Просмотр исходного кода

fix(agent): don't resolve whenIdle() early on pre-step cancel + requeue (Codex review)

Codex's converge pass found a quiescence-contract violation: a whenIdle() waiter
registered for prompt A, then cancel() clears A, then prompt B is queued BEFORE
the loop resumes from the idle wait. The window-1 cancel branch called
settleIdle() UNCONDITIONALLY, resolving the waiter while B was still
queued-and-unrun — whenIdle() resolved with zero events, then B ran afterward.

Fix: in window 1, only settleIdle() + re-park when NO new work is queued. If a
send() raced in after the cancel, the marker was for the cancelled work only —
clear it and fall through to run the new prompt's turn, letting THAT turn's
running→idle settle the waiter (so whenIdle() waits for B to actually run).

Adds a regression test reproducing the exact interleaving (send A → whenIdle →
cancel → send B): whenIdle() now resolves only after B's turn ran (B's user
message + a turn/end in the log), and A was dropped.
Tianyi Cui 3 месяцев назад
Родитель
Сommit
9ee22bc6f6
2 измененных файлов с 41 добавлено и 8 удалено
  1. 16 8
      packages/agent-loop/src/loop.ts
  2. 25 0
      packages/agent-loop/tests/cancel.spec.ts

+ 16 - 8
packages/agent-loop/src/loop.ts

@@ -169,16 +169,24 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH
     if (handle.isDisposed()) break
 
     // Pre-step cancel (window 1): a `cancel()` landed after a `send()` woke the
-    // idle wait but before we flip to `running`. Drop the about-to-run turn: the
-    // queued/steering work is already cleared by `cancel()`, and we settle any
-    // `whenIdle()` waiter DIRECTLY (no status transition fires here, so the
-    // running→idle settle never runs) WITHOUT emitting `agent/status` (an ACP
-    // listener must not see a spurious idle that resolves a freshly-queued prompt
-    // as cancelled). Clear the marker and re-park.
+    // idle wait but before we flip to `running`. The cancelled queued/steering
+    // work is already cleared by `cancel()`. Clear the marker, then:
+    //   - if NOTHING new is queued, drop the about-to-run turn and re-park,
+    //     settling any `whenIdle()` waiter DIRECTLY (no running→idle transition
+    //     fires here to settle it) and WITHOUT emitting `agent/status` (an ACP
+    //     listener must not see a spurious idle that resolves a freshly-queued
+    //     prompt as cancelled);
+    //   - if a NEW prompt was queued AFTER the cancel (a send() that raced in
+    //     before the loop resumed), the marker was for the cancelled work only —
+    //     fall through and run the new prompt's turn. Do NOT settle waiters here:
+    //     a whenIdle() waiter must wait for that new turn's running→idle, not
+    //     resolve before it runs (the quiescence contract).
     if (handle.isCancelled()) {
       handle.clearCancel()
-      handle.settleIdle()
-      continue
+      if (!agent.inbox.hasQueued) {
+        handle.settleIdle()
+        continue
+      }
     }
 
     handle.setStatus('running')

+ 25 - 0
packages/agent-loop/tests/cancel.spec.ts

@@ -249,6 +249,31 @@ describe('Agent.cancel()', () => {
     expect(agent.session.events.some(e => e.type === 'turn/start')).toBe(false)
   })
 
+  it('whenIdle() does NOT resolve early when a new prompt is queued during a pre-step cancel', async () => {
+    // The subtle race: a whenIdle() waiter is registered for prompt A; cancel()
+    // clears A; prompt B is queued BEFORE the loop resumes from the idle wait.
+    // The window-1 cancel branch must NOT settle the waiter while B is still
+    // queued-and-unrun — whenIdle() must wait for B's turn to actually run and
+    // settle (the quiescence contract), not resolve before B's first event.
+    const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create('a1', { model: 'mock' })
+
+    send(agent, 'A')           // queues A (status still idle, loop microtask pending)
+    const idle = agent.whenIdle() // registers a waiter (idle + hasQueued → no fast path)
+    agent.cancel('drop A')     // arms marker, clears A
+    send(agent, 'B')           // B races in before the loop resumes
+
+    // whenIdle() must resolve only AFTER B's turn fully ran — by which point B's
+    // user message and a turn/end are in the log. (Before the fix it resolved
+    // immediately, with zero events, then B ran afterward.)
+    await idle
+    expect(userTexts(agent)).toContain('B')
+    expect(agent.session.events.some(e => e.type === 'turn/end')).toBe(true)
+    // A was dropped (never ran); only B's turn is recorded.
+    expect(userTexts(agent)).not.toContain('A')
+  })
+
   it("cancel clears the turn's steering — it is not re-enqueued as a fresh turn", async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)