codex: refine reasoning effort validation

[YusukeShimizu]

Summary

Refine Codex provider reasoning-effort validation and expand supported CODEX_REASONING_EFFORT values to include xhigh and none. Add model-aware validation so none is rejected for *-codex models (falls back to high with a warning).

I will handle documentation updates in a separate PR, in accordance with the policy.

Type of Change

• Feature
• Bug fix
• Refactor / Code quality
• Performance improvement
• Documentation
• Tests
• Security fix
• Build / Release
• Other (specify below)

AI Assistance

• This PR was created or reviewed with AI assistance

Testing

GitHub Actions (Build and Test Rust Project).

Related Issues

Relates to: N/A
Discussion: N/A

Screenshots/Demos (for UX changes)

Before: N/A
After: N/A

[Copilot]

Pull request overview

This PR refines the reasoning effort validation for the Codex provider by adding support for xhigh and none levels, and implementing model-specific validation where none is only supported on non-codex models (like gpt-5.2).

Changes:

• Added xhigh and none to the list of valid reasoning effort levels
• Implemented model-specific validation logic via a new supports_reasoning_effort helper function
• Updated documentation to reflect the new reasoning effort levels (should be removed per project guidelines)

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
crates/goose/src/providers/codex.rs	Added supports_reasoning_effort function to validate reasoning levels based on model type; updated constant and comments to include new levels; added comprehensive tests
documentation/docs/guides/cli-providers.md	Updated feature descriptions and configuration table to document new reasoning effort levels

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

[michaelneale]

thanks - I think this may fix warnings I saw with things (maybe)