Agent Thinking

Voice Agent

The AgentThinking message is used to inform the client the agent is processing information.

The AgentThinking message informs the client when the agent is processing internally, without verbalizing its thoughts. This allows the system to handle non-verbalized reasoning and, in some cases, determine which functions to call, ensuring smoother and more dynamic interactions.

The server will send an AgentThinking message to inform the client of a non-verbalized agent thought. When functions are available, some LLMs use these thoughts to decide which functions to call.

JSON

{
  "type": "AgentThinking",
  "content": "" // The text of the agent's thought
}