After enabling E2EE for the first time, keep the media transform
inplace, but make it a no-op.

This simplifies the flow a little since it doesn't require a media
session restart.

Way back when, there were performance concerns when having a transform,
which is what prompted us to implement the restar mechanism, but a lot
has changed since and both audio and video frames don't need to jump
threads these days. We are still not enabling an empty transform at all
times out of precaution.

it removed support for functions being simultaneous async and have done parameter in callback

Drop end to end signature. The impersonation attack vector is deemed out of
scope since insiders are already part of the meeting.

Signs and verifies frames. For now this is done on every frame.
This is not the long-term goal and there needs to be a better strategy.

and make them a bit more concise. No functional changes

Both for just encode function as well as an end-to-end test.