🚀 New
  • Added feature that allows users to add a custom model for OpenRouter or a fine-tuned model based on gpt-3.5-turbo.
  • Added a toggle button in the toolbar to switch between markdown mode and text mode.
  • Added a button to switch between markdown mode and text mode for each message by hovering on the message.
✨ Improved
  • Improved error handling by displaying clear error messages with detailed information when adding new API endpoints or new models fails.
  • Sorted items in the output preferences picker in ascending order.
🔧 Fixed
  • Fixed an issue where the response sometimes contained weird text chunks when the temperature was set near "More Creative".
  • Fixed an issue where the prompt list would show slowly when typing "/p" in inline mode.