@@ -8,6 +8,7 @@
|
||||
|
||||
### Fixed
|
||||
|
||||
- Updated `@anthropic-ai/sdk` to `^0.91.1` to clear GHSA-p7fg-763f-g4gf audit findings ([#3992](https://github.com/badlogic/pi-mono/issues/3992)).
|
||||
- Fixed DeepSeek V4 Flash `xhigh` thinking support so requests preserve `xhigh` and map it to DeepSeek's `max` reasoning effort ([#3944](https://github.com/badlogic/pi-mono/issues/3944)).
|
||||
- Fixed Anthropic streams that end before `message_stop` to be treated as errors instead of successful partial responses ([#3936](https://github.com/badlogic/pi-mono/issues/3936)).
|
||||
- Fixed generated OpenAI-compatible DeepSeek V4 models to carry the provider-specific reasoning effort mapping outside the direct DeepSeek provider ([#3940](https://github.com/badlogic/pi-mono/issues/3940)).
|
||||
|
||||
Reference in New Issue
Block a user