Matt e01d741f01 Fix GPT-5 nano empty response issue with token limits
GPT-5 nano (and other GPT-5 models) use reasoning that consumes
the output token budget. When max_tokens is too low, all tokens
get used by internal reasoning, leaving nothing for the response.

- Add needsHigherTokenLimit() to detect models needing more tokens
- Add getMinTokenLimit() to ensure minimum 16k tokens for GPT-5
- Update buildCompletionParams to apply minimum token limits
- This fixes the No response from AI error with gpt-5-nano

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-05 15:02:22 +01:00
Description
No description provided
22 MiB
Languages
TypeScript 99.4%
JavaScript 0.2%
CSS 0.2%
Shell 0.2%