Measure whether the SSE token relay works

Translate the claim into assertions or a tiny eval harness. The metric to protect is: time-to-first-byte, event count, cancel stops within N events. Always record the denominator (how many cases) beside any rate. A percentage without a denominator is marketing, not measurement.

const parsed = OutputSchema.safeParse(raw);
if (!parsed.success) {
  throw new ContractError("invalid_output", parsed.error.issues.map(i => ({
    path: i.path.join("."), code: i.code
  })));
}
return parsed.data;

Expected evidence: The client renders “Hello 👋” in order, receives done once, and closes cleanly.. A passing assertion proves only the behavior it names; broader usefulness still needs the chapter’s full limits.

Be explicit: beating the baseline (non-streaming JSON endpoint latency for the same prompt) on this fixture does not prove behavior under buffering the whole answer before first byte, or ignoring client disconnect. Label observations separately from conclusions so the next page inherits honest evidence about the SSE token relay.

Compute time-to-first-byte, event count, cancel stops within N events with the denominator written beside the rate every time. For this chapter, the evaluation set is intentionally tiny; that is allowed only if you say so in the evidence. Compare against non-streaming JSON endpoint latency for the same prompt before celebrating.

Add one negative case aimed at buffering the whole answer before first byte, or ignoring client disconnect. A suite with only happy cases cannot protect the SSE token relay when the characteristic failure appears in review.

If a check is expensive or flaky, shrink it until it is deterministic on fake chunk iterator yielding three tokens then done. Flaky green builds teach the team to ignore gates. Record what this page does not prove so security-ops and mastery-ship inherit honest limits.

At the evaluation stage for streaming-responses, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about fake chunk iterator yielding three tokens then done that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: non-streaming JSON endpoint latency for the same prompt.

For this page specifically, success looks like metrics with explicit denominators and a negative case while still centering the user decision to stream tokens to a client while honoring cancel and partial failure. If you cannot point to a file, command, or assertion that proves that for the SSE token relay, stay on this page instead of advancing.

Glossary: tool · Glossary: structured output · Cheatsheet: production ops signals

Previous · Next