Combined wiki extraction can require well over 8k completion tokens. When MaxTokens is unset, OpenAI-compatible clients omit max_tokens and providers such as DeepSeek default to 8192, truncating mid-JSON and failing postprocess.wiki.extract with unexpected end of JSON input. Set a 32768 completion budget for all generateWithTemplate calls so large extracts can finish while short replies still stop early. Fixes #2604 |
||
|---|---|---|
| .. | ||
| repository | ||
| service | ||