agents-test/ai.koog.agents.testing.tools/MockPromptExecutor

MockPromptExecutor

class MockPromptExecutor : PromptExecutor(source)

A mock implementation of PromptExecutor used for testing.

This class simulates an LLM by returning predefined responses based on the input prompt. It supports different types of matching:

Exact matching - Returns a response when the input exactly matches pattern
Partial matching - Returns a response when the input contains a pattern
Conditional matching - Returns a response when the input satisfies condition
Default response - Returns a default response when no other matches are found

It also supports tool calls and can be configured to return specific tool results.

Types

object Companion

Functions

open override fun close()

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

Executes a prompt with tools and returns a list of responses.

executeMultipleChoices

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

executeStreaming

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

Executes a prompt and returns a flow of string responses.

getBasicJsonSchemaGenerator

open fun getBasicJsonSchemaGenerator(model: LLModel): BasicJsonSchemaGenerator

getStandardJsonSchemaGenerator

open fun getStandardJsonSchemaGenerator(model: LLModel): StandardJsonSchemaGenerator

open suspend fun models(): List<LLModel>

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

Processes a given prompt to determine if it adheres to moderation rules and returns a moderation result.