Starstruk Logo MarkStarstruk

v3.10.0

ruvnet/ruflov3.10.0May 25, 2026by ruvnet

AI Summary

This release completes the ADR-130 Unified Knowledge Graph Backend implementation by shipping Phases 4-6. It introduces a plugin adapter for graph-to-plugin communication, three pathfinder algorithms (Personalized PageRank, Dynamic MinCut, and Spectral Sparsification), and a comprehensive benchmark suite with defined performance targets.

Key Highlights

  • Completes full ADR-130 implementation (P1-P3 in 3.9.0 + P4-P6 in 3.10.0)
  • P4 Plugin Adapter enables graph_edges reads/writes to plugin runtime
  • P5 Pathfinder Algorithms: PPR, Dynamic MinCut, and Spectral Sparsification for graph traversal
  • P6 Benchmark Suite with defined performance targets (>500 ops/sec write, <10ms p99 k-hop queries)
  • Tracking issue #2128

New Features

  • Plugin Adapter (P4): Graph-to-plugin bridge exposing graph_edges reads/writes to the plugin runtime
  • Pathfinder Algorithms (P5): Personalized PageRank (PPR) for relevance-weighted neighbourhood scoring
  • Pathfinder Algorithms (P5): Dynamic MinCut for partitioning agent communication graphs
  • Pathfinder Algorithms (P5): Spectral Sparsification for efficient sparse approximations
  • Benchmark Suite (P6): Write throughput >500 ops/sec (single-session, N=200 edges)
  • Benchmark Suite (P6): k-hop query latency: depth-1 <10ms p99, depth-3 <50ms p99
  • Benchmark Suite (P6): PQ encode <1ms p99, PQ decode <0.5ms p99
  • Benchmark Suite (P6): SQLite footprint <1 KB/edge

Full Release Notes

## ADR-130 Unified Knowledge Graph Backend — Phases 4-6

Completes the full ADR-130 implementation shipping P1-P3 (3.9.0) + P4-P6 (3.10.0).

### New in 3.10.0

- **P4 — Plugin Adapter**: Graph-to-plugin bridge exposing `graph_edges` reads/writes to the plugin runtime
- **P5 — Pathfinder Algorithms**: Three graph traversal strategies over the `graph_edges` SQLite backend:
  - Personalized PageRank (PPR) for relevance-weighted neighbourhood scoring
  - Dynamic MinCut for partitioning agent communication graphs
  - Spectral Sparsification for efficient sparse approximations
- **P6 — Benchmark Suite**: CI-friendly benchmark measuring:
  - Write throughput: >500 ops/sec (single-session, N=200 edges)
  - k-hop query latency: depth-1 <10ms p99, depth-3 <50ms p99
  - PQ encode <1ms p99, PQ decode <0.5ms p99
  - SQLite footprint: <1 KB/edge

### Install

```
npx @claude-flow/cli@latest
npx claude-flow@latest
npx ruflo@latest
```

Tracking issue: #2128