- Added sparse vector support (auto‑indexing, HNSW index, RESTful API) and RBAC for database describe/alter APIs.
- Improved performance via parallel Bloom filter processing, collection‑level flush rate limiting, faster small collection loading, and multiple cache/memory optimizations.
- Fixed stability and security issues such as concurrent load/release crashes, potential data loss on deletion, incorrect vector size handling, and masked Kafka credentials.