From cfcfd655e7ae92103229d23b48f5ff3f49120164 Mon Sep 17 00:00:00 2001 From: Celes Renata Date: Wed, 29 Apr 2026 06:18:26 +0000 Subject: [PATCH] fix: reduce max_tokens to 2048 to fit 8192 context window --- infra/migrations/031_fix_agent_defaults.sql | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/infra/migrations/031_fix_agent_defaults.sql b/infra/migrations/031_fix_agent_defaults.sql index ca84312..ca8c554 100644 --- a/infra/migrations/031_fix_agent_defaults.sql +++ b/infra/migrations/031_fix_agent_defaults.sql @@ -6,7 +6,7 @@ UPDATE ai_agents SET model_provider = 'vllm', model_name = 'AxionML/Qwen3.5-9B-NVFP4', - max_tokens = 4096, + max_tokens = 2048, updated_at = NOW() WHERE slug IN ('document-extractor', 'event-classifier', 'thesis-rewriter') AND source = 'system'