Merge remote-tracking branch 'origin/master' into worktree/locale-browser-default

packages/client/connection/src/client/fixture.ts

@@ -15,6 +15,7 @@ import type {
   AssistantMessage,
   ContentBlock,
   MessageSource,
+  TokenUsage,
   ToolResultMessage,
   UserMessage,
 } from '@deepseek-ai/dsh-llm'
@@ -327,6 +328,16 @@ function sid(id: string): SessionId {
   return id as SessionId
 }
 
+/** Deterministic provider billing attached to fixture assistant messages. */
+function fixtureUsage(turn: number, step: number): TokenUsage {
+  return {
+    inputTokens: 20 + turn % 5,
+    outputTokens: 8 + step,
+    cacheReadTokens: turn === 0 ? 0 : 80,
+    cacheWriteTokens: turn % 10 === 0 ? 4 : 0,
+  }
+}
+
 /** fx-alpha history script: 60 turns (~130+ messages -> 3 pages at PAGE_MESSAGES=50),
  *  mixing reasoning blocks / tool call+result / steering / context. */
 function buildAlphaLog(): SessionEvent[] {
@@ -334,7 +345,17 @@ function buildAlphaLog(): SessionEvent[] {
   let time = Date.now() - 3_600_000
   const push = (e: Record<string, unknown>): number => {
     const seq = events.length
-    events.push({ seq, time: (time += 800), ...e })
+    const data = e['data'] as Record<string, unknown> | undefined
+    const authored = e['type'] === 'assistant/message' && data !== undefined
+      ? {
+        ...e,
+        data: {
+          ...data,
+          usage: fixtureUsage(data['turn'] as number, data['step'] as number),
+        },
+      }
+      : e
+    events.push({ seq, time: (time += 800), ...authored })
     return seq
   }
   for (let turn = 0; turn < 60; turn++) {
@@ -727,6 +748,113 @@ function permissionSelectOf(
   }
 }
 
+interface FixtureTokenUsageProjection {
+  uncachedInputTokens: number
+  outputTokens: number
+  cacheReadTokens: number
+  cacheWriteTokens: number
+}
+
+interface FixtureUsageSample {
+  turn: number
+  step: number
+  usage: TokenUsage
+}
+
+/** Read one provider usage sample from either durable carrier. */
+function usageSampleOf(event: SessionEvent): FixtureUsageSample | undefined {
+  const item = event as unknown as {
+    type: string
+    data: {
+      turn?: number
+      step?: number
+      usage?: TokenUsage
+      chunk?: { type?: string; usage?: TokenUsage }
+    }
+  }
+  const usage = item.type === 'assistant/chunk' && item.data.chunk?.type === 'usage'
+    ? item.data.chunk.usage
+    : item.type === 'assistant/message'
+      ? item.data.usage
+      : undefined
+  return usage === undefined || item.data.turn === undefined || item.data.step === undefined
+    ? undefined
+    : { turn: item.data.turn, step: item.data.step, usage }
+}
+
+/** Fixture parallel of token-meter's last-sample-replacing usage projection. */
+function tokenUsageOf(log: readonly SessionEvent[]): FixtureTokenUsageProjection {
+  const totals: FixtureTokenUsageProjection = {
+    uncachedInputTokens: 0,
+    outputTokens: 0,
+    cacheReadTokens: 0,
+    cacheWriteTokens: 0,
+  }
+  let last: {
+    turn: number
+    step: number
+    buckets: FixtureTokenUsageProjection
+  } | null = null
+  for (const event of log) {
+    const sample = usageSampleOf(event)
+    if (sample === undefined) continue
+    const buckets: FixtureTokenUsageProjection = {
+      uncachedInputTokens: sample.usage.inputTokens,
+      outputTokens: sample.usage.outputTokens,
+      cacheReadTokens: sample.usage.cacheReadTokens ?? 0,
+      cacheWriteTokens: sample.usage.cacheWriteTokens ?? 0,
+    }
+    const previous = last?.turn === sample.turn && last.step === sample.step
+      ? last.buckets
+      : undefined
+    totals.uncachedInputTokens += buckets.uncachedInputTokens - (previous?.uncachedInputTokens ?? 0)
+    totals.outputTokens += buckets.outputTokens - (previous?.outputTokens ?? 0)
+    totals.cacheReadTokens += buckets.cacheReadTokens - (previous?.cacheReadTokens ?? 0)
+    totals.cacheWriteTokens += buckets.cacheWriteTokens - (previous?.cacheWriteTokens ?? 0)
+    last = { turn: sample.turn, step: sample.step, buckets }
+  }
+  return totals
+}
+
+interface FixtureRequestContext {
+  provider: string
+  model: string
+  contextWindow?: number
+}
+
+/** Latest log-only route context, or undefined before any request ran. */
+function lastRequestContext(
+  log: readonly SessionEvent[],
+): FixtureRequestContext | undefined {
+  const event = log.findLast(item => (item as { type: string }).type === 'request/context')
+  return event === undefined
+    ? undefined
+    : (event as unknown as { data: FixtureRequestContext }).data
+}
+
+/**
+ * Fixture parallel of token-meter's request-pressure projection: the last
+ * provider-reported prompt size paired with the last recorded capacity. The
+ * two need not come from one request — see the token-meter README.
+ */
+function contextPressureOf(
+  log: readonly SessionEvent[],
+): { pressureTokens?: number; contextWindow?: number } {
+  let pressureTokens: number | undefined
+  for (const event of log) {
+    const sample = usageSampleOf(event)
+    if (sample === undefined) continue
+    pressureTokens = sample.usage.inputTokens
+      + (sample.usage.cacheReadTokens ?? 0)
+      + (sample.usage.cacheWriteTokens ?? 0)
+  }
+  const contextWindow = lastRequestContext(log)?.contextWindow
+  return {
+    ...pressureTokens === undefined ? {} : { pressureTokens },
+    ...contextWindow === undefined ? {} : { contextWindow },
+  }
+}
+
 function projectionValuesOf(log: readonly SessionEvent[]): Record<string, unknown> {
   const values: Record<string, unknown> = {}
   const titleEvent = log.findLast(item => (item as { type: string }).type === 'session/title')
@@ -741,12 +869,32 @@ function projectionValuesOf(log: readonly SessionEvent[]): Record<string, unknow
   values['plan'] = planViewOf(log)
   // Always present (GoalService unit composed): null before create / after clear.
   values['goal'] = backscanGoal(log)
+  // Always present (token-meter composed): full-log provider billing.
+  values['tokenUsage'] = tokenUsageOf(log)
+  // Always present (token-meter composed): last request pressure and capacity.
+  values['contextPressure'] = contextPressureOf(log)
   return values
 }
 
 /** Host push-frame parallel: emit one session/projection frame per key the given event advanced. */
 function projectionFramesOf(id: SessionId, log: readonly SessionEvent[], event: SessionEvent): Extract<MuxFrame, { type: 'session/projection' }>[] {
   const type = (event as { type: string }).type
+  // One usage sample advances both token-meter units.
+  if (usageSampleOf(event) !== undefined) {
+    return [
+      { type: 'session/projection', sessionId: id, key: 'tokenUsage', value: tokenUsageOf(log), seq: event.seq },
+      { type: 'session/projection', sessionId: id, key: 'contextPressure', value: contextPressureOf(log), seq: event.seq },
+    ]
+  }
+  if (type === 'request/context') {
+    return [{
+      type: 'session/projection',
+      sessionId: id,
+      key: 'contextPressure',
+      value: contextPressureOf(log),
+      seq: event.seq,
+    }]
+  }
   if (type === 'session/title') {
     const values = projectionValuesOf(log)
     /* v8 ignore next -- the advancing title event is in the log, so the key is present. */
@@ -1443,7 +1591,16 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
       replays.delete(id)
       const done = pieces.slice(0, i).join('')
       append(id, { type: 'assistant/chunk', data: { turn, step, chunk: { type: 'block-end', index: 0, block: { type: 'text', text: done } } } })
-      append(id, { type: 'assistant/message', surfaceOp: 'append', data: { turn, step, message: assistantMessage(text(aborted ? `${done}（已中断）` : done)) } })
+      append(id, {
+        type: 'assistant/message',
+        surfaceOp: 'append',
+        data: {
+          turn,
+          step,
+          message: assistantMessage(text(aborted ? `${done}（已中断）` : done)),
+          usage: fixtureUsage(turn, step),
+        },
+      })
       append(id, { type: 'step/end', data: { turn, step } })
       append(id, { type: 'turn/end', data: { turn, reason: { kind: aborted ? 'cancelled' : 'completed' } } })
       setRunning(id, false)
@@ -1712,6 +1869,16 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
           append(id, { type: 'plan/mode', data: { active: plan.wanted } })
         }
         append(id, { type: 'user/message', surfaceOp: 'append', data: userMessage(content) })
+        // Capacity parallel of the host token-meter's request/context record:
+        // log-only, appended inside the open turn, and deduplicated against the
+        // route already recorded (the fixture never varies contextWindow).
+        const target = modelTargets.get(id) ?? { provider: 'deepseek', model: 'deepseek-v4-flash' }
+        if (lastRequestContext(logOf(id))?.model !== target.model) {
+          append(id, {
+            type: 'request/context',
+            data: { provider: target.provider, model: target.model, contextWindow: 128_000 },
+          })
+        }
         startReply(
           id,
           turn,

packages/client/connection/tests/fixture.spec.ts

@@ -141,6 +141,14 @@ describe('createFixtureApi', () => {
         },
         plan: { active: false, pending: false },
         goal: null,
+        tokenUsage: {
+          uncachedInputTokens: 0,
+          outputTokens: 0,
+          cacheReadTokens: 0,
+          cacheWriteTokens: 0,
+        },
+        // No request ran, so neither pressure nor capacity is known yet.
+        contextPressure: {},
       } },
     })
   })
@@ -275,6 +283,17 @@ describe('createFixtureApi', () => {
     expect(types).toContain('assistant/chunk')
     expect(types).toContain('assistant/message')
     expect(types.at(-1)).toBe('turn/end')
+    // Capacity is durable log state, not a transient frame: the prompt path
+    // records request/context and the projection carries it to the client.
+    expect(types).toContain('request/context')
+    expect(frames.some(frame =>
+      frame.type === 'session/projection'
+      && frame.key === 'tokenUsage'
+      && (frame.value as { outputTokens?: number }).outputTokens === 8)).toBe(true)
+    expect(frames.some(frame =>
+      frame.type === 'session/projection'
+      && frame.key === 'contextPressure'
+      && (frame.value as { contextWindow?: number }).contextWindow === 128_000)).toBe(true)
     const finalize = frames.find((f): f is Extract<MuxFrame, { type: 'session/event' }> => f.type === 'session/event' && f.event.type === 'assistant/message')
     expect(JSON.stringify(finalize?.event.data)).toContain('（已中断）')
     // Idle cancel: no replay in flight, must not explode; running flips false.
@@ -306,7 +325,7 @@ describe('createFixtureApi', () => {
       const envelopes: RpcRequest<MuxFrame>[] = []
       for await (const envelope of api.events.mux(req({}), abort.signal)) {
         envelopes.push(envelope)
-        if (envelopes.length >= 8) abort.abort()
+        if (envelopes.length >= 10) abort.abort()
       }
       return envelopes
     }
@@ -314,16 +333,18 @@ describe('createFixtureApi', () => {
     const second = await openOnce()
     expect(first[0]?.payload).toMatchObject({ type: 'session/subscribed', sessionId: 'fx-alpha' })
     expect((first[0]?.payload as { lastSeq: number }).lastSeq).toBeGreaterThan(0)
-    // Projection baseline frames follow the subscribed frame (title + todos + permissions + plan + goal units).
+    // Projection baseline frames follow subscribed (domain units + token usage).
     expect(first[1]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'title', value: 'Fixture 历史会话' })
     expect(first[2]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'todos' })
     expect(first[3]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'permissions' })
     expect(first[4]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'plan', value: { active: false, pending: false } })
     expect(first[5]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'goal', value: null })
-    expect(first[6]?.payload).toMatchObject({ type: 'approval/requested', toolName: 'dangerous_tool' })
-    expect(second[6]?.rpcId).toBe(first[6]?.rpcId) // stable rpcId across replays (host replay semantics)
-    expect(first[7]?.payload).toMatchObject({ type: 'question/requested', sessionId: 'fx-alpha' })
-    expect(second[7]?.rpcId).toBe(first[7]?.rpcId)
+    expect(first[6]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'tokenUsage' })
+    expect(first[7]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'contextPressure' })
+    expect(first[8]?.payload).toMatchObject({ type: 'approval/requested', toolName: 'dangerous_tool' })
+    expect(second[8]?.rpcId).toBe(first[8]?.rpcId) // stable rpcId across replays (host replay semantics)
+    expect(first[9]?.payload).toMatchObject({ type: 'question/requested', sessionId: 'fx-alpha' })
+    expect(second[9]?.rpcId).toBe(first[9]?.rpcId)
   })
 
   it('steer with no replay in flight falls through to a fresh queued turn; non-text blocks stringify empty', async () => {

packages/client/connection/tests/node-half.spec.ts

@@ -61,23 +61,9 @@ describe('connection node half', () => {
     const ctx = new Context()
     ctx.provide('httpServer', fakeHttpServer(routes) as HttpServerService)
     ctx.provide('apiProxy', {} as unknown as ApiProxy)
-    // The apply throw also escapes cordis as a late rejection — the shape the
-    // boot's installFailLoud is contracted to catch. Capture it so the run
-    // stays clean, same pattern as the webserver bind-failure test.
-    const rejections: unknown[] = []
-    const onUnhandled = (err: unknown): void => { rejections.push(err) }
-    process.on('unhandledRejection', onUnhandled)
-    try {
-      const fiber = ctx.plugin({ inject: [...inject], apply }, { trustedHosts: ['harness.internal/path'] })
-      await expect(fiber.await()).rejects.toThrow(/not a bare host\[:port\] authority/)
-      expect(routes).toHaveLength(0)
-      for (let i = 0; i < 100 && rejections.length === 0; i++) {
-        await new Promise(resolve => setTimeout(resolve, 10))
-      }
-      expect(rejections.map(String).join('\n')).toContain('not a bare host[:port] authority')
-    } finally {
-      process.off('unhandledRejection', onUnhandled)
-    }
+    const fiber = ctx.plugin({ inject: [...inject], apply }, { trustedHosts: ['harness.internal/path'] })
+    await expect(fiber).rejects.toThrow(/not a bare host\[:port\] authority/)
+    expect(routes).toHaveLength(0)
   })
 
   it('registers the /api prefix route and removes it with the fiber', async () => {

packages/client/runtime/tests/slots-service.spec.ts

@@ -41,8 +41,8 @@ interface Bench {
 
 async function boot(): Promise<Bench> {
   const ctx = new Context()
-  ctx.plugin(SlotsService)
-  await ctx.fiber.await()
+  const fiber = ctx.plugin(SlotsService)
+  await fiber
   // Service accessor (ctx.get reads the reflect store, which Service-class
   // plugins do not write; the accessor is the product path).
   const svc = ctx.slots

packages/client/ui-conversation/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/client/ui-conversation/README.md
-README.md: dea051fa608119ec1386299d48a1be8aef23aaec
-README.zh.md: ae4537b899f44badba5d7e2051434bbbddb410c3
+README.md: 5e918bbf06e163c50e184f500b565eb2436729e0
+README.zh.md: e8ef25b0734e73ff32dc57c12a76adbf6a2fcb6f

packages/client/ui-conversation/README.md

@@ -34,6 +34,8 @@ Per-session UI state for selection and the active view lives in the declared cha
 
 The composer bar declares session-scoped single seats for `'conversation.input.plan'` (right of the local access-mode control) and `'conversation.input.model'` (immediately before the pending indicator and send/stop button), plus list slots for overlay, dock, left, and right input extensions. Feature packages own each control and its state; ui-conversation supplies placement, the `locked` owner prop, and the standard slot shares. The leading plus button is a Command launcher, not an attachment surface: it asks the session's `SlashController` to open only the `/` trigger's `command` source over the current textarea selection, while ui-slash's existing `MenuView` remains the sole floating menu and pick path. No file row, file input, upload protocol, or second menu component is introduced. While the `plan` projection's effective target is plan mode, InputBar swaps its textarea placeholder to the plan-task wording, localized through the `conversation` locale namespace this package registers (the `placeholder.plan` / `hint.plan` keys) and shared verbatim with the claimed `/plan` command hint (a host-folded value read through the standard-kit `useProjection`; owner-supplied placeholders win). A pending composer takeover remains mounted when another conversation view is active so the blocked agent can still receive its answer; without a pending interaction, the active-session composer belongs to Chat. The composer-bar slot itself is `session-maybe`: with no current session the same bar renders inert (machine faces absent, `disabled` owner prop) instead of swapping in a parallel disabled tree, so the textarea DOM survives the workspace pick; the strict-session control seats simply stay empty until a session exists.
 
+The chat stats line takes its token accounting from two generic token-meter projections read through the standard-kit `useProjection`: `tokenUsage` for full-log billing (billed input is uncached input plus cache reads and writes; cache hit divides cache reads by that total) and `contextPressure` for context occupancy. Visible nodes supply only the turn and step counts plus the LLM and tool wall times, which are window-scoped facts about what is on screen rather than accounting; durable token and context groups remain visible when compaction leaves no assistant node in the loaded window. A deployment without token-meter drops the token groups, and occupancy stays hidden until both provider pressure and route capacity are known. Occupancy is deliberately an approximation — its numerator and capacity are independent last-wins projection fields, not one atomic request observation ([rationale](../../llm/token-meter/README.md)). The inline stats row remains the sole context UI; the model selector has no circle or accessory.
+
 `src/client/` is organized for the future package split: `contract/` is the sole inter-domain shared face (`slots.ts` slot declarations + composed slot props including the tool-row contract, `views.ts` shared primitives, `tool-call-model.ts`); the `skeleton/`, `chat/`, and `toolviews/` (sample registrants) domain directories import contract files and never each other; `apply.ts` is the only assembly point allowed to import all three domains. The `/client` export surface is the contract only — `apply`/`inject`, the two service classes, and the `contract/` type families; implementation components (skeleton, chat rows) and the store factory stay internal and reach the page exclusively through apply's slot registrations (tests take them via the `./src/*` subpath).
 
 ## Model Experience

packages/client/ui-conversation/README.zh.md

@@ -34,6 +34,8 @@ todo 两个面就是在该形状上的两个注册项，都是普通注册方插
 
 输入栏为 `'conversation.input.plan'`（位于本地 access 模式控件右侧）和 `'conversation.input.model'`（渲染在 pending 指示器与发送／停止按钮之前）声明会话作用域的单实例 seat，并为 overlay、dock、left 和 right 输入扩展声明列表 slot。各功能包拥有相应控件及其状态；ui-conversation 提供放置位置、`locked` owner prop 和标准 slot share。前置加号按钮是 Command launcher，而非附件入口：它要求当前会话的 `SlashController` 基于 textarea 当前 selection，只打开 `/` trigger 的 `command` source，同时 ui-slash 既有的 `MenuView` 仍是唯一的浮层菜单与 pick 路径。不引入 File 行、file input、上传协议或第二套菜单组件。当 `plan` 投影的有效目标为 plan mode 时，InputBar 将文本框 placeholder 切换为 plan 任务措辞，经本包注册的 `conversation` locale 命名空间（`placeholder.plan` / `hint.plan` 键）本地化，并与已认领 `/plan` 命令的提示逐字共用同一份文案（经标准套件 `useProjection` 读取的 host 折叠值；owner 提供的 placeholder 优先）。另一个会话视图活跃时，待处理的 composer 接管仍保持挂载，使被阻塞的 agent（智能体）仍能收到回答；没有待处理交互时，活跃会话的 composer 归 Chat 所有。composer bar slot 本身为 `session-maybe`：没有当前会话时，同一个 bar 以不可交互状态渲染（machine face 均缺席、`disabled` owner prop），而不是换入一棵平行的 disabled 树，因此选择 workspace 时 textarea DOM 不会被销毁；严格会话作用域的控件 seat 在会话存在之前保持为空。
 
+聊天统计行的 token 账目来自经标准套件 `useProjection` 读取的两个通用 token-meter 投影：`tokenUsage` 提供完整日志计费用量（计费输入为未缓存输入、缓存读取与缓存写入之和；缓存命中率以缓存读取除以该总量），`contextPressure` 提供上下文占用率。可见节点只提供轮次与步骤计数，以及 LLM（大语言模型）和工具的墙钟时间：这些是关于「屏幕上有什么」的窗口作用域事实，而非账目；压缩（compaction）使已加载窗口不再包含 assistant 节点时，持久 token 与上下文分组仍保持可见。未组合 token-meter 的部署会整组省略 token 分组；只有提供方压力与路由容量都已知时才显示占用率。占用率是刻意为之的近似值：它的分子与容量是两个相互独立的「后写覆盖」投影字段，并非同一次请求的原子观测（[原理](../../llm/token-meter/README.md)）。行内统计行仍是唯一的上下文 UI；模型选择器不增加圆环或附属控件。
+
 `src/client/` 按未来的包拆分组织：`contract/` 是唯一的跨领域共享表层（`slots.ts` slot 声明 + 组合后的 slot props，包括工具行契约、`views.ts` 共享原语、`tool-call-model.ts`）；`skeleton/`、`chat/` 和 `toolviews/`（示例注册方）领域目录只导入 contract 文件，彼此绝不导入；`apply.ts` 是唯一允许导入全部三个领域的组装点。`/client` 导出表层只包含契约：`apply`／`inject`、两个服务类和 `contract/` 类型家族；实现组件（骨架、聊天行）与 store factory 保持内部状态，只能通过 apply 的 slot 注册到达页面（测试通过 `./src/*` 子路径获取它们）。
 
 ## 模型体验
@@ -46,7 +48,7 @@ todo 两个面就是在该形状上的两个注册项，都是普通注册方插
 
 ## 已知限制与暂缓事项
 
-- **统计行的耗时只覆盖窗口内消息流**：LLM（大语言模型）与工具墙钟时间由快照的 assistant `timing` 与工具 call/result 配对折算，落在已加载事件窗口之外的节点（更早的历史）不计入。
+- **统计行的耗时只覆盖窗口内消息流**：LLM 与工具墙钟时间由快照的 assistant `timing` 与工具 call/result 配对折算，落在已加载事件窗口之外的节点（更早的历史）不计入。
 - **详情面板是最小形态，且当前没有入口**：以原始形式显示已选择调用的参数／结果；Input/Output/Metadata 切换、Prev/Next 步进与 See-in-trajectory 深链接暂缓实现。工具行已不再是详情面板的点击目标，且没有任何手势接替它，因此 `ChatViewInjected.openDetails` 虽已实现却无人调用，该面板（含其终端卡片）在组装后的应用中不可达；其渲染仍由直接以选中态挂载它来覆盖。
 - **assistant 逐消息分页是预留 slot**：设计中已有图稿，尚未实现。已定稿的内容 IconActions 行（复制／分支／时钟）只挂在每个轮次中最后一条带 text 内容的 assistant 下；轮次中间的叙述与纯 Think 节点不带 chrome。分支会 fork 到包含该消息的轮次末尾，在 client 端递增继承标题后打开子会话，而 fork 或改名失败时源会话保持选中。
 - **已发送的 user 消息无法编辑**：user 气泡的 IconActions 行只有时钟／复制／分支，从该消息分支是最接近的手势。该控件要与其背后的能力一起回归：既需要针对已定稿 user 消息的 client 变更，也需要 host 侧对已经消费过它的轮次给出行为（[决策](../../../.agents/notes/implemented/simplification/2026-07-31-drop-user-message-edit-stub.md)）。

packages/client/ui-conversation/package.json

@@ -45,6 +45,7 @@
     "@deepseek-ai/dsh-client-ui-slash": "^0.0.1",
     "@deepseek-ai/dsh-client-ui-slots": "^0.0.1",
     "@deepseek-ai/dsh-invariants": "^0.0.1",
+    "@deepseek-ai/dsh-token-meter": "^0.0.1",
     "cordis": "^4.0.0-rc.7",
     "react": "^18.2.0"
   },
@@ -61,6 +62,7 @@
     "@deepseek-ai/dsh-invariants": "workspace:^",
     "@deepseek-ai/dsh-permission": "workspace:^",
     "@deepseek-ai/dsh-session-projection": "workspace:^",
+    "@deepseek-ai/dsh-token-meter": "workspace:^",
     "@deepseek-ai/dsh-tool-todo": "workspace:^",
     "@types/react": "~18.3.1",
     "cordis": "^4.0.0-rc.7",

packages/client/ui-conversation/src/client/chat/StatsLine.tsx

@@ -3,43 +3,35 @@
 // active conversation scrollport (see ConversationRoot data-conversation-scroll).
 
 import { Fragment, memo, useMemo } from 'react'
-import type { ConversationSnapshot } from '@deepseek-ai/dsh-client-runtime/client'
+import type { ConversationSnapshot, UseProjection } from '@deepseek-ai/dsh-client-runtime/client'
 import type { SnapshotSelectorHook } from '@deepseek-ai/dsh-client-ui-slots'
+import type { ContextPressureProjection, TokenUsageProjection } from '@deepseek-ai/dsh-token-meter/client'
 import css from './StatsLine.module.css'
 
-interface UsageTotals {
+interface WindowStats {
   turns: number
   steps: number
   /** Summed request wall time (step/start → assistant/message); 0 when no node carries timing. */
   llmMs: number
   /** Summed tool wall time (tool/call → tool/result); 0 when no pair is in-window. */
   toolMs: number
-  /** Prompt-side tokens: inputTokens + cacheReadTokens. */
-  inputTokens: number
-  outputTokens: number
-  cacheHitPct: number | null
-}
-
-/** Token accounting slice of assistant `usage` (typed upstream as unknown). */
-interface UsageLike {
-  inputTokens?: number
-  outputTokens?: number
-  cacheReadTokens?: number
 }
 
 /**
- * Fold assistant and tool-result nodes into display totals.
+ * Fold assistant and tool-result nodes into the window-scoped display totals.
+ *
+ * Counts and wall times describe the loaded window on purpose — they answer
+ * "what is on screen". Token accounting deliberately does NOT come from here:
+ * the window is paged and compaction rewrites it, so billing rides the durable
+ * `tokenUsage` projection instead.
  * @param nodes - snapshot nodes.
- * @returns totals; cacheHitPct null until any cache accounting arrives.
+ * @returns visible counts and summed wall times.
  */
-export function deriveStats(nodes: ConversationSnapshot['nodes']): UsageTotals {
+export function deriveStats(nodes: ConversationSnapshot['nodes']): WindowStats {
   const turns = new Set<number>()
   let steps = 0
   let llmMs = 0
   let toolMs = 0
-  let input = 0
-  let output = 0
-  let cacheRead = 0
   for (const node of nodes) {
     if (node.kind === 'tool-result') {
       if (node.callTime !== null) toolMs += Math.max(0, node.time - node.callTime)
@@ -51,22 +43,8 @@ export function deriveStats(nodes: ConversationSnapshot['nodes']): UsageTotals {
     if (node.timing !== undefined && node.timing.stepStartTime !== null) {
       llmMs += Math.max(0, node.timing.completedTime - node.timing.stepStartTime)
     }
-    const usage = node.usage as UsageLike | undefined
-    if (usage === undefined) continue
-    input += usage.inputTokens ?? 0
-    output += usage.outputTokens ?? 0
-    cacheRead += usage.cacheReadTokens ?? 0
-  }
-  const denom = input + cacheRead
-  return {
-    turns: turns.size,
-    steps,
-    llmMs,
-    toolMs,
-    inputTokens: input + cacheRead,
-    outputTokens: output,
-    cacheHitPct: denom === 0 ? null : Math.round((cacheRead / denom) * 100),
   }
+  return { turns: turns.size, steps, llmMs, toolMs }
 }
 
 /**
@@ -94,21 +72,82 @@ export function formatDuration(ms: number): string {
   return `${Math.floor(whole / 60)}m${whole % 60}s`
 }
 
-/** Props: the conversation-snapshot selector (dock registration or unit mount). */
-export interface StatsLineProps { useSession: SnapshotSelectorHook<ConversationSnapshot> }
+/**
+ * Cache-hit share of prompt-side input over the whole durable log.
+ * @param usage - the session's token-usage projection value.
+ * @returns rounded integer percent, or null when no input was billed.
+ */
+export function cacheHitPercent(usage: TokenUsageProjection): number | null {
+  const denominator = billedInputTokens(usage)
+  return denominator === 0
+    ? null
+    : Math.round(usage.cacheReadTokens / denominator * 100)
+}
 
-export const StatsLine = memo(function StatsLine({ useSession }: StatsLineProps) {
+/** Sum the three disjoint prompt-side billing buckets. */
+function billedInputTokens(usage: TokenUsageProjection): number {
+  return usage.uncachedInputTokens + usage.cacheReadTokens + usage.cacheWriteTokens
+}
+
+interface ContextOccupancy {
+  percent: number
+  contextWindow: number
+}
+
+/**
+ * Approximate context occupancy, using the TUI's integer rounding and upper
+ * clamp. The numerator and capacity are independent last-wins projection
+ * fields, so this is a reference figure rather than an exact measurement of one
+ * request (see the token-meter README).
+ * @param pressure - the session's context-pressure projection value.
+ * @returns occupancy and its denominator, or null until both values are known.
+ */
+export function contextOccupancy(
+  pressure: ContextPressureProjection | undefined,
+): ContextOccupancy | null {
+  if (pressure?.pressureTokens === undefined || pressure.contextWindow === undefined) return null
+  return {
+    percent: Math.min(100, Math.round(pressure.pressureTokens / pressure.contextWindow * 100)),
+    contextWindow: pressure.contextWindow,
+  }
+}
+
+/** Props: the conversation-snapshot selector plus the projection read seat. */
+export interface StatsLineProps {
+  useSession: SnapshotSelectorHook<ConversationSnapshot>
+  useProjection: UseProjection
+}
+
+export const StatsLine = memo(function StatsLine({ useSession, useProjection }: StatsLineProps) {
   const nodes = useSession(s => s.nodes)
+  const usage = useProjection('tokenUsage')
+  const pressure = useProjection('contextPressure')
   const stats = useMemo(() => deriveStats(nodes), [nodes])
-  if (stats.steps === 0) return null
   // Pipe-separated groups (figma stats strip); a group with no data drops out whole.
-  const groups: string[] = [`${stats.turns} turns · ${stats.steps} steps`]
-  const durations: string[] = []
-  if (stats.llmMs > 0) durations.push(`LLM ${formatDuration(stats.llmMs)}`)
-  if (stats.toolMs > 0) durations.push(`Tool call ${formatDuration(stats.toolMs)}`)
-  if (durations.length > 0) groups.push(durations.join(' · '))
-  if (stats.cacheHitPct !== null) groups.push(`Cache hit ${stats.cacheHitPct}%`)
-  groups.push(`Input ${formatTokens(stats.inputTokens)} tok · Output ${formatTokens(stats.outputTokens)} tok`)
+  const groups: string[] = []
+  if (stats.steps > 0) {
+    groups.push(`${stats.turns} turns · ${stats.steps} steps`)
+    const durations: string[] = []
+    if (stats.llmMs > 0) durations.push(`LLM ${formatDuration(stats.llmMs)}`)
+    if (stats.toolMs > 0) durations.push(`Tool call ${formatDuration(stats.toolMs)}`)
+    if (durations.length > 0) groups.push(durations.join(' · '))
+  }
+  const context = contextOccupancy(pressure)
+  if (context !== null) {
+    groups.push(`Context ${context.percent}% of ${formatTokens(context.contextWindow)}`)
+  }
+  // Billing rides the durable projection, so these survive paging and
+  // compaction. Suppress the empty projection on a brand-new session.
+  if (usage !== undefined
+    && (stats.steps > 0 || billedInputTokens(usage) > 0 || usage.outputTokens > 0)) {
+    const cacheHit = cacheHitPercent(usage)
+    if (cacheHit !== null) groups.push(`Cache hit ${cacheHit}%`)
+    groups.push(
+      `Input ${formatTokens(billedInputTokens(usage))} tok`
+      + ` · Output ${formatTokens(usage.outputTokens)} tok`,
+    )
+  }
+  if (groups.length === 0) return null
   return (
     <div className={css.root}>
       {groups.map((group, i) => (

packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx

@@ -417,14 +417,19 @@ describe('small branch tails', () => {
   })
 
   it('StatsLine omits the cache-hit segment when no input accounting exists at all', () => {
-    // cacheHitPct is null only when input+cacheRead are both zero (pure
-    // output accounting) — any input makes it a real 0%.
+    // Cache hit is null only when all three prompt buckets are zero (pure
+    // output accounting) — any billed input makes it a real 0%.
     const snap = {
       nodes: [{ kind: 'assistant', seq: 1, turn: 1, step: 1, blocks: [], usage: { outputTokens: 10 } }],
     }
     const source = { getSnapshot: () => snap, subscribe: () => () => {} }
     const view = render(
-      <StatsLine useSession={bindSnapshotSelector(source) as unknown as StatsLineProps['useSession']} />,
+      <StatsLine
+        useSession={bindSnapshotSelector(source) as unknown as StatsLineProps['useSession']}
+        useProjection={(key: string) => key === 'tokenUsage'
+          ? { uncachedInputTokens: 0, outputTokens: 10, cacheReadTokens: 0, cacheWriteTokens: 0 }
+          : undefined}
+      />,
     )
     expect(view.container.textContent).toBe('1 turns · 1 steps|Input 0 tok · Output 10 tok')
   })

packages/client/ui-conversation/tests/chat-stats-bash-sample.spec.tsx

@@ -58,7 +58,7 @@ function makeSource(init?: Partial<ConversationSnapshot>) {
 }
 
 describe('deriveStats', () => {
-  it('folds turns/steps/token split and cache hit percentage', () => {
+  it('counts turns and steps and never folds node usage into accounting', () => {
     const stats = deriveStats([
       assistant(1, 1, { inputTokens: 100, outputTokens: 50, cacheReadTokens: 900 }),
       assistant(2, 1, { inputTokens: 100, outputTokens: 50 }),
@@ -66,12 +66,12 @@ describe('deriveStats', () => {
     ])
     expect(stats.turns).toBe(2)
     expect(stats.steps).toBe(3)
-    expect(stats.inputTokens).toBe(1100)
-    expect(stats.outputTokens).toBe(100)
-    expect(stats.cacheHitPct).toBe(82)
+    // Window-scoped by design: the paged window is not an accounting source, so
+    // the fold exposes no token fields at all (billing rides the projection).
+    expect(Object.keys(stats).sort()).toEqual(['llmMs', 'steps', 'toolMs', 'turns'])
   })
 
-  it('cache hit stays null with no cache accounting; out-of-window tool results ignored', () => {
+  it('ignores tool results with no call time', () => {
     const tool: ToolResultNode = {
       kind: 'tool-result', seq: 5, time: 5_000, callId: 'c', call: null, callTime: null, content: [],
       isError: false, callView: null, resultView: null,
@@ -79,7 +79,6 @@ describe('deriveStats', () => {
     const stats = deriveStats([tool, assistant(1, 1)])
     expect(stats.steps).toBe(1)
     expect(stats.toolMs).toBe(0)
-    expect(stats.cacheHitPct).toBeNull()
   })
 
   it('sums LLM wall time from assistant timing and tool wall time from call/result pairs', () => {
@@ -116,22 +115,105 @@ describe('formatters', () => {
 })
 
 describe('StatsLine', () => {
-  function props(source: { getSnapshot(): ConversationSnapshot; subscribe(fn: () => void): () => void }): StatsLineProps {
-    return { useSession: bindSnapshotSelector(source) }
+  const USAGE = { uncachedInputTokens: 10, outputTokens: 5, cacheReadTokens: 90, cacheWriteTokens: 0 }
+
+  /** Stub the projection seat: a key-addressed table of whole values. */
+  function projections(values: Record<string, unknown>): StatsLineProps['useProjection'] {
+    return (key: string) => values[key]
   }
 
-  it('renders the grouped stats row and hides with zero steps', () => {
-    const { source } = makeSource({
-      nodes: [assistant(1, 1, { inputTokens: 10, outputTokens: 5, cacheReadTokens: 90 })],
-    })
+  function props(
+    source: { getSnapshot(): ConversationSnapshot; subscribe(fn: () => void): () => void },
+    values: Record<string, unknown> = { tokenUsage: USAGE },
+  ): StatsLineProps {
+    return { useSession: bindSnapshotSelector(source), useProjection: projections(values) }
+  }
+
+  it('renders the grouped stats row and hides a brand-new empty session', () => {
+    const { source } = makeSource({ nodes: [assistant(1, 1)] })
     const view = render(<StatsLine {...props(source)} />)
-    // No timing on the fixture: the duration group drops out whole.
+    // No timing on the fixture: the duration group drops out whole. Tokens come
+    // from the projection, so paging the window cannot change them.
     expect(view.container.textContent).toBe('1 turns · 1 steps|Cache hit 90%|Input 100 tok · Output 5 tok')
     const empty = makeSource()
-    const emptyView = render(<StatsLine {...props(empty.source)} />)
+    const emptyView = render(<StatsLine {...props(empty.source, {
+      tokenUsage: { uncachedInputTokens: 0, outputTokens: 0, cacheReadTokens: 0, cacheWriteTokens: 0 },
+      contextPressure: {},
+    })} />)
     expect(emptyView.container.textContent).toBe('')
   })
 
+  it('keeps durable token and context groups after the visible step window is empty', () => {
+    const { source } = makeSource()
+    const view = render(<StatsLine {...props(source, {
+      tokenUsage: USAGE,
+      contextPressure: { pressureTokens: 32_000, contextWindow: 128_000 },
+    })} />)
+    expect(view.container.textContent)
+      .toBe('Context 25% of 128K|Cache hit 90%|Input 100 tok · Output 5 tok')
+  })
+
+  it('renders context occupancy only when the projection knows a capacity', () => {
+    const { source } = makeSource({ nodes: [assistant(1, 1)] })
+    const withCapacity = render(<StatsLine {...props(source, {
+      tokenUsage: USAGE,
+      contextPressure: { pressureTokens: 32_000, contextWindow: 128_000 },
+    })} />)
+    expect(withCapacity.container.textContent).toContain('Context 25% of 128K')
+    // Pressure without capacity has no denominator: the group drops out.
+    const noCapacity = render(<StatsLine {...props(source, {
+      tokenUsage: USAGE,
+      contextPressure: { pressureTokens: 32_000 },
+    })} />)
+    expect(noCapacity.container.textContent).not.toContain('Context')
+    // Capacity arrives before usage in the log; no provider sample means there
+    // is no numerator yet, rather than a synthetic 0%.
+    const noPressure = render(<StatsLine {...props(source, {
+      tokenUsage: USAGE,
+      contextPressure: { contextWindow: 128_000 },
+    })} />)
+    expect(noPressure.container.textContent).not.toContain('Context')
+  })
+
+  it('clamps occupancy at 100% when pressure exceeds the recorded capacity', () => {
+    // Capacity and pressure are independent last-wins fields, so a model switch
+    // can pair a smaller new window with the previous route's larger prompt.
+    const { source } = makeSource({ nodes: [assistant(1, 1)] })
+    const view = render(<StatsLine {...props(source, {
+      tokenUsage: USAGE,
+      contextPressure: { pressureTokens: 300_000, contextWindow: 128_000 },
+    })} />)
+    expect(view.container.textContent).toContain('Context 100% of 128K')
+  })
+
+  it('drops every token group when no projection is composed', () => {
+    const { source } = makeSource({ nodes: [assistant(1, 1)] })
+    const view = render(<StatsLine {...props(source, {})} />)
+    expect(view.container.textContent).toBe('1 turns · 1 steps')
+  })
+
+  it('omits cache hit when nothing was billed on the input side', () => {
+    const { source } = makeSource({ nodes: [assistant(1, 1)] })
+    const view = render(<StatsLine {...props(source, {
+      tokenUsage: { uncachedInputTokens: 0, outputTokens: 7, cacheReadTokens: 0, cacheWriteTokens: 0 },
+    })} />)
+    expect(view.container.textContent).toBe('1 turns · 1 steps|Input 0 tok · Output 7 tok')
+  })
+
+  it('includes cache writes in billed input and the cache-hit denominator', () => {
+    const { source } = makeSource({ nodes: [assistant(1, 1)] })
+    const view = render(<StatsLine {...props(source, {
+      tokenUsage: {
+        uncachedInputTokens: 10,
+        outputTokens: 7,
+        cacheReadTokens: 90,
+        cacheWriteTokens: 100,
+      },
+    })} />)
+    expect(view.container.textContent)
+      .toBe('1 turns · 1 steps|Cache hit 45%|Input 200 tok · Output 7 tok')
+  })
+
   it('renders ZERO times during streaming chunk frames (RFC hard acceptance)', () => {
     const { set, source } = makeSource({ nodes: [assistant(1, 1)] })
     let renders = 0

packages/client/ui-conversation/tests/gate-branch-tails.spec.tsx

@@ -43,20 +43,24 @@ describe('render branch tails', () => {
     expect(view.container.querySelector('[data-state="ok"]')).not.toBeNull()
   })
 
-  it('StatsLine skips usage-less nodes and defaults each absent counter to zero', () => {
+  it('StatsLine counts window nodes but drops every token group without a projection', () => {
+    // Node `usage` is deliberately ignored: billing rides the durable
+    // tokenUsage projection, so an absent projection leaves counts only.
     const snap = {
       nodes: [
         { kind: 'assistant', seq: 1, turn: 1, step: 1, blocks: [] },
         { kind: 'assistant', seq: 2, turn: 1, step: 2, blocks: [], usage: { inputTokens: 4, outputTokens: 6 } },
-        // outputTokens absent: the tokens sum's ?? 0 arm for output.
         { kind: 'assistant', seq: 3, turn: 2, step: 1, blocks: [], usage: { inputTokens: 5 } },
       ],
     }
     const source = { getSnapshot: () => snap, subscribe: () => () => {} }
     const view = render(
-      <StatsLine useSession={bindSnapshotSelector(source) as unknown as UseSession<ConversationSnapshot>} />,
+      <StatsLine
+        useSession={bindSnapshotSelector(source) as unknown as UseSession<ConversationSnapshot>}
+        useProjection={() => undefined}
+      />,
     )
-    expect(view.container.textContent).toBe('2 turns · 3 steps|Cache hit 0%|Input 9 tok · Output 6 tok')
+    expect(view.container.textContent).toBe('2 turns · 3 steps')
   })
 
   it('AssistantMarkdown reasoning as the streaming tail renders the running ring', () => {

packages/client/ui-conversation/tsconfig.json

@@ -26,6 +26,9 @@
     {
       "path": "../../session-projection/session-projection"
     },
+    {
+      "path": "../../llm/token-meter"
+    },
     {
       "path": "../../plan/plan-mode"
     },