miuuyy/codex-chatgpt-web v6.1.16

on GitHub

V6 brings ChatGPT Web models into Codex's model and Effort selectors, optional Pro usage estimates, Bigger Context, and control over browser conversations. 6.1.16 is a hotfix for missing Web models and tasks failing before Send after ChatGPT changed its model control.

Changes in 6.1.16

• Web models return after ChatGPT's latest UI change. Recognizes the new inline model control while preserving earlier supported layouts. This fixes model selection failing before Send and the misleading capacity error that follows (#924).
• Setup no longer mistakes an unknown interface for a Luna-only account. Paid model detection uses the updated control. An unrecognized interface now reports a clear error and preserves the previous configuration; a browser check cannot pass on a different model. Already affected installations need the model refresh described above (#932).
• Oversized compaction can recover within Bigger Context's limit. When the retained browser chat is lost, a multipart compaction request can trim older history to fit the actual transport limit while preserving the latest checkpoint and instruction. Ordinary task requests are not trimmed (#930).
• Targeted recovery avoids duplicate tool work. A delivery-timeout alert attached to the current response can be retried only when native tool state permits it. Malformed multipart acknowledgements can restart staging before the task is committed. Generic frozen pages and missing final answers still require separate evidence (#929).
• Connector navigation failures appear in diagnostics. Errors while opening the ChatGPT home page during connector verification are now recorded. The model-control repair should also address the pre-Send failures captured in #925; any remaining turn-ID conflict needs a fresh report after updating.

V6 features and earlier fixes

• Models and effort. Account-supported GPT-5.6 and GPT-6 models appear in Codex's native picker. Sol reasoning uses Effort, Instant keeps a separate context budget, and Free accounts expose Luna/Think. Earlier patches improved translated controls, Pro verification, locked options, exact Sol/Astra selection, six-position controls and Browser Smoke cancellation.
• Bigger Context and long tasks. Large histories use one, two or six ordered messages. GPT-6 Sol supports configured windows up to 120,000 tokens on Plus and 240,000 on Pro at supported reasoning levels; Instant keeps standard context. These are bridge context budgets, not guaranteed upstream message limits. Earlier fixes preserve the accepted task, active goal, date and delegation context through compaction, handle formatted user messages, and prevent repeated uploads of the same rejected transaction. One oversized message still must fit its individual stage. Luna/Think Bigger Context remains experimental.
• Chat controls and Pro estimates. Temporary Chat is enabled by default; turn off Settings → Temporary Chat to use saved conversations. An explicit opt-out is preserved. Optional fresh chats rebuild the same Codex task in a new browser conversation. Optional next-message suggestions use GPT-6 Sol Medium when the context fits. The Limits tab estimates the launcher's own submissions for supported Pro plans; it does not report OpenAI's remaining allowance or messages sent elsewhere.
• Tools and replies. Full harness mode provides native files, commands, tools and approvals through MCP. Command polls are bounded to 60 seconds per MCP call. Earlier updates improved permission guidance, worktree access, tool settlement, cancellation, Markdown fidelity and delayed-final handling without resubmitting accepted work. Think recognizes the current icon across languages.
• Setup and desktop reliability. MCP setup and model-catalog loading have separate health checks. Doctor explains conflicting context overrides. Session warnings stay above the browser without shrinking it, and startup preserves settings and owned runtime state on failure. Earlier patches improved passkey sign-in, account switching, system proxy support, Windows certificate handling, update rollback and downgrade prevention.
• Diagnostics and packages. Failed browser captures are retained for up to three days within a 100 MB budget, with active captures protected. Diagnostics record stream completion and observed UI structures without message text or tool arguments. UI contracts have separate owners, dated evidence and regression fixtures. The launcher uses Electron 42.11.16 and pinned Bun 1.4.0, with Windows x64, macOS Apple silicon/Intel and Linux x64/ARM64 packages.

The frozen-page case in #929, Windows tunnel installation in #870 and the context-overflow report in #913 still need the requested reporter evidence. The separate long-running recovery work in draft PR #914 is not included. ChatGPT account limits and safety refusals still apply; shared safety reports remain tracked in #622.

Thanks to @kaimiller144-web and @nofihq for the model-control fixes and platform checks; @zmahomedy for the compaction reproduction and recovery testing; @iminfine, @etsynam-pixel, @osuki9x, @MardSilva and @hey-yulee for detailed reports; and everyone who supplied logs or confirmed the affected platforms. Earlier V6 fixes also include contributions and evidence from @nofihq, @lce52147, @thomastsaidotcom, @alexzwy51 and @martjay.

The Pro Researcher skill is available for delegating research to Pro sub-agents.

Update

Finish active tasks, quit the launcher, install the update and reopen it. If your Web models disappeared, run Setup → Install into Codex → Reinstall after updating, then fully quit and reopen Codex. Do not delete your launcher data or ChatGPT profile. Check Settings → Temporary Chat if you prefer ordinary saved conversations.

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

If a closed issue still happens, open a new issue with Activity → Export safe log, the failure time, launcher/Codex versions and model/effort. If your issue remains open, add the new results there.