RubyGems - openai - Versions diffs - 0.91.0 → 0.93.0 - Mend

openai 0.91.0 → 0.93.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (1351) hide show

data/sig/openai/models/beta/beta_response.rbs CHANGED Viewed

@@ -43,98 +43,476 @@ module OpenAI
         }
       class BetaResponse < OpenAI::Internal::Type::BaseModel
+        # Unique identifier for this Response.
         attr_accessor id: String
+        # Unix timestamp (in seconds) of when this Response was created.
         attr_accessor created_at: Float
+        # An error object returned when the model fails to generate a Response.
         attr_accessor error: OpenAI::Beta::BetaResponseError?
+        # Details about why the response is incomplete.
         attr_accessor incomplete_details: OpenAI::Beta::BetaResponse::IncompleteDetails?
+        # A system (or developer) message inserted into the model's context.
+        #
+        # When using along with `previous_response_id`, the instructions from a previous
+        # response will not be carried over to the next response. This makes it simple to
+        # swap out system (or developer) messages in new responses.
         attr_accessor instructions: OpenAI::Models::Beta::BetaResponse::instructions?
+        # Set of 16 key-value pairs that can be attached to an object. This can be useful
+        # for storing additional information about the object in a structured format, and
+        # querying for objects via API or the dashboard.
+        #
+        # Keys are strings with a maximum length of 64 characters. Values are strings with
+        # a maximum length of 512 characters.
         attr_accessor metadata: ::Hash[Symbol, String]?
+        # Model ID used to generate the response, like `gpt-6-astra`. OpenAI offers a wide
+        # range of models with different capabilities, performance characteristics, and
+        # price points. Refer to the
+        # [model guide](https://developers.openai.com/api/docs/models) to browse and
+        # compare available models.
         attr_accessor model: OpenAI::Models::Beta::BetaResponse::model
+        # The object type of this resource - always set to `response`.
         attr_accessor object: :response
+        # An array of content items generated by the model.
+        #
+        # - The length and order of items in the `output` array is dependent on the
+        #   model's response.
+        # - Rather than accessing the first item in the `output` array and assuming it's
+        #   an `assistant` message with the content generated by the model, you might
+        #   consider using the `output_text` property where supported in SDKs.
         attr_accessor output: ::Array[OpenAI::Models::Beta::beta_response_output_item]
+        # Whether to allow the model to run tool calls in parallel.
         attr_accessor parallel_tool_calls: bool
+        # What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+        # make the output more random, while lower values like 0.2 will make it more
+        # focused and deterministic. We generally recommend altering this or `top_p` but
+        # not both.
         attr_accessor temperature: Float?
+        # How the model should select which tool (or tools) to use when generating a
+        # response. See the `tools` parameter to see how to specify which tools the model
+        # can call.
         attr_accessor tool_choice: OpenAI::Models::Beta::BetaResponse::tool_choice
+        # An array of tools the model may call while generating a response. You can
+        # specify which tool to use by setting the `tool_choice` parameter.
+        #
+        # We support the following categories of tools:
+        #
+        # - **Built-in tools**: Tools that are provided by OpenAI that extend the model's
+        #   capabilities, like
+        #   [web search](https://developers.openai.com/api/docs/guides/tools-web-search)
+        #   or
+        #   [file search](https://developers.openai.com/api/docs/guides/tools-file-search).
+        #   Learn more about
+        #   [built-in tools](https://developers.openai.com/api/docs/guides/tools).
+        # - **MCP Tools**: Integrations with third-party systems via custom MCP servers or
+        #   predefined connectors such as Google Drive and SharePoint. Learn more about
+        #   [MCP Tools](https://developers.openai.com/api/docs/guides/tools-connectors-mcp).
+        # - **Function calls (custom tools)**: Functions that are defined by you, enabling
+        #   the model to call your own code with strongly typed arguments and outputs.
+        #   Learn more about
+        #   [function calling](https://developers.openai.com/api/docs/guides/function-calling).
+        #   You can also use custom tools to call your own code.
         attr_accessor tools: ::Array[OpenAI::Models::Beta::beta_tool]
+        # An alternative to sampling with temperature, called nucleus sampling, where the
+        # model considers the results of the tokens with top_p probability mass. So 0.1
+        # means only the tokens comprising the top 10% probability mass are considered.
+        #
+        # We generally recommend altering this or `temperature` but not both.
         attr_accessor top_p: Float?
+        # Whether to run the model response in the background.
+        # [Learn more](https://developers.openai.com/api/docs/guides/background).
         attr_accessor background: bool?
+        # Unix timestamp (in seconds) of when this Response was completed. Only present
+        # when the status is `completed`.
         attr_accessor completed_at: Float?
+        # The conversation that this response belonged to. Input items and output items
+        # from this response were automatically added to this conversation.
         attr_accessor conversation: OpenAI::Beta::BetaResponse::Conversation?
+        # An upper bound for the number of tokens that can be generated for a response,
+        # including visible output tokens and
+        # [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning).
         attr_accessor max_output_tokens: Integer?
+        # The maximum number of total calls to built-in tools that can be processed in a
+        # response. This maximum number applies across all built-in tool calls, not per
+        # individual tool. Any further attempts to call a tool by the model will be
+        # ignored.
         attr_accessor max_tool_calls: Integer?
+        # Moderation results for the response input and output, if moderated completions
+        # were requested.
         attr_accessor moderation: OpenAI::Beta::BetaResponse::Moderation?
+        # The unique ID of the previous response to the model. Use this to create
+        # multi-turn conversations. Learn more about
+        # [conversation state](https://developers.openai.com/api/docs/guides/conversation-state).
+        # Cannot be used in conjunction with `conversation`.
         attr_accessor previous_response_id: String?
+        # Reference to a prompt template and its variables.
+        # [Learn more](https://developers.openai.com/api/docs/guides/text?api-mode=responses#version-prompts-in-code).
         attr_accessor prompt: OpenAI::Beta::BetaResponsePrompt?
+        # Prompt cache diagnostics requested for this response.
         attr_reader prompt_cache_diagnostics: OpenAI::Models::Beta::BetaResponse::prompt_cache_diagnostics?
+        # Prompt cache diagnostics requested for this response.
         def prompt_cache_diagnostics=: (
           OpenAI::Models::Beta::BetaResponse::prompt_cache_diagnostics
         ) -> OpenAI::Models::Beta::BetaResponse::prompt_cache_diagnostics
+        # Used by OpenAI to cache responses for similar requests to optimize your cache
+        # hit rates. Replaces the `user` field.
+        # [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching).
         attr_accessor prompt_cache_key: String?
+        # The prompt-caching options that were applied to the response. Supported for
+        # `gpt-5.6` and later models.
         attr_reader prompt_cache_options: OpenAI::Beta::BetaResponse::PromptCacheOptions?
+        # The prompt-caching options that were applied to the response. Supported for
+        # `gpt-5.6` and later models.
         def prompt_cache_options=: (
           OpenAI::Beta::BetaResponse::PromptCacheOptions
         ) -> OpenAI::Beta::BetaResponse::PromptCacheOptions
+        # Deprecated. Use `prompt_cache_options.ttl` instead.
+        #
+        # The retention policy for the prompt cache. Set to `24h` to enable extended
+        # prompt caching, which keeps cached prefixes active for longer, up to a maximum
+        # of 24 hours.
+        # [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention).
+        # This field expresses a maximum retention policy, while
+        # `prompt_cache_options.ttl` expresses a minimum cache lifetime. The two fields
+        # are independent and do not interact. For `gpt-5.5`, `gpt-5.5-pro`, and future
+        # models, only `24h` is supported.
+        #
+        # For older models that support both `in_memory` and `24h`, the default depends on
+        # your organization's data retention policy:
+        #
+        # - Organizations without ZDR enabled default to `24h`.
+        # - Organizations with ZDR enabled default to `in_memory` when
+        #   `prompt_cache_retention` is not specified.
         attr_accessor prompt_cache_retention: OpenAI::Models::Beta::BetaResponse::prompt_cache_retention?
+        # Configuration options for
+        # [reasoning models](https://developers.openai.com/api/docs/guides/reasoning).
         attr_accessor reasoning: OpenAI::Beta::BetaResponse::Reasoning?
+        # A stable identifier used to help detect users of your application that may be
+        # violating OpenAI's usage policies. The IDs should be a string that uniquely
+        # identifies each user, with a maximum length of 64 characters. We recommend
+        # hashing their username or email address, in order to avoid sending us any
+        # identifying information.
+        # [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).
         attr_accessor safety_identifier: String?
+        # Specifies the processing type used for serving the request.
+        #
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the request will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to
+        #   '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then
+        #   the request will be processed with the Flex Processing service tier.
+        # - To opt-in to
+        #   [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the
+        #   request level, include the `service_tier=fast` or `service_tier=priority`
+        #   parameter for Responses or Chat Completions. The response will show
+        #   `service_tier=priority` regardless of if you specify `service_tier=fast` or
+        #   `priority` in your request.
+        # - If set to 'ultrafast', then the request will be processed with the
+        #   access-controlled Ultrafast Processing service tier. This tier is currently
+        #   available for `gpt-5.6-sol`; a response served through it will show
+        #   `service_tier=ultrafast`.
+        # - When not set, the default behavior is 'auto'.
+        #
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         attr_accessor service_tier: OpenAI::Models::Beta::BetaResponse::service_tier?
+        # The status of the response generation. One of `completed`, `failed`,
+        # `in_progress`, `cancelled`, `queued`, or `incomplete`.
         attr_reader status: OpenAI::Models::Beta::beta_response_status?
+        # The status of the response generation. One of `completed`, `failed`,
+        # `in_progress`, `cancelled`, `queued`, or `incomplete`.
         def status=: (
           OpenAI::Models::Beta::beta_response_status
         ) -> OpenAI::Models::Beta::beta_response_status
+        # Configuration options for a text response from the model. Can be plain text or
+        # structured JSON data. Learn more:
+        #
+        # - [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text)
+        # - [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs)
         attr_reader text: OpenAI::Beta::BetaResponseTextConfig?
+        # Configuration options for a text response from the model. Can be plain text or
+        # structured JSON data. Learn more:
+        #
+        # - [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text)
+        # - [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs)
         def text=: (
           OpenAI::Beta::BetaResponseTextConfig
         ) -> OpenAI::Beta::BetaResponseTextConfig
+        # An integer between 0 and 20 specifying the maximum number of most likely tokens
+        # to return at each token position, each with an associated log probability. In
+        # some cases, the number of returned tokens may be fewer than requested.
         attr_accessor top_logprobs: Integer?
+        # The truncation strategy to use for the model response.
+        #
+        # - `auto`: If the input to this Response exceeds the model's context window size,
+        #   the model will truncate the response to fit the context window by dropping
+        #   items from the beginning of the conversation.
+        # - `disabled` (default): If the input size will exceed the context window size
+        #   for a model, the request will fail with a 400 error.
         attr_accessor truncation: OpenAI::Models::Beta::BetaResponse::truncation?
+        # Represents token usage details including input tokens, output tokens, a
+        # breakdown of output tokens, and the total tokens used.
         attr_reader usage: OpenAI::Beta::BetaResponseUsage?
+        # Represents token usage details including input tokens, output tokens, a
+        # breakdown of output tokens, and the total tokens used.
         def usage=: (
           OpenAI::Beta::BetaResponseUsage
         ) -> OpenAI::Beta::BetaResponseUsage
+        # This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use
+        # `prompt_cache_key` instead to maintain caching optimizations. A stable
+        # identifier for your end-users. Used to boost cache hit rates by better bucketing
+        # similar requests and to help OpenAI detect and prevent abuse.
+        # [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).
         attr_reader user: String?
+        # This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use
+        # `prompt_cache_key` instead to maintain caching optimizations. A stable
+        # identifier for your end-users. Used to boost cache hit rates by better bucketing
+        # similar requests and to help OpenAI detect and prevent abuse.
+        # [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).
         def user=: (String) -> String
+        # @param id
+        #   Unique identifier for this Response.
+        # @param created_at
+        #   Unix timestamp (in seconds) of when this Response was created.
+        # @param error
+        #   An error object returned when the model fails to generate a Response.
+        # @param incomplete_details
+        #   Details about why the response is incomplete.
+        # @param instructions
+        #   A system (or developer) message inserted into the model's context.
+        #
+        #   When using along with `previous_response_id`, the instructions from a previous
+        #   response will not be carried over to the next response. This makes it simple to
+        #   swap out system (or developer) messages in new responses.
+        # @param metadata
+        #   Set of 16 key-value pairs that can be attached to an object. This can be useful
+        #   for storing additional information about the object in a structured format, and
+        #   querying for objects via API or the dashboard.
+        #
+        #   Keys are strings with a maximum length of 64 characters. Values are strings with
+        #   a maximum length of 512 characters.
+        # @param model
+        #   Model ID used to generate the response, like `gpt-6-astra`. OpenAI offers a wide
+        #   range of models with different capabilities, performance characteristics, and
+        #   price points. Refer to the
+        #   [model guide](https://developers.openai.com/api/docs/models) to browse and
+        #   compare available models.
+        # @param output
+        #   An array of content items generated by the model.
+        #
+        #   - The length and order of items in the `output` array is dependent on the
+        #     model's response.
+        #   - Rather than accessing the first item in the `output` array and assuming it's
+        #     an `assistant` message with the content generated by the model, you might
+        #     consider using the `output_text` property where supported in SDKs.
+        # @param parallel_tool_calls
+        #   Whether to allow the model to run tool calls in parallel.
+        # @param temperature
+        #   What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+        #   make the output more random, while lower values like 0.2 will make it more
+        #   focused and deterministic. We generally recommend altering this or `top_p` but
+        #   not both.
+        # @param tool_choice
+        #   How the model should select which tool (or tools) to use when generating a
+        #   response. See the `tools` parameter to see how to specify which tools the model
+        #   can call.
+        # @param tools
+        #   An array of tools the model may call while generating a response. You can
+        #   specify which tool to use by setting the `tool_choice` parameter.
+        #
+        #   We support the following categories of tools:
+        #
+        #   - **Built-in tools**: Tools that are provided by OpenAI that extend the model's
+        #     capabilities, like
+        #     [web search](https://developers.openai.com/api/docs/guides/tools-web-search)
+        #     or
+        #     [file search](https://developers.openai.com/api/docs/guides/tools-file-search).
+        #     Learn more about
+        #     [built-in tools](https://developers.openai.com/api/docs/guides/tools).
+        #   - **MCP Tools**: Integrations with third-party systems via custom MCP servers or
+        #     predefined connectors such as Google Drive and SharePoint. Learn more about
+        #     [MCP Tools](https://developers.openai.com/api/docs/guides/tools-connectors-mcp).
+        #   - **Function calls (custom tools)**: Functions that are defined by you, enabling
+        #     the model to call your own code with strongly typed arguments and outputs.
+        #     Learn more about
+        #     [function calling](https://developers.openai.com/api/docs/guides/function-calling).
+        #     You can also use custom tools to call your own code.
+        # @param top_p
+        #   An alternative to sampling with temperature, called nucleus sampling, where the
+        #   model considers the results of the tokens with top_p probability mass. So 0.1
+        #   means only the tokens comprising the top 10% probability mass are considered.
+        #
+        #   We generally recommend altering this or `temperature` but not both.
+        # @param background
+        #   Whether to run the model response in the background.
+        #   [Learn more](https://developers.openai.com/api/docs/guides/background).
+        # @param completed_at
+        #   Unix timestamp (in seconds) of when this Response was completed. Only present
+        #   when the status is `completed`.
+        # @param conversation
+        #   The conversation that this response belonged to. Input items and output items
+        #   from this response were automatically added to this conversation.
+        # @param max_output_tokens
+        #   An upper bound for the number of tokens that can be generated for a response,
+        #   including visible output tokens and
+        #   [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning).
+        # @param max_tool_calls
+        #   The maximum number of total calls to built-in tools that can be processed in a
+        #   response. This maximum number applies across all built-in tool calls, not per
+        #   individual tool. Any further attempts to call a tool by the model will be
+        #   ignored.
+        # @param moderation
+        #   Moderation results for the response input and output, if moderated completions
+        #   were requested.
+        # @param previous_response_id
+        #   The unique ID of the previous response to the model. Use this to create
+        #   multi-turn conversations. Learn more about
+        #   [conversation state](https://developers.openai.com/api/docs/guides/conversation-state).
+        #   Cannot be used in conjunction with `conversation`.
+        # @param prompt
+        #   Reference to a prompt template and its variables.
+        #   [Learn more](https://developers.openai.com/api/docs/guides/text?api-mode=responses#version-prompts-in-code).
+        # @param prompt_cache_diagnostics
+        #   Prompt cache diagnostics requested for this response.
+        # @param prompt_cache_key
+        #   Used by OpenAI to cache responses for similar requests to optimize your cache
+        #   hit rates. Replaces the `user` field.
+        #   [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching).
+        # @param prompt_cache_options
+        #   The prompt-caching options that were applied to the response. Supported for
+        #   `gpt-5.6` and later models.
+        # @param prompt_cache_retention
+        #   Deprecated. Use `prompt_cache_options.ttl` instead.
+        #
+        #   The retention policy for the prompt cache. Set to `24h` to enable extended
+        #   prompt caching, which keeps cached prefixes active for longer, up to a maximum
+        #   of 24 hours.
+        #   [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention).
+        #   This field expresses a maximum retention policy, while
+        #   `prompt_cache_options.ttl` expresses a minimum cache lifetime. The two fields
+        #   are independent and do not interact. For `gpt-5.5`, `gpt-5.5-pro`, and future
+        #   models, only `24h` is supported.
+        #
+        #   For older models that support both `in_memory` and `24h`, the default depends on
+        #   your organization's data retention policy:
+        #
+        #   - Organizations without ZDR enabled default to `24h`.
+        #   - Organizations with ZDR enabled default to `in_memory` when
+        #     `prompt_cache_retention` is not specified.
+        # @param reasoning
+        #   Configuration options for
+        #   [reasoning models](https://developers.openai.com/api/docs/guides/reasoning).
+        # @param safety_identifier
+        #   A stable identifier used to help detect users of your application that may be
+        #   violating OpenAI's usage policies. The IDs should be a string that uniquely
+        #   identifies each user, with a maximum length of 64 characters. We recommend
+        #   hashing their username or email address, in order to avoid sending us any
+        #   identifying information.
+        #   [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).
+        # @param service_tier
+        #   Specifies the processing type used for serving the request.
+        #
+        #   - If set to 'auto', then the request will be processed with the service tier
+        #     configured in the Project settings. Unless otherwise configured, the Project
+        #     will use 'default'.
+        #   - If set to 'default', then the request will be processed with the standard
+        #     pricing and performance for the selected model.
+        #   - If set to
+        #     '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then
+        #     the request will be processed with the Flex Processing service tier.
+        #   - To opt-in to
+        #     [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the
+        #     request level, include the `service_tier=fast` or `service_tier=priority`
+        #     parameter for Responses or Chat Completions. The response will show
+        #     `service_tier=priority` regardless of if you specify `service_tier=fast` or
+        #     `priority` in your request.
+        #   - If set to 'ultrafast', then the request will be processed with the
+        #     access-controlled Ultrafast Processing service tier. This tier is currently
+        #     available for `gpt-5.6-sol`; a response served through it will show
+        #     `service_tier=ultrafast`.
+        #   - When not set, the default behavior is 'auto'.
+        #
+        #   When the `service_tier` parameter is set, the response body will include the
+        #   `service_tier` value based on the processing mode actually used to serve the
+        #   request. This response value may be different from the value set in the
+        #   parameter.
+        # @param status
+        #   The status of the response generation. One of `completed`, `failed`,
+        #   `in_progress`, `cancelled`, `queued`, or `incomplete`.
+        # @param text
+        #   Configuration options for a text response from the model. Can be plain text or
+        #   structured JSON data. Learn more:
+        #
+        #   - [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text)
+        #   - [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs)
+        # @param top_logprobs
+        #   An integer between 0 and 20 specifying the maximum number of most likely tokens
+        #   to return at each token position, each with an associated log probability. In
+        #   some cases, the number of returned tokens may be fewer than requested.
+        # @param truncation
+        #   The truncation strategy to use for the model response.
+        #
+        #   - `auto`: If the input to this Response exceeds the model's context window size,
+        #     the model will truncate the response to fit the context window by dropping
+        #     items from the beginning of the conversation.
+        #   - `disabled` (default): If the input size will exceed the context window size
+        #     for a model, the request will fail with a 400 error.
+        # @param usage
+        #   Represents token usage details including input tokens, output tokens, a
+        #   breakdown of output tokens, and the total tokens used.
+        # @param user
+        #   This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use
+        #   `prompt_cache_key` instead to maintain caching optimizations. A stable
+        #   identifier for your end-users. Used to boost cache hit rates by better bucketing
+        #   similar requests and to help OpenAI detect and prevent abuse.
+        #   [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).
+        # @param object
+        #   The object type of this resource - always set to `response`.
         def initialize: (
           id: String,
           created_at: Float,
@@ -217,12 +595,22 @@ module OpenAI
           }
         class IncompleteDetails < OpenAI::Internal::Type::BaseModel
+          # The reason why the response is incomplete. `steered` means the response stopped
+          # at a safe output boundary after a WebSocket `response.steer` event. The server
+          # can then create a successor response automatically with the queued input.
           attr_reader reason: OpenAI::Models::Beta::BetaResponse::IncompleteDetails::reason?
+          # The reason why the response is incomplete. `steered` means the response stopped
+          # at a safe output boundary after a WebSocket `response.steer` event. The server
+          # can then create a successor response automatically with the queued input.
           def reason=: (
             OpenAI::Models::Beta::BetaResponse::IncompleteDetails::reason
           ) -> OpenAI::Models::Beta::BetaResponse::IncompleteDetails::reason
+          # @param reason
+          #   The reason why the response is incomplete. `steered` means the response stopped
+          #   at a safe output boundary after a WebSocket `response.steer` event. The server
+          #   can then create a successor response automatically with the queued input.
           def initialize: (
             ?reason: OpenAI::Models::Beta::BetaResponse::IncompleteDetails::reason
           ) -> void
@@ -278,6 +666,7 @@ module OpenAI
           | :"gpt-5.1"
           | :"gpt-5.1-2025-11-13"
           | :"gpt-5.1-codex"
+          | :"gpt-5.1-mini"
           | :"gpt-5.1-chat-latest"
           | :"gpt-5"
           | :"gpt-5-mini"
@@ -343,7 +732,6 @@ module OpenAI
           | :"gpt-3.5-turbo-1106"
           | :"gpt-3.5-turbo-0125"
           | :"gpt-3.5-turbo-16k-0613"
-          | :"gpt-5.1-mini"
           | :"o1-pro"
           | :"o1-pro-2025-03-19"
           | :"o3-pro"
@@ -390,6 +778,7 @@ module OpenAI
           GPT_5_1: :"gpt-5.1"
           GPT_5_1_2025_11_13: :"gpt-5.1-2025-11-13"
           GPT_5_1_CODEX: :"gpt-5.1-codex"
+          GPT_5_1_MINI: :"gpt-5.1-mini"
           GPT_5_1_CHAT_LATEST: :"gpt-5.1-chat-latest"
           GPT_5: :"gpt-5"
           GPT_5_MINI: :"gpt-5-mini"
@@ -455,7 +844,6 @@ module OpenAI
           GPT_3_5_TURBO_1106: :"gpt-3.5-turbo-1106"
           GPT_3_5_TURBO_0125: :"gpt-3.5-turbo-0125"
           GPT_3_5_TURBO_16K_0613: :"gpt-3.5-turbo-16k-0613"
-          GPT_5_1_MINI: :"gpt-5.1-mini"
           O1_PRO: :"o1-pro"
           O1_PRO_2025_03_19: :"o1-pro-2025-03-19"
           O3_PRO: :"o3-pro"
@@ -495,8 +883,11 @@ module OpenAI
             { ?type: :programmatic_tool_calling }
           class BetaSpecificProgrammaticToolCallingParam < OpenAI::Internal::Type::BaseModel
+            # The tool to call. Always `programmatic_tool_calling`.
             attr_accessor type: :programmatic_tool_calling
+            # @param type
+            #   The tool to call. Always `programmatic_tool_calling`.
             def initialize: (?type: :programmatic_tool_calling) -> void
             def to_hash: -> { ?type: :programmatic_tool_calling }
@@ -508,8 +899,11 @@ module OpenAI
         type conversation = { id: String }
         class Conversation < OpenAI::Internal::Type::BaseModel
+          # The unique ID of the conversation that this response was associated with.
           attr_accessor id: String
+          # @param id
+          #   The unique ID of the conversation that this response was associated with.
           def initialize: (id: String) -> void
           def to_hash: -> { id: String }
@@ -522,10 +916,16 @@ module OpenAI
           }
         class Moderation < OpenAI::Internal::Type::BaseModel
+          # Moderation for the response input.
           attr_accessor input: OpenAI::Models::Beta::BetaResponse::Moderation::input
+          # Moderation for the response output.
           attr_accessor output: OpenAI::Models::Beta::BetaResponse::Moderation::output
+          # @param input
+          #   Moderation for the response input.
+          # @param output
+          #   Moderation for the response output.
           def initialize: (
             input: OpenAI::Models::Beta::BetaResponse::Moderation::input,
             output: OpenAI::Models::Beta::BetaResponse::Moderation::output
@@ -554,18 +954,40 @@ module OpenAI
               }
             class ModerationResult < OpenAI::Internal::Type::BaseModel
+              # A dictionary of moderation categories to booleans, True if the input is flagged
+              # under this category.
               attr_accessor categories: ::Hash[Symbol, bool]
+              # Which modalities of input are reflected by the score for each category.
               attr_accessor category_applied_input_types: ::Hash[Symbol, ::Array[OpenAI::Models::Beta::BetaResponse::Moderation::Input::ModerationResult::category_applied_input_type]]
+              # A dictionary of moderation categories to scores.
               attr_accessor category_scores: ::Hash[Symbol, Float]
+              # A boolean indicating whether the content was flagged by any category.
               attr_accessor flagged: bool
+              # The moderation model that produced this result.
               attr_accessor model: String
+              # The object type, which was always `moderation_result` for successful moderation
+              # results.
               attr_accessor type: :moderation_result
+              # @param categories
+              #   A dictionary of moderation categories to booleans, True if the input is flagged
+              #   under this category.
+              # @param category_applied_input_types
+              #   Which modalities of input are reflected by the score for each category.
+              # @param category_scores
+              #   A dictionary of moderation categories to scores.
+              # @param flagged
+              #   A boolean indicating whether the content was flagged by any category.
+              # @param model
+              #   The moderation model that produced this result.
+              # @param type
+              #   The object type, which was always `moderation_result` for successful moderation
+              #   results.
               def initialize: (
                 categories: ::Hash[Symbol, bool],
                 category_applied_input_types: ::Hash[Symbol, ::Array[OpenAI::Models::Beta::BetaResponse::Moderation::Input::ModerationResult::category_applied_input_type]],
@@ -599,12 +1021,21 @@ module OpenAI
             type error = { code: String, message: String, ?type: :error }
             class Error < OpenAI::Internal::Type::BaseModel
+              # The error code.
               attr_accessor code: String
+              # The error message.
               attr_accessor message: String
+              # The object type, which was always `error` for moderation failures.
               attr_accessor type: :error
+              # @param code
+              #   The error code.
+              # @param message
+              #   The error message.
+              # @param type
+              #   The object type, which was always `error` for moderation failures.
               def initialize: (
                 code: String,
                 message: String,
@@ -635,18 +1066,40 @@ module OpenAI
               }
             class ModerationResult < OpenAI::Internal::Type::BaseModel
+              # A dictionary of moderation categories to booleans, True if the input is flagged
+              # under this category.
               attr_accessor categories: ::Hash[Symbol, bool]
+              # Which modalities of input are reflected by the score for each category.
               attr_accessor category_applied_input_types: ::Hash[Symbol, ::Array[OpenAI::Models::Beta::BetaResponse::Moderation::Output::ModerationResult::category_applied_input_type]]
+              # A dictionary of moderation categories to scores.
               attr_accessor category_scores: ::Hash[Symbol, Float]
+              # A boolean indicating whether the content was flagged by any category.
               attr_accessor flagged: bool
+              # The moderation model that produced this result.
               attr_accessor model: String
+              # The object type, which was always `moderation_result` for successful moderation
+              # results.
               attr_accessor type: :moderation_result
+              # @param categories
+              #   A dictionary of moderation categories to booleans, True if the input is flagged
+              #   under this category.
+              # @param category_applied_input_types
+              #   Which modalities of input are reflected by the score for each category.
+              # @param category_scores
+              #   A dictionary of moderation categories to scores.
+              # @param flagged
+              #   A boolean indicating whether the content was flagged by any category.
+              # @param model
+              #   The moderation model that produced this result.
+              # @param type
+              #   The object type, which was always `moderation_result` for successful moderation
+              #   results.
               def initialize: (
                 categories: ::Hash[Symbol, bool],
                 category_applied_input_types: ::Hash[Symbol, ::Array[OpenAI::Models::Beta::BetaResponse::Moderation::Output::ModerationResult::category_applied_input_type]],
@@ -680,12 +1133,21 @@ module OpenAI
             type error = { code: String, message: String, ?type: :error }
             class Error < OpenAI::Internal::Type::BaseModel
+              # The error code.
               attr_accessor code: String
+              # The error message.
               attr_accessor message: String
+              # The object type, which was always `error` for moderation failures.
               attr_accessor type: :error
+              # @param code
+              #   The error code.
+              # @param message
+              #   The error message.
+              # @param type
+              #   The object type, which was always `error` for moderation failures.
               def initialize: (
                 code: String,
                 message: String,
@@ -717,16 +1179,28 @@ module OpenAI
             }
           class CacheMiss < OpenAI::Internal::Type::BaseModel
+            # The estimated number of input tokens affected after the first detected
+            # divergence.
             attr_accessor cache_missed_tokens: Integer
+            # The reason prompt cache reuse did not occur.
             attr_accessor reason: OpenAI::Models::Beta::BetaResponse::PromptCacheDiagnostics::CacheMiss::reason
             attr_accessor type: :cache_miss
+            # The raw token count of the reusable prefix in the compared response.
             attr_reader comparison_reusable_tokens: Integer?
+            # The raw token count of the reusable prefix in the compared response.
             def comparison_reusable_tokens=: (Integer) -> Integer
+            # @param cache_missed_tokens
+            #   The estimated number of input tokens affected after the first detected
+            #   divergence.
+            # @param reason
+            #   The reason prompt cache reuse did not occur.
+            # @param comparison_reusable_tokens
+            #   The raw token count of the reusable prefix in the compared response.
             def initialize: (
               cache_missed_tokens: Integer,
               reason: OpenAI::Models::Beta::BetaResponse::PromptCacheDiagnostics::CacheMiss::reason,
@@ -811,12 +1285,21 @@ module OpenAI
           }
         class PromptCacheOptions < OpenAI::Internal::Type::BaseModel
+          # Whether implicit prompt-cache breakpoints were enabled.
           attr_accessor mode: OpenAI::Models::Beta::BetaResponse::PromptCacheOptions::mode
+          # The minimum lifetime applied to each cache breakpoint.
           attr_accessor ttl: OpenAI::Models::Beta::BetaResponse::PromptCacheOptions::ttl
+          # The response ID supplied as the prompt cache diagnostics comparison.
           attr_accessor comparison_response_id: String?
+          # @param mode
+          #   Whether implicit prompt-cache breakpoints were enabled.
+          # @param ttl
+          #   The minimum lifetime applied to each cache breakpoint.
+          # @param comparison_response_id
+          #   The response ID supplied as the prompt cache diagnostics comparison.
           def initialize: (
             mode: OpenAI::Models::Beta::BetaResponse::PromptCacheOptions::mode,
             ttl: OpenAI::Models::Beta::BetaResponse::PromptCacheOptions::ttl,
@@ -872,20 +1355,80 @@ module OpenAI
           }
         class Reasoning < OpenAI::Internal::Type::BaseModel
+          # 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.
           attr_accessor context: OpenAI::Models::Beta::BetaResponse::Reasoning::context?
+          # 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](https://developers.openai.com/api/docs/guides/reasoning) for
+          # model-specific support.
           attr_accessor effort: OpenAI::Models::Beta::BetaResponse::Reasoning::effort?
+          # **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`.
           attr_accessor generate_summary: OpenAI::Models::Beta::BetaResponse::Reasoning::generate_summary?
+          # Controls the reasoning execution mode for the request.
+          #
+          # When returned on a response, this is the effective execution mode.
           attr_reader mode: OpenAI::Models::Beta::BetaResponse::Reasoning::mode?
+          # Controls the reasoning execution mode for the request.
+          #
+          # When returned on a response, this is the effective execution mode.
           def mode=: (
             OpenAI::Models::Beta::BetaResponse::Reasoning::mode
           ) -> OpenAI::Models::Beta::BetaResponse::Reasoning::mode
+          # 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`.
           attr_accessor summary: OpenAI::Models::Beta::BetaResponse::Reasoning::summary?
+          # @param context
+          #   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.
+          # @param effort
+          #   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](https://developers.openai.com/api/docs/guides/reasoning) for
+          #   model-specific support.
+          # @param generate_summary
+          #   **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`.
+          # @param mode
+          #   Controls the reasoning execution mode for the request.
+          #
+          #   When returned on a response, this is the effective execution mode.
+          # @param summary
+          #   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`.
           def initialize: (
             ?context: OpenAI::Models::Beta::BetaResponse::Reasoning::context?,
             ?effort: OpenAI::Models::Beta::BetaResponse::Reasoning::effort?,