Dave
6c41f4c662
MiniMax M2.x reasons inside <think> tags in the normal content field, and that reasoning is billed against max_tokens. At 4096 the heavier batches spent the entire budget thinking, were truncated before writing a single answer, and stripThinking correctly removed the unclosed block — leaving an empty response. The signature was distinctive: batches returned 25/25 or 0/25, never anything partial. 193 of 779 commits went unsummarised with no error anywhere. At 16384 the same 193 completed 8/8 batches with zero failures. The interview's question call had the same bug at 1024, where it would have returned an empty question and silently ended the interview on the first turn. Now 8192. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| brief.test.ts | ||
| brief.ts | ||
| interview.ts | ||
| prompt.test.ts | ||
| prompt.ts | ||
| size.test.ts | ||
| size.ts | ||
| turn.test.ts | ||
| turn.ts | ||