'none' value for model_reasoning_summary rejected despite documentation stating it's valid
What version of Codex is running?
0.25.0
Which model were you using?
gpt-5
What platform is your computer?
Windows 11, WSL2.0
What steps can reproduce the bug?
Environment
- Operating System: Windows 10 with WSL2 (Ubuntu or similar Linux distro inside WSL).
- Codex CLI Version: 0.25.0 (research preview).
- Model: gpt-5.
- Provider: openai.
- Authentication: Using OpenAI Teams membership.
Steps to Reproduce
- Install Codex CLI v0.25.0.
- Authenticate using an OpenAI Teams membership.
- Run the following command in WSL2:
````
codex exec --full-auto \
--config model_reasoning_effort="minimal" \
--config model_reasoning_summary="none" \
"list the files in the current directory"
- Observe the error after retries.
Expected Behavior
The command should execute successfully, as the documentation in <https://github.com/openai/codex/blob/main/docs/config.md#model_reasoning_summary> explicitly states that "none" is a valid value for model_reasoning_summary. (The docs indicate supported values include 'none' alongside others like 'concise', 'detailed', etc.)
Actual Behavior
The CLI rejects "none" as an invalid value for the reasoning.summary parameter, resulting in a 400 Bad Request error from the API. It retries 5 times before failing. The inline CLI output shows "reasoning summaries: none" being set, but the API call fails with the error message: "Invalid value: 'none'. Supported values are: 'concise', 'detailed', and 'auto'."
This suggests a mismatch between the CLI's config handling/docs and the backend API validation.
Error Logs
[2025-08-28T14:00:55] OpenAI Codex v0.25.0 (research preview)
--------
workdir: /mnt/c/code/etc
model: gpt-5
provider: openai
approval: never
sandbox: workspace-write [workdir, /tmp, $TMPDIR]
reasoning effort: minimal
reasoning summaries: none
--------
[2025-08-28T14:00:55] User instructions:
list the files in the current directory
[2025-08-28T14:00:58] stream error: unexpected status 400 Bad Request: {
"error": {
"message": "Invalid value: 'none'. Supported values are: 'concise', 'detailed', and 'auto'.",
"type": "invalid_request_error",
"param": "reasoning.summary",
"code": "invalid_value"
}
}; retrying 1/5 in 206ms…
[2025-08-28T14:00:59] stream error: unexpected status 400 Bad Request: {
"error": {
"message": "Invalid value: 'none'. Supported values are: 'concise', 'detailed', and 'auto'.",
"type": "invalid_request_error",
"param": "reasoning.summary",
"code": "invalid_value"
}
}; retrying 2/5 in 389ms…
[2025-08-28T14:01:00] stream error: unexpected status 400 Bad Request: {
"error": {
"message": "Invalid value: 'none'. Supported values are: 'concise', 'detailed', and 'auto'.",
"type": "invalid_request_error",
"param": "reasoning.summary",
"code": "invalid_value"
}
}; retrying 3/5 in 778ms…
[2025-08-28T14:01:02] stream error: unexpected status 400 Bad Request: {
"error": {
"message": "Invalid value: 'none'. Supported values are: 'concise', 'detailed', and 'auto'.",
"type": "invalid_request_error",
"param": "reasoning.summary",
"code": "invalid_value"
}
}; retrying 4/5 in 1.737s…
[2025-08-28T14:01:05] stream error: unexpected status 400 Bad Request: {
"error": {
"message": "Invalid value: 'none'. Supported values are: 'concise', 'detailed', and 'auto'.",
"type": "invalid_request_error",
"param": "reasoning.summary",
"code": "invalid_value"
}
}; retrying 5/5 in 3.125s…
[2025-08-28T14:01:09] ERROR: unexpected status 400 Bad Request: {
"error": {
"message": "Invalid value: 'none'. Supported values are: 'concise', 'detailed', and 'auto'.",
"type": "invalid_request_error",
"param": "reasoning.summary",
"code": "invalid_value"
}
}
Thanks for looking into this! Let me know if you need any further info.
What is the expected behavior?
_No response_
What do you see instead?
_No response_
Additional information
_No response_
This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗