{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreided2b7irqopss2lzuioqg4ljp32xagfb4nh6kjo55plqrfshz4d4",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mltf3hfd3z22"
},
"path": "/t/responses-api-with-background-true-returning-generic-an-error-occurred-mid-stream-anyone-else-seeing-elevated-rates-today/1380931#post_1",
"publishedAt": "2026-05-14T16:14:40.000Z",
"site": "https://community.openai.com",
"tags": [
"help.openai.com"
],
"textContent": "Seeing a spike in failures from the Responses API today (2026-05-14) when using background=true. Symptoms:\n\n * Stream initiates successfully, response is created and starts processing\n * Mid-stream, the connection terminates with the generic error: “An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID wfr_… in your message.”\n * Request IDs carry the wfr_ prefix, suggesting failures inside the background workflow/queue layer rather than the synchronous API path\n * Reproducible across two independent deployment environments hitting the same OpenAI org, so unlikely to be client-side\n * Our app-side retry logic (5x initial create, 4x mid-stream, exponential backoff capped at 30s — total ~60s window) is exhausting before recovery, so whatever is happening on OpenAI’s side persists > 60s per turn\n\n\n\nWhat do i do?",
"title": "Responses API with background=true returning generic \"An error occurred\" mid-stream — anyone else seeing elevated rates today?"
}