Traditional MCTS analyzes each line all the way to endgame.
I believe neural-net based MCTS (ex: AlphaZero and similar) use the neural-net to determine how deep any line should go. (Ex: which moves are worth exploring? Well, might as well have that itself part of the training / inference neural net).
In my understanding, in KataGo, the decision of how long to follow a line is made solely by MCTS via its exploration/exploitation components. These in turn are influence by the policy/value outputs of the DCNN. So in practical terms, your statement might just be called true.
The raw net output includes some values that could be used in addition, but they are not used. I don't know if they were ever looked at closely for this purpose.
I believe neural-net based MCTS (ex: AlphaZero and similar) use the neural-net to determine how deep any line should go. (Ex: which moves are worth exploring? Well, might as well have that itself part of the training / inference neural net).