common : re-arm reasoning budget after DONE on new <think> (#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 <think> 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).
This commit is contained in:
@@ -122,6 +122,20 @@ static void common_reasoning_budget_accept(struct llama_sampler * smpl, llama_to
|
||||
}
|
||||
break;
|
||||
case REASONING_BUDGET_DONE:
|
||||
// Re-arm on a new start tag: some models emit multiple <think> blocks
|
||||
// per response, and each should get a fresh budget window.
|
||||
if (ctx->start_matcher.advance(token)) {
|
||||
ctx->state = REASONING_BUDGET_COUNTING;
|
||||
ctx->remaining = ctx->budget;
|
||||
ctx->end_matcher.reset();
|
||||
LOG_INF("reasoning-budget: re-activated on new start tag, budget=%d tokens\n", ctx->budget);
|
||||
|
||||
if (ctx->remaining <= 0) {
|
||||
ctx->state = REASONING_BUDGET_FORCING;
|
||||
ctx->force_pos = 0;
|
||||
LOG_INF("reasoning-budget: budget=0, forcing immediately\n");
|
||||
}
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user