Merge goal tool fixes and align same-session blockers

This commit is contained in:
Tianyi Cui
2026-07-20 17:23:55 +08:00
55 changed files with 860 additions and 891 deletions

View File

@@ -41,12 +41,15 @@ export type { AgentUnderTest } from './launcher.ts'
* the client observes the selected update (`agent_message_chunk` by default),
* then cancels and awaits completion. A named `waitForToolCallUpdate` keeps the
* step open for a terminal tool update that may follow the prompt response.
* `promptAndWaitForAgentMessage` arms an exact text-chunk waiter before sending
* the prompt, then keeps the application live until that later update arrives.
*/
export type InputStep =
| { op: 'initialize'; terminalOutput?: boolean }
| { op: 'newSession' }
| { op: 'newSessionExpectError'; additionalDirectories?: string[] }
| { op: 'prompt'; text: string }
| { op: 'promptAndWaitForAgentMessage'; text: string; waitForText: string }
| { op: 'promptExpectError'; text: string }
| {
op: 'promptAndCancel'
@@ -331,6 +334,15 @@ async function runStep(
await client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
return
}
case 'promptAndWaitForAgentMessage': {
const sessionId = getSessionId()
if (sessionId === undefined) throw new Error('snapshot-harness: promptAndWaitForAgentMessage before newSession')
const updateDone = waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk'
&& update.content.type === 'text' && update.content.text === step.waitForText)
await client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
await updateDone
return
}
case 'promptExpectError': {
const sessionId = getSessionId()
if (sessionId === undefined) throw new Error('snapshot-harness: promptExpectError before newSession')

View File

@@ -334,6 +334,21 @@ describe('runScenario', () => {
expect(result.rawStdout.indexOf('thinking about it')).toBeLessThan(result.rawStdout.indexOf('cancelled'))
})
it('promptAndWaitForAgentMessage keeps the app live through a matching later update', { timeout: 20_000 }, async () => {
const { fixtureFile } = await scenario({ prompt: 'respond' })
const result = await runScenario(
{
steps: [...boot, {
op: 'promptAndWaitForAgentMessage',
text: 'go',
waitForText: 'thinking about it',
}],
},
{ agent: AGENT, mode: 'replay', fixtureFile },
)
expect(result.rawStdout).toContain('thinking about it')
})
it('promptAndCancel can bracket cancellation with tool-call updates', { timeout: 20_000 }, async () => {
const { fixtureFile } = await scenario({
prompt: 'hang-until-cancel',