0.5.75: thoughts, quests, api models, bugfixes
Added 2025-10-24 17:14:16 +0000 UTC✨ character thoughts in a separate animated block (feels more alive and aesthetic to me)
✨ quest/task system
✨ 3 settings moved to experimental and now available starting from the base tier
✨ windows, linux, mac: added live lists of all available api models for gemini, openrouter, openai, anthropic, grok, cohere, groq; the “recommended models” toggle has been retired
✨ all characters are less rambling by default, but will be verbose if asked or when the situation calls for it
✨ added items to the gallery
🛠 fixed a bug in the dialog history where the narrator’s text got “split” in streaming mode
🛠 improved censorship bypass for api models when forming the prompt for local image generation
🛠 fixed a bug with english language for quick replies
🛠 redesign of the “erase” part of a character’s context: added color markers, new phrasing, and an explanation in the help section
🛠 fixed a claude issue when two characters are on screen with streaming enabled
🛠 fixed the story intro animation for character reveals (bottom-up)
🛠 default number of messages in history increased to 18
🛠 tamagotchi memory message counts reduced from (45, 90, 135, 180, 225, 270) to (27, 45, 90, 135); 45 is recommended — higher values will be too expensive for api models, and locals won’t handle them
🛠 increased scrollbar thumb width in locations and the journal
🛠 optimized gallery images/videos and character pictures
🛠 koboldcpp updated to 1.100.1
🛠 fixed the nvidia/amd toggle display on entering the game
the resources archive with heavy models (for windows, linux, mac) changes less often than the build, so you don’t need to download the full win-local version every time — the regular one is enough. hopefully this reduces download issues and simplifies setup for linux and mac
if resources change, i’ll note it in the release post. in this update, models didn’t change; if u already had the previous (win-local) version, just download win
to activate quests, enable them in settings (experimental features next to “password”) and sleep until morning. tasks/quests are issued in packs of 3; until you complete them all, you won’t get new ones for that character. rewards for completed tasks appear in the journal. the bot is aware of completed tasks and may continue a chain if it finds something interesting. tasks/quests are available from the base tier and up
p.s. the next update will be partly about optimization — uploading big builds with bad internet is pain. after cleanup and possibly heavier model quantization, the full build should shrink
Comments
Thanks for updates. Some problem with dowloading local windows version 20gb.
Danieli privat
2025-10-29 19:29:46 +0000 UTCthanks, yeah, the location detection needs some improvement - I’ll think about how to handle it better. could u pls tell me which text model u’re using?
Stvoler
2025-10-25 08:21:38 +0000 UTCI have a problem with the automatic room change in the new version. After every sentence I write, the room changes even if I'm still in the same room. For example, I'm standing at the kiosk drinking a coffee. A kiosk is loaded in the local model. Then the ladies ask me if I want to drink a coffee. Suddenly, it loads the living room. I say no, I'm fine here at the kiosk. The local model reloads the kiosk. No sooner has the new image with a kiosk been generated than the room changes again and the bathroom is loaded. Is there an option to turn off this automatic change? Since I have an AMD graphics card, it sometimes takes up to 10 minutes for everything to load, which is very frustrating. In the last version, the problem wasn't as frequent; it only happened once every 5 generated images. Otherwise, everything works as usual. Thank you in advance for your help.
Dark
2025-10-24 20:26:27 +0000 UTC
