test(acp): snapshot cancelled queued tool calls

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

@@ -37,11 +37,10 @@ export type { AgentUnderTest } from './launcher.ts'
  * (random) session id into a `{{sessionId}}` variable that later steps
  * reference, since a committed file cannot know the id in advance.
  *
- * `promptAndCancel` sends a prompt WITHOUT awaiting its response, waits until
- * the client observes the first streamed `agent_message_chunk` (so the emitted
- * frames deterministically precede the cancellation), then cancels the turn —
- * the only way to exercise a cancel deterministically (a plain `prompt` step
- * awaits the response, which a cancel/hang scenario would block on forever).
+ * `promptAndCancel` starts a prompt without awaiting completion, waits until
+ * the client observes the selected update (`agent_message_chunk` by default),
+ * then cancels and awaits completion. This keeps update/cancel order
+ * deterministic for fixtures that a plain `prompt` cannot drive.
  */
 export type InputStep =
   | { op: 'initialize'; terminalOutput?: boolean }
@@ -49,7 +48,7 @@ export type InputStep =
   | { op: 'newSessionExpectError'; additionalDirectories?: string[] }
   | { op: 'prompt'; text: string }
   | { op: 'promptExpectError'; text: string }
-  | { op: 'promptAndCancel'; text: string }
+  | { op: 'promptAndCancel'; text: string; afterUpdate?: 'agent_message_chunk' | 'tool_call' }
   | { op: 'cancel' }
   | { op: 'setConfigOption'; configId: string; value: string }
   | { op: 'setConfigOptionExpectError'; configId: string; value: string }
@@ -342,15 +341,12 @@ async function runStep(
     case 'promptAndCancel': {
       const sessionId = getSessionId()
       if (sessionId === undefined) throw new Error('snapshot-harness: promptAndCancel before newSession')
-      // Dispatch the prompt WITHOUT awaiting (a hang fixture never resolves on
-      // its own). To pin frame order deterministically, wait until the client
-      // has OBSERVED the hang's streamed agent_message_chunk before cancelling —
-      // so those update frames always precede the cancelled prompt response in
-      // the transcript (without this, the late chunk and the response race).
-      // Then cancel and await the prompt, which the bridge settles as
-      // `cancelled` once the abort propagates.
+      // Dispatch without awaiting because the fixture does not settle on its
+      // own. Waiting for the selected update pins it before cancellation and
+      // the cancelled prompt response in the transcript.
       const promptDone = client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
-      await waitForUpdate(u => u.sessionUpdate === 'agent_message_chunk')
+      const afterUpdate = step.afterUpdate ?? 'agent_message_chunk'
+      await waitForUpdate(u => u.sessionUpdate === afterUpdate)
       await client.cancel({ sessionId })
       await promptDone
       return

packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts

@@ -33,6 +33,8 @@ interface Behavior {
   rejectExtraDirs?: boolean
   /** How `session/prompt` settles: a clean response, a JSON-RPC error, or a hang until `session/cancel`. */
   prompt?: 'respond' | 'error' | 'hang-until-cancel'
+  /** Emit a tool call instead of a message chunk before parking a cancellable prompt. */
+  cancelAtToolCall?: boolean
   /** Before responding to a prompt, send a `session/request_permission` request and echo its outcome as a chunk. */
   permissionProbe?: boolean
   /** Echo the `DSH_SNAPSHOT_*` env the harness set as a chunk (spec-side env-plumbing assertions). */
@@ -126,7 +128,23 @@ async function handlePrompt(id: number | string): Promise<void> {
       params: { sessionId, update: { sessionUpdate: 'agent_thought_chunk', content: { type: 'text', text: 'mulling' } } },
     })
   }
-  chunk('thinking about it')
+  if (behavior.cancelAtToolCall === true) {
+    send({
+      method: 'session/update',
+      params: {
+        sessionId,
+        update: {
+          sessionUpdate: 'tool_call',
+          toolCallId: 'call_fake_1',
+          title: 'fake tool',
+          kind: 'execute',
+          status: 'in_progress',
+        },
+      },
+    })
+  } else {
+    chunk('thinking about it')
+  }
   if (behavior.echoEnv === true) {
     chunk(`env:${JSON.stringify({
       mode: process.env.DSH_SNAPSHOT,

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

@@ -334,6 +334,16 @@ describe('runScenario', () => {
     expect(result.rawStdout.indexOf('thinking about it')).toBeLessThan(result.rawStdout.indexOf('cancelled'))
   })
 
+  it('promptAndCancel can wait for a tool call before cancelling', { timeout: 20_000 }, async () => {
+    const { fixtureFile } = await scenario({ prompt: 'hang-until-cancel', cancelAtToolCall: true })
+    const result = await runScenario(
+      { steps: [...boot, { op: 'promptAndCancel', text: 'hang', afterUpdate: 'tool_call' }] },
+      { agent: AGENT, mode: 'replay', fixtureFile },
+    )
+    expect(result.rawStdout).toContain('"sessionUpdate":"tool_call"')
+    expect(result.rawStdout.indexOf('"sessionUpdate":"tool_call"')).toBeLessThan(result.rawStdout.indexOf('cancelled'))
+  })
+
   it('promptExpectError swallows a model-error response as the expected outcome', { timeout: 20_000 }, async () => {
     const { fixtureFile } = await scenario({ prompt: 'error' })
     const result = await runScenario(