codex

package
v6.7.2 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Jan 16, 2026 License: MIT Imports: 5 Imported by: 0

Documentation

Overview

Package codex implements thinking configuration for Codex (OpenAI Responses API) models.

Codex models use the reasoning.effort format with discrete levels (low/medium/high). This is similar to OpenAI but uses nested field "reasoning.effort" instead of "reasoning_effort". See: _bmad-output/planning-artifacts/architecture.md#Epic-8

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

This section is empty.

Types

type Applier

type Applier struct{}

Applier implements thinking.ProviderApplier for Codex models.

Codex-specific behavior:

  • Output format: reasoning.effort (string: low/medium/high/xhigh)
  • Level-only mode: no numeric budget support
  • Some models support ZeroAllowed (gpt-5.1, gpt-5.2)

func NewApplier

func NewApplier() *Applier

NewApplier creates a new Codex thinking applier.

func (*Applier) Apply

func (a *Applier) Apply(body []byte, config thinking.ThinkingConfig, modelInfo *registry.ModelInfo) ([]byte, error)

Apply applies thinking configuration to Codex request body.

Expected output format:

{
  "reasoning": {
    "effort": "high"
  }
}

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL