hindsight

What's Changed

• docs(retrieval): add pgroonga to the BM25 backends table by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1783
• docs: add 0.7.0 changelog and release blog post by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1781
• fix(control-plane): add graph_maintenance to operations type filter by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1785
• fix(control-plane): polish zh translation for naturalness by @XIYBHK in https://github.com/vectorize-io/hindsight/pull/1791
• docs(blog): OpenClaw agent that remembers your codebase by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1768
• fix(openclaw): stop silently skipping dispatch on synthetic-main + static-banking setups by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1802
• fix markdown tables in mental models and cosmetic issues by @chrislatimer in https://github.com/vectorize-io/hindsight/pull/1800
• docs(retrieval): note pg_search configurable tokenizer in BM25 backends table by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1790
• fix(openclaw): label "Current time" as UTC in injected memory context by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1804
• fix(api): anchor recall recency to query timestamp by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/1788
• fix(openclaw): flush un-retained turns on session_end by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1806
• feat(embeddings): add token refresh to CodexOAuthEmbeddings; extract CodexAuthManager by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1712
• feat(control-plane): add Chinese locale variants by @MapleEve in https://github.com/vectorize-io/hindsight/pull/1784
• docs(models): add claude-code Docker recipe with host Max Plan auth by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1526
• feat(integrations): default recallTypes to ['observation'] for openclaw + claude-code by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1808
• feat(reranker): per-provider HTTP timeout env vars by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1810
• fix(embeddings): clean up CodexOAuthEmbeddings token-refresh follow-up by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1809
• docs(docker): add local llama.cpp sidecar compose example by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1814
• feat(api): configure LLM reasoning effort via environment by @s9rkn in https://github.com/vectorize-io/hindsight/pull/1815
• docs(integrations): default recallTypes to ["observation"] for openclaw + claude-code (#1808) by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1812
• fix(retain): keep oversized items in one async child to stop FK race (#1795) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1805
• feat(worker): add priority-based consolidation bank scheduling by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1813
• fix(consolidation): indefinite retry with backoff + dedup-by-bank guard by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1811
• docs(models): list openai-codex and openrouter in embeddings Supported Providers table by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1792

New Contributors

• @XIYBHK made their first contribution in https://github.com/vectorize-io/hindsight/pull/1791
• @MapleEve made their first contribution in https://github.com/vectorize-io/hindsight/pull/1784
• @s9rkn made their first contribution in https://github.com/vectorize-io/hindsight/pull/1815

Full Changelog: https://github.com/vectorize-io/hindsight/compare/v0.7.0...v0.7.1