org.llm4s.agent.events

The events an agent run sends, each an org.llm4s.agent.graph.EventType to match a StreamEvent with:

agent.stream(threadId, "Explain monads") {
 case AgentEvents.TextDelta(d)          => print(d.text)
 case AgentEvents.ToolExecuted(t)       => println(s"${t.tool}: ${t.outcome} in ${t.duration}")
 case _                                 => ()
}

Durable (stored, replayed, no content): ModelCallCompleted, ToolExecuted, HandedOff, GuardrailBlocked. Live (current subscribers only): ModelCallStarted, TextDelta, ThinkingDelta, ToolCallStarted, ToolCallResult.

A model call's token usage, as plain numbers.

A guardrail blocked the turn; the reason is on AgentStatus.Blocked, never in the log.

Where a guardrail blocked the turn.

The active agent changed from from to to.

agent's model call returned. attempts counts the calls its model wrappers made to the model, the last one succeeding; it is 0 when a model middleware answered without calling the model. usage and estimatedCost (USD) are the completion's, when the provider reported them.

agent's model is being called; a higher attempt in the same task discards the earlier attempt's text.

A chunk of the model's answer, for attempt.

A chunk of the model's thinking, for attempt.

The result the loop recorded for a call, as the model will see it.

A tool call passed its argument checks and is about to run through the middleware chain.

One tool call's outcome; duration is the middleware chain's, zero for a call refused before it. tool is the called tool's name when the agent has that tool, else "<unknown>" (ToolLoop.UnknownTool): a name the model invented is not stored.

How a tool call ended for the loop.