As refdb and odb backends can be allocated by client code, libgit2
can’t know whether an alternative memory allocator was used, and thus
should not try to call `git__free` on those objects.

Instead, odb and refdb backend implementations must always provide
their own `free` functions to ensure memory gets freed correctly.

Restricting files to size_t is a silly limitation. The loose backend
writes to a file directly, so there is no issue in using 63 bits for the
size.

We still assume that the header is going to fit in 64 bytes, which does
mean quite a bit smaller files due to the run-length encoding, but it's
still a much larger size than you would want Git to handle.

There were a couple of "init_opts()" functions a few more cases
of structure initialization that I somehow missed.

The basic structure of each function is courtesy of arrbee.

When given an ODB from which to read objects, the indexer will attempt
to inject the missing bases at the end of the pack and update the
header and trailer to reflect the new contents.

Previously, `git_object_read()`, `git_object_read_prefix()` and
`git_object_exists()` were implementing an auto refresh logic. When the
expected object couldn't be found in any backend, a call to
`git_odb_refresh()` was triggered and the lookup was once again performed
against all backends.

This commit removes this auto-refresh logic from the odb layer and pushes
it down into the pack-backend (as it's the only one currently exposing
a `refresh()` endpoint).

Clarify the role of each function and in particular mention that there
is no need for the backend or stream to worry about the object's id,
as it will be given when `finalize_write` is called.