fix(redis): add opt-in health_check_interval for stale pooled connections (open-webui#23573)

Introduces REDIS_HEALTH_CHECK_INTERVAL and wires it through to every
Redis client created by get_redis_connection (plain, cluster and
sentinel paths, sync and async). When set, redis-py will PING any
connection idle longer than the interval on checkout, so dead sockets
are surfaced as reconnectable errors before a real command lands on
them.

Defaults to unset (empty string) so existing deployments see no
behavioural change. Operators who want the protection should set it
shorter than the Redis server `timeout` setting and any firewall/LB
idle timeout on the path to Redis.

Co-authored-by: Claude <noreply@anthropic.com>

Author: Classic298

backend/open_webui/env.py

@@ -435,6 +435,20 @@ def parse_section(section):
     os.environ.get('REDIS_SOCKET_KEEPALIVE', 'False').lower() == 'true'
 )
 
+# How often (in seconds) redis-py should PING an idle pooled connection
+# before reusing it. Opt-in: defaults to unset (empty string) so behavior
+# is unchanged for existing deployments. When set, should be shorter than
+# the Redis server `timeout` setting and any firewall/LB idle timeout on
+# the path to Redis, so stale connections are detected before a real
+# command lands on them. Set to 0 or empty to disable.
+REDIS_HEALTH_CHECK_INTERVAL = os.environ.get('REDIS_HEALTH_CHECK_INTERVAL', '')
+try:
+    REDIS_HEALTH_CHECK_INTERVAL = int(REDIS_HEALTH_CHECK_INTERVAL)
+    if REDIS_HEALTH_CHECK_INTERVAL <= 0:
+        REDIS_HEALTH_CHECK_INTERVAL = None
+except ValueError:
+    REDIS_HEALTH_CHECK_INTERVAL = None
+
 REDIS_RECONNECT_DELAY = os.environ.get('REDIS_RECONNECT_DELAY', '')
 
 if REDIS_RECONNECT_DELAY == '':

backend/open_webui/utils/redis.py

@@ -9,6 +9,7 @@
 
 from open_webui.env import (
     REDIS_CLUSTER,
+    REDIS_HEALTH_CHECK_INTERVAL,
     REDIS_SOCKET_CONNECT_TIMEOUT,
     REDIS_SOCKET_KEEPALIVE,
     REDIS_SENTINEL_HOSTS,
@@ -202,6 +203,12 @@ def get_redis_connection(
         {'socket_keepalive': True} if REDIS_SOCKET_KEEPALIVE else {}
     )
 
+    health_check_kwargs = (
+        {'health_check_interval': REDIS_HEALTH_CHECK_INTERVAL}
+        if REDIS_HEALTH_CHECK_INTERVAL
+        else {}
+    )
+
     if async_mode:
         import redis.asyncio as redis
 
@@ -217,6 +224,7 @@ def get_redis_connection(
                 decode_responses=decode_responses,
                 socket_connect_timeout=REDIS_SOCKET_CONNECT_TIMEOUT,
                 **keepalive_kwargs,
+                **health_check_kwargs,
             )
             connection = SentinelRedisProxy(
                 sentinel,
@@ -231,13 +239,15 @@ def get_redis_connection(
                 decode_responses=decode_responses,
                 **connect_timeout_kwargs,
                 **keepalive_kwargs,
+                **health_check_kwargs,
             )
         elif redis_url:
             connection = redis.from_url(
                 redis_url,
                 decode_responses=decode_responses,
                 **connect_timeout_kwargs,
                 **keepalive_kwargs,
+                **health_check_kwargs,
             )
     else:
         import redis
@@ -253,6 +263,7 @@ def get_redis_connection(
                 decode_responses=decode_responses,
                 socket_connect_timeout=REDIS_SOCKET_CONNECT_TIMEOUT,
                 **keepalive_kwargs,
+                **health_check_kwargs,
             )
             connection = SentinelRedisProxy(
                 sentinel,
@@ -267,13 +278,15 @@ def get_redis_connection(
                 decode_responses=decode_responses,
                 **connect_timeout_kwargs,
                 **keepalive_kwargs,
+                **health_check_kwargs,
             )
         elif redis_url:
             connection = redis.Redis.from_url(
                 redis_url,
                 decode_responses=decode_responses,
                 **connect_timeout_kwargs,
                 **keepalive_kwargs,
+                **health_check_kwargs,
             )
 
     _CONNECTION_CACHE[cache_key] = connection