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>
This commit is contained in:
co-authored by
Claude Opus 4.5
parent
e15f223ed8
commit
2f2ef10ec9
@@ -0,0 +1,15 @@
|
||||
import { Scenario } from '../types';
|
||||
|
||||
export const scenario: Scenario = {
|
||||
id: 'dimension-lifecycle',
|
||||
name: 'Dimension lifecycle (create/update/lock/unlock)',
|
||||
description: 'Create a dimension, update its description, lock it, then unlock it.',
|
||||
tools: ['createDimension', 'updateDimension', 'lockDimension', 'unlockDimension'],
|
||||
input: {
|
||||
message: 'Create a dimension named "eval-dim" with description "temporary eval dimension", then update the description to "eval dimension updated", then lock it, then unlock it.',
|
||||
},
|
||||
expect: {
|
||||
toolsCalledSoft: ['createDimension', 'updateDimension', 'lockDimension', 'unlockDimension'],
|
||||
responseContainsSoft: ['eval-dim'],
|
||||
},
|
||||
};
|
||||
Reference in New Issue
Block a user