Skip to content

Loki Mode

v7.86.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

✓ 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

The Evidence Receipt summary endpoint aggregates verification counts and displays a dashboard badge.

Full changelog

The trust story, made visible (honestly)

The Evidence Receipt shipped in v7.85.0; this release surfaces it so a reader can
see the trust differentiator without digging, and re-verify any of it themselves.

  • Honest verified-counter: a new GET /api/proofs/summary aggregates the project's
    Evidence Receipts into {total, verified, with_gaps, not_verified, unknown},
    computed ONLY from the deterministic honesty headline. A v1.0 receipt with no
    headline is counted as unknown, never as verified. Empty means zero, shown
    honestly. The dashboard shows a small header badge from this (and nothing when
    there are no receipts) -- it reflects real receipts, never an invented number.
  • Positioning: README and SKILL now describe the trust layer plainly -- Loki does
    not call work done until it is verified, and every build produces an Evidence
    Receipt you can re-check with loki proof verify. The claim is specific and
    true (honesty-of-done, independently re-verifiable); it does not claim the
    generated code is bug-free.

No new product capability beyond v7.85.0 -- this makes the existing one legible.

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]