From 28092194fe31bebf305cf7c62e9736a34d2552f9 Mon Sep 17 00:00:00 2001 From: Don Garrett Date: Wed, 7 Oct 2026 22:49:13 +0000 Subject: [PATCH] E2E on qwen3.8-27b without thinking The e2e roles move to qwen3.8-27b-nothink, a LiteLLM alias for the same model with chat_template_kwargs enable_thinking false. With thinking, a growing share of answers ran to 2-8k tokens (two hit the 8192 cap), which took one test from 3.5 to 20 minutes. Co-Authored-By: Claude Opus 5.5 (1M context) Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE --- tests/integration/e2e_support.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tests/integration/e2e_support.py b/tests/integration/e2e_support.py index 3a51403..e63950f 100644 --- a/tests/integration/e2e_support.py +++ b/tests/integration/e2e_support.py @@ -15,8 +15,10 @@ from nisse_dev.llm import RoleMap # The end-to-end tests run every role on a local model, which costs nothing # per call; NISSE_E2E_MODEL overrides it (e.g. claude-haiku-4-5 for a quick, -# paid run). -E2E_MODEL = "qwen3.8-27b" +# paid run). The no-thinking alias (LiteLLM: chat_template_kwargs +# enable_thinking false): with thinking, some answers ran to 6-8k tokens, +# minutes each, and stretched a test from 3.5 to 20 minutes. +E2E_MODEL = "qwen3.8-27b-nothink" def e2e_roles() -> RoleMap: