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!
Viewing post in Desktop Companion - Your AI Desktop Pal comments
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.