fix(runtime): close lifecycle teardown races

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

@@ -187,6 +187,51 @@ describe('LocalPtyBackend startup rollback', () => {
     expect(initialized).toHaveBeenCalledWith(undefined)
   })
 
+  it('forwards setup cancellation only while terminal allocation is unpublished', async () => {
+    const ctx = new Context()
+    await ctx.plugin(EmptySandbox)
+    await ctx.plugin(SandboxPolicyService, { mode: 'danger-full-access', workspaceRoot: '/tmp' })
+
+    const publishedController = new AbortController()
+    let publishedSignal: AbortSignal | undefined
+    const published = new LocalPtyBackend(
+      ctx,
+      config(),
+      async (spawnSpec) => {
+        publishedSignal = spawnSpec.signal
+        return terminalHandle()
+      },
+      () => stubLocalSession(),
+    )
+    await published.spawn(spec(agent(ctx), publishedController.signal))
+    expect(publishedSignal).toBeDefined()
+    expect(publishedSignal).not.toBe(publishedController.signal)
+    publishedController.abort(new Error('originating turn ended'))
+    expect(publishedSignal?.aborted).toBe(false)
+
+    const pendingController = new AbortController()
+    const seen = Promise.withResolvers<AbortSignal>()
+    const pending = new LocalPtyBackend(
+      ctx,
+      config(),
+      async spawnSpec => await new Promise<SubprocessTerminalHandle>((_resolve, reject) => {
+        const setupSignal = spawnSpec.signal as AbortSignal
+        seen.resolve(setupSignal)
+        const onAbort = (): void => {
+          reject(setupSignal.reason instanceof Error ? setupSignal.reason : new Error(String(setupSignal.reason)))
+        }
+        setupSignal.addEventListener('abort', onAbort, { once: true })
+      }),
+      () => stubLocalSession(),
+    )
+    const spawning = pending.spawn(spec(agent(ctx), pendingController.signal))
+    const pendingSignal = await seen.promise
+    const reason = new Error('cancel pending allocation')
+    pendingController.abort(reason)
+    await expect(spawning).rejects.toBe(reason)
+    expect(pendingSignal.aborted).toBe(true)
+  })
+
   it('composes the default local session around a spawned terminal', async () => {
     const ctx = new Context()
     await ctx.plugin(EmptySandbox)

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

@@ -1,4 +1,4 @@
-import { mkdtempSync, realpathSync, rmSync } from 'node:fs'
+import { existsSync, mkdtempSync, readFileSync, realpathSync, rmSync } from 'node:fs'
 import { tmpdir } from 'node:os'
 import { join } from 'node:path'
 import { afterEach, describe, expect, it } from 'vitest'
@@ -156,6 +156,47 @@ describe('pty-local real shell', () => {
     expect(() => process.kill(pid, 0)).toThrow()
   }, 10_000)
 
+  it('reaps a disowned same-session descendant after the shell exits naturally', async () => {
+    const { ctx, root, agent } = await harness('danger-full-access')
+    const created = await ctx.pty.spawn(agent, { type: 'shell' })
+    const pidFile = join(root, 'disowned.pid')
+    let pid: number | undefined
+    try {
+      const background = ctx.pty.startSend(agent, created.sessionId, {
+        text: `sh -c 'trap "" TERM; printf "%s" "$$" > "$1"; sleep 60' dsh "${pidFile}" & disown`,
+        submit: true,
+      })
+      await background.done
+      const pidDeadline = Date.now() + 2_000
+      let childPid = 0
+      while (childPid === 0 && Date.now() < pidDeadline) {
+        if (existsSync(pidFile)) childPid = Number(readFileSync(pidFile, 'utf8'))
+        if (childPid > 0) break
+        await new Promise(resolve => setTimeout(resolve, 10))
+      }
+      expect(existsSync(pidFile), ctx.pty.read(agent, created.sessionId, { offset: 0, count: 100 }).text).toBe(true)
+      expect(childPid).toBeGreaterThan(0)
+      pid = childPid
+      expect(() => process.kill(childPid, 0)).not.toThrow()
+      await ctx.pty.startSend(agent, created.sessionId, { text: 'exit', submit: true }).done
+      const deadline = Date.now() + 2_000
+      while (ctx.pty.list(agent)[0]?.status.kind !== 'exited' && Date.now() < deadline) {
+        await new Promise(resolve => setTimeout(resolve, 10))
+      }
+      expect(ctx.pty.list(agent)[0]?.status.kind).toBe('exited')
+      await ctx.pty.kill(agent, created.sessionId)
+      expect(() => process.kill(childPid, 0)).toThrow()
+    } finally {
+      if (pid !== undefined) {
+        try {
+          process.kill(pid, 'SIGKILL')
+        } catch (_alreadyReaped) {
+          // Product cleanup is the expected path; this only contains a failed regression.
+        }
+      }
+    }
+  }, 10_000)
+
   it('cancels a slow-starting raw-mode foreground process with a real SIGINT', async () => {
     const { ctx, agent } = await harness('danger-full-access', {
       idleSilenceMs: 10_000,

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

@@ -27,6 +27,7 @@ class FakeInspector implements ProcessInspector {
   foregroundPgid() { return this.pgid }
   isStdinWaiting() { return this.waiting }
   processTree() { return this.members }
+  processSession() { return [] }
   isAlive(identity: ProcessIdentity) { return this.alive.has(identity.pid) }
   signalGroup(pgid: number, signal: PtySignal) {
     if (this.throwGroup) throw new Error('group failed')
@@ -325,6 +326,32 @@ describe('LocalPtySession readiness and output', () => {
     expect((await next.done).waitReason).toBe('inferred_idle')
   })
 
+  it('retains send ownership when cancellation signalling fails during an asynchronous write', async () => {
+    vi.useFakeTimers()
+    const terminal = new FakeTerminal()
+    const inspector = new FakeInspector()
+    const session = makeSession(terminal, inspector, config())
+    await initialize(session, terminal)
+
+    const writeGate = Promise.withResolvers<undefined>()
+    terminal.write = async () => { await writeGate.promise }
+    terminal.signalForeground = async () => { throw new Error('interrupt failed') }
+    const operation = session.startSend({ text: 'slow write', submit: true })
+    await Promise.resolve()
+    await Promise.resolve()
+    const rejected = expect(operation.done).rejects.toThrow('interrupt failed')
+    expect(operation.cancel()).toBe(true)
+    await rejected
+    expect(() => session.startSend({ text: 'must wait', submit: true })).toThrow('active send')
+
+    writeGate.resolve(undefined)
+    await Promise.resolve()
+    await Promise.resolve()
+    const next = session.startSend({ text: '', submit: false })
+    await vi.advanceTimersByTimeAsync(100)
+    expect((await next.done).waitReason).toBe('inferred_idle')
+  })
+
   it('handles startup exit, unknown exit signals, cancel-write failure, and stale polls', async () => {
     vi.useFakeTimers()
     const startupTerminal = new FakeTerminal()