onLLMCallStarting

suspend fun onLLMCallStarting(eventId: String, executionInfo: AgentExecutionInfo, runId: String, prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>, context: AIAgentContext)(source)

Notifies all registered LLM handlers before a language model call is made.

Parameters

eventId

The unique identifier for the event group;

executionInfo

The execution information for the LLM call event;

runId

The unique identifier for the current run;

prompt

The prompt that will be sent to the language model;

model

The language model instance that will process the request;

tools

The list of tool descriptors available for the LLM call;

context

The AI agent context in which the LLM call is being executed.