From 626654f81617a8b76b3ec13d2a537d4cbaee7276 Mon Sep 17 00:00:00 2001
From: laihenyi <lai@coach.ee>
Date: Fri, 13 Mar 2026 11:03:48 +0800
Subject: [PATCH] fix: prevent infinite restart loop on FOREIGN KEY constraint
 errors (#1334)

The pending-work-restart logic had no retry limit, causing infinite loops
when sessions encountered FOREIGN KEY constraint failures. This led to
2000+ error log entries per minute and eventual worker crash via SIGTERM.

Two fixes:
1. Add 'FOREIGN KEY constraint failed' to unrecoverable error patterns
   so it short-circuits immediately instead of falling through to restart
2. Add MAX_PENDING_RESTARTS (3) limit to pending-work-restart path as a
   safety net for any future unhandled persistent errors

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
---
 src/services/worker-service.ts | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/src/services/worker-service.ts b/src/services/worker-service.ts
index f43e05d7..2639df47 100644
--- a/src/services/worker-service.ts
+++ b/src/services/worker-service.ts
@@ -561,6 +561,7 @@ export class WorkerService {
           'ENOENT',
           'spawn',
           'Invalid API key',
+          'FOREIGN KEY constraint failed',
         ];
         if (unrecoverablePatterns.some(pattern => errorMessage.includes(pattern))) {
           hadUnrecoverableError = true;
@@ -659,16 +660,35 @@ export class WorkerService {
 
         // Check if there's pending work that needs processing with a fresh AbortController
         const pendingCount = pendingStore.getPendingCount(session.sessionDbId);
+        const MAX_PENDING_RESTARTS = 3;
 
         if (pendingCount > 0) {
+          // Track consecutive pending-work restarts to prevent infinite loops (e.g. FK errors)
+          session.consecutiveRestarts = (session.consecutiveRestarts || 0) + 1;
+
+          if (session.consecutiveRestarts > MAX_PENDING_RESTARTS) {
+            logger.error('SYSTEM', 'Exceeded max pending-work restarts, stopping to prevent infinite loop', {
+              sessionId: session.sessionDbId,
+              pendingCount,
+              consecutiveRestarts: session.consecutiveRestarts
+            });
+            session.consecutiveRestarts = 0;
+            this.broadcastProcessingStatus();
+            return;
+          }
+
           logger.info('SYSTEM', 'Pending work remains after generator exit, restarting with fresh AbortController', {
             sessionId: session.sessionDbId,
-            pendingCount
+            pendingCount,
+            attempt: session.consecutiveRestarts
           });
           // Reset AbortController for restart
           session.abortController = new AbortController();
           // Restart processor
           this.startSessionProcessor(session, 'pending-work-restart');
+        } else {
+          // Successful completion with no pending work — reset counter
+          session.consecutiveRestarts = 0;
         }
 
         this.broadcastProcessingStatus();