fix: support vision prompt modes

backend/models.py

@@ -13,6 +13,8 @@ from typing import Literal
 from pydantic import BaseModel, Field
 
 RuntimeMode = Literal["pipeline", "realtime"]
+VisionPromptMode = Literal["fixed", "runtime", "guided"]
+VISION_PROMPT_MODES = frozenset({"fixed", "runtime", "guided"})
 
 
 class RuntimeMcpServer(BaseModel):
@@ -92,7 +94,8 @@ class AssistantConfig(BaseModel):
     llm_support_image_input: bool = False
     vision_enabled: bool = False
     vision_model_resource_id: str | None = None
-    vision_focus_prompt: str = ""
+    vision_prompt_mode: VisionPromptMode = "runtime"
+    vision_prompt: str = ""
     vision_model: str = ""
     vision_llm_interface_type: str = "openai-llm"
     vision_llm_values: dict = {}