Interface JudgeNodeConfig

Judge configuration for orchestration human-node delegation — the shared shape for the IR node type, the public builder, and the NodeExecutor runtime (previously three drifting inline copies).

interface JudgeNodeConfig {
    model?: string;
    provider?: string;
    effort?: "low" | "high" | "medium" | "xhigh" | "max";
    criteria?: string;
    confidenceThreshold?: number;
}

Hierarchy

  • JudgeLlmConfig
    • JudgeNodeConfig

Properties

model? provider? effort? criteria? confidenceThreshold?

Properties

Optional model

model?: string

Judge model id. Default: the central resolver (gpt-5.6).

Optional provider

provider?: string

Provider id. Pinning a non-openai provider REQUIRES an explicit model.

Optional effort

effort?: "low" | "high" | "medium" | "xhigh" | "max"

Reasoning effort. When omitted, the resolver's default effort is applied ONLY when the resolver's model was also selected — a caller-pinned model gets no injected effort (zero request-shape change for pinned callers).

Optional criteria

criteria?: string

Custom evaluation criteria/rubric.

Optional confidenceThreshold

confidenceThreshold?: number

Confidence threshold (0–1). Below this, fall through to the human interrupt. Defaults to 0.7.

Settings

Member Visibility

Theme

On This Page

modelprovidereffortcriteriaconfidenceThreshold