prompt-executor-openai-client/ai.koog.prompt.executor.clients.openai/OpenAIResponsesParams

OpenAIResponsesParams

@ApiStatus.Experimental

class OpenAIResponsesParams(temperature: Double? = null, maxTokens: Int? = null, numberOfChoices: Int? = null, speculation: String? = null, schema: LLMParams.Schema? = null, toolChoice: LLMParams.ToolChoice? = null, user: String? = null, includeThoughts: Boolean? = null, thinkingBudget: Int? = null, additionalProperties: Map<String, JsonElement>? = null, val background: Boolean? = null, val include: List<String>? = null, val maxToolCalls: Int? = null, val parallelToolCalls: Boolean? = null, val reasoning: ReasoningConfig? = null, val truncation: Truncation? = null, val promptCacheKey: String? = null, val safetyIdentifier: String? = null, val serviceTier: ServiceTier? = null, val store: Boolean? = null, val logprobs: Boolean? = null, val topLogprobs: Int? = null, val topP: Double? = null) : LLMParams, OpenAIParams(source)

OpenAI Responses API parameters layered on top of LLMParams.

Use these options to generate text or JSON, call built-in tools (e.g., web/file search) or your own functions, enable background processing, include auxiliary outputs, and tune sampling, reasoning, and truncation behavior. All parameters are optional; when unset, provider/model defaults apply.

Constructors

OpenAIResponsesParams

constructor(temperature: Double? = null, maxTokens: Int? = null, numberOfChoices: Int? = null, speculation: String? = null, schema: LLMParams.Schema? = null, toolChoice: LLMParams.ToolChoice? = null, user: String? = null, includeThoughts: Boolean? = null, thinkingBudget: Int? = null, additionalProperties: Map<String, JsonElement>? = null, background: Boolean? = null, include: List<String>? = null, maxToolCalls: Int? = null, parallelToolCalls: Boolean? = null, reasoning: ReasoningConfig? = null, truncation: Truncation? = null, promptCacheKey: String? = null, safetyIdentifier: String? = null, serviceTier: ServiceTier? = null, store: Boolean? = null, logprobs: Boolean? = null, topLogprobs: Int? = null, topP: Double? = null)

Properties

additionalProperties

val additionalProperties: Map<String, JsonElement>?

background

val background: Boolean? = null

Run the response in the background (non-blocking).

include

val include: List<String>? = null

Additional output sections to include (see the list above).

includeThoughts

val includeThoughts: Boolean?

logprobs

val logprobs: Boolean? = null

Whether to include log-probabilities for output tokens.

maxTokens

val maxTokens: Int?

maxToolCalls

val maxToolCalls: Int? = null

Maximum total number of built-in tool calls allowed in this response (≥ 0).

numberOfChoices

val numberOfChoices: Int?

parallelToolCalls

val parallelToolCalls: Boolean? = null

Whether tool calls may run in parallel.

promptCacheKey

val promptCacheKey: String? = null

Stable cache key for prompt caching (non-blank when provided).

reasoning

val reasoning: ReasoningConfig? = null

Reasoning configuration for reasoning-capable models.

safetyIdentifier

val safetyIdentifier: String? = null

Stable app-scoped user ID for policy enforcement (non-blank when provided).

schema

val schema: LLMParams.Schema?

serviceTier

val serviceTier: ServiceTier? = null

Processing tier selection for cost/latency trade-offs.

speculation

val speculation: String?

store

val store: Boolean? = null

Whether the provider may store outputs for later retrieval/evals.

temperature

val temperature: Double?

thinkingBudget

val thinkingBudget: Int?

toolChoice

val toolChoice: LLMParams.ToolChoice?

topLogprobs

val topLogprobs: Int? = null

Number of top alternatives per position (0–20). Requires logprobs = true.

topP

val topP: Double? = null

Nucleus sampling in (0.0, 1.0]; use instead of temperature.

truncation

val truncation: Truncation? = null

Truncation strategy when nearing the context window.

user

val user: String?

Functions

component1

operator fun component1(): Double?

component10

operator fun component10(): Map<String, JsonElement>?

component2

operator fun component2(): Int?

component3

operator fun component3(): Int?

component4

operator fun component4(): String?

component5

operator fun component5(): LLMParams.Schema?

component6

operator fun component6(): LLMParams.ToolChoice?

component7

operator fun component7(): String?

component8

operator fun component8(): Boolean?

component9

operator fun component9(): Int?

copy

fun copy(temperature: Double? = this.temperature, maxTokens: Int? = this.maxTokens, numberOfChoices: Int? = this.numberOfChoices, speculation: String? = this.speculation, schema: LLMParams.Schema? = this.schema, toolChoice: LLMParams.ToolChoice? = this.toolChoice, user: String? = this.user, includeThoughts: Boolean? = this.includeThoughts, thinkingBudget: Int? = this.thinkingBudget, additionalProperties: Map<String, JsonElement>? = this.additionalProperties, background: Boolean? = this.background, include: List<String>? = this.include, maxToolCalls: Int? = this.maxToolCalls, parallelToolCalls: Boolean? = this.parallelToolCalls, reasoning: ReasoningConfig? = this.reasoning, truncation: Truncation? = this.truncation, promptCacheKey: String? = this.promptCacheKey, safetyIdentifier: String? = this.safetyIdentifier, serviceTier: ServiceTier? = this.serviceTier, store: Boolean? = this.store, logprobs: Boolean? = this.logprobs, topLogprobs: Int? = this.topLogprobs, topP: Double? = this.topP): OpenAIResponsesParams

Creates a copy of this instance with the ability to modify any of its properties.

open fun copy(temperature: Double?, maxTokens: Int?, numberOfChoices: Int?, speculation: String?, schema: LLMParams.Schema?, toolChoice: LLMParams.ToolChoice?, user: String?, includeThoughts: Boolean?, thinkingBudget: Int?, additionalProperties: Map<String, JsonElement>?): LLMParams

default

fun default(default: LLMParams): LLMParams

equals

open operator override fun equals(other: Any?): Boolean

hashCode

open override fun hashCode(): Int

toString

open override fun toString(): String