The memory_index FT schema only materializes embedding, scope,
categories, created_at, and importance. ValkeyStorage._vector_search
was emitting metadata_filter clauses as @{key}:{value} against that
index, but metadata keys are user-defined and not part of the schema,
so the FT.SEARCH server would either error out or silently return
results that the metadata predicate failed to narrow.
Move metadata_filter to a Python post-filter that runs after FT.SEARCH
parses results. Overfetch from KNN (limit * 10, capped at 1000) when
metadata_filter is supplied so the post-filter still returns the
caller-requested number of hits in the common case, then truncate to
limit. Scope/categories predicates remain pushed down into FT.SEARCH
because they are valid index fields.
Adds TestValkeyStorageMetadataPostFilter and
TestValkeyStorageMatchesMetadataFilter test classes; updates three
pre-existing tests that asserted the broken contract.
Closes#5794
Co-Authored-By: João <joao@crewai.com>
808654c2f2