Skip to content

Loki Mode

v7.41.2 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 1mo 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

Fixed two shell test defects from v7.41.1 and added a regression guard for the plan JSON output.

Full changelog

CI integrity patch. The v7.41.1 release shipped to npm but its Tests workflow
went red on two test-only defects (the runtime code was unaffected). This patch
makes the suite green again and adds a permanent guard for the class of
regression that v7.41.1 introduced.

Fixed

  • Shell tests: tests/test-completion-summary.sh now accepts the v7.41.1
    pathspec-filtered review_cmd (git diff <sha>..HEAD -- . ':(exclude).loki/');
    the glob previously required the command to end at ..HEAD.
  • ShellCheck: _loki_caveman_infer_level in autonomy/lib/claude-flags.sh is
    annotated # shellcheck disable=SC2120 (its $1 is intentionally optional with
    a global fallback). Older shellcheck on CI flagged SC2120 as a warning and
    failed the lint gate; newer shellcheck does not.

Added

  • tests/test-plan-json-smoke.sh: a fast direct regression guard asserting
    loki plan --json exits 0, emits valid JSON with a populated
    cost.iterations_by_model, and never prints "unbound variable" (the v7.41.1
    heredoc $5-unbound regression). Wired into tests/run-all-tests.sh.
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]