Just built some FastAPI SSE backend streaming LLM responses token-by-token, after i got some free time.Two things broke in production that worked fine locally 🙃:nginx buffers SSE by default. The stream was delivering locally, dead silent on Railway. proxy_buffering off, two hours later, fixed.The LLM API returns an empty_retrieval event when no docs match. I wasn't handling it, so the frontend sat on a loading spinner indefinitely. Added the handler, resolved.https://zooming-charm-production-547e.up.railway.app/