prompt-executor-model/ai.koog.prompt.executor.llms/RoutingLLMPromptExecutor/execute

execute

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

Executes a given prompt using the specified tools and model, and returns the assistant response.

This legacy extension point is kept open for existing subclasses. New subclasses should prefer overriding the ResolvedModel-based overload. If this method is overridden without calling super, resolveModel is bypassed.

open suspend override fun execute(prompt: Prompt, model: ResolvedModel, tools: List<ToolDescriptor> = emptyList()): Message.Assistant(source)

Executes a given prompt using the specified tools and resolved model, and returns the assistant response. Preferred extension point for subclasses that want to preserve this executor's model-resolution flow.

Return

A Message.Assistant containing the response generated based on the prompt.

Parameters

prompt

The Prompt to be executed, containing the input messages and parameters.

resolvedModel

The resolved LLM model to use for execution.

tools

A list of ToolDescriptor objects representing external tools available for use during execution.