fix(workflow): track fixed speech at transport output

backend/services/pipecat/transports.py

@@ -14,15 +14,67 @@ from pipecat.transports.base_transport import TransportParams
 
 # WebRTC
 from pipecat.transports.smallwebrtc.connection import SmallWebRTCConnection
-from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
+from pipecat.transports.smallwebrtc.transport import (
+    SmallWebRTCOutputTransport,
+    SmallWebRTCTransport,
+)
 
 # 裸 WS 音频流
 from pipecat.transports.websocket.fastapi import (
+    FastAPIWebsocketOutputTransport,
     FastAPIWebsocketTransport,
     FastAPIWebsocketParams,
 )
 from pipecat.serializers.protobuf import ProtobufFrameSerializer
 
+from services.pipecat.call_lifecycle import FixedSpeechPlaybackMarkerFrame
+
+
+class _PlaybackMarkerOutputMixin:
+    """Resolve fixed-speech markers after preceding audio has been sent."""
+
+    async def write_transport_frame(self, frame):
+        if isinstance(frame, FixedSpeechPlaybackMarkerFrame):
+            await frame.completion.mark_played()
+            return
+        await super().write_transport_frame(frame)
+
+
+class _WebRTCOutputTransport(
+    _PlaybackMarkerOutputMixin,
+    SmallWebRTCOutputTransport,
+):
+    pass
+
+
+class _WebRTCTransport(SmallWebRTCTransport):
+    def output(self) -> SmallWebRTCOutputTransport:
+        if not self._output:
+            self._output = _WebRTCOutputTransport(
+                self._client,
+                self._params,
+                name=self._input_name,
+            )
+        return self._output
+
+
+class _WebsocketOutputTransport(
+    _PlaybackMarkerOutputMixin,
+    FastAPIWebsocketOutputTransport,
+):
+    pass
+
+
+class _WebsocketTransport(FastAPIWebsocketTransport):
+    def __init__(self, websocket: WebSocket, params: FastAPIWebsocketParams):
+        super().__init__(websocket=websocket, params=params)
+        self._output = _WebsocketOutputTransport(
+            self,
+            self._client,
+            self._params,
+            name=self._output_name,
+        )
+
 
 def _base_params(*, video_in_enabled: bool = False) -> dict:
     """两种 transport 共享的音频参数。"""
@@ -41,7 +93,7 @@ def build_webrtc_transport(
     *,
     video_in_enabled: bool = False,
 ) -> SmallWebRTCTransport:
-    return SmallWebRTCTransport(
+    return _WebRTCTransport(
         webrtc_connection=connection,
         params=TransportParams(**_base_params(video_in_enabled=video_in_enabled)),
     )
@@ -51,7 +103,7 @@ def build_ws_transport(websocket: WebSocket) -> FastAPIWebsocketTransport:
     """裸 WS 输出。序列化用 protobuf(自定义客户端用同款解码);
     若对接电话商,把 serializer 换成对应的 TwilioFrameSerializer 等即可。
     """
-    return FastAPIWebsocketTransport(
+    return _WebsocketTransport(
         websocket=websocket,
         params=FastAPIWebsocketParams(
             serializer=ProtobufFrameSerializer(),