feat: add model_type field to backend /config and /list responses

Derive a single model_type string ("text" | "vision" | "audio" | "embeddings")
from existing is_vision and audio_type detection, so the frontend doesn't have
to infer modality from scattered boolean flags.

studio/backend/models/models.py

@@ -7,6 +7,8 @@ Pydantic schemas for Model Management API
 from pydantic import BaseModel, Field
 from typing import Optional, List, Dict, Any, Literal
 
+ModelType = Literal["text", "vision", "audio", "embeddings"]
+
 
 class CheckpointInfo(BaseModel):
     """Information about a discovered checkpoint directory."""
@@ -60,6 +62,7 @@ class ModelDetails(BaseModel):
     is_audio: bool = Field(False, description="Whether model is a TTS audio model")
     audio_type: Optional[str] = Field(None, description="Audio codec type: snac, csm, bicodec, dac")
     has_audio_input: bool = Field(False, description="Whether model accepts audio input (ASR)")
+    model_type: Optional[ModelType] = Field(None, description="Collapsed model modality: text, vision, audio, or embeddings")
     base_model: Optional[str] = Field(None, description="Base model if this is a LoRA adapter")
 
 

studio/backend/routes/models.py

@@ -60,12 +60,21 @@ from models import (
     LoRAInfo,
     ModelListResponse,
 )
-from models.models import GgufVariantDetail, GgufVariantsResponse
+from models.models import GgufVariantDetail, GgufVariantsResponse, ModelType
 from models.responses import LoRABaseModelResponse, VisionCheckResponse
 
 router = APIRouter()
 logger = logging.getLogger(__name__)
 
+
+def derive_model_type(is_vision: bool, audio_type: Optional[str]) -> ModelType:
+    """Collapse individual capability flags into a single model modality string."""
+    if audio_type is not None:
+        return "audio"
+    if is_vision:
+        return "vision"
+    return "text"
+
 # Configure logger
 if not logger.handlers:
     handler = logging.StreamHandler()
@@ -224,14 +233,17 @@ async def list_models(
         # Get loaded models
         loaded_models = []
         for model_name, model_data in inference_backend.models.items():
+            _is_vision = model_data.get("is_vision", False)
+            _audio_type = model_data.get("audio_type")
             model_info = ModelDetails(
                 id=model_name,
                 name=model_name.split("/")[-1] if "/" in model_name else model_name,
-                is_vision=model_data.get("is_vision", False),
+                is_vision=_is_vision,
                 is_lora=model_data.get("is_lora", False),
                 is_audio=model_data.get("is_audio", False),
-                audio_type=model_data.get("audio_type"),
+                audio_type=_audio_type,
                 has_audio_input=model_data.get("has_audio_input", False),
+                model_type=derive_model_type(_is_vision, _audio_type),
             )
             loaded_models.append(model_info)
         
@@ -309,6 +321,7 @@ async def get_model_config(
             is_audio=audio_type is not None,
             audio_type=audio_type,
             has_audio_input=is_audio_input_type(audio_type),
+            model_type=derive_model_type(is_vision, audio_type),
             base_model=base_model,
         )