{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiht62md55zoyfmzp6hzo25dwnlhvr3q5obldeobf4va37zznchini",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3moumg6ooves2"
  },
  "path": "/t/add-persistent-user-preference-recall-across-codex-cli-conversations/1378787#post_16",
  "publishedAt": "2026-06-22T09:07:24.000Z",
  "site": "https://community.openai.com",
  "textContent": "One implementation detail I would want in a first-class preference layer is that every remembered preference is a scoped record, not just another instruction blob.\n\nSomething like: scope (global / repo / subdirectory / task), source, created-at, last-confirmed-at, expiry or review policy, and conflict behavior. Then the agent can show “I am applying these three preferences in this run” before acting, and it becomes possible to reject stale or cross-repo leakage.\n\nThat also keeps AGENTS.md useful for durable repo behavior, while avoiding the silent promotion problem where a one-off chat preference becomes a permanent default.",
  "title": "Add persistent user preference recall across Codex CLI conversations"
}