Fix timer bounds and ACP teardown ownership

packages/subagent/subagent-acp/src/index.ts

@@ -17,6 +17,7 @@ import type {
   SubagentProvider,
   SubagentStartRequest,
 } from '@deepseek-ai/dsh-subagent'
+import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
 import { type AcpRunSpec, DEFAULT_DISPOSE_EOF_GRACE_MS, DEFAULT_DISPOSE_GRACE_MS, type PermissionPolicy, startAcpRun } from './run.ts'
 
 export const name = 'subagent-acp'
@@ -54,10 +55,11 @@ export interface Config {
   /**
    * Grace period (ms) for the child's EOF-driven quiesce on dispose — its
    * window to flush persistence and tear down its own nested subprocesses
-   * before the parent escalates to a signal.
+   * before the parent escalates to a signal. Must not exceed
+   * `MAX_TIMER_DELAY_MS`.
    */
   disposeEofGraceMs?: number
-  /** Termination confirmation window (ms), including forced exit on every platform. */
+  /** Termination-escalation grace (ms); must not exceed `MAX_TIMER_DELAY_MS`. */
   disposeGraceMs?: number
 }
 
@@ -72,10 +74,10 @@ export const Config: z<Config> = z.object({
   disposeGraceMs: z.number().default(DEFAULT_DISPOSE_GRACE_MS),
 })
 
-/** A dispose grace must be a positive finite number (it bounds the teardown wait). */
+/** A dispose grace must fit the single Node timer that owns its teardown tier. */
 function assertPositiveFinite(name: string, value: number): void {
-  if (!Number.isFinite(value) || value <= 0) {
-    throw new Error(`subagent-acp: ${name} must be a positive finite number`)
+  if (!Number.isFinite(value) || value <= 0 || value > MAX_TIMER_DELAY_MS) {
+    throw new Error(`subagent-acp: ${name} must be a positive finite number no greater than ${MAX_TIMER_DELAY_MS}`)
   }
 }
 

packages/subagent/subagent-acp/src/run.ts

@@ -62,9 +62,9 @@ export interface AcpRunSpec {
    */
   disposeEofGraceMs: number
   /**
-   * Termination confirmation window (ms) in {@link SubagentRun.dispose}; POSIX applies it after
-   * `SIGTERM` and `SIGKILL`, while Windows applies it after direct forced termination. The plugin
-   * fills this from its `disposeGraceMs` config.
+   * Termination-escalation grace (ms) in {@link SubagentRun.dispose}; POSIX
+   * waits this long after `SIGTERM` before `SIGKILL`, while Windows
+   * force-terminates directly. The plugin fills it from `disposeGraceMs`.
    */
   disposeGraceMs: number
   /**
@@ -105,14 +105,12 @@ async function treeExitsWithin(child: SubprocessHandle, ms: number): Promise<boo
  * Cooperative teardown ladder for an out-of-process agent, over the seam's
  * public verbs; resolves only at whole-tree quiescence: stdin EOF (the child's
  * window to flush persistence and reap its own descendants), then the
- * terminate() escalation (SIGTERM → spec grace → SIGKILL), then a bounded
- * confirmation wait.
+ * terminate() escalation (SIGTERM → spec grace → SIGKILL) and its
+ * whole-tree exit proof.
  * @param child - the spawned ACP child's handle.
  * @param eofGraceMs - tier-1 window after stdin EOF.
- * @param graceMs - confirmation window after the escalation's SIGKILL.
- * @throws when the tree still has not exited `graceMs` after forced termination.
  */
-export async function disposeAcpChild(child: SubprocessHandle, eofGraceMs: number, graceMs: number): Promise<void> {
+export async function disposeAcpChild(child: SubprocessHandle, eofGraceMs: number): Promise<void> {
   // A spawn failure has no process to tear down; observe the rejection so
   // disposal in a finally block cannot surface it as unhandled.
   if (child.pid <= 0) {
@@ -121,13 +119,10 @@ export async function disposeAcpChild(child: SubprocessHandle, eofGraceMs: numbe
   }
   child.stdin?.end()
   if (await treeExitsWithin(child, eofGraceMs)) return
-  // terminate() sends SIGTERM now and SIGKILL after the spawn spec's grace
-  // (this plugin passes disposeGraceMs there), so the bound covers both the
-  // escalation window and an equal confirmation window after the SIGKILL.
+  // terminate() owns the bounded SIGTERM→SIGKILL timer. Its unbounded wait is
+  // the process owner's exit proof, not a second derived grace that can overflow.
   child.terminate()
-  if (!(await treeExitsWithin(child, graceMs * 2))) {
-    throw new Error('ACP child process tree did not exit within its dispose windows')
-  }
+  await child.waitForExit()
 }
 
 /**
@@ -235,7 +230,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe
 
   // Startup rollback and the published handle share one process teardown.
   let processDisposal: Promise<void> | undefined
-  const disposeProcess = (): Promise<void> => (processDisposal ??= disposeAcpChild(child, spec.disposeEofGraceMs, spec.disposeGraceMs))
+  const disposeProcess = (): Promise<void> => (processDisposal ??= disposeAcpChild(child, spec.disposeEofGraceMs))
 
   // Accumulate the child's streamed assistant text — the SubagentResult output.
   const output: string[] = []