- 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
- 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>