Class: OpenAI::Models::Beta::ResponseCreateParams::Reasoning

Inherits:

Internal::Type::BaseModel

• Object
• Internal::Type::BaseModel
• OpenAI::Models::Beta::ResponseCreateParams::Reasoning

Defined in:

lib/openai/models/beta/response_create_params.rb,
sig/openai/models/beta/response_create_params.rbs

Defined Under Namespace

Modules: Context, Effort, GenerateSummary, Mode, Summary

Instance Attribute Summary

• #context ⇒ Symbol, ...

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

• #effort ⇒ Symbol, ...

  Constrains effort on reasoning for reasoning models.

• #generate_summary ⇒ Symbol, ... deprecated Deprecated.
• #mode ⇒ String, ...

  Controls the reasoning execution mode for the request.

• #summary ⇒ Symbol, ...

  A summary of the reasoning performed by the model.

Class Method Summary

• .values ⇒ Array<Symbol>

Instance Method Summary

• #initialize(context: nil, effort: nil, generate_summary: nil, mode: nil, summary: nil) ⇒ Object constructor

  Some parameter documentations has been truncated, see Reasoning for more details.

• #to_hash ⇒ {

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, #inspect, inspect, meta_info, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize(context: nil, effort: nil, generate_summary: nil, mode: nil, summary: nil) ⇒ Object

Some parameter documentations has been truncated, see OpenAI::Models::Beta::ResponseCreateParams::Reasoning for more details.

gpt-5 and o-series models only

Configuration options for reasoning models.

Parameters:

• context (Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::Context, nil) (defaults to: nil) —

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

• effort (Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::Effort, nil) (defaults to: nil) —

  Constrains effort on reasoning for reasoning models. Currently supported

• generate_summary (Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::GenerateSummary, nil) (defaults to: nil) —

  Deprecated: use summary instead.

• mode (String, Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::Mode) (defaults to: nil) —

  Controls the reasoning execution mode for the request.

• summary (Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::Summary, nil) (defaults to: nil) —

  A summary of the reasoning performed by the model. This can be

# File 'lib/openai/models/beta/response_create_params.rb', line 1084

Instance Attribute Details

#context ⇒ Symbol, ...

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.

Parameters:

• value (OpenAI::Models::Beta::ResponseCreateParams::Reasoning::context, nil)

Returns:

• (Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::Context, nil)

# File 'lib/openai/models/beta/response_create_params.rb', line 1038

optional :context, enum: -> { OpenAI::Beta::ResponseCreateParams::Reasoning::Context }, nil?: true

#effort ⇒ Symbol, ...

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

Parameters:

• value (OpenAI::Models::Beta::ResponseCreateParams::Reasoning::effort, nil)

Returns:

• (Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::Effort, nil)

# File 'lib/openai/models/beta/response_create_params.rb', line 1049

optional :effort, enum: -> { OpenAI::Beta::ResponseCreateParams::Reasoning::Effort }, nil?: true

#generate_summary ⇒ Symbol, ...

Deprecated.

Deprecated: use summary instead.

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.

Parameters:

• value (OpenAI::Models::Beta::ResponseCreateParams::Reasoning::generate_summary, nil)

Returns:

• (Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::GenerateSummary, nil)

# File 'lib/openai/models/beta/response_create_params.rb', line 1061

optional :generate_summary,
enum: -> { OpenAI::Beta::ResponseCreateParams::Reasoning::GenerateSummary },
nil?: true

#mode ⇒ String, ...

Controls the reasoning execution mode for the request.

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

Returns:

• (String, Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::Mode, nil)

# File 'lib/openai/models/beta/response_create_params.rb', line 1071

optional :mode, union: -> { OpenAI::Beta::ResponseCreateParams::Reasoning::Mode }

#summary ⇒ Symbol, ...

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.

Parameters:

• value (OpenAI::Models::Beta::ResponseCreateParams::Reasoning::summary, nil)

Returns:

• (Symbol, OpenAI::Models::Beta::ResponseCreateParams::Reasoning::Summary, nil)

# File 'lib/openai/models/beta/response_create_params.rb', line 1082

optional :summary, enum: -> { OpenAI::Beta::ResponseCreateParams::Reasoning::Summary }, nil?: true

Class Method Details

.values ⇒ Array<Symbol>

Returns:

• (Array<Symbol>)

# File 'lib/openai/models/beta/response_create_params.rb', line 1118

Instance Method Details

#to_hash ⇒ {

Returns:

• ({)

# File 'sig/openai/models/beta/response_create_params.rbs', line 650

def to_hash: -> {