feat: refine token usage display modes (#2329)

* feat: refine token usage display modes

* docs: clarify token usage accounting semantics

* fix: avoid duplicate subtask debug keys

* style: format token usage tests

* chore: address token attribution review feedback

* Update test_token_usage_middleware.py

* Update test_token_usage_middleware.py

* chore: simplify token attribution fallback

* fix token usage metadata follow-up handling

---------

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

frontend/src/core/i18n/locales/zh-CN.ts

@@ -292,9 +292,31 @@ export const zhCN: Translations = {
     input: "输入",
     output: "输出",
     total: "总计",
+    view: "显示方式",
     unavailable:
       "暂无 Token 用量。只有模型成功返回且供应商提供 usage_metadata 时才会显示。",
     unavailableShort: "未返回用量",
+    note: "基于供应商返回的 usage_metadata 展示。当前总量是 best-effort 的会话参考值，可能与平台账单页不完全一致。",
+    presets: {
+      off: "关闭",
+      summary: "总览",
+      perTurn: "每轮",
+      debug: "调试",
+    },
+    presetDescriptions: {
+      off: "隐藏顶部和会话内的 token 展示。",
+      summary: "只在顶部显示当前对话累计 token。",
+      perTurn: "显示顶部累计，并为每轮 assistant 回复显示一条汇总 token。",
+      debug: "显示顶部累计，并展示按步骤归类的 token 调试信息。",
+    },
+    finalAnswer: "最终回复",
+    stepTotal: "步骤总计",
+    sharedAttribution: "该 token 由此步骤中的多个动作共同消耗",
+    subagent: (description: string) => `子任务：${description}`,
+    startTodo: (content: string) => `开始 To-do：${content}`,
+    completeTodo: (content: string) => `完成 To-do：${content}`,
+    updateTodo: (content: string) => `更新 To-do：${content}`,
+    removeTodo: (content: string) => `移除 To-do：${content}`,
   },
 
   // Shortcuts