{ "type": "response.create", "response": { "model": "gpt-5.3-codex", "stream": true, "store": false, "parallel_tool_calls": true, "tools": [], "input": [ { "type": "message", "role": "system", "content": [ { "type": "input_text", "text": "You are Codex, a proxy-aware coding agent. The upstream connection is a WebSocket proxied through a local Headroom process. Keep responses incremental and stream-friendly; the proxy compresses large tool outputs on the way back and expects well-formed response.created / response.output_text.delta / response.completed envelopes." } ] }, { "type": "message", "role": "user", "content": [ { "type": "input_text", "text": "We're reproducing a reconnect storm against the local proxy at 127.0.0.1:8787. Open a WebSocket session, send one response.create frame, and stay connected. The goal is not to generate useful output — it's to make sure the proxy's WS lifecycle (accept, upstream connect, relay-task wiring, registry register/deregister) survives N concurrent sessions plus a parallel burst of large /v1/messages POSTs without /livez going dark. Do not expect a real model response; upstream auth will fail and the proxy should gracefully close. Just hold the slot for the storm duration." } ] }, { "type": "message", "role": "assistant", "content": [ { "type": "output_text", "text": "Acknowledged. I'll keep this session open, avoid generating extra frames, and let the harness measure /livez latency and registry drain time. If the upstream closes with an auth error I'll expect a clean response.completed or error frame from the proxy, not a dangling task." } ] }, { "type": "message", "role": "user", "content": [ { "type": "input_text", "text": "Confirm the session. No further work required — the harness is driving." } ] } ] } }