feat: show token usage per assistant response (#2270)

* feat: show token usage per assistant response

* fix: align client models response with token usage

* fix: address token usage review feedback

* docs: clarify token usage config example

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

frontend/src/core/models/hooks.ts

@@ -9,5 +9,10 @@ export function useModels({ enabled = true }: { enabled?: boolean } = {}) {
     enabled,
     refetchOnWindowFocus: false,
   });
-  return { models: data ?? [], isLoading, error };
+  return {
+    models: data?.models ?? [],
+    tokenUsageEnabled: data?.token_usage.enabled ?? false,
+    isLoading,
+    error,
+  };
 }