{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreicu2iopisjkla7kfku4r5n27fh66gsqjqx7zjovuj4nl6vtv5tgxa",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mkuhonxxbr52"
},
"path": "/t/responses-corrupts-previous-conversations-assistant-item/1380154#post_5",
"publishedAt": "2026-05-02T10:30:26.000Z",
"site": "https://community.openai.com",
"textContent": "OK one slightly odd thing you are doing is you are appending a system message using responses after the conversation is well under way. Can you avoid that?\n\n\n 1. system → original system\n 2. user → original user\n 3. assistant → your injected assistant\n 4. system → NEW system (from Responses input)\n\n\nI would expect (and I’m probably not the only one) only one system message and then a series of user and assistant messages.\n\nSo your pattern is at least non-standard and might not be supported.",
"title": "`responses` corrupts previous conversations `assistant` item"
}