Feature suggestions

Some long conversations have a lot of redundant information, and exporting them all is unnecessary and not easy to find the necessary information. If users filter and search in Notepad, they don't have the excellent rendering function of chatbox

When there is no timestamp in the exported chat log file and AI is required to organize the conversation, it is impossible to make an effective time judgment and give an effective report

Manually set the model, instructions, etc. used to generate chat titles

If you want to know the balance status of the account by calling Silicon-based Flow, I hope there is a separate conversation where you can check the account status specifically. To list silicon-based flows, call methods related to querying account information are as follows: curl --request GET\ --url https://api.siliconflow.cn/v1/user/info\ --header 'Authorization: Bearer {token} '

I love chatbox but one thing that keeps happening is that I'm loosing long prompts in the middle of writing them (either a shortcut that switch chat, or me wanting to check another thread). For me as soon as one write into a text field (even for an non created chat) it should create a temp thread and store the text live to avoid these issues

I've noticed that Chatbox surprisingly lacks a quick access tool for custom prompts similar to what Monica or Chatwise offers, which is a significant inconvenience. I hope you can take inspiration from Monica by implementing a feature that allows users to quickly access custom prompts through buttons in the chat interface or via keyboard shortcuts, with support for corresponding customization options.

The display area of the text input box is too small. It is very inconvenient to read when entering long texts. You need to scroll up and down. Can you change it to an adjustable format

For conversations under specific prompts set by oneself, there are usually multiple different topics. The software automatically names them by default, so finding previous ideas can be very troublesome

Currently, most large models can set the output max_tokens, so that the maximum amount of content output by the large model is controlled by the user. I'd like this feature to be added to the advanced settings, at the same level as contextual message limits, rigor and imagination (temperature).

Add an option to automatically roll down the entire process to the streaming generation, instead of necessarily stopping the scroll when it hits the top