From fe6826a3be9691917c9b51eb5f763d2e5ad03822 Mon Sep 17 00:00:00 2001
From: Richard Loyer <richard.loyer@c42.lu>
Date: Mon, 25 May 2026 09:38:25 +0200
Subject: [PATCH] Integration #277: hang=thinking non bride, fix budget0+cap;
 4B>9B CPU

---
 CLAUDE.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/CLAUDE.md b/CLAUDE.md
index 06b3974..a847f51 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -105,3 +105,6 @@ Talker=qwen3 GGUF chargeable engine (poids OK). Decoder RTF0.96 chraac valide hi
 
 ## GDN chunkwise verdict
 Chunkwise batchable, 55->100 credible MAIS HMX accumulateur FP16 -> bit-exact impossible. Voie=HVX qf32 3-5sem frontiere. Prefill GDN-HTP encore not-bit-correct (2287 default OFF), decode CPU bit-exact. Reco: rester 55/15, gain pas worth (4s masques). Optim sure=release Thinker+KV f16.
+
+## #277 integration: cause hang = thinking non bride
+Dev report: 4B/9B 6-13min/tour, jamais done. CAUSE: EngineLlmEngine generate() sans reasoning_budget0 -> thinking infini (pas decode lent: 4B CPU=15tok/s ok). FIX bridge: enable_thinking=false + maxTok 64. 9B trop lent CPU (8.4)->4B speaker. .pte garde en attendant. #277=2 fixes Kotlin/JNI pas kernel. RAM 4.5 vs 3 mmap accepte.