vigiles API reference
    Preparing search index...

    Interface SelectionOptions

    Knobs for the selection-collision measurement.

    interface SelectionOptions {
        adapter?: HarnessAdapter;
        concurrency?: number;
        dialect?: HarnessDialect;
        effort?: string | number;
        harness?: string;
        layout?: PluginLayout;
        model?: string;
        trials?: number;
    }

    Hierarchy (View Summary)

    Index

    Properties

    adapter?: HarnessAdapter

    Which harness drives it — the adapter itself (default defaultAdapter). A harness whose firing signal is INFERRED rather than a discrete event reports n/a: the matrix asks WHICH skill fired, which an inference cannot answer.

    concurrency?: number

    Parallel runs across the prompts × trials grid (default 1).

    dialect?: HarnessDialect
    effort?: string | number

    Reasoning budget (claude --effort) for the selector, or undefined for the harness default. Present for measureSelectionMatrix, the ASSERTABLE test primitive, where the configuration a number came from has to be pinnable.

    Deliberately NOT exposed as an audit CLI flag: audit is a local report, not a reproducibility surface, and a flag nobody can act on is surface without a use. The audit probe therefore leaves this unset and runs at the default.

    harness?: string

    Pass SelectionOptions.adapter instead. Kept for one release because this options type is public API (vigiles/claude-code); a name is resolved through the registry, never compared to a literal.

    layout?: PluginLayout

    Layout + dialect for candidate discovery, mirroring ProbeOptions — so a Codex repo's skills are found under the Codex layout, not silently missed by the Claude Code one.

    model?: string

    Selector model — defaults to Sonnet (a weaker model under-selects).

    trials?: number

    Repeats per prompt (default 1).