Instrument image-token cost and error classes

Instrument typed receipt-vision API that extracts total + merchant with uncertainty so expense bot that must refuse blurry or non-receipt images can answer: demand, errors, latency/age, saturation. Emit fields needed by extraction_precision and abstain_on_non_receipt ≥ 0.95 with bounded labels. Sample successful high-volume traces; keep errors and rollout transitions denser within policy.

Define at least one alert that would fire for VISION-MEME-77, with a for/pending window that survives deploy blips. Missing scrape or missing revision labels must not look like health. Include a trace/log example id format you will actually search.

Add a unit/integration check that metrics increment on the happy path and on the screenshot of a meme parsed as a $9,999 expense branch. Store machine-readable output in CI artifacts when practical.

Cardinality discipline: tenant and revision are usually enough; raw question text is not a label. Exemplars or trace links beat screenshots alone when debugging VISION-MEME-77. Define who owns alert fatigue review. If you export to a vendor, record retention and access. Synthetic probes should use non-sensitive fixtures and still exercise POST /v1/receipts/extract. Practice the query you will type at 2am once, while calm.

Document the exact PromQL or log query in the runbook stub for this service. Verify histograms have buckets around your SLO target. Add a canary synthetic check that exercises the oracle path every few minutes in staging. Confirm that PII redaction happens before export. Track build/version as a label on the golden signals. Delete noisy debug logs before they become accidental product dependencies. 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.