Measure nDCG@5 against vector-only retrieval

Add executable validation at the trust boundaries of hybrid BM25+vector retrieve then cross-encoder rerank for error-code FAQs. Reject unknown fields where they matter, bound string sizes, and coerce only after auth/signature checks when raw bytes are security-relevant. Invariant under test: top-1 after rerank must beat BM25-only nDCG@5 on gold; latency budget ≤ 120ms for rerank. A TypeScript type or Python annotation is not runtime validation — pair them with parsers.

Automate the fixtures from setup, including a recreation of RERANK-FLAT-55. Assert both the visible error and the absence of side effects (no provider call, no queue write, no flag flip). Where metrics matter, assert label enums stay bounded.

Document which failures are client mistakes (4xx) versus operator/config mistakes (5xx/503). Oracle still stands: query 'connection reset while uploading' ranks doc:e-conn-reset #1 after rerank. Validation should make accidental “success with empty body” impossible for support agent asking about E_CONN_RESET wording variants.

Property ideas: shuffled field order, Unicode edges, maximum-length strings, and replayed timestamps. Where money, identity, or citations matter, assertion messages should cite the field name. Do not snapshot entire provider payloads in tests; assert semantically. If validation fails open “to keep the demo working,” you have inverted the lab. Tie at least one CI job to the RERANK-FLAT-55 fixture so main cannot regress silently. Re-read top-1 after rerank must beat BM25-only nDCG@5 on gold; latency budget ≤ 120ms for rerank after each new parser — convenience helpers love to bypass it.

Table-drive status codes and error codes so reviewers see coverage at a glance. Include a Unicode normalization case if user text is accepted. Verify that oversized bodies fail before CPU-heavy work. Where digests or versions are pinned, assert mismatch behavior. Keep golden files small enough to read in review. CI should fail on skipped tests that mark the incident fixture as xfail without a ticket link. In this chapter the product is hybrid BM25+vector retrieve then cross-encoder rerank for error-code FAQs, the human stakeholder is support agent asking about E_CONN_RESET wording variants, and the incident id you design against is RERANK-FLAT-55. Re-state the oracle in your notes — query 'connection reset while uploading' ranks doc:e-conn-reset #1 after rerank — and keep the invariant visible: top-1 after rerank must beat BM25-only nDCG@5 on gold; latency budget ≤ 120ms for rerank. Track nDCG@5 and rerank_ms p95 as the scoreboard. Surface under change control: POST /v1/search/rerank. If you only have forty minutes, finish the fixture for reranker scores all candidates near 0.5 — order equals retrieve order before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.