OMK

v0.90.7 Feature

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

Published 16d AI & Machine Learning

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-orchestration agent-runtime ai-coding claude-code cli code-review

+14 more

codex coding-agent developer-tools devtools evidence local-first local-llm mcp model-context-protocol multi-agent opencode software-engineering typescript workflow-automation

Affected surfaces

auth

Summary

AI summary

Added an ultra thinking level to CLI and refreshed model metadata.

Changes in this release

Type	Severity	Summary	CVE
Feature	Low	Adds "ultra" thinking level to CLI --thinking flag and related components Adds "ultra" thinking level to CLI --thinking flag and related components Source: llm_adapter@2026-07-15 Confidence: low	—
Feature	Low	Adds "ultra" thinking level to CLI --thinking flag, selector, settings, theme colors, and router feedback levels Adds "ultra" thinking level to CLI --thinking flag, selector, settings, theme colors, and router feedback levels Source: granite4.1:30b@2026-07-15-audit Confidence: low	—
Bugfix
Bugfix	Medium	Fixes false positives in secret.read_path command-safety for search commands Fixes false positives in secret.read_path command-safety for search commands Source: llm_adapter@2026-07-15 Confidence: low	—
Bugfix	Low	Fixes npm trusted-publishing identity after GitHub repository rename Fixes npm trusted-publishing identity after GitHub repository rename Source: llm_adapter@2026-07-15 Confidence: high	—
Bugfix	Low	Corrects secret.read_path false positives for search command patterns after `--` in grep/egrep/fgrep/rg Corrects secret.read_path false positives for search command patterns after `--` in grep/egrep/fgrep/rg Source: granite4.1:30b@2026-07-15-audit Confidence: low	—
Refactor	Low	Refreshes built-in model metadata via omk-ai regeneration for OpenRouter and OpenCode Go catalog entries Refreshes built-in model metadata via omk-ai regeneration for OpenRouter and OpenCode Go catalog entries Source: granite4.1:30b@2026-07-15-audit Confidence: low	—

Full changelog

Added

Added the ultra thinking level (maximum reasoning with automatic task delegation, GPT-5.6 Sol/Terra via openai-codex) to the CLI --thinking flag, thinking selector, settings, theme colors, and router feedback levels; the reasoning router never auto-selects ultra, and models without it clamp down to their highest supported level.

Changed

Refreshed built-in model metadata via omk-ai regeneration so OpenRouter latest tool-capable models and OpenCode Go (opencode-go) catalog entries stay current for /model and provider defaults.
Changed the root README project demo link to Mario's Threads profile.

Fixed

Fixed secret.read_path command-safety false positives for search commands: the pattern argument immediately after -- in grep/egrep/fgrep/rg is no longer treated as a secret file operand, while real secret-file operands (e.g. rg -- needle .env, grep -f .env needle) stay confirm-tier.
Fixed npm trusted-publishing identity after the GitHub repository rename by aligning package metadata with dmae97/omk.

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 OMK

Get notified when new releases ship.

About OMK

Provider-neutral CLI control plane for coding agents: routes runtimes, scopes MCP, runs DAG workers, and verifies evidence before completion. MIT.

All releases →

Related context

Related tools

amux