prompt-executor-anthropic-client/ai.koog.prompt.executor.clients.anthropic.models/AnthropicMessageRequest

AnthropicMessageRequest

data class AnthropicMessageRequest(val model: String, val messages: List<AnthropicMessage>, val maxTokens: Int = MAX_TOKENS_DEFAULT, val container: String? = null, val mcpServers: List<AnthropicMCPServerURLDefinition>? = null, val serviceTier: AnthropicServiceTier? = null, val stopSequence: List<String>? = null, val stream: Boolean = false, val system: List<SystemAnthropicMessage>? = null, val temperature: Double? = null, val thinking: AnthropicThinking? = null, val toolChoice: AnthropicToolChoice? = null, val tools: List<AnthropicTool>? = null, val topK: Int? = null, val topP: Double? = null, val additionalProperties: Map<String, JsonElement>? = null)(source)

Represents a request for an Anthropic message-based interaction.

This data class is used to configure the parameters for an Anthropic message request, including the model, messages, and additional settings for generation behavior.

Constructors

AnthropicMessageRequest

constructor(model: String, messages: List<AnthropicMessage>, maxTokens: Int = MAX_TOKENS_DEFAULT, container: String? = null, mcpServers: List<AnthropicMCPServerURLDefinition>? = null, serviceTier: AnthropicServiceTier? = null, stopSequence: List<String>? = null, stream: Boolean = false, system: List<SystemAnthropicMessage>? = null, temperature: Double? = null, thinking: AnthropicThinking? = null, toolChoice: AnthropicToolChoice? = null, tools: List<AnthropicTool>? = null, topK: Int? = null, topP: Double? = null, additionalProperties: Map<String, JsonElement>? = null)

Types

object Companion

Companion object with default values for request

Properties

additionalProperties

val additionalProperties: Map<String, JsonElement>?

val container: String?

Container identifier for reuse across requests.

@SerialName(value = "max_tokens")

val maxTokens: Int

The maximum number of tokens to generate in the response. Defaults to 2048.

@SerialName(value = "mcp_servers")

val mcpServers: List<AnthropicMCPServerURLDefinition>?

MCP servers to be used in this request

val messages: List<AnthropicMessage>

A list of messages constituting the dialogue. Each message contains a role and corresponding content.

val model: String

The identifier of the Anthropic model to be used for processing the request.

@SerialName(value = "service_tier")

val serviceTier: AnthropicServiceTier?

Determines whether to use priority capacity (if available) or standard capacity for this request.

@SerialName(value = "stop_sequence")

val stopSequence: List<String>?

Custom text sequences that will cause the model to stop generating.

val stream: Boolean

Whether responses should be returned as a stream. Defaults to false.

val system: List<SystemAnthropicMessage>?

An optional list of system-level messages defining additional context or instructions.

val temperature: Double?

The sampling temperature for adjusting randomness in generation. Higher values increase randomness.

val thinking: AnthropicThinking?

Configuration for enabling Claude's extended thinking.

@SerialName(value = "tool_choice")

val toolChoice: AnthropicToolChoice?

An optional specification for tool selection during processing, which may define automatic, specific, or no tool usage.

val tools: List<AnthropicTool>?

An optional list of tools that the Anthropic model can utilize during processing.

val topK: Int?

Only sample from the top K options for each subsequent token.

val topP: Double?

Use nucleus sampling.