airkjw/claude-mem
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: prevent zombie process accumulation by verifying subprocess exit (#1168) (#1175)

Browse Source 
Two changes fix the observer process resource leak:

1. Add ensureProcessExit to generator finally blocks in SessionRoutes and
   worker-service, matching the pattern already working in SDKAgent.

2. Add stale session reaper (every 2m) that removes sessions with no active
   generator and no pending work after 15m idle. This unblocks the orphan
   reaper which previously skipped processes for "active" sessions.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Alex Newman
2026-02-18 16:33:23 -05:00
committed by GitHub
parent 2180d31ee6
commit 5d79bb7a7a
5 changed files with 172 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/services/worker-service.ts
+29 -2
View File
@@ -116,7 +116,7 @@ import { LogsRoutes } from './worker/http/routes/LogsRoutes.js';
import { MemoryRoutes } from './worker/http/routes/MemoryRoutes.js';
// Process management for zombie cleanup (Issue #737)
import { startOrphanReaper, reapOrphanedProcesses } from './worker/ProcessRegistry.js';
import { startOrphanReaper, reapOrphanedProcesses, getProcessBySession, ensureProcessExit } from './worker/ProcessRegistry.js';
/**
* Build JSON status output for hook framework communication.
@@ -176,6 +176,9 @@ export class WorkerService {
// Orphan reaper cleanup function (Issue #737)
private stopOrphanReaper: (() => void) | null = null;
// Stale session reaper interval (Issue #1168)
private staleSessionReaperInterval: ReturnType<typeof setInterval> | null = null;
// AI interaction tracking for health endpoint
private lastAiInteraction: {
timestamp: number;
@@ -465,6 +468,18 @@ export class WorkerService {
});
logger.info('SYSTEM', 'Started orphan reaper (runs every 5 minutes)');
// Reap stale sessions to unblock orphan process cleanup (Issue #1168)
this.staleSessionReaperInterval = setInterval(async () => {
try {
const reaped = await this.sessionManager.reapStaleSessions();
if (reaped > 0) {
logger.info('SYSTEM', `Reaped ${reaped} stale sessions`);
}
} catch (e) {
logger.error('SYSTEM', 'Stale session reaper error', { error: e instanceof Error ? e.message : String(e) });
}
}, 2 * 60 * 1000);
// Auto-recover orphaned queues (fire-and-forget with error logging)
this.processPendingQueues(50).then(result => {
if (result.sessionsStarted > 0) {
@@ -593,7 +608,13 @@ export class WorkerService {
};
throw error;
})
.finally(() => {
.finally(async () => {
// CRITICAL: Verify subprocess exit to prevent zombie accumulation (Issue #1168)
const trackedProcess = getProcessBySession(session.sessionDbId);
if (trackedProcess && !trackedProcess.process.killed && trackedProcess.process.exitCode === null) {
await ensureProcessExit(trackedProcess, 5000);
}
session.generatorPromise = null;
// Record successful AI interaction if no error occurred
@@ -823,6 +844,12 @@ export class WorkerService {
this.stopOrphanReaper = null;
}
// Stop stale session reaper (Issue #1168)
if (this.staleSessionReaperInterval) {
clearInterval(this.staleSessionReaperInterval);
this.staleSessionReaperInterval = null;
}
await performGracefulShutdown({
server: this.server.getHttpServer(),
sessionManager: this.sessionManager,