Merge pull request #5721 from deepseek-harness/worktree/long-session-paging-observer-20261005

test(bench): exclude paging locator preparation from timing

.agents/notes/implemented/testing/2026-09-06-frontend-performance-budgets.i18n.yaml

@@ -9,17 +9,20 @@
   en: 9bf1200b5f980008
   zh: d2dc07922817c581
 /agent-note-frontend-large-session-performance-budgets/decision:
-  en: 8603790da3e6f1b8
-  zh: aa7bda7b42c60984
+  en: db46b4d42d64aa1b
+  zh: a21caffa675e8b42
 /agent-note-frontend-large-session-performance-budgets/calibration:
-  en: f3be2a0d346e80cc
-  zh: c49cc56e7714f68c
+  en: 2bbee3ec0bc9e618
+  zh: b4f937d7f4f09ae5
 /agent-note-frontend-large-session-performance-budgets/calibration/actual-ci-runs:
   en: d4d6aebafcdb8c12
   zh: 112d3ca1a4ea8ae1
 /agent-note-frontend-large-session-performance-budgets/calibration/standard-hosted-expectations-and-input-scheduling:
   en: 346cd1b3d5acf0ea
   zh: 42e08cd387f982c8
+/agent-note-frontend-large-session-performance-budgets/calibration/older-page-control-preparation:
+  en: de392f6c19df72ee
+  zh: 32cbabf9ebcacbcc
 /agent-note-frontend-large-session-performance-budgets/calibration/trajectory-readiness-polling:
   en: bdcfefd7358e335b
   zh: f718f66ca5944203

.agents/notes/implemented/testing/2026-09-06-frontend-performance-budgets.md

@@ -14,7 +14,7 @@ The existing serial benchmark inventory includes two frontend owners: [active re
 
 `build:bench` keeps the Node-only library and worker build. `test:bench` additionally builds the Web shell before running all cases; the required benchmark CI job follows the [standard hosted runner reference](../../../../.github/workflows/ci.yml), unconditionally provisions Chromium and its Linux dependencies on that hosted runner, and enables the existing verbose gate output so successful raw samples remain available for calibration. Browser cases reuse the shipped-composition Web scaffold with private temporary roots and an atomically assigned loopback port. Only the nondeterministic model is replaced by synthetic replay. The scaffold Host runs under the existing Vitest source resolver; measured Client rendering runs built bundles in fresh Chromium processes. Browser wall times therefore include this test Host, transport, Playwright actionability, and rendering, and are not claims about a published Host process.
 
-The browser input contains 240 closed turns, 40 tool results, and 20 code fences, plus mixed-language prose and reasoning. Historical Assistant records carry matching compact streams built through the production accumulator with 12-character reasoning/text deltas and 8-character tool-argument deltas; empty streams would omit stored and transferred payload costs. Nine older-page actions exhaust this input from its observed 25-turn initial window; the readiness probe follows mounted turn growth rather than duplicating the pagination algorithm. Each sample uses a fresh scaffold and browser. Setup, seeding, browser launch, initial shell load, and sidebar expansion are excluded from open timing. Open ends at transcript availability and an editable composer; page and navigation timings end at their target DOM state. Two animation frames include a rendering opportunity, not hardware presentation or a guarantee that every offscreen node painted.
+The browser input contains 240 closed turns, 40 tool results, and 20 code fences, plus mixed-language prose and reasoning. Historical Assistant records carry matching compact streams built through the production accumulator with 12-character reasoning/text deltas and 8-character tool-argument deltas; empty streams would omit stored and transferred payload costs. Nine older-page actions exhaust this input from its observed 25-turn initial window; the readiness probe follows mounted turn growth rather than duplicating the pagination algorithm. Each sample uses a fresh scaffold and browser. Setup, seeding, browser launch, initial shell load, and sidebar expansion are excluded from open timing. Paging resolves exactly one current `Load earlier` control before timing, excluding its read-only accessibility lookup. The 875 ms paging ceiling includes actionability, the trusted click, mounted turn-tail growth and the final two animation frames; a replaced control fails. Open ends at transcript availability and an editable composer; page and navigation timings end at their target DOM state. Two animation frames include a rendering opportunity, not hardware presentation or a guarantee that every offscreen node painted.
 
 The continuation sends 120 text deltas at 16 ms replay pacing. The input witness is installed before Enter submission from the focused composer; typing retains focus without a mouse-refocus action or a separate pre-input animation-frame wait. First/final marker lookups sample visible text inside the latest Assistant step on animation frames, avoiding selector retry backoff. Hidden text and markers in older steps cannot satisfy the observer. The first observation captures reply markers and focus in the browser; diagnostics are retrieved after typing to avoid an additional pre-input round trip. Diagnostics also capture browser-clock timestamps and focus at the first actual input event. Replay never waits for input; starvation can still fail overlap. The synchronous input witness reads that same bounded reply. Whole-history text and accessibility queries add observer CPU and garbage collection to the measured interval, so reducing that observer work is benchmark repair, not product optimization. It records Enter-to-first-visible-reply, trusted draft typing whose first actual input event observes the first reply but no completion marker, complete reply wall time through settled persistence and the new rendered turn-tail, and Chromium main-thread task duration. The complete wall budget adds the fixed 1984 ms scripted pacing to a scaled overhead allowance; input and completion have their own enforced budgets. Post-GC browser heap and DOM counts remain diagnostics because one endpoint does not prove a leak.
 
@@ -22,7 +22,7 @@ Reconnect uses three fresh compiled plain-Node children. Each creates a 100,000-
 
 ## Calibration
 
-Three-sample medians on the arm64 reference machine, Node 24.19 and Chromium 149.0.7827.55, at the PR #3537 merge, establish the baseline below. An isolated repeat follows a complete workflow smoke. Each browser sample reports raw endpoint values and every page; the paging verdict uses the median of the sample maxima. Reconnect reports all child measurements. The following historical reference table uses 8 ms replay pacing and includes a two-frame wait in first-reply timing. Standard-hosted open, paging, Trajectory, and reconnect expectations are recorded separately below; other source reference constants retain these allowances. The bounded-observer 261.60 ms paging median exceeds its 260 ms reference allowance but remains below its 650 ms CI limit; the shared 2× time scale and 1.25× variance allowance produce CI limits. Memory uses only variance allowance. The shared scale originates in Node CI calibration. Both actual x64 browser runs below pass the fixed budgets on unchanged benchmark code; this supplies repeated-run evidence for these runners, not a universal browser speed ratio.
+Three-sample medians on the arm64 reference machine, Node 24.19 and Chromium 149.0.7827.55, at the PR #3537 merge, establish the baseline below. An isolated repeat follows a complete workflow smoke. Each browser sample reports raw endpoint values and every page; the paging verdict uses the median of the sample maxima. Reconnect reports all child measurements. The following historical reference table uses 8 ms replay pacing and includes a two-frame wait in first-reply timing. Its paging samples include the accessibility lookup of the older-page control. Standard-hosted open, paging, Trajectory, and reconnect expectations are recorded separately below; other source reference constants retain these allowances. The bounded-observer 261.60 ms paging median exceeds its 260 ms reference allowance but remains below its 650 ms CI limit; the shared 2× time scale and 1.25× variance allowance produce CI limits. Memory uses only variance allowance. The shared scale originates in Node CI calibration. Both actual x64 browser runs below pass the fixed budgets on unchanged benchmark code; this supplies repeated-run evidence for these runners, not a universal browser speed ratio.
 
 | Endpoint | Measured median | Reference allowance | Historical CI limit |
 |---|---:|---:|---:|
@@ -72,6 +72,12 @@ A controlled mouse-refocus delay waits for the real DONE marker without pausing
 
 The current Trajectory acceptance limit is 650 ms, represented by a 520 ms target with the shared 1.25× headroom. Run 35095609422 records medians of 666.651723 ms and 630.843184 ms on its original attempt and retry. This explicit 4% relaxation of the former 625 ms limit accepts the retry median but still rejects the original median; it is a budget decision, not a measured product speedup. Recorded retry samples exercise the accepted range, and the same verdict assertion rejects 651 ms. Other endpoint budgets and workload parameters remain unchanged.
 
+### Older-page control preparation
+
+Older-page measurements wait for a uniquely named attached control before capturing it. Availability and read-only accessibility lookup are preparation; visibility, enabled/stable actionability, the trusted click, turn-tail growth and the final two frames remain timed. The historical 260 ms reference allowance, 261.60 ms median and 700 ms hosted expectation include the lookup that this endpoint excludes.
+
+Local samples with lookup excluded are 141.202083/126.114041/140.003334 ms, median 140.003334 ms. Hosted run 37272669722, benchmark job 111642813553 records 524.083466/355.648835/349.959862 ms, median 355.648835 ms, under the same 875 ms ceiling. These are observed samples, not a new calibration; the 700 ms expectation and 875 ms ceiling remain conservative retained limits pending repeated hosted measurements of this endpoint. The earlier same-checkout 887.624/441.989 ms CI medians include lookup and establish retry-cleared failure, not the composition of the first miss.
+
 ### Trajectory readiness polling
 
 Trajectory activation samples its visible searchbox and a visible record inside `[data-trajectory-scroll]` on animation frames. Playwright's selector polling uses increasing delays up to 500 ms, so DOM readiness can precede the observer by hundreds of milliseconds. The trusted tab click, its actionability checks and the final two-frame wait remain timed; workload and the current 650 ms budget are unchanged.

.agents/notes/implemented/testing/2026-09-06-frontend-performance-budgets.zh.md

@@ -14,7 +14,7 @@ Node 对话折叠很快，并不能证明浏览器能绘制长对话或在流式
 
 `build:bench` 保留仅 Node 的 library 与 worker 构建。`test:bench` 额外构建 Web shell 后再运行所有用例；必需的基准 CI job 遵循[标准托管运行器说明](../../../../.github/workflows/ci.yml)，在该托管运行器上无条件安装 Chromium 及其 Linux 依赖，并启用现有门禁详细输出，使成功用例的原始样本可用于校准。浏览器用例复用产品组合的 Web scaffold，使用私有临时目录和原子分配的回环端口。只有不确定的模型被合成重放替代。scaffold Host 通过现有 Vitest 源码解析器运行；被测 Client 渲染在全新 Chromium 进程中执行构建后的 bundle。因此浏览器壁钟时间包含测试 Host、传输、Playwright 可交互性等待及渲染，不代表发布版 Host 进程。
 
-浏览器输入包含 240 个已关闭轮次、40 个工具结果和 20 个代码块，以及混合语言正文和推理。历史 Assistant 记录携带匹配的紧凑 stream，通过生产 accumulator 按 12 字符推理/文本 delta 和 8 字符工具参数 delta 构建；空 stream 会遗漏存储与传输负载成本。从观察到的初始 25 轮窗口开始，九次更早分页操作读完该输入；就绪探针跟踪已挂载轮次增长，不复制分页算法。每个样本使用全新 scaffold 和浏览器。环境准备、数据播种、浏览器启动、初始 shell 加载及侧栏展开不计入打开时间。打开测量在对话可用且输入框可编辑时结束；分页与导航测量在目标 DOM 状态出现时结束。两次动画帧包含一次渲染机会，不代表硬件显示或保证每个屏幕外节点都已绘制。
+浏览器输入包含 240 个已关闭轮次、40 个工具结果和 20 个代码块，以及混合语言正文和推理。历史 Assistant 记录携带匹配的紧凑 stream，通过生产 accumulator 按 12 字符推理/文本 delta 和 8 字符工具参数 delta 构建；空 stream 会遗漏存储与传输负载成本。从观察到的初始 25 轮窗口开始，九次更早分页操作读完该输入；就绪探针跟踪已挂载轮次增长，不复制分页算法。每个样本使用全新 scaffold 和浏览器。环境准备、数据播种、浏览器启动、初始 shell 加载及侧栏展开不计入打开时间。分页计时前解析恰好一个当前的 `Load earlier` 控件，将只读的无障碍查找归入准备。875 ms 分页上限仍包含可操作性等待、受信任的点击、已挂载 turn-tail 增长及最后两次动画帧；控件被替换时失败。打开测量在对话可用且输入框可编辑时结束；分页与导航测量在目标 DOM 状态出现时结束。两次动画帧包含一次渲染机会，不代表硬件显示或保证每个屏幕外节点都已绘制。
 
 续接以 16 ms 重放间隔发送 120 个文本 delta。输入观察器在从已聚焦输入框按 Enter 提交前安装；键入保留焦点，不执行鼠标重新聚焦，也不单独等待输入前动画帧。首段/最终标记查找在动画帧上采样最新 Assistant step 内的可见文本，避免选择器重试退避。隐藏文本和较早步骤中的标记均不能满足观察条件。首次观察在浏览器内记录回复标记与焦点；诊断在键入后取回，避免增加输入前的通信往返。诊断还记录首个实际输入事件的浏览器时钟时间戳与焦点。重放从不等待输入；响应阻塞仍可能导致重叠失败。同步输入证据读取同一个受限回复。全历史文本与无障碍查询会向测量区间加入观察器 CPU 和垃圾回收成本，因此减少此类观察工作属于基准修正，而非产品优化。它记录 Enter 提交到首段可见回复的时间、首个实际输入事件观察到首段回复且完成标记尚未出现时的真实草稿键入、直到持久化结算并渲染新 turn-tail 的完整回复壁钟时间，以及 Chromium 主线程任务时间。完整壁钟预算在缩放后的额外开销额度上加固定的 1984 ms 脚本节奏；输入和完成均有独立执行的预算。强制 GC 后的浏览器 heap 和 DOM 数量仍仅供诊断，因为单个终点不能证明泄漏。
 
@@ -22,7 +22,7 @@ Node 对话折叠很快，并不能证明浏览器能绘制长对话或在流式
 
 ## 校准
 
-在 arm64 参考机器、Node 24.19、Chromium 149.0.7827.55 和PR #3537 合并结果 上，三个样本的中位数建立下表基线。完整工作流 smoke 后执行一次隔离重复测量。每个浏览器样本报告原始终点数据和每一页；分页判定使用各样本最大值的中位数。重连报告全部子进程测量。下列历史参考表使用 8 ms 重放节奏，首段回复计时包含两帧等待。标准托管打开、分页、Trajectory 和重连预期在下文单独记录；其他源码参考常量保留这些额度。受限观察器的分页中位数 261.60 ms 超过 260 ms 参考额度，但仍低于 650 ms CI 限制；共享的 2× 时间倍率和 1.25× 方差余量产生 CI 限制。内存仅使用方差余量。共享倍率源自 Node CI 校准。下述两次实际 x64 浏览器运行在基准代码不变的情况下均通过固定预算；这提供这些 runner 的重复运行证据，而非普遍适用的浏览器速度比。
+在 arm64 参考机器、Node 24.19、Chromium 149.0.7827.55 和PR #3537 合并结果 上，三个样本的中位数建立下表基线。完整工作流 smoke 后执行一次隔离重复测量。每个浏览器样本报告原始终点数据和每一页；分页判定使用各样本最大值的中位数。重连报告全部子进程测量。下列历史参考表使用 8 ms 重放节奏，首段回复计时包含两帧等待。其中的分页样本包含较早分页控件的无障碍查找。标准托管打开、分页、Trajectory 和重连预期在下文单独记录；其他源码参考常量保留这些额度。受限观察器的分页中位数 261.60 ms 超过 260 ms 参考额度，但仍低于 650 ms CI 限制；共享的 2× 时间倍率和 1.25× 方差余量产生 CI 限制。内存仅使用方差余量。共享倍率源自 Node CI 校准。下述两次实际 x64 浏览器运行在基准代码不变的情况下均通过固定预算；这提供这些 runner 的重复运行证据，而非普遍适用的浏览器速度比。
 
 | 终点 | 实测中位数 | 参考额度 | 历史 CI 限制 |
 |---|---:|---:|---:|
@@ -72,6 +72,12 @@ Node 对话折叠很快，并不能证明浏览器能绘制长对话或在流式
 
 当前 Trajectory 验收上限为 650 ms，由 520 ms 目标与共享的 1.25× 余量表示。运行 35095609422 的首次执行与重试分别记录中位数 666.651723 ms 和 630.843184 ms。相较于原先的 625 ms 上限，这次明确的 4% 放宽接受重试中位数，但仍拒绝首次中位数；这是预算决策，不代表测得产品提速。记录的重试样本覆盖新增的接受区间，同一个判定断言拒绝 651 ms。其他终点预算与工作负载参数保持不变。
 
+### 较早分页控件准备
+
+较早分页测量先等待具有唯一名称的控件挂载，再捕获该控件。可用性与只读的无障碍查找归入准备；可见、启用及稳定等可操作性检查、受信任的点击、turn-tail 增长和最后两帧仍计时。历史 260 ms 参考额度、261.60 ms 中位数及 700 ms 托管预期包含当前终点已排除的查找。
+
+排除查找后的本地样本为 141.202083/126.114041/140.003334 ms，中位数 140.003334 ms。托管运行 37272669722 的 benchmark job 111642813553 记录 524.083466/355.648835/349.959862 ms，中位数 355.648835 ms，仍通过相同的 875 ms 上限。这些是观察样本，不是新校准；700 ms 预期与 875 ms 上限作为保守的现有值保留，待此终点的重复托管测量核验。先前相同 checkout 的 887.624/441.989 ms CI 中位数包含查找，只建立重跑可清除的失败，不分解首次超限的组成。
+
 ### Trajectory 就绪轮询
 
 Trajectory 激活在动画帧上采样可见搜索框与 `[data-trajectory-scroll]` 内的可见记录。Playwright 选择器轮询使用逐步增加、最高 500 ms 的延迟，因此 DOM 可能比观察器早数百毫秒就绪。真实 tab 点击、其可交互性检查与最后两帧等待仍计时；工作负载与当前 650 ms 预算不变。

benchmarks/long-session-browser/README.i18n.yaml

@@ -9,5 +9,5 @@
   en: e52e52132fec9fbd
   zh: fd2265d32153358a
 /long-session-browser-benchmark/measurements:
-  en: dd010ca8b05cf27a
-  zh: 7921924e92ac145c
+  en: 0cf9081811536a04
+  zh: 65e378793c8fca14

benchmarks/long-session-browser/README.md

@@ -10,7 +10,7 @@ The required Chromium workflow in [long-session.bench.ts](long-session.bench.ts)
 
 ## Measurements
 
-Three fresh browser processes and scaffold worlds produce raw samples and median verdicts. Open and paging end after the expected transcript state and two animation frames; this includes a rendering opportunity, not a hardware presentation timestamp. Paging reports every page and gates the median of each sample’s slowest page. Stream reports first visible reply, trusted draft typing, complete reply wall time, and Chromium main-thread task duration. Enter submits from the focused composer; draft typing retains that focus without a mouse click. Reply-marker lookups and the input-event text witness read only the latest Assistant step, avoiding repeated whole-history text and accessibility scans. The input witness is installed before submission, and draft typing starts as soon as the first marker is visible, without an extra pre-input animation-frame wait. Reply markers are sampled on animation frames, with visible text required inside the latest step. The first observation captures marker state and focus in the browser; its diagnostics are retrieved after typing so they add no pre-input round trip. Diagnostics also include browser-clock timestamps and focus at the first input event. They do not pause replay; a delayed first observation or input can still fail overlap. The actual first input event must observe an unfinished reply; completion waits for the new rendered turn-tail after Host settlement. After measurement, a trusted keystroke after DONE must fail the same overlap assertion. Open, the slowest older page, and first Trajectory use standard-hosted expectations of 900/700/520 ms. Shared 1.25× headroom gives limits of 1125/875/650 ms respectively; stream endpoint overhead budgets are unchanged. Heap after forced GC and DOM counts are diagnostics, not leak budgets.
+Three fresh browser processes and scaffold worlds produce raw samples and median verdicts. Open and paging end after the expected transcript state and two animation frames; this includes a rendering opportunity, not a hardware presentation timestamp. Paging waits for the named `Load earlier` control to attach and resolves exactly one current button before timing; actionability, the trusted click, turn-tail growth and the final two animation frames remain timed. A replaced button fails instead of selecting a replacement. Paging reports every page and gates the median of each sample’s slowest page. Stream reports first visible reply, trusted draft typing, complete reply wall time, and Chromium main-thread task duration. Enter submits from the focused composer; draft typing retains that focus without a mouse click. Reply-marker lookups and the input-event text witness read only the latest Assistant step, avoiding repeated whole-history text and accessibility scans. The input witness is installed before submission, and draft typing starts as soon as the first marker is visible, without an extra pre-input animation-frame wait. Reply markers are sampled on animation frames, with visible text required inside the latest step. The first observation captures marker state and focus in the browser; its diagnostics are retrieved after typing so they add no pre-input round trip. Diagnostics also include browser-clock timestamps and focus at the first input event. They do not pause replay; a delayed first observation or input can still fail overlap. The actual first input event must observe an unfinished reply; completion waits for the new rendered turn-tail after Host settlement. After measurement, a trusted keystroke after DONE must fail the same overlap assertion. Open, the slowest older page, and first Trajectory use standard-hosted expectations of 900/700/520 ms. Shared 1.25× headroom gives limits of 1125/875/650 ms respectively; stream endpoint overhead budgets are unchanged. Heap after forced GC and DOM counts are diagnostics, not leak budgets.
 
 Trajectory readiness is sampled on animation frames from the visible searchbox and a visible record inside its own table. The trusted tab click and final two-frame wait remain inside the measured interval; hidden records and unrelated table rows cannot satisfy readiness.
 

benchmarks/long-session-browser/README.zh.md

@@ -10,7 +10,7 @@
 
 ## 测量
 
-三个全新浏览器进程与 scaffold 环境产生原始样本及中位数判定。打开和分页在预期 transcript（文本记录）状态出现且经过两次动画帧后结束；这包含一次渲染机会，而非硬件显示时间戳。分页报告每一页，并对各样本最慢分页时间的中位数执行预算检查。流式报告首次可见回复、受信任的草稿键入、完整回复壁钟时间和 Chromium 主线程任务时间。Enter 从已聚焦的输入框提交；草稿键入保留该焦点，不执行鼠标点击。回复标记查找与输入事件文本观察器仅读取最新 Assistant 步骤，避免重复进行全量历史文本扫描和无障碍扫描。输入事件文本观察器在提交前安装，首个标记可见后立即开始草稿键入，不额外等待输入前动画帧。回复标记在动画帧上采样，要求文本在最新步骤内可见。首次观察在浏览器内记录标记状态与焦点；诊断在键入后取回，不增加输入前的通信往返。诊断还包含首个输入事件的浏览器时钟时间戳与焦点。诊断不会暂停回放；首次观察或输入延迟仍可能导致重叠失败。实际首个输入事件必须观察到未完成的回复；完整回复的测量会在 Host 结算后等待新 turn-tail 渲染完成。测量后，在 DONE 之后发送的受信任按键必须无法通过同一个重叠断言。打开、最慢的较早页面和首次 Trajectory 使用标准托管预期 900/700/520 ms。共享的 1.25× 余量分别产生 1125/875/650 ms 上限；流式终点的额外开销预算不变。强制 GC 后的 heap 与 DOM 数量仅供诊断，不作为泄漏预算。
+三个全新浏览器进程与 scaffold 环境产生原始样本及中位数判定。打开和分页在预期 transcript（文本记录）状态出现且经过两次动画帧后结束；这包含一次渲染机会，而非硬件显示时间戳。分页计时前先等待名为 `Load earlier` 的控件挂载，再解析恰好一个当前按钮；可操作性等待、受信任的点击、turn-tail 增长及最后两次动画帧仍计时。按钮被替换时失败，不改选替代节点。分页报告每一页，并对各样本最慢分页时间的中位数执行预算检查。流式报告首次可见回复、受信任的草稿键入、完整回复壁钟时间和 Chromium 主线程任务时间。Enter 从已聚焦的输入框提交；草稿键入保留该焦点，不执行鼠标点击。回复标记查找与输入事件文本观察器仅读取最新 Assistant 步骤，避免重复进行全量历史文本扫描和无障碍扫描。输入事件文本观察器在提交前安装，首个标记可见后立即开始草稿键入，不额外等待输入前动画帧。回复标记在动画帧上采样，要求文本在最新步骤内可见。首次观察在浏览器内记录标记状态与焦点；诊断在键入后取回，不增加输入前的通信往返。诊断还包含首个输入事件的浏览器时钟时间戳与焦点。诊断不会暂停回放；首次观察或输入延迟仍可能导致重叠失败。实际首个输入事件必须观察到未完成的回复；完整回复的测量会在 Host 结算后等待新 turn-tail 渲染完成。测量后，在 DONE 之后发送的受信任按键必须无法通过同一个重叠断言。打开、最慢的较早页面和首次 Trajectory 使用标准托管预期 900/700/520 ms。共享的 1.25× 余量分别产生 1125/875/650 ms 上限；流式终点的额外开销预算不变。强制 GC 后的 heap 与 DOM 数量仅供诊断，不作为泄漏预算。
 
 Trajectory 就绪状态在动画帧上采样，要求搜索框可见且其自身表格中存在可见记录。真实 tab 点击和最后的两帧等待仍计入测量区间；隐藏记录与无关表格行不能满足就绪条件。
 

benchmarks/long-session-browser/long-session.bench.ts

@@ -4,7 +4,7 @@ import { tmpdir } from 'node:os'
 import { join } from 'node:path'
 import { performance } from 'node:perf_hooks'
 import { chromium, type Page, type CDPSession, type Locator } from 'playwright'
-import { expect, it } from 'vitest'
+import { expect, it, vi } from 'vitest'
 import { launchWebScaffold, seedSession, watchConsole, webSnapshotMode } from '../../apps/web/tests/scaffold.ts'
 import { newEnglishPage } from '../../apps/web/tests/support.ts'
 import { ciTimeBudget, PERFORMANCE_BUDGET_HEADROOM } from '../support/calibration.ts'
@@ -26,11 +26,27 @@ async function painted(page: Page): Promise<void> {
   await page.evaluate(() => new Promise<void>(resolve => requestAnimationFrame(() => requestAnimationFrame(() => resolve()))))
 }
 
-async function measure(page: Page, action: () => Promise<void>): Promise<number> {
-  const start = performance.now()
+async function measure(page: Page, action: () => Promise<void>, now = () => performance.now()): Promise<number> {
+  const start = now()
   await action()
   await painted(page)
-  return performance.now() - start
+  return now() - start
+}
+
+/** Time one trusted paging action after resolving its unique button. */
+async function measureOlderPage(page: Page, previous: number, now = () => performance.now()): Promise<number> {
+  const locator = page.getByRole('button', { name: 'Load earlier', exact: true })
+  await locator.waitFor({ state: 'attached' })
+  const buttons = await locator.elementHandles()
+  try {
+    expect(buttons).toHaveLength(1)
+    return await measure(page, async () => {
+      await buttons[0]!.click()
+      await page.waitForFunction(({ selector, previous }) => document.querySelectorAll(selector).length > previous, { selector: TAIL, previous })
+    }, now)
+  } finally {
+    await Promise.all(buttons.map(button => button.dispose()))
+  }
 }
 
 async function taskMs(cdp: CDPSession): Promise<number> {
@@ -155,6 +171,166 @@ it('waits for visible Trajectory controls and records rather than unrelated tabl
   }
 })
 
+it('excludes older-page selector preparation while retaining the trusted click', async () => {
+  const browser = await chromium.launch({ headless: true })
+  const entered = Promise.withResolvers<undefined>()
+  const release = Promise.withResolvers<undefined>()
+  let operation: Promise<{ value: number } | { error: unknown }> | undefined
+  try {
+    const page = await browser.newPage()
+    await page.setContent('<button type="button">Load earlier</button><div data-chat-flow-key="9:turn-tail"></div>')
+    await page.locator('button').evaluate(button => {
+      button.addEventListener('click', event => {
+        button.setAttribute('data-click-trusted', String(event.isTrusted))
+        const tail = document.createElement('div')
+        tail.setAttribute('data-chat-flow-key', '9:turn-tail:next')
+        document.body.append(tail)
+      })
+    })
+    const button = page.getByRole('button', { name: 'Load earlier', exact: true })
+    const click = button.click.bind(button)
+    const elementHandles = button.elementHandles.bind(button)
+    const prepare = async (): Promise<void> => { entered.resolve(undefined); await release.promise }
+    vi.spyOn(page, 'getByRole').mockReturnValue(button)
+    // The Locator spy gates preparation in the original selector-inside-timer control.
+    vi.spyOn(button, 'click').mockImplementation(async options => { await prepare(); await click(options) })
+    vi.spyOn(button, 'elementHandles').mockImplementation(async () => { await prepare(); return elementHandles() })
+    let now = 0
+    operation = measureOlderPage(page, 1, () => now).then(value => ({ value }), (error: unknown) => ({ error }))
+    await Promise.race([
+      entered.promise,
+      operation.then(outcome => {
+        if ('error' in outcome) throw outcome.error
+        throw new Error('Paging completed before the selector preparation barrier')
+      }),
+    ])
+    expect(await page.locator('button').getAttribute('data-click-trusted')).toBeNull()
+    expect(await page.locator(TAIL).count()).toBe(1)
+    now = PAGE_BUDGET_MS + 1
+    release.resolve(undefined)
+    const outcome = await operation
+    if ('error' in outcome) throw outcome.error
+    expectEndpointWithinBudget(outcome.value, PAGE_BUDGET_MS)
+    expect(outcome.value).toBe(0)
+    expect(await page.locator('button').getAttribute('data-click-trusted')).toBe('true')
+    expect(await page.locator(TAIL).count()).toBe(2)
+  } finally {
+    release.resolve(undefined)
+    try { await browser.close() } finally {
+      try { await operation } finally { vi.restoreAllMocks() }
+    }
+  }
+})
+
+it('waits for a named older-page control before starting its clock', async () => {
+  const browser = await chromium.launch({ headless: true })
+  const entered = Promise.withResolvers<undefined>()
+  let operation: Promise<{ value: number } | { error: unknown }> | undefined
+  try {
+    const page = await browser.newPage()
+    await page.setContent('<button type="button" disabled>Loading…</button><div data-chat-flow-key="9:turn-tail"></div>')
+    await page.locator('button').evaluate(button => {
+      button.addEventListener('click', event => {
+        button.setAttribute('data-click-trusted', String(event.isTrusted))
+        const tail = document.createElement('div')
+        tail.setAttribute('data-chat-flow-key', '9:turn-tail:next')
+        document.body.append(tail)
+      })
+    })
+    const locator = page.getByRole('button', { name: 'Load earlier', exact: true })
+    const waitFor = locator.waitFor.bind(locator)
+    vi.spyOn(page, 'getByRole').mockReturnValue(locator)
+    vi.spyOn(locator, 'waitFor').mockImplementation(options => { entered.resolve(undefined); return waitFor(options) })
+    let now = 0
+    operation = measureOlderPage(page, 1, () => now).then(value => ({ value }), (error: unknown) => ({ error }))
+    await Promise.race([
+      entered.promise,
+      operation.then(outcome => {
+        if ('error' in outcome) throw outcome.error
+        throw new Error('Paging completed before control readiness')
+      }),
+    ])
+    expect(await page.locator('button').getAttribute('data-click-trusted')).toBeNull()
+    now = PAGE_BUDGET_MS + 1
+    await page.locator('button').evaluate(button => {
+      button.textContent = 'Load earlier'
+      button.removeAttribute('disabled')
+    })
+    const outcome = await operation
+    if ('error' in outcome) throw outcome.error
+    expect(outcome.value).toBe(0)
+    expect(await page.locator('button').getAttribute('data-click-trusted')).toBe('true')
+    expect(await page.locator(TAIL).count()).toBe(2)
+  } finally {
+    try { await browser.close() } finally {
+      try { await operation } finally { vi.restoreAllMocks() }
+    }
+  }
+})
+
+it('keeps browser deadlines active with a fixed measurement clock', async () => {
+  const browser = await chromium.launch({ headless: true })
+  try {
+    const page = await browser.newPage()
+    await expect(measure(page, async () => {
+      const pending = await page.waitForFunction(() => false, undefined, { timeout: 100 })
+      await pending.dispose()
+    }, () => 0)).rejects.toThrow('Timeout 100ms exceeded')
+  } finally {
+    await browser.close()
+  }
+})
+
+it('rejects older-page rendering beyond the unchanged paging ceiling', async () => {
+  const browser = await chromium.launch({ headless: true })
+  let operation: Promise<{ value: number } | { error: unknown }> | undefined
+  try {
+    const page = await browser.newPage()
+    await page.setContent('<button type="button">Load earlier</button><div data-chat-flow-key="9:turn-tail"></div>')
+    await page.locator('button').evaluate(button => {
+      button.addEventListener('click', event => { button.setAttribute('data-click-trusted', String(event.isTrusted)) })
+    })
+    let now = 0
+    operation = measureOlderPage(page, 1, () => now).then(value => ({ value }), (error: unknown) => ({ error }))
+    await page.waitForFunction(() => document.querySelector('button')?.getAttribute('data-click-trusted') === 'true')
+    now = PAGE_BUDGET_MS + 1
+    await page.evaluate(() => {
+      const tail = document.createElement('div')
+      tail.setAttribute('data-chat-flow-key', '9:turn-tail:next')
+      document.body.append(tail)
+    })
+    const outcome = await operation
+    if ('error' in outcome) throw outcome.error
+    expect(outcome.value).toBe(PAGE_BUDGET_MS + 1)
+    expect(() => expectEndpointWithinBudget(outcome.value, PAGE_BUDGET_MS)).toThrow()
+  } finally {
+    try { await browser.close() } finally {
+      try { await operation } finally { vi.restoreAllMocks() }
+    }
+  }
+})
+
+it('rejects ambiguous or replaced older-page buttons before paging', async () => {
+  const browser = await chromium.launch({ headless: true })
+  try {
+    const page = await browser.newPage()
+    await page.setContent('<button type="button">Load earlier</button><button type="button">Load earlier</button>')
+    await expect(measureOlderPage(page, 0)).rejects.toThrow('strict mode violation')
+    await page.setContent('<button type="button">Load earlier</button>')
+    const button = page.getByRole('button', { name: 'Load earlier', exact: true })
+    const elementHandles = button.elementHandles.bind(button)
+    vi.spyOn(page, 'getByRole').mockReturnValue(button)
+    vi.spyOn(button, 'elementHandles').mockImplementation(async () => {
+      const handles = await elementHandles()
+      await button.evaluate(element => { element.replaceWith(element.cloneNode(true)) })
+      return handles
+    })
+    await expect(measureOlderPage(page, 0)).rejects.toThrow('Element is not attached')
+  } finally {
+    try { await browser.close() } finally { vi.restoreAllMocks() }
+  }
+})
+
 it('opens, pages, navigates and streams into a 240-turn browser history', async () => {
   if (webSnapshotMode() !== 'replay') throw new Error('browser benchmarks require keyless replay mode')
   const samples: { open: number; page: number; trajectory: number; first: number; streamTask: number; streamWall: number; input: number; inputOverlapped: boolean; heapMb: number; nodes: number }[] = []
@@ -192,10 +368,7 @@ it('opens, pages, navigates and streams into a 240-turn browser history', async
           expect(initialTurns).toBeLessThan(HISTORY_TURNS)
           let count = initialTurns
           while (count < HISTORY_TURNS) {
-            pages.push(await measure(page, async () => {
-              await page.getByRole('button', { name: 'Load earlier', exact: true }).click()
-              await page.waitForFunction(({ selector, previous }) => document.querySelectorAll(selector).length > previous, { selector: TAIL, previous: count })
-            }))
+            pages.push(await measureOlderPage(page, count))
             count = await page.locator(TAIL).count()
           }
           const trajectory = await measure(page, async () => {