--- url: >- https://adk.nht.io/api/@nhtio/adk/batteries/llm/openai_responses/types/interfaces/OpenAIResponsesRequestBody.md description: >- The WIRE body shape this battery constructs and sends — not a 1:1 mirror of consumer-settable options. `instructions` and `store` are ALWAYS adapter-computed; neither is a key on [`OpenAIResponsesAdapterOptions`](https://adk.nht.io/api/@nhtio/adk/batteries/llm/openai_responses/types/interfaces/OpenAIResponsesAdapterOptions). --- # Interface: OpenAIResponsesRequestBody Defined in: [src/batteries/llm/openai\_responses/types.ts:641](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L641) The WIRE body shape this battery constructs and sends — not a 1:1 mirror of consumer-settable options. `instructions` and `store` are ALWAYS adapter-computed; neither is a key on [OpenAIResponsesAdapterOptions](OpenAIResponsesAdapterOptions.md). ## Indexable ```ts [key: string]: unknown ``` ## Properties | Property | Type | Description | Defined in | | ---------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | | `background?` | `boolean` | Request the generation run in the background (async). | [src/batteries/llm/openai\_responses/types.ts:688](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L688) | | `include?` | [`OpenAIResponsesIncludable`](../type-aliases/OpenAIResponsesIncludable.md)\[] | Additional output data requested from the model, e.g. `'reasoning.encrypted_content'`. | [src/batteries/llm/openai\_responses/types.ts:653](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L653) | | `input` | [`OpenAIResponsesInputItem`](../type-aliases/OpenAIResponsesInputItem.md)\[] | The flat array of input items — messages, tool calls/results, and reasoning items. | [src/batteries/llm/openai\_responses/types.ts:645](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L645) | | `instructions?` | `string` | ALWAYS ADK-rendered; never a consumer-settable option. | [src/batteries/llm/openai\_responses/types.ts:649](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L649) | | `max_output_tokens?` | `number` | Hard limit on the number of generated output tokens. | [src/batteries/llm/openai\_responses/types.ts:664](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L664) | | `metadata?` | [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `string`> | Metadata key-value pairs forwarded to the provider. | [src/batteries/llm/openai\_responses/types.ts:684](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L684) | | `model` | `string` | ID of the model to use for generation. | [src/batteries/llm/openai\_responses/types.ts:643](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L643) | | `parallel_tool_calls?` | `boolean` | Allow the model to emit multiple tool calls in one turn. | [src/batteries/llm/openai\_responses/types.ts:666](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L666) | | `prompt_cache_key?` | `string` | Vendor cache key for caching prefix content. | [src/batteries/llm/openai\_responses/types.ts:678](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L678) | | `prompt_cache_retention?` | `"in_memory"` | `"24h"` | Cache retention strategy for cached prefix content. | [src/batteries/llm/openai\_responses/types.ts:680](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L680) | | `reasoning?` | { `effort?`: `"none"` | `"minimal"` | `"low"` | `"medium"` | `"high"` | `"xhigh"`; `summary?`: `"auto"` | `"concise"` | `"detailed"`; } | Reasoning-effort / summary configuration for reasoning-capable models. | [src/batteries/llm/openai\_responses/types.ts:659](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L659) | | `reasoning.effort?` | `"none"` | `"minimal"` | `"low"` | `"medium"` | `"high"` | `"xhigh"` | - | [src/batteries/llm/openai\_responses/types.ts:660](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L660) | | `reasoning.summary?` | `"auto"` | `"concise"` | `"detailed"` | - | [src/batteries/llm/openai\_responses/types.ts:661](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L661) | | `safety_identifier?` | `string` | Unique safety system identifier or configuration id. | [src/batteries/llm/openai\_responses/types.ts:682](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L682) | | `service_tier?` | `"default"` | `"auto"` | `"flex"` | `"scale"` | `"priority"` | Service reliability tier for processing the request. | [src/batteries/llm/openai\_responses/types.ts:676](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L676) | | `store` | `false` | ALWAYS `false` — this adapter is stateless; see the battery's design notes. | [src/batteries/llm/openai\_responses/types.ts:651](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L651) | | `stream` | `boolean` | If set, partial output deltas are sent as server-sent events. | [src/batteries/llm/openai\_responses/types.ts:647](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L647) | | `stream_options?` | { `include_obfuscation?`: `boolean`; } | Configuration options for response streaming. | [src/batteries/llm/openai\_responses/types.ts:690](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L690) | | `stream_options.include_obfuscation?` | `boolean` | - | [src/batteries/llm/openai\_responses/types.ts:690](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L690) | | `temperature?` | `number` | Sampling temperature control. | [src/batteries/llm/openai\_responses/types.ts:668](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L668) | | `text?` | { `format?`: [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `unknown`>; `verbosity?`: `"low"` | `"medium"` | `"high"`; } | Structured-output format / verbosity configuration. | [src/batteries/llm/openai\_responses/types.ts:686](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L686) | | `text.format?` | [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `unknown`> | - | [src/batteries/llm/openai\_responses/types.ts:686](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L686) | | `text.verbosity?` | `"low"` | `"medium"` | `"high"` | - | [src/batteries/llm/openai\_responses/types.ts:686](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L686) | | `tool_choice?` | [`OpenAIResponsesToolChoice`](../type-aliases/OpenAIResponsesToolChoice.md) | Tool-choice directive constraining which (if any) tool the model may call. | [src/batteries/llm/openai\_responses/types.ts:657](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L657) | | `tools?` | [`OpenAIResponsesTool`](../type-aliases/OpenAIResponsesTool.md)\[] | Function-tool definitions the model may call. | [src/batteries/llm/openai\_responses/types.ts:655](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L655) | | `top_logprobs?` | `number` | Top log-probability tokens limit. | [src/batteries/llm/openai\_responses/types.ts:672](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L672) | | `top_p?` | `number` | Nucleus sampling probability threshold. | [src/batteries/llm/openai\_responses/types.ts:670](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L670) | | `truncation?` | `"auto"` | `"disabled"` | Context-truncation strategy. | [src/batteries/llm/openai\_responses/types.ts:674](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L674) |