I noticed it recently too, but disconnecting my Bluetooth headset first allowed it to suspend properly (it seems like the wifi chip kept it awake before making like a yo-yo back and forth).
Me 3 and it's maddening. I've posted this [1] on the Arch Linux forums but haven't found a fix. I've seen it mentioned around the web that it's a known bug, but I have yet to find a bug report
It's an open question whether Bluetooth should prevent sleep, or let sleep go through.
On a well done "modern suspend/suspend to idle", I use disconnected modern sleep + Windows Media Player on Windows 11 to listen to songs on my bluetooth headphones for a cost of about 1% of the battery per hour (as measured and plotted with powercfg) which can come down to about half of it, 0.5%/h when not using Bluetooth.
I wouldn't want Bluetooth to prevent sleep (a 1% drop per hour is better than not sleeping!)
I also wouldn't want sleep to prevent me from using my Bluetooth headset (the difference between 0.5% and 1% is significant, but it doesn't matter much in practice if my computer can be usable in the morning)
This is one of the rare examples of "modern suspend" delivering on its promises, and blowing the good old ACPI S3 away: I never saw a drop of battery <5% on S3 suspend-to-ram unless it also involved S4 in a hybrid sleep of "ACPI S3 suspend-to-ram then S4 suspend-to-disk after a while or when I run out of power whichever comes first"!
Be that as it may, acting like a yo-yo is certainly the wrong direction on a "desired behavior" scale. Especially when the headset itself is announcing the up and down events in synthesized speech interrupting what else is going on.
