- 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
17 lines
476 B
TypeScript
17 lines
476 B
TypeScript
import { Scenario } from '../types';
|
|
|
|
export const scenario: Scenario = {
|
|
id: 'hard-mode-query',
|
|
name: 'Hard mode retrieval query',
|
|
description: 'Run a baseline retrieval query in hard mode.',
|
|
tools: ['queryNodes', 'searchContentEmbeddings'],
|
|
input: {
|
|
message: 'What have I captured about plaintext productivity and tools?',
|
|
mode: 'hard',
|
|
},
|
|
expect: {
|
|
toolsCalledSoft: ['queryNodes'],
|
|
responseContainsSoft: ['plaintext', 'productivity'],
|
|
},
|
|
};
|