From 6f4f864d28aee4909ff1885557bb87382294628f Mon Sep 17 00:00:00 2001
From: rob thijssen <grenade@rob.tn>
Date: Mon, 9 Mar 2026 18:17:48 +0200
Subject: [PATCH] fix: increase max_tokens to 8192 for R1 reasoning overhead
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

R1 models use 500-2000 tokens for <think> blocks before the final
response. 4096 was too tight — the model would exhaust the budget
mid-thought and never emit the JSON.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 src/claude.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/claude.rs b/src/claude.rs
index 370ca8e..37381cc 100644
--- a/src/claude.rs
+++ b/src/claude.rs
@@ -63,7 +63,7 @@ impl ClaudeClient {
     ) -> Result<(String, Option<Usage>)> {
         let body = MessagesRequest {
             model: self.model.clone(),
-            max_tokens: 4096,
+            max_tokens: 8192,
             system: system.to_string(),
             messages: messages.to_vec(),
         };