This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite.
已打开 10:07AM - 26 Jun 26 UTC
bug
custom-model
app
config
### What version of the Codex App are you using (From “About Codex” dialog)?
26….623.31921
### What subscription do you have?
plus
### What platform is your computer?
win11
### What issue are you seeing?
The API returns this error when using `X-OpenAI-Internal-Codex-Responses-Lite`:
`This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite.`
We are using `gpt-5.5-high` and `gpt-5.5-xhigh`. Please help confirm whether these models are supported with this header.
### What steps can reproduce the bug?
After updating to the latest version, the issue occurs when starting a new conversation.
Steps to reproduce:
1. Set `model_provider = "openai_http"`.
2. Start a new conversation.
3. Use `gpt-5.5-high` or `gpt-5.5-xhigh`.
4. Send any message.
5. The request fails with the error:
`This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite.`
### What is the expected behavior?
_No response_
### Additional information
_No response_
aaa 06-27 10:301楼
xiaocenfox 06-27 10:372楼
laodeng 06-27 10:453楼
hui 06-27 10:484楼
Coeus 06-27 13:386楼