Measure false hits, hits, and token savings

Add executable validation at the trust boundaries of tenant-scoped semantic cache for repeated FAQ paraphrases. 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: cache key includes tenant_id + policy_version; similarity ≥ 0.92 and risk≠high. A TypeScript type or Python annotation is not runtime validation — pair them with parsers.

Automate the fixtures from setup, including a recreation of CACHE-XTENANT-2. 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: paraphrase hit returns cached answer with cache=HIT; different tenant never hits. Validation should make accidental “success with empty body” impossible for cost owner cutting duplicate GPT calls for Acme Corp FAQs.

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 CACHE-XTENANT-2 fixture so main cannot regress silently. Re-read cache key includes tenant_id + policy_version; similarity ≥ 0.92 and risk≠high 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 tenant-scoped semantic cache for repeated FAQ paraphrases, the human stakeholder is cost owner cutting duplicate GPT calls for Acme Corp FAQs, and the incident id you design against is CACHE-XTENANT-2. Re-state the oracle in your notes — paraphrase hit returns cached answer with cache=HIT; different tenant never hits — and keep the invariant visible: cache key includes tenant_id + policy_version; similarity ≥ 0.92 and risk≠high. Track hit_rate ∈ [0.25,0.55] and cross_tenant_hits == 0 as the scoreboard. Surface under change control: POST /v1/answer. If you only have forty minutes, finish the fixture for cross-tenant near-duplicate question returns Acme's private pricing blurb before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.

For semantic-cache-lab, write a transfer example that differs in one constraint from the chapter scenario. Keep the quality bar fixed. Explain which check still applies.

For semantic-cache-lab, write a transfer example that differs in one constraint from the chapter scenario. Keep the quality bar fixed. Explain which check still applies.