v0.4.14

## What's Changed
* doc: 0.4.13 changelog by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/411
* fix(chore): include hindsight-crewai in release workflow by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/412
* feat(openclaw): add autoRecall toggle and excludeProviders schema by @slayoffer in https://github.com/vectorize-io/hindsight/pull/413
* doc: improve api explanation by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/415
* misc: fix vertex/gemini errors and use it for ci tests by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/414
* Fix bank config API for multi-tenant schema isolation by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/417
* feat: add ZeroEntropy reranker provider support by @franchb in https://github.com/vectorize-io/hindsight/pull/420
* Fix reflect based_on population and enforce full hierarchical retrieval by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/421
* fix: improve memory footprint of recall by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/423
* feat: include doc metadata in fact extraction by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/424
* feat: increase customization for reflect, retain and consolidation by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/419
* feat: enable bank config API by default by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/426
* feat: add reflect mode to LoComo benchmark and improve reflect agent by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/428
* fix(openclaw): pass auth token to health check endpoint by @slayoffer in https://github.com/vectorize-io/hindsight/pull/427
* fix: handle observations regeneration when memories get deleted by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/429
* feat: batch observations consolidation by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/430
* feat: expand MCP tool surface area by @DK09876 in https://github.com/vectorize-io/hindsight/pull/435
* feat: filter graph memories with tags by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/431
* fix: pass encoding_format="float" in LiteLLM SDK embedding calls by @franchb in https://github.com/vectorize-io/hindsight/pull/434
* fix: catch ValueError instead of bare except in date parsing by @haosenwang1018 in https://github.com/vectorize-io/hindsight/pull/438
* feat: configure exposed mcp tools per bank by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/439
* fix(storage): use dynamic schema_getter in PostgreSQLFileStorage for multi-tenant by @Andreymi in https://github.com/vectorize-io/hindsight/pull/440
* fix: fail fast HNSW index when embedding dimension exceeds 2000 by @slayoffer in https://github.com/vectorize-io/hindsight/pull/361
* feat: add Chat SDK integration for persistent chat bot memory by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/442
* chore: integrate chat with release by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/443
* fix: doc build and add chat doc by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/444

## New Contributors
* @haosenwang1018 made their first contribution in https://github.com/vectorize-io/hindsight/pull/438
* @Andreymi made their first contribution in https://github.com/vectorize-io/hindsight/pull/440

**Full Changelog**: https://github.com/vectorize-io/hindsight/compare/v0.4.13...v0.4.14