From 6a17855e17b847f00de02b707f0e111d3e1b03d1 Mon Sep 17 00:00:00 2001 From: Xin Wang Date: Wed, 8 Jul 2026 12:40:14 +0800 Subject: [PATCH] Refactor vision model configuration handling in voice_webrtc.py - Update vision model authorization logic to rely solely on server-side configuration, removing client offer dependency for vision capabilities. - Enhance clarity in comments regarding the role of server configurations in enabling vision understanding. --- backend/routes/voice_webrtc.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/backend/routes/voice_webrtc.py b/backend/routes/voice_webrtc.py index 45d72c0..61ee9b8 100644 --- a/backend/routes/voice_webrtc.py +++ b/backend/routes/voice_webrtc.py @@ -87,7 +87,8 @@ async def _handle_offer(websocket, payload, peers): await pc.renegotiate(sdp=offer.sdp, type=offer.type, restart_pc=False) else: cfg = await _resolve_config(offer) # 解析放在建连前,配置错就别建连 - vision_enabled = offer.vision_enabled or cfg.vision_enabled + # 服务端助手配置是视觉理解的唯一授权来源；客户端 offer 只负责携带媒体轨。 + vision_enabled = cfg.vision_enabled if vision_enabled: has_native_vision = ( not cfg.vision_model_resource_id and cfg.llm_support_image_input