Module openai_models 

Shared model metadata types exchanged between Codex services and clients.

These types are serialized across core, TUI, app-server, and SDK boundaries, so field defaults are used to preserve compatibility when older payloads omit newly introduced attributes.

Structs

ApprovalMessages

AutoReviewMessages

ClientVersion

Semantic version triple encoded as an array in JSON (e.g. [0, 62, 0]).

ConfigShellToolTypeIter

An iterator over the variants of ConfigShellToolType

InputModalityIter

An iterator over the variants of InputModality

ModelAvailabilityNux

ModelInfo

Model metadata returned by the Codex backend /models endpoint.

ModelInfoUpgrade

ModelInstructionsVariables

ModelMessages

A strongly-typed template for assembling model instructions and developer messages. If instructions_* is populated and valid, it will override base_instructions.

ModelPreset

Metadata describing a Codex-supported model.

ModelServiceTier

ModelUpgrade

ModelVisibilityIter

An iterator over the variants of ModelVisibility

ModelsResponse

Response wrapper for /models.

PermissionMessages

ReasoningEffortPreset

A reasoning effort option that can be surfaced for a model.

TruncationPolicyConfig

Enums

ApplyPatchToolType

ConfigShellToolType

Shell execution capability for a model.

InputModality

Canonical user-input modality tags advertised by a model.

ModelVisibility

Visibility of a model in the picker or APIs.

ReasoningEffort

See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning

ToolMode

TruncationMode

Server-provided truncation policy metadata for a model.

WebSearchToolType

Constants

SPEED_TIER_FAST

Functions

default_input_modalities

Backward-compatible default when input_modalities is omitted on the wire.