I wouldn't bet my income on my 97-year-old grandmother for surviving as long as I promised my clients their website would stay online.
That said, I don't think Heroku is that close to being sunset, but that's my guess, and that guess is as good as the people who say it is. I'm currently messing around with fly.io and that product is so young one would be crazy to think it has better chances to last the next decade than Heroku does.
I don't think Salesforce is probably planning on sunseting Heroku anytime soon.
But they seem to be totally starving it, allocating it the minimum of resources they think they can to keep it going pretty much as it is without any new features.
Based on how they handled the recent security update, I won't be surprised if it... just kind of crumbles into the sea at some point.
We all know that software doesn't just "keep working" at all without continual maintenance. For several different reasons, security being one of them. Heroku's ability to keep "just working" with the languages/platforms it does, as new versions of such come out, seems to be dependent on an increasingly smaller workforce that goes above and beyond.
That said, I don't think Heroku is that close to being sunset, but that's my guess, and that guess is as good as the people who say it is. I'm currently messing around with fly.io and that product is so young one would be crazy to think it has better chances to last the next decade than Heroku does.