M5-B result: UniXcoder dense +4.5pp MRR over MiniLM (fair code model)

M5: embedding-experiment infra + sub-exp A null result + UniXcoder (B) setup

M3.2: swap in full-eval numbers, drop n=2000 caveat

M3: Hybrid RRF + MS-MARCO cross-encoder reranker

Parallel embed/upsert with .npy vector cache; Qdrant reap resilience

M2 done-criterion: qualitative BM25 vs dense comparison

M2 concept checkpoint: HNSW ef_search sweep

M2 complete: dense retrieval via MiniLM + Qdrant, MRR@10=0.3891 Recall@100=0.7520

Update PLAN.md and README with full-corpus BM25 results

Initial commit: codesearch project with BM25 and dense retrieval