chore(api)!: remove tool_runtime.rag_tool from the API surface (#4067)

RAG aka file search is implemented via the Responses API by specifying
the file-search tool. The backend implementation remains unchanged. This
PR merely removes the directly exposed API surface which allowed users
to directly perform searches from the client.

This facility is now available via the `client.vector_store.search()`
OpenAI compatible API.

docs/openapi_generator/pyopenapi/operations.py

@@ -170,7 +170,7 @@ def _get_endpoint_functions(
         for webmethod in webmethods:
             print(f"Processing {colored(func_name, 'white')}...")
             operation_name = func_name
-            
+
             if webmethod.method == "GET":
                 prefix = "get"
             elif webmethod.method == "DELETE":
@@ -196,16 +196,10 @@ def _get_endpoint_functions(
 def _get_defining_class(member_fn: str, derived_cls: type) -> type:
     "Find the class in which a member function is first defined in a class inheritance hierarchy."
 
-    # This import must be dynamic here
-    from llama_stack.apis.tools import RAGToolRuntime, ToolRuntime
-
     # iterate in reverse member resolution order to find most specific class first
     for cls in reversed(inspect.getmro(derived_cls)):
         for name, _ in inspect.getmembers(cls, inspect.isfunction):
             if name == member_fn:
-                # HACK ALERT
-                if cls == RAGToolRuntime:
-                    return ToolRuntime
                 return cls
 
     raise ValidationError(