feat: add configurable vision focus prompts

backend/services/workflow/agent.py

@@ -11,7 +11,7 @@ from pipecat.services.settings import LLMSettings
 
 from services.brains.base import BrainRuntime
 from services.runtime_variables import DynamicVariableStore
-from services.vision import VISION_SYSTEM_HINT
+from services.vision import vision_system_hint
 from services.workflow_engine import WorkflowEngine
 from services.workflow_router import WorkflowLLMRouter
 
@@ -47,7 +47,10 @@ class WorkflowAgentStage:
         stage_prompt = self._engine.prompt_for(node_id, self._store)
         stage = self._engine.agent_stage_config(node_id)
         if stage.vision_enabled:
-            stage_prompt = f"{stage_prompt}\n\n[视觉能力]\n{VISION_SYSTEM_HINT}"
+            stage_prompt = (
+                f"{stage_prompt}\n\n[视觉能力]\n"
+                f"{vision_system_hint(stage.vision_focus_prompt)}"
+            )
         instruction = (
             EDGE_TOOL_STAGE_INSTRUCTION
             if self._engine.llm_routing_mode() == "edge_tool"
@@ -109,6 +112,7 @@ class WorkflowAgentStage:
                 {
                     "enabled": stage.vision_enabled,
                     "vision_model_resource_id": stage.vision_model_resource_id,
+                    "vision_focus_prompt": stage.vision_focus_prompt,
                     "llm_resource_id": stage.llm_resource_id,
                 }
             )

backend/services/workflow/realtime.py

@@ -31,10 +31,11 @@ from services.system_tools import state_update_properties, system_tool_kind
 from services.tool_executor import ToolExecutionError, ToolExecutor
 from services.tool_policy import policy_for_tool
 from services.vision import (
-    VISION_SYSTEM_HINT,
     VISION_TOOL_NAME,
     analyze_image_with_vision_model,
     config_with_vision_resource,
+    vision_system_hint,
+    vision_tool_description,
 )
 from services.workflow.agent import EDGE_TOOL_STAGE_INSTRUCTION
 from services.workflow.models import WorkflowRuntimeState, WorkflowStatus
@@ -407,12 +408,13 @@ class WorkflowRealtimeController:
         return RealtimeActivation(continue_response=generate)
 
     def _agent_prompt(self, node_id: str) -> str:
+        stage = self._engine.agent_stage_config(node_id)
         prompt = (
             f"{self._engine.prompt_for(node_id, self._store)}\n\n"
             f"[工作流执行规则]\n{EDGE_TOOL_STAGE_INSTRUCTION}"
         )
-        if self._engine.agent_stage_config(node_id).vision_enabled:
-            prompt = f"{prompt}\n{VISION_SYSTEM_HINT}"
+        if stage.vision_enabled:
+            prompt = f"{prompt}\n{vision_system_hint(stage.vision_focus_prompt)}"
         return prompt
 
     def _build_agent_tools(self, node_id: str) -> list[RealtimeTool]:
@@ -603,6 +605,7 @@ 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,
@@ -634,7 +637,7 @@ class WorkflowRealtimeController:
         return (
             RealtimeTool(
                 name=VISION_TOOL_NAME,
-                description="获取用户摄像头的当前画面，并回答一个视觉问题。",
+                description=vision_tool_description(stage.vision_focus_prompt),
                 properties={
                     "question": {
                         "type": "string",