feat: add realtime workflow vision tools

backend/services/pipecat/pipeline_events.py

@@ -230,6 +230,8 @@ def bind_realtime_pipeline_events(
     brain,
     text_input,
     greeting: str,
+    vision_enabled: bool,
+    vision_state: dict[str, str | None],
 ) -> None:
     """Connect text and lifecycle events for a realtime model pipeline."""
 
@@ -274,6 +276,19 @@ def bind_realtime_pipeline_events(
 
     @transport.event_handler("on_client_connected")
     async def on_client_connected(_transport, _client):
+        if vision_enabled:
+            try:
+                vision_state["client_id"] = get_transport_client_id(
+                    _transport,
+                    _client,
+                )
+                await maybe_capture_participant_camera(_transport, _client)
+                logger.info(
+                    f"Realtime 视觉理解已接入视频客户端: "
+                    f"{vision_state['client_id']}"
+                )
+            except Exception as exc:  # noqa: BLE001 - video remains optional
+                logger.warning(f"Realtime 视觉理解摄像头捕获初始化失败: {exc}")
         await brain.on_connected(greeting_pending=bool(greeting))
         await brain.on_client_ready()
         if greeting: