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:
“BeeRad”
2025-12-28 16:09:25 +11:00
co-authored by Claude Opus 4.5
parent e15f223ed8
commit 2f2ef10ec9
29 changed files with 1489 additions and 50 deletions
+29
View File
@@ -0,0 +1,29 @@
export type ScenarioExpectations = {
toolsCalled?: string[];
toolsCalledSoft?: string[];
responseContains?: string[];
responseContainsSoft?: string[];
responseNotContains?: string[];
maxLatencyMs?: number;
};
export type ScenarioInput = {
message: string;
focusedNodeId?: number;
focusedNodeQuery?: {
titleContains?: string;
titleEquals?: string;
};
mode?: 'easy' | 'hard';
};
export type Scenario = {
id: string;
name: string;
input: ScenarioInput;
expect?: ScenarioExpectations;
description?: string;
tools?: string[];
enabled?: boolean;
notes?: string;
};