Codex Web GPT v6.1.4

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 v6.1.4

• Prompts and attachments. Prevents doubled prompts, recognizes completed uploads, and protects large context messages from the browser’s Markdown parser. Stops promptly when ChatGPT rejects an oversized message and shows the size error.
• Replies and formatting. Supports both ChatGPT layouts and follows replies through page redraws. Repeated paragraphs and headings no longer cause false “changed a completed text block” failures; formulas are returned once. Keeps changing page controls out of answer text and preserves code line breaks, links, and plan markers.
• Models and effort. Fixes menus closing after a model switch, handles slow loading and locked Pro options, and checks the requested model and effort before sending. Recognizes the active model header when the slider does not announce the family. 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. Cancelling one request no longer crashes the browser helper and interrupts other tasks. Settings changes during startup keep valid setup state. Preserves the browser’s system theme, restores windows after monitor changes, and accepts unchanged interrupt-hook settings that Codex writes explicitly.
• 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 and continuation, including extra output folders allowed by Codex. Compaction keeps the selected model, and waiting for the previous response no longer consumes the summary request’s own time allowance. Reports missing summaries explicitly. Some long-session failures still need investigation.
• Activity and diagnostics. Shows whether a task is preparing, waiting for ChatGPT, waiting for a tool, or awaiting approval, with elapsed time and a button to open its browser tab. Stale status is marked explicitly. Tool timeouts identify the affected tool, and safe logs include more useful browser and context-size details.
• 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.
• Tool connections and approvals. Checks the selected Codex plugin on every tool-enabled follow-up. Settings now exposes optional one-time tool approval, off by default; otherwise the launcher shows when approval is needed. Zero Risk stays manual, with 60 seconds to send and a timer reset when copying again. Failed startup cleanup preserves other running connections.
• Update downloads. Uses the system proxy settings while retaining HTTPS and checksum checks. Bundled dependencies also include security updates.

ChatGPT-side safety refusals and account quotas are not presented as fixed by this release.

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, @midorikawadaisuke4500, @korboybeats, 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