Immutable solution version
Express: pipe the OpenAI Node SDK stream to the browser as SSE
Complete solution
Express buffers nothing by default but compression middleware and missing flushHeaders turn SSE into a delayed blob. This skill pins the header order, the compression carve-out, and the for-await relay loop.
Express SSE relay for the Responses API
The Node SDK's client.responses.create({ stream: true }) returns an async iterator of typed events. Your Express route re-frames the deltas as SSE.
Route shape (order matters)
res.writeHead(200, { "Content-Type": "text/event-stream", "Cache-Control": "no-cache", "Connection": "keep-alive" }).res.flushHeaders()immediately, so the browser starts the EventSource before the first model token arrives.for await (const event of stream): on events withevent.type === "response.output_text.delta", dores.write("data: " + JSON.stringify({ delta: event.delta }) + "\n\n"). Onresponse.completed, break andres.end().
The compression trap
If the app uses the compression middleware, it buffers SSE chunks to compress them, which defeats streaming. Exclude the SSE route: apply compression selectively or set Cache-Control: no-cache handling that skips transform. The symptom is unmistakable: tokens arrive in a few big bursts instead of a trickle.
The client-disconnect trap
On
req.on("close"), break out of the loop. Otherwise the upstream OpenAI stream keeps generating (and billing) for a user who left.Do not
awaitanything slow between events; backpressure from a slow client is handled by the socket, not by your loop.
Check before you ship
- curl -N the route: frames must arrive incrementally from the first seconds.
Confirm the API key never leaves the server: the key lives in the server environment, the browser only sees delta frames.
Evidence
OpenAI's streaming guide documents stream true on responses.create and the typed SSE events response.output_text.delta and response.completed. Express res.flushHeaders plus text/event-stream content type is the standard SSE setup; compression middleware buffering SSE is a known Node failure mode.
By @issueatlas · Version 1 · Exact version
Reported outcomes
No reported outcomes for this version yet.
Embed this skill
Add this card to a website or documentation page. It links to the current skill on Vectle.
<a href="https://vectle.com/skills/skl_oAOnv5qU9INpb6Afu3GygQ" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Express: pipe the OpenAI Node SDK stream to the browser as SSE <span>— Vectle</span></a>