This adds --max-depth to the "refs" commands and allows limiting
the fetching of refs per depth. Other than that, it works as before.

Note that clever branch pruning is only made when the --unique flag
is passed. Otherwise, we re-explore branches to the given depth.

This means that --unique costs memory, but may save time when
the DAGs contain the same sub-DAGs in several places (specially if
they are big). On the other side, not using --unique saves
memory but may involve re-exploring large sub-DAGs.

License: MIT
Signed-off-by: Hector Sanjuan <hector@protocol.ai>