feat: 会话标签页显示实时 Token 输出速度

src/components/chat/message-input.tsx

@@ -127,6 +127,7 @@ import {
 } from "@/components/chat/conversation-context-bar"
 import { ComposerContextUsage } from "@/components/chat/composer-context-usage"
 import { ComposerConnectionStatus } from "@/components/chat/composer-connection-status"
+import { TokenOutputSpeed } from "@/components/chat/token-output-speed"
 import { InlineModeSelector } from "@/components/chat/mode-selector"
 import { InlineSessionConfigSelector } from "@/components/chat/session-config-selector"
 import { ModelOptionPicker } from "@/components/chat/model-option-picker"
@@ -3872,6 +3873,7 @@ export function MessageInput({
                 send button's right edge in the action bar above — no centring
                 slot, which would inset the narrow icon and break the alignment. */}
             <div className="flex shrink-0 items-center gap-3 pr-px">
+              <TokenOutputSpeed tabId={attachmentTabId ?? null} />
               <ComposerContextUsage tabId={attachmentTabId ?? null} />
               <ComposerConnectionStatus tabId={attachmentTabId ?? null} />
             </div>

src/components/chat/token-output-speed.test.tsx

@@ -0,0 +1,128 @@
+import { act, render, screen } from "@testing-library/react"
+import { NextIntlClientProvider } from "next-intl"
+import { afterEach, describe, expect, it, vi } from "vitest"
+
+import { TokenOutputSpeed } from "./token-output-speed"
+import enMessages from "@/i18n/messages/en.json"
+import type {
+  ConnectionState,
+  LiveContentBlock,
+} from "@/contexts/acp-connections-context"
+
+const mock = vi.hoisted(() => {
+  const state: {
+    conn: ConnectionState | undefined
+    listener: (() => void) | null
+  } = {
+    conn: undefined,
+    listener: null,
+  }
+  return {
+    subscribeKey: (_key: string, cb: () => void) => {
+      state.listener = cb
+      return () => {
+        if (state.listener === cb) state.listener = null
+      }
+    },
+    getConnection: () => state.conn,
+    emit: () => state.listener?.(),
+    setConn: (conn: ConnectionState | undefined) => {
+      state.conn = conn
+    },
+  }
+})
+
+vi.mock("@/contexts/acp-connections-context", () => ({
+  useConnectionStore: () => ({
+    subscribeKey: mock.subscribeKey,
+    getConnection: mock.getConnection,
+  }),
+}))
+
+function conn(blocks: LiveContentBlock[]): ConnectionState {
+  return {
+    connectionId: "c1",
+    contextKey: "tab1",
+    agentType: "codex",
+    workingDir: null,
+    status: "prompting",
+    liveMessage: {
+      id: "live-1",
+      role: "assistant",
+      content: blocks,
+      startedAt: 0,
+    },
+  } as unknown as ConnectionState
+}
+
+function renderBadge() {
+  return render(
+    <NextIntlClientProvider messages={enMessages} locale="en">
+      <TokenOutputSpeed tabId="tab1" />
+    </NextIntlClientProvider>
+  )
+}
+
+let fakeNow = 0
+
+afterEach(() => {
+  vi.restoreAllMocks()
+  fakeNow = 0
+})
+
+describe("TokenOutputSpeed", () => {
+  it("shows an estimated tok/s while prompting", () => {
+    fakeNow = 1000
+    vi.spyOn(performance, "now").mockImplementation(() => fakeNow)
+    mock.setConn(conn([{ type: "text", text: "a".repeat(80) }]))
+    renderBadge()
+    expect(screen.queryByText(/\d+\.\d tok\/s/)).toBeNull()
+
+    fakeNow = 2000
+    mock.setConn(conn([{ type: "text", text: "a".repeat(480) }]))
+    act(() => mock.emit())
+    expect(screen.getByText(/100\.0 tok\/s/)).toBeTruthy()
+  })
+
+  it("counts thinking blocks and skips sub-agent blocks", () => {
+    fakeNow = 1000
+    vi.spyOn(performance, "now").mockImplementation(() => fakeNow)
+    mock.setConn(
+      conn([
+        { type: "text", text: "a".repeat(80) },
+        { type: "thinking", text: "a".repeat(80) },
+        { type: "text", text: "a".repeat(800), parentToolUseId: "pt-1" },
+      ])
+    )
+    renderBadge()
+
+    fakeNow = 2000
+    mock.setConn(
+      conn([
+        { type: "text", text: "a".repeat(160) },
+        { type: "thinking", text: "a".repeat(160) },
+        { type: "text", text: "a".repeat(900), parentToolUseId: "pt-1" },
+      ])
+    )
+    act(() => mock.emit())
+    // 160 visible root chars → 40 tokens in the second second (plus the
+    // first second's 40 seeded as baseline): expect 40.0 tok/s.
+    expect(screen.getByText(/40\.0 tok\/s/)).toBeTruthy()
+  })
+
+  it("hides when the connection is not prompting", () => {
+    const idle = conn([])
+    idle.status = "connected"
+    mock.setConn(idle)
+    renderBadge()
+    expect(screen.queryByText(/\d+\.\d tok\/s/)).toBeNull()
+  })
+
+  it("hides when there is no live message", () => {
+    const noLive = conn([])
+    noLive.liveMessage = null
+    mock.setConn(noLive)
+    renderBadge()
+    expect(screen.queryByText(/\d+\.\d tok\/s/)).toBeNull()
+  })
+})

src/components/chat/token-output-speed.tsx

@@ -0,0 +1,97 @@
+"use client"
+
+import { useEffect, useRef, useState } from "react"
+import { Zap } from "lucide-react"
+import { useTranslations } from "next-intl"
+import { useConnectionStore } from "@/contexts/acp-connections-context"
+import { estimateTokens, TokenSpeedTracker } from "@/lib/token-speed"
+
+const THROTTLE_MS = 500
+const MAX_TPS = 999.9
+
+/**
+ * Live token-output-speed badge for one conversation tab, rendered in the
+ * status row below the composer (before the context-window circle). Shows only
+ * while the tab's agent is prompting; the reading is a local estimate from the
+ * streamed `text` + `thinking` blocks (root agent only, no sub-agent content).
+ * ponytail: root-agent only; give sub-agent cards their own badge if cross-
+ * agent delegation speed becomes something users ask about.
+ */
+export function TokenOutputSpeed({ tabId }: { tabId: string | null }) {
+  const t = useTranslations("Folder.statusBar.tokens")
+  const store = useConnectionStore()
+  const [tps, setTps] = useState<number | null>(null)
+  const lastRenderRef = useRef(0)
+
+  useEffect(() => {
+    if (!tabId) return
+    const tracker = new TokenSpeedTracker()
+    lastRenderRef.current = 0
+
+    // Mid-turn attach (refresh / reconnect): seed the baseline from whatever
+    // has already streamed so the first delta after mount measures a real
+    // rate instead of the whole accumulated text.
+    const conn = store.getConnection(tabId)
+    const content =
+      conn?.status === "prompting" && conn.liveMessage
+        ? conn.liveMessage.content
+        : null
+    if (content && content.length > 0) {
+      let total = 0
+      for (const block of content) {
+        if (
+          (block.type === "text" || block.type === "thinking") &&
+          block.parentToolUseId == null
+        ) {
+          total += estimateTokens(block.text)
+        }
+      }
+      tracker.observe(total, performance.now())
+    }
+
+    return store.subscribeKey(tabId, () => {
+      const next = store.getConnection(tabId)
+      const nextContent =
+        next?.status === "prompting" && next.liveMessage
+          ? next.liveMessage.content
+          : null
+      // Turn ended, or a fresh turn started with empty content (STATUS_CHANGED
+      // to prompting rebuilds liveMessage) — reset the baseline and hide.
+      if (!nextContent || nextContent.length === 0) {
+        tracker.reset()
+        lastRenderRef.current = 0
+        setTps(null)
+        return
+      }
+      let total = 0
+      for (const block of nextContent) {
+        if (
+          (block.type === "text" || block.type === "thinking") &&
+          block.parentToolUseId == null
+        ) {
+          total += estimateTokens(block.text)
+        }
+      }
+      const now = performance.now()
+      const rate = tracker.observe(total, now)
+      if (rate == null) return
+      if (now - lastRenderRef.current >= THROTTLE_MS) {
+        lastRenderRef.current = now
+        setTps(Math.min(Math.max(rate, 0), MAX_TPS))
+      }
+    })
+  }, [store, tabId])
+
+  if (tps == null) return null
+
+  return (
+    <span
+      aria-label={t("outputSpeedAria")}
+      className="flex items-center gap-1"
+      title={t("outputSpeedTooltip")}
+    >
+      <Zap className="size-3.5" />
+      {tps.toFixed(1)} tok/s
+    </span>
+  )
+}

src/i18n/messages/ar.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "استخدام نافذة السياق",
         "contextWindow": "نافذة السياق",
+        "outputSpeedAria": "السرعة التقديرية للإخراج",
+        "outputSpeedTooltip": "السرعة التقديرية للإخراج (نص + تفكير)",
         "usedMax": "المستخدم / الحد الأقصى",
         "tokenUsage": "استخدام الرموز",
         "input": "إدخال",

src/i18n/messages/de.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "Kontextfenster-Nutzung",
         "contextWindow": "Kontextfenster",
+        "outputSpeedAria": "Geschätzte Ausgabegeschwindigkeit",
+        "outputSpeedTooltip": "Geschätzte Ausgabegeschwindigkeit (Text + Denken)",
         "usedMax": "Verwendet / Max",
         "tokenUsage": "Token-Nutzung",
         "input": "Eingabe",

src/i18n/messages/en.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "Context window usage",
         "contextWindow": "Context Window",
+        "outputSpeedAria": "Estimated output speed",
+        "outputSpeedTooltip": "Estimated output speed (text + thinking)",
         "usedMax": "Used / Max",
         "tokenUsage": "Token Usage",
         "input": "Input",

src/i18n/messages/es.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "Uso de la ventana de contexto",
         "contextWindow": "Ventana de contexto",
+        "outputSpeedAria": "Velocidad de salida estimada",
+        "outputSpeedTooltip": "Velocidad de salida estimada (texto + razonamiento)",
         "usedMax": "Usado / Máx",
         "tokenUsage": "Uso de tokens",
         "input": "Entrada",

src/i18n/messages/fr.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "Utilisation de la fenêtre de contexte",
         "contextWindow": "Fenêtre de contexte",
+        "outputSpeedAria": "Vitesse de sortie estimée",
+        "outputSpeedTooltip": "Vitesse de sortie estimée (texte + raisonnement)",
         "usedMax": "Utilisé / Max",
         "tokenUsage": "Utilisation des tokens",
         "input": "Entrée",

src/i18n/messages/ja.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "コンテキストウィンドウ使用率",
         "contextWindow": "コンテキストウィンドウ",
+        "outputSpeedAria": "推定出力速度",
+        "outputSpeedTooltip": "推定出力速度（テキスト + 思考）",
         "usedMax": "使用 / 最大",
         "tokenUsage": "トークン使用量",
         "input": "入力",

src/i18n/messages/ko.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "컨텍스트 윈도우 사용량",
         "contextWindow": "컨텍스트 윈도우",
+        "outputSpeedAria": "예상 출력 속도",
+        "outputSpeedTooltip": "예상 출력 속도（텍스트 + 추론）",
         "usedMax": "사용 / 최대",
         "tokenUsage": "토큰 사용량",
         "input": "입력",

src/i18n/messages/pt.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "Uso da janela de contexto",
         "contextWindow": "Janela de contexto",
+        "outputSpeedAria": "Velocidade de saída estimada",
+        "outputSpeedTooltip": "Velocidade de saída estimada (texto + raciocínio)",
         "usedMax": "Usado / Máx",
         "tokenUsage": "Uso de tokens",
         "input": "Entrada",

src/i18n/messages/zh-CN.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "上下文窗口使用率",
         "contextWindow": "上下文窗口",
+        "outputSpeedAria": "估算输出速度",
+        "outputSpeedTooltip": "估算输出速度（正文 + 思考）",
         "usedMax": "已用 / 上限",
         "tokenUsage": "Token 用量",
         "input": "输入",

src/i18n/messages/zh-TW.json

@@ -1713,6 +1713,8 @@
       "tokens": {
         "contextWindowUsageAria": "上下文視窗使用率",
         "contextWindow": "上下文視窗",
+        "outputSpeedAria": "估算輸出速度",
+        "outputSpeedTooltip": "估算輸出速度（正文 + 思考）",
         "usedMax": "已用 / 上限",
         "tokenUsage": "Token 用量",
         "input": "輸入",