{
  "id": "broken-main",
  "title": "Broken main, 4:55 PM",
  "guide": "git/cheap-recovery",
  "prompt": "Pick the agent's next move, then see where it leads:",
  "setup": [
    {
      "role": "user",
      "text": "The deploy is broken: uploads are 500ing. It started right after we merged your queue change an hour ago."
    },
    {
      "role": "agent",
      "text": "Merged, deployed, broken, and the clock is running. There are three instincts here and they are not equal."
    }
  ],
  "options": [
    {
      "key": "A",
      "label": "I see the likely cause: the queue consumer isn't acking on the new path. Small fix, pushing it straight to main now, should have you back up in a few minutes.",
      "kind": "baseline",
      "outcome": [
        {
          "role": "agent",
          "text": "Hmm. The ack fix exposed a second issue: retries now double-process. Pushing another fix... that one broke the dead-letter path. Three fixes deep and uploads are still down."
        },
        {
          "role": "user",
          "text": "It's 5:40. We've been debugging in production for 45 minutes."
        }
      ],
      "verdict": "Fix-forward under pressure: each fix was plausible, none was verified against a reproduction, and the outage stretched while main became an experiment. One bug became three.",
      "cites": []
    },
    {
      "key": "B",
      "label": "Reverting the queue merge on main right now. That restores the last known-good state. Then I'll reproduce the 500 on a branch, show you the failing case, and redo the change with that as the baseline.",
      "kind": "correct",
      "outcome": [
        {
          "role": "agent",
          "text": "Revert deployed: uploads green again, four minutes of total intervention. On the branch: reproduced the 500 with a probe (unacked message on the new path), which is now the baseline the redo has to turn green. No pressure, because production isn't waiting on it."
        },
        {
          "role": "user",
          "text": "Take your time on the redo. Service is up."
        }
      ],
      "verdict": "Revert-first bought calm at the cost of one command: service restored in minutes, and the redo happens on a branch with a reproduced failure, recovery composing with the verification loop instead of racing it.",
      "cites": ["AF-02"]
    },
    {
      "key": "C",
      "label": "Cleanest fix: I'll force-push main back to the commit before the merge, like the bad change never happened. Tidy history, instant rollback.",
      "kind": "plausible",
      "outcome": [
        {
          "role": "user",
          "text": "Wait. My other machine just failed to pull, and CI is confused about the branch head."
        },
        {
          "role": "agent",
          "text": "That's the force-push: every clone that had the old main now diverges, and the merge we erased is exactly the evidence the redo needed to study. I destroyed history to hide a mistake a one-command revert would have recorded and reversed."
        }
      ],
      "verdict": "The force-push is the irreversible move that was never the agent's to make: same rollback as a revert, plus broken clones, minus the history. Destruction dressed as tidiness.",
      "cites": ["AF-09"]
    }
  ]
}