From 8aa9c0f5345bea66fd8d89bec8cc82ea49ea446a Mon Sep 17 00:00:00 2001
From: Debanjum <debanjum@gmail.com>
Date: Fri, 22 Aug 2025 18:57:38 -0700
Subject: [PATCH] Reduce max reasoning tokens for gemini models

A high reasoning tokens does not seem to help for standard Khoj use
cases. And hopefully reducing it may avoid repetition loops by model.
---
 src/khoj/processor/conversation/google/utils.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/khoj/processor/conversation/google/utils.py b/src/khoj/processor/conversation/google/utils.py
index 3a64434c..b6d965e4 100644
--- a/src/khoj/processor/conversation/google/utils.py
+++ b/src/khoj/processor/conversation/google/utils.py
@@ -46,7 +46,7 @@ gemini_clients: Dict[str, genai.Client] = {}
 # This avoids premature response termination.
 MAX_OUTPUT_TOKENS_FOR_REASONING_GEMINI = 20000
 MAX_OUTPUT_TOKENS_FOR_STANDARD_GEMINI = 8000
-MAX_REASONING_TOKENS_GEMINI = 10000
+MAX_REASONING_TOKENS_GEMINI = 512
 
 SAFETY_SETTINGS = [
     gtypes.SafetySetting(