Files
hapi/shared/src/agentCliSpawnLease.ts
T
df1a56e1db fix(cursor): exclusive agent spawn lease for list-models vs ACP (#1529)
* fix(cursor): exclusive agent spawn lease for list-models vs ACP (#1520)

Add a proper-lockfile spawn lease beside agent-acp-active so model probes
and ACP transport acquire mutual exclusion atomically before spawning
agent children, closing the post-#1518 check-then-act overlap window.

Fixes #1520

Co-authored-by: Cursor <cursoragent@cursor.com>

* chore(web): fix markdown-a test HappyChatContext mock for typecheck

Adds showSessionSummaryInChat to chatContext() so CI typecheck passes on
the PR branch (pre-existing main breakage unrelated to #1520).

Co-authored-by: Cursor <cursoragent@cursor.com>

* Revert "chore(web): fix markdown-a test HappyChatContext mock for typecheck"

This reverts commit 4973f321a31fda772e8990ea6cda20517ca906aa.

* fix(cursor): scope spawn lease to agent spawn window only (#1520)

Hold agent-cli.spawn only around spawn('agent') in AcpStdioTransport, not
for the full ACP session. Restores N concurrent cursor sessions per host;
list-models probe lease unchanged.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cursor): tighten spawn lease lifecycle for babysit (#1520)

Acquire spawn lease before ACP marker publish; unregister on spawn failure.
Hold list-models probe lease until child exit on timeout. Add missing
showSessionSummaryInChat to markdown-a test mock (unblocks CI typecheck).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cursor): re-check ACP marker after spawn lease acquire (#1520)

Close check-then-act window where ACP could publish its marker between
the inactive guard read and list-models spawn. Add regression test.

Co-authored-by: Cursor <cursoragent@cursor.com>

* test(cursor): fix ACP-after-acquire mock call order (#1520)

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cursor): async spawn lease + force-kill probe timeout (#1520)

Add acquireAgentCliSpawnLease (setTimeout yields) for ACP create path;
AcpStdioTransport.create() async factory. Probe timeout uses
killProcessByChildProcess(force) while holding lease until child exit.

Addresses Bugbot Majors: session-lifetime mutex (fe07b708d), probe lease
release, post-acquire re-check (137baa779), sync loop starvation, timeout
escalation.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(acp): coalesce concurrent initialize() transport spawns (#1520)

Await shared bootstrapTransport promise so overlapping initialize calls
do not spawn duplicate ACP children while create() is in flight.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-12 18:42:43 +01:00

171 lines
5.0 KiB
TypeScript

/**
* Cross-process exclusive lease for Cursor `agent` child processes.
* ACP transport and `agent --list-models` probes must not overlap — Cursor
* SIGTERMs the other child (exit 143). Uses proper-lockfile beside the
* agent-acp-active marker dir so acquisition is atomic (no check-then-act).
*/
import { existsSync, mkdirSync, writeFileSync } from 'node:fs'
import { join } from 'node:path'
import lockfile from 'proper-lockfile'
const SPAWN_LOCK_STALE_MS = 120_000
const SPAWN_LOCK_UPDATE_MS = 30_000
const SPAWN_LOCK_RETRY_INTERVAL_MS = 100
const SPAWN_LOCK_MAX_ATTEMPTS = 300
/** Cross-process lease release fn when this process holds the spawn lease. */
let leaseRelease: (() => void) | null = null
/** Nested ACP registerActiveAcpTransport calls sharing one lease. */
let acpRegisterLeaseDepth = 0
function sleepMsSync(ms: number): void {
const bun = (globalThis as { Bun?: { sleepSync?: (duration: number) => void } }).Bun
if (bun?.sleepSync) {
bun.sleepSync(ms)
return
}
const end = Date.now() + ms
while (Date.now() < end) {
// Node vitest fallback when Bun.sleepSync is unavailable.
}
}
function spawnLockfilePath(lockTarget: string): string {
return `${lockTarget}.hapi.lock`
}
function lockOptions(lockTarget: string): {
realpath: boolean
lockfilePath: string
stale: number
update: number
retries: number
} {
return {
realpath: false,
lockfilePath: spawnLockfilePath(lockTarget),
stale: SPAWN_LOCK_STALE_MS,
update: SPAWN_LOCK_UPDATE_MS,
retries: 0,
}
}
/** Lease anchor file colocated with the agent-acp-active marker directory. */
export function getAgentCliSpawnLockTarget(hapiHome: string): string {
const locksDir = join(hapiHome, 'locks')
mkdirSync(locksDir, { recursive: true })
const target = join(locksDir, 'agent-cli.spawn')
if (!existsSync(target)) {
writeFileSync(target, '', { flag: 'a' })
}
return target
}
function claimSpawnLeaseSync(hapiHome: string): boolean {
if (leaseRelease !== null) {
return false
}
const lockTarget = getAgentCliSpawnLockTarget(hapiHome)
try {
leaseRelease = lockfile.lockSync(lockTarget, lockOptions(lockTarget))
return true
} catch {
return false
}
}
/**
* Non-blocking exclusive lease for model-list probes. Returns false when
* another holder (ACP or probe) already owns the spawn lease.
*/
export function tryAcquireAgentCliSpawnLeaseSync(hapiHome: string): boolean {
if (leaseRelease !== null || acpRegisterLeaseDepth > 0) {
return false
}
return claimSpawnLeaseSync(hapiHome)
}
function sleepMs(ms: number): Promise<void> {
return new Promise((resolve) => setTimeout(resolve, ms))
}
/** Blocking exclusive lease for ACP transport startup (sync — tests only). */
export function acquireAgentCliSpawnLeaseSync(hapiHome: string): void {
if (acpRegisterLeaseDepth > 0) {
acpRegisterLeaseDepth += 1
return
}
for (let attempt = 0; attempt < SPAWN_LOCK_MAX_ATTEMPTS; attempt++) {
if (claimSpawnLeaseSync(hapiHome)) {
acpRegisterLeaseDepth = 1
return
}
sleepMsSync(SPAWN_LOCK_RETRY_INTERVAL_MS)
}
throw new Error('agent CLI spawn lease held by another process')
}
/** Blocking exclusive lease for ACP transport startup (yields event loop between retries). */
export async function acquireAgentCliSpawnLease(hapiHome: string): Promise<void> {
if (acpRegisterLeaseDepth > 0) {
acpRegisterLeaseDepth += 1
return
}
for (let attempt = 0; attempt < SPAWN_LOCK_MAX_ATTEMPTS; attempt++) {
if (claimSpawnLeaseSync(hapiHome)) {
acpRegisterLeaseDepth = 1
return
}
await sleepMs(SPAWN_LOCK_RETRY_INTERVAL_MS)
}
throw new Error('agent CLI spawn lease held by another process')
}
/** Release after a list-models probe child exits. */
export function releaseAgentCliSpawnLeaseSync(): void {
if (acpRegisterLeaseDepth > 0 || leaseRelease === null) {
return
}
leaseRelease()
leaseRelease = null
}
/** Release after the last ACP transport unregisters in this process. */
export function releaseAgentCliSpawnLeaseFromAcpRegisterSync(): void {
if (acpRegisterLeaseDepth <= 0) {
return
}
acpRegisterLeaseDepth -= 1
if (acpRegisterLeaseDepth > 0 || leaseRelease === null) {
return
}
leaseRelease()
leaseRelease = null
}
/** @internal test-only */
export function _resetAgentCliSpawnLeaseForTests(hapiHome?: string): void {
acpRegisterLeaseDepth = 0
if (leaseRelease) {
leaseRelease()
leaseRelease = null
}
if (!hapiHome) {
return
}
const lockTarget = getAgentCliSpawnLockTarget(hapiHome)
try {
lockfile.unlockSync(lockTarget, {
realpath: false,
lockfilePath: spawnLockfilePath(lockTarget),
})
} catch {
// Best effort — lock may not exist.
}
}