Measure field match and abstention quality

Add executable validation at the trust boundaries of typed receipt-vision API that extracts total + merchant with uncertainty. 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: image ≤ 4 MiB, MIME allowlisted, model output schema-validated before DB write. A TypeScript type or Python annotation is not runtime validation — pair them with parsers.

Automate the fixtures from setup, including a recreation of VISION-MEME-77. 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: sharp receipt → total=24.50 merchant=Cafe Nora confidence≥0.7; blurry → abstain. Validation should make accidental “success with empty body” impossible for expense bot that must refuse blurry or non-receipt images.

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 VISION-MEME-77 fixture so main cannot regress silently. Re-read image ≤ 4 MiB, MIME allowlisted, model output schema-validated before DB write 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 typed receipt-vision API that extracts total + merchant with uncertainty, the human stakeholder is expense bot that must refuse blurry or non-receipt images, and the incident id you design against is VISION-MEME-77. Re-state the oracle in your notes — sharp receipt → total=24.50 merchant=Cafe Nora confidence≥0.7; blurry → abstain — and keep the invariant visible: image ≤ 4 MiB, MIME allowlisted, model output schema-validated before DB write. Track extraction_precision and abstain_on_non_receipt ≥ 0.95 as the scoreboard. Surface under change control: POST /v1/receipts/extract. If you only have forty minutes, finish the fixture for screenshot of a meme parsed as a $9,999 expense before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.