Codex Web GPT v6.1.3

V6 brings a new model picker, optional Pro usage tracking, more control over browser chats, and the fixes developed since v5.0.8.

V6 highlights

• Clear model names and native Effort controls. Automatic models end in (Web): GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Pro, and GPT-6 Pro. Sol exposes the reasoning levels your account supports through Codex's Effort selector. Instant stays separate to preserve its context budget. Existing tasks keep their original modes.
• A Limits tab for Pro. Optional tracking for supported Pro $100 and $200 plans, with separate model allowances and a warning from 75% usage. These are local estimates; messages sent outside the launcher are not counted. Tracking is unavailable in Zero Risk.
• Smaller parts for Bigger Context. Large requests use six ordered parts, with tools and attachments on the final part. The overall context and compaction budgets are preserved.
• New browser chat for each turn. An optional setting rebuilds the same task in a fresh ChatGPT conversation. This can help when ChatGPT loses tools across follow-ups, at the cost of sending more context.
• Save chats in ChatGPT. Regular conversations can replace Temporary Chat. ChatGPT memory and custom instructions may apply. Both chat settings are off by default and work independently.
• Native Linux ARM64 packages. x64 and ARM64 AppImages and runtime bundles, with installation and updates for each architecture.
• A new application icon. The launcher keeps its familiar ChatGPT mark inside the interface.

Fixes and improvements through v6.1.3

• Prompts and attachments. Clears leftover drafts before inserting another request, preventing doubled prompts and “did not preserve the complete prompt” errors. Recognizes completed file uploads so Send can proceed.
• Replies and activity. Supports both ChatGPT layouts and follows replies when the page redraws, including unfinished replies. Does not declare a response missing while generation is visibly running. Keeps changing code-block and writing-card controls out of answer text; code retains its line breaks. Activity descriptions appear separately as grey status text.
• Models and effort. Fixes the menu closing unexpectedly after a model switch. Handles menus loading slowly, recognizes locked Pro options on Plus, and verifies the requested model and effort before sending. Available Sol effort levels remain selectable when Pro is unavailable.
• Sign-in and Limits. Improves sign-out and account-switch detection, including with the browser hidden. A working page session is no longer contradicted by a separate sign-in check. Limits reads the signed-in plan without opening Billing or depending on its wording or language.
• Startup and desktop behavior. Changing Bigger Context or other settings during startup no longer marks a healthy setup incomplete. Restores the macOS menu-bar icon and windows after a monitor disconnects; preserves Activity across rotated logs and improves cancelled-tab cleanup.
• Windows connections. Uses Windows-trusted certificates in the launcher and background processes while keeping certificate verification enabled. Improves tunnel installation and setup recovery.
• Long tasks and summaries. Improves workspace recovery, continuation, and compaction; accepts extra folders explicitly allowed by Codex. Reports a missing summary instead of waiting for the full timeout. Some long-session failures still need investigation; ChatGPT-side safety refusals are not guaranteed resolved.
• Formatting and diagnostics. Preserves Markdown links, plan markers, and Windows file labels. Makes safe-log exports more useful, including model and effort failures, and preserves the original connection error if cleanup also fails.
• Plugin names and setup. Change the part after Codex in Settings → Plugin name when a deleted name cannot be reused. Create and verify the new plugin; tunnel credentials and login are kept. The setup video has click-to-pause and a pause indicator; Linux update instructions are clearer.
• Manual sending and tool connections. Zero Risk gives you 60 seconds to send; copying again restarts that timer. Failed startup cleanup no longer removes another running connection. Dismisses the observed ChatGPT announcement banner and clarifies how tools use Codex permissions.

Full-mode users: refresh your Codex plugin in ChatGPT's plugin settings after updating if you have not done so since V6, to load the updated tool description.

Thanks to @renanassisalves for PR #664, page details, and testing that helped identify the ChatGPT interface changes. Thanks also to @NC-Channel-Coder, @eisen0419, @omarcosr, @Wandersport, @b-y-f, @djblack1209-coder, and everyone who shared reports, proposed fixes, and retest results.

Install

Quit the launcher, replace the existing application with the package for your system, then reopen it. Restart Codex after the launcher refreshes its integration. Do not delete your launcher data or ChatGPT profile.

• Windows x64
• macOS Apple silicon · macOS Intel
• Linux x64 · Linux ARM64