Back
AI summary
Written by AI from the official notes. Check them for exact details.Codex CLI 0.144.0 introduces new features for usage credits, authentication, and diagnostics, along with several bug fixes.
- Usage-limit reset credits now show type and expiration.
- Introduced
writesapp-approval mode for read-only actions. - MCP tools can now request authentication interactively.
- Global pnunen installs are detected for diagnostics.
- Warnings added for high multi-agent concurrency usage.
Why it matters: Developers using Codex CLI should review these changes for improved functionality and security.
Full release notes17 changes
New Features
- Usage-limit reset credits now show their type and expiration, and let you choose which credit to redeem.
- Added a
writesapp-approval mode that allows declared read-only actions while prompting for writes. - MCP tools can now request authentication interactively without an experimental opt-in.
- App-server hosts can provide Codex authentication at runtime and redirect successful logins to a hosted page.
- Global pnunen installs are now detected so diagnostics and updates use the correct package manager.
- Selecting Ultra reasoning now warns when high multi-agent concurrency could increase usage quickly.
Bug Fixes
- Resumed ChatGPT threads recover when compaction references a retired model by retrying with the currently selected model.
- Fixed Code Mode crashes in Intel macOS release binaries.
- Windows sandbox sessions can delete files in writable roots and access the managed primary runtime.
- Pasted terminal control sequences can no longer corrupt TUI rendering or resumed conversation history.
- Long-running app sessions now refresh expired authentication for the hosted
codex_appsconnector. - Responses WebSockets continue using the low-latency transport while respecting system proxies and custom certificate authorities.
Documentation
- Device-code login warnings now explain how to recognize and stop phishing attempts.
Chores
- Reduced plugin skill-loading time on remote executors by resolving namespaces once per root.
- Made the
/reviewbranch picker faster and more reliable in large repositories. - Improved automatic review behavior with clearer instructions and a focused tool set.
- Made Amazon Bedrock model names clearly identify their GPT-5.6 family and variant.