Skip to content

Reasoning Effort Levels Not Reflected for OpenAI Models (GPT-5.2-Codex Extra Level Missing) #10068

Closed as duplicate

Description

@murtazaairesearcher

Question

GitHub Copilot recently introduced configurable reasoning-effort levels for OpenAI models. In OpenCode, I can see similar options—Low, Medium, and High—but it’s unclear whether these settings are actually applied, as they appear to have existed prior to Copilot’s recent update.

Additionally, GPT-5.2-Codex supports an extra reasoning-effort level beyond the standard Low/Medium/High options. Currently, this additional level does not appear to be exposed or configurable in OpenCode.

Questions

Are the existing reasoning-effort options (Low / Medium / High) in OpenCode actively mapped to the underlying OpenAI model parameters?

If so, how can this be verified or observed in practice?

Is it possible to expose and support the additional reasoning-effort level that GPT-5.2-Codex provides?

Activity

  1. github-actions commented on Jan 22, 2026

    @github-actions
    Contributor

    This issue might be a duplicate of existing issues. Please check:

    Feel free to ignore if your specific case addresses something different from these existing issues.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

zenRelates to Zen

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions