Fix Codex wire frames and bound grace timers

packages/subprocess/subprocess-local/package.json

@@ -29,11 +29,13 @@
   "peerDependencies": {
     "@deepseek-ai/dsh-invariants": "^0.0.1",
     "@deepseek-ai/dsh-subprocess": "^0.0.1",
+    "@deepseek-ai/dsh-timeout": "^0.0.1",
     "cordis": "^4.0.0-rc.7"
   },
   "devDependencies": {
     "@deepseek-ai/dsh-invariants": "workspace:^",
     "@deepseek-ai/dsh-subprocess": "workspace:^",
+    "@deepseek-ai/dsh-timeout": "workspace:^",
     "cordis": "^4.0.0-rc.7"
   }
 }

packages/subprocess/subprocess-local/src/spawn.ts

@@ -15,6 +15,7 @@ import { tmpdir } from 'node:os'
 import { join } from 'node:path'
 import { setTimeout as sleepMs } from 'node:timers/promises'
 import { scrubbedParentEnv } from '@deepseek-ai/dsh-subprocess'
+import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
 import type {
   CollectedOutput,
   SubprocessCollect,
@@ -55,47 +56,6 @@ function sleepTick(): Promise<void> {
   return sleepMs(15)
 }
 
-/** Largest delay Node schedules without collapsing it to one millisecond. */
-const MAX_TIMER_DELAY_MS = 2_147_483_647n
-
-/**
- * Schedule a positive finite millisecond delay across as many Node-safe timer
- * segments as necessary. Fractional milliseconds round up so a grace never
- * expires earlier than configured.
- * @param delayMs - positive finite delay in milliseconds.
- * @param callback - work to run after the complete delay.
- * @returns a handle that cancels the active segment and all future segments.
- */
-export function scheduleFiniteTimeout(
-  delayMs: number,
-  callback: () => void,
-): { cancel(): void } {
-  let remaining = BigInt(Math.ceil(delayMs))
-  let timer: ReturnType<typeof setTimeout> | undefined
-  const arm = (): void => {
-    const chunk = remaining > MAX_TIMER_DELAY_MS
-      ? MAX_TIMER_DELAY_MS
-      : remaining
-    remaining -= chunk
-    timer = setTimeout(() => {
-      timer = undefined
-      if (remaining === 0n) {
-        callback()
-      } else {
-        arm()
-      }
-    }, Number(chunk))
-  }
-  arm()
-  return {
-    cancel(): void {
-      if (timer === undefined) return
-      clearTimeout(timer)
-      timer = undefined
-    },
-  }
-}
-
 let spillCounter = 0
 let defaultSpillDir: string | undefined
 
@@ -339,8 +299,12 @@ function signalTree(
  * @param spec - fully resolved argv, cwd, stdio, grace, cancellation, environment.
  * @param internals - test-only spill-directory, platform, and taskkill overrides.
  * @returns live subprocess handle.
+ * @throws when `graceMs` cannot be represented by one Node timer.
  */
 export function spawnSubprocess(spec: SubprocessSpawnSpec, internals: SpawnInternals = {}): SubprocessHandle {
+  if (!Number.isFinite(spec.graceMs) || spec.graceMs <= 0 || spec.graceMs > MAX_TIMER_DELAY_MS) {
+    throw new Error(`subprocess graceMs must be a positive finite number no greater than ${MAX_TIMER_DELAY_MS}`)
+  }
   const spillDir = internals.spillDir ?? privateSpillDir()
   const platform = internals.platform ?? process.platform
   const taskkill = internals.taskkill ?? taskkillProcessTree
@@ -382,7 +346,7 @@ export function spawnSubprocess(spec: SubprocessSpawnSpec, internals: SpawnInter
   const stdoutCollector = collectStream(outMode, child.stdout, 'stdout')
   const stderrCollector = collectStream(errMode, child.stderr, 'stderr')
 
-  let graceTimer: ReturnType<typeof scheduleFiniteTimeout> | undefined
+  let graceTimer: ReturnType<typeof setTimeout> | undefined
   let treeExitObserved = false
   let treeExitObservation: Promise<void> | undefined
   let settled = false
@@ -426,7 +390,7 @@ export function spawnSubprocess(spec: SubprocessSpawnSpec, internals: SpawnInter
     treeExitObservation ??= (async () => {
       while (treeAlive()) await sleepTick()
       treeExitObserved = true
-      graceTimer?.cancel()
+      if (graceTimer !== undefined) clearTimeout(graceTimer)
       graceTimer = undefined
     })()
     return treeExitObservation
@@ -457,7 +421,7 @@ export function spawnSubprocess(spec: SubprocessSpawnSpec, internals: SpawnInter
     // kill() re-probes tree liveness before force-killing. It stays ref'd:
     // the pending SIGKILL is a commitment, and a parent exiting before it
     // fires would orphan a trapped survivor. Self-bounds at graceMs.
-    graceTimer = scheduleFiniteTimeout(spec.graceMs, () => { kill('SIGKILL') })
+    graceTimer = setTimeout(() => { kill('SIGKILL') }, spec.graceMs)
   }
 
   // The caller owns timeout classification; this layer only reacts to abort.
@@ -472,7 +436,7 @@ export function spawnSubprocess(spec: SubprocessSpawnSpec, internals: SpawnInter
   }
 
   const done = new Promise<SubprocessOutcome>((resolve, reject) => {
-    let pipeDrainTimer: ReturnType<typeof scheduleFiniteTimeout> | undefined
+    let pipeDrainTimer: ReturnType<typeof setTimeout> | undefined
     const settle = (exitCode: number | null, signal: NodeJS.Signals | null): void => {
       if (settled) return
       settled = true
@@ -495,15 +459,15 @@ export function spawnSubprocess(spec: SubprocessSpawnSpec, internals: SpawnInter
       // A surviving descendant that inherited a pipe must not hold the
       // outcome open indefinitely: after exit, the same bounded grace that
       // governs kills also bounds the close wait.
-      pipeDrainTimer = scheduleFiniteTimeout(spec.graceMs, () => {
+      pipeDrainTimer = setTimeout(() => {
         settle(exitCode, signal)
-      })
+      }, spec.graceMs)
     })
     child.on('close', settle)
     function cleanup(): void {
       // graceTimer deliberately NOT cleared: the SIGKILL escalation must be
       // able to reach tree survivors after the direct child settles.
-      pipeDrainTimer?.cancel()
+      if (pipeDrainTimer !== undefined) clearTimeout(pipeDrainTimer)
       spec.signal?.removeEventListener('abort', onAbort)
     }
   })

packages/subprocess/subprocess-local/tests/spawn.spec.ts

@@ -5,11 +5,11 @@ import { describe, expect, it, vi } from 'vitest'
 import {
   killGroup,
   OutputCollector,
-  scheduleFiniteTimeout,
   spawnSubprocess,
   taskkillProcessTree,
 } from '../src/spawn.ts'
 import type { SubprocessHandle, SubprocessOutputReader } from '@deepseek-ai/dsh-subprocess'
+import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
 
 const { failNextClose, failNextUnlink } = vi.hoisted(() => ({
   failNextClose: { value: false },
@@ -107,31 +107,15 @@ async function waitForPidFile(path: string, timeoutMs = 5_000): Promise<number>
   throw new Error(`pid file ${path} was not written after ${timeoutMs}ms`)
 }
 
-describe('scheduleFiniteTimeout', () => {
-  it('rounds fractions up, chains Node-safe segments, and cancels idempotently', async () => {
-    vi.useFakeTimers()
-    try {
-      const fired = vi.fn()
-      const chained = scheduleFiniteTimeout(2_147_483_647.25, fired)
-      await vi.advanceTimersByTimeAsync(2_147_483_647)
-      expect(fired).not.toHaveBeenCalled()
-      await vi.advanceTimersByTimeAsync(1)
-      expect(fired).toHaveBeenCalledOnce()
-      chained.cancel()
-
-      const cancelled = vi.fn()
-      const timer = scheduleFiniteTimeout(0.25, cancelled)
-      timer.cancel()
-      timer.cancel()
-      await vi.advanceTimersByTimeAsync(1)
-      expect(cancelled).not.toHaveBeenCalled()
-    } finally {
-      vi.useRealTimers()
-    }
-  })
-})
-
 describe('spawnSubprocess', () => {
+  it.each([0, -1, Number.NaN, Number.POSITIVE_INFINITY, MAX_TIMER_DELAY_MS + 1])(
+    'rejects an invalid grace before spawning: %s',
+    (graceMs) => {
+      expect(() => spawnSubprocess(spec('true', { graceMs })))
+        .toThrow(`subprocess graceMs must be a positive finite number no greater than ${MAX_TIMER_DELAY_MS}`)
+    },
+  )
+
   it('captures stdout on success', async () => {
     const result = await finish(spawnSubprocess(spec('echo hello')))
     expect(result.exitCode).toBe(0)
@@ -194,17 +178,6 @@ describe('spawnSubprocess', () => {
     expect(result.signal).toBe('SIGKILL')
   })
 
-  it('cancels a larger-than-Node escalation timer once SIGTERM removes the tree', async () => {
-    const running = spawnSubprocess(spec('echo ready; sleep 60', {
-      graceMs: Number.MAX_VALUE,
-    }))
-    await waitForStdout(running, 'ready\n')
-    running.terminate()
-    const result = await running.done
-    expect(result.signal).toBe('SIGTERM')
-    await expect(running.waitForExit()).resolves.toBe(true)
-  })
-
   it('cancels escalation when the terminated group vanishes before collected pipes drain', async () => {
     const pidFile = join(spillDir, `escaped-pipe-holder-${Date.now()}.pid`)
     const graceMs = 160

packages/subprocess/subprocess-local/tsconfig.json

@@ -17,6 +17,9 @@
     {
       "path": "../subprocess"
     },
+    {
+      "path": "../../util/timeout"
+    },
     {
       "path": "../../support/invariants"
     }

packages/subprocess/subprocess/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/subprocess/subprocess/README.md
-README.md: c360437bf2b2b95734f55f6aec46b0cecffb9260
-README.zh.md: dac459a6ed1b92c2354bf0a2cc4e0c23e824154f
+README.md: a8061e67a5346fce785f3c9fb27c8f885bf99921
+README.zh.md: 0e6a7e9192eb7028ea951681f5e013f8012a4121

packages/subprocess/subprocess/README.md

@@ -7,7 +7,7 @@ The subprocess seam (`ctx.subprocess`). The abstract `SubprocessService` exposes
 ## Contract
 
 - `spawn(spec)` returns immediately with a live handle; `done` resolves at process close with exit facts (`SubprocessOutcome` carries no output and no cause classification) and rejects only for spawn-level failures.
-- The spec is fully explicit — argv, cwd, per-stream stdio dispositions, grace — because deployment-varying defaults belong to the calling seam's config, not to a hidden subprocess-service default (the `dsh-bash` request/spec split is the owning template). `argv` is never shell-interpreted; a consumer that wants a shell passes `['bash', '-c', command]` itself.
+- The spec is fully explicit — argv, cwd, per-stream stdio dispositions, grace — because deployment-varying defaults belong to the calling seam's config, not to a hidden subprocess-service default (the `dsh-bash` request/spec split is the owning template). Grace must be positive, finite, and no greater than [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md), so the implementation can represent it with one Node timer instead of accepting a value that Node collapses to one millisecond. `argv` is never shell-interpreted; a consumer that wants a shell passes `['bash', '-c', command]` itself.
 - Stdio is Node-shaped per stream: `'pipe'` hands the caller the raw stream for its own protocol framing (LSP JSON-RPC, ACP ndjson), `'inherit'` passes the parent descriptor through for diagnostics, and collect mode (`{ maxBytes, spill? }`) buffers a bounded tail with an optional full-stream spill file. Collect readers take whole-stream byte offsets and never consume, so independent readers cannot steal one another's deltas; a read whose offset slid out of the in-memory tail is `lossy` and points at the spill file when one exists. Collected output stays readable after settlement.
 - Termination is tree-scoped on every platform (POSIX detached groups with direct-child fallback; Windows `taskkill /T`): `terminate()` — the only termination verb — escalates SIGTERM→grace→SIGKILL (idempotent, driven by the spec's abort signal too, a no-op once the tree is gone), and `waitForExit(signal?)` observes whole-tree liveness so a consumer-owned teardown ladder holds each tier on real quiescence — the manager reacts but never classifies why (callers own deadlines, teardown ladders, and cause classification).
 - `scrubbedParentEnv()` / `SENSITIVE_ENV_PATTERN` are the one shared scrub definition: ambient credential-shaped and `DSH_*` names are dropped, and the spec's explicit `env` merges after the scrub with no namespace validation — a deliberately forwarded credential or a current `DSH_*` fact survives precisely because it is an explicit caller opt-in, while the stale ambient namesake never reaches the child. Spawners that cannot route through the service (node-pty backends, SDK-managed transports) import the scrub.

packages/subprocess/subprocess/README.zh.md

@@ -7,7 +7,7 @@
 ## 契约
 
 - `spawn(spec)` 立即返回一个活动句柄；`done` 在进程关闭时以退出事实 resolve（`SubprocessOutcome` 不携带输出，也不携带原因分类），仅在 spawn 层面失败时 reject。
-- spec 完全显式（argv、cwd、按流划分的 stdio 处置方式（disposition）、宽限期），因为随部署变化的默认值属于调用方 seam 的配置，而不属于某个隐藏的子进程默认值（`dsh-bash` 的 request/spec 拆分是这条规则的所属模板）。`argv` 绝不经过 shell 解释；需要 shell 的消费方自行传入 `['bash', '-c', command]`。
+- spec 完全显式（argv、cwd、按流划分的 stdio 处置方式（disposition）、宽限期），因为随部署变化的默认值属于调用方 seam 的配置，而不属于某个隐藏的子进程默认值（`dsh-bash` 的 request/spec 拆分是这条规则的所属模板）。宽限期须为正有限值，且不得大于 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md)，这样实现便可用一个 Node 定时器表示它，而不会接受会被 Node 折叠为 1 毫秒的值。`argv` 绝不经过 shell 解释；需要 shell 的消费方自行传入 `['bash', '-c', command]`。
 - stdio 按流采用 Node 风格：`'pipe'` 把原始流交给调用方做自己的协议分帧（LSP 的 JSON-RPC、ACP（Agent Client Protocol）的 ndjson），`'inherit'` 直通父进程描述符以承载诊断输出，收集模式（collect）`{ maxBytes, spill? }` 则缓冲一段有界尾部，外加可选的完整流 spill 文件。收集模式的读取器接受全流字节偏移量且从不消费，因此独立的读取器不会抢走彼此的增量；偏移量滑出内存尾部窗口的读取标记为 `lossy`，并在 spill 文件存在时指向它。收集到的输出在结算后仍可读取。
 - 终止在每个平台上都以进程树为范围（POSIX 用 detached 进程组并以直接子进程回退；Windows 用 `taskkill /T`）：`terminate()`（唯一的终止动词）执行 SIGTERM→宽限期→SIGKILL 升级（幂等，也由 spec 的 abort 信号驱动，进程树消亡后为空操作）；`waitForExit(signal?)` 观察整棵进程树的存活状态，使消费方自有的拆卸阶梯能在真正完全停稳后才进入下一层。管理器只响应中止，但绝不判定原因（deadline、拆卸阶梯与原因分类归调用方所有）。
 - `scrubbedParentEnv()` / `SENSITIVE_ENV_PATTERN` 是唯一一份共享的环境清理定义：环境中形似凭据的名称与 `DSH_*` 名称都会被丢弃，spec 的显式 `env` 在清除之后合并且不做命名空间校验——有意转发的凭据或当前 `DSH_*` 事实之所以能保留下来，正因为它是调用方的显式选择，而陈旧的同名环境值永远到不了子进程。无法把 spawn 路由到该服务的进程启动方（node-pty 后端、由 SDK 管理的传输层）改为导入环境清理函数。

packages/subprocess/subprocess/src/types.ts

@@ -80,10 +80,11 @@ export interface SubprocessSpawnSpec {
   /** Per-stream stdio dispositions. */
   stdio: SubprocessStdio
   /**
-   * Grace period in milliseconds for the {@link SubprocessHandle.terminate}
-   * escalation and for draining still-open collected pipes after the process
-   * exits (an inherited descriptor held by a surviving descendant cannot hold
-   * the outcome open indefinitely).
+   * Positive finite grace period in milliseconds, no greater than
+   * `MAX_TIMER_DELAY_MS`, for the {@link SubprocessHandle.terminate} escalation
+   * and for draining still-open collected pipes after the process exits (an
+   * inherited descriptor held by a surviving descendant cannot hold the
+   * outcome open indefinitely).
    */
   graceMs: number
   /**