feat: add configurable vision focus prompts

backend/services/pipecat/pipeline.py

@@ -31,7 +31,6 @@ from services.input_assets import consume_input_image
 from services.client_tools import ClientToolBroker
 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_main_llm_as_vision,
@@ -39,6 +38,8 @@ from services.vision import (
     image_data_uri,
     image_frame_from_jpeg,
     image_jpeg_bytes,
+    vision_system_hint,
+    vision_tool_description,
 )
 from services.workflow_engine import WorkflowEngine
 
@@ -348,7 +349,7 @@ async def run_pipeline(
     def with_vision_hint(text: str) -> str:
         hints = []
         if vision_enabled and cfg.type != "workflow":
-            hints.append(VISION_SYSTEM_HINT)
+            hints.append(vision_system_hint(cfg.vision_focus_prompt))
         if cfg.knowledge_base_id:
             hints.append(
                 AUTOMATIC_KNOWLEDGE_SYSTEM_HINT
@@ -449,6 +450,7 @@ async def run_pipeline(
     workflow_vision_scope: dict[str, Any] = {
         "enabled": False,
         "vision_model_resource_id": None,
+        "vision_focus_prompt": "",
         "llm_resource_id": None,
     }
 
@@ -458,10 +460,7 @@ async def run_pipeline(
         return vision_native_mode
     vision_schema = FunctionSchema(
         name=VISION_TOOL_NAME,
-        description=(
-            "获取用户当前摄像头画面。当用户询问当前画面、看到了什么、"
-            "人/物品/环境状态或需要视觉判断时调用。"
-        ),
+        description=vision_tool_description(cfg.vision_focus_prompt),
         properties={
             "question": {
                 "type": "string",
@@ -572,10 +571,15 @@ async def run_pipeline(
         resource_id = vision_resource_id or llm_resource_id
         resource = cfg.workflow_model_resources.get(resource_id)
         if resource:
-            return config_with_vision_resource(cfg, resource)
-        if not vision_resource_id:
-            return config_with_main_llm_as_vision(cfg)
-        raise ValueError(f"视觉模型资源未加载:{vision_resource_id}")
+            result = config_with_vision_resource(cfg, resource)
+        elif not vision_resource_id:
+            result = config_with_main_llm_as_vision(cfg)
+        else:
+            raise ValueError(f"视觉模型资源未加载:{vision_resource_id}")
+        result.vision_focus_prompt = str(
+            workflow_vision_scope.get("vision_focus_prompt") or ""
+        ).strip()
+        return result
 
     if cfg.type == "workflow" and vision_enabled:
         async def native_flow_fetch_user_image(params: FunctionCallParams) -> None: