{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifk645qyllkqheva3g5jeeyqlhjbrktfmbioicum5alyayerq2vs4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mjtncz2czr72"
  },
  "path": "/t/add-persistent-user-preference-recall-across-codex-cli-conversations/1378787#post_5",
  "publishedAt": "2026-04-19T08:31:09.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@adrian.a.adewunmi"
  ],
  "textContent": "OpenAI_Support:\n\n> Hi @adrian.a.adewunmi\n>\n> Thanks for the clear write-up, the distinction you’re making between repo-level instructions (AGENTS.md) and user-level preferences across sessions is spot on.\n>\n> Right now Codex CLI is stateless, so things like commit style or PR structure need to be reintroduced or handled per-repo, which creates the friction you’re describing.\n>\n> The idea of separating repo conventions, user defaults, and per-chat overrides makes a lot of sense and fits well with real workflows.\n>\n> ~SD\n\nHi ~SD,\n\nThanks for confirming this. That split between repo conventions, user defaults, and per-chat overrides feels like the missing piece to me.\n\n`AGENTS.md` works well for codebase-specific guidance, but it’s not a good place for persistent personal working preferences that should follow the user across repos and sessions. Re-stating things like commit style, PR format, or review preferences each time adds avoidable overhead.\n\nA layered model like:\n\n  * repo-level instructions\n  * user-level defaults\n  * chat-level overrides\n\n\n\nwould map much more cleanly to how people actually work in practice.\n\nAppreciate the thoughtful response.\n\nBest wishes,\n\nAdrian",
  "title": "Add persistent user preference recall across Codex CLI conversations"
}