This release adds 2 notable features for engineering teams evaluating rollout.
Published 3mo
AI Agents & Assistants
✓ No known CVEs patched
✓ 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
Affected surfaces
breaking_upgrade
Summary
AI summaryInternal architecture refactored to separate high‑risk components into focused owners while keeping public imports stable.
Full changelog
v0.15.7
Completes the post-usage-governance package-boundary cleanup, keeping public imports stable while splitting high-risk runtime, compiler, contract, entrypoint, and runner internals into focused owners.
Added
- ADR-0007, ADR-0008, and ADR-0009 for runtime authority packages, the contract facade, and stage metadata.
- Source hygiene guardrails for dependency direction, contract-layer imports, path-only workspace modeling, generic helper modules, and wildcard imports.
Changed
- Split workspace bootstrap and CLI view ownership.
- Packaged runtime usage governance and graph authority as internal authority domains.
- Split compiler internals, contracts, entrypoint parsing/linting, stage metadata, and Codex CLI runner internals behind stable public facades.
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 Millrace
All releases →Related context
Related tools
Beta — feedback welcome: [email protected]