Abiba 3cbf38e3e2 fix: raise heavy threshold — 4000→12000 tokens, 8→15 turns ...

Agent conversations with system prompts easily exceed 4000 tokens,
forcing everything to Dense. Now only truly heavy work triggers Dense.
Most agent convos will route to MoE (default) instead.

2026-05-19 20:09:59 +00:00

..

Dockerfile

Initial commit: CT 116 inference harness — nginx, LiteLLM, router, dashboard, Redis

2026-05-16 18:51:50 +00:00

requirements.txt

Initial commit: CT 116 inference harness — nginx, LiteLLM, router, dashboard, Redis

2026-05-16 18:51:50 +00:00

router.py

fix: raise heavy threshold — 4000→12000 tokens, 8→15 turns

2026-05-19 20:09:59 +00:00