Struct AgentGateResult 

pub struct AgentGateResult {
    pub baseline: AgentBenchSummary,
    pub atlas: AgentBenchSummary,
    pub search_reduced: bool,
    pub files_bounded: bool,
    pub first_correct_bounded: bool,
    pub passed: bool,
}

A-vs-E agent-behavior gate result: does the atlas variant (E) reduce exploration vs the baseline (A)?

Fields

baseline: AgentBenchSummary

atlas: AgentBenchSummary

search_reduced: bool

E.mean_search_tool_calls < A.mean_search_tool_calls.

files_bounded: bool

E.mean_files_opened <= A.mean_files_opened + 1.

first_correct_bounded: bool

E.mean_first_correct_ms <= A.mean_first_correct_ms. Fails closed: when either side has no first-correct mean (no JSON event stream) the clause cannot be verified and is false.

passed: bool

Trait Implementations

impl Clone for AgentGateResult

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 AgentGateResult

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

Formats the value using the given formatter.

impl Serialize for AgentGateResult

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

where __S: Serializer,

Serialize this value into the given Serde serializer.