The previous implementation resolved condition at Join compilation time
which required introducing a specialized expression resolving mode to
alter the join reuse logic solely during that phase.
FilteredRelation.condition is now resolved when the relation is first
referenced which maintains the existing behavior while allowing the
removal of the specialized resolving mode and address an issue where
conditions couldn't spawn new joins.
Changed __eq__ to return NotImplemented instead of False if compared to
an object of the same type, as is recommended by the Python data model
reference. Now these models can be compared to ANY (or other objects
with __eq__ overwritten) without returning False automatically.
Using annotated FilteredRelations raised a FieldError when coupled with
exclude(). This is due to not passing filtered relation fields to the
subquery created in split_exclude(). We fixed this issue by passing the
filtered relation data to the newly created subquery.
Secondly, in the case where an INNER JOIN is used in the excluded
subquery, the ORM would trim the filtered relation INNER JOIN in attempt
to simplify the query. This will also remove the ON clause filters
generated by the FilteredRelation. We added logic to not trim the INNER
JOIN if it is from FilteredRelation.