大功告成

webrtc/gateway.py

@@ -3,21 +3,18 @@ from __future__ import annotations
 from aiortc import RTCPeerConnection
 from fastapi import FastAPI
 
-from config import settings
-from core.state_machine import Arbitrator
-from services.avatar import AvatarService
 from webrtc.audio_track import build_audio_track
 from webrtc.tracks import AudioBus
-from webrtc.video_track import build_video_track
 
 
 def attach_webrtc_tracks(
     pc: RTCPeerConnection,
-    avatar_service: AvatarService,
-    arbitrator: Arbitrator,
+    avatar_service,
+    arbitrator,
     audio_bus: AudioBus,
 ) -> None:
-    pc.addTrack(build_video_track(avatar_service, arbitrator, audio_bus, settings.avatar_fps))
+    _ = avatar_service
+    _ = arbitrator
     pc.addTrack(build_audio_track(audio_bus))
 
 

webrtc/tracks.py

@@ -6,10 +6,7 @@ from collections import deque
 
 import numpy as np
 from aiortc import MediaStreamTrack
-from av import AudioFrame, VideoFrame
-
-from core.state_machine import Arbitrator, SessionState
-from services.avatar import AvatarService
+from av import AudioFrame
 
 
 class AudioBus:
@@ -55,41 +52,6 @@ class AudioBus:
             self._level = 0.0
 
 
-class AvatarVideoTrack(MediaStreamTrack):
-    kind = "video"
-
-    def __init__(
-        self,
-        avatar_service: AvatarService,
-        arbitrator: Arbitrator,
-        audio_bus: AudioBus,
-        fps: int = 25,
-    ) -> None:
-        super().__init__()
-        self.avatar_service = avatar_service
-        self.arbitrator = arbitrator
-        self.audio_bus = audio_bus
-        self.fps = fps
-        self._pts = 0
-        self._time_base = Fraction(1, 90000)
-
-    async def recv(self) -> VideoFrame:
-        await asyncio.sleep(1 / self.fps)
-        generated = await self.avatar_service.pop_generated_frame()
-        if generated is not None:
-            arr = generated
-        else:
-            level = await self.audio_bus.level()
-            speaking = self.arbitrator.state == SessionState.AVATAR_SPEAKING or level > 0.02
-            arr = await self.avatar_service.render_frame(mouth_open=level, speaking=speaking)
-
-        frame = VideoFrame.from_ndarray(arr, format="bgr24")
-        frame.pts = self._pts
-        frame.time_base = self._time_base
-        self._pts += int(90000 / self.fps)
-        return frame
-
-
 class AvatarAudioTrack(MediaStreamTrack):
     kind = "audio"
 

webrtc/video_track.py

@@ -1,21 +1,7 @@
 from __future__ import annotations
 
-from core.state_machine import Arbitrator
-from services.avatar import AvatarService
-from webrtc.tracks import AudioBus, AvatarVideoTrack
-
-__all__ = ["AvatarVideoTrack", "build_video_track"]
+__all__: list[str] = []
 
 
-def build_video_track(
-    avatar_service: AvatarService,
-    arbitrator: Arbitrator,
-    audio_bus: AudioBus,
-    fps: int = 25,
-) -> AvatarVideoTrack:
-    return AvatarVideoTrack(
-        avatar_service=avatar_service,
-        arbitrator=arbitrator,
-        audio_bus=audio_bus,
-        fps=fps,
-    )
+def build_video_track(*_args, **_kwargs):
+    raise RuntimeError("Server-side video tracks are disabled in 3D avatar mode.")