vigiles API reference
    Preparing search index...

    Interface TriggerRateReport

    interface TriggerRateReport {
        competitors: number;
        errored?: number;
        falsePositiveRate?: number;
        n: number;
        perIrrelevant?: readonly PromptTriggerStat[];
        perPrompt: readonly PromptTriggerStat[];
        precision?: number;
        rate: number;
    }
    Index

    Properties

    competitors: number

    Competitor skills co-installed via TriggerRateSpec.installSet. 0 (the default) means the skill was measured ISOLATED — so rate is an UPPER bound on real recall and falsePositiveRate a LOWER bound, because selection is competitive (a populated harness can evict or out-compete the description). A non-zero count is the whole-harness measurement.

    errored?: number

    Runs EXCLUDED because the turn errored / was rate-limited (detected by the driver's runError), present only when > 0. These are NOT counted in n or as misses — so rate reflects only valid runs. A large errored relative to n means the measurement is thin (e.g. a Codex usage limit was hit); re-run.

    falsePositiveRate?: number

    Fraction of irrelevant runs that wrongly fired (lower is better). Present only when TriggerRateSpec.irrelevantPrompts was given.

    n: number

    Total relevant runs (prompts × trials).

    perIrrelevant?: readonly PromptTriggerStat[]

    Per-prompt stats for the irrelevant set. Present with irrelevant prompts.

    perPrompt: readonly PromptTriggerStat[]
    precision?: number

    relevantFired / (relevantFired + irrelevantFired) — of all firings, the share on the right prompts. Present only when irrelevant prompts were given AND something fired (undefined when nothing fired at all). Pairs with rate (recall) to catch a skill that fires on everything or nothing.

    rate: number

    Overall fraction of relevant runs in which the behaviour fired (recall, 0..1).