a25f1950601df5cf GIT binary patch literal 7171 zcmV+e9Q@;nP)C^Maw}Qv4AoK#*mmaXEkyj9T!XCz1 zf$bI89zIR1tRT!-1Jg$f2(yCl?tpIv=>foqmL>ixRFRbNos;8xB@zWvtRf190^a@p z{Tqs+D2k#eit-lt@3sTpy?f_EkJ%E&i4P#)e|56$W|cWsM^ThL!Z-;){nM{~Tms0o zk1C3yOcz@Y+IMY&)%ZP37$*w=*LZF8?z0APyWOk`yBaBqQYVa)C8&@34TqHg9st~L zH>=XRQi`G|N@vvgoe*K1JOWtuIHd$|x!tT%8~P}UvLlQW55N=JC#H1@02kZMDwo$t zQ4~cPf-U3szpO|-VZu1MLqEe806YMXy!@&tie0{;pWzFTcle17XGKvI<%DUC`Bip= zaS{Qz8hE+~dMUpbQb$pY3FG7j6dGVcw%x4G1=KNyLmi@lr+WY%0bB^FqbQ2fN*E^+ z?#(k@x$2I3e*5vs@O+gyb~BdjKK;f8lj1wk||R$(g`_+;>NJ7cOzwGb`1OlpIA-?BLlF%m(i#&?=H|s~ym|9f9{KgmIDr z_zoadLs(Iiw@z!!FQ@0a7jD-FZ7dlKXI%&+l&P`aZdPkynfsKMi?>N{3p0UC3Eg>mwzam|XNyk$CVc-wAPUqH)fk}SeFxf*gJ7nm4yZUZ@h zFUP(VtOS({$x##u%CQxgAcd5mFis*idcR?K779r`P)xHL!HS~1S^8vqxPahGfw}9O z`<4f5Bd_rRN>GCPvgNp3pe+d*ilXcxI6-|j6%fXW$E#CMn1<1Nh$Vm@L!A(cq9}8v zv+>J@;RWP9Mc;ZRmj4F%n7oUQ8}PmhwDna$hN38kSsR{T0!U2+@C5w{@~cxe@IX!o zE%2cz^QIhIfjQAD&o3uXJ{lS@5FZ^qxt8L5zx41J-NVfLooW(lMX|~)%w7TyCL6+d zCF=*~x3M(>g+c@)>!B#h0MxeVNADsRydmsfSdZ5DUrTYm>+NQB-}PWa?{^N$B%vsZ zC3ppA=mdSe-K=hgw#|m)6Xu(2-UF3*4o22PQ53~0gDSjP+5mSn{+E~Iq~m;Z40uWM z?CKo-Vt3a7&Nao5qS%Kg=zaGn+-^6k!IM)Sqilp^xyFMUz>1=rI40$dZES!$7XK^# zQYq1GgWEy2n^nHutj<99V2#%kfs#MF2k?HoSzW5(t0?Z+ZdU1bvwDwR-tK(wkOI_4 zzkvGajbW4Da5@ESJdgqGjjV^FD2f#Zmp9&SR%I9`7m!`%^Fbcoi|T_gPHrH-Te|B8 zw?;Sza%w6^Q4~9{7kF*64G!6gY_>519%yVo8(9xUQ511ZJioR!!2OB;Im4M9q{pbK5U}$>Q55B*c=!AF@8$#Ey=xW1Ss1QlRQkg?s9@kgcDxu7sIRfw(NKe1V=_TkMJ%e5_si10us9nzo(6iy(-zNa)A;3k^a)g6*K3fGg7RpmbLpe}BKT$4)*R?Gx#@%9SOrkO zEtN8|B!&Qwn3{2EhF^!tPm% zdWtCV@>(+K--4?^MkX?(jbDL2nnB>6&B6HfKraH%R4EIT0M1N1pTq+S;TK755M4li zQ(y|&rTN(f#Phv(dx%CSw`plHMR<>&Ga!(KGEeNqtawJXs_JFO5|_WI@^ zqbCP>pt4%K9(I$#51{J}Ea_2kW@=zM>e~+zhA@YF3=LeLsX+q(+mq`+>nQb;wx*K`N_ zp-2H}jJpft&% z;)QYY4YU(Ga@1@DN_`~m@roO2fAlJcpM!CQR5eI zlUk?;sf}f#vET>g7wj%gHF3o+6i-4}trYA+Lf$|kP$yiDsKZGhX!uqHn63f*QBYP1 z+K-S*2;(vM4E@L90%SN>xykdPI&j|}bF2c!>)T%4m}AekWWVrmJSTo5wF${k53~)I zAmj0FXkX_LB#FtzP&@#SVVn&5UB;mH{*6Xb!3RCZk7L|3apM;NI9@KdA-e}TrsstQ z2HqF;x=x{jR0Q(m7*Q()>zm3Fzyl3j(p3cC4E(aU5&s-unyJJhL0LwI<{`G5RmtOU zmoYE{8Q<@>o0aj#s)?0(_CS5xb!>hByr}#qjgOuNHS6+(aVI2AT!D<>MW2%Y+qmM2zf|J9F@yncJyd0t>=!G&?`%V0(&%w2s`js7Z1`(LNOeXenth4NC z02j6tnISfpPp^6`i#}V@;SU{Ca&={GGc1d}z_&-fPC-WRxm0}Yg!}fDEne{J@Q zMTc}i0Q9m)mw<5rV4dB{low&_+`UWG(Aoa#62lYX+h>uCO%WY z>N)TN_;XETE>E?w3_B+F*IdGX@L~T2+vf4*$P-w%2`h%-)kKC89qk7GEteK`F~I|^ICvxL@q(I7;f<@w zK>`S@DtE=E=Xb0Pa5gu%<(A|g!}Ugyz6|lCTw~hT1kkSPXlx~Bgzun@g@ZP_5(&vk z9ZsOWU}yA7Wxv_y8q)}4YU0k3M=pRH!)(!URb+~xL;IAVm599UK#O5kk_3>A^_F1D zjwirjRY|MHFW`Iw+{tWk)SY&}}=`^0BC@`Ok+wL$BxVl~0OE&fc7m65AqNCx<%w>G;8=5khwn-i9v2dY_A=fS@ zsMd{Nz}W`49Mjz3)|-hh=j_vGfS-f+p~BY;5R)SqTLI=TAvw8_oGCD;z8yH~+rEP~ zfcEDxa-oC)C3+aX;Y=!P)^KI0doAD3sgGLs>N_!h8Jip6N=$cy+YmCC<(YKJqRT<- z^{8*qtN#PN-!DKh>?yjx z>r3?W_yQf{oF_!D6;c}rPZ%=Lb8xoz4Ez)H46Fs(h-`a*#VWkDVYvdFtqpEADBBL; zYdN=2b)~?|3@ZHE4$FiK({^eUpaJ%8?7U|l$TL`#d-Vj`@xwS-oKle#MX`XS zF;c)?-wtN<-e@8){Jslcno5q>#{abXjNe~X$z<=qX(f6ZzTvJEvlJE6g{)euBl-F=xgv6Ihb#Tas&oyz7B% zbfp{sKBNR?39hFNAUot4=NX~tLmHvoQ*FKTfd?1ivYj7cHfWVN{F~=^o%T+;%xI2r zLV-%`uGxp%{#iO~OCcfw89B(n%8q=W0x$Zugy+`k%k>Bu|MejEKJ|M2_8GZ0;ZO0OT3-=I$(#>p*)+kHNVR22iyZ^Vi5>nOMDQy3@jPblv91-wi9 zqJtq(fF9Jmi(DRnmxk&c)1}^qDMLHoCCn-;`C**+$9Bn^?h5CZfn=%C9OH!nt$B0n z3$~k88pcThJ0VZAo!6=lh0e z)F30{zd6e(hw3u$yo%edhVLF`lUy(ukK7>0UPYCZI zy9w}qyIHyNWbIR+!HdSm${O?7^jJD-C&2tY)q&ypWB2U2=^(e9km{DoD#tOkP~^&(ifN&VHj(}u5Wn0hw(PF2Cy_?u%7LK z<5d^7+hL5#?#=;T23UZMjq<=DSD-=an*Td$_~!|!)h5R`l)vwB=*xrQ`GMj2FQ}D( zT?&aTLCeNt8NLAU(BTDU`a3wGgEzJiYU-nqoL0g(3Bow}W+CUOXL!D8-!?tpGd#bI zE`?0iHWlFKIk(xyKmw2h;FqJydk6QubcI*>3MpkAB9-mqq_ArI@<8i4rOcJZ9FC2jmRu6qI@>6Ow15MskJRp@v1a`8pl%Y6WrCFwmSeoU*>heQyn*ZXPXUJ|WRJoVm?y|> z`Yb`4Mta9fTA=80k4uYsxS|l0W!*WzW8t#)QG|&Z!9$t)gsMlH#KNK)l>_0{W*Y)5 z&`=OU;GJF=o(}-e2IqPL?JGi9F@AaW=3*D?F+2daXOUJ3ir{spsMa4#g!l%mJ6xg{N3QV7ag+Dw37+iZM@2q$6$Pn2S81?q72mrG200=j5exh)K3 zdxqx&8bWX~*xK+Wkr&StA2jH{+GRTwSH?7Z&40kY(OZI+t36D(=C|pNY!`LHkF@Jy z7ke$mn48)p@Wxia6yBvTDe^Illfsf0v&&cM4Y8<1mD0>jw z&1%h?1g|mO&8OEm5C_eh&P?QbCMPq#!MV9W`(u!e*mhw{u(@cGDOF9dw)z(JI4uAf;@6`VVqmC3Zg~Fe;1H!t&NA@{G)6@j z_Rh)n{y!Kfr;e@admjPZ3_Y3qRAkV8X>hIy&oI+_XijD!{%u97sPS7%);}e#!#K(3 zQlge84}qbW5;Q3NA2GH9kS_vJW#0C8kCE)7$QWdx}gv97+-TSi6(vWfo)WnR#0@>w@-{}AIU9t>DYn} z=N*ml7fj(8;PA6mV7NmeXv*2%fyKb{D$0iMd_&nb`3%EKp;cMxDXl7r8NW48!xVXB z1GpGlkq(#)<|SyBw(fFpt-_FP3d8fGp&lYOM17OSyLww|lfS^Ey&5IR=uL&>y~1I( zfjJSNeW@>nor;x9P#kay^4PRiuH@$~0Ob)~KsJS8rO(+BJqp7%mSLQH9kQY!)VFh! z^XCeu1P%CquR-sf2Xv?k+60Fte1*C3>mT{NX!x!Rk9b*?vlBc{n)dgmY!kkr>?Sgp zIb)V#oIDuzl}FG@{55E@m5%Mqk@WmZF7Zm^fxIf6Yg3PbK&jA9hOebq)T3-St0Ih( z5@s*u-f@wfR?O4`+uEL``~VbgztEj>tQUXq=@m$v&cw7R*iGW#=ZuinVXUO-ZFvV z`CikP>>>IDnw2*mYk?GI-T)84k1or?Jh*>`%rluaeaT@e*N`3XQ;-*?s%;J&H*}h+ z21We$VA_7C8tx4!`W zw$%zm(Lw$d?56Ka1>`UJU3lBHs>WmQ5@sPp73Em_HP{=U!@M+ewJ#y>ass~_?{N6u zd7uf{6>q@&>N+IC*!Vp%i!|j6@2I|jSvkRdmSLRy963dlZ&CJL7$=|bdQkrh?z}|D z_zs!a;w5$ibM^0U?2N!jpp80h6{Kv$xGx}UR7n+Om;=76hIow1FrHEBf}+Dq={sbe z*DKJ=uz;JsoeImF1AQDyK6tzZ0QT_b{BJ+bU-}(W9Qu$~8VZ>A^8mEs0PGwb&!ALh ze(j$Wsi3SOe1*AlEdWhYQ&69OF(Kl~LI8RemgxR0L?Dm+9q2v{3WMs4k@0J3gIih| zr~GochpcgZ7sg3z9Gyjc%kl$Ea7X=ivq}Y)N9*{oe=o;;PLz4@1(cTXROzx}km9(9 zX9zyr^zFiO8Po4?jG~X(lNRdh5P7wOdWdS!*WQONrg8X z<#vyiYQ2E$!|q|4nJLPV+ARcREIJ%>FVvO`vaw>cW=PbrhIQiC8aft`5sSE^7l$iF$NM(AQ<8%z*96i%Pao?UppDEF83<~V3 z;gm>URZ-DD<{IYQ)Z8TPP+ z<#NvbcC&K6yw7R3a+huPz-mzmWfu5DPGS$wdrbG)ZX?4$!?%WwJsMKH#lBr&J`=JM zJys96zfEd5f$bj3!?{d(D`)CfjZ@G)cIvc-XoY>gl zcH7tM$TvnhZZv?q4FUh^aE$Hc(;Tm3`lLM0WtW2{W+arLN!WU1J*?33Lh&4_;i|2` zK^u*1H>;9YH!d*!xWqMp_ma!A6YSgPr`oqGnw&TMJl=qe;I$)_`cT5a=;7a1dQ<#R z?zfxO*_12E0x$Y#I<6*vNa4`%1v(nP95=KSZhLS%3_t9tq%xqo(>KC058<~Rz{bis z>~!We4$Mk<5|RqYZ>nGZf;}UlY&qN(YtYL-9jSfgMA>du>2|Yv51PytBdb%V#O}Gb z5(7K2zMTy?*AvymK0(_7+s&%r-{hYlPjF#br!K5Pzfo=?gvakQj8{Uq0KHe|u%R2k zpFVnlarY_|p!?Q20zisZayEq>!BvcN7$>)&`r-@pk4H=aeDAXC$L*c52VA0_d1tuo z8vr+4GW#RwdL?zpKxG-%YVgjM0ONUgjNm@FW&?f!Dgzq9UK*+#bg!O4D{ZBvb{cWi zw^LBxPG{J+y|EhR$w>-&&qSc-v3f2gDY>0zSpJQweKWiP>@(LHVte>WcRKmYrGk#L)(Kzj}OjQ{2U{s!HL?AXC3Ol75@ ziKc6J`AoCX7Z|qH_)H6p2ZhVYZ|%MWAl<9yy!yO}0=w0cXHdVi_Pk3n<-RS{FWM@V zRc(2&+%JZ}W1Ekczfbl5NA&RNIe zV}sCp#Ktoa;B_C3T29OOZvpC~nTc*~HtJAXjbBAk6h%=KML88r${Q<+q9}@@D9Wr* z<5y7>MNt$*c{8Z-t0;=1D2k%I8Pxby6h%=KMN!@i{||bl#Pk^xJAwcJ002ovPDHLk FV1jL625A5Q literal 0 HcmV?d00001 diff --git a/main/manager-web/src/assets/xiaozhi-ai_zh_CN.png b/main/manager-web/src/assets/xiaozhi-ai_zh_CN.png new file mode 100644 index 0000000000000000000000000000000000000000..ef3834afc08b6e3c1ffa652275e4a2d3d455facc GIT binary patch literal 1946 zcmV;L2W9w)P)#zkSF%Cpze@m{hjesxUwZlV>lX+i`SRb?Z-5XoEffJlGKV5S zNaj!k2+5rPZJzY<@-q7WLX}GZE6aOzOvD72z>LCd6yty+50}Y6D*Hgn6%00?-bv+6#+r3qASo zv49q(H=+0BjkgF4l#WbGi2##6fDkJN08Y@>M0AWP9wJzm?9DZIIGgxBtP53cr`}eD zI0hxZR6=61gWQ63YU-*oR*b|ocg8m}8D1h_tbi$2A3~fk6HIcF4SicT{Q?dgjMH)w ze76I%0z4Rr28666t3s8b*LZ5o_buUv>NyTQ`b}N6g(@rfJ6C&N0elpyR4M%=J$9OxeJ)ga zfF5Yakm9aFl{L~tDqOae&%{Te%6(H;QR;6(YX``KV!Y@5^0qdDu*V=4?ob<$%2|9w zo+1DMTl1T}Nrw8(gf+nQ)sV=E%1s0&#Uy_GX-Z=9 zFKnYNm)tc62ko@xAbgimAK%VICr|`7lCAojMBs7|k1=pMg@%mw(A{T7%}U1vq%0UT zdRZX6vdxu6p~@5|+2p<@c$e!z?ANnmqZl>^%VfW@1 z+9HtpK3eEO7qgr5qgw)(#b{TbcbWHZMEeW&0=tP>P3U3?bkHIo6=UwbysjauUKQt* z$#xgxsh27>{Rd+a0O3M#f=*3sP3B-Myb59h!i2WTOwkX?F`q#}i|oD6v5#3i1UQI* zamu|3IsaM!3MTsrZWCIWvdu?}4#Zr+T0mrL@Cm)@bc4TR!J`)xEph#~s&HOBMvtAF>=-h$5`Tv_JzWM{KLGx$iso82 zrcspeNMc%~8MGVN)z!Dq=H{sRYb=6qg4u>Qb3Z&-VjhW5u^2ktC61jN#mf>HQmFC= zo;!m}%=++Hp>6pmZTL1ky5>Y&SywKoKA$ zbEb9-eoJw}%8WuulG}ma(|>}tFnpVnkj$A{1g1LFVJbvLU~t0IGv{fL$V@E)Ss~nB zjL0C`s%wn7H-Di|fRN0g2uwtzMj(VZ!|gyKjOl-?Y}6Z@2C!G&(+d8LLms-KbHKqI z!Imu)fkc@4ao3ZbZz51i8{$x01v+)vICdsXEdsfP2qi_J!?dNep>+tKU%4lgy6A>r^>5=k*uo#JmKoLlc@rX-IV2S_{ zfg&&sp%eJT@EVbVA}|f1A`ta33X&HTfoTX40o&uR2(f}9@K_w7&u!pVfQTWHClInK zB}p9(Os|cR+++KhhbPc{rpT_$knBr|tqva{ggh_Y4iJ(#6ahjqhax~o=1>F($sCFR gA(=xFAS82s1LfGVwb@@<$p8QV07*qoM6N<$g5r986951J literal 0 HcmV?d00001 diff --git a/main/manager-web/src/assets/xiaozhi-ai_zh_TW.png b/main/manager-web/src/assets/xiaozhi-ai_zh_TW.png new file mode 100644 index 0000000000000000000000000000000000000000..ac5f59aa4905100f8da843a3cc178fa25956f55d GIT binary patch literal 1828 zcmV+<2iy3GP)^&2XIQ-V@LC;>`9C6E%7 zH@}h+a0$mHa33UtNt{Hsej>~3o5{>MkT@o>m$vrr-PhL_2qDYmpIe^*A>_7D1PEC; z6ahjO4n=^Fh4b(65AN>n2A^07xd!m)c-*$uN_m`D(Nsd-1CSG6eyFwDd%ph@fYsF3 z*IK>$ygvy?2*>`32wdO^z}E4(&lApNN!$Z?nfTgg0A3;hBj!^@r~y#C2vkBo0??j^ z5x#<*f-xd6=AwD2gq(Vj_u151sX$-IXlkv7&7usbgme|;A=VzRz4v_YU9DB)@p=G2 zCFCbOteHgUN=(&SCmH|`z6WsnzGKSid6H*jImcS#- z%`?Ul=x33Q*+Q%xvd>yf+gCMxfeDnsNJw#LT0oZEL&SCXr1>qG&5cc*tu2$g9 z9mlm+mwZaZ0gAwauwmc#fnRL_Y%3vK7(v)#X30pmDl$ts)Q_Mf=%pBKv^=`5(unpop-v+ z@>8`|ZJ=WphrQ|jlg0_bgqGu#klRYgzldYnbo=_&un6%;-u#o5k+kiD>pMs79ezq1dpoNzi=c))-FgN`Qx9=&?Z4qex8v31_ z8yJfq)MwKG_=C7fH^D4{fms-(x4K{3zZo!*p&*OnIZL30`EWzUl@Bn2GB!-r!d#TI z%3kYZzqF57$F~*%;4cIR0Do$&8k;#7i;!u)Yh>ziPrwF&EaX9-K&@3|^Z3B??GBiMa=EfNvjx&v&(h`K+7X|6>qr^&;W8=o7G+V0)M_;FLXL3v+R`01lOq zV#KkYy9>s~ZnGT(a*0~2)~>8ktr`1WtufAeYhXU-{8oZ(mtFB1yjt3f^ z8%PSwX7rN}SF`b^Pzm{tIC=XgX~S1?2!53e&z*(mOKfVbRO*4GWIC}dfpc>KkGCIt z{0uSedze$=Jxw_v*$fKJp#+*DkcL>^cGo zQnqE9_hjBBLlH;=v*bv&Pz2Jze0h>B6ahjOPD;n%LqBIA7MV702)P~TJpBh43u9_? zl45Y|ebH5@P6^d2nDFt{@6o=`JKU#m^$G6ub0MV&e9qV->q}4(=uLYnIcLL}1i~)? z$OPB#o2}U0q*yRJxE)A9tyNQNb=N&WZ+1|uD3+38`UtaNCad112#_MEwR%Qb4%nAU z$WLn-M1>-dm`II4h#~oYIx;H&@0E}`W}i)F3`WN8+dmMYiqOR&cIKRXQdOhWSA-zs zwjfYCuc)=!PiV;dir;>u#-7tUMiCYZh<+2RfanF`Iy61QLOp_vIMI zoY$Di-U