From e90bf0216d6449edfdc14295407826441d9e46f7 Mon Sep 17 00:00:00 2001 From: Abiba Date: Tue, 19 May 2026 20:10:07 +0000 Subject: [PATCH] =?UTF-8?q?fix:=20raise=20heavy=20threshold=20=E2=80=94=20?= =?UTF-8?q?4000=E2=86=9212000=20tokens,=208=E2=86=9215=20turns?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- router/router.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/router/router.py b/router/router.py index e600365..da4a36d 100644 --- a/router/router.py +++ b/router/router.py @@ -181,8 +181,8 @@ def route(rd, tier): if "qwen3.6-27B-code" in avail and not is_gpu_busy("qwen3.6-27B-code"): return {"model":"qwen3.6-27B-code","reason":"simple_conv_fallback"} - # TIER 3: Heavy reasoning — large context or very long conversations - if t > 4000 or turns > 8: + # TIER 3: Heavy reasoning — very large context or very long conversations + if t > 12000 or turns > 15: candidates = [m for m in ["qwen3.6-27B-code","qwen3.6-35B-A3B","qwen3.5-9b-vlm"] if m in avail] result = select_best_gpu(candidates, "heavy_reasoning") if result: return result