fix: support vision prompt modes

backend/routes/assistants.py

@@ -2,7 +2,7 @@
 
 import uuid
 
-from models import RuntimeModelResource, RuntimeTool
+from models import VISION_PROMPT_MODES, RuntimeTool
 from db.models import (
     Assistant,
     AssistantModelBinding,
@@ -16,15 +16,12 @@ from fastapi import APIRouter, Depends, HTTPException
 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
@@ -79,7 +76,8 @@ 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 = ""
+    body.vision_prompt_mode = "runtime"
+    body.vision_prompt = ""
     refs = graph_references(body.graph)
     body.tool_ids = list(dict.fromkeys([*body.tool_ids, *sorted(refs["tools"])]))
 
@@ -271,6 +269,13 @@ async def _validate_vision_model(
     if body.type == "workflow":
         return
     if body.vision_enabled:
+        if body.vision_prompt_mode not in VISION_PROMPT_MODES:
+            raise HTTPException(400, "视觉提示词模式无效")
+        if (
+            body.vision_prompt_mode in {"fixed", "guided"}
+            and not body.vision_prompt.strip()
+        ):
+            raise HTTPException(400, "固定或引导模式必须填写视觉提示词")
         if body.vision_model_resource_id:
             resource = await session.get(ModelResource, body.vision_model_resource_id)
         else:
@@ -396,7 +401,8 @@ 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 "",
+        vision_prompt_mode=assistant.vision_prompt_mode or "runtime",
+        vision_prompt=assistant.vision_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 {},
@@ -448,43 +454,6 @@ 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)
@@ -513,7 +482,8 @@ 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 "",
+        vision_prompt_mode=source.vision_prompt_mode or "runtime",
+        vision_prompt=source.vision_prompt or "",
         knowledge_base_id=source.knowledge_base_id,
         knowledge_retrieval_config=dict(source.knowledge_retrieval_config or {}),
         prompt=source.prompt,