“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
16 lines
521 B
TypeScript
16 lines
521 B
TypeScript
import { Scenario } from '../types';
|
|
|
|
export const scenario: Scenario = {
|
|
id: 'create-edge',
|
|
name: 'Create edge between two new nodes',
|
|
description: 'Create two nodes and connect them with an edge.',
|
|
tools: ['createNode', 'createEdge'],
|
|
input: {
|
|
message: 'Create nodes titled "Eval Edge A" and "Eval Edge B" (one sentence each), then create an edge from A to B labeled "related".',
|
|
},
|
|
expect: {
|
|
toolsCalledSoft: ['createNode', 'createEdge'],
|
|
responseContainsSoft: ['edge', 'connected'],
|
|
},
|
|
};
|