[FIX] VLLM reasoning with mm: is a part of context

#6
by voves - opened

Minimax have custom mm: block of reasoning, so i fixed block to exclude it only {{- think_end_token }} is emitted the actual reasoning content is stripped from the prompt sent to the model.

Why: Multi-turn conversations with full reasoning rendered each turn caused context window bloat. Now the model gets a signal (think_end_token) that thinking occurred, but the reasoning text itself is omitted from history to save tokens/context space.

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment