Struct ReasoningArgs 

pub struct ReasoningArgs { /* private fields */ }

Builder for Reasoning.

Implementations

impl ReasoningArgs

pub fn effort<VALUE>(&mut self, value: VALUE) -> &mut ReasoningArgs

where VALUE: Into<ReasoningEffort>,

Constrains effort on reasoning for reasoning models. Currently supported values are minimal, low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Note: The gpt-5-pro model defaults to (and only supports) high reasoning effort.

pub fn summary<VALUE>(&mut self, value: VALUE) -> &mut ReasoningArgs

where VALUE: Into<ReasoningSummary>,

A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model’s reasoning process. One of auto, concise, or detailed.

concise is supported for computer-use-preview models and all reasoning models after gpt-5.

pub fn mode<VALUE>(&mut self, value: VALUE) -> &mut ReasoningArgs

where VALUE: Into<ReasoningModeEnum>,

Controls the reasoning execution mode for the request.

When returned on a response, this is the effective execution mode.

pub fn context<VALUE>(&mut self, value: VALUE) -> &mut ReasoningArgs

where VALUE: Into<ReasoningContext>,

Controls which reasoning items are rendered back to the model on later turns.

If omitted or set to auto, the model determines the context mode. The gpt-5.6 model family defaults to all_turns; earlier models default to current_turn.

When returned on a response, this is the effective reasoning context mode used for the response.

pub fn build(&self) -> Result<Reasoning, OpenAIError>

Builds a new Reasoning.

Errors

If a required field has not been initialized.

Trait Implementations

impl Clone for ReasoningArgs

fn clone(&self) -> ReasoningArgs

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Default for ReasoningArgs

fn default() -> ReasoningArgs

Returns the “default value” for a type.