Skip to content

Loki Mode

v7.91.1 Bugfix

This release fixes issues for SREs watching stability and regressions.

Published 29d AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

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

Whitelisted claude login in caveman moat-audit to fix a false-positive CI failure.

Full changelog

Fix: green the CI shell suite (caveman moat-audit false positive)

The v7.91.0 fail-fast auth preflight added an error-message line that prints
claude login as a fix hint. The caveman moat-audit (test-caveman-flags.sh)
does a tree-wide scan for unsuppressed claude subcalls and matched that literal
string, failing the CI "Shell tests" job. Whitelisted claude login in the audit
(it is a user-instruction string, not a spawned subcall - same class as the
already-whitelisted claude auth status / command -v claude). No runtime
behavior change; all other v7.91.0 features intact.

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 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]