Merge branch 'main' into py-display

main/xiaozhi-server/core/connection.py

@@ -751,8 +751,8 @@ class ConnectionHandler:
         memory_type = self.config["Memory"][self.config["selected_module"]["Memory"]][
             "type"
         ]
-        # 如果使用 nomen，直接返回
-        if memory_type == "nomem":
+        # 如果使用 nomen 或 mem_report_only，直接返回
+        if memory_type == "nomem" or memory_type == "mem_report_only":
             return
         # 使用 mem_local_short 模式
         elif memory_type == "mem_local_short":

main/xiaozhi-server/core/handle/sendAudioHandle.py

@@ -280,6 +280,8 @@ async def send_tts_message(conn: "ConnectionHandler", state, text=None):
             await sendAudio(conn, audios)
         # 等待所有音频包发送完成
         await _wait_for_audio_completion(conn)
+        # 停止音频发送循环
+        conn.audio_rate_controller.stop_sending()
         # 清除服务端讲话状态
         conn.clearSpeakStatus()
 

main/xiaozhi-server/core/providers/memory/mem_report_only/mem_report_only.py

@@ -0,0 +1,20 @@
+"""
+仅上报聊天记录，不进行记忆总结
+"""
+
+from ..base import MemoryProviderBase, logger
+
+TAG = __name__
+
+
+class MemoryProvider(MemoryProviderBase):
+    def __init__(self, config, summary_memory=None):
+        super().__init__(config)
+
+    async def save_memory(self, msgs, session_id=None):
+        logger.bind(tag=TAG).debug("mem_report_only mode: No memory saving or summarization is performed.")
+        return None
+
+    async def query_memory(self, query: str) -> str:
+        logger.bind(tag=TAG).debug("mem_report_only mode: No memory query is performed.")
+        return ""

main/xiaozhi-server/core/utils/audioRateController.py

@@ -27,6 +27,7 @@ class AudioRateController:
         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
+        self._last_queue_empty_time = 0  # 上次队列清空的时间（秒）
 
     def reset(self):
         """重置控制器状态"""
@@ -37,12 +38,25 @@ class AudioRateController:
         self.queue.clear()
         self.play_position = 0
         self.start_timestamp = None  # 由首个音频包设置
+        self._last_queue_empty_time = 0  # 重置时间
         # 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"""
+        # 如果队列之前为空，需要调整时间戳以保持播放时间连续
+        # 这样工具调用等待期间，新加入的音频不会提前播放
+        # 如果间隔很短（<1帧），说明是正常的流式传输，不需要重置
+        if len(self.queue) == 0 and self.play_position > 0:
+            elapsed_since_empty = (time.monotonic() - self._last_queue_empty_time) * 1000
+            # 只有间隔超过1帧时长，才认为是真正的"暂停恢复"
+            if elapsed_since_empty >= self.frame_duration:
+                self.start_timestamp = time.monotonic() - (self.play_position / 1000)
+                self.logger.bind(tag=TAG).debug(
+                    f"队列从空恢复，重置时间戳，当前播放位置: {self.play_position}ms，间隔: {elapsed_since_empty:.0f}ms"
+                )
+
         self.queue.append(("audio", opus_packet))
         # 相关事件处理
         self.queue_empty_event.clear()
@@ -55,6 +69,14 @@ class AudioRateController:
         Args:
             message_callback: 消息发送回调函数 async def()
         """
+        if len(self.queue) == 0 and self.play_position > 0:
+            elapsed_since_empty = (time.monotonic() - self._last_queue_empty_time) * 1000
+            if elapsed_since_empty >= self.frame_duration:
+                self.start_timestamp = time.monotonic() - (self.play_position / 1000)
+                self.logger.bind(tag=TAG).debug(
+                    f"队列从空恢复，重置时间戳，当前播放位置: {self.play_position}ms，间隔: {elapsed_since_empty:.0f}ms"
+                )
+
         self.queue.append(("message", message_callback))
         # 相关事件处理
         self.queue_empty_event.clear()
@@ -126,6 +148,7 @@ class AudioRateController:
         # 队列处理完后清除事件
         self.queue_empty_event.set()
         self.queue_has_data_event.clear()
+        self._last_queue_empty_time = time.monotonic()  # 记录队列清空时间
 
     def start_sending(self, send_audio_callback):
         """

main/xiaozhi-server/requirements.txt

@@ -26,7 +26,7 @@ mem0ai==1.0.0
 powermem>=0.3.1
 bs4==0.0.2
 modelscope==1.32.0
-sherpa_onnx==1.12.17
+sherpa_onnx==1.12.29
 mcp==1.22.0
 cnlunar==0.2.0
 PySocks==1.7.1

main/xiaozhi-server/test/js/app.js

@@ -192,7 +192,7 @@ class App {
                     }
                     log('正在请求摄像头权限...', 'info');
                     this.cameraStream = await navigator.mediaDevices.getUserMedia({
-                        video: { width: 320, height: 240, facingMode: this.currentFacingMode },
+                        video: { width: 180, height: 240, facingMode: this.currentFacingMode },
                         audio: false
                     });
                     cameraVideo.srcObject = this.cameraStream;
@@ -274,7 +274,7 @@ class App {
                         return;
                     }
 
-                    canvas.width = video.videoWidth || 320;
+                    canvas.width = video.videoWidth || 180;
                     canvas.height = video.videoHeight || 240;
                     const ctx = canvas.getContext('2d');
                     ctx.drawImage(video, 0, 0, canvas.width, canvas.height);