From a5ea8b0b8a086d1c61a47702854289d34f823659 Mon Sep 17 00:00:00 2001
From: Classic298 <27028174+Classic298@users.noreply.github.com>
Date: Sat, 29 Aug 2026 21:00:52 +0200
Subject: [PATCH] fix: stopping a response across instances on Redis Cluster
 (#29165)

On Redis Cluster deployments the stop button never stopped a running response when the request landed on a different instance than the one streaming it. The pub/sub listener that carries the stop signal between instances never managed to subscribe, so the command was published to a channel nobody was listening on.

The listener subscribes through a cluster client that connects lazily, and redis-py resolves the pub/sub node from a slot cache that is still empty at that point, which fails with a bare KeyError. Awaiting initialize() first fills that cache. It is a no-op on standalone and Sentinel clients, so nothing has to branch on the deployment type, and it stays inside the reconnect loop so a failover refreshes the cache instead of resubscribing against a stale one.

Before 0.11.1 the listener died on that first exception and cross-instance stop never worked at all. The reconnect loop added in 0.11.1 turned it into a startup window plus KeyError retry spam in the logs. Reported upstream as redis/redis-py#4296.

Fixes #19840
---
 backend/open_webui/tasks.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/backend/open_webui/tasks.py b/backend/open_webui/tasks.py
index ef15c57a18..0eb223e9b6 100644
--- a/backend/open_webui/tasks.py
+++ b/backend/open_webui/tasks.py
@@ -32,6 +32,9 @@ async def redis_task_command_listener(app):
     while True:
         pubsub = None
         try:
+            # RedisCluster can't route a pubsub subscribe until initialize() fills its slot cache.
+            await redis.initialize()
+
             pubsub = redis.pubsub()
             await pubsub.subscribe(REDIS_PUBSUB_CHANNEL)
             reconnect_interval = REDIS_PUBSUB_RECONNECT_INTERVAL