Skip to content

claude-flow

v3.10.16 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 4d AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agentic-ai agentic-framework agentic-rag agentic-workflow agents ai-agents
+14 more
ai-assistant ai-coding ai-skills autonomous-agents claude-code codex mcp-server multi-agent multi-agent-systems npm skills swarm swarm-intelligence typescript

Summary

AI summary

New structured distillation module improves trajectory MRR by 41.8%.

Changes in this release

Feature Low

Adds hooks_post-edit to feed trajectory pipeline with one-step trajectory from edit outcome.

Adds hooks_post-edit to feed trajectory pipeline with one-step trajectory from edit outcome.

Source: llm_adapter@2026-05-30

Confidence: high

 —
Feature Low

Adds hooks_post-command to feed trajectory pipeline with one-step trajectory from command outcome.

Adds hooks_post-command to feed trajectory pipeline with one-step trajectory from command outcome.

Source: llm_adapter@2026-05-30

Confidence: high

 —
Feature Low

Modifies hooks_intelligence_trajectory-end to also bump globalStats and include learning.globalStatsTrajectoriesDelta in response.

Modifies hooks_intelligence_trajectory-end to also bump globalStats and include learning.globalStatsTrajectoriesDelta in response.

Source: llm_adapter@2026-05-30

Confidence: high

 —
Feature Low

All handlers now return learningPath ('trajectory-pipeline' or 'recorded-only') and an explicit note naming the fired hook.

All handlers now return learningPath ('trajectory-pipeline' or 'recorded-only') and an explicit note naming the fired hook.

Source: llm_adapter@2026-05-30

Confidence: high

 —
Feature Low

Introduces new module src/memory/structured-distill.ts with 4‑field schema (summary, detail, labels, paths).

Introduces new module src/memory/structured-distill.ts with 4‑field schema (summary, detail, labels, paths).

Source: llm_adapter@2026-05-30

Confidence: high

 —
Feature Low

Adds new corpus bench/trajectory-mrr-corpus.json containing 30 paired (raw, query) trajectories.

Adds new corpus bench/trajectory-mrr-corpus.json containing 30 paired (raw, query) trajectories.

Source: llm_adapter@2026-05-30

Confidence: high

 —
Feature Low

Adds new MRR harness scripts/benchmark-trajectory-mrr.mjs bridging ONNX embedder with hash‑deterministic fallback.

Adds new MRR harness scripts/benchmark-trajectory-mrr.mjs bridging ONNX embedder with hash‑deterministic fallback.

Source: llm_adapter@2026-05-30

Confidence: high

 —
Feature Low

Adds 12 new tests (9 schema + 3 Round B wiring) to the test suite.

Adds 12 new tests (9 schema + 3 Round B wiring) to the test suite.

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

 —
Performance Medium

Improves MRR from 0.0964 to 0.1367 (+41.8%) using distilled trajectories.

Improves MRR from 0.0964 to 0.1367 (+41.8%) using distilled trajectories.

Source: llm_adapter@2026-05-30

Confidence: high

 —
Full changelog

Two SOTA-direction rounds packaged together.

Round B — finishes the #2245 wiring story (closes the "wiring side" gap left in ADR-074/ADR-075)

  • hooks_post-edit now feeds the trajectory pipeline (synthesises a one-step trajectory from the edit outcome).
  • hooks_post-command does the same for command outcomes.
  • hooks_intelligence_trajectory-end ALSO bumps globalStats (was only feeding sonaCoordinator); response includes learning.globalStatsTrajectoriesDelta.
  • Every handler returns learningPath: 'trajectory-pipeline' | 'recorded-only' + an explicit note naming what fired.

Round C — Structured Distillation (#2241 §SOTA, arXiv:2603.13017)

  • New module src/memory/structured-distill.ts — 4-field schema (summary / detail / labels / paths), rule-based deterministic extractor, embedding-ready serialiser that puts high-signal tokens at the front.
  • New corpus bench/trajectory-mrr-corpus.json — 30 paired (raw, query) trajectories.
  • New MRR harness scripts/benchmark-trajectory-mrr.mjs — bridge ONNX embedder with hash-deterministic fallback (clearly warned as degraded).

Measured proof (bridge ONNX, Xenova/all-MiniLM-L6-v2, N=30):

| Metric | Raw | Distilled | Δ |
|---|---:|---:|---:|
| MRR | 0.0964 | 0.1367 | +0.0403 (+41.8%) |
| Direction | — | — | ✅ distilled better |

Direction matches arXiv:2603.13017 (+0.014 absolute on a 214K paper corpus); relative delta is larger here because the small curated corpus benefits more from labels-and-paths-first ordering.

Honest: a rule-based distiller cannot deliver the paper's 11× byte compression (current ratio: 0.74× — distilled is 35% bigger). The schema, corpus, harness, and serialiser are in place so a future round can plug in a learned distiller as a drop-in extractor swap and pick up that compression number while keeping this MRR direction.

Tests: 9 schema tests + 3 Round B wiring tests = 12 new. Affected suite 135/135.

Install: npx [email protected]

View diff on GitHub

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

Share on X Share on Bluesky

Track claude-flow

Get notified when new releases ship.

Sign up free

About claude-flow

Deploy multi-agent swarms with coordinated workflows.

All releases →

Related context

Beta — feedback welcome: [email protected]