Skip to content

Loki Mode

v7.95.0 Security

This release includes 1 security fix for security teams reviewing exposed deployments.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →
This release patches 1 known CVE

Topics

ai-agents aider anthropic autonomous ci-cd claude
+13 more
cline code-review devops gemini github-action github-issues loki-mode multi-agent openai-codex openapi pull-request-review sdlc spec-driven-development

Summary

AI summary

Completion gates now fail closed if core gate functions cannot be loaded.

Full changelog

Trust moat: completion gates now fail CLOSED

  • Fail-closed completion gates (autonomy/run.sh): each completion gate was
    armed as type <gate_fn> && ! <gate_fn>, so if the council library failed to
    source, the type probe was false and the gate was silently skipped - a
    completion claim could then reach the accept branch UNVERIFIED (a fake-green).
    The gate chain now verifies the core gate functions are loadable before running;
    if any is missing, the completion claim is refused and the loop keeps iterating
    rather than passing ungated. Never fires in a healthy install (functions are
    sourced); only triggers on a genuinely broken/partial load, exactly when
    failing open is unsafe. Found by the cycle-3 adversarial bug-hunt.

Breaking Changes

  • Completion gates now refuse claims when any core gate function is missing (fail-closed behavior).

Security Fixes

  • Fail‑closed completion gates prevent unverified claims from being accepted when the council library fails to source.

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 Loki Mode

Get notified when new releases ship.

Sign up free

About Loki Mode

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates.

All releases →

Related context

Beta — feedback welcome: [email protected]