fix(#2732): detect crashed subagent sessions with shorter timeout
When a subagent session disappears from the status registry (process crashed), the main agent was waiting the full stale timeout before acting. Fix: - Add sessionGoneTimeoutMs config option (default 60s, vs 30min normal) - task-poller: use shorter timeout when session is gone from status - manager: verify session existence when gone, fail crashed tasks immediately with descriptive error - Add legacy-plugin-toast hook for #2823 migration warnings - Update schema with new config option
This commit is contained in:
@@ -1787,6 +1787,53 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
|
||||
})
|
||||
}
|
||||
|
||||
private async verifySessionExists(sessionID: string): Promise<boolean> {
|
||||
try {
|
||||
const result = await this.client.session.get({ path: { id: sessionID } })
|
||||
return !!result.data
|
||||
} catch {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
private async failCrashedTask(task: BackgroundTask, errorMessage: string): Promise<void> {
|
||||
task.status = "error"
|
||||
task.error = errorMessage
|
||||
task.completedAt = new Date()
|
||||
if (task.rootSessionID) {
|
||||
this.unregisterRootDescendant(task.rootSessionID)
|
||||
}
|
||||
this.taskHistory.record(task.parentSessionID, { id: task.id, sessionID: task.sessionID, agent: task.agent, description: task.description, status: "error", category: task.category, startedAt: task.startedAt, completedAt: task.completedAt })
|
||||
if (task.concurrencyKey) {
|
||||
this.concurrencyManager.release(task.concurrencyKey)
|
||||
task.concurrencyKey = undefined
|
||||
}
|
||||
|
||||
const completionTimer = this.completionTimers.get(task.id)
|
||||
if (completionTimer) {
|
||||
clearTimeout(completionTimer)
|
||||
this.completionTimers.delete(task.id)
|
||||
}
|
||||
const idleTimer = this.idleDeferralTimers.get(task.id)
|
||||
if (idleTimer) {
|
||||
clearTimeout(idleTimer)
|
||||
this.idleDeferralTimers.delete(task.id)
|
||||
}
|
||||
|
||||
this.cleanupPendingByParent(task)
|
||||
this.clearNotificationsForTask(task.id)
|
||||
removeTaskToastTracking(task.id)
|
||||
this.scheduleTaskRemoval(task.id)
|
||||
if (task.sessionID) {
|
||||
SessionCategoryRegistry.remove(task.sessionID)
|
||||
}
|
||||
|
||||
this.markForNotification(task)
|
||||
this.enqueueNotificationForParent(task.parentSessionID, () => this.notifyParentSession(task)).catch(err => {
|
||||
log("[background-agent] Error in notifyParentSession for crashed task:", { taskId: task.id, error: err })
|
||||
})
|
||||
}
|
||||
|
||||
private async pollRunningTasks(): Promise<void> {
|
||||
if (this.pollingInFlight) return
|
||||
this.pollingInFlight = true
|
||||
@@ -1848,11 +1895,20 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
|
||||
}
|
||||
|
||||
// Session is idle or no longer in status response (completed/disappeared)
|
||||
const sessionGoneFromStatus = !sessionStatus
|
||||
const completionSource = sessionStatus?.type === "idle"
|
||||
? "polling (idle status)"
|
||||
: "polling (session gone from status)"
|
||||
const hasValidOutput = await this.validateSessionHasOutput(sessionID)
|
||||
if (!hasValidOutput) {
|
||||
if (sessionGoneFromStatus) {
|
||||
const sessionExists = await this.verifySessionExists(sessionID)
|
||||
if (!sessionExists) {
|
||||
log("[background-agent] Session no longer exists (crashed), marking task as error:", task.id)
|
||||
await this.failCrashedTask(task, "Subagent session no longer exists (process likely crashed). The session disappeared without producing any output.")
|
||||
continue
|
||||
}
|
||||
}
|
||||
log("[background-agent] Polling idle/gone but no valid output yet, waiting:", task.id)
|
||||
continue
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user