FeatureOpenAI Codexv0.145.0Vibe Builder Developer

Codex CLI stabilizes multi-agent V2 with sub-agent model controls

By Harsh Desai23 July 2026

TL;DR

Codex CLI stabilizes the multi-agent V2 experience with configurable sub-agent models, adjustable reasoning levels, concurrency controls, restored roles, and improved navigation.

What changed

Developers now access the stabilized multi-agent V2 experience in Codex CLI with configurable sub-agent models. Vibe Builders adjust reasoning levels and concurrency controls as needed. Basic Users benefit from restored roles and improved navigation throughout the interface.

Why it matters

Developers gain precise management of sub-agents in multi-agent workflows. This setup supports Basic Users handling routine coordination tasks more effectively. Vibe Builders see advantages in dynamic model selection for parallel operations compared to fixed setups in tools like Cursor.

What to watch for

Developers should compare the new controls against alternatives like manual agent scripting in other CLIs. Basic Users can verify changes by testing concurrency settings in a sample multi-agent session within Codex CLI.

Who this matters for

Vibe Builders: Set custom sub-agent models and concurrency limits in Codex CLI to run multi-agent workflows faster.
Developers: Fine-tune reasoning levels and balance sub-agent workloads to optimize terminal multi-agent tasks.

Harsh’s take

Configurable sub-agent models and explicit concurrency limits give CLI users actual operational control over orchestration overhead. Instead of locking every task into a single execution model, operators can now delegate heavy reasoning to top-tier models while routing routine parallel checks to lighter endpoints. This stabilization puts Codex CLI directly ahead of fixed multi-agent setups that hide sub-agent routing. Teams running complex terminal workflows should migrate off static scripts and lock in explicit per-agent model configurations today.

by Harsh Desai

Source:developers.openai.com