Implement the happy path

Code the narrow path that serves ops coordinator clearing a 200-message backlog without auto-sending refunds: accept → authorize/normalize → call dependency → validate → record. Keep stages named so a trace can show which boundary passed. Success must emit evidence useful to unapproved_send_count == 0 and median_time_to_draft ≤ 45s, not only a 200 with prose. Predict the observable for POST /v1/workflows/email-triage/runs before running: fixture thread reaches awaiting_approval with draft; send blocked until Approve(id).

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 workflow that classifies inbound email → draft reply → human approve → send — resist adding unrelated features mid-path.

For Workflow automation in code, paste the CLI/HTTP transcript beside your prediction for POST /v1/workflows/email-triage/runs. If the oracle is unmet (fixture thread reaches awaiting_approval with draft; send blocked until Approve(id)), 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 WF-AUTOSEND-19.

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 unapproved_send_count == 0 and median_time_to_draft ≤ 45s. 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 ops coordinator clearing a 200-message backlog without auto-sending refunds 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 workflow that classifies inbound email → draft reply → human approve → send, the human stakeholder is ops coordinator clearing a 200-message backlog without auto-sending refunds, and the incident id you design against is WF-AUTOSEND-19. Re-state the oracle in your notes — fixture thread reaches awaiting_approval with draft; send blocked until Approve(id) — and keep the invariant visible: send step requires approval token; classifier never triggers send directly. Track unapproved_send_count == 0 and median_time_to_draft ≤ 45s as the scoreboard. Surface under change control: POST /v1/workflows/email-triage/runs. If you only have forty minutes, finish the fixture for model labels 'issue refund' and workflow auto-calls payment tool before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.