Merge branch 'master' into fix/web-ui-optimization

.agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.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 .agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.md
-2026-07-16-persistent-pty-sessions.md: 55ab262b89526911e16a3fec5dd624fc42fb2222
-2026-07-16-persistent-pty-sessions.zh.md: 525d199298bc071c36444d689368317968186c9f
+2026-07-16-persistent-pty-sessions.md: 691ccd4341837d63bb48d27c2a3fb007657fe7ba
+2026-07-16-persistent-pty-sessions.zh.md: 86d57f79ee74429542730ebcad60bc9f3c9f15ca

.agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.md

@@ -74,7 +74,7 @@ With `run_in_background: true`, `dsh-tool-pty` registers the in-flight send on `
 
 The local backend first recognizes a private OSC prompt marker emitted by its controlled bash startup, then requires printable prompt text after that marker before declaring prompt readiness and runs three bounded fallback tiers. Carrying that state across data callbacks covers macOS delivery where the OSC marker and `PS1` arrive separately; the marker alone can no longer publish an empty MOTD. The marker is removed before output reaches the model and avoids a fixed silence delay for ordinary shell commands on both platforms. Unpublished startup does not accept zero-output silence as readiness; timeout rejects the spawn. If caller cancellation wins during startup, the backend closes the private session and propagates the exact `AbortSignal.reason`; a foreground PGID that is not observable yet cannot replace cancellation with a lookup error. All timings are validated config fields: `pollIntervalMs`, `exactProbeAfterMs`, `idleSilenceMs`, `handoffGraceMs`, and `timeoutMs`.
 
-On Linux, the inspector reads the shell's terminal foreground PGID from `/proc/<shellPid>/stat`, enumerates every process and thread in that process group, and probes their current syscalls. A positive Tier 1 result requires an observed stdin wait: direct `read(0)`, a permitted read of a `select`/`pselect6` or `poll`/`ppoll` argument containing fd 0, or an epoll interest list containing fd 0. Unreadable process memory and unrecognized syscalls are misses, never positive guesses. Architecture tables contain only syscall numbers defined by the corresponding Linux UAPI; unsupported architectures skip Tier 1.
+On Linux, the inspector reads the shell's terminal foreground PGID from `/proc/<shellPid>/stat`, enumerates every process and thread in that process group, and probes their current syscalls. A positive Tier 1 result requires an observed stdin wait: direct `read(0)`, a permitted read of a `select`/`pselect6` or `poll`/`ppoll` argument containing fd 0, or an epoll interest list containing fd 0. A wait already present before terminal input is not post-write readiness: the same PGID must be observed outside that wait before re-entering it, while a changed foreground PGID is new evidence. Unreadable process memory and unrecognized syscalls are misses, never positive guesses. Architecture tables contain only syscall numbers defined by the corresponding Linux UAPI; unsupported architectures skip Tier 1.
 
 On macOS there is no exact syscall tier. Output silence returns `inferred_idle` for any foreground process group, including Python and `gdb`; `ps`-derived terminal PGID is used for signaling, not as proof that only the shell can be idle. Pure process-inspector logic is injectable and unit-tested on Linux, while a macOS CI job exercises the real PTY and process-table path.
 
@@ -155,7 +155,7 @@ The package ships concise tool guidance explaining persistent state, owner isola
 
 ## Verification
 
-- Per-file coverage pins owner fencing, concurrent reservations, unpublished-spawn cancellation and awaited teardown, sandbox-mode change rejection, retriable lifecycle cleanup, readiness tiers, the configured handoff grace holding the idle fallback past one poll and its rejection below `pollIntervalMs`, sanitizer carry state, complete UTF-8 bounds, task integration, schemas, and exact render intents.
+- Per-file coverage pins owner fencing, concurrent reservations, unpublished-spawn cancellation and awaited teardown, sandbox-mode change rejection, retriable lifecycle cleanup, readiness tiers, rejection of pre-write stdin waits, the configured handoff grace holding the idle fallback past one poll and its rejection below `pollIntervalMs`, sanitizer carry state, complete UTF-8 bounds, task integration, schemas, and exact render intents.
 - Linux process fixtures cover non-leader and non-main-thread stdin waits, zombie quiescence, unreadable process state, supported syscall tables, unsupported architectures, and false-positive rejection; macOS inspector logic is injected into the same unit suite.
 - Real `node-pty` tests exercise shell state, shared sandbox policy, environment scrubbing, raw-mode foreground `SIGINT` after deliberately delayed child readiness under scenario-owned timing bounds, a TERM-ignoring descendant, and immediate post-disposal quiescence on supported hosts.
 - A Loader-driven `cordis.yml` test mounts the real three-package composition. ACP and headless snapshots pin the six schemas, bounded results, and errors through opt-in overlays; TUI snapshots pin terminal and generic card presentation.
@@ -168,7 +168,7 @@ The package ships concise tool guidance explaining persistent state, owner isola
 
 **Idle below Linux Tier 1 is heuristic.** Output silence cannot distinguish a prompt from sleep or network I/O. The typed result preserves uncertainty, and bounded timeout plus task waiting and signaling keep control with the model.
 
-**The exact-versus-inferred boundary is a latency trade, not a solvable race.** Attribution depends on whether the kernel publishes the foreground handoff before or after the silence bound elapses, so any fixed grace is a scheduling bet. `handoffGraceMs` puts that bet in deployment configuration: raising it buys exact `stdin_read` attribution on a slow or loaded host at the cost of interactive return latency after a prompt marker, and lowering it does the reverse. Tests that must not depend on the winner assert the observable behavior — the next send runs — rather than the attribution.
+**The exact-versus-inferred boundary is a latency trade, not a solvable race.** Attribution depends on whether the kernel publishes the foreground handoff before or after the silence bound elapses, so any fixed grace is a scheduling bet. `handoffGraceMs` puts that bet in deployment configuration: raising it buys exact `stdin_read` attribution on a slow or loaded host at the cost of interactive return latency after a prompt marker, and lowering it does the reverse. Tests that must not depend on the winner assert child-produced output from the next send, using a token absent from echoed input, rather than the attribution.
 
 **Persistent state can drift from the model's belief.** The model may forget its cwd or active REPL. Session summaries and retained output help recovery, but no prompt can make state persistence deterministic.
 

.agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.zh.md

@@ -74,7 +74,7 @@ UI 渲染契约精确且不携带位置信息。`terminal_send` 只为前台发
 
 本地后端先识别受控 bash 启动时发出的私有 OSC prompt marker，并且只有在该 marker 后出现可打印的 prompt 文本时才据此声明 prompt 就绪；除此之外，它还运行 3 个有界 fallback 层级。在 data callback 之间保留这项状态，可以适配 macOS 分开交付 OSC marker 与 `PS1` 的情况；单独的 marker 不会发布空 MOTD。marker 在输出到达模型前被移除，使两个平台上的普通 shell 命令都无需固定等待静默阈值。尚未发布的 startup 不会把零输出静默视为就绪；timeout 会拒绝 spawn。若调用方取消在 startup 期间胜出，后端会关闭私有会话并原样抛出 `AbortSignal.reason`；尚不可观察的前台 PGID 不会再用查找错误覆盖取消原因。所有时间参数都是经校验的配置字段：`pollIntervalMs`、`exactProbeAfterMs`、`idleSilenceMs`、`handoffGraceMs` 和 `timeoutMs`。
 
-在 Linux 上，检查器从 `/proc/<shellPid>/stat` 读取 shell 的终端前台 PGID，枚举该进程组中的每个进程与线程，并检查它们当前的 syscall。Tier 1 只有观察到 stdin 等待才返回正结果：直接 `read(0)`、获准读取且含 fd 0 的 `select`/`pselect6` 或 `poll`/`ppoll` 参数，或者含 fd 0 的 epoll interest list。无法读取的进程内存和未识别的 syscall 都是 miss，绝不作为正向猜测。架构表只包含对应 Linux UAPI 定义的 syscall number；不支持的架构跳过 Tier 1。
+在 Linux 上，检查器从 `/proc/<shellPid>/stat` 读取 shell 的终端前台 PGID，枚举该进程组中的每个进程与线程，并检查它们当前的 syscall。Tier 1 只有观察到 stdin 等待才返回正结果：直接 `read(0)`、获准读取且含 fd 0 的 `select`/`pselect6` 或 `poll`/`ppoll` 参数，或者含 fd 0 的 epoll interest list。终端输入前就已存在的等待并不代表写入后就绪：必须先观察到同一 PGID 脱离该等待，之后再次进入等待才能使该次 send 完成；前台 PGID 发生变化则构成新的证据。无法读取的进程内存和未识别的 syscall 都是 miss，绝不作为正向猜测。架构表只包含对应 Linux UAPI 定义的 syscall number；不支持的架构跳过 Tier 1。
 
 macOS 没有精确 syscall 层。任何前台进程组输出静默都会返回 `inferred_idle`，包括 Python 和 `gdb`；从 `ps` 推导的终端 PGID 只用于发送信号，不作为「只有 shell 才能 idle」的证明。纯进程检查逻辑可注入并在 Linux 上完成 unit 覆盖率，同时由 macOS CI job 驱动真实 PTY 和进程表路径。
 
@@ -155,7 +155,7 @@ plugins:
 
 ## 验证
 
-- 每文件覆盖率固定 owner 隔离、并发预留、未发布 spawn 的取消与等待式 teardown、沙箱模式变更拒绝、可重试的生命周期清理、就绪层级、配置化交接宽限把 idle fallback 顶过一次轮询以及低于 `pollIntervalMs` 时的拒绝、sanitizer carry state、完整 UTF-8 结果上限、task 集成、schema 和精确 render intent。
+- 每文件覆盖率固定 owner 隔离、并发预留、未发布 spawn 的取消与等待式 teardown、沙箱模式变更拒绝、可重试的生命周期清理、就绪层级、对写入前 stdin 等待的拒绝、配置化交接宽限把 idle fallback 顶过一次轮询以及低于 `pollIntervalMs` 时的拒绝、sanitizer carry state、完整 UTF-8 结果上限、task 集成、schema 和精确 render intent。
 - Linux 进程 fixture 覆盖非 leader 与非主线程的 stdin 等待、僵尸进程静止性、不可读进程状态、受支持的 syscall 表、不支持的架构和误报拒绝；同一单元测试套件通过注入覆盖 macOS 检查器逻辑。
 - 真实 `node-pty` 测试在受支持宿主上覆盖 shell 状态、共享沙箱策略、环境清洗、在由场景掌控的时间界限内先有意延迟子进程就绪，再对 raw mode 前台进程发送 `SIGINT`、忽略 `SIGTERM` 的子进程，以及 dispose 返回后立即完全停稳。
 - Loader 驱动的 `cordis.yml` 测试挂载真实三包组合。ACP 与 headless 快照通过 opt-in overlay 固定 6 个 schema、有界结果和错误；TUI 快照固定 terminal 与 generic 卡片展示。
@@ -168,7 +168,7 @@ plugins:
 
 **Linux Tier 1 之外的 idle 都是启发式结果。**输出静默无法区分 prompt、sleep 和网络 I/O。类型化结果保留不确定性，有界 timeout、task 等待与信号让模型仍能掌握控制权。
 
-**精确归因与推断归因的边界是延迟取舍，不是可消除的竞态。**归因取决于内核在静默上限到达之前还是之后发布前台交接，因此任何固定宽限都是一次调度上的赌注。`handoffGraceMs` 把这个赌注交给部署配置：调大它可以在慢速或高负载主机上换到精确的 `stdin_read` 归因，代价是见过 prompt marker 之后的交互返回延迟；调小则相反。不应依赖胜负结果的测试断言可观察行为——下一次 send 能正常执行——而不是断言归因路径。
+**精确归因与推断归因的边界是延迟取舍，不是可消除的竞态。**归因取决于内核在静默上限到达之前还是之后发布前台交接，因此任何固定宽限都是一次调度上的赌注。`handoffGraceMs` 把这个赌注交给部署配置：调大它可以在慢速或高负载主机上换到精确的 `stdin_read` 归因，代价是见过 prompt marker 之后的交互返回延迟；调小则相反。不应依赖胜负结果的测试使用不会出现在输入回显中的 token，断言下一次 send 中由子进程产生的输出，而不是断言归因路径。
 
 **持久状态可能偏离模型认知。**模型可能忘记 cwd 或活跃 REPL。会话摘要和保留输出有助恢复，但任何 prompt 都无法让状态持久化变成确定行为。
 

packages/llm/llm-retry/tests/transport-recovery.spec.ts

@@ -204,7 +204,9 @@ describe('bounded retry through the real DeepSeek HTTP/SSE adapter', () => {
       apiKey: 'mock-key',
       successText: 'recovered after timeout',
     })
-    context = await harness(server.baseURL, { streamIdleTimeoutMs: 30 })
+    // This crosses the real HTTP idle timer, so leave scheduler slack between
+    // the stalled attempt and the mock server's immediate successful response.
+    context = await harness(server.baseURL, { streamIdleTimeoutMs: 1_000 })
     const agent = context.agentLoop.create(SessionId('wire-stall'), {
       provider: 'deepseek',
       model: 'mock-model',
@@ -216,7 +218,7 @@ describe('bounded retry through the real DeepSeek HTTP/SSE adapter', () => {
     expect(agent.session.events.filter(event => event.type === 'llm/retry').map(event => event.data.failure.code))
       .toEqual(['TIMEOUT'])
     expect(finalAssistantText(agent)).toBe('recovered after timeout')
-  })
+  }, 10_000)
 
   it('stops after the configured transport retry budget is exhausted', async () => {
     const server = await start(['connection_reset', 'connection_reset', 'connection_reset'], {

packages/pty/pty-local/README.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # 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
-README.md: abc7d9bc81b6ec43bed6277de7f42ddf5728c7a8
-README.zh.md: 7a99a303ac3b6c83e2acd0f8154e9b313ef673d1
+#   pnpm run verify-translation-pairing --write packages/pty/pty-local/README.md
+README.md: 6f243a6edf3ab8bc228cfda3f6b3b774dabadcbb
+README.zh.md: c417828a443d227b5bfcdc1c788cf4ab6751b2ee

packages/pty/pty-local/README.md

@@ -8,7 +8,7 @@ Local Linux/macOS `node-pty` backend for `ctx.pty`; loading it on another platfo
 
 The plugin injects `pty`, `sandbox`, and `sandboxPolicy`, then registers the configured backend type (`shell`). `danger-full-access` starts the shell directly; confined modes wrap the exact shell argv through `ctx.sandbox`. The effective session mode is resolved at spawn. A change to a different effective mode is rejected before its `sandbox/mode` event commits while that owner has an open PTY or a spawn in progress; the fence is attached to the exact owner and therefore outlives a local-provider reload that retains existing sessions. Wait for creation to settle and close the sessions before changing modes, so a terminal opened with wider access cannot survive a downgrade.
 
-Linux readiness combines a foreground-verified private bash prompt marker, foreground-process-group syscall inspection, silence fallback, and absolute timeout. macOS uses the verified prompt marker plus silence/timeout because it has no `/proc` syscall surface. A marker is not ready until printable prompt text arrives, including when the OSC marker and `PS1` are split across data callbacks; when bash prints the marker before the kernel publishes its return to the foreground process group, polling retains the candidate for `handoffGraceMs` past the ordinary silence bound so a coincident handoff can win; that grace must cover at least one `pollIntervalMs` and is rejected at load otherwise. An interactive child that inherits `PROMPT_COMMAND` therefore cannot suppress inferred-idle readiness until the absolute timeout. Unrecognized or unreadable process state is never a positive exact-idle signal. During unpublished startup, a fallback requires observed output; zero-output silence cannot publish an empty session, and timeout rejects the spawn. Cancellation closes the unpublished shell and rejects with the caller's exact abort reason even when its foreground process group is not observable yet; if that close fails, `PtyBackendCleanupError` separately preserves the cleanup failure for registry disposal. Incomplete terminal-control sequences are bounded by `maxReadBytes` and discarded through their terminator after crossing that limit; a trailing carriage return is carried across callbacks so split CRLF becomes one newline.
+Linux readiness combines a foreground-verified private bash prompt marker, foreground-process-group syscall inspection, silence fallback, and absolute timeout. macOS uses the verified prompt marker plus silence/timeout because it has no `/proc` syscall surface. A marker is not ready until printable prompt text arrives, including when the OSC marker and `PS1` are split across data callbacks; when bash prints the marker before the kernel publishes its return to the foreground process group, polling retains the candidate for `handoffGraceMs` past the ordinary silence bound so a coincident handoff can win; that grace must cover at least one `pollIntervalMs` and is rejected at load otherwise. An interactive child that inherits `PROMPT_COMMAND` therefore cannot suppress inferred-idle readiness until the absolute timeout. Unrecognized or unreadable process state is never a positive exact-idle signal. A foreground group's stdin wait that already existed before a send is likewise not post-write readiness: the same group must be observed outside that wait before a later wait can settle the send, while a changed foreground group is new evidence. During unpublished startup, a fallback requires observed output; zero-output silence cannot publish an empty session, and timeout rejects the spawn. Cancellation closes the unpublished shell and rejects with the caller's exact abort reason even when its foreground process group is not observable yet; if that close fails, `PtyBackendCleanupError` separately preserves the cleanup failure for registry disposal. Incomplete terminal-control sequences are bounded by `maxReadBytes` and discarded through their terminator after crossing that limit; a trailing carriage return is carried across callbacks so split CRLF becomes one newline.
 
 Send cancellation resolves the current foreground process group and delivers a real `SIGINT`; it never emulates interruption by writing `\x03`, so raw-mode programs remain cancellable. Close sends `SIGTERM` to descendants, waits, then sends `SIGKILL` to the union of captured survivors and newly scanned descendants so reparenting cannot hide a process from teardown. It verifies that every retained identity is gone or, on Linux, a non-executing zombie before stopping the shell; zombie entries are quiescent and are reaped as the shell exits. A survivor failure does not cache a permanently rejected close; a later close retries the teardown.
 

packages/pty/pty-local/README.zh.md

@@ -8,7 +8,7 @@
 
 该插件注入 `pty`、`sandbox` 和 `sandboxPolicy`，然后注册所配置的后端类型（`shell`）。`danger-full-access` 会直接启动 shell；受限模式则通过 `ctx.sandbox` 包装确切的 shell argv。系统在 spawn 时解析会话的实际模式。当某个所有者存在开放的 PTY 或正在进行 spawn 时，如果配置变更会得到不同的实际模式，系统会在对应 `sandbox/mode` 事件提交前拒绝该变更。该限制绑定到确切所有者，因此即使本地提供方重新加载并保留现有会话，它仍然有效。更改模式前，请等待创建结算并关闭会话，避免以更宽权限打开的终端在权限降级后继续存在。
 
-Linux 的就绪检测结合以下机制：由前台状态验证的私有 bash 提示符标记、前台进程组 syscall 检查、静默回退和绝对超时。macOS 没有 `/proc` syscall 接口，因此使用经过验证的提示符标记以及静默／超时。当可打印的提示符文本尚未到达时，即使 OSC 标记和 `PS1` 被拆到多个数据回调中，系统也不会把标记视为就绪。如果 bash 在内核发布其重新取得前台进程组的状态前打印标记，轮询会在普通静默上限之后再保留该候选状态 `handoffGraceMs`，使恰好同时发生的前台交接有机会胜出；该宽限至少要覆盖一个 `pollIntervalMs`，否则加载时即被拒绝。因此，继承 `PROMPT_COMMAND` 的交互式子进程无法持续压制推断空闲就绪，最多只能延续到绝对超时。无法识别或读取的进程状态绝不会作为精确空闲的正向信号。尚未发布的启动过程中，回退路径要求已经观察到输出；零输出静默不能发布空会话，超时则拒绝 spawn。取消操作会关闭尚未发布的 shell，并以调用方提供的确切中止原因拒绝，即使当时还无法观察其前台进程组。如果关闭失败，`PtyBackendCleanupError` 会单独保留清理失败，供注册表释放资源时处理。未完成的终端控制序列受 `maxReadBytes` 限制；超过上限后，系统会丢弃内容直到其终止符。末尾的回车会跨回调保留，使拆分的 CRLF 合并为一个换行。
+Linux 的就绪检测结合以下机制：由前台状态验证的私有 bash 提示符标记、前台进程组 syscall 检查、静默回退和绝对超时。macOS 没有 `/proc` syscall 接口，因此使用经过验证的提示符标记以及静默／超时。当可打印的提示符文本尚未到达时，即使 OSC 标记和 `PS1` 被拆到多个数据回调中，系统也不会把标记视为就绪。如果 bash 在内核发布其重新取得前台进程组的状态前打印标记，轮询会在普通静默上限之后再保留该候选状态 `handoffGraceMs`，使恰好同时发生的前台交接有机会胜出；该宽限至少要覆盖一个 `pollIntervalMs`，否则加载时即被拒绝。因此，继承 `PROMPT_COMMAND` 的交互式子进程无法持续压制推断空闲就绪，最多只能延续到绝对超时。无法识别或读取的进程状态绝不会作为精确空闲的正向信号。同样，一次 send 之前就已存在的前台进程组 stdin 等待并不代表写入后就绪：必须先观察到同一进程组脱离该等待，之后再次进入等待才能使该次 send 完成；前台进程组发生变化则构成新的证据。尚未发布的启动过程中，回退路径要求已经观察到输出；零输出静默不能发布空会话，超时则拒绝 spawn。取消操作会关闭尚未发布的 shell，并以调用方提供的确切中止原因拒绝，即使当时还无法观察其前台进程组。如果关闭失败，`PtyBackendCleanupError` 会单独保留清理失败，供注册表释放资源时处理。未完成的终端控制序列受 `maxReadBytes` 限制；超过上限后，系统会丢弃内容直到其终止符。末尾的回车会跨回调保留，使拆分的 CRLF 合并为一个换行。
 
 取消发送时，系统会解析当前前台进程组并发送真正的 `SIGINT`；它绝不会通过写入 `\x03` 模拟中断，因此原始模式程序仍可取消。关闭操作先向后代发送 `SIGTERM` 并等待，再向已捕获的存活进程与新扫描到的后代之并集发送 `SIGKILL`，防止进程通过重新设定父进程而逃避清理。系统确认每个保留的进程身份都已消失；在 Linux 上，非执行中的僵尸进程也视为完全停稳，并会随 shell 退出而回收。如果仍有进程存活，失败结果不会缓存成永久拒绝的关闭操作；后续关闭仍会重试清理。
 

packages/pty/pty-local/src/session.ts

@@ -79,14 +79,18 @@ class LocalSendOperation implements PtySendOperation {
   private readonly output: BoundedTextBuffer
   private readonly promise: PromiseWithResolvers<PtySendResult>
   private finished = false
+  private initialForegroundLeftWait: boolean
 
   constructor(
     maxBytes: number,
     readonly startedAt: number,
+    private readonly initialForegroundPgid: number | undefined,
+    initialForegroundWasWaiting: boolean,
     private readonly onCancel: () => void,
   ) {
     this.output = new BoundedTextBuffer(maxBytes)
     this.promise = Promise.withResolvers<PtySendResult>()
+    this.initialForegroundLeftWait = !initialForegroundWasWaiting
   }
 
   get done(): Promise<PtySendResult> {
@@ -119,6 +123,15 @@ class LocalSendOperation implements PtySendOperation {
     return this.output.consume()
   }
 
+  acceptsStdinWait(pgid: number, waiting: boolean): boolean {
+    // The same group may still expose the wait that existed before terminal.write.
+    // Observe every poll so a departure before the exact-settlement threshold
+    // still makes a later return to that wait post-write evidence.
+    if (pgid !== this.initialForegroundPgid) return waiting
+    if (!waiting) this.initialForegroundLeftWait = true
+    return waiting && this.initialForegroundLeftWait
+  }
+
   cancel(): boolean {
     if (this.finished) return false
     this.onCancel()
@@ -200,9 +213,14 @@ export class LocalPtySession implements PtyBackendSession {
     if (this.active !== undefined) throw new Error('PTY session already has an active send')
     if (request.signal?.aborted === true) throw new Error('PTY send aborted before write')
 
+    const initialForegroundPgid = this.inspector.foregroundPgid(this.pid)
+    const initialForegroundWasWaiting = initialForegroundPgid !== undefined
+      && this.inspector.isStdinWaiting(initialForegroundPgid)
     const operation = new LocalSendOperation(
       this.config.maxReadBytes,
       Date.now(),
+      initialForegroundPgid,
+      initialForegroundWasWaiting,
       () => { this.interrupt(operation) },
     )
     this.active = operation
@@ -321,12 +339,15 @@ export class LocalPtySession implements PtyBackendSession {
     }
     const elapsed = Date.now() - operation.startedAt
     const startupHasOutput = !this.initializing || this.scrollback.snapshot().text.length > 0
-    if (startupHasOutput && elapsed >= this.config.exactProbeAfterMs) {
+    let acceptsStdinWait = false
+    if (startupHasOutput) {
       const pgid = this.inspector.foregroundPgid(this.pid)
-      if (pgid !== undefined && this.inspector.isStdinWaiting(pgid)) {
-        this.settleActive('stdin_read')
-        return
-      }
+      acceptsStdinWait = pgid !== undefined
+        && operation.acceptsStdinWait(pgid, this.inspector.isStdinWaiting(pgid))
+    }
+    if (elapsed >= this.config.exactProbeAfterMs && acceptsStdinWait) {
+      this.settleActive('stdin_read')
+      return
     }
     // A prompt candidate can race bash's foreground handoff, but an interactive
     // child also inherits PROMPT_COMMAND. Silence therefore remains the bound

packages/pty/pty-local/tests/local.spec.ts

@@ -170,12 +170,15 @@ describe('pty-local real shell', () => {
     controller.abort()
     const result = await foreground.done
     expectReadyForNextSend(result.waitReason)
-    const after = await ctx.pty.startSend(agent, created.sessionId, {
-      text: 'echo AFTER_SIGINT',
+    const afterReady = 'AFTER_SIGINT'
+    const afterCommand = 'printf "AFTER_%s\\n" SIGINT'
+    expect(afterCommand).not.toContain(afterReady)
+    const after = ctx.pty.startSend(agent, created.sessionId, {
+      text: afterCommand,
       submit: true,
-    }).done
-    expect(after.viewport).toContain('AFTER_SIGINT')
-    expectReadyForNextSend(after.waitReason)
+    })
+    await waitForOutput(after, afterReady, 15_000)
+    expectReadyForNextSend((await after.done).waitReason)
     await ctx.pty.kill(agent, created.sessionId)
-  }, 20_000)
+  }, 35_000)
 })

packages/pty/pty-local/tests/session.spec.ts

@@ -115,12 +115,60 @@ describe('LocalPtySession readiness and output', () => {
     inspector.waiting = true
     const operation = session.startSend({ text: 'python3', submit: true })
     expect(terminal.writes).toEqual(['python3', '\r'])
+    inspector.pgid = 789
     terminal.emitData('Python\r\n>>> ')
     await vi.advanceTimersByTimeAsync(20)
     expect(await operation.done).toMatchObject({ waitReason: 'stdin_read', viewport: 'Python\n>>> ', sessionStatus: { kind: 'running' } })
     expect(operation.cancel()).toBe(false)
   })
 
+  it('does not reuse a pre-write stdin wait as post-write readiness', async () => {
+    vi.useFakeTimers()
+    const terminal = new FakeTerminal()
+    const inspector = new FakeInspector()
+    const session = new LocalPtySession(terminal.asPty(), inspector, config())
+    await initialize(session, terminal)
+
+    inspector.waiting = true
+    const operation = session.startSend({ text: 'echo ready', submit: true })
+    let settled = false
+    void operation.done.then(() => { settled = true })
+    await vi.advanceTimersByTimeAsync(20)
+    expect(settled).toBe(false)
+
+    inspector.waiting = false
+    await vi.advanceTimersByTimeAsync(10)
+    expect(settled).toBe(false)
+    inspector.waiting = true
+    await vi.advanceTimersByTimeAsync(10)
+    expect((await operation.done).waitReason).toBe('stdin_read')
+  })
+
+  it('tracks a pre-write wait exit before exact probing begins', async () => {
+    vi.useFakeTimers()
+    const terminal = new FakeTerminal()
+    const inspector = new FakeInspector()
+    const session = new LocalPtySession(terminal.asPty(), inspector, config({
+      exactProbeAfterMs: 50,
+      idleSilenceMs: 100,
+      timeoutMs: 200,
+    }))
+    await initialize(session, terminal)
+
+    inspector.waiting = true
+    const operation = session.startSend({ text: 'fast command', submit: true })
+    let settled = false
+    void operation.done.then(() => { settled = true })
+    inspector.waiting = false
+    await vi.advanceTimersByTimeAsync(10)
+    inspector.waiting = true
+    await vi.advanceTimersByTimeAsync(30)
+    expect(settled).toBe(false)
+    await vi.advanceTimersByTimeAsync(10)
+    expect(settled).toBe(true)
+    expect((await operation.done).waitReason).toBe('stdin_read')
+  })
+
   it('distinguishes inferred idle, timeout, exit signal, and operation reads', async () => {
     vi.useFakeTimers()
     const terminal = new FakeTerminal()

packages/ui/tui/tests/tui.spec.ts

@@ -3040,12 +3040,14 @@ describe('pi-tui chat lifecycle and transcript', () => {
     expect(result.terminal.output).toContain('advertised by multiple providers')
     expect(result.terminal.output).toContain('already alpha/a1')
 
+    const firstSelectorOutput = result.terminal.output.length
     result.terminal.send('/model')
     result.terminal.send('\r')
     result.terminal.send('/model')
     result.terminal.send('\r')
-    await tick()
-    expect(result.terminal.output).toContain('Select model')
+    await vi.waitFor(() => {
+      expect(result.terminal.output.slice(firstSelectorOutput)).toContain('Select model')
+    })
     result.terminal.send('\x1b')
     await tick()