{
  "run_id": "TayHCode--readtrial-claude-haiku-5-5-1792637142222214564",
  "checker": {
    "claims": [
      {
        "claim": "The demo finishes in under 20 seconds and writes real sample reports and a diff.",
        "command": "'C:\\coldpass\\python\\python.exe' -m readtrial demo --out 'trial-results\\claim-demo-diff-checker-86e5f0e7f00f42d6b6f0f7618efd6db8'",
        "evidence": "diff.json: 1 resolved finding; evidence in before/ and after/.\r\n",
        "expected": "diff.json reports resolved findings and evidence folders are written",
        "input": "offline demo with --out trial-results\\claim-demo-diff",
        "kind": "claim",
        "outcome": "Real input produced the expected result: diff.json: 1 resolved finding; evidence in before/ and after/.",
        "returncode": 0,
        "source": "The demo finishes in under 20 seconds and writes real sample reports and a diff;",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      },
      {
        "claim": "The Windows PowerShell demo command runs the offline FAIL then PASS loop.",
        "command": "'C:\\coldpass\\python\\python.exe' -m readtrial demo --out 'trial-results\\claim-windows-cmd-checker-73976f621b2444aeb58897560035e621'",
        "evidence": "Before: FAIL (README step exit 3; declared check failed)\r\nAfter: PASS (README step exit 0; declared check passed)\r\ndiff.json: 1 resolved finding; evidence in before/ and after/.\r\n",
        "expected": "Before run reports FAIL and after run reports PASS",
        "input": "py -3 -m readtrial demo with a fresh --out folder (absolute Python used in place of py -3)",
        "kind": "claim",
        "outcome": "Real input produced the expected result: Before: FAIL (README step exit 3; declared check failed)",
        "returncode": 0,
        "source": "py -3 -m readtrial demo --out trial-results\\demo",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      },
      {
        "claim": "Isolated trials on Windows require a disposable Linux VM; they cannot run on this Windows guest.",
        "command": "",
        "evidence": "Isolated trials are POSIX-only with LXC/LXD; this guest is Windows and no Linux controller with LXD was available through coldpass.exec, so the isolated trial was not run.",
        "expected": "",
        "input": "",
        "kind": "claim",
        "outcome": "Isolated trials are POSIX-only with LXC/LXD; this guest is Windows and no Linux controller with LXD was available through coldpass.exec, so the isolated trial was not run.",
        "source": "For isolated trials on Windows, create a disposable Linux VM and follow",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "blocked"
      },
      {
        "claim": "A first real trial also requires a supported target and an authenticated agent CLI.",
        "command": "",
        "evidence": "A real trial needs a Linux controller with LXD storage and an authenticated Claude CLI; not available in this Windows guest, and no credentials were provided or obtained.",
        "expected": "",
        "input": "",
        "kind": "claim",
        "outcome": "A real trial needs a Linux controller with LXD storage and an authenticated Claude CLI; not available in this Windows guest, and no credentials were provided or obtained.",
        "source": "A first real trial also requires a supported target and an authenticated agent CLI.",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "blocked"
      }
    ],
    "cycle_checks": [
      {
        "claim": "The demo runs one FAIL then PASS learning loop per invocation",
        "command": "'C:\\coldpass\\python\\python.exe' -m readtrial demo --out 'trial-results\\cycle-demo-checker-1d851aef0da0462d9efd439a29e58b8d'",
        "evidence": "OFFLINE DEMO: fake agent and fake target; no model, SSH, LXC or repository execution.\r\nBefore: FAIL (README step exit 3; declared check failed)\r\nAfter: PASS (README step exit 0; declared check passed)\r\ndiff.json: 1 resolved finding; evidence in before/ and after/.",
        "expected": "Before run FAILs, After run PASSes, diff written",
        "input": "demo --out trial-results\\cycle-demo",
        "kind": "cycle",
        "method": "run-once",
        "outcome": "Triggered one cycle by hand (run-once; normal trigger: no timer; manual one-shot trigger of the demo command): OFFLINE DEMO: fake agent and fake target; no model, SSH, LXC or repository execution.\r\nBefore: FAIL (README step exit 3; declared check failed)\r\nAfter: PASS (README step exit 0; declared check passed)\r\ndiff.json: 1 resolved finding; evidence in before/ and after/.",
        "returncode": 0,
        "schedule": "no timer; manual one-shot trigger of the demo command",
        "source": "readtrial/demo.py",
        "verdict": "yes"
      }
    ],
    "details": {
      "argv": [
        "C:\\coldpass\\python\\python.exe",
        "-m",
        "readtrial",
        "demo",
        "--out",
        "trial-results\\probe-demo-checker-f3fad4ab84b2494694b235dae29d0db5"
      ],
      "kind": "cli",
      "needs_browser": false,
      "needs_credentials": false,
      "returncode": 0,
      "scope": "product operation",
      "stderr": "",
      "stdout": "OFFLINE DEMO: fake agent and fake target; no model, SSH, LXC or repository execution.\nBefore: FAIL (README step exit 3; declared check failed)\nAfter: PASS (README step exit 0; declared check passed)\ndiff.json: 1 resolved finding; evidence in before/ and after/.\n[excerpt truncated]",
      "working": false
    },
    "evidence_strength": "partly_checked",
    "example_checks": [
      {
        "claim": "Unit suite runs offline on Windows; POSIX-only tests are skipped",
        "command": "'C:\\coldpass\\python\\python.exe' -m unittest discover -s tests -q",
        "deferred": false,
        "evidence": "ssh:example: AGENT deviation: ignored added cd; selected the exact README command from the clone root: py -3 hello.py --name Check\r\nC:\\coldpass\\workspace\\.scratch\\tmp5oryig8t\\out\\verify.json\r\nRecorded 0 requirements; Factory decides gate passage.\r\nreadtrial: previous run is incompatible or did not fetch source successfully\r\nreadtrial: --out must be a new folder beneath job.evidence_dir\r\nreadtrial: model and source hash overrides must match the supplied job\r\n----------------------------------------------------------------------\r\nRan 399 tests in 0.652s\r\n\r\nOK (skipped=138)",
        "expected": "OK with skipped POSIX tests",
        "input": "python -m unittest discover -s tests -q",
        "kind": "example",
        "outcome": "command completed successfully",
        "returncode": 0,
        "source": "README.md: Windows PowerShell (py -3 -m unittest discover -s tests -q)",
        "verdict": "yes"
      },
      {
        "claim": "Offline demo from the Windows quickstart writes a before/after evidence folder",
        "command": "'C:\\coldpass\\python\\python.exe' -m readtrial demo --out 'trial-results\\example-demo-checker-2df444435f4c4777943978077318066c'",
        "deferred": false,
        "evidence": "OFFLINE DEMO: fake agent and fake target; no model, SSH, LXC or repository execution.\r\nBefore: FAIL (README step exit 3; declared check failed)\r\nAfter: PASS (README step exit 0; declared check passed)\r\ndiff.json: 1 resolved finding; evidence in before/ and after/.",
        "expected": "Before FAIL, after PASS, diff written",
        "input": "demo --out trial-results\\example-demo",
        "kind": "example",
        "outcome": "command completed successfully",
        "returncode": 0,
        "source": "README.md: Windows PowerShell (py -3 -m readtrial demo --out trial-results\\demo)",
        "verdict": "yes"
      }
    ],
    "status": "PASS"
  },
  "diagnosis": null
}