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>

tests/evals/dataset.json

@@ -0,0 +1,5 @@
+{
+  "id": "golden-v1",
+  "name": "Golden Dataset v1",
+  "description": "Baseline eval scenarios for core RA-H helper behavior."
+}