In legacy (pre-merge) sync mode, headers were contiguously downloaded from the network and when no more headers were available, we checked every few seconds whether there are 64 new blocks to move the pivot.

In beacon (post-merge) sync mode, we don't need to check for new skeleton headers non stop, since those re delivered one by one by the engine API. The missing code snippet from the header fetcher was to actually look at the latest head and move the pivot if it was more than 2*64-8 away. This PR adds the missing movement logic.