Struct Agent 

pub struct Agent { /* private fields */ }

Available on crate feature agent only.

Struct representing an LLM agent. An agent is an LLM model combined with a preamble (i.e.: system prompt) and a static set of context documents and tools. All context documents and tools are always provided to the agent when prompted.

Default hooks attached with AgentBuilder::add_hook are used for every prompt request, plus any added on the request or runner.

Example

use rig_agent::prelude::*;
use rig_core::{client::ProviderClient, providers::openai};

let openai = openai::Client::from_env()?;

let comedian_agent = openai
    .agent(openai::GPT_5_2)
    .preamble("You are a comedian here to entertain the user using humour and jokes.")
    .temperature(0.9)
    .build();

let response = comedian_agent.prompt("Entertain me!").await?;

Implementations

impl Agent

pub fn name(&self) -> Option<&str>

Returns the configured agent name.

pub fn description(&self) -> Option<&str>

Returns the configured agent description.

pub fn runner(&self, prompt: impl Into<Message>) -> AgentRunner

Build a hook-aware AgentRunner for this agent, seeded with the agent’s default hook stack. Attach more hooks with AgentRunner::add_hook, then call AgentRunner::run.

pub fn model_handle(&self) -> &ModelHandle

Returns the agent’s current default model handle.

pub fn set_model_handle(&mut self, model: ModelHandle)

Replace the default model used by runners created after this call.

Existing runners retain their model snapshot, and replacing one cloned agent does not mutate another clone. Model-selection hooks may replace the captured default at each model-call boundary.

pub fn set_model<M>(&mut self, model: M)

where M: CompletionModel + 'static,

Erase and install a typed completion model as this agent’s new default.

pub fn with_model_handle(self, model: ModelHandle) -> Agent

Return this agent with a replacement default model handle.

Model-selection hooks may replace this default for individual calls.

pub fn with_model<M>(self, model: M) -> Agent

where M: CompletionModel + 'static,

Return this agent with an erased typed model as its new default.

pub async fn tool_definitions( &self, prompt: Option<String>, ) -> Result<Vec<ToolDefinition>, ToolServerError>

Resolve the provider-facing tool definitions available for a prompt.

This read-only view does not expose tool dispatch. Agent execution and tool lifecycle hooks remain owned by Self::runner.

impl Agent

pub fn into_tool(self) -> DynamicTool

Convert this agent into a runtime-defined tool.

The configured agent name becomes the tool name. Unnamed agents use agent_tool. This explicit conversion keeps runtime identity out of the statically named Tool trait.

Trait Implementations

impl Chat for Agent

async fn chat( &self, prompt: impl Into<Message> + WasmCompatSend, chat_history: &mut Vec<Message>, ) -> Result<String, PromptError>

Execute one turn and append only committed messages to chat_history.

impl Clone for Agent

fn clone(&self) -> Agent

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl DiscordExt for Agent

async fn into_discord_bot(self, token: &str) -> Result<Client, DiscordBotError>

fn into_discord_bot_from_env( self, ) -> impl Future<Output = Result<Client, DiscordBotError>> + Send

impl From<Agent> for DynamicTool

fn from(agent: Agent) -> DynamicTool

Converts to this type from the input type.

impl Prompt for Agent

fn prompt( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> PromptRequest<Standard>

Send a prompt and return accepted assistant text after runtime orchestration.

impl Prompt for &Agent

fn prompt( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> PromptRequest<Standard>

Send a prompt and return accepted assistant text after runtime orchestration.

impl StreamingChat for Agent

fn stream_chat<I, T>( &self, prompt: impl Into<Message> + WasmCompatSend, chat_history: I, ) -> StreamingPromptRequest

where I: IntoIterator<Item = T>, T: Into<Message>,

Create a classic streaming request with canonical chat history.

impl StreamingPrompt for Agent

fn stream_prompt( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> StreamingPromptRequest

Create a classic streaming request for prompt.

impl TypedPrompt for Agent

fn prompt_typed<T>( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> TypedPromptRequest<T, Standard>

where T: JsonSchema + DeserializeOwned + WasmCompatSend,

Send a prompt and receive a typed structured response.

The JSON schema for T is automatically generated and sent to the provider. Providers that support native structured outputs will constrain the model’s response to match this schema.

Example

use rig_core::prelude::*;
use schemars::JsonSchema;
use serde::Deserialize;

#[derive(Debug, Deserialize, JsonSchema)]
struct WeatherForecast {
    city: String,
    temperature_f: f64,
    conditions: String,
}

let agent = client.agent("gpt-4o").build();

// Type inferred from variable
let forecast: WeatherForecast = agent
    .prompt_typed("What's the weather in NYC?")
    .await?;

// Or explicit turbofish syntax
let forecast = agent
    .prompt_typed::<WeatherForecast>("What's the weather in NYC?")
    .max_turns(3)
    .await?;

type TypedRequest<T: JsonSchema + DeserializeOwned + WasmCompatSend + 'static> = TypedPromptRequest<T, Standard>

Request type returned for one target output type.

impl TypedPrompt for &Agent

type TypedRequest<T: JsonSchema + DeserializeOwned + WasmCompatSend + 'static> = TypedPromptRequest<T, Standard>

Request type returned for one target output type.

fn prompt_typed<T>( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> TypedPromptRequest<T, Standard>

where T: JsonSchema + DeserializeOwned + WasmCompatSend,

Send a prompt and deserialize the accepted structured response as T.