From d1789c889beb534784bfe44a820b80feb0ccbbfa Mon Sep 17 00:00:00 2001
From: Classic298 <27028174+Classic298@users.noreply.github.com>
Date: Mon, 28 Sep 2026 09:50:22 +0200
Subject: [PATCH] fix: server memory grows with every chat until a restart

Every chat that got a reply left a small lock behind in the server process, so a long-running server kept one for every chat it had ever answered and only a restart gave the memory back. The lock is now dropped as soon as nothing is using it, so a finished reply leaves nothing behind per chat, while replies, sub-agent results and timers for the same chat still wait for each other as before.

Fixes #31521
---
 backend/open_webui/utils/subagents.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/backend/open_webui/utils/subagents.py b/backend/open_webui/utils/subagents.py
index 13b9699216..efb8161a0f 100644
--- a/backend/open_webui/utils/subagents.py
+++ b/backend/open_webui/utils/subagents.py
@@ -3,6 +3,7 @@ from __future__ import annotations
 import asyncio
 import copy
 import time
+import weakref
 from datetime import timedelta
 from uuid import uuid4
 
@@ -41,7 +42,7 @@ MUTATING_MEMORY_TOOLS = {
 _background_active: set[str] = set()
 _background_lock = asyncio.Lock()
 _foreground_semaphore: asyncio.Semaphore | None = None
-_parent_locks: dict[str, asyncio.Lock] = {}
+_parent_locks: weakref.WeakValueDictionary[str, asyncio.Lock] = weakref.WeakValueDictionary()
 
 
 def _build_request(source: Request, user_id: str, *, internal: bool) -> Request: