fix: support vision prompt modes

backend/schemas.py

@@ -15,6 +15,7 @@ from pydantic import BaseModel, ConfigDict, Field, field_validator, model_valida
 from pydantic.alias_generators import to_camel
 
 RuntimeMode = Literal["pipeline", "realtime"]
+VisionPromptMode = Literal["fixed", "runtime", "guided"]
 ModelType = Literal["LLM", "ASR", "TTS", "Realtime", "Embedding", "Agent"]
 AssistantType = Literal["prompt", "workflow", "dify", "fastgpt", "opencode"]
 TurnEndStrategy = Literal["silence", "smart_turn"]
@@ -198,7 +199,8 @@ class AssistantUpsert(CamelModel):
     startup: StartupConfig = Field(default_factory=StartupConfig)
     vision_enabled: bool = False
     vision_model_resource_id: str | None = None
-    vision_focus_prompt: str = Field(default="", max_length=4000)
+    vision_prompt_mode: VisionPromptMode = "runtime"
+    vision_prompt: str = Field(default="", max_length=4000)
     model_resource_ids: dict[ModelType, str] = Field(default_factory=dict)
     knowledge_base_id: str | None = None
     knowledge_retrieval_config: KnowledgeRetrievalConfig = Field(
@@ -264,15 +266,6 @@ class AssistantOut(AssistantUpsert):
     updated_at: str | None = None
 
 
-class VisionFocusPromptGenerateRequest(CamelModel):
-    source_prompt: str = Field(min_length=1, max_length=20000)
-    model_resource_id: str = Field(min_length=1, max_length=40)
-
-
-class VisionFocusPromptGenerateResult(CamelModel):
-    focus_prompt: str
-
-
 class DynamicVariableDefinition(CamelModel):
     type: DynamicVariableType = "string"
     required: bool = False