Build the first working normalize-and-analyze path

Code the narrow path that serves expense bot that must refuse blurry or non-receipt images: accept → authorize/normalize → call dependency → validate → record. Keep stages named so a trace can show which boundary passed. Success must emit evidence useful to extraction_precision and abstain_on_non_receipt ≥ 0.95, not only a 200 with prose. Predict the observable for POST /v1/receipts/extract before running: sharp receipt → total=24.50 merchant=Cafe Nora confidence≥0.7; blurry → abstain.

Drive the path with recording fakes or local stubs. Assert call order and arguments. Idempotency keys or stable ids should keep retries from duplicating costly work where the product requires it. Product under test remains typed receipt-vision API that extracts total + merchant with uncertainty — resist adding unrelated features mid-path.

For Multimodal API lab, paste the CLI/HTTP transcript beside your prediction for POST /v1/receipts/extract. If the oracle is unmet (sharp receipt → total=24.50 merchant=Cafe Nora confidence≥0.7; blurry → abstain), stop and debug this page; do not compensate with prompt folktales. Re-run once after a clean process start to catch hidden global state that would invalidate VISION-MEME-77.

Performance sketch: measure local p95 for the fake-backed path so later regressions are obvious. Keep concurrency modest until failure-handling proves limits. Log a single structured event per success with request id, revision, and the evidence field behind extraction_precision and abstain_on_non_receipt ≥ 0.95. Avoid hidden global caches in the happy path unless the lab is about caching — and even then key by tenant. If the path calls a model, pin model id in config and echo it in the response for auditability. Remember expense bot that must refuse blurry or non-receipt images experiences wall-clock time, not your debugger’s single-step comfort.

Prefer explicit function names over a single god-object handleRequest. Thread a correlation id from ingress to the last log line. When streaming, define what partial failure means before coding. Snapshot one successful response body in fixtures after redaction. If the path writes to a queue, assert message attributes in the fake. Stop adding retries on this page; that is the next concern. 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.