{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibmg5rnpfsw2xky3xb6lxnwvi2iujangmzf5xq433g5gk45hkmuii",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mnu33b7tbka2"
  },
  "path": "/t/file-citations-bug-in-file-search-citations-using-gpt-5-5/1383150#post_2",
  "publishedAt": "2026-06-09T10:51:21.000Z",
  "site": "https://community.openai.com",
  "textContent": "Thanks for the report that has no ambiguity.\n\nThat’s how the AI-written citations generally should look:\n\nIt is not a completely faulty request like having two of the second parts in one container.\n\nA few times, with new model releases and also on the same, OpenAI has revised their character scheme from oddball Unicode blocks that they instruct the model to create. The internal tool instructions for the AI must match what sequence the API strips out of the response and recognizes.\n\nThe API is not capturing the citation string if you are seeing it.\n\nThis is an API configuration bug for the model or for the whole endpoint if the AI is always writing the same citation characters, never parsed out, and the vector store and file search tool remains attached.\n\nOpenAI staff must recognize, escalate, and fix the issue.",
  "title": "File Citations bug in file_search citations using gpt-5.5"
}