{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreih5ymmpnor27sybdyn75puodgpcb7rvmjhnzsgpgdq7nhzy532o6q",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmcc4hxewgv2"
  },
  "path": "/t/codex-users-report-rapid-quota-drains-since-may-10/1380649#post_15",
  "publishedAt": "2026-05-20T15:35:20.000Z",
  "site": "https://community.openai.com",
  "textContent": "One practical way to debug this is to separate three counters that often get collapsed together: prompt text size, tool/runtime activity, and verified progress. A short prompt can still become expensive if it opens browser/tool loops, retries after failures, or keeps re-reading large context without producing a durable change.\n\nThe usage UI would be much easier to trust if each Codex run exposed a small receipt: model used, wall time, tool calls, context/read volume, whether files/tests changed, and the stop reason. Then users could tell the difference between a real metering bug, a workspace-specific loop, and a normal higher-cost task.",
  "title": "Codex users report rapid quota drains since May 10"
}