vectorize-io/hindsight v0.9.1 on GitHub

What's Changed

docs: 0.9.0 changelog + blog posts by @nicoloboschi in #3189
fix(coding-agents): seed the actual harness, not the "opencode" default (#3247, #3248) by @nicoloboschi in #3266
fix(docker): repair PGroonga Compose image by @JiehoonKwak in #3316
fix(engine): stop concurrent bank deletes from deadlocking on vector-index DDL by @nicoloboschi in #3245
fix(coding-agents): fall back from filesystem-root worktrees by @koriyoshi2041 in #3286
fix(worker): serialise graph_maintenance per bank at claim time by @nicoloboschi in #3235
fix(llm): forward extra body to Codex requests by @koriyoshi2041 in #3305
fix(api): knowledge-base search 500s on non-native text-search backends (#3268) by @nicoloboschi in #3318
test(ci): gate every build on hermes-agent@main co-installability by @nicoloboschi in #3265
fix(config): validate bank config value types and stop them wedging tasks (#3218) by @nicoloboschi in #3319
test(bank-template): round-trip every exportable field through export+import by @nicoloboschi in #3324
perf(reflect): drop retrieval plumbing from reflect tool results by @JoshFunnell in #3310
feat(bank-template): make every bank config field export+importable by @nicoloboschi in #3332
fix(structured-doc): add TableBlock to fix markdown table rendering by @dragonkid in #3289
feat(reflect): resolve entity names on reflect sub-recalls by @nicoloboschi in #3334
fix(api): gate knowledge-base routes through the operation validator (#3312) by @nicoloboschi in #3331
fix(coding-agents): write back only the new turns (append + idempotent retain) by @nicoloboschi in #3336
Pin embed to the metapackage release by @koriyoshi2041 in #3261
feat(transfer): carry Knowledge Pages tree + regenerate mental-model search state on import (#3308, #3323) by @nicoloboschi in #3330
fix(api): return 400 for malformed UUID on GET /entities/{id} and /memories/{id}/history by @Alan5168 in #3260
fix(control-plane): surface direct request failures by @Sanderhoff-alt in #3333
fix(api): add a DB-free liveness probe so a slow database stops restarting pods by @nicoloboschi in #3337
fix(coding-agents,ci): drop the periodic re-sync; stop running doc examples for integration changes by @nicoloboschi in #3341
fix(coding-agents): bound transcript reads so an oversized session still retains (#3292) by @nicoloboschi in #3345
fix(ollama): make native think configurable via extra_body by @nicoloboschi in #3344
feat(llm): xai-oauth provider — run the engine's LLM lanes on a flat-rate SuperGrok subscription (device-code OAuth, no API key), production-hardened by @JoshFunnell in #3272
fix(reflect): provide the current date for temporal reasoning by @koriyoshi2041 in #3287
fix(transfer): reject a wrong import zip with a 400 that names the fix by @nicoloboschi in #3339
blog: guest post — writenode, continuity over retrieval (Josh Groves) by @benfrank241 in #3243
docs(config): name LM Studio/Ollama/Volcano for LLM_STRICT_SCHEMA by @nicoloboschi in #3348
fix(search): use PGroonga for Knowledge Pages by @JiehoonKwak in #3335
fix(engine): normalize whitespace in candidate entity names at resolution intake by @nicoloboschi in #3338
fix(gemini): fail fast on deterministic 400 INVALID_ARGUMENT (#3256) by @nicoloboschi in #3347
fix(ci): compare OpenAPI against the merge-base; build benchmark role configs whole by @nicoloboschi in #3349
feat(coding-agents): retainTags / retainMetadata, with HINDSIGHT_RETAIN_TAGS (#3269, #2896) by @nicoloboschi in #3346
fix(coding-agents): seed bank missions once, then leave them to the user (#2492) by @nicoloboschi in #3352
fix(coding-agents): report configured MCP harness by @TheAngryPit in #3342
feat(llm): restore server-side prompt caching on load-balanced OpenAI-compatible backends — measured 0.085% aggregate hit rate without affinity vs 99.4% with, same backend by @JoshFunnell in #3271
fix(retain): cut oversized sub-batches on native chunk boundaries (#3282) by @nicoloboschi in #3351
perf(docs): switch the Docusaurus build to Rspack + SWC by @nicoloboschi in #3357
feat(transfer): async document export (#3321) by @nicoloboschi in #3340
fix(obsidian): scope sync index to bank and API target (#3257) by @benfrank241 in #3354
fix(coding-agents): drop harness transport wrappers from retained turns (#3023) by @nicoloboschi in #3378
docs(coding-agents): say which harnesses retainEveryTurns applies to by @nicoloboschi in #3380
fix(transfer): mint a fresh internal_id on whole-bank import (#3270) by @nicoloboschi in #3353
fix(coding-agents): drop Claude Code's compaction summary from retained turns (#3379) by @nicoloboschi in #3383
fix deletion of failed document uploads by @koriyoshi2041 in #3366
fix(retain): sweep observations when delta retain deletes chunks by @nicoloboschi in #3384
docs: correct the Azure OpenAI base URL by @nicoloboschi in #3385
feat(llm): opt-in forced-tool structured output for LiteLLM providers (#3300) by @nicoloboschi in #3382
feat(memories): per-bank store capabilities on main (writes_memory_rows_in_sql_for / owns_document_store_for) by @nicoloboschi in #3388
fix(retain): fold shared document_id items on the sync path (#3363) by @nicoloboschi in #3386
fix(reflect): decouple page max_tokens from the provider output cap (#3365) by @nicoloboschi in #3389
fix(retain): match chunk-delete link endpoints through indexable joins (#3387) by @nicoloboschi in #3393
feat(agent-plugin): portable Hindsight plugin for the Agent Plugins standard by @benfrank241 in #3394
fix(retain): stop concurrent appends to one document from losing turns by @nicoloboschi in #3395
fix(stats): drop permanently failed memories from pending_consolidation by @nicoloboschi in #3397
blog: Best Open-Source Agent Memory Systems (Self-Hosted, 2026) by @benfrank241 in #3192
blog: update Best Open-Source Agent Memory Systems date to 2026-08-11 by @benfrank241 in #3399
fix(reflect): split synthesis — parallel claim extraction + reduce instead of dropping over-budget evidence by @nicoloboschi in #3392
fix(coding-agents): bound automatic reflect budget by @TheAngryPit in #3364
feat(coding-agents): add Prime Agent as a supported harness by @benfrank241 in #3240
fix(compose): use HINDSIGHT_API_LLM_API_KEY env var by @ishfuseini in #3398
fix(coding-agents): resolve the project when the working directory is gone (supersedes #3110) by @nicoloboschi in #3410
fix(retain): globalise memory_links lock order on the insert path (#3396) by @nicoloboschi in #3406
perf(graph): decouple stale-cooccurrence prune from hub-entity degree (#3367) by @nicoloboschi in #3408
docs(reflect): clarify tag-scoped directive behavior by @Sanderhoff-alt in #3038
fix(coding-agents): stop the prompt hook wiping the retain cursor; write state atomically (supersedes #3136) by @nicoloboschi in #3412
fix(knowledge): sync backing mental_model name on page rename (#3307) by @nicoloboschi in #3407
fix(search): stop extreme relative date offsets from crashing recall (#3217) by @nicoloboschi in #3413
feat(coding-agents)!: drop retainEveryTurns — batching belongs on the server by @nicoloboschi in #3415
fix(consolidation): cancel sibling tag groups when a batch fails by @nicoloboschi in #3417
feat(coding-agents): apply retain attribution to all ingestion paths by @voarsh2 in #3418
fix(recall): fill the source_facts budget in rank order and flag truncation (#3221) by @nicoloboschi in #3419
fix: untrack the coding-agents node_modules symlink by @nicoloboschi in #3422
fix(embed): define daemon stop() success by port occupancy, not the health probe by @Alan5168 in #3171
feat(coding-agents): handle 429 on both the request and the poll path by @nicoloboschi in #3423
fix(consolidation): refresh mental models every round, not just the final one (#3411) by @nicoloboschi in #3416
feat(coding-agents): optInOnly — run memory only in projects that were opted in by @nicoloboschi in #3433
fix(mental-models): trace delta-ops call and decouple its completion cap (#3421) by @nicoloboschi in #3424
fix(graph-maintenance): drive the entity prune off a queue, not a bank-wide sweep (#3222) by @nicoloboschi in #3409
fix(engine): scope document statements by bank_id (#3429) by @nicoloboschi in #3435
retain: don't hold the data-plane connection across a separate-store write by @nicoloboschi in #3414
fix(coding-agents): bound the 429 retry by the caller's clock, not a constant by @nicoloboschi in #3425
retrieval: one unified store call for all arms + all fact types by @nicoloboschi in #3434
fix(files): give each batched file a unique storage key (#3226) by @nicoloboschi in #3437
fix(llm): preserve inline literals in _strip_reasoning_tags by @hundunweimi in #3426
blog: Give Any Agent Plugins Client Long-Term Memory by @benfrank241 in #3440
fix(reranker): batch FlashRank passages instead of one unbounded forward pass (#3355) by @nicoloboschi in #3441
fix(release): ship Rust CLI license notices by @Sanderhoff-alt in #3447
fix(api): correct stale OpenAPI examples by @Sanderhoff-alt in #3436
fix(llamacpp): pass extra_body through factory to LlamaCppLLM by @handnewb in #3431
docs(config): clarify that zeroing maintenance intervals stops scheduling, not execution by @nicoloboschi in #3454
fix(coding-agents): say when a turn is running without memory by @nicoloboschi in #3455
perf(recall): score observation expansion set-wise, not per candidate row (#3085) by @nicoloboschi in #3451
fix(ci): fetch crates for all targets before the offline license scan by @nicoloboschi in #3457
perf(recall): make temporal extraction ~9x faster without changing behaviour by @nicoloboschi in #3452
fix(release): keep package-lock.json's version in step with the release by @nicoloboschi in #3456
refactor(kb): create pages and mental models atomically by @Sanderhoff-alt in #3369
fix(coding-agents): run the opencode survey under our own agent, not plan mode by @nicoloboschi in #3460
feat(api): forward allowlisted request headers to extensions by @rares-mollie in #3428
feat(docs): blog list infinite scroll, search, category badges, mobile polish by @nicoloboschi in #3463
recall: carry entity_ids on results, skip redundant re-fetch in entity_build by @nicoloboschi in #3461
feat(eliza): Hindsight long-term memory integration for elizaOS by @benfrank241 in #2385
fix(llm): send an explicitly configured reasoning_effort (#3449) by @nicoloboschi in #3459
docs(examples): add TEI embeddings + reranker docker-compose example by @nicoloboschi in #3465
Dedupe graph maintenance submits against running jobs, not just pending ones by @cdbartholomew in #3444
blog: Claude Code Now Builds and Reads Its Own Knowledge Base by @benfrank241 in #3464
docs: link Hindsight Academy from the docs navbar and footer by @benfrank241 in #3473
feat(memories): assert_writable — let a store close a bank to writes by @nicoloboschi in #3489

New Contributors

@JoshFunnell made their first contribution in #3310
@dragonkid made their first contribution in #3289
@Alan5168 made their first contribution in #3260
@TheAngryPit made their first contribution in #3342
@ishfuseini made their first contribution in #3398
@hundunweimi made their first contribution in #3426
@rares-mollie made their first contribution in #3428

Full Changelog: v0.9.0...v0.9.1