v0.4.17

## What's Changed
* doc: add 0.4.16 release blog post and changelog by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/502
* fix: truncate long bank names in selector dropdown by @dcbouius in https://github.com/vectorize-io/hindsight/pull/505
* fix: refresh bank list when dropdown is opened by @dcbouius in https://github.com/vectorize-io/hindsight/pull/504
* fix: openclaw tests + split doc-examples CI per language by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/503
* doc: document all missing bank config fields in memory-banks.mdx by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/508
* Add on_file_convert_complete extension hook after file-to-markdown conversion by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/507
* feat: add source facts token limits to consolidation and recall by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/509
* refactor: remove dead code and clarify observations vs mental models by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/512
* feat: per-request file parser selection with fallback chains by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/514
* feat: observation history tracking and diff UI by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/513
* feat: mental model history tracking and UI diff view by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/516
* doc: Upgrading OpenClaw's Memory with Hindsight by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/515
* Fix GCS auth for Workload Identity Federation credentials by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/518
* feat: change tags for a document by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/517
* fix: serialize Alembic upgrades in-process by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/521
* Fix Iris parser httpx read timeout by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/524
* fix: migrate mental_models.embedding dimension alongside memory_units by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/526
* feat: filter operations by type + fix stale auto-refresh closure (#522) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/527
* fix(consolidation): respect bank mission over ephemeral-state heuristic by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/525
* docs: add FAQ entry for conversation retain format by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/529
* fix: normalize named tool_choice to avoid HTTP 400 on LM Studio / Ollama by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/528
* doc: Your Pydantic AI Agent Forgets You After Every Run. Fix It in 5 Lines. by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/531
* Fix run-db-migration for all-tenant upgrades by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/530
* doc: What's New in Hindsight — Document File Upload by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/532
* doc: split blog index into Hindsight and Hindsight Cloud sections by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/534
* fix: strip null bytes from parsed file content before retain by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/535
* fix: resolve remaining webhook schema issues in multi-tenant retain by @Andreymi in https://github.com/vectorize-io/hindsight/pull/533
* feat: manual retry for failed async operations by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/537


**Full Changelog**: https://github.com/vectorize-io/hindsight/compare/v0.4.16...v0.4.17