From 2c01e7537433d2b6f0424de06b59cb6ad369f781 Mon Sep 17 00:00:00 2001
From: Rene Jean Corneille <14303619+RonsenbergVI@users.noreply.github.com>
Date: Sat, 22 Aug 2026 08:30:04 +0100
Subject: [PATCH] fix(graphiti): document the raised llm token ceiling

---
 benchmarks/graphiti/src/memory.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/benchmarks/graphiti/src/memory.py b/benchmarks/graphiti/src/memory.py
index 3d16eb0..29ee1dd 100644
--- a/benchmarks/graphiti/src/memory.py
+++ b/benchmarks/graphiti/src/memory.py
@@ -32,6 +32,9 @@
 with the same models. Override with ``--param model=...`` /
 ``--param embedding_model=...``; an explicit ``--param model=none`` (or
 ``embedding_model=none``) falls back to graphiti-core's own default.
+The LLM client runs with a raised completion ceiling (``LLM_MAX_TOKENS``)
+so gpt-5-mini's reasoning bursts cannot truncate structured output
+mid-JSON, and teardown closes every async client before its event loop.
 """
 
 import asyncio