From 7ca2a482316ca909076054eee21b1e0514a7e2de Mon Sep 17 00:00:00 2001
From: "llm-d-router-release-notes[bot]"
 <287676111+llm-d-router-release-notes[bot]@users.noreply.github.com>
Date: Thu, 23 Jul 2026 16:53:40 +0000
Subject: [PATCH] docs: add release-note fragment for PR #2123

Signed-off-by: llm-d-router-release-notes[bot] <287676111+llm-d-router-release-notes[bot]@users.noreply.github.com>
---
 release-notes.d/unreleased/2123.md | 7 +++++++
 1 file changed, 7 insertions(+)
 create mode 100644 release-notes.d/unreleased/2123.md

diff --git a/release-notes.d/unreleased/2123.md b/release-notes.d/unreleased/2123.md
new file mode 100644
index 0000000000..990f671067
--- /dev/null
+++ b/release-notes.d/unreleased/2123.md
@@ -0,0 +1,7 @@
+---
+pr: 2123
+url: https://github.com/llm-d/llm-d-router/pull/2123
+author: LukeAVanDrie
+date: 2026-07-23
+---
+Flow control queueing is now bounded by default: `defaultRequestTTL` defaults to 60s and per-band `maxRequests` defaults to 5000 when unset. For existing flow control users this is a behavior change: an explicit `defaultRequestTTL: "0s"` disables the TTL (requests then wait until client disconnect), and a band `maxRequests`/`maxBytes` of 0 is treated as unset and receives the default. To approximate the legacy fast-fail behavior for sheddable traffic, configure a small `defaultNegativePriorityBand.maxRequests`. Scale-to-zero deployments should raise `defaultRequestTTL` above the expected cold-start time.