Struct AgentResponse 

pub struct AgentResponse {
    pub text: String,
    pub tool_calls: Vec<ToolCallInfo>,
    pub token_usage: Option<TokenUsageStats>,
    pub duration: Duration,
    pub model_calls: usize,
}

Response from Agent.run() containing the result and execution statistics

Fields

text: String

The final text response from the agent

tool_calls: Vec<ToolCallInfo>

All tool calls made during this run

token_usage: Option<TokenUsageStats>

Total token usage across all model calls (if available)

duration: Duration

Total execution time

model_calls: usize

Number of model calls made (includes retries after tool use)

Implementations

impl AgentResponse

pub fn text(&self) -> &str

Get just the text response

Trait Implementations

impl Clone for AgentResponse

fn clone(&self) -> AgentResponse

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AgentResponse

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Display for AgentResponse

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl From<AgentResponse> for String

fn from(response: AgentResponse) -> Self

Converts to this type from the input type.

impl PartialEq<&str> for AgentResponse

fn eq(&self, other: &&str) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.