Skip to content

Galley

v0.8.4 Breaking

This release includes breaking changes for platform teams planning a safe upgrade.

Published 26d AI Coding Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agentic-workflow ai-coding claude-code code-review codex coding-agents
+8 more
daemon developer-tools glm grok openai orchestration task-runner workflow-automation

Affected surfaces

auth rbac

Summary

AI summary

Supervisor review prompts tightened to use a shared semantic contract and evidence now names authoritative sources.

Full changelog

Changed

  • Tightened supervisor review prompts so acceptance decisions are driven by a shared semantic contract rather than provider-specific duplicate rules.
  • Supervisor acceptance evidence now names authoritative sources for identifier-backed data sets, mappings, ordering, and categories before accepting.
  • Claude and Codex supervisor prompts now focus on runtime guidance, while brittle prompt-body section tests were removed in favor of routing and schema delivery tests.
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 Galley

Get notified when new releases ship.

Sign up free

About Galley

Local-first runtime for supervised AI coding tasks: isolated git worktrees, supervisor review against acceptance criteria, retry/escalate loops, on-disk run evidence, and PR handoff. Supports Codex CLI and Claude Code. Go, MIT.

All releases →

Related context

Beta — feedback welcome: [email protected]