From 9ab038f5737faf8f36d7564f28ba789aa11fdd52 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=9B=B7=E7=94=B5=E8=8A=BD=E8=A1=A3?=
 <zhangyanghaha0407@outlook.com>
Date: Mon, 21 Sep 2026 18:39:46 -0400
Subject: [PATCH] docs(agents): rewrap the reasoning-effort paragraph

---
 AGENTS.md | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/AGENTS.md b/AGENTS.md
index 20113f6..b000d94 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -533,8 +533,9 @@ client-side, no backend surface.
   never invents model availability. Canonical reasoning efforts:
   none/minimal/low/medium/high/xhigh/max (`max` split from `xhigh` 2026-07;
   the Codex backend advertises an `ultra` tier above `max` that kigi has no
-  level for; Kimi wire spells its top tier `max`, kimi_compat renames). config.toml accepts any
-  letter case: `ReasoningEffort` deserializes through `FromStr`.
+  level for; Kimi wire spells its top tier `max`, kimi_compat renames).
+  config.toml accepts any letter case: `ReasoningEffort` deserializes
+  through `FromStr`.
 
 ## Milestones (PRD §8.3)