Can someone explain to me why neither OpenAI or Google have implemented this yet for their consumer facing products? At the very least in their Pro and Ultra plans (respectively) to start. A counter would be nice as well (like the one in Google AI studio).

"Instead of returning errors when conversations get too long, Claude Sonnet 4.5 will now generate responses up to the available limit and clearly indicate why it stopped. This eliminates frustrating interruptions and allows users to maximize their available context window".

Thanks! Big Prof G. fan. Somehow I missed this in my feed today. I'll give it a listen on my run today.

Facts.