Steer Active Tasks in Real Time with Instant Interrupts
When you watch the model outputting a lengthy response or running a time-consuming program call, you can steer its train of thought in a new direction simply by typing. After enabling the instant_interrupt setting, you do not have to wait for the current output to finish or forcefully interrupt and start over; sending a new prompt directly guides Codex to adjust its next step mid-computation.
If you spot a mistake in your previous prompt or want to add details spontaneously, this mechanism lets you chime in at any time, saving you the wait of restarting conversations.
FEATURE
Preserve Unsent Drafts Across Tasks and Archive Empty Sessions
When you type out a lengthy prompt but suddenly need to switch to another task, the draft in the input box no longer disappears. Even if the current task is a brand-new blank session without any messages yet, your entered input is properly preserved when switching tasks. In addition, conversation threads where you have not sent a first message can now be listed directly or archived.
This ensures you will not lose half-written ideas when switching between multiple active tasks.
FEATURE
Streamlined Terminal Interface with Flexible Plan Review and Warning Inspection
When you start a new session, the terminal greets you with a cleaner welcome screen and unified header, offering helpful tips during or after conversations. If the warning viewer appears during execution, closing it automatically clears reviewed warnings, though you can press the k key to keep specific items for later review. Furthermore, when Codex presents an execution plan and asks for confirmation, you are no longer stuck on a rigid confirmation screen; instead, you can freely scroll up through conversation history to check prior context before deciding. These adjustments make reviewing and interacting in the terminal more intuitive and fluid.
FEATURE
Render Rich Flowchart Nodes and Copy Terminal Tables with Intact Layouts
When asking AI to generate architecture diagrams or data tables, rendering and copy-pasting formats are now significantly more accurate. The built-in Mermaid renderer supports more flowchart link styles, text labels, and node subgraphs, making layouts less prone to breaking. Meanwhile, selecting and copying conversation logs in the terminal fully preserves Markdown table structures, text styles, and indentation spacing, with broader support for copy-on-select terminal behaviors.
You no longer need to manually realign misaligned columns or redraw node groups.
FEATURE
Reliable Browser Launch for Local Login with Shortcut to Copy Links
When logging into your account after installing the tool, the authentication workflow is much smoother and more dependable. When logging into a ChatGPT account locally, the system reliably opens your default browser to complete authorization; if the browser fails to pop up, the onboarding screen provides a keyboard shortcut to directly copy the login URL and paste it manually.
This avoids past issues where login windows hung or users got stuck without an authorization URL during onboarding.
BUGFIX
Enforce File Access Restrictions on Approved Commands and Fix macOS Sandbox Networking
Even after approving execution permissions for specific commands, your security boundaries remain intact. Approved commands now strictly adhere to your explicitly configured filesystem access restrictions, and the .aws directory under writable roots is protected by default to prevent secret credential leaks. In addition, on macOS sandboxes with networking enabled and in proxy-reliant remote environments, prior TLS connection anomalies have been resolved.
Situations where network connections failed in restricted environments or secret files were unintentionally touched are now properly protected with stable connections.
FEATURE
Suppress Pop-up Console Windows on Windows and Support Paginated History
When launching tools on Windows, your desktop is no longer disrupted by sudden black terminal pop-ups. Spawning MCP servers, programmatic mode hosts, or piped commands avoids extraneous console windows, and the system automatically falls back to an embedded mode in permission-restricted launch environments. Meanwhile, the app-server now supports pagination, allowing clients to fetch history starting from a specific conversation item.
This makes multitasking on Windows cleaner and more organized.
FEATURE
Remove Automatic Prompt Suggestions and Streamline Built-in Plugin Creator Skill
If you prefer managing your conversation flow in the terminal yourself, the screen will no longer pop up follow-up prompt suggestions that interrupt your train of thought. This update officially removes automated follow-up prompt suggestions and retires the corresponding tui.prompt_suggestions setting. In addition, the system no longer bundles the built-in plugin-creator skill out of the box, keeping the default environment lightweight.
Where unused suggestions or preloaded tools once cluttered the view, the interface and configuration are now cleaner, handing full control back to your commands.
Original changelog
Original changelogSteer Active Tasks in Real Time with Instant Interrupts
Opt-in `instant_interrupt` lets new input steer Codex during model responses or long-running code-mode calls. (#48135, #48141)
Original changelogPreserve Unsent Drafts Across Tasks and Archive Empty Sessions
Blank sessions retain drafts when switching tasks, and threads can be archived and listed before their first turn. (#48628, #48828, #48199)
Original changelogStreamlined Terminal Interface with Flexible Plan Review and Warning Inspection
New sessions get a compact welcome screen and consistent headers, with occasional tips during and after turns. (#48513, #48562, #48352)
The warnings viewer dismisses reviewed warnings when closed; press `k` to keep one for later. (#48205, #48206)
You can scroll the transcript while deciding whether to implement a plan. (#48805)
Original changelogRender Rich Flowchart Nodes and Copy Terminal Tables with Intact Layouts
Native Mermaid rendering supports more flowchart edges, labels, and node groups. (#48814, #48895)
Copying transcript selections preserves Markdown tables, formatting, and significant whitespace. More terminals now copy automatically on selection. (#48548, #48549, #48469)
Original changelogReliable Browser Launch for Local Login with Shortcut to Copy Links
Local ChatGPT sign-in opens the browser reliably; onboarding also provides a shortcut to copy the login link. (#48502, #48544)
Original changelogEnforce File Access Restrictions on Approved Commands and Fix macOS Sandbox Networking
Approved commands retain explicit filesystem denials, and `.aws` directories are protected by default under writable roots. (#48155, #48176)
Fixed macOS TLS access in network-enabled sandboxes and remote environments that require proxy access. (#48565, #48198)
Original changelogSuppress Pop-up Console Windows on Windows and Support Paginated History
App-server clients can paginate thread history from a specific item. (#48151)
Windows launches avoid stray console windows for MCP servers, code-mode hosts, and piped commands; restrictive launchers can fall back to embedded mode. (#48138, #48238, #48483, #48491)
Original changelogRemove Automatic Prompt Suggestions and Streamline Built-in Plugin Creator Skill
Removed automatic follow-up prompt suggestions and the `tui.prompt_suggestions` setting. (#48621)
Removed the bundled `plugin-creator` skill. (#48604)