Struct AgentOutput 

#[non_exhaustive]
pub struct AgentOutput {
    pub result: String,
    pub tool_calls_made: usize,
    pub tokens_used: TokenUsage,
    pub structured: Option<Value>,
    pub estimated_cost_usd: Option<f64>,
    pub model_name: Option<String>,
    pub tool_call_results: Vec<ToolCallRecord>,
    pub goal_met: Option<bool>,
}

Output of a completed agent run.

Returned by AgentRunner::execute on success. Contains the agent’s final text response and usage accounting for the entire run.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

result: String

The agent’s final text response.

tool_calls_made: usize

Total number of tool calls made during the run.

tokens_used: TokenUsage

Aggregate token usage for the entire run.

structured: Option<Value>

Structured output when the agent was configured with a response schema. Contains the validated JSON conforming to the schema.

estimated_cost_usd: Option<f64>

Estimated cost in USD based on model pricing. None if the model is unknown or cost estimation is not available.

model_name: Option<String>

The model name used for this run. For cascading providers, this is the last model that produced a response.

tool_call_results: Vec<ToolCallRecord>

Per-tool-call records with full input + untruncated output. Empty when no tools were called or for composite agents that don’t track per-tool detail. Order matches dispatch order (which may differ from completion order due to parallel execution). Counts only tools that were actually executed — denied/blocked calls do not appear here.

goal_met: Option<bool>

Whether the run’s GoalCondition was met, as decided by the independent goal judge. None when no goal was set; Some(true) when the judge confirmed the objective; Some(false) when the continuation cap was exhausted without the objective being met.

Trait Implementations

impl Clone for AgentOutput

fn clone(&self) -> AgentOutput

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 Default for AgentOutput

fn default() -> AgentOutput

Returns the “default value” for a type.

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.