v0.4.16

## What's Changed
* docs: 0.4.15 release blog post and changelog by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/477
* doc: update cookbook by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/479
* blog: add LiteLLM persistent memory post by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/481
* doc: fix LiteLLM blog — OPINION → OBSERVATION, update title by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/482
* cli: add linux-arm64 binary to release and CI by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/484
* fix: resolve all Dependabot security vulnerabilities by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/486
* doc: add ZeroEntropy reranker to models.md by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/489
* feat: webhook system with retain.completed event, UI, and docs by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/487
* fix: resolve TypeError when LLM returns invalid JSON across all retries by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/490
* Fix bank-level MCP tool filtering for FastMCP 3.x by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/491
* doc: add MCP blog post by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/492
* perf: add GIN index on source_memory_ids for observation lookup by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/485
* fix: replace additive combined scoring with multiplicative CE boosts by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/494
* fix: cap uvicorn graceful shutdown at 5s and enable force-kill on double Ctrl+C by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/495
* fix: resolve chunks for observation results via source_memory_ids by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/496
* feat(openclaw): v2 recall/retention controls, scalability fixes, and Gemini safety settings by @mysteriousHerb in https://github.com/vectorize-io/hindsight/pull/480
* fix: use correct schema name in webhook outbox callback by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/499
* fix: run schema migrations in thread to prevent event loop deadlock by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/500
* doc: Give Your OpenAI App a Memory in 5 Minutes by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/498
* fix: preserve None temporal fields for observations without source dates by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/501

## New Contributors
* @mysteriousHerb made their first contribution in https://github.com/vectorize-io/hindsight/pull/480

**Full Changelog**: https://github.com/vectorize-io/hindsight/compare/v0.4.15...v0.4.16