Codex Web GPT v5.0.6

V5 adds Zero Risk Mode: the full Codex MCP harness still runs through ChatGPT, but the launcher never reads or changes the ChatGPT page and never sends a prompt for you.

V5 highlights

• Zero Risk Mode. The launcher prepares and copies the complete Codex prompt; you paste it into ChatGPT, add any images yourself, select the Codex Zero Risk connector plus the model and effort you want, send it, and confirm Sent. Codex tools, patches, terminal calls, structured output, streaming, and native progress stay available through the same turn-bound harness without browser automation.
• A separate Zero Risk MCP setup. Automatic and Zero Risk modes have independent connector identities, Tunnel IDs, API keys, runtime state, and recovery. Switching modes is transactional and never silently reuses the other mode's private credentials.
• Optional Zero Risk Pro profile. The install menu can add a second ChatGPT Web — Zero Risk Pro row with roughly 250,000 usable tokens before compaction. It is intentionally explicit: select ChatGPT Pro manually for every turn; a Pro account is required, and the larger limit may not work with every effort.
• Manual turns that remain real Codex turns. A neutral request ID binds each ChatGPT response to the exact Codex turn through MCP metadata. Concurrent turns stay isolated; reconnects rejoin the same request; cancellation, completion, retained-chat continuation, and compaction are explicit and fail closed.
• Zero Risk compaction. The active ChatGPT agent produces the checkpoint through the bound MCP control, the old chat is retired, and the compacted Codex continuation starts from a fresh manual chat without exposing private control values in the pasted prompt.
• A clearer launcher flow. First-run onboarding now offers With Automation and Zero Risk, defaults to automation, and keeps the same choice in Settings. The MCP guide includes trimmed, accelerated video walkthroughs with an in-launcher fullscreen viewer.
• Three-language product parity. The new setup, mode selection, manual-turn guidance, diagnostics, and model-profile controls are complete in English, Chinese, and Japanese.

v5.0.6 hotfixes

• Setup can recover a removed interrupt hook. Explicit Setup now reinstalls a fully absent managed hook while preserving the current Codex config. Changed or partly removed hooks still fail safely, and ordinary startup remains strict. Addresses #394.
• Concurrent browser tasks acquire their own pages independently. Page selection now uses native browser target identities, so an unrelated paused or busy renderer cannot block a responsive task. Install the complete launcher update and reopen it so the launcher and runtime use the matching browser descriptor. Addresses the reproduced acquisition defect investigated in #397.
• Effort selection avoids closing menus. A slider left visible by a menu's exit animation no longer counts as an open control. This fixes the observed effort-selection race; it does not establish a fix for the separate unresolved compaction failure reported in #321.
• ChatGPT response errors reach Codex accurately. The current response's error action is recognized even when its message is short or localized, and an old failed answer no longer rejects a new submission. A visible Stopped thinking status now ends the turn immediately with an explicit error and no automatic retry. A Web usage limit is one possible cause, not a confirmed diagnosis.
• Chinese personalization controls are recognized. Connector setup supports the observed Chinese Personalized/Unpersonalized labels alongside English. Includes #402.
• Japanese and Chinese launcher diagnostics are clearer. Connector verification progress and successful Doctor checks are localized. Connector names and endpoints remain literal; unknown messages and errors retain their original text. Completes Discussion #387.
• Native collaboration waits respect the MCP transport. The collaboration.wait_agent path now shares the wait guard used by V1/V2 tools, including calls inside exec. Polling uses Codex's 30-second default, preserves the native arguments and results, and treats a wait timeout as pending work rather than completion.
• Development checks work with standalone Bun. Type checking uses the installed Bun and local TypeScript without requiring a separate bunx command; test discovery is restricted to the tests directory. Synthetic Windows DEV discovery also stays independent of the real launcher registry. Fixes #379.
• Setup uses the fixed connector identities. Removed the unsupported --app-name setup option from both production and DEV commands and their launcher callers. Automatic, DEV and Zero Risk retain their designated connector names.

Thanks to @JulianZJN for the Chinese personalization fix (#402) and @cXSHoz for the Japanese diagnostics contribution (#400).

Please update through the launcher, restart Codex, and retry the affected workflow. If the same failure remains, reply in its issue with your versions and a fresh Activity safe-log export from that attempt.

Install

macOS or Linux:

curl -fsSL https://github.com/miuuyy/codex-chatgpt-web/releases/latest/download/install-launcher.sh | sh

Windows PowerShell:

irm https://github.com/miuuyy/codex-chatgpt-web/releases/latest/download/install-launcher.ps1 | iex