Class: OpenAI::Models::Responses::ResponsesClientEvent::ContextManagement

Inherits:

Internal::Type::BaseModel

• Object
• Internal::Type::BaseModel
• OpenAI::Models::Responses::ResponsesClientEvent::ContextManagement

Defined in:

lib/openai/models/responses/responses_client_event.rb

Instance Attribute Summary

• #compact_threshold ⇒ Integer^?

  Token threshold at which compaction should be triggered for this entry.

• #type ⇒ String

  The context management entry type.

Instance Method Summary

• #initialize(background: nil, context_management: nil, conversation: nil, include: nil, input: nil, instructions: nil, max_output_tokens: nil, max_tool_calls: nil, metadata: nil, model: nil, parallel_tool_calls: nil, previous_response_id: nil, prompt: nil, prompt_cache_key: nil, prompt_cache_retention: nil, reasoning: nil, safety_identifier: nil, service_tier: nil, store: nil, stream: nil, stream_options: nil, temperature: nil, text: nil, tool_choice: nil, tools: nil, top_logprobs: nil, top_p: nil, truncation: nil, user: nil, type: :"response.create") ⇒ Object constructor

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

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(background: nil, context_management: nil, conversation: nil, include: nil, input: nil, instructions: nil, max_output_tokens: nil, max_tool_calls: nil, metadata: nil, model: nil, parallel_tool_calls: nil, previous_response_id: nil, prompt: nil, prompt_cache_key: nil, prompt_cache_retention: nil, reasoning: nil, safety_identifier: nil, service_tier: nil, store: nil, stream: nil, stream_options: nil, temperature: nil, text: nil, tool_choice: nil, tools: nil, top_logprobs: nil, top_p: nil, truncation: nil, user: nil, type: :"response.create") ⇒ Object

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

Parameters:

• background (Boolean, nil) (defaults to: nil) —

  Whether to run the model response in the background.

• context_management (Array<OpenAI::Models::Responses::ResponsesClientEvent::ContextManagement>, nil) (defaults to: nil) —

  Context management configuration for this request.

• conversation (String, OpenAI::Models::Responses::ResponseConversationParam, nil) (defaults to: nil) —

  The conversation that this response belongs to. Items from this conversation are

• include (Array<Symbol, OpenAI::Models::Responses::ResponseIncludable>, nil) (defaults to: nil) —

  Specify additional output data to include in the model response. Currently suppo

• input (String, Array<OpenAI::Models::Responses::EasyInputMessage, OpenAI::Models::Responses::ResponseInputItem::Message, OpenAI::Models::Responses::ResponseOutputMessage, OpenAI::Models::Responses::ResponseFileSearchToolCall, OpenAI::Models::Responses::ResponseComputerToolCall, OpenAI::Models::Responses::ResponseInputItem::ComputerCallOutput, OpenAI::Models::Responses::ResponseFunctionWebSearch, OpenAI::Models::Responses::ResponseFunctionToolCall, OpenAI::Models::Responses::ResponseInputItem::FunctionCallOutput, OpenAI::Models::Responses::ResponseReasoningItem, OpenAI::Models::Responses::ResponseCompactionItemParam, OpenAI::Models::Responses::ResponseInputItem::ImageGenerationCall, OpenAI::Models::Responses::ResponseCodeInterpreterToolCall, OpenAI::Models::Responses::ResponseInputItem::LocalShellCall, OpenAI::Models::Responses::ResponseInputItem::LocalShellCallOutput, OpenAI::Models::Responses::ResponseInputItem::ShellCall, OpenAI::Models::Responses::ResponseInputItem::ShellCallOutput, OpenAI::Models::Responses::ResponseInputItem::ApplyPatchCall, OpenAI::Models::Responses::ResponseInputItem::ApplyPatchCallOutput, OpenAI::Models::Responses::ResponseInputItem::McpListTools, OpenAI::Models::Responses::ResponseInputItem::McpApprovalRequest, OpenAI::Models::Responses::ResponseInputItem::McpApprovalResponse, OpenAI::Models::Responses::ResponseInputItem::McpCall, OpenAI::Models::Responses::ResponseCustomToolCallOutput, OpenAI::Models::Responses::ResponseCustomToolCall, OpenAI::Models::Responses::ResponseInputItem::ItemReference>) (defaults to: nil) —

  Text, image, or file inputs to the model, used to generate a response.

• instructions (String, nil) (defaults to: nil) —

  A system (or developer) message inserted into the model’s context.

• max_output_tokens (Integer, nil) (defaults to: nil) —

  An upper bound for the number of tokens that can be generated for a response, in

• max_tool_calls (Integer, nil) (defaults to: nil) —

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

• metadata (Hash{Symbol=>String}, nil) (defaults to: nil) —

  Set of 16 key-value pairs that can be attached to an object. This can be

• model (String, Symbol, OpenAI::Models::ChatModel, OpenAI::Models::ResponsesModel::ResponsesOnlyModel) (defaults to: nil) —

  Model ID used to generate the response, like gpt-4o or o3. OpenAI

• parallel_tool_calls (Boolean, nil) (defaults to: nil) —

  Whether to allow the model to run tool calls in parallel.

• previous_response_id (String, nil) (defaults to: nil) —

  The unique ID of the previous response to the model. Use this to

• prompt (OpenAI::Models::Responses::ResponsePrompt, nil) (defaults to: nil) —

  Reference to a prompt template and its variables.

• prompt_cache_key (String) (defaults to: nil) —

  Used by OpenAI to cache responses for similar requests to optimize your cache hi

• prompt_cache_retention (Symbol, OpenAI::Models::Responses::ResponsesClientEvent::PromptCacheRetention, nil) (defaults to: nil) —

  The retention policy for the prompt cache. Set to 24h to enable extended promp

• reasoning (OpenAI::Models::Reasoning, nil) (defaults to: nil) —

  **gpt-5 and o-series models only**

• safety_identifier (String) (defaults to: nil) —

  A stable identifier used to help detect users of your application that may be vi

• service_tier (Symbol, OpenAI::Models::Responses::ResponsesClientEvent::ServiceTier, nil) (defaults to: nil) —

  Specifies the processing type used for serving the request.

• store (Boolean, nil) (defaults to: nil) —

  Whether to store the generated model response for later retrieval via

• stream (Boolean, nil) (defaults to: nil) —

  If set to true, the model response data will be streamed to the client

• stream_options (OpenAI::Models::Responses::ResponsesClientEvent::StreamOptions, nil) (defaults to: nil) —

  Options for streaming responses. Only set this when you set ‘stream: true`.

• temperature (Float, nil) (defaults to: nil) —

  What sampling temperature to use, between 0 and 2. Higher values like 0.8 will m

• text (OpenAI::Models::Responses::ResponseTextConfig) (defaults to: nil) —

  Configuration options for a text response from the model. Can be plain

• tool_choice (Symbol, OpenAI::Models::Responses::ToolChoiceOptions, OpenAI::Models::Responses::ToolChoiceAllowed, OpenAI::Models::Responses::ToolChoiceTypes, OpenAI::Models::Responses::ToolChoiceFunction, OpenAI::Models::Responses::ToolChoiceMcp, OpenAI::Models::Responses::ToolChoiceCustom, OpenAI::Models::Responses::ToolChoiceApplyPatch, OpenAI::Models::Responses::ToolChoiceShell) (defaults to: nil) —

  How the model should select which tool (or tools) to use when generating

• tools (Array<OpenAI::Models::Responses::FunctionTool, OpenAI::Models::Responses::FileSearchTool, OpenAI::Models::Responses::ComputerTool, OpenAI::Models::Responses::Tool::Mcp, OpenAI::Models::Responses::Tool::CodeInterpreter, OpenAI::Models::Responses::Tool::ImageGeneration, OpenAI::Models::Responses::Tool::LocalShell, OpenAI::Models::Responses::FunctionShellTool, OpenAI::Models::Responses::CustomTool, OpenAI::Models::Responses::ApplyPatchTool, OpenAI::Models::Responses::WebSearchTool, OpenAI::Models::Responses::WebSearchPreviewTool>) (defaults to: nil) —

  An array of tools the model may call while generating a response. You

• top_logprobs (Integer, nil) (defaults to: nil) —

  An integer between 0 and 20 specifying the number of most likely tokens to

• top_p (Float, nil) (defaults to: nil) —

  An alternative to sampling with temperature, called nucleus sampling,

• truncation (Symbol, OpenAI::Models::Responses::ResponsesClientEvent::Truncation, nil) (defaults to: nil) —

  The truncation strategy to use for the model response.

• user (String) (defaults to: nil) —

  This field is being replaced by safety_identifier and prompt_cache_key. Use

• type (Symbol, :"response.create") (defaults to: :"response.create") —

  The type of the client event. Always response.create.

# File 'lib/openai/models/responses/responses_client_event.rb', line 391

class ContextManagement < OpenAI::Internal::Type::BaseModel
  # @!attribute type
  #   The context management entry type. Currently only 'compaction' is supported.
  #
  #   @return [String]
  required :type, String

  # @!attribute compact_threshold
  #   Token threshold at which compaction should be triggered for this entry.
  #
  #   @return [Integer, nil]
  optional :compact_threshold, Integer, nil?: true

  # @!method initialize(type:, compact_threshold: nil)
  #   @param type [String] The context management entry type. Currently only 'compaction' is supported.
  #
  #   @param compact_threshold [Integer, nil] Token threshold at which compaction should be triggered for this entry.
end

Instance Attribute Details

#compact_threshold ⇒ Integer^?

Token threshold at which compaction should be triggered for this entry.

Returns:

• (Integer, nil)

# File 'lib/openai/models/responses/responses_client_event.rb', line 402

optional :compact_threshold, Integer, nil?: true

#type ⇒ String

The context management entry type. Currently only ‘compaction’ is supported.

Returns:

• (String)

# File 'lib/openai/models/responses/responses_client_event.rb', line 396

required :type, String