prompt-executor-clients/ai.koog.prompt.executor.clients.retry/RetryingLLMClient

RetryingLLMClient

class RetryingLLMClient @JvmOverloads constructor(delegate: LLMClient, config: RetryConfig = RetryConfig()) : LLMClient(source)

A decorator that adds retry capabilities to any LLMClient implementation.

This is a pure decorator - it has no knowledge of specific providers or implementations. It simply wraps any LLMClient and retries operations based on configurable policies.

Example usage:

val client = AnthropicLLMClient(apiKey)
val retryingClient = RetryingLLMClient(client, RetryConfig.CONSERVATIVE)

Parameters

delegate

The LLMClient to wrap with retry logic

config

Configuration for retry behavior

Constructors

RetryingLLMClient

@JvmOverloads

constructor(delegate: LLMClient, config: RetryConfig = RetryConfig())

Properties

clientName

open val clientName: String

The name of the client.

Functions

open override fun close()

execute

open suspend override fun execute(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): List<Message.Response>

Executes a prompt and returns a list of response messages.

executeMultipleChoices

open suspend override fun executeMultipleChoices(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): List<LLMChoice>

Executes a prompt and returns a list of LLM choices.

executeStreaming

open fun executeStreaming(prompt: Prompt, model: LLModel): Flow<StreamFrame>

open override fun executeStreaming(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): Flow<StreamFrame>

Executes a prompt and returns a streaming flow of response chunks.

getBasicJsonSchemaGenerator

open fun getBasicJsonSchemaGenerator(): BasicJsonSchemaGenerator

Basic JSON schema generator supported by the LLMClient. Return BasicJsonSchemaGenerator by default.

getStandardJsonSchemaGenerator

open fun getStandardJsonSchemaGenerator(): StandardJsonSchemaGenerator

Standard JSON schema generator supported by the LLMClient. Return StandardJsonSchemaGenerator by default.

llmProvider

open override fun llmProvider(): LLMProvider

Retrieves the configured instance of the LLMProvider in use.

models

open suspend override fun models(): List<LLModel>

Retrieves a list of ids of available Large Language Models (LLMs) supported by the client.

moderate

open suspend override fun moderate(prompt: Prompt, model: LLModel): ModerationResult

Analyzes the provided prompt for violations of content policies or other moderation criteria.

toRetryingClient

fun LLMClient.toRetryingClient(retryConfig: RetryConfig = RetryConfig.DEFAULT): RetryingLLMClient

Converts an instance of LLMClient into a retrying client with customizable retry behavior.