Introduce a dedicated Gemini API mode with thinking process display and accurate token usage reporting.
QQEat
While OpenAI-compatible mode is useful, a dedicated Gemini API mode would greatly enhance the experience for users leveraging Gemini models.
Firstly, for models like 'gemini-2.5-pro', it's crucial to display the "thinking process" or intermediate steps (e.g., tool calls, function executions, or complex reasoning steps). Currently, this is not visible, which limits understanding of how the model arrived at its response, especially in multi-turn or complex interactions. Showing these steps would provide valuable insights and improve transparency.
Secondly, the Gemini API response body typically includes precise token usage data. When using the Gemini API, it's highly requested that the app utilize these returned values for displaying message token consumption. The app's current internal calculation of token usage can be inaccurate, especially after conversation edits or due to other factors. Using the exact token counts from the API response would ensure accuracy and help users better track their usage and costs.
xianz
Why not just use the built-in Gemini provider? You can set your own API host
QQEat
xianz Because I might use multiple services, which would require me to constantly switch the API host and key.