Add support for image input in model resources and enhance related configurations

- Introduce a new `support_image_input` field in model resources, allowing models to indicate support for image input.
- Update the backend models, schemas, and database seed scripts to accommodate the new field.
- Enhance the AssistantConfig and related routes to handle image input capabilities, ensuring proper validation and error handling.
- Modify the frontend components to include toggles for enabling visual understanding and filtering models based on image input support.
- Implement necessary adjustments in the voice preview and pipeline to integrate video stream handling alongside audio functionalities.

backend/services/config_resolver.py

@@ -86,6 +86,9 @@ async def resolve_runtime_config(
         realtimeModel=str(_value(realtime_resource, "modelId", "")),
         llm_values=(llm_resource.values or {}) if llm_resource else {},
         llm_secrets=(llm_resource.secrets or {}) if llm_resource else {},
+        llm_support_image_input=(
+            bool(llm_resource.support_image_input) if llm_resource else False
+        ),
         stt_values=(stt_resource.values or {}) if stt_resource else {},
         stt_secrets=(stt_resource.secrets or {}) if stt_resource else {},
         tts_values=(tts_resource.values or {}) if tts_resource else {},