This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+8 more
Summary
AI summaryExecutor CLIs now use configured reasoning-effort defaults when omitted in task YAML or environment profiles.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Leaves executor.effort unset when omitted in both task YAML and environment profile. Leaves executor.effort unset when omitted in both task YAML and environment profile. Source: llm_adapter@2026-07-15 Confidence: high |
— |
| Feature | Low |
Delegates effort selection to the chosen provider CLI when executor.effort is unset. Delegates effort selection to the chosen provider CLI when executor.effort is unset. Source: granite4.1:30b@2026-07-15-audit Confidence: low |
— |
| Refactor | Low |
Updates packaged Galley plugins to version 0.1.25. Updates packaged Galley plugins to version 0.1.25. Source: granite4.1:30b@2026-07-15-audit Confidence: low |
— |
Full changelog
This patch release lets executor CLIs use their configured reasoning-effort defaults.
What's Changed
- When both task YAML and the environment profile omit
executor.effort, Galley leaves it unset and delegates effort selection to the chosen provider CLI. - Explicit task and environment effort settings keep their existing precedence and validation behavior.
- Packaged Galley plugins are updated to v0.1.25 with aligned task, profile, and setup guidance.
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 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.
Related context
Related tools
Beta — feedback welcome: [email protected]