feat: support image inputs in assistant tests

backend/services/pipecat/pipeline.py

@@ -34,12 +34,11 @@ from services.tool_policy import policy_for_tool
 from services.vision import (
     VISION_TOOL_NAME,
     analyze_image_with_vision_model,
-    config_with_main_llm_as_vision,
-    config_with_vision_resource,
     image_data_uri,
     image_frame_from_jpeg,
     image_jpeg_bytes,
     resolve_vision_question,
+    resolve_vision_input,
     vision_system_hint,
     vision_tool_schema_parts,
 )
@@ -151,30 +150,6 @@ def _require(value: str, label: str) -> str:
     raise ValueError(f"缺少模型资源配置: {label}")
 
 
-def _vision_uses_main_llm(cfg: AssistantConfig) -> bool:
-    """模型自己支持图片时,沿用 Pipecat 的同上下文视觉工具路径。"""
-    return not cfg.vision_model_resource_id and cfg.llm_support_image_input
-
-
-def _workflow_vision_uses_main_llm(
-    cfg: AssistantConfig,
-    scope: dict[str, Any],
-) -> bool:
-    """Resolve native versus auxiliary vision for the active Workflow Agent."""
-    if not scope.get("enabled"):
-        raise ValueError("当前 Workflow Agent 节点未启用视觉能力")
-    if scope.get("vision_model_resource_id"):
-        return False
-
-    llm_resource_id = str(scope.get("llm_resource_id") or "")
-    resource = cfg.workflow_model_resources.get(llm_resource_id)
-    if not resource:
-        raise ValueError(f"当前 Workflow Agent 的 LLM 资源未加载:{llm_resource_id}")
-    if not resource.support_image_input:
-        raise ValueError("当前 Workflow Agent 的 LLM 不支持图片输入")
-    return True
-
-
 def _multimodal_user_input_frame(
     image_frame: UserImageRawFrame,
     prompt_text: str,
@@ -485,7 +460,7 @@ async def run_pipeline(
     vision_native_mode = (
         vision_enabled
         and cfg.type != "workflow"
-        and _vision_uses_main_llm(cfg)
+        and resolve_vision_input(cfg).native
     )
     vision_state: dict[str, str | None] = {"client_id": None}
     workflow_vision_scope: dict[str, Any] = {
@@ -497,9 +472,9 @@ async def run_pipeline(
     }
 
     def active_vision_uses_main_llm() -> bool:
-        if cfg.type == "workflow":
-            return _workflow_vision_uses_main_llm(cfg, workflow_vision_scope)
-        return vision_native_mode
+        if cfg.type != "workflow":
+            return vision_native_mode
+        return resolve_vision_input(cfg, workflow_vision_scope).native
     vision_description, vision_properties, vision_required = vision_tool_schema_parts(
         cfg.vision_prompt_mode,
         cfg.vision_prompt,
@@ -609,29 +584,8 @@ async def run_pipeline(
     workflow_vision_function = None
 
     def active_vision_config() -> AssistantConfig:
-        if cfg.type != "workflow":
-            return cfg
-        if not workflow_vision_scope.get("enabled"):
-            raise ValueError("当前 Workflow Agent 节点未启用视觉能力")
-        vision_resource_id = str(
-            workflow_vision_scope.get("vision_model_resource_id") or ""
-        )
-        llm_resource_id = str(workflow_vision_scope.get("llm_resource_id") or "")
-        resource_id = vision_resource_id or llm_resource_id
-        resource = cfg.workflow_model_resources.get(resource_id)
-        if resource:
-            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_prompt_mode = str(
-            workflow_vision_scope.get("vision_prompt_mode") or "runtime"
-        )
-        result.vision_prompt = str(
-            workflow_vision_scope.get("vision_prompt") or ""
-        ).strip()
-        return result
+        scope = workflow_vision_scope if cfg.type == "workflow" else None
+        return resolve_vision_input(cfg, scope).config
 
     if cfg.type == "workflow" and vision_enabled:
         async def native_flow_fetch_user_image(params: FunctionCallParams) -> None: