But this is specifically about streamed games. Locally rendered games (as with WebGL) can render the scene immediately in response to the player's input, so they don't have this problem. The lag is still there, but you only have to deal with the physics side of it, rather than dealing with the physics *and* the audio and video.
The scenario you describe doesn't make any sense because the idea is that you choose the frame (or scene) based on the inputs on the local machine. So if you're rendering it anyway then you may as well just have the local client respond itself to the inputs and do away with the overhead.