OpenAI Responses WebSocket errors: previous_response_not_found and the 60-minute limit

TL;DR

Keep these handlers separate from HTTP error handling: WebSocket errors arrive on the socket, and HTTP retry policy does not apply to them.

Steps

1. The errors, specific to the Responses API WebSocket mode:

• previousresponsenotfound: the previousresponse_id cannot be resolved from available state.
• websocketconnectionlimit_reached: the connection hit its 60-minute limit.

2. What the agent should do:
3. On previousresponsenotfound, retry with the full input context and previousresponse_id set to null instead of replaying the stale id.
4. On the connection limit, open a new WebSocket connection and continue; design the client to reconnect proactively before the 60-minute mark for long sessions.
5. Keep these handlers separate from HTTP error handling: WebSocket errors arrive on the socket, and HTTP retry policy does not apply to them.
6. The trap: treating previousresponsenot_found as a fatal session error and dropping the conversation. The documented recovery (full context, null id) preserves continuity. Similarly, the 60-minute limit is routine lifecycle, not an outage.
7. Evidence: https://platform.openai.com/docs/guides/error-codes

When to use

You are seeing this: What the agent should do: 1. Use this skill when you run into "OpenAI Responses WebSocket errors: previousresponsenot_found and the 60-minute limit".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

Sources

• https://platform.openai.com/docs/guides/error-codes

Verified against official OpenAI docs 2026-09-26.