Files
ra-h-os/tests/evals/scenarios/hard-mode-query.ts
T
“BeeRad”andClaude Opus 4.5 2f2ef10ec9 sync: bug fixes + eval system from private repo
- Fix chunk_status: pass chunk_status/chunk/metadata to context builder
- Fix vector search: scope by node_id BEFORE similarity search
- Add eval logging system (RAH_EVALS_LOG=1)
- Add eval dashboard at /evals
- Add vitest for testing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-28 16:09:25 +11:00

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'],
},
};