codex - 💡(How to fix) Fix review error eats up 5hr limit [3 comments, 3 participants]

■ {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-5.1-codex-mini' model is not supported when using Codex with a ChatGPT account."}} ⚠ MCP client for codex_apps failed to start: MCP startup failed: handshaking with MCP server failed: Send message error Transport [rmcp::transport::worker::WorkerTransport<rmcp::t ransport::streamable_http_client::StreamableHttpClientWorker<codex_rmcp_client::rmcp_client::StreamableHttpResponseClient>>] error: Client error: error sending request for url ■ {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-5.1-codex-mini' model is not supported when using Codex with a ChatGPT account."}} set model to gpt-5.1-codex-mini, do a /review uncommited changes against base, it will show error, try again. 5h shouldn't go down at all from a server error.

TL;DR

The issue is likely due to the 'gpt-5.1-codex-mini' model not being supported with a ChatGPT account, causing errors and consuming the 5-hour limit.

Guidance

• Verify that the 'gpt-5.1-codex-mini' model is compatible with the ChatGPT account by checking the official documentation or support channels.
• Try using a different model that is supported with the ChatGPT account to see if the issue persists.
• Check the Codex CLI version (currently v0.121.0) to ensure it is up-to-date and compatible with the ChatGPT account.
• Review the error messages and logs to identify any other potential causes of the issue.

Example

No code snippet is provided as it is not clearly supported by the issue.

Notes

The issue may be specific to the 'gpt-5.1-codex-mini' model and ChatGPT account combination, and further investigation is needed to determine the root cause.

Recommendation

Apply workaround: Try using a different model that is supported with the ChatGPT account to avoid the error and consumption of the 5-hour limit.