--- url: >- https://adk.nht.io/api/@nhtio/adk/batteries/llm/openai_responses/types/interfaces/OpenAIResponsesAdapterOptions.md description: Configuration options for the OpenAI Responses adapter. --- # Interface: OpenAIResponsesAdapterOptions Defined in: [src/batteries/llm/openai\_responses/types.ts:825](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L825) Configuration options for the OpenAI Responses adapter. ## Properties | Property | Type | Default value | Description | Defined in | | ---------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | | `apiKey?` | `string` | `undefined` | API key for authenticating requests. | [src/batteries/llm/openai\_responses/types.ts:828](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L828) | | `autoAck?` | `boolean` | `undefined` | Whether the executor should call `ctx.ack()` itself when a generation completes with no tool calls. | [src/batteries/llm/openai\_responses/types.ts:866](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L866) | | `background?` | `boolean` | `undefined` | Request the generation run in the background (async). NOT SUPPORTED — this adapter has no polling/resumption logic for a `queued`/`in_progress` background response, so `true` is rejected at validation time (`E_INVALID_OPENAI_RESPONSES_OPTIONS`) rather than silently treated as a completed, empty answer. `false`/`undefined` (the default, synchronous request/response) are unaffected. | [src/batteries/llm/openai\_responses/types.ts:973](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L973) | | `baseURL?` | `string` | `undefined` | Base URL for the OpenAI-compatible Responses endpoint. | [src/batteries/llm/openai\_responses/types.ts:830](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L830) | | `bucketOrder?` | [`ChatCompletionsBucketOrder`](../../../../type-aliases/ChatCompletionsBucketOrder.md) | `undefined` | Determines order of memory and retrievable buckets in history assembly. | [src/batteries/llm/openai\_responses/types.ts:848](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L848) | | `contextWindow?` | `number` | `undefined` | Size of the model's token context window. | [src/batteries/llm/openai\_responses/types.ts:850](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L850) | | `fetch?` | { (`input`: `URL` | `RequestInfo`, `init?`: `RequestInit`): `Promise`<`Response`>; (`input`: `string` | `URL` | `Request`, `init?`: `RequestInit`): `Promise`<`Response`>; } | `undefined` | Custom fetch implementation to use for HTTP requests. | [src/batteries/llm/openai\_responses/types.ts:846](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L846) | | `forgeToolsFilter?` | (`forged`: [`ToolRegistry`](../../../../../forge/classes/ToolRegistry.md), `ctx`: [`DispatchContext`](../../../../../types/interfaces/DispatchContext.md)) => [`ToolRegistry`](../../../../../forge/classes/ToolRegistry.md) | `undefined` | Optional hook to shape forged artifact-query tools before they merge into the visible tool set. | [src/batteries/llm/openai\_responses/types.ts:878](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L878) | | `headers?` | [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `string`> | `undefined` | Extra HTTP headers to include with each request. | [src/batteries/llm/openai\_responses/types.ts:836](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L836) | | `helpers?` | [`Partial`](https://www.typescriptlang.org/docs/handbook/utility-types.html#partialtype)<[`OpenAIResponsesHelpers`](OpenAIResponsesHelpers.md)> | `undefined` | Optional overrides for OpenAI Responses helpers. | [src/batteries/llm/openai\_responses/types.ts:860](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L860) | | `include?` | [`OpenAIResponsesIncludable`](../type-aliases/OpenAIResponsesIncludable.md)\[] | `undefined` | Additional output data requested from the model. **Remarks** `'reasoning.encrypted_content'` is auto-added when `reasoningReplay === 'encrypted'`; a caller value does not need to repeat it (de-duplicated). | [src/batteries/llm/openai\_responses/types.ts:927](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L927) | | `localToolCallParser?` | | [`ToolCallParserName`](../../../transformers_js/helpers/type-aliases/ToolCallParserName.md) | [`ToolCallParserFn`](../../../transformers_js/helpers/type-aliases/ToolCallParserFn.md) | `undefined` | Optional fallback parser for tool calls the provider did not return structurally. | [src/batteries/llm/openai\_responses/types.ts:876](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L876) | | `max_output_tokens?` | `number` | `undefined` | Hard limit on generated output tokens. **Remarks** The API enforces an UNDOCUMENTED minimum of 16 (`400 Invalid 'max_output_tokens'... Expected a value >= 16`) — enforced in this battery's validation schema so a too-small value fails at config time, not dispatch time. | [src/batteries/llm/openai\_responses/types.ts:941](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L941) | | `metadata?` | [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `string`> | `undefined` | Metadata key-value pairs forwarded to the provider. | [src/batteries/llm/openai\_responses/types.ts:961](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L961) | | `model` | `string` | `undefined` | Name of the model to use for generation. REQUIRED. | [src/batteries/llm/openai\_responses/types.ts:919](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L919) | | `onPromptAssembled?` | [`PromptAssembledObserverFn`](../../../../type-aliases/PromptAssembledObserverFn.md) | `undefined` | Observe the fully-assembled request before dispatch. | [src/batteries/llm/openai\_responses/types.ts:872](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L872) | | `onRawGeneration?` | [`RawGenerationObserverFn`](../../../../type-aliases/RawGenerationObserverFn.md) | `undefined` | Observe the model's raw response for each completed generation. | [src/batteries/llm/openai\_responses/types.ts:870](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L870) | | `organization?` | `string` | `undefined` | Optional OpenAI organization id, sent as `OpenAI-Organization`. | [src/batteries/llm/openai\_responses/types.ts:832](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L832) | | `parallel_tool_calls?` | `boolean` | `undefined` | Allow the model to emit multiple tool calls in one turn. | [src/batteries/llm/openai\_responses/types.ts:943](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L943) | | `project?` | `string` | `undefined` | Optional OpenAI project id, sent as `OpenAI-Project`. | [src/batteries/llm/openai\_responses/types.ts:834](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L834) | | `prompt_cache_key?` | `string` | `undefined` | Vendor cache key for caching system/prefix content. | [src/batteries/llm/openai\_responses/types.ts:955](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L955) | | `prompt_cache_retention?` | `"in_memory"` | `"24h"` | `undefined` | Cache retention strategy for cached prefix content. | [src/batteries/llm/openai\_responses/types.ts:957](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L957) | | `reasoning?` | { `effort?`: `"none"` | `"minimal"` | `"low"` | `"medium"` | `"high"` | `"xhigh"`; `summary?`: `"auto"` | `"concise"` | `"detailed"`; } | `undefined` | Reasoning-effort / summary configuration for reasoning-capable models. | [src/batteries/llm/openai\_responses/types.ts:929](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L929) | | `reasoning.effort?` | `"none"` | `"minimal"` | `"low"` | `"medium"` | `"high"` | `"xhigh"` | `undefined` | - | [src/batteries/llm/openai\_responses/types.ts:930](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L930) | | `reasoning.summary?` | `"auto"` | `"concise"` | `"detailed"` | `undefined` | - | [src/batteries/llm/openai\_responses/types.ts:931](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L931) | | `reasoningReplay?` | [`ReasoningReplayMode`](../type-aliases/ReasoningReplayMode.md) | `'off'` | Reasoning-replay mode. **Remarks** `'off'` (default) — thoughts never replay as native `reasoning` items; they render as plain text instead. `'encrypted'` — replay signed reasoning items, auto-adding `'reasoning.encrypted_content'` to `include`. `'summary-only'` — replay reasoning items without requesting the encrypted payload. This is real, scoped, stateful machinery (persisted opaque payloads, prefix-fence fingerprinting, adjacency enforcement, item-id manipulation) — see the battery's design notes for the reasoning/output-item pairing hazard this default guards against. | [src/batteries/llm/openai\_responses/types.ts:908](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L908) | | `replayCompatibility?` | readonly `string`\[] | `undefined` | List of replay labels supported by the assistant. | [src/batteries/llm/openai\_responses/types.ts:858](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L858) | | `requestTimeoutMs?` | `number` | `undefined` | Request timeout in milliseconds for API calls. | [src/batteries/llm/openai\_responses/types.ts:842](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L842) | | `retry?` | [`ChatCompletionsRetryConfig`](../../../../interfaces/ChatCompletionsRetryConfig.md) | `undefined` | Configures request retry behavior. | [src/batteries/llm/openai\_responses/types.ts:844](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L844) | | `safety_identifier?` | `string` | `undefined` | Unique safety system identifier or configuration id. | [src/batteries/llm/openai\_responses/types.ts:959](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L959) | | `selfIdentity?` | `string` | `undefined` | Unique identity label for the assistant instance. | [src/batteries/llm/openai\_responses/types.ts:852](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L852) | | `service_tier?` | `"default"` | `"auto"` | `"flex"` | `"scale"` | `"priority"` | `undefined` | Service reliability tier for processing the request. | [src/batteries/llm/openai\_responses/types.ts:953](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L953) | | `spoolStore?` | [`SpoolStore`](../../../../../common/type-aliases/SpoolStore.md) | `undefined` | Backing store for `string` / `Uint8Array` tool returns. | [src/batteries/llm/openai\_responses/types.ts:862](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L862) | | `stream?` | `boolean` | `undefined` | Whether to stream the response via SSE. | [src/batteries/llm/openai\_responses/types.ts:838](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L838) | | `stream_options?` | { `include_obfuscation?`: `boolean`; } | `undefined` | Configuration options for response streaming. | [src/batteries/llm/openai\_responses/types.ts:975](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L975) | | `stream_options.include_obfuscation?` | `boolean` | `undefined` | - | [src/batteries/llm/openai\_responses/types.ts:975](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L975) | | `streamIdleTimeoutMs?` | `number` | `undefined` | Idle timeout in milliseconds for the stream before aborting. | [src/batteries/llm/openai\_responses/types.ts:840](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L840) | | `strict?` | `boolean` | `undefined` | Global `strict` default forwarded to every emitted tool declaration's `strict` field, when the caller hasn't already got a reason not to (kept `undefined` by default since `strict: true` requires `additionalProperties: false` and full `required` coverage that ADK's Joi-derived schemas don't guarantee). | [src/batteries/llm/openai\_responses/types.ts:915](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L915) | | `strictToolChoice?` | `boolean` | `undefined` | Whether a `tool_choice` forcing a forged ephemeral artifact-query tool throws instead of warning. | [src/batteries/llm/openai\_responses/types.ts:864](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L864) | | `systemPromptChannel?` | [`SystemPromptChannel`](../type-aliases/SystemPromptChannel.md) | `'instructions'` | Where the ADK-rendered system prompt is placed on the wire. **Remarks** `'instructions'` (default) — the top-level `instructions` string field. `'developer-item'` / `'system-item'` — a leading `developer`/`system`-role input message item instead, for gateways that only understand the item form. Either way the CONTENT is always ADK-rendered; there is no consumer-facing escape hatch to hand-author it directly (see the `instructions` note below). | [src/batteries/llm/openai\_responses/types.ts:892](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L892) | | `temperature?` | `number` | `undefined` | Sampling temperature control. | [src/batteries/llm/openai\_responses/types.ts:945](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L945) | | `text?` | { `format?`: [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `unknown`>; `verbosity?`: `"low"` | `"medium"` | `"high"`; } | `undefined` | Structured-output format / verbosity configuration. | [src/batteries/llm/openai\_responses/types.ts:965](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L965) | | `text.format?` | [`Record`](https://www.typescriptlang.org/docs/handbook/utility-types.html#recordkeys-type)<`string`, `unknown`> | `undefined` | - | [src/batteries/llm/openai\_responses/types.ts:965](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L965) | | `text.verbosity?` | `"low"` | `"medium"` | `"high"` | `undefined` | - | [src/batteries/llm/openai\_responses/types.ts:965](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L965) | | `thoughtSurfacing?` | `"all"` | `"all-self"` | `"latest-self"` | `undefined` | Determines which thoughts are surfaced back to the model. | [src/batteries/llm/openai\_responses/types.ts:854](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L854) | | `tokenEncoding?` | | [`TokenEncodingId`](../../../../../type-aliases/TokenEncodingId.md) | `null` | `undefined` | Tokenizer encoding configuration for token counting. | [src/batteries/llm/openai\_responses/types.ts:856](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L856) | | `tool_choice?` | [`OpenAIResponsesToolChoice`](../type-aliases/OpenAIResponsesToolChoice.md) | `undefined` | Tool-choice directive. | [src/batteries/llm/openai\_responses/types.ts:963](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L963) | | `toolCallIdFilter?` | [`ToolCallIdFilterFn`](../../../../type-aliases/ToolCallIdFilterFn.md) | `undefined` | Optional ingress hook for adapting provider tool-call ids; absent preserves the vendor id. | [src/batteries/llm/openai\_responses/types.ts:874](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L874) | | `top_logprobs?` | `number` | `undefined` | Top log-probability tokens limit. | [src/batteries/llm/openai\_responses/types.ts:949](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L949) | | `top_p?` | `number` | `undefined` | Nucleus sampling probability threshold. | [src/batteries/llm/openai\_responses/types.ts:947](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L947) | | `truncation?` | `"auto"` | `"disabled"` | `undefined` | Context-truncation strategy. | [src/batteries/llm/openai\_responses/types.ts:951](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L951) | | `unsupportedMediaPolicy?` | [`UnsupportedMediaPolicy`](../../../transformers_js/type-aliases/UnsupportedMediaPolicy.md) | `undefined` | Policy for a [@nhtio/adk!Media](../../../../../common/classes/Media.md) instance whose modality this wire cannot represent (audio, video). | [src/batteries/llm/openai\_responses/types.ts:868](https://github.com/NHTIO/ADK/blob/v1.20261003.0/src/src/batteries/llm/openai_responses/types.ts#L868) |