Weighted RRF (2:1): no recall recovery; hybrid still 0.86 vs dense 0.91

Day 5 ablations: hybrid recall@20=0.97, bge-reranker-base hurts MRR (0.71->0.63)

Baseline v0: recall@5 0.91, MRR 0.71, correct 0.89

Day 4: 42-question eval harness; fix max file size (routing.py was unindexed)

Add gitignore

Remove venv and generated data from git; add .gitignore

Day 3: embedding index + baseline ask pipeline

Day 2: AST-aware chunkers for code, docs, issues

Day 1: ingestion pipeline (code, docs, issues)