feat: sync runtime search and schema quality updates from app repo

- 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

tests/evals/scenarios/archive/simple-query.ts

@@ -0,0 +1,15 @@
+import { Scenario } from '../types';
+
+export const scenario: Scenario = {
+  id: 'simple-query',
+  name: 'Simple query routes to helper',
+  description: 'Baseline retrieval query against existing notes.',
+  tools: ['queryNodes'],
+  input: {
+    message: 'What do I know about machine learning?',
+  },
+  expect: {
+    toolsCalledSoft: ['queryNodes'],
+    responseContainsSoft: ['node', 'found'],
+  },
+};