struct

AI::OpenAI::Responses::ProviderOptions

Inherits JSON::Serializable < Struct < Value < Object

Provider options for Responses API

Constructors

new(pull : JSON::PullParser)

new(conversation : String | Nil = nil, include_values : Array(IncludeValue) | Nil = nil, instructions : String | Nil = nil, logprobs : LogprobsValue | Nil = nil, max_tool_calls : Int32 | Nil = nil, metadata : JSON::Any | Nil = nil, parallel_tool_calls : Bool | Nil = nil, previous_response_id : String | Nil = nil, prompt_cache_key : String | Nil = nil, prompt_cache_retention : PromptCacheRetention | Nil = nil, reasoning_effort : String | Nil = nil, reasoning_summary : String | Nil = nil, safety_identifier : String | Nil = nil, service_tier : ServiceTier | Nil = nil, store : Bool | Nil = nil, strict_json_schema : Bool | Nil = nil, text_verbosity : TextVerbosity | Nil = nil, truncation : Truncation | Nil = nil, user : String | Nil = nil, system_message_mode : SystemMessageMode | Nil = nil, force_reasoning : Bool | Nil = nil)

new(conversation : String | Nil = nil, include_values : Array(IncludeValue) | Nil = nil, instructions : String | Nil = nil, logprobs : Bool | Int32 | Nil = nil, max_tool_calls : Int32 | Nil = nil, metadata : JSON::Any | Nil = nil, parallel_tool_calls : Bool | Nil = nil, previous_response_id : String | Nil = nil, prompt_cache_key : String | Nil = nil, prompt_cache_retention : PromptCacheRetention | Nil = nil, reasoning_effort : String | Nil = nil, reasoning_summary : String | Nil = nil, safety_identifier : String | Nil = nil, service_tier : ServiceTier | Nil = nil, store : Bool | Nil = nil, strict_json_schema : Bool | Nil = nil, text_verbosity : TextVerbosity | Nil = nil, truncation : Truncation | Nil = nil, user : String | Nil = nil, system_message_mode : SystemMessageMode | Nil = nil, force_reasoning : Bool | Nil = nil)

Convenience initializer with Bool or Int32 for logprobs

new(*, __pull_for_json_serializable pull : JSON::PullParser)

Instance methods

conversation

The ID of the OpenAI Conversation to continue. You must create a conversation first via the OpenAI API. Cannot be used in conjunction with previousResponseId.

force_reasoning

Force treating this model as a reasoning model.

include_values

The set of extra fields to include in the response. Example values: 'reasoning.encrypted_content', 'file_search_call.results', 'message.output_text.logprobs'.

instructions

Instructions for the model. They can be used to change the system or developer message when continuing a conversation.

logprobs

Return the log probabilities of the tokens. Setting to true will return the log probabilities of the tokens that were generated. Setting to a number will return the log probabilities of the top n tokens.

max_tool_calls

The maximum number of total calls to built-in tools that can be processed in a response.

metadata

Additional metadata to store with the generation.

parallel_tool_calls

Whether to use parallel tool calls. Defaults to true.

previous_response_id

The ID of the previous response. You can use it to continue a conversation.

prompt_cache_key

Sets a cache key to tie this prompt to cached prefixes for better caching performance.

prompt_cache_retention

The retention policy for the prompt cache.

reasoning_effort

Reasoning effort for reasoning models. Valid values: 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh'

reasoning_summary

Controls reasoning summary output from the model.

safety_identifier

The identifier for safety monitoring and tracking.

service_tier

Service tier for the request.

store

Whether to store the generation. Defaults to true.

strict_json_schema

Whether to use strict JSON schema validation. Defaults to true.

system_message_mode

Override the system message mode for this model.

text_verbosity

Controls the verbosity of the model's responses.

truncation

Controls output truncation.

user

A unique identifier representing your end-user.