Fix OpenRouter DeepSeek V4 xhigh reasoning

closes #4801
This commit is contained in:
Mario Zechner
2026-05-28 23:56:59 +02:00
parent f9fa077bbb
commit 0127caea7b
3 changed files with 13 additions and 9 deletions

View File

@@ -9,6 +9,7 @@
### Fixed
- Fixed OpenRouter DeepSeek V4 `xhigh` reasoning metadata to preserve OpenRouter's native effort instead of sending DeepSeek's `max` effort ([#4801](https://github.com/earendil-works/pi/issues/4801)).
- Fixed OpenAI Codex Responses replay after switching from Anthropic extended-thinking sessions by generating unique fallback message item IDs for converted thinking/text blocks ([#5148](https://github.com/earendil-works/pi/issues/5148)).
- Fixed Anthropic-compatible replay for providers that return empty thinking signatures by adding an opt-in `allowEmptySignature` compatibility flag ([#4464](https://github.com/earendil-works/pi/issues/4464)).
- Fixed OpenAI and OpenRouter GPT-5.5 Pro thinking level metadata to expose only supported medium, high, and xhigh efforts.