Summary
Patch update addressing OpenAI GPT 5.x compatibility and increasing token output limits for all providers.
What's New
- Replaced deprecated
max_tokensparameter withmax_completion_tokensrequired by GPT 5.x models. - Increased max output tokens for OpenAI (GPT 5.2) and Claude (Sonnet 4.5) to 65,536.
- Increased max output tokens for Groq (Llama 3.3 70B) to 32,768.
Improvements
- Improved response length capabilities across all text-generation AI models.
- Updated connection test model to use
gpt-5.2-chat-latestinstead of the deprecatedgpt-3.5-turbo.
Fixes
- Fixed 400 error when using OpenAI GPT 5.x models for text queries and toggle actions.
Technical
- Replaced
max_tokenswithmax_completion_tokensinLLMHelper.tsandipcHandlers.ts.
⚠️macOS Installation (Unsigned Build)
Download the correct architecture .zip or .dmg file for your device (Apple Silicon or Intel).
If you see "App is damaged":
-
For .zip downloads:
- Move the app to your Applications folder.
- Open Terminal and run:
xattr -cr /Applications/Natively.app
-
For .dmg downloads:
- Open Terminal and run:
xattr -cr ~/Downloads/Natively-1.1.8-arm64.dmg - Install the natively.dmg
- Open Terminal and run:
xattr -cr /Applications/Natively.app
- Open Terminal and run: