Struct AgentOutput 

pub struct AgentOutput {
    pub name: String,
    pub answer: String,
    pub turns: u32,
    pub tool_calls: u32,
    pub duration_ms: f64,
    pub error: Option<String>,
    pub outcome: Option<AgentOutcome>,
    pub tokens: Option<TokenAccounting>,
    pub tools_used: Vec<String>,
}

Output from one agent’s execution.

Fields

name: String

answer: String

turns: u32

tool_calls: u32

duration_ms: f64

error: Option<String>

outcome: Option<AgentOutcome>

Structured outcome (when available). Products can use this instead of checking answer/error fields for completion semantics.

tokens: Option<TokenAccounting>

tools_used: Vec<String>

Names of the tools the agent invoked, in first-use order. Empty when the runner doesn’t track tools (most aggregate/combinator outputs). Lets downstream consumers (e.g. benchmark failure mining) reason about which tools a run actually used.

Implementations

impl AgentOutput

pub fn succeeded(&self) -> bool

Trait Implementations

impl Clone for AgentOutput

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AgentOutput

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for AgentOutput

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for AgentOutput

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.