From 62a71361a98d87b2b35a45d0f5ab7627eeea0916 Mon Sep 17 00:00:00 2001
From: Luke <92253590+ImLukeF@users.noreply.github.com>
Date: Thu, 12 Mar 2026 19:26:53 +1100
Subject: [PATCH] Docs: clarify llm-task thinking presets

---
 docs/tools/llm-task.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/docs/tools/llm-task.md b/docs/tools/llm-task.md
index 16de8230f..2626d3237 100644
--- a/docs/tools/llm-task.md
+++ b/docs/tools/llm-task.md
@@ -81,6 +81,8 @@ outside the list is rejected.
 - `maxTokens` (number, optional)
 - `timeoutMs` (number, optional)
 
+`thinking` accepts the standard OpenClaw reasoning presets, such as `low` or `medium`.
+
 ## Output
 
 Returns `details.json` containing the parsed JSON (and validates against