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/interface_catalog.py

@@ -138,13 +138,6 @@ INTERFACE_DEFINITIONS: list[dict] = [
             field("textAggregationMode", "Text Aggregation Mode", default="token"),
         ],
     },
-    {
-        "interface_type": "dashscope-llm",
-        "name": "DashScope LLM",
-        "capability": "LLM",
-        "fields": OPENAI_COMMON
-        + [field("temperature", "Temperature", type_="number", default=0.7)],
-    },
     {
         "interface_type": "dashscope-asr",
         "name": "DashScope ASR",
@@ -165,7 +158,6 @@ INTERFACE_DEFINITIONS: list[dict] = [
     },
 ]
 
-
 def validate_fields(definition: dict, values: dict, secrets: dict) -> None:
     for item in definition["fields"]:
         source = secrets if item["group"] == "secrets" else values