Enum AgentOutcome 

#[non_exhaustive]
pub enum AgentOutcome {
    Completed {
        text: String,
        steps_used: u32,
        usage: TokenUsage,
    },
    BudgetExhausted {
        reason: BudgetKind,
        steps_used: u32,
        usage: TokenUsage,
    },
    LoopDetected {
        tool: String,
        repeats: u32,
        steps_used: u32,
        usage: TokenUsage,
    },
    AwaitingApproval {
        state: Box<RunState>,
    },
}

The result of one agent run.

Marked #[non_exhaustive]: match with a wildcard arm so new stop reasons do not break your build.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

Completed

The model produced a final answer.

Fields

text: String

The model’s final text.

steps_used: u32

Tool-execution rounds used.

usage: TokenUsage

Provider-reported token totals.

BudgetExhausted

A budget ran out before the model finished.

Fields

reason: BudgetKind

Which budget ran out.

steps_used: u32

Tool-execution rounds used.

usage: TokenUsage

Provider-reported token totals.

LoopDetected

The model repeated the same tool call with the same result too often.

Fields

tool: String

The repeated tool.

repeats: u32

How often the call repeated inside the guard window.

steps_used: u32

Tool-execution rounds used.

usage: TokenUsage

Provider-reported token totals.

AwaitingApproval

The policy wants a person to approve one or more calls.

Fields

state: Box<RunState>

The paused run. Pass it to Agent::resume.

Implementations

impl AgentOutcome

pub fn steps_used(&self) -> u32

Tool-execution rounds consumed, whatever the outcome.

pub fn usage(&self) -> TokenUsage

Provider-reported token totals, whatever the outcome.

pub const fn is_completed(&self) -> bool

true when the model produced a final answer.

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

The final answer, when the model produced one.

Trait Implementations

impl Clone for AgentOutcome

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 AgentOutcome

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for AgentOutcome

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for AgentOutcome

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for AgentOutcome

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for AgentOutcome