Codex Web GPT v5.0.8

An urgent compatibility hotfix while work toward 6.0 continues. v5.0.7 was the last planned V5 patch; this additional update addresses a ChatGPT response-layout variant that the bridge could not read, together with the native system-proxy fix.

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.
• Five-language launcher. Setup, mode selection, manual-turn guidance, diagnostics, and model-profile controls are available in English, Simplified Chinese, Traditional Chinese, Japanese, and Korean.

v5.0.8 hotfixes

• Read replies rendered with ChatGPT’s DIL/PUIK components. Some ChatGPT pages render assistant replies without the previous .markdown container. The bridge now reads the observed assistant-owned response root and retains the same streaming, commentary and completion checks. This fixes the reproduced smoke-test timeout and unread-response defect investigated in #538. It does not establish that every reported compaction failure has the same cause.
• Use the launcher’s system HTTP(S) proxy for native Codex requests. Native catalog and passthrough requests can now use the proxy route resolved by the launcher when no explicit proxy environment is configured. Catalog failures show their actual error instead of repeatedly asking for another Codex restart. Addresses #535 and the system-proxy path reported in #438. Explicit proxy environment settings remain authoritative; SOCKS-only routes are not silently converted to HTTP.
• Optional Skills as files experiment. Settings can upload explicitly selected Codex skills as named UTF-8 text attachments instead of embedding their full instructions inline. This uses native selected-skill metadata, preserves the original resource references, and distinguishes changed versions. It is off by default, unavailable in Zero Risk, and shares the 10-attachment limit with images. Skill contents still count toward context limits. This is an independent implementation prompted by #534; improved model adherence is not yet established.
• Clarify the first-run X invitation. It now explains that the account shares product updates and other Codex tips, in all five launcher languages.

Thanks to @Andreitos97 for providing diagnostics and a captured ChatGPT response structure that helped reproduce and investigate the response-reading failure fixed in this release.

Please install the complete launcher update, reopen the launcher, and restart Codex before retrying. If the affected workflow still fails, reopen its issue (or leave a comment asking me to reopen it) with the exact error and a fresh Launcher → Activity → Export safe log from that attempt. The broader compaction, Zero Risk completion, tool-availability and upstream safety investigations remain open.

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