Struct LeakDetectorConfig 

pub struct LeakDetectorConfig {
    pub alpha: f64,
    pub lambda: f64,
    pub cusum_threshold: f64,
    pub cusum_allowance: f64,
    pub warmup_frames: usize,
    pub sigma_decay: f64,
    pub sigma_floor: f64,
}

Configuration for the allocation leak detector.

Fields

alpha: f64

False positive rate bound for the e-process (default: 0.05).

lambda: f64

Betting fraction λ for the e-process likelihood ratio. Controls sensitivity vs. evidence accumulation speed. Recommended: 0.1–0.5 (default: 0.2).

cusum_threshold: f64

CUSUM threshold h. Higher = fewer false positives, slower detection. Rule of thumb: h ≈ 8 with k=0.5 gives two-sided ARL₀ ≈ 2000 (default: 8.0).

cusum_allowance: f64

CUSUM reference value k (allowance). Typically δ/2 where δ is the minimum shift to detect. (default: 0.5).

warmup_frames: usize

Number of warmup frames to estimate baseline mean and σ (default: 30).

sigma_decay: f64

EMA decay for running σ estimate (default: 0.95).

sigma_floor: f64

Minimum σ floor to prevent division by zero (default: 1.0).

Trait Implementations

impl Clone for LeakDetectorConfig

fn clone(&self) -> LeakDetectorConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LeakDetectorConfig

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

Formats the value using the given formatter.

impl Default for LeakDetectorConfig

fn default() -> Self

Returns the “default value” for a type.