{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidto6muq6iv43dbiqmfcnpwoxlm7wvn2vdcisgxexyqnfjsut5am4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mphrixudwfp2"
  },
  "path": "/t/does-forking-a-codex-conversation-preserve-full-context/1385300#post_1",
  "publishedAt": "2026-06-30T00:29:58.000Z",
  "site": "https://community.openai.com",
  "textContent": "I’m trying to understand how forking works in Codex Desktop.\n\nI had a Codex conversation with a lot of concrete project details: source files, database paths, import rules, exclusions, and decisions we had already made.\n\nThen I forked the conversation.\n\nIn the fork, Codex acted like it barely remembered the original thread. It missed important decisions and even invented placeholder paths that contradicted what we had already discussed.\n\nFrom my side, it felt like the fork started from a very aggressive hidden summary/compaction, but I didn’t see any warning that context would be reduced.\n\nIs that expected?\n\nWhen I fork a Codex conversation, does the new thread get the full prior context, or only a compacted/summarized version of it?\n\nIf it’s summarized, I think the UI should make that clear, because in coding workflows this can lead to wrong code changes very quickly.",
  "title": "Does forking a Codex conversation preserve full context?"
}