Class: OpenAI::Models::Responses::EasyInputMessage

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/openai/models/responses/easy_input_message.rb

Defined Under Namespace

Modules: Content, Phase, Role, Type

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

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(content:, role:, phase: nil, type: nil) ⇒ Object

Some parameter documentations has been truncated, see OpenAI::Models::Responses::EasyInputMessage for more details.

A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.

Parameters:




# File 'lib/openai/models/responses/easy_input_message.rb', line 36

Instance Attribute Details

#content ⇒ String, Array<OpenAI::Models::Responses::ResponseInputText, OpenAI::Models::Responses::ResponseInputImage, OpenAI::Models::Responses::ResponseInputFile>

Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.

Returns:



12
 
# File 'lib/openai/models/responses/easy_input_message.rb', line 12

required :content, union: -> { OpenAI::Responses::EasyInputMessage::Content }

#phase ⇒ Symbol, ...

Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.

Returns:



28
 
# File 'lib/openai/models/responses/easy_input_message.rb', line 28

optional :phase, enum: -> { OpenAI::Responses::EasyInputMessage::Phase }, nil?: true

#role ⇒ Symbol, OpenAI::Models::Responses::EasyInputMessage::Role

The role of the message input. One of user, assistant, system, or developer.

Returns:



19
 
# File 'lib/openai/models/responses/easy_input_message.rb', line 19

required :role, enum: -> { OpenAI::Responses::EasyInputMessage::Role }

#type ⇒ Symbol, ...

The type of the message input. Always message.

Returns:



34
 
# File 'lib/openai/models/responses/easy_input_message.rb', line 34

optional :type, enum: -> { OpenAI::Responses::EasyInputMessage::Type }

Class Method Details

.values ⇒ Array<Symbol>

Returns:

  • (Array<Symbol>) 



# File 'lib/openai/models/responses/easy_input_message.rb', line 84

.variants ⇒ Array(String, Array<OpenAI::Models::Responses::ResponseInputText, OpenAI::Models::Responses::ResponseInputImage, OpenAI::Models::Responses::ResponseInputFile>)

Returns:




# File 'lib/openai/models/responses/easy_input_message.rb', line 68