“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
20 lines
676 B
TypeScript
20 lines
676 B
TypeScript
import { Scenario } from '../types';
|
|
|
|
export const scenario: Scenario = {
|
|
id: 'hub-traversal',
|
|
name: 'Hub traversal',
|
|
description: 'Traverse from core hubs and connected nodes to synthesize what the user should focus on next.',
|
|
tools: ['queryEdge'],
|
|
suites: ['traversal', 'internal'],
|
|
input: {
|
|
message: 'Traverse from my hub nodes "Building RA-H — Personal Knowledge Graph" and "Nature of Intelligence & Consciousness" and tell me what I should focus on next and why.',
|
|
},
|
|
expect: {
|
|
toolsCalledSoft: ['queryEdge'],
|
|
responseContainsSoft: ['focus', 'why'],
|
|
maxLatencyMs: 45000,
|
|
maxTotalTokens: 16000,
|
|
maxEstimatedCostUsd: 0.18,
|
|
},
|
|
};
|