feat: add configurable vision focus prompts

backend/routes/assistants.py

@@ -2,7 +2,7 @@
 
 import uuid
 
-from models import RuntimeTool
+from models import RuntimeModelResource, RuntimeTool
 from db.models import (
     Assistant,
     AssistantModelBinding,
@@ -13,12 +13,18 @@ from db.models import (
 )
 from db.session import get_session
 from fastapi import APIRouter, Depends, HTTPException
-from schemas import AssistantOut, AssistantUpsert
+from schemas import (
+    AssistantOut,
+    AssistantUpsert,
+    VisionFocusPromptGenerateRequest,
+    VisionFocusPromptGenerateResult,
+)
 from services.auth import require_admin
 from services.masking import mask, resolve_incoming_key
 from services.node_specs import graph_references, normalize_graph, validate_graph
 from services.system_tools import system_tool_kind
 from services.tool_policy import policy_for_tool
+from services.vision import generate_vision_focus_prompt
 from services.workflow_engine import WorkflowEngine
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -73,6 +79,7 @@ def _validate_workflow(body: AssistantUpsert) -> None:
     # capability summary used by clients to decide whether to open the camera.
     body.vision_enabled = WorkflowEngine(body.graph).uses_vision()
     body.vision_model_resource_id = None
+    body.vision_focus_prompt = ""
     refs = graph_references(body.graph)
     body.tool_ids = list(dict.fromkeys([*body.tool_ids, *sorted(refs["tools"])]))
 
@@ -389,6 +396,7 @@ async def _to_out(session: AsyncSession, assistant: Assistant) -> AssistantOut:
         startup=assistant.startup or {},
         vision_enabled=assistant.vision_enabled,
         vision_model_resource_id=assistant.vision_model_resource_id,
+        vision_focus_prompt=assistant.vision_focus_prompt or "",
         model_resource_ids=await _resource_ids(session, assistant.id),
         knowledge_base_id=assistant.knowledge_base_id,
         knowledge_retrieval_config=assistant.knowledge_retrieval_config or {},
@@ -440,6 +448,43 @@ async def create_assistant(
     return await _to_out(session, assistant)
 
 
+@router.post(
+    "/vision-focus/generate",
+    response_model=VisionFocusPromptGenerateResult,
+)
+async def generate_assistant_vision_focus(
+    body: VisionFocusPromptGenerateRequest,
+    session: AsyncSession = Depends(get_session),
+):
+    """Generate an editable visual focus draft from an assistant prompt."""
+
+    resource = await session.get(ModelResource, body.model_resource_id)
+    if (
+        resource is None
+        or resource.capability != "LLM"
+        or not resource.enabled
+    ):
+        raise HTTPException(400, "请选择可用的大语言模型生成视觉关注目标")
+    try:
+        focus_prompt = await generate_vision_focus_prompt(
+            RuntimeModelResource(
+                id=resource.id,
+                name=resource.name,
+                capability=resource.capability,
+                interface_type=resource.interface_type,
+                values=resource.values or {},
+                secrets=resource.secrets or {},
+                support_image_input=bool(resource.support_image_input),
+            ),
+            body.source_prompt,
+        )
+    except ValueError as exc:
+        raise HTTPException(400, str(exc)) from exc
+    except Exception as exc:
+        raise HTTPException(502, "生成视觉关注目标失败，请稍后重试") from exc
+    return VisionFocusPromptGenerateResult(focus_prompt=focus_prompt)
+
+
 @router.get("/{assistant_id}", response_model=AssistantOut)
 async def get_assistant(
     assistant_id: str, session: AsyncSession = Depends(get_session)
@@ -468,6 +513,7 @@ async def duplicate_assistant(
         startup=dict(source.startup or {}),
         vision_enabled=source.vision_enabled,
         vision_model_resource_id=source.vision_model_resource_id,
+        vision_focus_prompt=source.vision_focus_prompt or "",
         knowledge_base_id=source.knowledge_base_id,
         knowledge_retrieval_config=dict(source.knowledge_retrieval_config or {}),
         prompt=source.prompt,