This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+14 more
Summary
AI summaryAdded getUnifiedLearningStats() to aggregate four distinct stat sources and flag cross‑store drift.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds getUnifiedLearningStats() returning all four sub-views with source paths Adds getUnifiedLearningStats() returning all four sub-views with source paths Source: llm_adapter@2026-05-30 Confidence: high |
— |
| Feature | Medium |
Adds hooks_intelligence_unified-stats MCP tool exposing unified learning stats Adds hooks_intelligence_unified-stats MCP tool exposing unified learning stats Source: llm_adapter@2026-05-30 Confidence: high |
— |
| Feature | Medium |
Exports getMemoryBridgeStats() and getNeuralStoreStats() helper functions Exports getMemoryBridgeStats() and getNeuralStoreStats() helper functions Source: llm_adapter@2026-05-30 Confidence: high |
— |
| Feature | Medium |
Introduces a consistency block that flags cross-store drift between stats sources Introduces a consistency block that flags cross-store drift between stats sources Source: llm_adapter@2026-05-30 Confidence: high |
— |
| Feature | Low |
Adds 7 cross-store consistency tests for verification Adds 7 cross-store consistency tests for verification Source: llm_adapter@2026-05-30 Confidence: high |
— |
| Dependency | Low |
Updates installation command to use npx [email protected] Updates installation command to use npx [email protected] Source: llm_adapter@2026-05-30 Confidence: high |
— |
| Bugfix | Medium |
Fixes aggregation to combine views instead of store duplicates, resolving contradictory stat sources Fixes aggregation to combine views instead of store duplicates, resolving contradictory stat sources Source: llm_adapter@2026-05-30 Confidence: high |
— |
Full changelog
Resolves the "four contradictory stat sources" item ADR-074 deferred to a future round.
The four sources turned out not to be duplicates — they authoritatively measure four different layers (globalStats = trajectory-pipeline counters, sonaCoordinator = in-process SONA, memory-bridge = AgentDB entries, neural-patterns = neural store rows). So the fix is to aggregate the view, not the store.
New surface
getUnifiedLearningStats()— returns all 4 sub-views with each sub-view naming its source pathhooks_intelligence_unified-statsMCP tool exposing itgetMemoryBridgeStats()+getNeuralStoreStats()— exported helpers- A
consistencyblock that flags cross-store drift (e.g. globalStats reports N patterns but neural_patterns is empty) instead of silently disagreeing
Verification
- 7 cross-store consistency tests
- Benchmark §F observed: global=10/11 tracks SONA, bridge=10 rows, neural=10, sona.available=true, 1 consistency note correctly flagging the pretrain-vs-neural-store gap
- 123/123 across unified-stats + self-learning + mcp-tools-deep
Install: npx [email protected]
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
Related context
Related tools
Beta — feedback welcome: [email protected]