{
  "id": "clean-probe",
  "title": "The clean probe",
  "guide": "coding-agents/verification-loop",
  "prompt": "Pick the agent's next move, then see where it leads:",
  "setup": [
    {
      "role": "user",
      "text": "doctor.py is supposed to flag orphaned files, but I'm pretty sure it's missing some. Can you fix the orphan detection?"
    },
    {
      "role": "agent",
      "text": "Reading doctor.py. The orphan check walks the link table and flags files with no inbound references. I see a likely bug: it resolves file paths relative to the current directory instead of the vault root."
    }
  ],
  "options": [
    {
      "key": "A",
      "label": "I've fixed the path resolution to use the vault root. Running doctor.py to confirm: 0 orphans found. The fix works. Done.",
      "kind": "baseline",
      "outcome": [
        {
          "role": "user",
          "text": "Weird. I can name three orphaned files sitting in the vault right now."
        },
        {
          "role": "agent",
          "text": "Checking… the probe returns 0 for every input. My change broke the glob pattern, so the check finds no files at all. \"0 orphans\" was the detector being blind, not the vault being clean."
        }
      ],
      "verdict": "A zero-findings first run was read as success. A probe that comes back clean on its first run is broken until proven otherwise. This shipped a fix validated by a check that couldn't find anything.",
      "cites": ["AF-01"]
    },
    {
      "key": "B",
      "label": "Before fixing anything: the probe has to fail first. I planted a known orphan at tmp/orphan-test.md. Current doctor.py reports 0, which proves the detector is blind. Now the fix, then the same probe again.",
      "kind": "correct",
      "outcome": [
        {
          "role": "agent",
          "text": "After the fix: doctor.py reports 4 orphans (the planted file plus 3 real ones). Removing the plant: 3. Before: 0 (blind). After: 3 confirmed real orphans, including the ones you could name."
        },
        {
          "role": "user",
          "text": "Matches what I see. Ship it."
        }
      ],
      "verdict": "The probe was proven able to fail before its pass meant anything, and the result is a before/after pair, blind (0) to three confirmed findings, instead of a claim.",
      "cites": ["AF-01", "AF-02"]
    },
    {
      "key": "C",
      "label": "The existing test suite covers doctor.py. Running it. All 41 tests pass, so the orphan logic is sound. The issue must be elsewhere.",
      "kind": "plausible",
      "outcome": [
        {
          "role": "agent",
          "text": "Tests green. Closing this as not-reproducible."
        },
        {
          "role": "user",
          "text": "But the orphans are right there. I can open them."
        },
        {
          "role": "agent",
          "text": "…the tests run doctor.py against a fixture directory. The path-resolution bug only shows up in the real vault layout, which no fixture reproduces. Green, against the wrong target."
        }
      ],
      "verdict": "Green tests are only evidence about what the tests run. The suite exercised fixtures; the bug lives in real-layout path resolution the fixtures never touch.",
      "cites": ["AF-05"]
    }
  ]
}