fix(pty): retain cleanup evidence through policy

packages/pty/pty/README.md

@@ -8,6 +8,7 @@ Owner-scoped persistent PTY seam. `PtyService` registers as `ctx.pty`, mints opa
 - Spawn cancellation preserves the caller's exact abort reason. Service disposal and owner loss remain distinct machine-routable failures after backend setup.
 - Owner and service disposal abort unpublished setup through a service-owned signal and await backend settlement plus rollback before returning.
 - A service rollback or backend-reported startup cleanup failure rejects the disposing lifecycle instead of claiming quiescence; the spawn caller still receives its exact cancellation reason.
+- A backend cleanup failure that follows caller cancellation remains owner activity until owner or service disposal consumes and reports it, so lifecycle policy cannot mistake failed cleanup for quiescence.
 - `hasOwnerActivity(owner)` spans unpublished setup through final close, so lifecycle policy can fence the exact owner without a publication race.
 - A successful spawn publishes one `PtySessionId`. The optional `name` is owner-local display metadata, never authority.
 - One session accepts at most one live send operation. Reads and signals may observe it; another send fails until the operation settles.

packages/pty/pty/src/index.ts

@@ -90,6 +90,7 @@ interface SessionRecord {
 }
 
 interface PendingSpawn {
+  readonly owner: Agent
   readonly controller: AbortController
   readonly settled: Promise<void>
   cleanupFailure: { error: unknown } | undefined
@@ -349,7 +350,7 @@ export class PtyService extends Service {
   private reserveSpawn(owner: Agent): SpawnReservation {
     const controller = new AbortController()
     const settlement = Promise.withResolvers<void>()
-    const pending: PendingSpawn = { controller, settled: settlement.promise, cleanupFailure: undefined }
+    const pending: PendingSpawn = { owner, controller, settled: settlement.promise, cleanupFailure: undefined }
     const owned = this.pendingSpawns.get(owner) ?? new Set<PendingSpawn>()
     owned.add(pending)
     this.pendingSpawns.set(owner, owned)
@@ -357,13 +358,19 @@ export class PtyService extends Service {
       signal: controller.signal,
       release: (cleanupFailure) => {
         pending.cleanupFailure = cleanupFailure
-        owned.delete(pending)
-        if (owned.size === 0) this.pendingSpawns.delete(owner)
+        if (cleanupFailure === undefined) this.removePendingSpawn(pending)
         settlement.resolve()
       },
     }
   }
 
+  private removePendingSpawn(pending: PendingSpawn): void {
+    const owned = this.pendingSpawns.get(pending.owner)
+    if (owned === undefined) return
+    owned.delete(pending)
+    if (owned.size === 0) this.pendingSpawns.delete(pending.owner)
+  }
+
   private async abortPendingSpawns(owner: Agent | undefined, reason: PtyError): Promise<void> {
     const pending = owner === undefined
       ? [...this.pendingSpawns.values()].flatMap(owned => [...owned])
@@ -371,6 +378,7 @@ export class PtyService extends Service {
     for (const spawn of pending) spawn.controller.abort(reason)
     await Promise.all(pending.map(spawn => spawn.settled))
     const failures = pending.flatMap(spawn => spawn.cleanupFailure === undefined ? [] : [spawn.cleanupFailure.error])
+    for (const spawn of pending) this.removePendingSpawn(spawn)
     if (failures.length > 0) {
       throw new AggregateError(failures, 'failed to roll back unpublished PTY setup')
     }

packages/pty/pty/tests/service.spec.ts

@@ -160,6 +160,7 @@ describe('PtyService ownership and lifecycle', () => {
 
     const created = await ctx.pty.spawn(owner, { type: 'stub', name: 'main', cwd: '/tmp' })
     expect(created).toMatchObject({ sessionId: 'pty-1', name: 'main', type: 'stub', pid: 123, motd: 'stub ready', status: { kind: 'running' } })
+    expect(ctx.pty.hasOwnerActivity(owner)).toBe(true)
     expect(ctx.pty.list(owner)).toHaveLength(1)
     expect(ctx.pty.list(foreign)).toEqual([])
     expect(() => ctx.pty.read(foreign, created.sessionId)).toThrow('belongs to another agent')
@@ -256,6 +257,40 @@ describe('PtyService ownership and lifecycle', () => {
     await expect(pending).rejects.toBe(reason)
   })
 
+  it.each(['owner', 'service'] as const)('retains caller-triggered backend cleanup failure until %s disposal', async (scope) => {
+    const ctx = await harness()
+    const started = Promise.withResolvers<undefined>()
+    const cleanupFailure = new Error('backend cleanup failed')
+    ctx.pty.registerBackend({
+      type: 'cleanup-failing',
+      spawn: ({ signal }) => new Promise((_resolve, reject) => {
+        if (signal === undefined) throw new Error('missing spawn signal')
+        started.resolve(undefined)
+        signal.addEventListener('abort', () => {
+          reject(new PtyBackendCleanupError(signal.reason, cleanupFailure))
+        }, { once: true })
+      }),
+    })
+    const owner = stubAgent(ctx, 'owner')
+    ctx.agents.register(owner)
+    const controller = new AbortController()
+    const reason = new Error('cancelled by caller')
+
+    const pending = ctx.pty.spawn(owner, { type: 'cleanup-failing' }, controller.signal)
+    await started.promise
+    controller.abort(reason)
+
+    await expect(pending).rejects.toBe(reason)
+    expect(ctx.pty.hasOwnerActivity(owner)).toBe(true)
+    const internal = ctx.pty as unknown as {
+      disposeOwned(owner: Agent): Promise<void>
+      disposeAll(): Promise<void>
+    }
+    const disposal = scope === 'owner' ? internal.disposeOwned(owner) : internal.disposeAll()
+    await expect(disposal).rejects.toThrow('failed to clean up PTY lifecycle')
+    expect(ctx.pty.hasOwnerActivity(owner)).toBe(false)
+  })
+
   it.each([
     { scope: 'owner', code: 'OWNER_NOT_LIVE' },
     { scope: 'service', code: 'SERVICE_DISPOSING' },