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.

src/llama_stack/apis/tools/tools.py

@@ -16,8 +16,6 @@ from llama_stack.apis.version import LLAMA_STACK_API_V1
 from llama_stack.core.telemetry.trace_protocol import trace_protocol
 from llama_stack.schema_utils import json_schema_type, webmethod
 
-from .rag_tool import RAGToolRuntime
-
 
 @json_schema_type
 class ToolDef(BaseModel):
@@ -195,8 +193,6 @@ class SpecialToolGroup(Enum):
 class ToolRuntime(Protocol):
     tool_store: ToolStore | None = None
 
-    rag_tool: RAGToolRuntime | None = None
-
     # TODO: This needs to be renamed once OPEN API generator name conflict issue is fixed.
     @webmethod(route="/tool-runtime/list-tools", method="GET", level=LLAMA_STACK_API_V1)
     async def list_runtime_tools(