From a9af55e1785eff09725217d15de205cd6cef86d4 Mon Sep 17 00:00:00 2001
From: Ruslan Strazhnyk <strazhnyk@gmail.com>
Date: Sat, 5 Sep 2026 11:36:27 +0200
Subject: [PATCH] release: v1.32.0

---
 CHANGELOG.md | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 98426d5..9c7fb7d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,17 @@ All notable changes to qmax-code. Versions follow [Semantic Versioning](https://
 
 ## [Unreleased]
 
+## [1.32.0] - 2026-09-05
+
+### Added
+- `/orch` lists every supported Codex model — GPT 6 Astra, GPT 5.6 Sol,
+  Terra, and Luna, GPT 5.5, GPT 5.4, GPT 5.4 Mini, and GPT 5.3 Codex Spark —
+  alongside Codex default. A picker sync test keeps the list aligned with the
+  Codex runner allowlist in both directions.
+- Coming-soon Qwen 3.8 row in the `/orch` Cerebras section with `qwen-3.8`
+  model ID and `qwen` / `qwen3.8` config aliases. The ID follows Cerebras
+  naming conventions and must be confirmed against the live API at launch.
+
 ## [1.31.0] - 2026-09-05
 
 ### Added