fix(llmrails): backfill embedding model params into search provider config (fixes stale KB cache)#1753

Open

Pouyanpi wants to merge 3 commits intodevelopfrom

fix/kb-cache-invalidation-on-embedding-model-change

Commits on Mar 31, 2026

fix(llmrails): invalidate KB cache when embedding model changes via models config
Pouyanpi
committed
ensure that "embedding_model" and "embedding_engine" parameters are set
Pouyanpi
committed
assert KB provider gets backfill when core uses custom provider
Pouyanpi
committed