Codex Web GPT v5.0.3

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.

v5.0.3 hotfixes

• Pro and Extra High appear correctly again. Updated detection and selection for ChatGPT's effort slider. Upgrading in Automatic mode refreshes the saved account capabilities so an earlier incorrect result does not hide the available models. Addresses #322. Restart Codex after updating to reload its model catalog.
• Bigger Context compaction recognizes accepted progress. Acknowledgements for each staged part now reach the compaction controller, renewing the current phase's time budget when ChatGPT accepts a part. This fixes the case where compaction timed out five minutes after starting despite successfully processing earlier parts. Addresses part of #321.
• Compaction recovers observation of its existing browser page. Recovery is also available for compaction turns that run without tools, including the final staged prompt. It keeps the same page and does not send the prompt twice.
• Retrying compaction waits for the previous browser turn to finish cleaning up. A timeout is reported promptly, while the old turn retains ownership until its cleanup completes. This addresses the immediate Duplicate browser turn error after a failed compaction in #321.
• MCP setup keeps its verified state. Leaving and returning to the MCP screen no longer loses the Done button after a successful verification. A failed recheck still clears readiness. Addresses the setup-status portion of #308; the separate reported browser freeze remains under investigation.
• Regression checks and cleanup. Removed redundant source-format assertions while preserving behavioral checks for browser recovery, helper messaging, and compaction cleanup.

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