This release includes breaking changes for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Summary
AI summaryFixed eight regressions including endpoint looping, embedding fallbacks, memory discoverability, graph building, extraction cancellation, recall filtering, causal link persistence, and dead code removal.
Full changelog
External code review found 8 regressions introduced by the 14 rapid-fire commits that tried to fix benchmark extraction stalls. All 8 are now fixed.
Fixed (Critical)
/extractendpoint now loops through ALL batches instead of processing one batch and stopping- Batch fallback facts use real embedding vectors instead of empty
[](was crashing onvector(1536)column)
Fixed (High)
- Preference-only memories keep their fallback fact_unit so they stay discoverable in fact search
- Entity graph builds automatically after extraction (no more dead graph retrieval)
fireAndForgetExtractionuses AbortController to cancel zombie extractions on timeout
Fixed (Medium)
- Fact-based recall now applies scope, tags, and date filters (was ignoring all caller filters)
- Causal relations from GPT extraction are persisted to
fact_linkstable (graph traversal can use them) - Dead code cleanup: removed unused
factEntityMapvariable andconsolidateObservationsimport
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About AlekseiMarchenko/central-intelligence
Persistent memory for AI agents. Five tools (remember, recall, context, forget, share) with semantic search via vector embeddings and agent/user/org scoping. Works with Claude Code, Cursor, Windsurf, and any MCP client.
Related context
Related tools
Beta — feedback welcome: [email protected]