Skip to content

Millrace

v0.17.4 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-loop agentic-ai-development agentic-coding agentic-engineering agentic-framework agentic-workflow
+7 more
autonomous-agents governed-autonomy governed-loop harness-engineering loop-engineering runtime-engine runtime-engineering

Summary

AI summary

Compile validation now rejects Curator learning triggers lacking target_skill_id or preferred_output_paths.

Full changelog

Added

  • Added first-class learning no-op terminal outcomes for Analyst, Professor, and Curator so reviewed no-change learning requests close as done instead of appearing blocked.

Changed

  • Changed built-in learning-mode generic Doublechecker success learning to start at Analyst instead of direct Curator, keeping vague success evidence in the research stage.

Fixed

  • Compile validation now rejects direct Curator learning trigger rules unless they include target_skill_id or preferred_output_paths, preventing runtime-generated Curator requests that have no safe skill destination.

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

Track Millrace

Get notified when new releases ship.

Sign up free

About Millrace

All releases →

Related context

Beta — feedback welcome: [email protected]