import PageHero from '@site/src/components/PageHero';

This page covers the Hindsight core (API, CLI, control plane). Each integration is released on its own cadence and has its own changelog — find it on the integration's page.

0.10.2

Features

Configure independent refresh budgets for each mental model, without inheriting reflect defaults.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/022583d43" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>022583d43</a>
Add extension hooks for validating memory-curation operations.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/26981c6b4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>26981c6b4</a>
Add opt-in CUDA acceleration for ONNX embedding generation.·<a href="https://github.com/Alkapuce" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Alkapuce</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5c92e8ba2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5c92e8ba2</a>
Support multimodal extraction input in dry runs and add an Extraction Tester interface.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5e51d5350" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5e51d5350</a>
Allow pg0 PostgreSQL connection URL query parameters to be passed through.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fee3cad0b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fee3cad0b</a>
Allow reflect operations to use a document’s own metadata.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/82342ca62" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>82342ca62</a>
Carry attachments through observations and Reflect based_on inputs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/303216822" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>303216822</a>
Add bank aliases to support zero-downtime bank ID migrations and stable display IDs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a45a8821f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a45a8821f</a>
Add configurable consolidation strategies for individual memory scopes.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4133ae85c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4133ae85c</a>

Improvements

Distribute consolidation work more fairly across scope groups.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c08e07560" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c08e07560</a>
Speed up recall queries for observations from connected sources.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9a34cd0a8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9a34cd0a8</a>
Record reasoning-token usage separately in LLM traces.·<a href="https://github.com/PraveenKumarSridhar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@PraveenKumarSridhar</a>·<a href="https://github.com/vectorize-io/hindsight/commit/415a8d763" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>415a8d763</a>
Scope entity fuzzy matching by bank for faster, more isolated lookups.·<a href="https://github.com/slayoffer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@slayoffer</a>·<a href="https://github.com/vectorize-io/hindsight/commit/071330cd2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>071330cd2</a>
Stream bank and document exports to avoid building large exports entirely in memory.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0e3d28cf7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0e3d28cf7</a>
Improve control-plane translations and localize timeline content.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/45f7fe95a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>45f7fe95a</a>
Allow each tenant's memory store to migrate its derived state independently.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9b590b1f4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9b590b1f4</a>
Reduce Reflect input usage by sending mental models as a page with focused snippets.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5009e8ad4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5009e8ad4</a>
Reduce Reflect refresh cost by returning tool results directly and completing through the done tool.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/500da5372" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>500da5372</a>
Omit unused memory-unit fields from bank-list responses.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3684be009" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3684be009</a>
Make per-tenant metrics labels configurable to control metric cardinality.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/697a24534" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>697a24534</a>
Preserve store ordering when paginating bank lists.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2cfc7ab8e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2cfc7ab8e</a>

Bug Fixes

Restore OpenAI provider compatibility with GPT-6 models.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e329623c0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e329623c0</a>
Return a proper not-found response when recalling a bank deleted by another process.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/563a357b4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>563a357b4</a>
Discard consolidation results when their source facts change during processing.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ff7f96ce2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ff7f96ce2</a>
Retry mental-model updates when a response references a mistyped block ID.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ab602f522" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ab602f522</a>
Prevent in-process reranking from exceeding its wall-clock timeout.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/60f06e1de" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>60f06e1de</a>
Prevent untagged writes from incorrectly marking tagged mental models as stale.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6830c43f5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6830c43f5</a>
Clear completed operation errors and use consistent fields in operation responses.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f4f6b154b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f4f6b154b</a>
Enable all retain workflows when using Oracle storage.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8924a5bcf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8924a5bcf</a>
Handle JSON responses wrapped in code fences across supported LLM providers.·<a href="https://github.com/kuishou68" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@kuishou68</a>·<a href="https://github.com/vectorize-io/hindsight/commit/266d8aa73" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>266d8aa73</a>
Show each consolidation observation source only once.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9a5b9fa1c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9a5b9fa1c</a>
Apply consistent pagination and limit bounds to MCP list tools.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/78c34f201" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>78c34f201</a>
Bound TypeSafe reranker token use while preserving result order across chunks.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2fbc25e09" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2fbc25e09</a>
Enforce LLM request deadlines even when an upstream provider trickles responses.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/878f43998" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>878f43998</a>
Preserve result ordering when Memory Defense partially blocks a retain request.·<a href="https://github.com/dakjdakd" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dakjdakd</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3976f5d4b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3976f5d4b</a>
Honor native Anthropic tool-choice settings in agent calls.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/48ce1ecd1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>48ce1ecd1</a>
Preserve all caller-supplied fields when appending retained content.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a4e0f0a49" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a4e0f0a49</a>
Move explicitly scoped observations when renaming a tag.·<a href="https://github.com/nabilaameena" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nabilaameena</a>·<a href="https://github.com/vectorize-io/hindsight/commit/50ddb2b88" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>50ddb2b88</a>
Resolve chained section anchors during reflection.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8ad962683" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8ad962683</a>
Use compatible timeout handling for Anthropic API clients.·<a href="https://github.com/drakeo338" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@drakeo338</a>·<a href="https://github.com/vectorize-io/hindsight/commit/148ba350c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>148ba350c</a>
Support document and chunk IDs containing slashes in the control plane.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/25d266937" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>25d266937</a>
Make the embedding daemon start more reliably.·<a href="https://github.com/diatche" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@diatche</a>·<a href="https://github.com/vectorize-io/hindsight/commit/25b539ac9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>25b539ac9</a>
Ignore excessively long entity-name candidates during retain processing.·<a href="https://github.com/slayoffer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@slayoffer</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ccc832acc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ccc832acc</a>
Report tool-selection failures correctly in reflect compatibility errors.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c11676164" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c11676164</a>
Allow clients to download presigned export archives without API credentials.·<a href="https://github.com/dakjdakd" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dakjdakd</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e23de7e39" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e23de7e39</a>
Keep entity names that differ by numbers distinct.·<a href="https://github.com/jiangLLM" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@jiangLLM</a>·<a href="https://github.com/vectorize-io/hindsight/commit/aef669b1b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aef669b1b</a>
Avoid duplicating large tool results when splitting reflect requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/559050e49" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>559050e49</a>
Reduce recall strategy boosts based on source rank after reranking.·<a href="https://github.com/1346154262" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@1346154262</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ac4a4b31a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ac4a4b31a</a>
Allow graph links to be recreated after observation sweep source locks.·<a href="https://github.com/BrianMcBrayer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@BrianMcBrayer</a>·<a href="https://github.com/vectorize-io/hindsight/commit/93d6aeaa0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>93d6aeaa0</a>
Safely serialize conversation chunks containing lone Unicode surrogates.·<a href="https://github.com/kubaodias" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@kubaodias</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f41df14e3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f41df14e3</a>
Display causal links in control-plane bank statistics.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7be554770" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7be554770</a>
Show “all fact types” when no mental-model fact-type filter is selected.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5bb45ddc0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5bb45ddc0</a>
Handle GPT-6 as a reasoning model when using OpenAI Responses.·<a href="https://github.com/Harshul1484" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Harshul1484</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fd065ba38" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fd065ba38</a>
Prevent embedded daemon startup from inheriting interactive standard input and hanging.·<a href="https://github.com/E-R-Butch" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@E-R-Butch</a>·<a href="https://github.com/vectorize-io/hindsight/commit/403f9c68a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>403f9c68a</a>
Allow Reflect's completion tool to accept document arguments encoded as strings.·<a href="https://github.com/bannert1337" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@bannert1337</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ce8d5d6e4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ce8d5d6e4</a>
Make standalone Docker image build arguments take effect correctly.·<a href="https://github.com/M-r-A" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@M-r-A</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8f873ec30" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8f873ec30</a>
Route Helm Ingress data API requests through the /v1 endpoint.·<a href="https://github.com/dakjdakd" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dakjdakd</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dc642d650" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dc642d650</a>
Fix the control-plane document date-range picker being clipped.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/284db9c35" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>284db9c35</a>
Derive LLM session IDs correctly from Responses API input.·<a href="https://github.com/davidneyra2804" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@davidneyra2804</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5125ffad8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5125ffad8</a>
Prevent concurrent refreshes of the same mental model.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6be8d3bd3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6be8d3bd3</a>
Allow Retain to append monotonically growing JSON conversation arrays.·<a href="https://github.com/Tosko4" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Tosko4</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8f0eb1bae" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8f0eb1bae</a>
Avoid sending unsupported explicit tool choices to Z.AI models.·<a href="https://github.com/ebarkhordar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ebarkhordar</a>·<a href="https://github.com/vectorize-io/hindsight/commit/176c03e3a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>176c03e3a</a>
Reject no-op knowledge-node update requests without reading the bank.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c708ad53f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c708ad53f</a>
Return empty pages as empty content instead of placeholder text.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a7eafb2f3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a7eafb2f3</a>
Release the database migration lock when a migration fails.·<a href="https://github.com/nabilaameena" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nabilaameena</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f8980263d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f8980263d</a>
Avoid creating unnecessary per-bank vector indexes for store-owned memories.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/166ad9745" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>166ad9745</a>
Serve Prometheus metrics without blocking the API event loop.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/85c3dfcc6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>85c3dfcc6</a>
Support URL-encoded Oracle credentials and Oracle connect descriptors.·<a href="https://github.com/rodrigoedu94-png" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rodrigoedu94-png</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7a593e8ce" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7a593e8ce</a>
Persist Retain operation document IDs when using Oracle.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/66db5efa3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>66db5efa3</a>
Correct Oracle handling of parent-exclusion JSON queries.·<a href="https://github.com/rodrigoedu94-png" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rodrigoedu94-png</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6bac552e6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6bac552e6</a>
Treat PostgreSQL-specific SET LOCAL statements as no-ops on Oracle.·<a href="https://github.com/rodrigoedu94-png" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rodrigoedu94-png</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b8fc67672" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b8fc67672</a>
Allow knowledge-base trees with Oracle CLOB names to be sorted correctly.·<a href="https://github.com/rodrigoedu94-png" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rodrigoedu94-png</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2667fd388" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2667fd388</a>
Ensure Oracle JSON merge-patch operations return CLOB values.·<a href="https://github.com/rodrigoedu94-png" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rodrigoedu94-png</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9d153043c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9d153043c</a>
Compare mental-model staleness timestamps in UTC on Oracle.·<a href="https://github.com/rodrigoedu94-png" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rodrigoedu94-png</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a2a0000b3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a2a0000b3</a>
Allow UUID relationship IDs when relinking graph data on Oracle.·<a href="https://github.com/rodrigoedu94-png" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rodrigoedu94-png</a>·<a href="https://github.com/vectorize-io/hindsight/commit/53996a880" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>53996a880</a>
Restore bank archive rows correctly during transfers on Oracle.·<a href="https://github.com/rodrigoedu94-png" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rodrigoedu94-png</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0254f0d5b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0254f0d5b</a>
Reject invalid mental-model delta responses and request a schema-valid retry.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/63da77730" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>63da77730</a>
Fixed four product issues uncovered while validating all documentation code examples.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/83bd08ec7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>83bd08ec7</a>
Stop failed mental-model refreshes instead of repeatedly retrying and consuming LLM usage.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6786420d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6786420d</a>

Database Migrations

This release alters high-volume tables (entities). Migrations run on startup, so allow extra time on large deployments.

b8d3f1a6c2e4 — Add last_refresh_failed_at column to mental_models·<code>mental_models</code>medium·<a href="https://github.com/vectorize-io/hindsight/pull/4618" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>#4618</a>
c8d1e4f7a20b — Add bank_aliases: extra ids a bank also answers to.·<code>bank_aliases</code>small·<a href="https://github.com/vectorize-io/hindsight/pull/4706" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>#4706</a>
d4f8b1c6e903 — Let one of a bank's aliases be the id shown in its place.·<code>bank_aliases</code>small·<a href="https://github.com/vectorize-io/hindsight/pull/4724" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>#4724</a>
7c2e5a9d1f40 — Scope the entities trigram index by bank: GIN (bank_id, LOWER(canonical_name)).·<code>entities</code>high volume·<a href="https://github.com/vectorize-io/hindsight/pull/4775" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>#4775</a>
a6c4e8f1b203 — Store per-request reasoning tokens alongside visible output tokens.·<a href="https://github.com/vectorize-io/hindsight/pull/4745" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>#4745</a>
e5b1c7d3a902 — Merge divergent heads from the bank-scoped trigram index and reasoning tokens·<a href="https://github.com/vectorize-io/hindsight/pull/4788" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>#4788</a>

0.10.1

Features

Added a TypeSafe reranker provider to remove irrelevant recall candidates.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6fd2e95a8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6fd2e95a8</a>
Reflection search-observation budgets and entity settings are now configurable.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/610dfb0b0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>610dfb0b0</a>
The control plane document list now supports preset and custom date-range filters.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d6a4e89bb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d6a4e89bb</a>
Added an opt-in server setting that permits facts without when, where, who, or why fields.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c3aaf47ae" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c3aaf47ae</a>
Memory and document list APIs now support server-side time filtering and sorting.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5789679f3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5789679f3</a>
Added an advanced search dialog for knowledge pages in the control plane.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/55a3c8c2b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>55a3c8c2b</a>
Automatic mental-model refreshes can now use a separate LLM configuration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/311a2d495" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>311a2d495</a>
Added an API to clone a bank in a single request.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a71b06245" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a71b06245</a>
Added unified bank export and import APIs for transferring banks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6e6098a03" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6e6098a03</a>
Added an admin command to rename a bank without recreating it.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/88b1db875" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>88b1db875</a>
Simplified control-plane recall and reflect option forms and added help for every option.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d6bc553ce" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d6bc553ce</a>
Added configuration for the default trigger used when creating knowledge pages.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/08626936a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>08626936a</a>
Added attachment filenames for documents in store-owned banks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7ed568ac4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7ed568ac4</a>
Attachments are now explicitly associated with their source documents.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b6634ea2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b6634ea2</a>

Improvements

Retaining multi-chunk content now avoids repeated prompt and schema generation.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9f9a0d396" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9f9a0d396</a>
Listing banks no longer scans all memory units, improving performance at scale.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/81e4a674a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>81e4a674a</a>
Improved recall performance by reusing source-memory information throughout processing.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/be0e93997" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>be0e93997</a>
Released Jina MLX reranker memory after each batch to reduce memory pressure.·<a href="https://github.com/w-seok" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@w-seok</a>·<a href="https://github.com/vectorize-io/hindsight/commit/50c63abce" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>50c63abce</a>

Bug Fixes

Outbound HTTP requests now honor proxy environment variables.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/44bf0c4f5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>44bf0c4f5</a>
Embedding availability checks no longer disrupt the caller's event loop.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/272c7491f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>272c7491f</a>
Temporal recall results are now correctly ordered before result fusion.·<a href="https://github.com/rocke2020" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rocke2020</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ccfc38020" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ccfc38020</a>
Entity clustering now applies word-level agreement checks within the same ingestion batch.·<a href="https://github.com/ebarkhordar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ebarkhordar</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7905cb10d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7905cb10d</a>
Rate-limit retries now honor numeric retry-after values returned by providers.·<a href="https://github.com/i-Hun" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@i-Hun</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9f99abec9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9f99abec9</a>
Renaming a bank now moves its stored files to the new bank location.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ea55ac038" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ea55ac038</a>
Object-store backends now return retrieved content as native bytes.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/79a2fb152" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>79a2fb152</a>
MLX is now installed only on supported Apple Silicon systems.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8f852444e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8f852444e</a>
Retain retries foreign-key delete races instead of dropping the memory request.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f52c2f0a6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f52c2f0a6</a>
Knowledge-page search scores are now normalized to a consistent 0–1 range.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fb4a01625" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fb4a01625</a>
Reflection now rejects blank queries without making unnecessary LLM calls.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/13b828bb4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>13b828bb4</a>
Local models no longer use Apple Silicon MPS execution.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e73a4bf5e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e73a4bf5e</a>
Store-owned bank attachments and uploaded originals now stay synchronized with their documents.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/760c0ea57" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>760c0ea57</a>
Recall now correctly rejects requests for missing banks before responding with not found.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c4deb82af" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c4deb82af</a>
Reflection prompts now clearly define disposition levels for more reliable tool use.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/475cc0278" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>475cc0278</a>
Windows embedding support now correctly launches Python from uv virtual environments.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a63525347" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a63525347</a>
Bank imports and clones now work when memories are stored in the memories store.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/12a070cbb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>12a070cbb</a>
Bank archive creation now avoids blocking the event loop and long read transactions.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fea8cd8bb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fea8cd8bb</a>
Database migrations now scope vector-index lookups to the correct relation.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a5552d4e8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a5552d4e8</a>
Setting the recall query token cap to zero now correctly disables the cap.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e5c3f65f7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e5c3f65f7</a>
Cancelled client requests now stop waiting in capacity-retry backoff.·<a href="https://github.com/Tosko4" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Tosko4</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ba5f9a49c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ba5f9a49c</a>
Retained non-English facts now preserve their original writing script.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/de0b34a1a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>de0b34a1a</a>
Mental-model refreshes no longer overwrite a page with older event state.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a6518c919" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a6518c919</a>
Prevented remaining delete-and-reingest operations from deadlocking.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/590657901" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>590657901</a>
Made the control-plane UI available when the service is bound to a loopback address.·<a href="https://github.com/snevesgraca-nwmo" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@snevesgraca-nwmo</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1a000a527" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1a000a527</a>
Made retention apply its language behavior more consistently.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/567927c8f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>567927c8f</a>
Prevented observation cleanup and re-ingestion from deadlocking by using a consistent processing order.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f6077c31f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f6077c31f</a>
Made recall's default time window use UTC consistently across server time zones.·<a href="https://github.com/ebarkhordar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ebarkhordar</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5ef65534a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5ef65534a</a>
Improved full-text recall search by matching meaningful query terms instead of raw sentences.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d6c556f65" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d6c556f65</a>
Prevented tenant information from leaking between extension requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/882e32c3e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>882e32c3e</a>
Rejected bank IDs that are too long or contain control characters.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/909a8c18f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>909a8c18f</a>
Prevented same-bank cleanup from deadlocking while deleting or re-ingesting documents.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0246ee571" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0246ee571</a>
Made asynchronous retain submission validators receive the same context as synchronous submissions.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5f0d6c7df" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5f0d6c7df</a>
Made the API fail immediately when its configured listen port is unavailable.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/758e3c3d2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>758e3c3d2</a>
Avoided incorrectly redacting technical numbers as credit-card numbers.·<a href="https://github.com/kyletser" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@kyletser</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5f7d5216f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5f7d5216f</a>
Made embedding provider probing work reliably regardless of the server locale.·<a href="https://github.com/L4XB" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@L4XB</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2252291c5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2252291c5</a>
Deleted stored files with their bank and isolated file storage between tenants.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cfef62b8d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cfef62b8d</a>
Made reflection honor configured recall budgets and limit tool token requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4b5c0c461" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4b5c0c461</a>
Preserved converted-file references on documents in store-owned banks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2c96869c8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2c96869c8</a>
Made bulk memory deletion return the correct number of deleted memories.·<a href="https://github.com/1jeffchristensen" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@1jeffchristensen</a>·<a href="https://github.com/vectorize-io/hindsight/commit/041bb1f2b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>041bb1f2b</a>
Allowed OAuth store locking to continue when the local store cannot be written.·<a href="https://github.com/LoneExile" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@LoneExile</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fb6fc7629" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fb6fc7629</a>
Redacted Hindsight API keys from memory-defense output.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6e86e68bc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6e86e68bc</a>
Prevented store-owned bank attachments from being reclaimed unexpectedly.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ad068d99a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ad068d99a</a>

Database Migrations

a7c2e9f41b60 — Give every attachment an owning document, and drop document_attachments.·<code>attachments</code>medium <code>document_attachments</code>medium·<a href="https://github.com/vectorize-io/hindsight/pull/4471" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>#4471</a>

0.10.0

Breaking Changes

Mental-model list responses now return metadata by default rather than full model content.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fb94ce034" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fb94ce034</a>
API runtime Docker images no longer include curl.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5f9bff905" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5f9bff905</a>
Removed the bank profile and background API endpoints.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/163fbb0ed" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>163fbb0ed</a>
Removed the count_chunks extension hook from the memory extension API.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d8b11907b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d8b11907b</a>

Features

Configure separate timeout and retry limits for each model in a multi-LLM chain.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/54fc68e70" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>54fc68e70</a>
API requests can wait briefly for capacity, with clients retrying transient admission limits.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6ac46e230" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6ac46e230</a>
Prometheus metrics now cover every API worker and report event-loop lag distributions.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2cd0561f1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2cd0561f1</a>
Recall and read results now include the attachments supporting facts, including for store-owned banks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/48b62ee08" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>48b62ee08</a>
The control plane keeps the currently selected bank at the top of the bank selector.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4af316e74" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4af316e74</a>
Add a control-plane button to pause ambient constellation motion.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/558017a84" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>558017a84</a>
Enable CPU profiling through environment configuration and emit profiles to application logs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/da0444a72" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>da0444a72</a>
Add a control-plane prompt tester for retain and prompt previews for every operation.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9e6d9e76c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9e6d9e76c</a>
Route retained items to an LLM chain member based on their metadata.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/864d92692" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>864d92692</a>
Added a control-plane bank overview with bulk deletion support.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7244098c0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7244098c0</a>
Support images and files as first-class inline content when retaining memories.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/280f09820" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>280f09820</a>
Added Meta Model API as a first-class LLM provider.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/30ce3b8d1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>30ce3b8d1</a>
Added fuzzy matching support for leaf tags within tag groups during recall.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f747d96c3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f747d96c3</a>
Added an option to run database migrations in a separate subprocess.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a46783815" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a46783815</a>
Added multi-valued open-text entity labels.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/21c216004" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>21c216004</a>
Webhook deliveries now include timestamped SHA-256 signatures for verification.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d936d4931" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d936d4931</a>
Added separate credential directories for each Codex LLM provider configuration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c42e6323e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c42e6323e</a>
Mental-model delta refreshes now receive the operation schema.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f22c36250" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f22c36250</a>
Added configurable dimensions and more reliable startup checks for LiteLLM embeddings.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dd60a542e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dd60a542e</a>
Added a CUDA-enabled standalone Docker deployment recipe.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a6a6c8e5a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a6a6c8e5a</a>
Exposed the complete mental-model trigger policy through MCP, including knowledge pages.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/56ba04204" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>56ba04204</a>
Added a CLI option to choose full or delta trigger mode when updating mental models.·<a href="https://github.com/mdbenito" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@mdbenito</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1cc2f9c10" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1cc2f9c10</a>
Allow configuring the PostgreSQL schema that provides pg_search extension functions.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0b6b5261a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0b6b5261a</a>
Added Helm support for Prometheus Operator ServiceMonitors.·<a href="https://github.com/aWN4Y25pa2EK" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@aWN4Y25pa2EK</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a6f99c995" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a6f99c995</a>
Allow extra containers and init containers in Helm deployments for the API, worker, and control plane.·<a href="https://github.com/Adrastopoulos" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Adrastopoulos</a>·<a href="https://github.com/vectorize-io/hindsight/commit/eb3d1d587" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>eb3d1d587</a>
Added Control Plane translations for knowledge-base and mental-model refinement workflows.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/35b98cb94" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>35b98cb94</a>
Document transfers can now export a knowledge base.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8d8dab346" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8d8dab346</a>
Added a Business Executive memory-bank template.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b75fa6103" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b75fa6103</a>
Added a per-bank option to disable text search and use pure vector recall.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cd8d4d399" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cd8d4d399</a>

Improvements

Reduce CPU usage and latency on recall requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d9df6d2a4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d9df6d2a4</a>
Improve API throughput, especially for inexpensive routes.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2544a73c4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2544a73c4</a>
Speed up retain processing by accelerating semantic-link calculation within a batch.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b04579481" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b04579481</a>
Reduce overhead when resolving Hindsight configuration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3e1d47fdc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3e1d47fdc</a>
Improve performance when resolving duplicate entities within a retain batch.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bc06bd051" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bc06bd051</a>
Reduce API overhead by avoiding unnecessary mental-model staleness checks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/78c10a382" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>78c10a382</a>
Reduced standalone Docker image dependencies by removing the NodeSource bootstrap.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/798aebd66" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>798aebd66</a>
Reduced control-plane-only Docker image dependencies by omitting unused curl.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d6ec007df" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d6ec007df</a>
Updated container images to use the active Node.js 24 LTS runtime.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c57331a94" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c57331a94</a>
Improved Docker image build performance by setting file ownership during copy operations.·<a href="https://github.com/SharkyRawr" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@SharkyRawr</a>·<a href="https://github.com/vectorize-io/hindsight/commit/01ed1e15f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>01ed1e15f</a>
Reduced runtime Docker image size by removing unused libxml2 packages.·<a href="https://github.com/rschlek" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rschlek</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f9e91e21f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f9e91e21f</a>
Included operation attributes in exported tracing spans for better observability.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/356aa6cd4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>356aa6cd4</a>
Improved remote embedding throughput by processing provider batches concurrently.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9697c6900" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9697c6900</a>
Reduced API startup time by avoiding unnecessary loading of LLM and document-processing dependencies.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e48a0c9a7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e48a0c9a7</a>
Accelerated token counting used during memory processing.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bce43b8e1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bce43b8e1</a>
Added recall-phase metrics for recalls answered directly from stored memories.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b746ad139" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b746ad139</a>
Improved tracing by naming API operations clearly and linking queued retains to their workers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ebcd88f97" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ebcd88f97</a>
Added detailed timing metrics for recall request phases.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b00cc4047" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b00cc4047</a>
Added timing metrics for operation validation hooks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/97ae1d08c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>97ae1d08c</a>
Improved configuration hot-path performance by retaining cached settings where freshness is not required.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c9591229e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c9591229e</a>
Hardened Docker runtime images by removing npm from runtime stages and expanding base-image security scanning.·<a href="https://github.com/rschlek" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rschlek</a>·<a href="https://github.com/vectorize-io/hindsight/commit/466517ff9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>466517ff9</a>
Improved recall performance by fetching expanded observation graphs in a single database query.·<a href="https://github.com/jervaise" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@jervaise</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3bba2c01f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3bba2c01f</a>
Avoided unnecessary document retagging when a tags update makes no change.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/43f545e9b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>43f545e9b</a>
Improved retain throughput by reducing embedding-vector conversion overhead.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0478c09c4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0478c09c4</a>
Reduced unnecessary database queries when creating or accessing banks.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/059951ce1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>059951ce1</a>
Improved pg_search query handling by using the backend's native tokenization.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/600890c43" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>600890c43</a>
Meter mental-model content based on what is delivered rather than the endpoint used.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/870d20d6f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>870d20d6f</a>
Improved CPU reranker performance by avoiding unnecessary full garbage collections.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6f9f935e6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6f9f935e6</a>
Deployments can take ownership of database maintenance routines.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7ba5fb23a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7ba5fb23a</a>
Reduced memory overhead while retaining large documents by accumulating document content across sub-batches.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3ad9d618e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3ad9d618e</a>
Improved tokenization performance and updated the default tokenizer encoding.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9fcb7ca7a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9fcb7ca7a</a>
Improved retain throughput by batching chunk embedding requests for each document.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ca2c983e1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ca2c983e1</a>

Bug Fixes

CPU profiling now captures worker processes as well as the supervisor when enabled.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cdac00842" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cdac00842</a>
Custom memory stores no longer maintain indexes that do not apply to them.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5a6083175" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5a6083175</a>
Reflect no longer states a specific value for a period the memories don't cover — it says the data isn't recorded instead of extrapolating a number from neighbouring periods.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/630c3a63e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>630c3a63e</a>
Mental-model and knowledge-page delta refreshes no longer overwrite stored content from what the newest batch alone says, such as replacing a running count or erasing an earlier recorded event.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/630c3a63e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>630c3a63e</a>
Correct public API issues uncovered by end-to-end system testing.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/59e25d74f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>59e25d74f</a>
Generated API clients now receive downloaded binary content as bytes.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/88456981f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>88456981f</a>
Entity mention counts are restored correctly when mentions are removed.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/64a98aa56" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>64a98aa56</a>
Clearing an occurrence start date also clears the legacy event date.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/203d95c7c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>203d95c7c</a>
Reflection turns use unique tool-call IDs for compatibility with strict LLM APIs.·<a href="https://github.com/gwthm-in" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@gwthm-in</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5df6398fa" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5df6398fa</a>
Retain operations no longer risk chunk ID collisions between banks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/179938a65" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>179938a65</a>
Reflection reports when structured-output extraction fails instead of silently obscuring the cause.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f5b3f76a8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f5b3f76a8</a>
Expose the bank-template import request body in the API schema and generated clients.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1081a2ea4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1081a2ea4</a>
Store-owned retain operations no longer fail while recording their own log entries.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/134207d3c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>134207d3c</a>
List and graph API responses now return consistently typed records.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ef3ccdba3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ef3ccdba3</a>
Retain completion events are emitted only after the associated store transaction succeeds.·<a href="https://github.com/kyletser" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@kyletser</a>·<a href="https://github.com/vectorize-io/hindsight/commit/511c86e10" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>511c86e10</a>
Split append operations retain the full document body instead of only its trailing portion.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fda969777" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fda969777</a>
Recall traces now report the query timestamp supplied by the caller.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e366ff407" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e366ff407</a>
Vertex single-content embedding models now receive one text per embedding request.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b2a7257eb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b2a7257eb</a>
Local ML ARM64 images now run on older ARMv8.0 CPUs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/aeaf4b1bd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aeaf4b1bd</a>
Future-dated search items are safely handled in recency scoring.·<a href="https://github.com/ebarkhordar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ebarkhordar</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1ca8c4d60" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1ca8c4d60</a>
Sent Gemini embedding inputs as separate content items for correct provider handling.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a08ec8ddf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a08ec8ddf</a>
Returned 404 for bank-scoped read requests targeting banks that do not exist.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/66992496f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>66992496f</a>
Limited embedding requests to each model's usable context window, including provider prefixes.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a3c5b350d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a3c5b350d</a>
Improved consolidation by explicitly identifying deletion targets and accounting for discarded batch responses.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/05c775c41" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>05c775c41</a>
Processed queued concurrent requests in arrival order to prevent unfair waiting.·<a href="https://github.com/ebarkhordar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ebarkhordar</a>·<a href="https://github.com/vectorize-io/hindsight/commit/310c9f694" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>310c9f694</a>
Applied configured token limits when reflection uses forced synthesis.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d39170010" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d39170010</a>
Prevented imports from creating observations that cite missing source units.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4a447c061" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4a447c061</a>
Loaded environment configuration before engine startup so configured concurrency limits take effect.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f19c424e0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f19c424e0</a>
Allow cancellation of operations that are still in progress.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b1de1b941" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b1de1b941</a>
Correctly recognized requests made through OpenAI-compatible LLM providers.·<a href="https://github.com/SharkyRawr" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@SharkyRawr</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5092f3e11" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5092f3e11</a>
Sanitized all retained content at the memory engine boundary.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bd607ab8b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bd607ab8b</a>
Interpret "last weekend" requested during a weekend as the preceding weekend.·<a href="https://github.com/NgoQuocViet2001" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@NgoQuocViet2001</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cef202e6b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cef202e6b</a>
Prevented the CLI from aborting when its output is piped to a command that closes early.·<a href="https://github.com/2anoubis" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@2anoubis</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a72f9de15" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a72f9de15</a>
Added bounded retry handling for all remote reranker requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d69abe7b9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d69abe7b9</a>
Used one thread-local HTTP client per thread for TEI embeddings to avoid cross-thread client issues.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e7987ba69" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e7987ba69</a>
Applied the shared embedding retry policy to Cohere and ZeroEntropy providers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c1f70087f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c1f70087f</a>
Applied the shared embedding retry policy to Gemini requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/36f4a061f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>36f4a061f</a>
Made split-synthesis reflection map calls deterministic by using zero temperature.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/98e565d3f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>98e565d3f</a>
Allowed Bedrock inference profile ARNs to be used through the LiteLLM embedding provider.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7a52b0a6b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7a52b0a6b</a>
Preserved per-memory entity-label tags when re-retaining content updates document tags.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/576cf40a2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>576cf40a2</a>
Installed PostgreSQL extensions in the public schema for reliable database setup.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/901b5c696" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>901b5c696</a>
Forwarded all HINDSIGHT_* environment settings to the embedded daemon.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7eb0fcc61" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7eb0fcc61</a>
Ran tenant provisioning migrations within the database isolation boundary.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/216272814" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>216272814</a>
Showed the server response body in CLI output when API requests fail.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/737e5bf42" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>737e5bf42</a>
Paginated observation-scope and webhook listing endpoints.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d20893a83" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d20893a83</a>
Fixed fuzzy tag matching to compare tag values rather than namespaced tag names.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/00caa8eab" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>00caa8eab</a>
Fixed tokenizer cache leakage during memory processing.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/53ed37488" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>53ed37488</a>
Aligned bank configuration behavior between client wrappers and the server.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e8518c392" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e8518c392</a>
Duplicate mental-model IDs now return a conflict response instead of failing unexpectedly.·<a href="https://github.com/kubaodias" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@kubaodias</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1a8a1f50e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1a8a1f50e</a>
Improved concurrent API reliability when initializing date parsing locales.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3d0a66602" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3d0a66602</a>
Prevented shutdown activity from being falsely reported as an event-loop stall.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f0cf699cc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f0cf699cc</a>
Improved reliability of embedded local models with misaligned model weights.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4e952b4e5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4e952b4e5</a>
Re-retaining a document with changed scope now invalidates outdated observations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7be0f88ef" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7be0f88ef</a>
LLM timeout errors now identify the request phase in which they occurred.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3531e82f9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3531e82f9</a>
Reflection runs now fail when their retrieval tools fail, rather than continuing with incomplete results.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/921ae824a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>921ae824a</a>
Fixed prioritized recall ranking so boosts are applied consistently in rank space.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/aee42254a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aee42254a</a>
Fixed reflection output to use the required document sections format.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9bfad10a4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9bfad10a4</a>
Prevented bulk ingestion in one bank from starving work in other banks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b75e94191" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b75e94191</a>
Skipped unnecessary reflection loops when a mental-model scope has no content to process.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c507e70e3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c507e70e3</a>
Stopped retain extraction from deriving its narrator from a bank’s display name.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/aabbe8b22" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aabbe8b22</a>
Fixed authorization handling for bank-template imports.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/17fbc4f14" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>17fbc4f14</a>
Improved compatibility of strict structured-output schemas that use JSON references.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/db87a7467" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>db87a7467</a>
Fixed consolidation batching to resolve observation scopes before processing tag sets.·<a href="https://github.com/ferrastas" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ferrastas</a>·<a href="https://github.com/vectorize-io/hindsight/commit/eff3546ec" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>eff3546ec</a>
Ensured banks are authorized and provisioned before legacy mutations are applied.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/24adcfce7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>24adcfce7</a>
Expanded native knowledge BM25 searches to return matches for any search term.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a373ffab6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a373ffab6</a>
Memory edits now update their vector embedding together with their fields.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/31db3983a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>31db3983a</a>
Made Grafana dashboards compatible with older Grafana versions.·<a href="https://github.com/oldnicke" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@oldnicke</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7083fd790" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7083fd790</a>
Bank-specific configuration reads now use fresh bank settings instead of stale process-cached values.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/689c9b694" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>689c9b694</a>
Reprocessing retained content now re-runs extraction instead of leaving it unchanged.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9a4be5e05" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9a4be5e05</a>
Bound concurrent local embedding work to prevent resource exhaustion during ONNX embedding requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7051c6e3b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7051c6e3b</a>
Applied reliable per-request deadlines to all LLM providers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7729396e1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7729396e1</a>
Applied keyword minimum-score thresholds consistently across all text-search backends.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/78d46a718" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>78d46a718</a>
Updated standalone Docker images to remove fixed high-severity vulnerabilities.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/44f937631" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>44f937631</a>
Improved recall ranking for broad date expressions by scoring the full date period.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6a796f9f5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6a796f9f5</a>
Fixed malformed JSON handling for OpenAI-compatible LLM providers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/98e29817a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>98e29817a</a>
Correctly send consecutive Anthropic tool results together in a user message.·<a href="https://github.com/zlguo1996" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@zlguo1996</a>·<a href="https://github.com/vectorize-io/hindsight/commit/169c6ef58" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>169c6ef58</a>
Ensure complete mental-model documents are embedded whenever they are written.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fd2e0c61f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fd2e0c61f</a>
Allow reflection delta updates to add sections containing explicit IDs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6b8dfe74f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6b8dfe74f</a>
Accurately report visible output-token usage for OpenAI-compatible providers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/72c9c8f9e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>72c9c8f9e</a>
Read embedding profiles and log files as UTF-8 regardless of the host locale.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ff29e5ad7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ff29e5ad7</a>
Apply all memory writes from a consolidation response atomically.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ca38687cd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ca38687cd</a>
Report a clear truncation error when a non-streaming LLM completion exceeds its output limit.·<a href="https://github.com/ebarkhordar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ebarkhordar</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7ef98859e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7ef98859e</a>
Avoid unsupported occurred-date constraints on retain backends that do not support them.·<a href="https://github.com/nickanderson" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nickanderson</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5c78b8132" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5c78b8132</a>
Preserve base64 padding in API keys read from CLI configuration files.·<a href="https://github.com/2anoubis" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@2anoubis</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ddf57744c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ddf57744c</a>
Enforce the dedicated bank-read permission when viewing mental-model history.·<a href="https://github.com/Sword-Saint69" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sword-Saint69</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ad2ffa499" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ad2ffa499</a>
Preserve complete retain items so API reprocessing faithfully replays the original request.·<a href="https://github.com/shauneccles" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@shauneccles</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7b6177b46" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7b6177b46</a>
Avoid repeatedly attempting database settings that PostgreSQL has rejected as invalid.·<a href="https://github.com/Andreymi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Andreymi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/eca881d0b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>eca881d0b</a>
Honor configured LLM temperature settings during reflection.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7874561b0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7874561b0</a>
Read embedding profile configuration and Control Center environment files as UTF-8.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3e8226d1a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3e8226d1a</a>
Preserve intended HTTP validation status codes for webhooks.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8743b4594" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8743b4594</a>
Apply knowledge-base node updates atomically.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/29901d43b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>29901d43b</a>
Sanitize model-generated text consistently at all LLM boundaries.·<a href="https://github.com/BrianMcBrayer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@BrianMcBrayer</a>·<a href="https://github.com/vectorize-io/hindsight/commit/aab937e5f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aab937e5f</a>
Do not apply source-language rules when an output language is explicitly configured.·<a href="https://github.com/feniix" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@feniix</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ba0be9b30" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ba0be9b30</a>
Ensure SDK trigger updates modify only the settings explicitly supplied by callers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/55dafc27b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>55dafc27b</a>
Stop stalled consolidation tasks after a bounded idle period.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/698620786" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>698620786</a>
Accept reflection delta responses provided as a top-level operation array.·<a href="https://github.com/ebarkhordar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ebarkhordar</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7fe6a5e79" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7fe6a5e79</a>
Honor configured LLM timeouts when using the native Ollama provider.·<a href="https://github.com/MasterST1337" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@MasterST1337</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6e0f044f2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6e0f044f2</a>
Detect and recover worker tasks that are stuck without making stage progress.·<a href="https://github.com/BrianHotopp" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@BrianHotopp</a>·<a href="https://github.com/vectorize-io/hindsight/commit/532aa8698" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>532aa8698</a>
Add bounded retries, backoff, and timeouts for LiteLLM embedding providers.·<a href="https://github.com/icculp" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@icculp</a>·<a href="https://github.com/vectorize-io/hindsight/commit/906dbcdbd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>906dbcdbd</a>
Improve retry behavior for Text Embeddings Inference embedding requests.·<a href="https://github.com/oldnicke" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@oldnicke</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8916986f5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8916986f5</a>
Bound within-batch retain linking work to prevent large deltas from exhausting worker memory.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8833a7518" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8833a7518</a>
Improved OpenAI rate-limit handling by honoring the provider's reset timing after 429 responses.·<a href="https://github.com/romanbsd" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@romanbsd</a>·<a href="https://github.com/vectorize-io/hindsight/commit/20e66093d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>20e66093d</a>
Fixed transferred mental models so their evidence references remain valid.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c143de2a9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c143de2a9</a>
Fixed the Knowledge view so page and mental-model data is restricted to the selected bank.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3a399343b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3a399343b</a>
Fixed full-text search ranking so each result is scored independently.·<a href="https://github.com/mameikagou" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@mameikagou</a>·<a href="https://github.com/vectorize-io/hindsight/commit/23c63e173" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>23c63e173</a>
Fixed retain processing for oversized items so sub-batches are rebuilt from the correct source span.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d258f7b82" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d258f7b82</a>
Restore administrator identity sequence values after database restores.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e82f670f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e82f670f</a>

Other

Kept the llama.cpp prompt cache in RAM to avoid persisting potentially sensitive prompts.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/676e2139e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>676e2139e</a>

Database Migrations

This release alters high-volume tables (memory_units_bm25). Migrations run on startup, so allow extra time on large deployments.

e2f4a6c8b0d1 — Add attachments and document_attachments (inline retain attachments).·<code>attachments</code>medium <code>document_attachments</code>medium·<a href="https://github.com/vectorize-io/hindsight/pull/4077" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>#4077</a>
f3a5b7c9d1e2 — Drop the unused memory_units_bm25 materialized view.·<code>memory_units_bm25</code>high volume·<a href="https://github.com/vectorize-io/hindsight/pull/4357" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>#4357</a>

0.9.2

Features

Recall callers can now supply an explicit temporal window instead of relying on parsed time expressions.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3de41af86" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3de41af86</a>
Control plane now shows per-model staleness with consistent wording across views.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/97dbebb00" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>97dbebb00</a>
Automatic mental-model refreshes now enforce a minimum interval to prevent overly frequent refresh cycles.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2b54a1d3c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2b54a1d3c</a>
Text-in embedding providers can now use asymmetric query/passage prefixes to improve retrieval quality.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e256a7409" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e256a7409</a>
Knowledge-base tree now exposes each page’s refresh trigger, making refresh behavior easier to inspect.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0dd32a3d6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0dd32a3d6</a>
Add a GitHub Copilot subscription provider, so Hindsight can run its LLM lanes on a Copilot plan.·<a href="https://github.com/dudujuju828" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dudujuju828</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1d9a6a381" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1d9a6a381</a>
Expose the knowledge base as native MCP tools, so an agent can browse, search and maintain its pages over MCP instead of falling back to HTTP.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6582e26ef" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6582e26ef</a>

Improvements

Retain processing uses less memory and handles large batches more efficiently by streaming sub-batch splitting.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/634312795" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>634312795</a>
Mental model deltas are stored as verbatim Markdown blocks for more faithful, readable model change tracking.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fe5c25d64" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fe5c25d64</a>
Batch retain is routed through batch-capable multi-LLM handling for better throughput and provider compatibility.·<a href="https://github.com/handnewb" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@handnewb</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7f7d9c133" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7f7d9c133</a>
Database write overhead is reduced by disabling row counting when min_rows=0 and by interpreting 0 as 'off'.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/94815f5d0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>94815f5d0</a>
Engine now serves addressed document/chunk/entity reads from the backing store, improving read consistency.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7c5646436" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7c5646436</a>
Mental-model refresh operations now record what changes were made, improving auditability and debugging.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/300c546c5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>300c546c5</a>
CLI output is now non-interactive-friendly by disabling ANSI color and spinners when not running in a TTY.·<a href="https://github.com/yossiovadia" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@yossiovadia</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b7c65fbb2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b7c65fbb2</a>
Vector index creation is now proportional to bank size instead of always creating three per bank, reducing DB bloat.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/edd0d0c5b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>edd0d0c5b</a>
Retain and update_memory can now optionally resolve entities via a dedicated flag, enabling more controlled entity handling.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/df8ac42b5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>df8ac42b5</a>
Maintenance cross-tenant sweeps scale with tenant count to reduce unnecessary work on large deployments.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3770d62e3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3770d62e3</a>
Worker polling uses a pooled DB connection per cycle with consolidated session setup, improving throughput.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/32b90cc98" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>32b90cc98</a>
The bank list endpoint is now paginated.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6692e38c8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6692e38c8</a>
Background worker runs are now traced and join the caller's trace, giving end-to-end visibility into async work.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/08a119eeb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>08a119eeb</a>

Bug Fixes

Consolidation now avoids retrying an entire batch when only some LLM calls fail, improving reliability of batch runs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ad6312a51" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ad6312a51</a>
Retain now enforces a memory budget (rather than per-document limits) to prevent runaway memory usage on large inputs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e65973b1d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e65973b1d</a>
Consolidation claims are serialized per bank within a batch to prevent conflicts and inconsistent results.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/85bd23d50" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>85bd23d50</a>
Knowledge pages keep their intended scope reliably and trigger updates no longer reset it unexpectedly.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/99a319513" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>99a319513</a>
Entity resolution no longer merges entities based only on history-matched names, reducing incorrect merges.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/92695c6e5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>92695c6e5</a>
Retain retries and fails clearly when fact extraction encounters schema drift, instead of silently producing bad data.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d8a71c313" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d8a71c313</a>
Reflect runs now fail if no answer is produced, preventing placeholder memories from being stored.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f4a936950" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f4a936950</a>
Recall now skips over-budget facts instead of stopping early, and avoids returning empty matches.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1f5006583" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1f5006583</a>
If llama.cpp is missing, the system now reports the configuration problem instead of looping on connection errors.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bdee2bc88" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bdee2bc88</a>
Embedding profile env files are now read as UTF-8 to avoid failures with non-ASCII characters.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/86675983b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>86675983b</a>
Batch recovery is now correctly tied to the account that submitted the batch, preventing cross-account mixups.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6ff6dc692" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6ff6dc692</a>
Provider content-policy refusals during retain are treated as permanent failures rather than endlessly retried.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b81a3742b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b81a3742b</a>
Control plane: clearing the memories query no longer closes the search view unexpectedly.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9ef1f1b84" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9ef1f1b84</a>
Re-retain now correctly deletes chunks that were removed when content is reduced, preventing stale data from lingering.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/801f4910e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>801f4910e</a>
Query analyzer no longer misinterprets lone four-digit numbers as years.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e20bb290f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e20bb290f</a>
Knowledge tree writes are serialized to prevent write conflicts and corruption under concurrency.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ea9efa860" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ea9efa860</a>
CLI now exits with a non-zero status when configured with an invalid API URL, making failures script-friendly.·<a href="https://github.com/Alan5168" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Alan5168</a>·<a href="https://github.com/vectorize-io/hindsight/commit/71029fb81" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>71029fb81</a>
Retain strict-schema behavior is now honored consistently for batch processing.·<a href="https://github.com/kamilfurtak" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@kamilfurtak</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2bba17ee4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2bba17ee4</a>
Bank configuration is validated and persisted atomically to prevent partial or inconsistent config saves.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2e0af7550" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2e0af7550</a>
Consolidation now respects the configured temperature setting when generating consolidated results.·<a href="https://github.com/lusoris" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@lusoris</a>·<a href="https://github.com/vectorize-io/hindsight/commit/31cb1c2c8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>31cb1c2c8</a>
Retain now fails closed on malformed memory-defense policies instead of skipping screening.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/400fd3684" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>400fd3684</a>
Mental model refresh now removes references to facts that no longer exist, preventing stale citations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ba97f8585" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ba97f8585</a>
Misconfigured retain settings now fail loudly instead of silently falling back to defaults.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cc2dd3945" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cc2dd3945</a>
Ollama free-form calls now use the API path that honors num_ctx, improving context-window correctness.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2409c2d5a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2409c2d5a</a>
Voyage embeddings preserve asymmetric query/passage behavior to maintain retrieval quality.·<a href="https://github.com/Tosko4" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Tosko4</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4d03f7d48" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4d03f7d48</a>
Knowledge-base page staleness is now computed per scope rather than from the bank watermark, improving accuracy.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a5d00660b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a5d00660b</a>
Embedding configuration now inherits unspecified LLM settings instead of overwriting them with defaults.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e4e5f8b28" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e4e5f8b28</a>
Recall budget limits now apply all the way through vector-index querying, improving predictability of results.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/31c1aaf21" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>31c1aaf21</a>
Recall performance is improved by avoiding inefficient query plans on nested observation graph lookups.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5f137bf39" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5f137bf39</a>
Embedded daemon/UI lifecycle is hardened to reduce startup/shutdown errors and improve stability.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d98990b46" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d98990b46</a>
Consolidation preserves source dates when observations are merged, improving timeline accuracy.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2e2dfe130" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2e2dfe130</a>
Null metadata values are dropped during retain and recall to prevent invalid metadata from propagating.·<a href="https://github.com/NovaLux12" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@NovaLux12</a>·<a href="https://github.com/vectorize-io/hindsight/commit/19318ac08" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>19318ac08</a>
Secret redaction uses ASCII token boundaries so secrets adjacent to CJK text are properly detected and removed.·<a href="https://github.com/oldnicke" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@oldnicke</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e181fb75c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e181fb75c</a>
Mental models now ensure only one refresh is queued at a time, preventing refresh backlogs and duplication.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d69c53739" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d69c53739</a>
Knowledge-base page triggers are now patched (not replaced) on create/update, preserving existing trigger settings.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b64943d19" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b64943d19</a>
List endpoints for mental models and directives now return a correct total count for pagination.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/803a45171" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>803a45171</a>
Automatic cache affinity is disabled for Azure OpenAI to avoid routing issues and instability.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7850efcef" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7850efcef</a>
Memory updated_at is now refreshed on all writes that change a memory, improving freshness tracking and sync behaviors.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b919b97df" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b919b97df</a>
Retention sweep is now batched to prevent it from stalling foreground queries.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0480f171e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0480f171e</a>
Recall with long BM25 queries keeps the most selective terms, improving relevance and avoiding degraded search results.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a37257ede" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a37257ede</a>
Retain writes keep entity postings and witness coverage consistent by applying them together in one write group.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f660a4ad8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f660a4ad8</a>
A mental model's last_refreshed_at records when the refresh finished again, not the source-data watermark, which is now carried by the new last_memory_seen_at. Clients testing staleness against last_memory_write_at should compare last_memory_seen_at.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8fbdc6bf7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8fbdc6bf7</a>
Maintenance skips a schema under concurrent schema change instead of deadlocking against it.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/435f1640b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>435f1640b</a>
Vertex AI's EU and US regional endpoints work again instead of returning 404.·<a href="https://github.com/ferrastas" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ferrastas</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3e6a812f7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3e6a812f7</a>
The embedded daemon no longer flashes console windows on Windows.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3f14672ea" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3f14672ea</a>

0.9.1

Features

Add per-bank store capability checks, including the ability for a store to mark a bank as read-only (close it to writes).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6c5857813" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6c5857813</a>
Allow selected HTTP request headers to be forwarded to extensions.·<a href="https://github.com/rares-mollie" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rares-mollie</a>·<a href="https://github.com/vectorize-io/hindsight/commit/27d4386de" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>27d4386de</a>
Add asynchronous document export for bank transfers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/00b520e59" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>00b520e59</a>
Improve bank import/export by preserving the Knowledge Pages tree and rebuilding related search state on import.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fd294227c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fd294227c</a>
Make all bank configuration fields exportable and importable via bank templates.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3e3e3f372" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3e3e3f372</a>
Add a new xAI OAuth LLM provider for using LLM lanes with a SuperGrok subscription.·<a href="https://github.com/JoshFunnell" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@JoshFunnell</a>·<a href="https://github.com/vectorize-io/hindsight/commit/82852c522" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>82852c522</a>
Add an opt-in forced-tool mode to produce structured outputs when using LiteLLM providers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7b35d2c6f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7b35d2c6f</a>

Improvements

Restore server-side prompt caching when using load-balanced OpenAI-compatible backends.·<a href="https://github.com/JoshFunnell" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@JoshFunnell</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e62015cbf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e62015cbf</a>
Speed up recall by making temporal extraction significantly faster without changing results.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e8c42f2a7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e8c42f2a7</a>
Speed up recall scoring by evaluating observation expansion as sets instead of per-candidate rows.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e6fb5d479" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e6fb5d479</a>
Improve recall efficiency by reusing entity IDs already returned in results to avoid redundant fetches.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/00acde015" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>00acde015</a>
Reduce large entity-pruning sweeps by processing entity pruning through a queue.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/681a79e6b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>681a79e6b</a>
Make graph maintenance job submission smarter by deduplicating against running jobs as well as pending ones.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a763109d8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a763109d8</a>

Bug Fixes

Prevent recall from crashing when given extreme relative date offsets in queries.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/423e25db4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>423e25db4</a>
Ensure retrieved evidence is never dropped when synthesis is forced during reflection.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/07aec3b95" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>07aec3b95</a>
Fix document statements being incorrectly shared across banks by scoping them to the correct bank.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/da8077ade" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>da8077ade</a>
Prevent lost turns when appending to the same document concurrently.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/11a4eda80" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>11a4eda80</a>
Fix batched file uploads so each file gets a unique storage key.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/45713adcc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>45713adcc</a>
Fix markdown table rendering in structured documents.·<a href="https://github.com/dragonkid" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dragonkid</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e9a14da69" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e9a14da69</a>
Fix knowledge base search errors on deployments without native text-search backends.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/18bff79ae" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>18bff79ae</a>
Fix Knowledge Pages search to use PGroonga when configured, improving correctness and reliability.·<a href="https://github.com/JiehoonKwak" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@JiehoonKwak</a>·<a href="https://github.com/vectorize-io/hindsight/commit/81b58934d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>81b58934d</a>
Add a DB-independent liveness probe so slow databases don’t cause pods to restart unnecessarily.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/00bad1711" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>00bad1711</a>
Validate UUID inputs for entity and observation-history endpoints to prevent bad requests from triggering server errors.·<a href="https://github.com/Alan5168" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Alan5168</a>·<a href="https://github.com/vectorize-io/hindsight/commit/862a77c1a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>862a77c1a</a>
Fix OpenAI/LLM reasoning handling by preserving literal inline <think> text and honoring configured reasoning effort.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/39ee97a61" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>39ee97a61</a>
Fix Llama.cpp requests so extra request fields (extra_body) are correctly passed through.·<a href="https://github.com/handnewb" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@handnewb</a>·<a href="https://github.com/vectorize-io/hindsight/commit/650da8c1e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>650da8c1e</a>
Make Ollama “think” behavior configurable via extra request fields (extra_body).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3a4b0214f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3a4b0214f</a>
Prevent reranking failures/timeouts by batching FlashRank passage scoring instead of using an unbounded single pass.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3e1b4611c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3e1b4611c</a>
Prevent bank deletion deadlocks involving vector index schema changes during concurrent deletes.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d733772e3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d733772e3</a>
Validate bank configuration value types to prevent misconfigurations from wedging background tasks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2cf31d7fb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2cf31d7fb</a>
Improve transfer import handling by rejecting invalid import ZIPs with a clear 400 error explaining how to fix it.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d506641dc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d506641dc</a>
Fix whole-bank import to assign fresh internal IDs to avoid collisions.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d7c33fdea" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d7c33fdea</a>
Fix document upload cleanup so failed uploads are correctly deleted.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/78f1a0ef0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>78f1a0ef0</a>
Avoid database lock issues by using a consistent lock order when inserting memory links.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/83a080f90" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>83a080f90</a>
Fix long-running or stuck mental-model delta operations by tracing the call and decoupling its completion cap.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/500ab70f1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>500ab70f1</a>
Fix consolidation after multi-round drains by refreshing all affected mental models.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/64ede3617" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>64ede3617</a>
Fix consolidation batching so sibling tag groups are canceled when a batch fails, preventing cascading stuck work.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dca002551" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dca002551</a>
Fix pending consolidation statistics by removing memories that have permanently failed.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dbe0ffb98" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dbe0ffb98</a>
Fix embed daemon shutdown detection to use actual port occupancy instead of an unreliable health probe.·<a href="https://github.com/Alan5168" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Alan5168</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c094ac27d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c094ac27d</a>

0.9.0

Features

Add per-bank toggles to enable/disable temporal search, graph expansion, and reranking during recall.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d3946f17c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d3946f17c</a>
Allow configuring a per-budget cap on how many candidates the reranker considers during recall.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/359e619a4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>359e619a4</a>
Add a reranker failover chain so recall can fall back across multiple reranker configurations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/76d8ba8a5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>76d8ba8a5</a>
Add configurable locale detection for date parsing in the query analyzer.·<a href="https://github.com/yufanw03" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@yufanw03</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f2ae61eda" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f2ae61eda</a>
Add support for the OpenAI Responses API via a new openai-responses LLM provider.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/55883dc51" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>55883dc51</a>
Add a generic per-input token cap for embeddings across providers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8e953c230" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8e953c230</a>
Allow per-operation overrides of extra LLM request body fields via configuration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cac55feda" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cac55feda</a>
Introduce Knowledge Pages: client-managed knowledge content with Control Plane UI and hindsight fs CLI management.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/218e6d34b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>218e6d34b</a>
Add tools to troubleshoot mental model refreshes, including dry-run mode and trace retention.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/06e9c7054" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>06e9c7054</a>
Surface structured output for reflect/mental-model operations in the Control Plane.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4278f0989" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4278f0989</a>
Introduce Hindsight Coding Agents: harness-pluggable long-term memory for coding agents.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b5d8439c8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b5d8439c8</a>
Add a local daemon mode for Coding Agents and let users choose the server during installation.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e1b3d438e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e1b3d438e</a>
Add --import-conversations to Coding Agents to migrate/import conversations from older per-agent plugins.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/17b7f46ae" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>17b7f46ae</a>
Add a headless CLI tool to ingest/sync an Obsidian vault (hindsight-obsidian-sync).·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/93fa0b016" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>93fa0b016</a>
Add a recall option to prefer returning observations (via OpenClaw integration).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d19f54c77" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d19f54c77</a>
Allow agent_knowledge_recall (Agent SDK) to request source chunks alongside results.·<a href="https://github.com/chethanuk" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@chethanuk</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cd4064939" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cd4064939</a>
Add support for custom OCR headers in the file parser.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f61d383ac" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f61d383ac</a>

Improvements

Improve security and reliability of outbound webhooks by hardening delivery destinations and response handling.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ad85affb1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ad85affb1</a>
Add Hermes-branded bank templates grounded in real Hermes user stories.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5e557dbfc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5e557dbfc</a>
Require an explicit Coding Agents install target (e.g., install all or a specific harness) to avoid accidental installs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/05b55d20f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>05b55d20f</a>
Make the memories storage backend pluggable so deployments can swap storage implementations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b769045b6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b769045b6</a>
Add Control Plane indicators for documents being updated by an in-flight retain operation.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3868c8d05" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3868c8d05</a>
Show the originating coding agent’s logo on documents and memories in the Control Plane.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/aa38790dd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aa38790dd</a>
Improve the Control Plane UI design system and visual consistency.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bf6c12d55" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bf6c12d55</a>

Bug Fixes

Fix bank restore/import so label entities are correctly classified.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/53948468a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>53948468a</a>
Fix workers leaving behind in-progress operations by reconciling still-owned operations when a worker stops.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c15b565c8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c15b565c8</a>
Prevent scheduled mental-model refresh jobs from enqueueing duplicate work.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/afdea53a9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>afdea53a9</a>
Improve entity deduplication within a batch to avoid duplicate/variant entities being created.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/25a7237b1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>25a7237b1</a>
Fix recalls so created_after/created_before time windows also constrain graph expansion.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bda7ffd28" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bda7ffd28</a>
Fix embeddings so local providers honor configured query/document prompts.·<a href="https://github.com/jpmf33" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@jpmf33</a>·<a href="https://github.com/vectorize-io/hindsight/commit/468cc4b7d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>468cc4b7d</a>
Fix LLM retry behavior to release concurrency permits during backoff to avoid unnecessary throttling.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f6b3ce3e3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f6b3ce3e3</a>
Prevent unbounded log growth in the embedding daemon.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9d828cc7b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9d828cc7b</a>
Keep observations in the original source language during consolidation.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/42e8c53da" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>42e8c53da</a>
Prevent mental model documents from being overwritten by delta-window candidates.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ba5a4813b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ba5a4813b</a>
Ensure internal (non-HTTP) recall paths also enforce the query token cap.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5c15f28af" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5c15f28af</a>
Return a proper 422 error when recall requests specify invalid fact types.·<a href="https://github.com/tao943" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@tao943</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4b76d8be2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4b76d8be2</a>
Fix retention so metadata updates are applied even when memories are otherwise unchanged.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/751deb47b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>751deb47b</a>
Fix auto-splitting of overlong retention output by unifying the OutputTooLong error handling.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f572d8647" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f572d8647</a>
Show accurate last-write timestamps for banks and documents in the API.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1ce308f35" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1ce308f35</a>
Improve database connection handling so pooled connections aren’t held across embedding/LLM calls, reducing contention and timeouts.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/24825200b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>24825200b</a>
Retry embedding connect timeouts for TEI-based embedding providers.·<a href="https://github.com/jooneyp" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@jooneyp</a>·<a href="https://github.com/vectorize-io/hindsight/commit/417efb35d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>417efb35d</a>
Fix delete operations to sweep orphan entities even when no relink victims were enqueued.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/797faf798" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>797faf798</a>
Fix configuration errors to explicitly report which fields are disallowed when permissions are violated.·<a href="https://github.com/kubaodias" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@kubaodias</a>·<a href="https://github.com/vectorize-io/hindsight/commit/13cacf21a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>13cacf21a</a>
Fix Coding Agents session import attribution to use recorded working directory (cwd) rather than the session name.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d238d2f7d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d238d2f7d</a>
Fix Coding Agents Devin transcript ingestion by using node:sqlite and failing early if it’s missing.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/333812c85" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>333812c85</a>
Fix macOS installs so they work without requiring a Rust toolchain.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8de576b4b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8de576b4b</a>

0.8.6

Features

Control plane: add document tag filtering and a unified facet chip UI for browsing memories.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3a1841c42" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3a1841c42</a>
Reflect: add an option to apply directives across all scopes (bypass directive tag scoping) when needed.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6a460d2c9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6a460d2c9</a>
Retain: detect and report documents that produce zero extracted facts at write time.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9452ac29d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9452ac29d</a>
Configuration: allow per-operation overrides of LLM reasoning_effort.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b1a0ef5f7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b1a0ef5f7</a>
Temporal parsing: add Russian temporal period rules for better date/period understanding.·<a href="https://github.com/dimonnld" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dimonnld</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4724f26d3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4724f26d3</a>
Configuration: make embedding thresholds configurable.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ada3329bb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ada3329bb</a>
Control plane: display the API version in the sidebar.·<a href="https://github.com/handnewb" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@handnewb</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7a9ea7058" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7a9ea7058</a>
Engine: add a bulk API to delete multiple memory units in one operation.·<a href="https://github.com/chrislatimer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@chrislatimer</a>·<a href="https://github.com/vectorize-io/hindsight/commit/64fe5e81f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>64fe5e81f</a>
API/UI: filter memory lists by linked entity and add an entity timeline view.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c41ad9bd7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c41ad9bd7</a>
Extensions: support extension-owned, bank-scoped tables with automatic provisioning.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/57c18bc29" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>57c18bc29</a>
Configuration: allow per-bank overrides for storing document text (store_document_text).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6a0b85f10" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6a0b85f10</a>
TypeScript client: support custom HTTP headers on requests.·<a href="https://github.com/menelsystemsbot" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@menelsystemsbot</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dbf3b9d9b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dbf3b9d9b</a>
Engine: add created_before filtering to list_memory_units to query memories by ingest age.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/441cf2272" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>441cf2272</a>
Observability: a stalled /health check now self-diagnoses — it reports whether the event loop is blocked or the database connection pool is exhausted.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/489d55fa6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>489d55fa6</a>
Added a GitHub Copilot CLI integration that recalls memory before a session and retains a summary after.·<a href="https://github.com/ScottGuymer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ScottGuymer</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6500944c7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6500944c7</a>

Improvements

Reflect: fail fast on unusable tool calls instead of attempting to salvage leaked text, improving correctness and safety.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/678ca0e90" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>678ca0e90</a>
Performance: reduce redundant graph seeding and UUID scans for faster operation on large datasets.·<a href="https://github.com/zommiommy" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@zommiommy</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b475f5cca" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b475f5cca</a>
Retain: reject misplaced file retain metadata to prevent invalid ingestion requests.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1fa2de332" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1fa2de332</a>
Workers: per-type slot settings are now named HINDSIGHT_API_WORKER_<TYPE>_RESERVED_SLOTS, since they reserve a guaranteed minimum rather than cap concurrency. The old *_MAX_SLOTS names keep working but log a deprecation warning.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/979999651" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>979999651</a>
Python 3.14 is now supported.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a514d3962" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a514d3962</a>

Bug Fixes

Control plane: dark mode styling now correctly follows the configured dark theme class.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/94f4adfbe" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>94f4adfbe</a>
Python and other clients: expose mental-model query controls (and async retain operation_id) so callers can tune queries and track async operations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/70c09adcf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>70c09adcf</a>
Reflect: mental-model scoping is now applied correctly for empty scopes.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c5643fdf5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c5643fdf5</a>
Graph maintenance: fix a race between enqueuing maintenance work and worker draining to prevent missed/duplicated queue work.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/40d2b7f6b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>40d2b7f6b</a>
Oracle support: fix full-text/vector and audit/log related SQL issues to improve compatibility and reliability on Oracle.·<a href="https://github.com/dcbouius" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dcbouius</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4f4c2988e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4f4c2988e</a>
Tracing/observability: provider responses are now safely serialized even when unvalidated.·<a href="https://github.com/oldnicke" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@oldnicke</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b8e1524a1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b8e1524a1</a>
TEI embeddings/reranking: automatically retry on HTTP 429 backpressure to reduce transient failures.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/91160f3ba" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>91160f3ba</a>
Workers: prevent wedged retain jobs from occupying worker slots indefinitely.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8133c5ab7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8133c5ab7</a>
LLM integrations: reasoning_effort is now consistently sent across tool paths/providers (including Codex).·<a href="https://github.com/merlinr68" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@merlinr68</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9a1ba951f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9a1ba951f</a>
Batch retain: improve retry/recovery so parent jobs can be re-run and stranded work is reconciled after failures.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ac4df7eb8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ac4df7eb8</a>
Transfers/import: preserve consolidation lifecycle state when importing an entire bank.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/af196287e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>af196287e</a>
Local embeddings/reranking: default to CPU on Apple Silicon to avoid an MPS memory leak.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2620a2a3f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2620a2a3f</a>
Claude Code integration: reflect tool calls now work and honor the configured model.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8f19087c2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8f19087c2</a>
Control plane: audit-log and observations tabs now respect resolved per-bank configuration, and observations inheritance is preserved.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ed248447e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ed248447e</a>
Library import: avoid dotenv side effects when importing Hindsight as a dependency.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5792b2b86" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5792b2b86</a>
Consolidation: stop emitting an unsupported maxItems field that broke AWS Bedrock consolidation.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c908fade1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c908fade1</a>
Retain/dry run: return free-form entities from dry-run extraction and accept a text alias in fact extraction inputs.·<a href="https://github.com/oldnicke" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@oldnicke</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f7ff5341f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f7ff5341f</a>
Graph: edited/restored memories are now re-queued for relinking so links stay up to date.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/73b575c7a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>73b575c7a</a>
Curation: preserve causal links across edit and invalidate/restore operations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0e5aa8896" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0e5aa8896</a>
Auth: ensure bank writes are authorized before provisioning occurs.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0f47c7a8d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0f47c7a8d</a>
Helm/Kubernetes: ensure workers use the correct API port override to avoid service-discovery failures.·<a href="https://github.com/Fyko" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Fyko</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d29f4703e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d29f4703e</a>
Mental models: fix delta refresh watermarking so refreshes anchor to the newest processed memory.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/af8cf142d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>af8cf142d</a>
Retain: async retries are now idempotent via caller-supplied operation_id.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/31218127e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>31218127e</a>
CLI: preserve HTTP 400 error details to make failures easier to diagnose.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1ff09ccf9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1ff09ccf9</a>
LLM endpoints: normalize LM Studio/Ollama base URLs to /v1 for compatibility.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/47a7d4380" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>47a7d4380</a>
Retain/linking: fix within-batch cosine similarity and adjust causal-target offsets to improve link quality.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7b161740d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7b161740d</a>
Backups: fix restore schema compatibility issues.·<a href="https://github.com/oldnicke" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@oldnicke</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3cc371382" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3cc371382</a>
Retain: oversized append-only documents are recognized as appends again, so re-ingesting long histories no longer re-extracts everything from scratch.·<a href="https://github.com/Korayem" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Korayem</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a6c875156" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a6c875156</a>
Retain: fix a database deadlock where flushing statistics took a second connection while the first still held uncommitted row locks, which could hang a retain indefinitely (notably on Oracle, where no deadlock error is raised).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6d5157575" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6d5157575</a>

Other

Zapier: remove the memoryDefenseTriggered trigger (gated capability) from the integration surface.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e57765e01" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e57765e01</a>

0.8.5

Features

Add opt-in request dumps for rejected (4xx) LLM calls to make diagnosing provider errors easier.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/be6caf9dc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>be6caf9dc</a>
Add an optional fail-on-extraction-errors mode for retain(), allowing stricter handling when fact extraction fails.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ec3b415c4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ec3b415c4</a>
Add tag-based filtering to memory listing endpoints (list_memories and list_memory_units).·<a href="https://github.com/superafun" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@superafun</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c1fadc008" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c1fadc008</a>
Allow deleting terminal bank operations via the API (with control-plane support).·<a href="https://github.com/chethanuk" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@chethanuk</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dcef72480" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dcef72480</a>
Allow overriding audit logging settings per bank.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0d2dbe756" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0d2dbe756</a>
Add support for pg0:// URLs carrying optional user/password credentials for easier configuration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0c38d46ee" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0c38d46ee</a>
Add a configurable cap on planner parallelism to reduce connection pool pressure on busy deployments.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/347b9c23c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>347b9c23c</a>
Support Anthropic Message Batches (batch API) for discounted token usage.·<a href="https://github.com/hb-cam" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@hb-cam</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7f2df54e0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7f2df54e0</a>
Add Anthropic prompt caching support (including carrying cache markers in batch system prompts) to reduce repeated prompt costs.·<a href="https://github.com/hb-cam" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@hb-cam</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7c3a5619f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7c3a5619f</a>
Add step-by-step context caching for Gemini tool loops to improve efficiency across multi-step tool interactions.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/81aa4979b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>81aa4979b</a>

Improvements

Add bank attribution for remote reranker calls to improve per-bank observability and accounting.·<a href="https://github.com/Jordan-Jarvis" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Jordan-Jarvis</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8a7a70b82" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8a7a70b82</a>

Bug Fixes

Recover from malformed LLM JSON responses using a last-resort repair fallback, reducing failures on structured outputs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a23187a45" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a23187a45</a>
Ensure per-operation strict JSON schema handling works correctly and respects explicit per-call opt-out.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9fe339dfb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9fe339dfb</a>
Improve compatibility with OpenAI-style tool calling by emitting canonical tool-result messages and preserving required tools for custom endpoints.·<a href="https://github.com/Jordan-Jarvis" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Jordan-Jarvis</a>·<a href="https://github.com/vectorize-io/hindsight/commit/434dbee64" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>434dbee64</a>
Fix Claude Code LLM calls with max_turns=1 by preventing built-in tools from interfering with single-turn requests.·<a href="https://github.com/peter216" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@peter216</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b82fb603c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b82fb603c</a>
Increase reliability of retain() fact extraction by handling retries/edge cases (zero retry budgets, boundary batches, degenerate text) and preserving fact alignment.·<a href="https://github.com/chethanuk" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@chethanuk</a>·<a href="https://github.com/vectorize-io/hindsight/commit/912f8e22d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>912f8e22d</a>
Make retain() more robust by reasserting resolved entities before linking and standardizing extracted entities as plain strings.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0679d38e8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0679d38e8</a>
Preserve bank attribution and refresh search vectors during memory curation, improving correctness of curated memories.·<a href="https://github.com/Jordan-Jarvis" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Jordan-Jarvis</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6ba98c040" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6ba98c040</a>
Fix audit coverage so memory updates are properly recorded when auditing is enabled.·<a href="https://github.com/handnewb" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@handnewb</a>·<a href="https://github.com/vectorize-io/hindsight/commit/000fb9ddb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>000fb9ddb</a>
Repair vector index coverage per bank after restore/upgrade to prevent missing or incomplete search results.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bd853be35" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bd853be35</a>
Improve stability and correctness of background operation processing (retry budgeting, completing successful operations, bounding terminal history, and isolating side-effect failures).·<a href="https://github.com/handnewb" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@handnewb</a>·<a href="https://github.com/vectorize-io/hindsight/commit/234f5a062" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>234f5a062</a>
Fix delta refresh watermark handling so no-op refreshes still advance and don’t cause repeated processing.·<a href="https://github.com/SunneeYang" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@SunneeYang</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c1fae2ae1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c1fae2ae1</a>
Fix PostgreSQL startup to honor credentials embedded in the database URL.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/820019f3c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>820019f3c</a>
Fix database migrations to correctly handle percent-encoded database URLs and install maintenance routines in the configured schema.·<a href="https://github.com/Jordan-Jarvis" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Jordan-Jarvis</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8bd9ce194" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8bd9ce194</a>
Improve date parsing by selecting the strongest match and fixing day+month+year interpretation (avoids collapsing to whole-month dates).·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d28b85273" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d28b85273</a>
Fix crashes and incorrect results in Chinese temporal extraction (including year-0 edge cases).·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5f1a86765" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5f1a86765</a>
Prevent oversized embedding requests from failing by truncating inputs before embedding.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/263eba134" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>263eba134</a>
Improve consolidation robustness by requesting JSON dedup decisions and normalizing/handling invalid dedup actions safely.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6d82c8a55" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6d82c8a55</a>
Fix memory browsing endpoints to return associated metadata.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5cc1482a7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5cc1482a7</a>
Preserve JSONB and timestamp provenance during transfers to avoid losing data fidelity.·<a href="https://github.com/Korayem" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Korayem</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d7c32f963" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d7c32f963</a>
Make LLM trace writing safer by avoiding writes during startup/shutdown races and gating on lifecycle state.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3fb33b987" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3fb33b987</a>

0.8.4

Features

Added Requesty as an OpenAI-compatible LLM provider option.·<a href="https://github.com/Thibaultjaigu" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Thibaultjaigu</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6eb85570a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6eb85570a</a>
Recall can now return structured per-stage scores and supports two-level min_scores filtering for finer result control.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/758f346d3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>758f346d3</a>
Mental models can now be refreshed on a cron schedule automatically.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dae18b1fa" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dae18b1fa</a>
Multi-LLM setups now support configuring LiteLLM Router and Vertex service account keys.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/47992d843" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>47992d843</a>
Multi-LLM configurations can now set Vertex AI project and region per indexed member.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4fe477eaa" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4fe477eaa</a>
Added multi-LLM failover and round-robin selection via indexed configuration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f7c7a62e5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f7c7a62e5</a>
Added Atlas Cloud as an OpenAI-compatible LLM provider option.·<a href="https://github.com/lucaszhu-hue" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@lucaszhu-hue</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f8d277697" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f8d277697</a>
Recall can now prefer observations to avoid returning raw facts that have been superseded.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5f0b71551" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5f0b71551</a>
Recall supports configurable recency decay (linear, exponential, or none) to tune ranking toward recent memory.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a2166ee4f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a2166ee4f</a>
Local reranking can now accelerate on Intel XPU where available.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1a09a9ccc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1a09a9ccc</a>
Added an Aider integration to bracket sessions and persist memory more cleanly.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/aab703207" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aab703207</a>
Added an Eve (Microsoft Agent Framework) MCP connection helper for easier integration.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d0b77f5be" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d0b77f5be</a>
Added a Windsurf (Codeium) integration via MCP.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7194f98b1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7194f98b1</a>
Added a GitHub Copilot (VS Code) integration via MCP.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/91bf32842" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>91bf32842</a>

Improvements

Memory explorer now shows full memory details for easier inspection and debugging.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f8ce15b9b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f8ce15b9b</a>
Bank stats are faster and more scalable, with a refresh option to force recomputation when needed.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d68f61896" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d68f61896</a>
LLM configuration now supports per-operation temperature control for more predictable behavior across different workflows.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a27754fb1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a27754fb1</a>
Reflect structured output will retry fewer times, reducing latency and avoiding runaway retries.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/85599f3ef" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>85599f3ef</a>
Standalone workers now warn when worker_id is missing or unstable, helping prevent misconfigured deployments.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/680305aea" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>680305aea</a>
Recall tracing now reports phase timing that matches total request duration more accurately.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9e06237e4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9e06237e4</a>
Token usage reporting now includes cached tokens and model “thoughts” tokens where available.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b4874672f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b4874672f</a>
MCP responses omit reflect directives_applied by default to reduce noise in traces.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/246803bcf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>246803bcf</a>
Control plane upload size limit is now configurable.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5543992d7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5543992d7</a>
Database migrations are faster and more flexible, including optional extension reconciliation and dropping an unused global vector index.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/51cb32896" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>51cb32896</a>

Bug Fixes

Batch fact extraction now honors the configured LLM temperature, making outputs consistent with your settings.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8ed49e438" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8ed49e438</a>
CLI explore now correctly handles header selection when displaying results.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/82afa7618" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>82afa7618</a>
Per-scope LLM timeouts and retry policies are now correctly applied to providers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/40fe7aac8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>40fe7aac8</a>
LiteLLM-backed providers now correctly apply configured default request headers.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5e73d5ff6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5e73d5ff6</a>
Dynamic banks now correctly inherit configured defaults.·<a href="https://github.com/devinkuhn" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@devinkuhn</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ef2e8ab7f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ef2e8ab7f</a>
Reflect now correctly parses JSON-wrapped responses from models.·<a href="https://github.com/xmh1011" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xmh1011</a>·<a href="https://github.com/vectorize-io/hindsight/commit/82b01ace5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>82b01ace5</a>
Trace-based token/cost accounting is preserved even when tool-call argument parsing fails.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/01eda5188" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>01eda5188</a>
Python and TypeScript SDK wrappers now correctly pass recall min_scores filtering options.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cce0a2cb3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cce0a2cb3</a>
Consolidation no longer drops items when a dedup action is missing; it defaults to keeping data.·<a href="https://github.com/koriyoshi2041" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@koriyoshi2041</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1c1cf4ce5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1c1cf4ce5</a>
Markitdown parser now correctly handles certain UTF-8 text files that begin with an ASCII prefix.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/74e82a3ea" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>74e82a3ea</a>
Database migration bootstrap now respects the configured vector extension.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/017b8d727" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>017b8d727</a>
Consolidation now keeps search vectors up-to-date for observations, improving recall quality and reliability.·<a href="https://github.com/qxxaa" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@qxxaa</a>·<a href="https://github.com/vectorize-io/hindsight/commit/21176f8ee" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>21176f8ee</a>
Embedding on Windows now reliably finds pythonw when installed alongside the API script.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/911d27fc5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>911d27fc5</a>
Retain append mode now correctly merges JSON arrays to preserve conversation-aware chunking.·<a href="https://github.com/qxxaa" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@qxxaa</a>·<a href="https://github.com/vectorize-io/hindsight/commit/78d32cd16" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>78d32cd16</a>
Control plane now shows documents that are uploaded but still pending processing.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/91e095afa" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>91e095afa</a>
PATCH bank no longer accidentally creates new banks.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a7d1f26f9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a7d1f26f9</a>
Dry-run extraction no longer creates banks as a side effect.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0673131a8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0673131a8</a>
Memory defense now shows the correct number of matched patterns.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8e66c397a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8e66c397a</a>
CLI pagination now correctly supports large limit/offset values.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/63a92bef5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>63a92bef5</a>
Gemini structured output prompts no longer duplicate schema instructions.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/199ae146a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>199ae146a</a>
List endpoints now reject negative limit/offset with a clear 422 error instead of a server error.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4db8a1236" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4db8a1236</a>
Reduced risk of graph maintenance queue deadlocks under concurrency.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cabcb3bb0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cabcb3bb0</a>
Recall can now accurately filter for untagged/global observations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0ba613c3c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0ba613c3c</a>
Async operations now return a clean 404 for missing banks instead of an internal database error.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/04703d215" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>04703d215</a>
Bank configuration writes now validate disposition_* ranges to prevent invalid settings.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/387c09e91" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>387c09e91</a>
Anthropic strict structured output is now produced more reliably by using tool_use instead of prompt-based injection.·<a href="https://github.com/eldar702" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@eldar702</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cbce93704" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cbce93704</a>
Bank stats no longer become stale after deletes/clears thanks to improved cache invalidation.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f21944d78" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f21944d78</a>
Bank stats cache invalidation no longer leaves stale results in some cases.·<a href="https://github.com/zupengwang" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@zupengwang</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ccd3eb24c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ccd3eb24c</a>
Retain chunking is now idempotent, preventing failures when structured chunk size settings increase.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ba5ddd59a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ba5ddd59a</a>

0.8.3

Features

Added OpenHands integration with native MCP configuration and built-in recall/retain rules.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/65862c4fe" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>65862c4fe</a>
Added Zed editor integration via an MCP context server with recall/retain rules.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/539101af3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>539101af3</a>
Added Continue.dev integration via an HTTP context provider.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c05ab9103" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c05ab9103</a>
Added Composio integration so Hindsight memory can be used as custom tools.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1c9ba0e65" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1c9ba0e65</a>
Added a Zapier app with actions and REST-hook triggers for automating workflows with Hindsight.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/359b2bc76" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>359b2bc76</a>
Added a dry-run fact extraction API endpoint to preview extraction results without saving them.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d382b340f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d382b340f</a>
Added optional MarkItDown-based OCR support for extracting text from documents.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5ee53c512" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5ee53c512</a>
Improved Chinese temporal query understanding for more accurate time-based searches.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d0c54560a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d0c54560a</a>
Added tool annotations (read-only/destructive hints) to MCP tools for safer client behavior.·<a href="https://github.com/yunanwg" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@yunanwg</a>·<a href="https://github.com/vectorize-io/hindsight/commit/27aa6bbf4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>27aa6bbf4</a>
Added support for the "shared" observation scope across consolidation and the Control Plane UI.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0a046f97a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0a046f97a</a>
Added support for exact tag matching (tags_match=exact) across the UI and client libraries.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2f075dede" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2f075dede</a>
Added Intel XPU detection to enable local embedding acceleration when available.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2fb2de1aa" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2fb2de1aa</a>

Improvements

Exposed additional operation/worker backlog metrics to make async processing health easier to monitor.·<a href="https://github.com/MattJackson" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@MattJackson</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b1fe23fbe" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b1fe23fbe</a>
Added Gemini service tier configuration options.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d68bd0742" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d68bd0742</a>
API responses now omit wire-safe null fields to reduce payload size.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e20a36c95" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e20a36c95</a>
Improved search recency scoring using effective-time fallback for better ranking of results.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3d6b19af5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3d6b19af5</a>
Parallelized tenant schema migrations to reduce migration time on multi-tenant deployments.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/460fc63d9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>460fc63d9</a>

Bug Fixes

Fixed retain chunking so oversized documents no longer lose content when split into multiple sub-batches.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/81865bf87" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>81865bf87</a>
Fixed MCP so custom tool instructions are applied correctly again.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f4bac2d41" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f4bac2d41</a>
MCP responses no longer include reflect tool/LLM traces by default, preventing unexpected extra output.·<a href="https://github.com/yunanwg" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@yunanwg</a>·<a href="https://github.com/vectorize-io/hindsight/commit/44972d321" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>44972d321</a>
Prevented hung LiteLLM calls from blocking forever by enforcing a hard timeout.·<a href="https://github.com/kubaodias" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@kubaodias</a>·<a href="https://github.com/vectorize-io/hindsight/commit/551932991" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>551932991</a>
Fixed bank listing so bank-config disposition and mission overlays are applied consistently.·<a href="https://github.com/PathKnower" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@PathKnower</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cb73790c2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cb73790c2</a>
Dry-run extraction now rejects empty/whitespace inputs and runs only after passing the precheck step.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a92e25bcf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a92e25bcf</a>
Fixed consolidation when the LLM returns single-value source_fact_ids so runs don’t fail unexpectedly.·<a href="https://github.com/haodonp" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@haodonp</a>·<a href="https://github.com/vectorize-io/hindsight/commit/94619ce52" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>94619ce52</a>
Fixed metric labeling for HTTP endpoints so bank IDs are templated correctly (avoids high-cardinality labels).·<a href="https://github.com/sireika" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@sireika</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4efa20472" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4efa20472</a>
Fixed provider quota reset behavior by deferring retries to avoid unnecessary retry storms.·<a href="https://github.com/oldschoola" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@oldschoola</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2b521c3a0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2b521c3a0</a>
Honored CODEX_HOME for locating Codex auth.json, fixing auth in custom home directories.·<a href="https://github.com/mdenil" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@mdenil</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0c9bc765c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0c9bc765c</a>
Fixed the Control Plane so the “shared” observation scope is selectable in the Add Document UI.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0ca0226d3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0ca0226d3</a>
Improved output sanitization by stripping malformed reasoning tags/blocks from non-structured outputs.·<a href="https://github.com/grimmjoww" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@grimmjoww</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7b17da7a0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7b17da7a0</a>

0.8.2

Features

Added support for observation scopes, including listing, filtering, visualization, and per-scope observation limits.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b08f43496" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b08f43496</a>
Added SIEM-focused enrichment fields to Memory Defense webhook events to improve downstream security alert context.·<a href="https://github.com/chrislatimer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@chrislatimer</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f304ce7e0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f304ce7e0</a>
Introduced reversible memory curation so memory units can be edited, invalidated, and reverted.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/de22b606e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>de22b606e</a>
Added per-bank provider cost attribution using the OpenAI "user" field.·<a href="https://github.com/sireika" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@sireika</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fb16fc4fd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fb16fc4fd</a>
Added a native Nous Portal LLM provider with OAuth authentication (no external CLI dependency).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/82c7df726" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>82c7df726</a>
Added a per-bank LLM connectivity probe to help verify provider configuration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0d55a9b78" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0d55a9b78</a>
Added Gemini Batch API support for retain fact extraction.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a942b1c81" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a942b1c81</a>
Added support for the Gemini embedding-2 model family (per-input embeddings).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/22ae72a90" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>22ae72a90</a>
Improved retain ingestion by chunking JSONL files on line boundaries to avoid splitting records.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4e7780e59" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4e7780e59</a>
Added an option in the UI to export a constellation as a shareable SVG poster.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0280b3486" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0280b3486</a>
Added a Cursor plugin providing Hindsight persistent memory integration.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/91d767cdc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>91d767cdc</a>
Added a pip-installable Cline integration package (hindsight-cline).·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/36e31c675" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>36e31c675</a>
Added a pip-installable Cursor CLI integration package (hindsight-cursor-cli).·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c6dd08944" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c6dd08944</a>
Added Hindsight memory integration for Microsoft Agent Framework (no MCP required).·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f5a6c300f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f5a6c300f</a>

Improvements

Added a local Control Center web app for embedded deployments.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4032b2791" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4032b2791</a>
Improved reflect synthesis to better respect directives and language rules in final outputs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/90ee101be" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>90ee101be</a>
Added support for selecting Amazon Bedrock service tier.·<a href="https://github.com/mobilinkd" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@mobilinkd</a>·<a href="https://github.com/vectorize-io/hindsight/commit/27cb1c684" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>27cb1c684</a>

Bug Fixes

Fixed the control-plane bank view to avoid double-loading graph data, improving performance and reducing redundant requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d81486ff9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d81486ff9</a>
Fixed per-scope observation limiting so a limit of 0 correctly prevents new observations from being created.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f6710963e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f6710963e</a>
Improved cancellation handling so abandoned recall/reflect operations can be reliably cancelled on disconnect.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/07c85da98" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>07c85da98</a>
Fixed a concurrency issue where model initialization could change the global Torch default dtype, ensuring consistent float32 behavior.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/30fb287d1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>30fb287d1</a>
Fixed webhook payloads to include previously missing fields.·<a href="https://github.com/chrislatimer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@chrislatimer</a>·<a href="https://github.com/vectorize-io/hindsight/commit/87448b161" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>87448b161</a>
Fixed PostgreSQL history storage by widening history bank_id to TEXT to prevent failures with longer IDs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/621ab7e66" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>621ab7e66</a>
Fixed the CLI to correctly parse get-memory responses.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/72d9881a6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>72d9881a6</a>
Fixed the control-plane meeting notes flow to drop empty messages that could fail locale validation.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8e6dc5fcd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8e6dc5fcd</a>
Improved rolling-deployment migration skipping to handle wrapped dependency-resolution errors more reliably.·<a href="https://github.com/bionicbutterfly13" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@bionicbutterfly13</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0afa046fc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0afa046fc</a>

0.8.1

Features

Add an API configuration flag to skip storing raw document text.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1296e9fc1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1296e9fc1</a>
Add an Oh-My-OpenAgent (OMO) integration for connecting Hindsight memory to OMO workflows.·<a href="https://github.com/dcbouius" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dcbouius</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6dc56498c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6dc56498c</a>
Add a Cline integration that hooks into lifecycle events to save and retrieve Hindsight memory.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/66e58a23a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>66e58a23a</a>
Add a Haystack integration to use Hindsight as a memory component in Haystack pipelines.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/394d66e60" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>394d66e60</a>
Add a Cursor CLI integration for capturing and using Hindsight memory from Cursor workflows.·<a href="https://github.com/Korayem" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Korayem</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dbfe83a2a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dbfe83a2a</a>

Improvements

Introduce an official Obsidian plugin to sync and use Hindsight memory from Obsidian.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b0f86f9c0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b0f86f9c0</a>
Package the Roo Code integration as an installable PyPI CLI (hindsight-roo-code).·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/644e37ac1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>644e37ac1</a>

Bug Fixes

Fix vector index behavior to avoid forcing vchordrq.probes settings on vchord indexes that don't support it.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/109e1bd95" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>109e1bd95</a>
Ensure database maintenance routines are installed correctly when using the public schema.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/95d77233b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>95d77233b</a>

0.8.0

Features

Add periodic background maintenance to reconcile consolidation state and enforce retention across tenants.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e77461762" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e77461762</a>
Add durable progress snapshots for long-running consolidation and batch retain operations, so status can be resumed/inspected reliably.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c94935bfa" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c94935bfa</a>
Enable LLM request tracing by default (with per-bank support) and retain traces for 1 day for easier debugging/observability.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f4a3329ce" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f4a3329ce</a>
Add semantic deduplication of near-duplicate observations during consolidation (enabled by default, except on Oracle).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8aa31edd4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8aa31edd4</a>
Store mental-model and observation history in dedicated database tables for better scalability and reliability.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7e1145c08" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7e1145c08</a>
Add a local ONNX embeddings provider so embeddings can be generated without a hosted embeddings API.·<a href="https://github.com/shoveller" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@shoveller</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b5a324b77" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b5a324b77</a>
Add whole-bank export/import for cross-instance migration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/602c9f55e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>602c9f55e</a>
Add document export/import between banks without re-running the LLM (reusing previously extracted results).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1d6d73bce" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1d6d73bce</a>
Add provider-agnostic prompt-prefix caching (default on) to reduce repeated LLM work for retain, consolidation, and reflect.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d7a3aa526" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d7a3aa526</a>
Add global support for sending extra provider request fields via HINDSIGHT_API_LLM_EXTRA_BODY.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/01296d8d5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>01296d8d5</a>
Honor HINDSIGHT_API_LLM_STRICT_SCHEMA across all JSON-schema capable LLM providers for stricter structured outputs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a3d3d42b3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a3d3d42b3</a>
Add Superagent safety middleware integration for safer agent execution.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b70830218" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b70830218</a>

Improvements

Improve client SDK trace visibility by exposing reflect tool/LLM call details in the Python and TypeScript wrappers.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0db70bb88" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0db70bb88</a>
Allow tuning recall behavior with configurable per-strategy retrieval boosts via environment configuration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/01134047d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>01134047d</a>
Allow tuning semantic recall sensitivity with a configurable minimum similarity threshold (HINDSIGHT_API_SEMANTIC_MIN_SIMILARITY).·<a href="https://github.com/zwcf5200" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@zwcf5200</a>·<a href="https://github.com/vectorize-io/hindsight/commit/aa024a5cd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aa024a5cd</a>
Avoid an unnecessary extra LLM call during reflect when a fresh mental model can be used directly.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c255d3552" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c255d3552</a>
Speed up and reduce load from bank statistics queries via caching and more efficient computation.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7683f2900" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7683f2900</a>
Improve visibility when audit logs or LLM requests are disabled by showing a clear "not enabled" splash in the control plane UI.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/283419280" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>283419280</a>
Improve OpenCode integration observability with clearer debug logging, endpoint reporting, and surfaced errors.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/796a9eff9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>796a9eff9</a>

Bug Fixes

Fix consolidation runs failing or truncating output by enforcing an explicit output token budget.·<a href="https://github.com/xmh1011" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xmh1011</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c2524473e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c2524473e</a>
Reduce slow/expensive temporal recall paths by limiting how many entries are scanned per fact type.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4c33a4e55" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4c33a4e55</a>
Fix pgroonga BM25 search failures by escaping query text properly.·<a href="https://github.com/xmh1011" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xmh1011</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6b8fc53d7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6b8fc53d7</a>
Preserve correct RRF (fusion) source ranks in retrieval traces/results.·<a href="https://github.com/zwcf5200" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@zwcf5200</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f62500193" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f62500193</a>
Prevent the API from hanging indefinitely at startup by failing fast when model initialization blocks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4f5003480" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4f5003480</a>
Fix recall and mental-model history support when using the Oracle database backend.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/23710f4a8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>23710f4a8</a>
Validate embedding vector dimensions before writing to pgvector to prevent storage/query errors.·<a href="https://github.com/ai-ag2026" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ai-ag2026</a>·<a href="https://github.com/vectorize-io/hindsight/commit/06c88e043" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>06c88e043</a>
Improve retain concurrency safety by rechecking freshness before extraction and serializing concurrent writes to the same document.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/23168ebf6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>23168ebf6</a>
Fix incorrect fact attribution during retain caused by bank routing key leakage.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d695611ad" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d695611ad</a>
Fix mental model creation failures by ensuring the bank exists before inserting the model.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/56b4271d9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>56b4271d9</a>
Fix external Postgres setups using vchord by adding required catalogs to the session search_path.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/049901802" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>049901802</a>
Improve Docker standalone diagnostics by providing a clear error when pg0 bind-mount permissions prevent startup.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/75a7c19d6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>75a7c19d6</a>
Improve compatibility with LLM servers that mishandle tool_choice="required" by falling back to a safer tool-choice mode.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e30f8af14" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e30f8af14</a>
Fix Bedrock IAM authentication with the LiteLLM reranker by making the reranker API key optional.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3c8ca47dd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3c8ca47dd</a>
Expose retain outcome metadata so users can see what happened during a retain operation.·<a href="https://github.com/xmh1011" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xmh1011</a>·<a href="https://github.com/vectorize-io/hindsight/commit/831f0efa1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>831f0efa1</a>
Make bank config PATCH persist correctly even for banks that have never retained data yet.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a809547aa" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a809547aa</a>
Prevent fact extraction prompt formatting from breaking extraction by removing Markdown bold markers.·<a href="https://github.com/Oxygen56" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Oxygen56</a>·<a href="https://github.com/vectorize-io/hindsight/commit/50b7eda2a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>50b7eda2a</a>
Improve recall stability/performance by gating VectorChord BM25 usage and applying per-source candidate caps.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/70d98c7a2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>70d98c7a2</a>
Fix control plane UI localization issues for operations and graph legends.·<a href="https://github.com/MapleEve" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@MapleEve</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a14ce623c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a14ce623c</a>
Improve transfer import reporting by including mental_model_history counts in CLI summaries.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3346363d2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3346363d2</a>

0.7.2

Features

Added Google ADK integration to connect Hindsight memory with Google ADK agents.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c032a74f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c032a74f</a>
Added Flowise integration with Hindsight memory tools.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/41ad2b55" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>41ad2b55</a>
Added Fireworks AI as a batch inference provider.·<a href="https://github.com/Fyko" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Fyko</a>·<a href="https://github.com/vectorize-io/hindsight/commit/537b2812" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>537b2812</a>
Added Roo Code integration via MCP (including rules support) to connect Roo Code with Hindsight memory.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bf6b9026" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bf6b9026</a>
Added Vapi webhook integration to send voice-agent interactions into Hindsight memory.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dde133da" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dde133da</a>
Added Gemini Spark integration via MCP.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7cdacc4b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7cdacc4b</a>

Improvements

Improved graph maintenance performance for vector search seeding (faster ANN maintenance work).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/99c7367f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>99c7367f</a>
Improved vector search correctness/tuning by using cosine opclass for vchord ANN and applying backend-specific tuning settings.·<a href="https://github.com/isac322" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@isac322</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e4686b92" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e4686b92</a>
Reduced consolidation retry backoff to recover faster from transient failures.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f49b85c0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f49b85c0</a>

Bug Fixes

Fixed a control-plane i18n redirect loop by pinning the Next.js version.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/201f5d7c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>201f5d7c</a>
Limited native ML thread pools to available CPU cores to prevent resource overuse and instability.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0a2ee845" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0a2ee845</a>
Fixed PostgreSQL upgrade issues for v0.7.x deployments.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b7f267b0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b7f267b0</a>
Fixed backup/restore to include previously missing tables.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/867b7b4a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>867b7b4a</a>
Made memory consolidation more reliable under concurrency by improving scope-aware locking/dispatch and atomic submission behavior.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/08ce8176" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>08ce8176</a>
Fixed retention of oversized documents to prevent incorrect chunk indexing and loss of full document content.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/364ccf17" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>364ccf17</a>
Improved retain/recall robustness for unusual Unicode inputs (special-token literals and lone surrogates).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4bc7013e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4bc7013e</a>
Fixed a race condition when inserting memory links during retain operations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8cf0dcbf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8cf0dcbf</a>
Fixed Windows embedded daemon launch behavior to avoid opening an extra terminal tab.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4280ac3f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4280ac3f</a>
Improved embedded Postgres stop/restart reliability by updating the embedded DB dependency.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8d9000a8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8d9000a8</a>
Fixed CLI memory retain timestamp handling and corrected supported fact-type values.·<a href="https://github.com/slayoffer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@slayoffer</a>·<a href="https://github.com/vectorize-io/hindsight/commit/df73c792" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>df73c792</a>
Fixed directive listing/reflect to honor tag groups so filtering behaves as expected.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fb554664" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fb554664</a>
Fixed daemon networking to honor an explicitly configured host and port.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/77380211" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>77380211</a>
Isolated the Claude Code provider subprocess from user plugins to prevent interference and improve reliability.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bcae23d9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bcae23d9</a>
Improved daemon startup reliability by waiting for health before reclaiming its port.·<a href="https://github.com/s09x" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@s09x</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5e547f71" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5e547f71</a>
Made worker retry behavior respect the configured maximum retries.·<a href="https://github.com/aaronwestphal" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@aaronwestphal</a>·<a href="https://github.com/vectorize-io/hindsight/commit/85f6769e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>85f6769e</a>
Prevented retain from silently dropping memories when fact extraction fails.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6e734e1a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6e734e1a</a>
Fixed control-plane auth redirects to validate return targets and honor basePath (improving security and correct routing).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9571a341" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9571a341</a>
Preserved raw reranker scores for providers that already return calibrated [0,1] scores.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/18b9c596" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>18b9c596</a>

0.7.1

Features

Allow configuring LLM "reasoning effort" via environment variable.·<a href="https://github.com/s9rkn" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@s9rkn</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1890d2b7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1890d2b7</a>
Add per-provider HTTP timeout environment variables for reranker requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a510b07a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a510b07a</a>
Add additional Chinese locale variants in the control plane UI.·<a href="https://github.com/MapleEve" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@MapleEve</a>·<a href="https://github.com/vectorize-io/hindsight/commit/617939d8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>617939d8</a>

Improvements

Schedule consolidation work using bank priorities so higher-priority banks are processed first.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cf637799" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cf637799</a>
Expose "graph_maintenance" in the control plane operations type filter dropdown.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/691cb539" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>691cb539</a>

Bug Fixes

Make consolidation more reliable by retrying indefinitely with backoff and preventing duplicate work per bank.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0d2ba56f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0d2ba56f</a>
Fixed memory corruption when retaining large documents that exceeded a single LLM call — some extracted memories could be lost. Re-retain affected documents after upgrading.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/74525cc0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>74525cc0</a>
Improve Codex OAuth embeddings stability by adding token refresh support and follow-up fixes.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ffa6fbf2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ffa6fbf2</a>
Fix recall recency scoring to anchor timestamps to the query time for more consistent results.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2de19e57" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2de19e57</a>

0.7.0

Features

Added support for ParadeDB pg_search as a Citus-compatible BM25 search backend.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4cd260b6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4cd260b6</a>
Added tokenizer configuration for pg_search to better control how text is tokenized for search.·<a href="https://github.com/Sanderhoff-alt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Sanderhoff-alt</a>·<a href="https://github.com/vectorize-io/hindsight/commit/16f80769" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>16f80769</a>
Added a new embeddings provider: ZeroEntropy.·<a href="https://github.com/flamerged" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@flamerged</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ec49175f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ec49175f</a>
Added support for Codex OAuth-based embeddings authentication.·<a href="https://github.com/haha0815" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@haha0815</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d802f914" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d802f914</a>
Added an API endpoint to clear mental model content.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7bd11bed" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7bd11bed</a>
Added targeted consolidation by observation scope to focus consolidation on specific parts of memory.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ac3ab2b5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ac3ab2b5</a>
Added support for the Alibaba Qwen3 rerank model.·<a href="https://github.com/quicklyfast" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@quicklyfast</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b83bb87d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b83bb87d</a>
Added Right Agent integration.·<a href="https://github.com/onsails" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@onsails</a>·<a href="https://github.com/vectorize-io/hindsight/commit/203ddfdd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>203ddfdd</a>
Added an OpenCode Go LLM provider.·<a href="https://github.com/tevenfeng" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@tevenfeng</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c29c76e3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c29c76e3</a>

Improvements

Added configurable BM25 language/tokenization and optional PGroonga backend for better multilingual search tuning.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cb04cb79" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cb04cb79</a>
Added an environment variable to enable API access logging (Uvicorn access logs).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/25387083" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>25387083</a>
Control plane now exposes a UI action to clear the mental model.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6e9b741b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6e9b741b</a>
Improved observation consolidation quality, including better handling of temporal reasoning.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d1ef9da9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d1ef9da9</a>
Control plane now supports internationalization with 8 locales.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/486c3a8b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>486c3a8b</a>

Bug Fixes

Fixed stale outgoing links after deletions by recomputing links asynchronously.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cc3ba4a3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cc3ba4a3</a>
Fixed Codex configuration to ignore inherited base URLs and automatically refresh OAuth access tokens.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/795c081d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>795c081d</a>
Stopped sending the temperature parameter to Anthropic requests to avoid API incompatibilities.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dabbf9ff" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dabbf9ff</a>
Prevented duplicate webhook batch deliveries for retain events.·<a href="https://github.com/xmh1011" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xmh1011</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6348f424" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6348f424</a>
Improved reliability for large retain requests by splitting oversized single items in batch retains.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c3b2b154" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c3b2b154</a>
Fixed Ollama support by adding an Ollama Cloud provider and correcting authentication for cloud endpoints.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cb037290" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cb037290</a>
Ensured disabled tools are not included in the agent system prompt.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2582b45a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2582b45a</a>
Avoided retries when an embeddings provider returns invalid vector dimensions.·<a href="https://github.com/ai-ag2026" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ai-ag2026</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e1e1a5e0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e1e1a5e0</a>
Prevented prompt formatting errors by escaping literal braces in all user-supplied prompt fields.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/67ae2a41" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>67ae2a41</a>
Fixed issues with mental-model baseline refresh and capped history size to prevent database JSON overflow.·<a href="https://github.com/xmh1011" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xmh1011</a>·<a href="https://github.com/vectorize-io/hindsight/commit/44b34c89" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>44b34c89</a>
Enabled gzip handling to keep graph responses parseable when compressed.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/31d1e172" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>31d1e172</a>
Added per-operation LLM concurrency caps to prevent overload and improve stability under parallel workloads.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/daf2348b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>daf2348b</a>
Preserved tag group/triggers correctly when updating tags.·<a href="https://github.com/xmh1011" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xmh1011</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9c161e4e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9c161e4e</a>
Improved reranking robustness by detecting pre-normalized scores and applying rank-based normalization when needed.·<a href="https://github.com/xuli500177" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xuli500177</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dcf5588e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dcf5588e</a>
Fixed entity resolution so user-defined label entities are not fuzzy-matched incorrectly.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/46dd2dfd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>46dd2dfd</a>
Improved worker resilience by handling stale pending schema routines.·<a href="https://github.com/xmh1011" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xmh1011</a>·<a href="https://github.com/vectorize-io/hindsight/commit/592f01bb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>592f01bb</a>
Fixed embedded UI startup on Windows by resolving the correct npx path before launch.·<a href="https://github.com/tuancookiez-hub" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@tuancookiez-hub</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2e5186a6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2e5186a6</a>
Improved control-plane session security by verifying signed session cookies instead of just checking presence.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/878ef957" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>878ef957</a>

0.6.2

Features

Added a configurable MCP request timeout to the Claude Code integration so long-running recall/reflect calls no longer time out at the default.·<a href="https://github.com/rsaulo" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rsaulo</a>·<a href="https://github.com/vectorize-io/hindsight/commit/55ef7067" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>55ef7067</a>

Improvements

Renamed the Agent SDK agent_knowledge_recall max_results parameter to max_tokens and raised the default from 10 to 1024 so default-config users get useful recall results.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d9dd1499" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d9dd1499</a>
Applied the same max_results→max_tokens rename to the Claude Code MCP plugin so both integrations stay in sync.·<a href="https://github.com/offendingcommit" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@offendingcommit</a>·<a href="https://github.com/vectorize-io/hindsight/commit/909a4fd4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>909a4fd4</a>

Security

Bumped vulnerable dependencies across the stack to address GitHub-reported CVEs — including litellm to ≥1.83.14, urllib3 to 2.7.0, and additional high/critical pip and npm packages.·<a href="https://github.com/dcbouius" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dcbouius</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fd05bdab" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fd05bdab</a>

Bug Fixes

Fixed the CLI “memory retain” timestamp/Event Date option so the provided timestamp is actually sent to the API.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/51ea9aa2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>51ea9aa2</a>
Repaired a database migration issue affecting mental model subtype data at the current schema head.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/debbd919" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>debbd919</a>
Improved migration robustness by handling transient database OID errors during the embedding-dimension migration.·<a href="https://github.com/dcbouius" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dcbouius</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9dfbfb4b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9dfbfb4b</a>
Fixed Claude Code knowledge get_page calls to request detail=content and avoid tool-result spillover so full page content returns reliably.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b2a693ab" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b2a693ab</a>
Applied the same agent_knowledge_get_page detail=content fix to the Agent SDK so SDK callers also receive full page content.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b593d40f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b593d40f</a>
Aligned the Paperclip integration with Paperclip's actual event payload shape, restoring correct fact extraction from incoming events.·<a href="https://github.com/amirhmoradi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@amirhmoradi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/be908d5b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>be908d5b</a>

0.6.1

Features

Added AlloyDB ScaNN vector index support, providing a high-performance vector index option for AlloyDB deployments·<a href="https://github.com/can1357" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@can1357</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e4422a9b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e4422a9b</a>
Added map-type entity labels so entity extraction can produce structured groups (e.g. address fields) instead of flat strings·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2b725bc4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2b725bc4</a>
Added z.ai (智谱) as a first-class LLM provider with a free-tier-friendly default model·<a href="https://github.com/Burgunthy" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Burgunthy</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4c75cd9e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4c75cd9e</a>
Added a litellmrouter provider that lets the API call multiple LLM endpoints with automatic fallback chains·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/98f33cbf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>98f33cbf</a>
Added an optional read-only database backend for recall queries, letting recall traffic go to a replica while writes stay on the primary·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cf9b1f59" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cf9b1f59</a>
Added optional access-key login to the Control Plane for protecting the admin UI without a full SSO setup·<a href="https://github.com/ariel-ai-bot" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ariel-ai-bot</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c0ff87ea" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c0ff87ea</a>
Added a --strategy flag to memory retain-files in the CLI for selecting how files are split before retention·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/375747f5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>375747f5</a>
Bank dropdown in the Control Plane now shows per-bank memory counts to make bank selection easier·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5a0cb4a5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5a0cb4a5</a>

Improvements

Worker progress-stats fanout is now scoped to schemas with pending work, eliminating wasted polling on idle tenants·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/39d31ad2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>39d31ad2</a>

Bug Fixes

Fixed fact extraction reliability by removing multiplicative retry layers that could turn one transient LLM failure into many·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a22e8bdd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a22e8bdd</a>
Fixed reflect to read document metadata from the original retain parameters so reflect outputs include the right document context·<a href="https://github.com/nepenth" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nepenth</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f2a2f9fe" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f2a2f9fe</a>
Failed batch_retain operations now propagate the child error_message to the parent, so failures surface a meaningful reason instead of a generic error·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7b82d05b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7b82d05b</a>
Fixed macOS daemon mode by replacing os.fork() with subprocess.Popen, restoring compatibility with PyTorch MPS·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8d77976a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8d77976a</a>
Hardened Control Plane access-key authentication and improved login UX (clearer errors, redirect handling)·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b628716f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b628716f</a>
Reduced retain memory pressure by clearing content references after use, helping long-running workers avoid OOM on large batches·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c9145805" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c9145805</a>
Fixed Docker image to chmod 755 /home/hindsight so containers run cleanly with --user UID:GID overrides·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a5cef602" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a5cef602</a>
Hard-pinned meta packages (hindsight-api, hindsight-all, hindsight-all-slim) to matching hindsight-api-slim, preventing stale slim installs after upgrade·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a86d5381" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a86d5381</a>
Worker now probes pg_proc before calling the optional schemas_with_pending_work() function, so older databases without it don't crash the worker·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a1c1b7de" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a1c1b7de</a>
TypeScript client now derives CLIENT_VERSION via tsup define so the published package version is always reported correctly·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ab8cc3e6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ab8cc3e6</a>

0.6.0

Features

Added Dify integration providing Hindsight memory tools inside Dify workflows.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bc23750b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bc23750b</a>
Added n8n community node package for using Hindsight memory in n8n automations.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c1eaf711" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c1eaf711</a>
Added SmolAgents integration providing Hindsight memory tools for SmolAgents-based agents.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8314de5e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8314de5e</a>
Added AWS Bedrock AgentCore Runtime integration (hindsight-agentcore).·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c91696f5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c91696f5</a>
Added an Oracle Database backend option for enterprise storage.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/50f559c9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>50f559c9</a>
Added the ability to cancel long-running async operations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7f30dcc7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7f30dcc7</a>
Typescript client now supports AbortSignal across all methods for request cancellation.·<a href="https://github.com/harryplusplus" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@harryplusplus</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8367930c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8367930c</a>

Improvements

Python client now exposes retain_async via retain()/aretain() for async memory retention flows.·<a href="https://github.com/harryplusplus" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@harryplusplus</a>·<a href="https://github.com/vectorize-io/hindsight/commit/daae8223" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>daae8223</a>
Anthropic provider now supports environment-configurable max retries and default headers.·<a href="https://github.com/TuftyBruno" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@TuftyBruno</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fa4bf700" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fa4bf700</a>
Memories timeseries stats can now be grouped by different time fields (time_field toggle).·<a href="https://github.com/aliu-ronin" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@aliu-ronin</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cf1a97ab" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cf1a97ab</a>
Improved database performance for observation reads by reducing overhead and making reads backend-aware.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d8ec2d7f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d8ec2d7f</a>

Bug Fixes

Fixed search ranking by correcting BM25 score direction for the vchord backend.·<a href="https://github.com/liling" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@liling</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b322b0c5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b322b0c5</a>
Recall now correctly inherits observation entities through source_memory_ids, improving entity continuity across related memories.·<a href="https://github.com/youchi1" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@youchi1</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8507095a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8507095a</a>
Entity co-occurrence timestamps now use the event date instead of the ingestion time, improving timeline accuracy.·<a href="https://github.com/aliu-ronin" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@aliu-ronin</a>·<a href="https://github.com/vectorize-io/hindsight/commit/fc624cbf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fc624cbf</a>
Daemon mode now respects configured host settings (CLI --host and HINDSIGHT_API_HOST).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3d3aa76b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3d3aa76b</a>
Webhooks are now processed tenant-aware to prevent cross-tenant routing issues.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b9069c28" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b9069c28</a>
API per-document graph and counts now include observations, improving completeness of document-level views.·<a href="https://github.com/youchi1" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@youchi1</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7cc2daf4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7cc2daf4</a>
Improved compatibility with OpenAI-compatible providers by hardening JSON response parsing and handling null content.·<a href="https://github.com/voarsh2" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@voarsh2</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bc14e5c4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bc14e5c4</a>
Fixed Windows worker startup by handling platforms that don't implement add_signal_handler.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/08b56fdc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>08b56fdc</a>
Retain/batch retain reliability improved by fixing transactional atomicity, recovery checkpoint scoping, and a cascade deadlock risk.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f4ca3038" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f4ca3038</a>
Typescript client now exposes previously missing recall/reflect parameters.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/641b3912" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>641b3912</a>
MCP recall tool now exposes tag_groups so recalls can be filtered/grouped by tag groups.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b948b574" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b948b574</a>
Embed/daemon startup reliability improved (script path resolution, correct extras when spawning API, and safer subprocess output handling).·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/0f15f76a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0f15f76a</a>
Configuration logging now redacts database URLs to avoid leaking credentials in logs.·<a href="https://github.com/xmh1011" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@xmh1011</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2bada2db" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2bada2db</a>
Fixed support for OpenAI-compatible embedding dimensions by allowing provider-specific parameters.·<a href="https://github.com/zwcf5200" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@zwcf5200</a>·<a href="https://github.com/vectorize-io/hindsight/commit/324b4b0a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>324b4b0a</a>

0.5.6

Bug Fixes

Reverted the JSON schema simplification introduced in 0.5.5 (5b1c3486). The change inlined $ref/$defs into a large blob that caused some LLMs (notably GPT-4o-mini in soft-enforcement mode) to echo the schema structure instead of producing valid responses, resulting in 0 facts extracted during retain. If you are on 0.5.5, upgrade to 0.5.6 immediately.

0.5.5

:::warning 0.5.5 contains a regression that can cause 0 facts to be extracted during retain. The JSON schema simplification change (5b1c3486) was reverted in 0.5.6. Please upgrade to 0.5.6. :::

Features

Added a new LlamaParse file parser, using the LlamaIndex Cloud parsing API to convert documents (PDF, DOCX, etc.) to markdown before retain.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/91106f30" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>91106f30</a>
Added a new Mental Models list view and tag filtering from mental models.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8fbe85f0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8fbe85f0</a>
Added Pipecat voice AI pipeline integration so voice agents can use Hindsight long-term memory.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f7cc9ad6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f7cc9ad6</a>
Added an option to force IPv4 for Gemini embeddings to improve compatibility in restricted network environments.·<a href="https://github.com/connorblack" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@connorblack</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6fb8ac97" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6fb8ac97</a>
Added support to control Cohere embedding output dimensions via configuration.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a7514e18" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a7514e18</a>
Added a new Document Chunks API plus document reprocessing and a richer document detail experience in the UI.·<a href="https://github.com/vectorize-io/hindsight/commit/8eb6e0e5b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8eb6e0e5b</a>
Added an exclude_parents filter for list operations to better control what results are returned.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8f6e0e5b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8f6e0e5b</a>
Operation responses now include retry information (retry count and next retry time).·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/45f47a91" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>45f47a91</a>
Retain results now include processed content token counts for better usage/throughput visibility.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9c9d7917" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9c9d7917</a>

Improvements

Added full Windows support for the embedded runtime and improved how the local API is discovered/launched.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4ba54d8c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4ba54d8c</a>
Operation status reporting now includes processing and cancelled states across the API and UI.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/80982da5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>80982da5</a>
Workers can reserve per-operation slots when claiming tasks, improving fairness and throughput under load.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c81e62ae" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c81e62ae</a>
PostgreSQL connections now support a configurable statement timeout to prevent runaway queries.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/bdb3a55d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bdb3a55d</a>
~~Improved LLM interoperability by simplifying JSON schemas and avoiding problematic tool-choice defaults.~~ Reverted in 0.5.6 — caused 0 facts extracted with some LLMs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5b1c3486" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5b1c3486</a>
Worker scheduling no longer allows child tasks to block parent execution.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a49d19cd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a49d19cd</a>

Bug Fixes

Fixed DeepSeek compatibility issues (including tool-calling quirks) and added it as a first-class LLM provider.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/461b00d4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>461b00d4</a>
Fixed Amazon Bedrock Converse compatibility by adjusting how causal relations are represented.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4bc772d8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4bc772d8</a>
GET /banks/{bank_id}/profile no longer creates a bank as a side effect.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/99a89789" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>99a89789</a>
Reduced memory fan-out during consolidation recall to prevent excessive retrieval and improve stability.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/4ba2fffe" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4ba2fffe</a>
External PostgreSQL connection strings now accept asyncpg-style URLs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/db7f4921" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>db7f4921</a>
Timeseries stats buckets now return timezone-aware ISO timestamps.·<a href="https://github.com/aliu-ronin" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@aliu-ronin</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cd1ab497" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cd1ab497</a>
Fixed conversation storage when using streaming LLM responses via LiteLLM.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ac5181f5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ac5181f5</a>
Removed the MCP delete_memory tool to close an authorization-bypass vulnerability.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/90674aef" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>90674aef</a>
First-time UI launch no longer requires manual confirmation to install the control plane.·<a href="https://github.com/bwjoke" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@bwjoke</a>·<a href="https://github.com/vectorize-io/hindsight/commit/33aacf5c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>33aacf5c</a>

0.5.4

Features

Delta mental model refresh now scopes recall to memories created since the last refresh, making updates faster and more accurate.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e90cfa4a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e90cfa4a</a>
OpenAI-compatible embedding providers now support configurable batch sizes for better throughput.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/30700de6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>30700de6</a>
Embedded daemon now includes a liveness check that auto-recovers from crashes.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/59f9a2bf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>59f9a2bf</a>
Disable daemon idle timeout by default so embedded instances stay alive between requests.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f5dfe59b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f5dfe59b</a>
Add {user_id} template variable for retainTags in the Claude Code integration.·<a href="https://github.com/soichisumi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@soichisumi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9181c9a2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9181c9a2</a>
New decommission-workers and worker-status admin CLI commands for managing worker fleets.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c8b898bd" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c8b898bd</a>

Bug Fixes

Fix duplicate memory units caused by chunk index scrambling during concurrent upserts.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/511ca723" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>511ca723</a>
Prevent directive content from leaking into reflect answers on empty banks.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3d877b05" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3d877b05</a>
Honor the reflect_mission identity framing in the prompt builder so agent personality works correctly.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a3b0d265" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a3b0d265</a>
Allow reflect-specific LLM configuration when the default LLM provider is disabled.·<a href="https://github.com/zwcf5200" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@zwcf5200</a>·<a href="https://github.com/vectorize-io/hindsight/commit/afd00c03" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>afd00c03</a>
Preserve document created_at timestamp across upsert and add UI edit flow for documents.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/10785666" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>10785666</a>
Fix ensure_ascii=False in json.dumps for LLM prompts so non-Latin text is preserved.·<a href="https://github.com/harryplusplus" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@harryplusplus</a>·<a href="https://github.com/vectorize-io/hindsight/commit/d05b49a2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d05b49a2</a>
Route update_bank through the config resolver with generic config_updates.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/abbd3619" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>abbd3619</a>
Workers now scan for active schemas before claiming tasks, preventing work on decommissioned tenants.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7126bf8a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7126bf8a</a>
Pass DeferOperation through MemoryEngine.execute_task so extensions can requeue work.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/858f0b3a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>858f0b3a</a>
Downgrade LLM verify_connection failure to a warning instead of crashing on startup.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9901aa1e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9901aa1e</a>
Fix items_count in list_operations response to populate from result_metadata.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/41710ba1" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>41710ba1</a>
Align AI SDK ReflectBasedOn types with the OpenAPI spec.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3d6b3805" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3d6b3805</a>
Fix database migration path by merging divergent Alembic heads for v0.5.3.·<a href="https://github.com/grimmjoww" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@grimmjoww</a>·<a href="https://github.com/vectorize-io/hindsight/commit/487e2a5e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>487e2a5e</a>
Lower OpenCode retainEveryNTurns default from 10 to 3 for more frequent memory saves.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/902704df" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>902704df</a>

0.5.3

Features

Add a setting to limit how many memories can be consolidated per round, helping control consolidation workload and cost.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/ca561aca" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ca561aca</a>
Add integration with the OpenAI Agents SDK.·<a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b8da88c8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b8da88c8</a>
Improve mental model refresh and updates with structured operations and cleaner observation handling on upsert.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/8b80959b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>8b80959b</a>
Allow extensions to requeue work by throwing a DeferOperation exception from worker operations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f8904797" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f8904797</a>
Make recall budget mapping configurable per memory bank.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/576c44d2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>576c44d2</a>
Control plane now shows failed consolidation counts with a drilldown to investigate issues.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/e1e5f36c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e1e5f36c</a>
Add mental-model staleness signals and a refreshed UI/experience for reviewing model history and snapshots.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/654e4c0c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>654e4c0c</a>
Replace the embedded Paperclip library with the Paperclip plugin for more flexible integrations.·<a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a>·<a href="https://github.com/vectorize-io/hindsight/commit/c571fac7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c571fac7</a>
JSON logs can now include tenant information and support a configurable allowlist for what gets logged.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/3bedc1ce" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3bedc1ce</a>
CLI now supports named connection profiles (via -p/--profile) for easier switching between environments.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/70d60e96" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>70d60e96</a>

Improvements

Reduce the default number of retries for LLM calls to fail faster when providers are erroring or unavailable.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/b52b483c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b52b483c</a>
Make reranker failures easier to diagnose and add a configurable timeout for the TEI reranker.·<a href="https://github.com/octo-patch" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@octo-patch</a>·<a href="https://github.com/vectorize-io/hindsight/commit/69383af8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>69383af8</a>

Bug Fixes

Fix crashes when using Jina MLX on Metal GPUs by serializing GPU operations.·<a href="https://github.com/lkttle" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@lkttle</a>·<a href="https://github.com/vectorize-io/hindsight/commit/2e74a324" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>2e74a324</a>
Fix database migration path so upgrades from v0.4.22 to v0.5.x work correctly.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/5437cc02" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>5437cc02</a>
Prevent orphaned observations if a source memory is deleted during consolidation.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f9042e37" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f9042e37</a>
Fix Ollama requests by explicitly disabling "think" mode in the native call payload.·<a href="https://github.com/karl-8888" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@karl-8888</a>·<a href="https://github.com/vectorize-io/hindsight/commit/7d4fd1aa" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7d4fd1aa</a>
Fix file retain uploads and prevent orphaned retained files.·<a href="https://github.com/christerence" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@christerence</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9e30ae25" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9e30ae25</a>
Fix file retain API to correctly accept and map a provided "timestamp" field.·<a href="https://github.com/christerence" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@christerence</a>·<a href="https://github.com/vectorize-io/hindsight/commit/13f3052e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>13f3052e</a>
Improve fairness across tenants when workers claim tasks, reducing the chance of noisy tenants starving others.·<a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a>·<a href="https://github.com/vectorize-io/hindsight/commit/a5e53721" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a5e53721</a>
Ensure the mental model max_tokens setting is respected during refresh/reflect operations.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/568e3c30" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>568e3c30</a>
Fix control-plane links by properly encoding bank IDs in URLs end-to-end.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/cbaec36f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cbaec36f</a>
Make task submission idempotent when a payload is already set, preventing duplicate/failed submissions.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/088dfecb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>088dfecb</a>

0.5.2

Features

Added a co-occurrence graph view for exploring entity relationships in the control plane.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f64c5d20" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f64c5d20</a>
Added recall controls to the mental model trigger API/CLI so you can tune what gets recalled during runs.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/f2fc8f9f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f2fc8f9f</a>
Async operations now expose task payload details and associated document IDs for better observability and debugging.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/870bf4a3" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>870bf4a3</a>

Improvements

Revamped the control plane bank statistics view for clearer insights.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/34365c32" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>34365c32</a>
Clients now send an identifying User-Agent header on all HTTP requests for easier server-side diagnostics.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/9372462e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9372462e</a>

Bug Fixes

Fixed consolidation retry budget handling so retries are correctly applied at the LLM call site.·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dee58139" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dee58139</a>
Fixed a crash during retain when embeddings and extracted facts counts didn’t match.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/dbd1d1a7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dbd1d1a7</a>
Improved embedded mode cleanup stability by adding a timeout when acquiring the cleanup lock (prevents hangs).·<a href="https://github.com/r266-tech" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@r266-tech</a>·<a href="https://github.com/vectorize-io/hindsight/commit/6b5aa3af" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6b5aa3af</a>
OpenClaw plugins now reliably register agent hooks on every entry invocation.·<a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a>·<a href="https://github.com/vectorize-io/hindsight/commit/1be5ff33" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1be5ff33</a>
TypeScript SDK now re-exports BankTemplate types from the package root for simpler imports.·<a href="https://github.com/mrkhachaturov" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@mrkhachaturov</a>·<a href="https://github.com/vectorize-io/hindsight/commit/581bbf3f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>581bbf3f</a>
Bank template configuration validation was aligned with configurable fields to prevent invalid/ignored settings.·<a href="https://github.com/mrkhachaturov" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@mrkhachaturov</a>·<a href="https://github.com/vectorize-io/hindsight/commit/099f4c92" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>099f4c92</a>

0.5.1

Breaking Changes

OpenClaw now reads configuration from plugin config instead of environment variables. (e22ae05f)

Features

Added SiliconFlow as a supported reranker provider. (d0b2ab9a)
Added an interactive OpenClaw setup wizard with Cloud / API / Embedded modes. (87322396)
Added a config-aware CLI to backfill OpenClaw history. (72fd3d59)
Added OpenClaw session pattern filtering to ignore or treat sessions as stateless. (5a61ac50)
Added a Cloudflare OAuth proxy integration option for self-hosted Hindsight. (aad07a14)
Expanded the CLI to cover all OpenAPI endpoints and request-body parameters. (c05c491d)
Added a default bank template environment variable (HINDSIGHT_API_DEFAULT_BANK_TEMPLATE). (fc941d5c)
Added a daemon lifecycle package (@vectorize-io/hindsight-all) to simplify running the all-in-one daemon. (576016f5)
Added recallTags and recallTagsMatch configuration options to control which tagged memories are recalled. (b57e337f)

Improvements

Improved OpenClaw reliability with more resilient startup behavior and richer retain metadata. (1f1716bd)

Bug Fixes

OpenClaw setup wizard now prompts for the token value (not the env var name). (9679d813)
Fixed embedded mode daemon start/stop race that could terminate healthy daemons. (e5724fcb)
Fixed reranker initialization issues to show real import errors and avoid a Transformers 5.x race in jina-mlx. (f82f58fa)
Fixed worker consolidation slot accounting to respect the configured maximum concurrency. (2d74007d)
Improved CLI API error output by including the HTTP response body. (93300b91)
Fixed CLI memory listing showing "[UNKNOWN]" for fact types. (2635bbb4)
Fixed recall ranking so RRF ordering is preserved when the reranker is configured as a passthrough. (4f9cf15c)
Fixed retain chunk insertion to be idempotent and avoid repeated retries on integrity errors. (2d95f78b)
Fixed retain ANN seed temp table creation to run inside a transaction for better reliability. (3fc87e76)
Fixed LLM requests to use the correct max token parameter for reasoning models and Azure OpenAI. (7b2263ba)

0.5.0

Breaking Changes

Removed BFS and MPFP graph retrieval strategies. LinkExpansionRetriever is now the sole graph retrieval algorithm, offering simpler, faster, and more accurate results. (ea834bc7)
Dropped the hindsight-hermes integration package. (cf0537ba)

Features

Built-in llama.cpp LLM provider for fully local inference without external API calls. (f74b577e)
Retain update_mode='append' for concatenating new content onto an existing document instead of replacing it. (3c633e5e)
OpenRouter support for LLM, embeddings, and reranking. (e5944b63)
Bank template import/export with Template Hub — export a bank's configuration, mental models, and directives as a reusable manifest, then import into other banks. (30a319a6)
Constellation view in the Control Plane — interactive, zoomable canvas visualization of entity relationship graphs with heat-gradient coloring and dark mode support. (36783df3)
Added detail parameter to list/get mental model endpoints for controlling response verbosity. (8d1bfbbd)
Added AutoGen integration (hindsight-autogen) for persistent long-term memory in AutoGen agents. (a757765a)
Added Paperclip integration (@vectorize-io/hindsight-paperclip) with Express middleware and process adapter modes for stateless agent memory. (81441ee9)
Added OpenCode persistent memory plugin for the OpenCode editor. (e1c6220f)
OpenClaw JSONL-backed retain queue for external API resilience — buffers retain calls locally when the API is unreachable. (087545cc)
OpenClaw now supports bankId for static bank configurations. (0e81d1a2)
Added Google embeddings and reranker provider support. (07de798c)
Added persistent volume support in Helm chart for local model cache. (cefa7554)
MCP server now includes a sync_retain tool and validates UUID inputs. (48185a4b)
Recall combined scoring now includes proof_count boost for better ranking. (26794aab)

Improvements

3-phase retain pipeline restructures memory ingestion into pre-resolve, insert, and post-link phases, dramatically improving throughput under concurrent load by removing slow reads from write transactions. (914ba796)
Recall entity graph expansion now caps per-entity fanout and includes a timeout fallback, preventing slow queries on banks with high-fanout entities. (57f15445)
Fact serialization in think-prompt now includes occurred_end and mentioned_at for richer temporal context. (37348c85)
Consolidation observation quality improved with structured processing rules. (6f173b10)

Bug Fixes

LiteLLM SDK embeddings encoding_format is now configurable instead of hardcoded. (cece2c90)
Fixed out-of-range content_index crash in recall result mapping. (9790d904)
Experience fact types are now preserved correctly during normalization. (9cfdd464)
Clear memories endpoint no longer deletes the bank profile. (26a64cc0)
Embedding daemon clears stale processes on the port before starting. (7d6c570a)
Per-bank vector index migration now respects vector extension configuration. (4fd7c5d1)
Timeline group sort uses numeric date comparison instead of locale string comparison. (f3f2c6b0)
Resolved 25 test regressions from the streaming retain pipeline. (7415ebff)
MCP server now auto-coerces string-encoded JSON in tool arguments. (443c94c8)
Entity labels structure is now validated on PATCH to prevent invalid configurations. (7e23f8e1)
Fixed bank_id metric label to be opt-in, preventing OTel memory leak. (cf4bd598)
Fixed max_tokens handling for OpenAI-compatible endpoints with custom base URLs. (cd99eef4)
Fixed event_date AttributeError when date is None in fact extraction. (6cb309f7)
Query analyzer now handles dateparser internal crashes gracefully. (e0e65c44)
Embedding profile .env overwrite skipped when config has no Hindsight keys. (9e2890ba)
Windows compatibility fix for hindsight-embed. (f9fe6953)
Addressed critical and high severity security vulnerabilities in dependencies. (ee4510a7)

0.4.22

Features

API now supports passing custom LLM request parameters via the HINDSIGHT_API_LLM_EXTRA_BODY configuration. (ecaa1ad1)
Document metadata is now exposed through the API and control plane. (627ec5d5)
Added a /code-review skill for automated code quality checks against project standards. (bdb33c58)
ZeroEntropy reranker now supports a configurable base URL. (a915584e)
Codex can now retain structured tool calls from rollout files. (3461398b)

Improvements

Embeddings via the LiteLLM SDK can now optionally specify output dimensions. (f841bcb9)
API responses now include an X-Ignored-Params header to warn when unknown request parameters were ignored. (cef42d81)
OpenClaw CLI startup is faster by deferring heavy initialization until the service starts. (41025c3b)

Bug Fixes

Mental model triggers now support the full config schema, including tag matching and tag group filters. (2c32ffad)
Cohere reranking via Azure endpoints now works reliably (avoids 404 errors). (84985ee9)
Claude Code provider no longer defers to built-in tools, preventing MCP tool handling issues. (fa82efc8)
Recall endpoint now returns metadata correctly instead of dropping it from the response. (4768bf39)
Gemini 3.1+ tool calls now read thought signatures correctly. (1b5c262a)
First-person agent memories are now correctly classified as "experience" facts. (00961156)
Codex upgrades now preserve and merge new settings instead of skipping them. (b104bad0)
LlamaIndex integration fixes improve document ID handling, memory API behavior, and ReAct tracing. (d93dfea8)

0.4.21

Features

Added audit logging for feature usage tracking, including request duration in audit entries. (083295dc)
Added Hindsight memory integration for the OpenAI Codex CLI. (0b17a67c)
Added an MCP hook to filter tool visibility per user. (f8285b7b)
Added a per-bank limit setting to cap the number of observations stored per scope. (b32767ca)
Added native Windows support so Hindsight can run without Docker. (c5700ff5)
Added a 'none' LLM provider to support chunk-only storage without LLM calls. (9e5a066d)
Added a setup command/skill to register hooks more reliably. (22ca6a8d)
Hermes now supports file-based configuration. (0ff36548)
Added a LiteLLM-based provider to support Bedrock and many additional LLM providers. (db70fdbe)
Added support for Strands Agents SDK integration with Hindsight memory tools. (7fe773c0)
Added LlamaIndex integration. (2d787c4f)
Added AG2 framework integration. (73123870)
Added support for Ark and Volcano LLM providers. (417fac61)
Retain now supports delta mode to skip LLM processing for unchanged chunks on upsert. (fd88c0ef)
Claude Code integration can now retain full sessions with document upsert and configurable tags, and records tool calls as structured JSON. (2d31b67d)
MCP retain tool now supports selecting a retain strategy via a parameter. (4285e944)

Improvements

OpenClaw logging is now configurable and can emit structured output. (d441ab81)
Made inclusion of source facts in search observations configurable. (5095d5e3)
Integrations no longer use hardcoded default models, relying on configured defaults instead. (58e68f3e)

Bug Fixes

Improved MCP server compatibility by handling Claude Code GET probes and allowing stateless HTTP mode to be configured. (d8050387)
Per-bank vector index creation now respects the configured vector extension setting. (6488c9bc)
Verbose retain extraction now correctly includes the retain mission context. (d2965e64)
Codex integration no longer crashes on startup when the API quota is exhausted (HTTP 429). (111e8c70)
OpenAI embeddings client now correctly parses query parameters included in base_url. (a209ef1a)
Fixed tool_choice handling for Codex/Claude Code when forcing specific tool calls. (585ac76f)
OpenClaw auto-recall now supports a configurable timeout to prevent hangs. (cd4d449f)
Fixed control plane UI issues affecting recall and data viewing. (6bb83f46)
Recall responses now include associated metadata. (0bcbf849)
Python client update_bank_config() now exposes all configurable fields. (7c18723f)
API OpenAPI schema now correctly includes Pydantic v2 ValidationError fields. (939cb40a)
JSON-string tags are now coerced to lists for MemoryItem and MCP tools to prevent tagging errors. (c5273f5f)

0.4.20

Features

Add a one-command setup CLI package for the NemoClaw integration. (d284de28)
Add a LangGraph integration for using Hindsight memory within LangGraph agents. (b4320254)
Add reflect filters to exclude specific fact types and mental model content during reflection. (ea662d06)
Introduce independent versioning for integrations so they can be released separately from the core server. (31f1c53c)
Add a Claude Code integration plugin. (f4390bdc)

Improvements

Add a wall-clock timeout to reflect operations so they don’t run indefinitely. (8ce06e3e)
Provide richer context when validating operations via the OperationValidator extension. (2eb1019d)
Make the hindsight-api package runnable directly via uvx by adding script entry points. (97f7a365)
Support passing query parameters during OpenAI-compatible client initialization for broader provider compatibility. (20e17f28)
Upgrade the default MiniMax model from M2.5 to M2.7. (1f1462a5)

Bug Fixes

Prevent context overflow during observation search by disabling source facts in results. (8e2e2d5b)
Fix Claude Code integration session startup by pre-starting the daemon in the background. (26944e25)
Fix Claude Code integration installation and configuration experience so setup is more reliable. (35b2cbb6)
Fix a memory leak in entity resolution that could grow over time under load. (e6333719)
Avoid crashes and retain failures when the Postgres pg_trgm extension is unavailable by handling detection/fallback correctly. (365fa3ce)
Strip Markdown code fences from model outputs across all LLM providers for more consistent parsing. (2f2db2a6)
Return a clear 400 error for empty recall queries and fix a SQL parameterization issue. (5cdc714a)
Ensure file retain requests include authentication headers so uploads work in authenticated deployments. (78aa7c53)
Fix MCP tool calls when MCP_AUTH_TOKEN and TENANT_API_KEY differ. (8364b9c5)
Allow claude-agent-sdk to install correctly on Linux/Docker environments. (3f31cbf5)
In LiteLLM mode, fall back to the last user message when no explicit hindsight query is provided. (5e8952c5)
Fix non-atomic async operation creation to prevent inconsistent operation records. (94cf89b5)
Prevent orphaned parent operations when a batch retain child fails unexpectedly. (43942455)
Fix failures for non-ASCII entity names by ensuring entity IDs are set correctly. (438ce98b)
Correctly store LLM facts labeled as "assistant" as "experience" in the database. (446c75f3)

0.4.19

Features

TypeScript client now works in Deno environments. (72c25c97)
Added Agno integration to use Hindsight as a memory toolkit. (8c378b98)
Added Hermes Agent integration (hindsight-hermes) for persistent memory. (ef90842f)
Expanded retain behavior with new verbatim and chunks extraction modes and named retain strategies. (e4f8a157)

Improvements

Improved local reranker performance/efficiency with FP16 and bucketed batching, plus compatibility with Transformers 5.x. (e7da7d0e)

Bug Fixes

Prevented silent memory loss when consolidation fails (failed consolidations are tracked and can be recovered). (28dac7c7)
Fixed Docker control-plane startup to respect the configured control-plane hostname. (8a64dc8d)
Database cleanup migration now removes orphaned observation memory units to avoid inconsistent memory state. (f09ad9de)
Deleting a document now also deletes linked memory units to prevent leftover/stale memory entries. (f27bd953)
Fixed MCP middleware to send an Accept header, preventing 406 response errors in some setups. (836fd81e)
Improved compatibility with Gemini tool-calling by preserving thought signature metadata to avoid failures on gemini-3.1-flash-lite-preview. (21f9f46c)

0.4.18

Features

Add compound tag filtering using tag groups. (5de793ee)
Publish new slim Python packages (hindsight-api-slim and hindsight-all-slim) for smaller installs. (15ea23d5)
Add MiniMax as a supported LLM provider. (2344484f)
Add Jina MLX reranker provider optimized for Apple Silicon. (1caf5ec9)

Improvements

Allow configuring maximum recall query tokens via an environment variable. (66dedb8d)
Improve retrieval performance by switching to per-bank HNSW indexes. (43b3efc4)

Bug Fixes

Prevent reranking failures by truncating long documents that exceed LiteLLM reranker context limits. (eeb938fc)
Ensure recalled memories are injected as system context for OpenClaw. (b17f338e)
Ensure embedded profiles are registered in CLI metadata when the daemon starts. (06b0f74a)
Cancel in-flight async operations when a bank is deleted to avoid dangling work. (0560f626)

0.4.17

Features

Added a manual retry option for failed asynchronous operations. (dcaacbe4)
You can now change/update tags on an existing document. (1b4ad7f4)
Added history tracking and a diff view for mental model changes. (e2baca8b)
Added observation history tracking with a UI diff view to review changes over time. (576473b6)
File uploads can now choose a parser per request, with configurable fallback chains. (99220d05)
Added an extension hook that runs after file-to-Markdown conversion completes. (1d17dea2)

Improvements

Operations view now supports filtering by operation type and has more reliable auto-refresh behavior. (f7a60f89)
Added token limits for “source facts” used during consolidation and recall to better control context usage. (5d05962d)
Improved bank selector usability by truncating very long bank names in the dropdown. (1e40cd22)

Bug Fixes

Fixed webhook schema issues affecting multi-tenant retain webhooks. (32a4882a)
Fixed file ingestion failures by stripping null bytes from parsed file content before retaining. (cd3a6a22)
Fixed tool selection handling for OpenAI-compatible providers when using named tool_choice. (1cdfb7c2)
Improved consolidation behavior to prioritize a bank’s mission over an ephemeral-state heuristic. (00ccf0b2)
Fixed database migrations to correctly handle mental model embedding dimension changes. (7accac94)
Fixed file upload failures caused by an Iris parser httpx read timeout. (fa3501d4)
Improved reliability of running migrations by serializing Alembic upgrades within the process. (f88b50a4)
Fixed Google Cloud Storage authentication when using Workload Identity Federation credentials. (d2504ac5)
Fixed the bank selector to refresh the bank list when the dropdown is opened. (0ad8c2d0)

0.4.16

Features

Added Webhooks with consolidation.completed and retain.completed events. (abbf874d)

Improvements

Improved OpenClaw recall/retention controls. (d425e93c)
Improved search/reranking quality by switching combined scoring to multiplicative boosts. (aa8e5475)
Improved performance of observation recall by 40x on large banks. (ad2cf72a)
Improved server shutdown behavior by capping graceful shutdown time and allowing a forced kill on a second Ctrl+C. (4c058b4b)

Bug Fixes

Fixed an async deadlock risk by running database schema migrations in a background thread during startup. (e0a2ac63)
Fixed webhook delivery/outbox processing so transactions don’t silently roll back due to using the wrong database schema name. (75b95106)
Fixed observation results to correctly resolve and return related chunks using source_memory_ids. (cb6d1c46)
Fixed MCP bank-level tool filtering compatibility with FastMCP 3.x. (f17406fd)
Fixed crashes when an LLM returns invalid JSON across all retries (now handled cleanly instead of raising a TypeError). (66423b85)
Fixed observations without source dates to preserve missing (None) temporal fields instead of incorrectly populating them. (891c33b1)

0.4.15

Features

Added observation_scopes to control the granularity/visibility of observations. (55af4681)
List documents API now supports filtering by tags (and fixes the q parameter description). (1d70abfe)
Added PydanticAI integration for persistent agent memory. (cab5a40f)
Added richer entity label support (optional labels, free-form values, multi-value fields, and UI polish). (9b96becc)
Added support for timestamp="unset" so content can be retained without a date. (f903948a)
OpenClaw can now automatically retain the last n+2 turns every n turns (default n=10). (ad1660b3)
Added configurable Gemini/Vertex AI safety settings for LLM calls. (73ef99e7)
Added extension hooks to customize root routing and error headers. (e407f4bc)

Improvements

Improved recall performance by fetching all recall chunks in a single query. (61bf428b)
Improved recall/retain performance and scalability for large memory banks. (7942f181)

Bug Fixes

Fixed the TypeScript SDK to send null (not undefined) when includeEntities is false. (15f4b876)
Prevented reflect from failing with context_length_exceeded on large memory banks. (77defd96)
Fixed a consolidation deadlock caused by retrying after zombie processing tasks. (c2876490)
Fixed observations count in the control plane that always showed 0. (eaeaa1f2)
Fixed ZeroEntropy rerank endpoint URL and ensured the MCP retain async_processing parameter is handled correctly. (f6f1a7d8)
Fixed JSON serialization issues and logging-related exception propagation when using the claude_code LLM provider. (ecb833f4)
Added bank-scoped request validation to prevent cross-bank/invalid bank operations. (5270aa5a)

0.4.14

Features

Add Chat SDK integration to give chatbots persistent memory. (fed987f9)
Allow configuring which MCP tools are exposed per memory bank, and expand the MCP tool set with additional tools and parameters. (3ffec650)
Enable the bank configuration API by default. (4d030707)
Support filtering graph-based memory retrieval by tags. (0bb5ca4c)
Add batch observations consolidation to process multiple observations more efficiently. (0aa7c2b3)
Add OpenClaw options to toggle autoRecall and exclude specific providers. (3f9eb27c)
Add a ZeroEntropy reranker provider option. (17259675)

Improvements

Increase customization options for reflect, retain, and consolidation behavior. (2a322732)
Include source document metadata in fact extraction results. (87219b73)

Bug Fixes

Raise a clear error when embedding dimensions exceed pgvector HNSW limits (instead of failing later at runtime). (8cd65b98)
Fix multi-tenant schema isolation issues in storage and the bank config API. (b180b3ad)
Ensure LiteLLM embedding calls use the correct float encoding format to prevent embedding failures. (58f2de70)
Improve recall performance by reducing memory usage during retrieval. (9f0c031d)
Handle observation regeneration correctly when underlying memories are deleted. (ac9a94ad)
Fix reflect retrieval to correctly populate dependencies and enforce full hierarchical retrieval. (8b1a4658)
Fix OpenClaw health checks by passing the auth token to the health endpoint. (40b02645)

0.4.13

Features

Switched the default OpenAI LLM to gpt-4o-mini. (325b5cc1)
Observation recall now includes the source facts behind recalled observations. (5569d4ad)
Added CrewAI integration to enable persistent memory. (41db2960)

Bug Fixes

Fixed npx hindsight-control-plane failing to run. (0758827d)
Improved MCP compatibility by aligning the local MCP implementation with the server and removing the deprecated stateless parameter. (ea8163c5)
Fixed Docker startup failures when using named Docker volumes. (ac739487)
Prevented reranker crashes when an upstream provider returns an error. (58c4d657)
Improved accuracy of fact temporal ordering by reducing per-fact time offsets. (c3ef1555)
Client timeout settings are now properly respected. (dcaa9f14)
Fixed documents not being tracked when fact extraction returns zero facts. (f78278ea)

0.4.12

Features

Accept and ingest PDFs, images, and common Office documents as inputs. (224b7b74)
Add the Iris file parser for improved document parsing support. (7eafba66)
Add async Retain support via provider Batch APIs (e.g., OpenAI and Groq) for higher-throughput ingestion. (40d42c58)
Allow Recall to return chunks only (no memories) by setting max_tokens=0. (7dad9da0)
Add a Go client SDK for the Hindsight API. (2a47389f)
Add support for the pgvectorscale (DiskANN) vector index backend. (95c42204)
Add support for Azure pg_diskann vector indexing. (476726c2)

Improvements

Improve reliability of async batch Retain when ingesting large payloads. (aefb3fcf)
Improve AI SDK tooling to make it easier to work with Hindsight programmatically. (d06a0259)

Bug Fixes

Ensure document tags are preserved when using the async Retain flow. (b4b5c44a)
Fix OpenClaw ingestion failures for very large content (E2BIG). (6bad6673)
Harden OpenClaw behavior (safer shell usage, better HTTP mode handling, and more reliable initialization), including per-user banks support. (c4610130)
Improve Python client async API consistency and reduce connection drop issues via keepalive timeout fixes. (8114ef44)

0.4.11

Features

Added support for LiteLLM SDK as an embeddings and reranking provider. (e408b7e)
Expanded Postgres search support with additional text/vector extensions, including TimescaleDB pg_textsearch and vchord/pgvector options. (d871c30)
Added hierarchical configuration scopes (system, tenant, bank) for more flexible multi-tenant setup and overrides. (8d731f2)
Added reverse proxy/base-path support for running Hindsight behind a proxy. (93ddd41)
Added MCP tools to create, read, update, and delete mental models. (f641b30)
Added a "docs" skill for agents/tools to access documentation-oriented capabilities. (dd1e098)
Added an OpenClaw configuration option to skip recall/retain for specific providers. (fb7be3e)

Improvements

Improved LiteLLM gateway model configuration for more reliable provider/model selection. (7d95a00)
Exposed actual LLM token usage in retain results to improve cost/usage visibility. (83ca669)
Added user-initiated attribution to request context to improve async task and usage attribution. (90be7c6)
Added OpenTelemetry tracing for improved request traceability and observability. (69dec8e)
Helm chart: split TEI embedding and reranker into separate deployments for independent scaling and rollout. (43f9a8b)
Helm chart: added PodDisruptionBudgets and per-component affinity controls for more resilient scheduling. (9943957)

Bug Fixes

Fixed a recursion issue in memory retention that could cause failures or runaway memory usage. (4f11210)
Fixed Reflect API serialization/schema issues for "based_on" so reflections are returned and stored correctly. (f9a8a8e)
Improved MCP server compatibility by allowing extra tool arguments when appropriate and fixing bank ID resolution priority. (7ee229b)
Added missing trust_code environment configuration support. (60574ee)
Hardened the MCP server with fixes to routing/validation and more accurate usage metering. (e798979)
Fixed the slim Docker image to include tiktoken to prevent runtime tokenization errors. (6eec83b)
Fixed MCP operations not being tracked correctly for usage metering. (888b50d)
Helm chart: fixed GKE deployments overriding the configured HINDSIGHT_API_PORT. (03f47e2)

0.4.10

Features

Provided a slimmer Docker distribution to reduce image size and speed up pulls. (f648178)
Added Markdown support in Reflect and Mental Models content. (c4ef090)
Added built-in Supabase tenant extension for running Hindsight with Supabase-backed multi-tenancy. (e99ee0f)
Added TenantExtension authentication support to the MCP endpoint. (fedfb49)

Improvements

Improved MCP tool availability/routing based on the endpoint being used. (d90588b)

Bug Fixes

Stopped logging database usernames and passwords to prevent credential leaks in logs. (c568094)
Fixed OpenClaw sessions wiping memory on each new session. (981cf60)
Fixed hindsight-embed profiles not loading correctly. (0430588)
Fixed tagged directives so they correctly apply to tagged mental models. (278718d)
Fixed a cast error that could cause failures at runtime. (093ecff)

Other

Added a docker-compose example to simplify local deployment and testing. (5179d5f)

0.4.9

Features

New AI SDK integration. (7e339e1)
Add a Python SDK for running Hindsight in embedded mode (HindsightEmbedded). (d3302c9)
Add streaming support to the hindsight-litellm wrappers. (665877b)
Add OpenClaw support for connecting to an external Hindsight API and using dynamic per-channel memory banks. (6b34692)

Improvements

Improve the mental models experience in the control plane UI. (7097716)
Reduce noisy Hugging Face logging output. (34d9188)

Bug Fixes

Improve recall endpoint reliability by handling timeouts correctly and rejecting overly long queries. (dd621a6)
Improve /reflect behavior with Claude Code and Codex providers. (a43d208)
Fix OpenClaw shell argument escaping for more reliable command execution. (63e2964)

0.4.8

Features

Added profile support for hindsight-embed, enabling separate embedding configurations/workspaces. (6c7f057)
Added support for additional LLM backends, including OpenAI Codex and Claude Code. (539190b)

Improvements

Enhanced OpenClaw and hindsight-embed parameter/config options for easier configuration and better defaults. (749478d)
Added OpenClaw plugin configuration options to select LLM provider and model. (8564135)
Server now prints its version during startup to simplify debugging and support requests. (1499ce5)
Improved tracing/debuggability by propagating request context through asynchronous background tasks. (44d9125)
Added stronger validation and context for mental model create/refresh operations to prevent invalid requests. (35127d5)

Bug Fixes

Improved embedding CLI experience with richer logs and isolated profiles to avoid cross-contamination between runs. (794a743)
Operation validation now runs correctly in the worker process, preventing invalid background operations from slipping through. (96f0e54)
Fixed unreliable behavior when using a custom PostgreSQL schema. (3825506)

0.4.7

Features

Add extension hooks to validate and customize mental model operations. (9c3fda7)
Add support for using an external embedding API provider in OpenClaw plugin (with additional OpenClaw compatibility fixes). (4b57b82)

Improvements

Speed up container startup by preloading the tiktoken encoding during Docker image builds. (039944c)

Bug Fixes

Prevent PostgreSQL insert failures by stripping null bytes from text fields before saving. (ef9d3a1)
Fix worker schema selection so it uses the correct default database schema. (d788a55)
Honor an already-set HINDSIGHT_API_DATABASE_URL instead of overwriting it in the hindsight-embed workflow. (f0cb192)

0.4.6

Improvements

Improved OpenClaw configuration setup to make embedding integration easier to configure. (27498f9)

Bug Fixes

Fixed OpenClaw embedding version binding/versioning to prevent mismatches when using the embed integration. (1163b1f)

0.4.5

Bug Fixes

Fixed occasional failures when retaining memories asynchronously with timestamps. (cbb8fc6)

0.4.4

Bug Fixes

Fixed async “retain” operations failing when a timestamp is provided. (35f0984)
Corrected the OpenClaw daemon integration name to “openclaw” (previously “openclawd”). (b364bc3)

0.4.3

Features

Add Vertex AI as a supported LLM provider. (c2ac7d0, 49ae55a)
Add Bearer token authentication for MCP and propagate tenant authentication across MCP requests. (0da77ce)

Improvements

CLI: add a --wait flag for consolidate and a --date filter for listing documents. (ff20bf9)

Bug Fixes

Fix worker polling deadlocks to prevent background processing from stalling. (f4f86e3)
Improve reliability of Docker builds by retrying ML model downloads. (ecc590c)
Fix tenant authentication handling for internal background tasks and ensure the control-plane forwards required auth to the dataplane. (03bf13e)
Ensure tenant database migrations run at startup and workers use the correct tenant schema context. (657fe02)
Fix control-plane graph endpoint errors when upstream data is missing. (751f99a)

Other

Rename the default bot/user identity from "moltbot" to "openclaw". (728ce13)

0.4.2

Features

Added Clawdbot/Moltbot/OpenClaw integration. (12e9a3d)

Improvements

Added additional configuration options to control LLM retry behavior. (3f211f0)
Added real-time logs showing a detailed timing breakdown during consolidation runs. (8781c9f)

Bug Fixes

Fixed hindsight-embed crashing on macOS. (c16ccc2)

0.4.1

Features

Added support for using a non-default PostgreSQL schema by default. (2b72e1f)

Improvements

Improved memory consolidation performance (benchmarking and optimizations). (b43ef98)

Bug Fixes

Fixed the /version endpoint returning an incorrect version. (cfcc23c)
Fixed mental model search failing due to UUID type mismatch after text-ID migration. (94cc0a1)
Added safer PyTorch device detection to prevent crashes on some environments. (67c4788)
Fixed Python packages exposing an incorrect version value. (fccbdfe)

0.4.0

Observations, Mental Models, new Agentic Reflect and Directives, read the announcement.

Features

Added support for providing a custom prompt for memory extraction. (3172e99)
Expanded the LiteLLM integration with async retain/reflect support, cleaner API, and support for tags/mission (including passing API keys correctly). (1d4879a)
Added a new worker service to run background tasks at scale. (4c79240)
MCP retain now supports timestamps. (b378f68)
Added support for installing skills via npx add-skill. (ec22317)

Improvements

CLI retain-files now accepts more file types. (1eeced3)

Bug Fixes

Fixed a macOS crash in the embed daemon caused by an XPC connection issue. (e5fc6ee)
Fixed occasional extraction in the wrong language. (87d4a36)
Fixed PyTorch model initialization issues that could cause startup failures (meta tensor/init problems). (ddaa5f5)

Features

Add memory tags so you can label and filter memories during recall/reflect. (20c8f8b)
Allow choosing different AI providers/models per operation. (e6709d5)
Add Cohere support for embeddings and reranking. (4de0730)
Add configurable embedding dimensions and OpenAI embeddings support. (70de23e)
Support custom base URLs for OpenAI-style embeddings and Cohere endpoints. (fa53917)
Add LiteLLM gateway support for routing LLM/embedding requests. (d47c8a2)
Add multilingual content support to improve handling and retrieval across languages. (c65c6a9)
Add delete memory bank capability. (4b82d2d)
Add backup/restore tooling for memory banks. (67b273d)

Improvements

Add retention modes to control how memories are extracted and stored. (fb31a35)
Add offline (optional) database migrations to support restricted/air-gapped deployments. (233bd2e)
Add database connection configuration options for more flexible deployments. (33fac2c)
Load .env automatically on startup to simplify configuration. (c06d9b4)
Expose an operation ID from retain requests so async/background processing can be tracked. (1dacd0e)
Add per-request LLM token usage metrics for monitoring and cost tracking. (29a542d)
Add LLM call latency metrics for performance monitoring. (5e1f13e)
Include tenant in metrics labels for better multi-tenant observability. (1ffc2a4)
Add async processing option to MCP retain tool for background retention workflows. (37fc7fb)

Bug Fixes

Fix extension loading in multi-worker deployments so all workers load extensions correctly. (f5f3fca)
Improve recall performance by batching recall queries. (5991308)
Improve retrieval quality and stability for large memory banks (graph/MPFP retrieval fixes). (6232e69)
Fix entities list being limited to 100 entities. (26bf571)
Fix UI only showing the first 1000 memories. (67c1a42)
Fix duplicated causal relationships and improve token usage during processing. (49e233c)
Improve causal link detection accuracy. (2a00df0)
Make retain max completion tokens configurable to prevent truncation issues. (7715a51)
Fix Python SDK not sending the Authorization header, preventing authenticated requests. (39e3f7c)
Fix stats endpoint missing tenant authentication in multi-tenant setups. (d6ff191)
Fix embedding dimension handling for tenant schemas in multi-tenant databases. (6fe9314)
Fix Groq free-tier compatibility so requests work correctly. (d899d18)
Fix security vulnerability (qs / CVE-2025-15284). (b3becb6)
Restore MCP tools for listing and creating memory banks. (9fd5679)

0.2.0

Features

Add additional model provider support, including Anthropic Claude and LM Studio. (787ed60)
Add multi-bank access and new MCP tools for interacting with multiple memory banks via MCP. (6b5f593)
Allow supplying custom entities when retaining memories via the retain endpoint. (dd59bc8)
Enhance the /reflect endpoint with max_tokens control and optional structured output responses. (d49e820)

Improvements

Improve local LLM support for reasoning-capable models and streamline Docker startup for local deployments. (eea0f27)
Support operation validator extensions and return proper HTTP errors when validation fails. (ce45d30)
Add configurable observation thresholds to control when observations are created/updated. (54e2df0)
Improve graph visualization to the control plane for exploring memory relationships. (1a62069)

Bug Fixes

Fix MCP server lifecycle handling so MCP lifespan is correctly tied to the FastAPI app lifespan. (6b78f7d)

0.1.15

Features

Add the ability to delete documents from the web UI. (f7ff32d)

Improvements

Improve the API health check endpoint and update the generated client APIs/types accordingly. (e06a612)

0.1.14

Bug Fixes

Fixes the embedded “get-skill” installer so installing skills works correctly. (0b352d1)

0.1.13

Improvements

Improve reliability by surfacing task handler failures so retries can occur when processing fails. (904ea4d)
Revamp the hindsight-embed component architecture, including a new daemon/client model and CLI updates for embedding workflows. (e6511e7)

Bug Fixes

Fix memory retention so timestamps are correctly taken into account. (234d426)

0.1.12

Features

Added an extensions system for plugging in new operations/skills (including built-in tenant support). (2a0c490)
Introduced the hindsight-embed tool and a native agentic skill for embedding/agent workflows. (da44a5e)

Improvements

Improved reliability when parsing LLM JSON by retrying on parse errors and adding clearer diagnostics. (a831a7b)

Bug Fixes

Fixed structured-output support for Ollama-based LLM providers. (32bca12)
Adjusted LLM validation to cap max completion tokens at 100 to prevent validation failures. (b94b5cf)

0.1.11

Bug Fixes

Fixed the standalone Docker image and control plane standalone build process so standalone deployments build correctly. (2948cb6)

0.1.10

This release contains internal maintenance and infrastructure changes only.

0.1.9

Features

Simplified local MCP installation and added a standalone UI option for easier setup. (1c6acc3)

Bug Fixes

Fixed the standalone Docker image so it builds and starts reliably. (b52eb90)
Improved Docker runtime reliability by adding required system utilities (procps). (ae80876)

0.1.8

Bug Fixes

Fix bank list responses when a bank has no name. (04f01ab)
Fix failures when retaining memories asynchronously. (63f5138)
Fix a race condition in the bank selector when switching banks. (e468a4e)

0.1.7

This release contains internal maintenance and infrastructure changes only.

0.1.6

Features

Added support for the Gemini 3 Pro and GPT-5.2 models. (bb1f9cb)
Added a local MCP server option for running/connecting to Hindsight via MCP without a separate remote service. (7dd6853)

Improvements

Updated the Postgres/pg0 dependency to a newer 0.11.x series for improved compatibility and stability. (47be07f)

0.1.5

Features

Added LiteLLM integration so Hindsight can capture and manage memories from LiteLLM-based LLM calls. (dfccbf2)
Added an optional graph-based retriever (MPFP) to improve recall by leveraging relationships between memories. (7445cef)

Improvements

Switched the embedded Postgres layer to pg0-embedded for a smoother local/standalone experience. (94c2b85)

Bug Fixes

Fixed repeated retries on 400 errors from the LLM, preventing unnecessary request loops and failures. (70983f5)
Fixed recall trace visualization in the control plane so search/recall debugging displays correctly. (922164e)
Fixed the CLI installer to make installation more reliable. (158a6aa)
Updated Next.js to patch security vulnerabilities (CVE-2025-55184, CVE-2025-55183). (f018cc5)

0.1.3

Improvements

Improved CLI and UI branding/polish, including new banner/logo assets and updated interface styling. (fa554b8)

0.1.2

Bug Fixes

Fixed the standalone Docker image so it builds/runs correctly. (1056a20)

/hindsight-docs

hindsight-docsreferenceschangelogindex.md

Third-party checks

Provenance

README badge

Related skills

referenceschangelogindex.md