You're welcome! I'm really looking forward to seeing where this app goes. I'm an advanced local LLM user, so I'm familiar with the tech, I can actually turn off reasoning in my Gemma 4 Jinja templates without any problem. I only wanted to use reasoning to boost the logic for some massive structured prompts I run, so I was curious if there's a trick to fix the incompatibility with Gemma 4 that I might not know about. Anyway, I'll just stick with Qwen for now since it works great with your app, even though I prefer Gemma 4's more natural sounding response style. Keep up the good work. I'm sharing this app with my friends and hopefully they'll like it and support you guys too.
Viewing post in Desktop Companion - Your AI Desktop Pal comments
Oh I see — so I have a strip for <thinking> tags in the LM Studio connector, but it only works when both the opening and closing thinking tags are in the complete response, even though it's plugged in streaming mode. You can try increasing the response length to the max (600) in the AI tab so the full response includes both opening and closing thinking tags. Also, I'm a solo dev working on this — thanks again for the support!
Yeah, I figured you were a solo dev, which is why I was just reporting the issue rather than expecting an immediate solution. Feel free to look into it at your own pace, I just wanted to let you know about it. I have a feeling Gemma 4 will be quite popular with people interested in using your companion app. You've done an excellent job so far, I'm very impressed. P.S. Gemma 4 reasoning parsing happens inside (Start String: <|channel>thought End String: <channel|>) No idea if it helps or not, I just figured I mention it here.