Streaming responses
Set release boundaries for the SSE token relay
Page 7 defines what the SSE relay for model tokens must refuse before release—security here is not a pasted happy path.
1Learn the idea
Read
Threats for this artifact only
Operational risks for the SSE relay for model tokens center on streaming secrets from upstream error bodies to the browser, plus the earlier failure mode (buffering the whole answer before first byte, or ignoring client disconnect). Safety lives in executable gates, allowlists, redaction, and a named owner—not in a warning paragraph under an unsafe function.
Read
Run the release gate
function authorize(ctx: Context, action: Action) {
if (!ctx.permissions.has(action.permission)) {
throw new SafeError("forbidden");
}
if (action.risk === "write" && !ctx.approvalToken) {
throw new SafeError("approval_required");
}
}
Expected evidence: The client renders “Hello 👋” in order, receives done once, and closes cleanly.. A failed assertion means stop, investigate, and do not publish the SSE token relay.
Read
Owner, retention, rollback
Name who can disable the feature, what data is retained, and how to roll back to the last known good artifact. Pin the reviewed configuration (versions, thresholds, allowlists) so “what shipped” is reconstructable for streaming-responses.
Read
Lab notebook: release blocker
Write the release blocker as a predicate, not a feeling: “Do not ship the SSE token relay if streaming secrets from upstream error bodies to the browser.” Pair it with a passing control that shows the reviewed configuration still works for fake chunk iterator yielding three tokens then done. Name an owner and a rollback handle (git tag, docs_version, previous image).
Security pages must not paste the happy-path demo. If your gate code looks like the implementation page, replace it with a deny/allow check aimed at streaming secrets from upstream error bodies to the browser.
Read
Worked judgment
State the data retention rule in one line (what is stored, for how long, who can read it). Then state the kill switch (env flag, config pin, or feature owner). The SSE token relay is not shippable without both, even when time-to-first-byte, event count, cancel stops within N events looks healthy.
Read
Why this stage matters for the SSE token relay
At the safety and operations 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 an executable deny gate for the lab-specific threat 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
Go deeper
Before you start
Why this matters
Write an attack or unsafe misuse specific to this lab: streaming secrets from upstream error bodies to the browser. Predict whether your current code blocks it. Then run the gate below and compare.
In the wild
See how this idea shows up as a product and a company — then come back to the lesson. Skills transfer across vendors.
Related lessons
Check your understanding
Page assessment
Answer from memory. Completion is saved from this evidence, not from opening the next page.
All responses are required.