{
  "checker": {
    "claims": [
      {
        "claim": "The demo runs two free stand-in agents without a model or network.",
        "command": "<guest-path> demo",
        "evidence": "stub-solver  pass    0.1s   1,060  $0.0000\nstub-lazy    FAIL    0.1s   1,060  $0.0000\n\nFull report: results.html\nstub-solver copies the known fix and stub-lazy changes nothing: they test the pipeline, not any model. Run `agentbench start` to compare real agents on your own code.\nNext: agentbench doctor, then agentbench start\n",
        "expected": "stub-solver passes and stub-lazy fails",
        "input": "documented agentbench demo",
        "kind": "claim",
        "outcome": "Real input produced the expected result: stub-solver  pass",
        "returncode": 0,
        "source": "They cost nothing and use no model, so they test the plumbing, not any agent.",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      }
    ],
    "cycle_checks": [
      {
        "claim": "Scheduled or looping main behavior",
        "command": "",
        "evidence": "README describes one-shot CLI commands and no product scheduler, loop or webhook; demo is a single invocation.",
        "expected": "identify the product trigger",
        "input": "source inspection",
        "kind": "cycle",
        "outcome": "README describes one-shot CLI commands and no product scheduler, loop or webhook; demo is a single invocation.",
        "source": "repository entry points",
        "verdict": "yes"
      }
    ],
    "details": {
      "argv": [
        "<guest-path>",
        "demo"
      ],
      "kind": "cli",
      "needs_browser": false,
      "needs_credentials": false,
      "returncode": 0,
      "scope": "product operation",
      "stderr": "",
      "stdout": "1/3  Building a toy task: a small repo, a bug, and a hidden test that proves it is fixed ...\n2/3  Running two free stand-in agents on it (no model, no network, $0) ...\n3/3  Results:\n\nContestant   Result  Time  Tokens  $ equiv\n-----------  ------  ----  ------  -------\nstub-solver  pass    0.1s   1,060  $0.0000\nstub-lazy    FAIL    0.1s   1,060  $0.0000\n\nFull report: results.html\nstub-solver copies the known fix and stub-lazy changes nothing: they test the pipeline, not any model. Run `agentbench start` to compare real agents on your own code.\nNext: agentbench doctor, then agentbench start",
      "working": true
    },
    "evidence_strength": "readme_checked",
    "example_checks": [
      {
        "claim": "README quickstart demo",
        "command": "<guest-path> demo",
        "deferred": false,
        "evidence": "1/3  Building a toy task: a small repo, a bug, and a hidden test that proves it is fixed ...\n2/3  Running two free stand-in agents on it (no model, no network, $0) ...\n3/3  Results:\n\nContestant   Result  Time  Tokens  $ equiv\n-----------  ------  ----  ------  -------\nstub-solver  pass    0.1s   1,060  $0.0000\nstub-lazy    FAIL    0.1s   1,060  $0.0000\n\nFull report: results.html\nstub-solver copies the known fix and stub-lazy changes nothing: they test the pipeline, not any model. Run `agentbench start` to compare real agents on your own code.\nNext: agentbench doctor, then agentbench start",
        "expected": "stub-solver passes and stub-lazy fails",
        "input": "demo",
        "kind": "example",
        "outcome": "command completed successfully",
        "returncode": 0,
        "source": "README.md#Quickstart: three commands, no login, no cost",
        "verdict": "yes"
      }
    ],
    "status": "PASS"
  },
  "deviations": [
    "Initial venv creation failed because ensurepip was unavailable; installed python3.12-venv with sudo and retried successfully.",
    "Requested pinned git fetch failed: fatal: couldn't find remote ref ad01b757a0565c35fa590fe531964019363e70d."
  ],
  "fault_owner": null,
  "main_blocker": null,
  "operation": "agentbench demo",
  "operation_scope": "Installed from the checkout in a Python 3.12.3 virtual environment; free stand-in pipeline without model login.",
  "outcome": "working",
  "plain_failure": null,
  "steps": [
    "Created .venv after installing Ubuntu python3.12-venv and git.",
    "Ran the README install command: .venv/bin/python -m pip install .",
    "Ran .venv/bin/agentbench demo; stub-solver passed and stub-lazy failed as expected.",
    "Ran .venv/bin/agentbench doctor; core prerequisites are ready and real agent CLIs are optional for demo.",
    "Validated and replayed .coldpass/probe.json, claims, cycles and examples successfully."
  ],
  "stuck_step": null,
  "suggested_fix": null
}