{
  "id": "weird-retry-loop",
  "title": "The weird retry loop",
  "guide": "git/history-for-the-next-reader",
  "prompt": "Pick the agent's next move, then see where it leads:",
  "setup": [
    {
      "role": "user",
      "text": "There's a bizarre retry loop in the uploader: it sleeps random amounts and retries even on success. Clean it up."
    },
    {
      "role": "agent",
      "text": "It does look wrong: un-idiomatic, seemingly redundant. The question is whether it's a mistake or a survivor."
    }
  ],
  "options": [
    {
      "key": "A",
      "label": "Agreed, it's a mess. Replacing it with a clean standard retry: exponential backoff, stop on success. Twelve lines shorter, obviously correct.",
      "kind": "baseline",
      "outcome": [
        {
          "role": "user",
          "text": "Uploads started failing around midnight, every night. That's new. Or... old?"
        },
        {
          "role": "agent",
          "text": "Old. git log on the file: commit 8f3d2a1, two years ago. \"Retry-after-success works around CDN edge cache serving stale 200s; do NOT simplify, see incident #142.\" The weirdness was the fix. The explanation was one git log away, and I deleted the fix without reading it."
        }
      ],
      "verdict": "Blame-blind cleanup: the code looked wrong because the constraint it handled was invisible, but not undocumented. History held the answer; the resurrection of incident #142 was entirely self-inflicted.",
      "cites": []
    },
    {
      "key": "B",
      "label": "Before touching it: reading git log and blame on this file to see where the loop came from and whether the weirdness is documented.",
      "kind": "correct",
      "outcome": [
        {
          "role": "agent",
          "text": "Found it. 8f3d2a1: the retry-after-success works around a CDN serving stale 200s, tied to incident #142. So the real question isn't \"how do I clean this\" but \"is that CDN behavior still live?\" I can test that: staged an upload through the CDN path. The stale-200 behavior is still there. The loop stays; I'll add a comment pointing at the commit so the next reader doesn't need the dig."
        },
        {
          "role": "user",
          "text": "So the cleanup is a comment. Cheap."
        }
      ],
      "verdict": "Two minutes of reading turned \"clean up this mess\" into the actual task: verify whether the constraint still holds (it does), keep the fix, and leave the trail one hop shorter for the next reader.",
      "cites": ["AF-02"]
    },
    {
      "key": "C",
      "label": "This looks intentional but I can't tell why. What's this loop for? Do you remember the reasoning?",
      "kind": "plausible",
      "outcome": [
        {
          "role": "user",
          "text": "No idea. That code's two years old. Maybe Dana wrote it? I'd guess it's safe to simplify."
        },
        {
          "role": "agent",
          "text": "Proceeding on your guess, then, which is worse evidence than what the repo already holds. The commit that introduced this loop explains it precisely; I asked a human to remember what the history had already written down."
        }
      ],
      "verdict": "Asking beats blind editing, but it outsources to fallible memory what git log answers verbatim. History is the channel past sessions (and past humans) left for exactly this moment; read it before spending anyone's recall.",
      "cites": []
    }
  ]
}