ggml-org/llama.cpp b8964

on GitHub

common : re-arm reasoning budget after DONE on new (#22323)

DONE state absorbs all tokens including a new start tag, causing any think blocks after the first to run unbudgeted. Observed on unsloth/Qwen3.6-27B-GGUF which interleaves multiple blocks per response.

Fixed by advancing start_matcher in DONE branch and re-arming to COUNTING with a fresh budget on match. Adds regression test (test-reasoning-budget: test 6).