0.3.49: threesome, grok, bugfix

✨ a feature with two characters on the screen added to the sandbox *
✨ support for the grok-beta model (the one from E Musk) **
✨ a button for forcibly returning Dina to the screen
🛠 a critical bug with custom contexts for the female hero fixed, now everything works including dnd mode
🛠 maximum temperature reduced to 1.8
🛠 gemini-1.0-pro and gpt-3.5-turbo-1106 models removed
🛠 dark theme fixed
🛠 apk: less screen dimming while typing
🛠 gemini: optimized the work of bots responsible for changing locations and saving history; the location-bot now works correctly, always creates a new empty session and only looks at the last 2 messages, not the entire history; the history-saving bot no longer has redundant duplicated text. especially relevant for long gaming sessions
🛠 in the prologue dream, the embarrassing (poor-quality) videos with dina and lora have been removed, replaced with images
🛠 music files re-encoded into ogg (same quality but half the size)
🛠 all webm videos slightly compressed without visible quality loss
🗝️ person and base passwords changed

💘 download game 

*invocation in the top-left corner, can be called by text as well, but the menu is more reliable. it works like this: if two characters are on the screen, a hidden bot decides before each response who should speak, switching from one character to the other along with all their custom contexts

** grok - interesting, has a free $25 trial, seems not to censor at all; be cautious with temperature, above 1 it starts hallucinating; gets buggy, repeats phrases in prolonged conversations

the main problem with multiple characters is that almost all language models only have a marker with two options - either the user or the assistant/model. that is, there is no separate field to indicate a character, so we have to ask them to add "(Name):" to differentiate speech. haven't tested with local models, but it should be fine

have a nice weekend )