fix: support vision prompt modes

backend/services/workflow/agent.py

@@ -49,7 +49,7 @@ class WorkflowAgentStage:
         if stage.vision_enabled:
             stage_prompt = (
                 f"{stage_prompt}\n\n[视觉能力]\n"
-                f"{vision_system_hint(stage.vision_focus_prompt)}"
+                f"{vision_system_hint(stage.vision_prompt_mode, stage.vision_prompt)}"
             )
         instruction = (
             EDGE_TOOL_STAGE_INSTRUCTION
@@ -112,7 +112,8 @@ class WorkflowAgentStage:
                 {
                     "enabled": stage.vision_enabled,
                     "vision_model_resource_id": stage.vision_model_resource_id,
-                    "vision_focus_prompt": stage.vision_focus_prompt,
+                    "vision_prompt_mode": stage.vision_prompt_mode,
+                    "vision_prompt": stage.vision_prompt,
                     "llm_resource_id": stage.llm_resource_id,
                 }
             )

backend/services/workflow/realtime.py

@@ -34,8 +34,9 @@ from services.vision import (
     VISION_TOOL_NAME,
     analyze_image_with_vision_model,
     config_with_vision_resource,
+    resolve_vision_question,
     vision_system_hint,
-    vision_tool_description,
+    vision_tool_schema_parts,
 )
 from services.workflow.agent import EDGE_TOOL_STAGE_INSTRUCTION
 from services.workflow.models import WorkflowRuntimeState, WorkflowStatus
@@ -414,7 +415,10 @@ class WorkflowRealtimeController:
             f"[工作流执行规则]\n{EDGE_TOOL_STAGE_INSTRUCTION}"
         )
         if stage.vision_enabled:
-            prompt = f"{prompt}\n{vision_system_hint(stage.vision_focus_prompt)}"
+            prompt = (
+                f"{prompt}\n"
+                f"{vision_system_hint(stage.vision_prompt_mode, stage.vision_prompt)}"
+            )
         return prompt
 
     def _build_agent_tools(self, node_id: str) -> list[RealtimeTool]:
@@ -573,10 +577,15 @@ class WorkflowRealtimeController:
                     {"status": "stale", "message": "当前 Agent 已经切换。"},
                     continue_response=False,
                 )
-            question = str(arguments.get("question") or "").strip()
-            if not question:
+            try:
+                question = resolve_vision_question(
+                    stage.vision_prompt_mode,
+                    stage.vision_prompt,
+                    arguments,
+                )
+            except ValueError as exc:
                 return RealtimeToolResult(
-                    {"status": "error", "message": "视觉问题为空"}
+                    {"status": "error", "message": str(exc)}
                 )
             if self._runtime.capture_image is None:
                 return RealtimeToolResult(
@@ -605,7 +614,6 @@ class WorkflowRealtimeController:
 
             try:
                 if vision_cfg is not None:
-                    vision_cfg.vision_focus_prompt = stage.vision_focus_prompt
                     observation = await analyze_image_with_vision_model(
                         vision_cfg,
                         frame,
@@ -634,17 +642,16 @@ class WorkflowRealtimeController:
                 }
             )
 
+        description, properties, required = vision_tool_schema_parts(
+            stage.vision_prompt_mode,
+            stage.vision_prompt,
+        )
         return (
             RealtimeTool(
                 name=VISION_TOOL_NAME,
-                description=vision_tool_description(stage.vision_focus_prompt),
-                properties={
-                    "question": {
-                        "type": "string",
-                        "description": "需要根据当前画面判断的具体问题",
-                    }
-                },
-                required=("question",),
+                description=description,
+                properties=properties,
+                required=tuple(required),
             ),
             handler,
         )