One thing that occurred to me here is that perhaps you could shape the balloon like an airfoil to help increase the lift in the right kind of crosswind. Then you'd have to figure out if the increase in thermal losses were sufficiently small.
>I sort of handwaved the drag away by claiming this really only makes sense at low velocities.
But... how low "low" is still matters!
Quantity makes a difference, even post-handwaving. If that extra drag makes you go from (say) 20% weather availability down to 10% availability, that's a significant incremental operating cost.
It's not like "the wind problem can't get any worse!" if we mention it beforehand. It can (and would) get quantitatively worse with a larger balloon, and that has a non-trivial cost.
>shape the balloon like [a low-drag body]
Actual spheres are surprisingly draggy!
However, my sense is that the real dealbreaker is that it’s impossible to find a suitably insulating material. A sphere with r=30m is already over a hectare of surface area.