### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

I can't use OpenAI Codex with LiteLLM.

Codex CLI output:

``` ◦ Reconnecting... 2/5 (6s • esc to interrupt) └ Stream disconnected before completion: error sending request for url (https://0.0.0.0:4000/v1/responses) ```

LiteLLM proxy output: `WARNING: Invalid HTTP request received.`

Searching this error I found this issue from 2 years ago: https://github.com/BerriAI/litellm/issues/5836

### Steps to Reproduce

``` model_list: - model_name: gpt-5.5 litellm_params: model: openai/gpt-5.5 api_key: os.environ/OPENAI_API_KEY ```

### Relevant log output

```shell

```

### What part of LiteLLM is this about?

Proxy

### What LiteLLM version are you on ?

1.87.1

### Twitter / LinkedIn details

_No response_