“BeeRad”
4c75df101f
- port retrieval, validation, and eval improvements relevant to os - align prompts and dimensions with the flat single-agent model - replace the old eval suite with the focused core scenarios Generated with Codex
39 lines
863 B
TypeScript
39 lines
863 B
TypeScript
export type ScenarioExpectations = {
|
|
skillsRead?: string[];
|
|
skillsReadSoft?: string[];
|
|
skillsNotRead?: string[];
|
|
skillsNotReadSoft?: string[];
|
|
toolsCalled?: string[];
|
|
toolsCalledSoft?: string[];
|
|
toolsNotCalled?: string[];
|
|
toolsNotCalledSoft?: string[];
|
|
responseContains?: string[];
|
|
responseContainsSoft?: string[];
|
|
responseNotContains?: string[];
|
|
maxLatencyMs?: number;
|
|
maxTotalTokens?: number;
|
|
maxEstimatedCostUsd?: number;
|
|
};
|
|
|
|
export type ScenarioInput = {
|
|
message: string;
|
|
focusedNodeId?: number;
|
|
focusedNodeQuery?: {
|
|
titleContains?: string;
|
|
titleEquals?: string;
|
|
};
|
|
mode?: 'easy' | 'hard';
|
|
};
|
|
|
|
export type Scenario = {
|
|
id: string;
|
|
name: string;
|
|
input: ScenarioInput;
|
|
expect?: ScenarioExpectations;
|
|
description?: string;
|
|
tools?: string[];
|
|
suites?: string[];
|
|
enabled?: boolean;
|
|
notes?: string;
|
|
};
|