Merge branch 'codex/simp-shared-acp-test-launcher' into codex/simp-trim-hook-snapshot-noise

packages/support/acp-snapshot/src/launcher.ts

@@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent {
   stderr(): string
   /** Resolve when a future session update matches the predicate. */
   waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise<SessionNotification['update']>
-  /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, and ACP parser drain. */
+  /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, ACP parsing, and client callbacks. */
   close(signal?: NodeJS.Signals): Promise<void>
 }
 
@@ -137,29 +137,41 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe
     Writable.toWeb(child.stdin) as WritableStream<Uint8Array>,
     Readable.toWeb(passthrough) as ReadableStream<Uint8Array>,
   )
+  const inFlightClientCallbacks = new Set<Promise<unknown>>()
+  const trackClientCallback = <T>(callback: () => T | PromiseLike<T>): Promise<T> => {
+    const pending = Promise.resolve().then(callback)
+    inFlightClientCallbacks.add(pending)
+    void pending.then(
+      () => { inFlightClientCallbacks.delete(pending) },
+      () => { inFlightClientCallbacks.delete(pending) },
+    )
+    return pending
+  }
+  const requestPermission = options.requestPermission
+    ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' as const } }))
   const makeClient = (_agent: AcpAgent): Client => ({
     sessionUpdate(params: SessionNotification): Promise<void> {
-      updates.push(params.update)
-      for (let index = updateWaiters.length - 1; index >= 0; index--) {
-        const waiter = updateWaiters[index]
-        /* v8 ignore next 1 -- index is bounded by the array length */
-        if (waiter === undefined) continue
-        let matches: boolean
-        try {
-          matches = waiter.match(params.update)
-        } catch (error: unknown) {
+      return trackClientCallback(() => {
+        updates.push(params.update)
+        for (let index = updateWaiters.length - 1; index >= 0; index--) {
+          const waiter = updateWaiters[index]
+          /* v8 ignore next 1 -- index is bounded by the array length */
+          if (waiter === undefined) continue
+          let matches: boolean
+          try {
+            matches = waiter.match(params.update)
+          } catch (error: unknown) {
+            updateWaiters.splice(index, 1)
+            waiter.reject(error)
+            continue
+          }
+          if (!matches) continue
           updateWaiters.splice(index, 1)
-          waiter.reject(error)
-          continue
+          waiter.resolve(params.update)
         }
-        if (!matches) continue
-        updateWaiters.splice(index, 1)
-        waiter.resolve(params.update)
-      }
-      return Promise.resolve()
+      })
     },
-    requestPermission: options.requestPermission
-      ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })),
+    requestPermission: params => trackClientCallback(() => requestPermission(params)),
   })
   const client = new ClientSideConnection(makeClient, stream)
   // `exit` only reports the parent process's status. Descendants may retain
@@ -168,7 +180,14 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe
   // `closed` follows parser exhaustion. Capture both eagerly so a caller that
   // invokes close after process exit still joins the complete drain boundary.
   const stdioClosed = new Promise<void>(resolve => child.once('close', () => { resolve() }))
-  const drained = Promise.all([stdioClosed, client.closed]).then(() => undefined)
+  const drained = Promise.all([stdioClosed, client.closed]).then(async () => {
+    // The ACP SDK's readable loop dispatches client callbacks without awaiting
+    // them. Once `closed` settles no new callbacks can start, but callbacks
+    // already in flight still belong to this launch's teardown boundary.
+    while (inFlightClientCallbacks.size > 0) {
+      await Promise.allSettled([...inFlightClientCallbacks])
+    }
+  })
   // A caller may await a pending update without calling close(). Make natural
   // stream exhaustion terminal for those waiters too, but only after the
   // parser has dispatched every buffered frame.

packages/support/acp-snapshot/tests/harness.spec.ts

@@ -1,4 +1,5 @@
 import { mkdtemp, rm, writeFile } from 'node:fs/promises'
+import { once } from 'node:events'
 import { tmpdir } from 'node:os'
 import { delimiter, join } from 'node:path'
 import { fileURLToPath } from 'node:url'
@@ -112,6 +113,41 @@ describe('runScenario', () => {
     expect(launched.stderr()).toContain('late inherited stderr')
   })
 
+  it('waits for in-flight client callbacks after the ACP stream closes', { timeout: 20_000 }, async () => {
+    const { dir, fixtureFile } = await scenario({ permissionProbe: true })
+    let releasePermission: (() => void) | undefined
+    const permissionReleased = new Promise<void>((resolve) => { releasePermission = resolve })
+    let markPermissionStarted: (() => void) | undefined
+    const permissionStarted = new Promise<void>((resolve) => { markPermissionStarted = resolve })
+    let permissionFinished = false
+    const launched = launchAcpTestAgent({
+      agent: AGENT,
+      cwd: dir,
+      env: { DSH_SNAPSHOT_FILE: fixtureFile },
+      async requestPermission() {
+        markPermissionStarted?.()
+        await permissionReleased
+        permissionFinished = true
+        return { outcome: { outcome: 'cancelled' } }
+      },
+    })
+    await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] })
+    void launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => undefined)
+    await permissionStarted
+
+    const childClosed = once(launched.child, 'close')
+    let closeSettled = false
+    const closing = launched.close('SIGKILL').then(() => { closeSettled = true })
+    await childClosed
+    await launched.client.closed
+    expect(closeSettled).toBe(false)
+
+    releasePermission?.()
+    await closing
+    expect(permissionFinished).toBe(true)
+  })
+
   it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => {
     const { fixtureFile } = await scenario({
       permissionProbe: true,