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/i18n/locales/en-US.ts

@@ -298,9 +298,13 @@ export const enUS: Translations = {
   // Token Usage
   tokenUsage: {
     title: "Token Usage",
+    label: "Tokens",
     input: "Input",
     output: "Output",
     total: "Total",
+    unavailable:
+      "No token usage yet. Usage appears only after a successful model response when the provider returns usage_metadata.",
+    unavailableShort: "No usage returned",
   },
 
   // Shortcuts