Merge remote-tracking branch 'origin/master' into codex/rfc-subagent-background-tasks

Adopts #185 (dsh-timeout: clampTimeout/deadline/timeoutOf drive bash
run() timeout classification; runBash loses its own timer) and #108
(ask_user_question) across the task-runtime rework: bash-local keeps
the BashProcess handle shape with master's deadline mechanics, tool
catalogs/expectations carry both the task_* and ask-user tools, and
generated docs are regenerated on the union.
This commit is contained in:
Yichen Jiang
2026-07-09 21:32:07 +08:00
128 changed files with 6732 additions and 332 deletions

View File

@@ -77,6 +77,8 @@ describe('LocalBashExecutor.run', () => {
const { bash } = await setup({ timeoutMs: 60_000 })
const result = await bash.run(bash.resolve({ command: 'sleep 60', timeoutMs: 100 }))
expect(result.timedOut).toBe(true)
// Mutually exclusive: a timeout classifies as timedOut, never also aborted.
expect(result.aborted).toBe(false)
expect(result.timeoutMs).toBe(100)
})
@@ -87,6 +89,20 @@ describe('LocalBashExecutor.run', () => {
setTimeout(() => { controller.abort() }, 50)
const result = await pending
expect(result.aborted).toBe(true)
// Mutually exclusive: an upstream cancel classifies as aborted, never also timedOut.
expect(result.timedOut).toBe(false)
})
it('classifies a self-killed command as neither timed out nor aborted', async () => {
// The command kills itself (SIGTERM) with no timeout and no upstream abort:
// the deadline signal never fires, so both classifications are false — the
// fused-signal classification reports the cause that cut the command short,
// and here nothing the executor owns did.
const { bash } = await setup({ timeoutMs: 60_000 })
const result = await bash.run(bash.resolve({ command: 'kill -TERM $$' }))
expect(result.signal).toBe('SIGTERM')
expect(result.timedOut).toBe(false)
expect(result.aborted).toBe(false)
})
it('rejects on spawn failure (bad workdir)', async () => {

View File

@@ -26,7 +26,6 @@ function spec(command: string, overrides: Partial<Parameters<typeof runBash>[0]>
return {
command,
cwd: process.cwd(),
timeoutMs: 0,
maxOutputBytes: 64_000,
graceMs: 3_000,
...overrides,
@@ -56,13 +55,25 @@ async function waitForStdout(running: RunningBash, expected: string, timeoutMs =
throw new Error(`stdout did not include ${JSON.stringify(expected)} after ${timeoutMs}ms`)
}
async function waitForPidFile(path: string, timeoutMs = 5_000): Promise<number> {
const deadline = Date.now() + timeoutMs
while (Date.now() < deadline) {
try {
const pid = Number(readFileSync(path, 'utf8').trim())
if (Number.isSafeInteger(pid) && pid > 0) return pid
} catch {
// The child shell has not written the pid file yet.
}
await new Promise(resolve => setTimeout(resolve, 20))
}
throw new Error(`pid file ${path} was not written after ${timeoutMs}ms`)
}
describe('runBash', () => {
it('captures stdout on success', async () => {
const result = await runBash(spec('echo hello')).done
expect(result.exitCode).toBe(0)
expect(result.signal).toBeNull()
expect(result.timedOut).toBe(false)
expect(result.aborted).toBe(false)
expect(result.stdout.text).toBe('hello\n')
expect(result.stdout.truncated).toBe(false)
expect(result.stderr.text).toBe('')
@@ -97,17 +108,22 @@ describe('runBash', () => {
expect(result.stdout.text.trim()).toMatch(/\/tmp$/)
})
it('kills with SIGTERM on timeout', async () => {
it('kills the process group with SIGTERM when the signal fires', async () => {
// runBash owns no timer: it kills on abort. The executor drives the timeout
// by firing this signal via a deadline (see executor.spec.ts); here we
// assert the kill itself lands as SIGTERM.
const controller = new AbortController()
const start = Date.now()
const result = await runBash(spec('sleep 60', { timeoutMs: 100 })).done
const running = runBash(spec('sleep 60', { signal: controller.signal }))
setTimeout(() => { controller.abort('deadline') }, 100)
const result = await running.done
expect(Date.now() - start).toBeLessThan(5_000)
expect(result.timedOut).toBe(true)
expect(result.signal).toBe('SIGTERM')
expect(result.exitCode).toBeNull()
})
it('escalates to SIGKILL when SIGTERM is trapped', async () => {
const running = runBash(spec('trap \'\' TERM; echo ready; sleep 60', { graceMs: 200 }))
const running = runBash(spec('trap \'\' TERM; echo ready; while :; do sleep 60 & wait $!; done', { graceMs: 200 }))
await waitForStdout(running, 'ready\n')
running.kill()
const result = await running.done
@@ -119,8 +135,7 @@ describe('runBash', () => {
// group must take the sleep down with bash.
const pidFile = join(spillDir, `grandchild-${Date.now()}.pid`)
const running = runBash(spec(`sleep 60 & echo $! > ${pidFile}; wait`))
await new Promise(resolve => setTimeout(resolve, 300))
const grandchild = Number(readFileSync(pidFile, 'utf8').trim())
const grandchild = await waitForPidFile(pidFile)
expect(grandchild).toBeGreaterThan(0)
running.kill()
@@ -134,7 +149,6 @@ describe('runBash', () => {
const running = runBash(spec('sleep 60', { signal: controller.signal }))
setTimeout(() => { controller.abort('user cancelled') }, 50)
const result = await running.done
expect(result.aborted).toBe(true)
expect(result.signal).toBe('SIGTERM')
})
@@ -211,7 +225,6 @@ describe('stdin and extra env (set by in-process plugins)', () => {
const big = 'x'.repeat(1024 * 1024)
const result = await runBash(spec('exit 7', { stdin: big })).done
expect(result.exitCode).toBe(7)
expect(result.aborted).toBe(false)
})
})
@@ -339,11 +352,11 @@ describe('abort edge cases', () => {
.toThrow(/aborted before spawn: aborted/)
})
it('reports an externally self-killed command without the timeout marker', async () => {
it('reports the terminating signal of an externally self-killed command', async () => {
// runBash reports the raw signal; whether it counts as timeout/cancel is the
// executor's classification (a self-kill is neither) — see executor.spec.ts.
const result = await runBash(spec('kill -TERM $$')).done
expect(result.signal).toBe('SIGTERM')
expect(result.timedOut).toBe(false)
expect(result.aborted).toBe(false)
})
})
@@ -396,10 +409,9 @@ describe('review fixes: env scrubbing and spill hardening', () => {
it('honors AbortSignal on background-style runs (no timeout)', async () => {
const controller = new AbortController()
const running = runBash(spec('sleep 60', { timeoutMs: 0, signal: controller.signal }))
const running = runBash(spec('sleep 60', { signal: controller.signal }))
setTimeout(() => { controller.abort() }, 50)
const result = await running.done
expect(result.aborted).toBe(true)
expect(result.signal).toBe('SIGTERM')
})
})