I've been thinking about this for the last couple of days, and I just don't see how you could do it without (as Uncle GroOve suggests) either overdubbing or finding some way to spawn a new mononote sequencer. Since Jim immediately seemed to think it was possible to implement this, I assume we're both thinking of it the wrong way.
Sounds like everyone's busy, but I'd be willing to take a crack at it if someone can give me a hint!