Add baseline harness: ingest, metrics, ablation arms, external counterpart, audit

- bench/ingest_baseline.py drives the unmodified product IngestionService over
  all 50,789 corpus files in sharded SQLite DBs, then merges them. Thread and
  memory ceilings are set explicitly: ONNX Runtime defaulted to every core
  (95 threads/worker, load 490) and its CPU arena kept freed pages mapped,
  which OOM-killed workers.
- bench/metrics.py: recall@k, MRR, nDCG@10, Wilson lower bound, chance
  baseline. No model, no product import, so the scorer cannot grade itself.
- bench/systems.py + bench/run.py: the five ablation arms over the merged DB,
  latency percentiles, scale curve, and a top-10 equivalence check against the
  live RetrievalService.
- bench/counterpart.py + bench/run_external.py: in-repo Mem0-style flat store
  and Zep-style temporal store as the external reference point.
- bench/audit.py: enforces single-attempt scoring, frozen n, a chance row
  beside every score, and producer != verifier. It already flags the product's
  retry-until-target loop at backend/src/ely_eye/evals.py:2351.
- backend/pyproject.toml: rapidocr-onnxruntime>=1.4.4 was unsatisfiable
  (PyPI maxes at 1.2.3); the successor is the renamed rapidocr package.

bench/build_code.py

@@ -217,7 +217,7 @@ def build() -> tuple[list, list, dict]:
 def main() -> None:
     corpus, queries, report = build()
     corpus_count, corpus_sha = write_jsonl(SETS / "corpus" / "code.jsonl", corpus)
-    query_count, query_sha = write_jsonl(SETS / "code.jsonl", queries)
+    _query_count, query_sha = write_jsonl(SETS / "code.jsonl", queries)
     report |= {"corpus_records": corpus_count, "corpus_sha256": corpus_sha, "queries_sha256": query_sha}
     (SETS / "reports").mkdir(parents=True, exist_ok=True)
     (SETS / "reports" / "code.json").write_text(