Feedback

Seems like the request format is different for these

When changing to Anthropic models, always cut by 1024 token output if not explicitly set 4096. This behaviour is annoying because I have to regenerate with max token output available (4096), this makes inferencing not efficient. Seems for Anthropic model, you should make it 4096 by default, except user set lower. Many of my process has long input tokens, so when the output is only 1024 by default I lost money on my first process. This is specific to Antropic.

Hey, I've installed this newest release. I applied a prompt by using Cmd+L, but there's nothing showing on input box.

When we add context to certain amount, some endpoint not carrying user prompts. Perplexity is one of it. This happened when I set context to 5 last messages. Is it really you're not including previous user/assistant chats? Please fix this.

Is this a bug? I can't set topK nor topP

Thank's for this features to directly follow last output and autoscroll, but it's not working when the texts is beyond window height. It only showing maximum to a window, not to last message streaming.

New 1.9.13 version has a bug in inertia scrolling using trackpad. If the mouse pointer is right on assistant's chat bubble and I throw scrolling from there, it will stuck and inertia scrolling is not rolling. But if I throw it on user's input bubble or anywhere outside of both bubbles, it scroll normally.

Can you please update the model list to include the two new models. Perhaps use the openAI compatability to auto update the model list

When I scroll in a chat it's quite laggy, especially with syntax highlight. Great app though, I just bought a licence