{
  "run_id": "TayHCode--readtrial-claude-haiku-5-5-1792637142222214564",
  "date": "2026-10-22T02:50:08.507035+00:00",
  "repo": "TayHCode/readtrial",
  "kind": "repo",
  "source": "https://github.com/TayHCode/readtrial",
  "commit": "1662f23f8b0d88c1fe3d028265786f3f3b141171",
  "model": "claude-haiku-5-5",
  "model_version": "claude-haiku-5-5",
  "test_version": "readme-1924d8f529c6fc4500abb29916f5c9ac942027957e7b82d725d5610040cd3b4a",
  "pass": null,
  "outcome": "unverified",
  "time_to_working_s": null,
  "total_s": 266.2846088409424,
  "steps": [
    "cd C:\\coldpass\\workspace; Get-ChildItem -Force | Select-Object Name,Length; Write-Output '---'; & C:\\coldpass\\python\\python.exe --version; Write-Output '---'; Get-Content README.md -TotalCount 200",
    "cd C:\\coldpass\\workspace; git --version 2>&1; Write-Output '---'; Test-Path .git; Write-Output '---'; Get-ChildItem C:\\coldpass -Force | Select-Object Name",
    "cd C:\\coldpass\\workspace; $t = Get-Content README.md -Raw; $t.Length; ($t -split \"`n\") | Select-String -Pattern '^#' | ForEach-Object { $_.LineNumber.ToString() + ': ' + $_.Line.Trim() }; Write-Output '---'; Get-ChildItem C:\\coldpass\\workspace\\.coldpass -Force -ErrorAction SilentlyContinue | Select-Object Name; Write-Output '--- winget'; Get-Command winget -ErrorAction SilentlyContinue | Select-Object Source; Write-Output '--- network'; try { (Invoke-WebRequest -Uri https://github.com -UseBasicParsing -TimeoutSec 20).StatusCode } catch { $_.Exception.Message }",
    "$ErrorActionPreference='Stop'; $dest='C:\\coldpass\\tools\\git'; New-Item -ItemType Directory -Force -Path $dest | Out-Null; try { $rel = Invoke-RestMethod -Uri 'https://api.github.com/repos/git-for-windows/git/releases/latest' -TimeoutSec 60; $asset = $rel.assets | Where-Object { $_.name -match '^PortableGit-.*-64-bit\\.7z\\.exe$' } | Select-Object -First 1; $asset.browser_download_url; Invoke-WebRequest -Uri $asset.browser_download_url -OutFile \"$dest\\pg.7z.exe\" -UseBasicParsing -TimeoutSec 600; & \"$dest\\pg.7z.exe\" -y \"-o$dest\" | Out-Null; & \"$dest\\bin\\git.exe\" --version } catch { \"ERR: \" + $_.Exception.Message }",
    "$env:PATH = \"C:\\coldpass\\tools\\git\\cmd;C:\\coldpass\\tools\\git\\bin;$env:PATH\"; cd C:\\coldpass\\workspace; git init 2>&1; git remote add origin https://github.com/TayHCode/readtrial 2>&1; git fetch --depth 1 origin 1662f23f8b0d88c1fe3d028265786f3f3b141171 2>&1; git reset --mixed FETCH_HEAD 2>&1; git rev-parse HEAD; git status --short | Select-Object -First 20",
    "$g='C:\\coldpass\\tools\\git\\bin\\git.exe'; cd C:\\coldpass\\workspace; & $g init 2>&1; & $g remote add origin https://github.com/TayHCode/readtrial 2>&1; & $g fetch --depth 1 origin 1662f23f8b0d88c1fe3d028265786f3f3b141171 2>&1; & $g reset --mixed FETCH_HEAD 2>&1; & $g rev-parse HEAD; & $g status --short 2>&1 | Select-Object -First 20",
    "Get-ChildItem Env: | Where-Object { $_.Name -like 'GIT_*' } | ForEach-Object { $_.Name + '=' + $_.Value }; Write-Output '---'; $g='C:\\coldpass\\tools\\git\\bin\\git.exe'; Get-ChildItem Env: | Where-Object { $_.Name -like 'GIT_CONFIG*' } | ForEach-Object { Remove-Item ('Env:' + $_.Name) }; cd C:\\coldpass\\workspace; & $g init 2>&1 | Out-String; & $g remote add origin https://github.com/TayHCode/readtrial 2>&1 | Out-String; & $g fetch --depth 1 origin 1662f23f8b0d88c1fe3d028265786f3f3b141171 2>&1 | Out-String; & $g reset --mixed FETCH_HEAD 2>&1 | Out-String; & $g rev-parse HEAD 2>&1 | Out-String; & $g status --short 2>&1 | Out-String",
    "cd C:\\coldpass\\workspace; & C:\\coldpass\\python\\python.exe -m readtrial --help 2>&1 | Out-String; Write-Output \"rc=$LASTEXITCODE\"; Write-Output '--- demo'; & C:\\coldpass\\python\\python.exe -m readtrial demo --out trial-results\\demo 2>&1 | Out-String; Write-Output \"rc=$LASTEXITCODE\"; Get-ChildItem -Recurse trial-results | Select-Object FullName,Length",
    "cd C:\\coldpass\\workspace; Get-ChildItem -Recurse -File readtrial,scripts | Select-Object -ExpandProperty FullName | Measure-Object | Select-Object -ExpandProperty Count; Write-Output '--- grep'; Select-String -Path README.md,DEMO.md,readtrial\\*.py,readtrial\\**\\*.py -Pattern 'cron|schedul|webhook|--once|--now|interval|loop' -SimpleMatch:$false -ErrorAction SilentlyContinue | Select-Object -First 40 | ForEach-Object { $_.Path.Replace((Get-Location).Path,'') + ':' + $_.LineNumber + ': ' + $_.Line.Trim() }",
    "cd C:\\coldpass\\workspace; & C:\\coldpass\\python\\python.exe -m unittest discover -s tests -q 2>&1 | Out-String; Write-Output \"rc=$LASTEXITCODE\"",
    "cd C:\\coldpass\\workspace; Get-Content tests\\test_proof_integrity.py -TotalCount 50 | ForEach-Object { $_ }; Write-Output '---'; Select-String -Path README.md -Pattern 'unittest discover' | ForEach-Object { $_.LineNumber.ToString() + ': ' + $_.Line.Trim() }",
    "$env:Path = 'C:\\coldpass\\tools\\git\\bin;' + $env:Path; cd C:\\coldpass\\workspace; git --version; & C:\\coldpass\\python\\python.exe -m unittest discover -s tests -q 2>&1 | Out-String; Write-Output \"rc=$LASTEXITCODE\"",
    "Get-ChildItem Env: | Where-Object { $_.Name -like 'GIT_CONFIG*' } | ForEach-Object { Remove-Item ('Env:' + $_.Name) }; $env:Path = 'C:\\coldpass\\tools\\git\\bin;' + $env:Path; $env:GIT_CONFIG_NOSYSTEM='1'; cd C:\\coldpass\\workspace; & C:\\coldpass\\python\\python.exe -m unittest discover -s tests -q 2>&1 | Out-String; Write-Output \"rc=$LASTEXITCODE\"",
    "cd C:\\coldpass\\workspace; Remove-Item -Recurse -Force trial-results\\demo -ErrorAction SilentlyContinue; New-Item -ItemType Directory -Force -Path .coldpass | Out-Null; $t = [IO.File]::ReadAllText((Join-Path (Get-Location) 'README.md')); foreach ($q in @('The demo finishes in under 20 seconds and writes real sample reports and a diff;','py -3 -m readtrial demo --out trial-results\\demo','py -3 -m unittest discover -s tests -q','For isolated trials on Windows, create a disposable Linux VM and follow','A first real trial also requires a supported target and an authenticated agent CLI.')) { $q + ' => ' + $t.Contains($q) }; Get-ChildItem .coldpass -Force | Select-Object Name",
    "cd C:\\coldpass\\workspace\\.coldpass; $enc = New-Object System.Text.UTF8Encoding($false); $py = 'C:\\\\coldpass\\\\python\\\\python.exe'; $ws = 'C:\\\\coldpass\\\\workspace'\n$probe = @\"\n{\"kind\":\"cli\",\"argv\":[\"$py\",\"-m\",\"readtrial\",\"demo\",\"--out\",\"trial-results\\\\probe-demo\"],\"cwd\":\"$ws\",\"expected_text\":\"After: PASS (README step exit 0; declared check passed)\"}\n\"@\n$claims = @\"\n[\n{\"kind\":\"claim\",\"claim\":\"The demo finishes in under 20 seconds and writes real sample reports and a diff.\",\"source\":\"The demo finishes in under 20 seconds and writes real sample reports and a diff;\",\"input\":\"offline demo with --out trial-results\\\\claim-demo-diff\",\"expected\":\"diff.json reports resolved findings and evidence folders are written\",\"probe_kind\":\"cli\",\"argv\":[\"$py\",\"-m\",\"readtrial\",\"demo\",\"--out\",\"trial-results\\\\claim-demo-diff\"],\"expected_text\":\"diff.json: 1 resolved finding; evidence in before/ and after/.\",\"cwd\":\"$ws\"},\n{\"kind\":\"claim\",\"claim\":\"The Windows PowerShell demo command runs the offline FAIL then PASS loop.\",\"source\":\"py -3 -m readtrial demo --out trial-results\\demo\",\"input\":\"py -3 -m readtrial demo with a fresh --out folder (absolute Python used in place of py -3)\",\"expected\":\"Before run reports FAIL and after run reports PASS\",\"probe_kind\":\"cli\",\"argv\":[\"$py\",\"-m\",\"readtrial\",\"demo\",\"--out\",\"trial-results\\\\claim-windows-cmd\"],\"expected_text\":\"Before: FAIL (README step exit 3; declared check failed)\",\"cwd\":\"$ws\"},\n{\"kind\":\"claim\",\"claim\":\"Isolated trials on Windows require a disposable Linux VM; they cannot run on this Windows guest.\",\"source\":\"For isolated trials on Windows, create a disposable Linux VM and follow\",\"testable\":false,\"reason\":\"Isolated trials are POSIX-only with LXC/LXD; this guest is Windows and no Linux controller with LXD was available through coldpass.exec, so the isolated trial was not run.\"},\n{\"kind\":\"claim\",\"claim\":\"A first real trial also requires a supported target and an authenticated agent CLI.\",\"source\":\"A first real trial also requires a supported target and an authenticated agent CLI.\",\"testable\":false,\"reason\":\"A real trial needs a Linux controller with LXD storage and an authenticated Claude CLI; not available in this Windows guest, and no credentials were provided or obtained.\"}\n]\n\"@\n$examples = @\"\n[\n{\"kind\":\"example\",\"claim\":\"Unit suite runs offline on Windows; POSIX-only tests are skipped\",\"source\":\"README.md: Windows PowerShell (py -3 -m unittest discover -s tests -q)\",\"input\":\"python -m unittest discover -s tests -q\",\"expected\":\"OK with skipped POSIX tests\",\"argv\":[\"$py\",\"-m\",\"unittest\",\"discover\",\"-s\",\"tests\",\"-q\"],\"cwd\":\"$ws\",\"env\":{\"GIT_CONFIG_COUNT\":\"0\",\"GIT_CONFIG_NOSYSTEM\":\"1\",\"PATH\":\"C:\\\\coldpass\\\\tools\\\\git\\\\bin;C:\\\\Windows\\\\System32;C:\\\\Windows\"},\"expected_text\":\"OK (skipped=138)\"},\n{\"kind\":\"example\",\"claim\":\"Offline demo from the Windows quickstart writes a before/after evidence folder\",\"source\":\"README.md: Windows PowerShell (py -3 -m readtrial demo --out trial-results\\demo)\",\"input\":\"demo --out trial-results\\\\example-demo\",\"expected\":\"Before FAIL, after PASS, diff written\",\"argv\":[\"$py\",\"-m\",\"readtrial\",\"demo\",\"--out\",\"trial-results\\\\example-demo\"],\"cwd\":\"$ws\",\"expected_text\":\"After: PASS (README step exit 0; declared check passed)\"}\n]\n\"@\n$cycles = @\"\n{\"detected\":true,\"checks\":[{\"claim\":\"The demo runs one FAIL then PASS learning loop per invocation\",\"source\":\"readtrial/demo.py\",\"quote\":\"Offline learning loop with fake targets and agents; no subprocesses or network.\",\"schedule\":\"no timer; manual one-shot trigger of the demo command\",\"method\":\"run-once\",\"input\":\"demo --out trial-results\\\\cycle-demo\",\"expected\":\"Before run FAILs, After run PASSes, diff written\",\"kind\":\"cli\",\"argv\":[\"$py\",\"-m\",\"readtrial\",\"demo\",\"--out\",\"trial-results\\\\cycle-demo\"],\"cwd\":\"$ws\",\"expected_text\":\"After: PASS (README step exit 0; declared check passed)\"}]}\n\"@\n[IO.File]::WriteAllText(\"$PWD\\probe.json\", $probe.Trim(), $enc)\n[IO.File]::WriteAllText(\"$PWD\\claims.json\", $claims.Trim(), $enc)\n[IO.File]::WriteAllText(\"$PWD\\examples.json\", $examples.Trim(), $enc)\n[IO.File]::WriteAllText(\"$PWD\\cycles.json\", $cycles.Trim(), $enc)\nforeach ($f in 'probe.json','claims.json','examples.json','cycles.json') { \"== $f\"; Get-Content $f -Raw | ForEach-Object { $_ } ; & C:\\coldpass\\python\\python.exe -c \"import json,sys; json.load(open(sys.argv[1], encoding='utf-8')); print('valid json')\" $f }",
    "cd C:\\coldpass\\workspace\\.coldpass; $enc = New-Object System.Text.UTF8Encoding($false); foreach ($f in 'claims.json','examples.json') { $s = [IO.File]::ReadAllText(\"$PWD\\$f\"); $s = $s.Replace('trial-results\\demo','trial-results\\\\demo'); [IO.File]::WriteAllText(\"$PWD\\$f\", $s, $enc) }; foreach ($f in 'probe.json','claims.json','examples.json','cycles.json') { & C:\\coldpass\\python\\python.exe -c \"import json,sys; d=json.load(open(sys.argv[1], encoding='utf-8')); print(sys.argv[1], 'valid', type(d).__name__, len(d) if isinstance(d,list) else '')\" $f }; $r = @'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run readtrial's documented offline demo (FAIL then PASS learning loop) and its documented unit-test suite on Windows, using the README's Windows PowerShell commands with the absolute Python path\",\"operation_scope\":\"Windows guest, Python 3.14 at C:\\\\coldpass\\\\python, Git 2.56 portable installed user-local. Covers the offline demo and the unit suite only (138 POSIX-only tests skipped). Isolated LXC trials (run, verify, doctor, setup-linux) are POSIX-only and were not run; they need a Linux controller with LXD and an authenticated Claude CLI.\",\"steps\":[\"git init; git remote add origin https://github.com/TayHCode/readtrial; git fetch --depth 1 origin 1662f23f8b0d88c1fe3d028265786f3f3b141171; git reset --mixed FETCH_HEAD\",\"py -3 -m readtrial --help (run as C:\\\\coldpass\\\\python\\\\python.exe -m readtrial --help)\",\"py -3 -m readtrial demo --out trial-results\\\\demo (run as C:\\\\coldpass\\\\python\\\\python.exe -m readtrial demo --out <fresh folder>)\",\"py -3 -m unittest discover -s tests -q (run as C:\\\\coldpass\\\\python\\\\python.exe -m unittest discover -s tests -q)\"],\"deviations\":[\"Git was not installed in the guest. Installed PortableGit 2.56.0.2 (64-bit) user-local to C:\\\\coldpass\\\\tools\\\\git from the git-for-windows GitHub release; no admin install.\",\"The inherited environment set GIT_CONFIG_COUNT=4 with only three GIT_CONFIG_VALUE_* entries, so git failed with 'missing config value GIT_CONFIG_VALUE_3'. Cleared GIT_CONFIG_* in the shell; the example env sets GIT_CONFIG_COUNT=0 for replay.\",\"Git was not on PATH for the first unit-suite run, which caused one setUp error in tests/test_proof_integrity.py; fixed by prepending the Git bin folder to PATH. Final suite: Ran 399 tests, OK (skipped=138), rc=0.\",\"README 'py -3' launcher replaced with absolute C:\\\\coldpass\\\\python\\\\python.exe; same module and arguments.\",\"Isolated trial path (readtrial run/verify/doctor) not exercised: README says isolated trials are POSIX only and need a Linux controller with LXD; not available in this Windows guest.\",\"No product scheduler, cron, webhook or --once/--now entry point exists; the only loop is the one-shot demo, which is used as the cycle check.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\n'@; [IO.File]::WriteAllText(\"$PWD\\report.json\", $r.Trim(), $enc); & C:\\coldpass\\python\\python.exe -c \"import json,sys; json.load(open(sys.argv[1], encoding='utf-8')); print('report valid')\" report.json",
    "$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; cd C:\\coldpass\\workspace; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | Out-String; Write-Output \"rc=$LASTEXITCODE\"",
    "Select-String -Path C:\\coldpass\\checker\\check.py -Pattern '\"working\"|working\\s*=' | Select-Object -First 15 | ForEach-Object { $_.LineNumber.ToString() + ': ' + $_.Line.Trim() }",
    "$l = Get-Content C:\\coldpass\\checker\\check.py; foreach ($range in @(@(736,746),@(812,834),@(1168,1190))) { Write-Output ('--- ' + $range[0]); for ($i=$range[0]; $i -le $range[1]; $i++) { '{0}: {1}' -f $i, $l[$i-1] } }",
    "cd C:\\coldpass\\workspace\\.coldpass; $enc = New-Object System.Text.UTF8Encoding($false); $p = \"$PWD\\report.json\"; $r = Get-Content $p -Raw | ConvertFrom-Json; $r.deviations += \"Checker replay reports evidence_strength 'partly_checked' and records the CLI probe with working=false (checker rule for cli probes, check.py line 822). The product is a CLI with no MCP or HTTP surface, so a CLI probe is the only applicable kind; the demo output and both README claims were verified by replay with verdict yes.\"; $json = $r | ConvertTo-Json -Depth 10 -Compress; [IO.File]::WriteAllText($p, $json, $enc); & C:\\coldpass\\python\\python.exe -c \"import json,sys; d=json.load(open(sys.argv[1], encoding='utf-8')); print('report valid', d['outcome'], len(d['deviations']))\" report.json; cd C:\\coldpass\\workspace; $env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | Out-String | ForEach-Object { $_.Substring(0, [Math]::Min(400, $_.Length)) }; Write-Output \"rc=$LASTEXITCODE\""
  ],
  "stuck_step": "'C:\\coldpass\\python\\python.exe' -m readtrial demo --out 'trial-results\\probe-demo-checker-f3fad4ab84b2494694b235dae29d0db5'",
  "error_excerpt": "The saved checks do not fully confirm documented product behavior.",
  "what_it_did": "Run readtrial's documented offline demo (FAIL then PASS learning loop) and its documented unit-test suite on Windows, using the README's Windows PowerShell commands with the absolute Python path",
  "suggested_fix": "Keep the partial evidence and check the documented behavior with real input and expected output.",
  "tokens_in": 650792,
  "tokens_out": 21332,
  "cost_usd": 0.027822839999999998,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": false,
        "argv": [
          "C:\\coldpass\\python\\python.exe",
          "-m",
          "readtrial",
          "demo",
          "--out",
          "trial-results\\probe-demo-checker-f3fad4ab84b2494694b235dae29d0db5"
        ],
        "kind": "cli",
        "returncode": 0,
        "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]",
        "stderr": "",
        "needs_credentials": false,
        "needs_browser": false,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "No problems traced to this repository code in these checks.",
    "findings": [],
    "context": [],
    "limitations": [
      "A short run cannot establish that code is safe.",
      "Connections show IP addresses; proxies can hide the final hostname.",
      "Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing.",
      "windows behavior observation needs an OS-native file/network/process collector; only the static scan ran.",
      "No Linux syscall trace was collected."
    ],
    "static": {
      "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check."
    },
    "evidence_url": "/safety/?run=TayHCode--readtrial-claude-haiku-5-5-1792637142222214564",
    "evidence_file": "/data/safety/TayHCode--readtrial-claude-haiku-5-5-1792637142222214564.json.gz"
  },
  "agent_execution": "native_agent",
  "agent_runtime": "claude-code",
  "agent_runtime_version": "2.1.300 (Claude Code)",
  "tool_transport": "mcp-assigned-vm",
  "platform": "windows",
  "reasoning": "low",
  "service_tier": null,
  "resources": {
    "cpus": 2,
    "memory_mib": 4096,
    "disk_mib": 32768
  },
  "native_tool_calls": 20,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "windows"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "1662f23f8b0d88c1fe3d028265786f3f3b141171",
    "url": "https://github.com/TayHCode/readtrial"
  },
  "purpose": "initial",
  "profile": {
    "model": "claude-haiku-5-5",
    "reasoning": "low"
  },
  "fault": {
    "owner": "unknown",
    "status": "pending",
    "reason": "The saved checks do not fully confirm documented product behavior."
  },
  "fix_id": null,
  "verifies_run_id": null,
  "hosting": null,
  "operation_scope": "product operation",
  "tool_calls": 20,
  "guest_setup": null,
  "runtime": null,
  "runtime_version": null,
  "runtime_revision": null,
  "source_revision": null,
  "evidence_version": null,
  "failure_origin": null,
  "evidence_strength": "partly_checked",
  "works": "untested",
  "install_s": null,
  "first_use_s": null,
  "mcp": "none",
  "needs": [],
  "needs_which": null,
  "agent_interface": [
    "cli"
  ],
  "license": "MIT",
  "repo_url": "https://github.com/TayHCode/readtrial",
  "cost_to_try": null,
  "hardware": null,
  "what_failed": "The saved checks do not fully confirm documented product behavior.",
  "local_or_hosted": "local",
  "cycle_checks": [
    {
      "kind": "cycle",
      "claim": "The demo runs one FAIL then PASS learning loop per invocation",
      "source": "readtrial/demo.py",
      "input": "demo --out trial-results\\cycle-demo",
      "expected": "Before run FAILs, After run PASSes, diff written",
      "command": "'C:\\coldpass\\python\\python.exe' -m readtrial demo --out 'trial-results\\cycle-demo-checker-1d851aef0da0462d9efd439a29e58b8d'",
      "schedule": "no timer; manual one-shot trigger of the demo command",
      "method": "run-once",
      "verdict": "yes",
      "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/.",
      "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/.",
      "returncode": 0
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "The demo finishes in under 20 seconds and writes real sample reports and a diff.",
      "source": "The demo finishes in under 20 seconds and writes real sample reports and a diff;",
      "input": "offline demo with --out trial-results\\claim-demo-diff",
      "expected": "diff.json reports resolved findings and evidence folders are written",
      "command": "'C:\\coldpass\\python\\python.exe' -m readtrial demo --out 'trial-results\\claim-demo-diff-checker-86e5f0e7f00f42d6b6f0f7618efd6db8'",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: diff.json: 1 resolved finding; evidence in before/ and after/.",
      "evidence": "diff.json: 1 resolved finding; evidence in before/ and after/.\r\n",
      "returncode": 0,
      "source_checked": true,
      "source_file": "README.md"
    },
    {
      "kind": "claim",
      "claim": "The Windows PowerShell demo command runs the offline FAIL then PASS loop.",
      "source": "py -3 -m readtrial demo --out trial-results\\demo",
      "input": "py -3 -m readtrial demo with a fresh --out folder (absolute Python used in place of py -3)",
      "expected": "Before run reports FAIL and after run reports PASS",
      "command": "'C:\\coldpass\\python\\python.exe' -m readtrial demo --out 'trial-results\\claim-windows-cmd-checker-73976f621b2444aeb58897560035e621'",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: Before: FAIL (README step exit 3; declared check failed)",
      "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",
      "returncode": 0,
      "source_checked": true,
      "source_file": "README.md"
    },
    {
      "kind": "claim",
      "claim": "Isolated trials on Windows require a disposable Linux VM; they cannot run on this Windows guest.",
      "source": "For isolated trials on Windows, create a disposable Linux VM and follow",
      "input": "",
      "expected": "",
      "command": "",
      "verdict": "blocked",
      "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.",
      "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.",
      "source_checked": true,
      "source_file": "README.md"
    },
    {
      "kind": "claim",
      "claim": "A first real trial also requires a supported target and an authenticated agent CLI.",
      "source": "A first real trial also requires a supported target and an authenticated agent CLI.",
      "input": "",
      "expected": "",
      "command": "",
      "verdict": "blocked",
      "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.",
      "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.",
      "source_checked": true,
      "source_file": "README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Unit suite runs offline on Windows; POSIX-only tests are skipped",
      "source": "README.md: Windows PowerShell (py -3 -m unittest discover -s tests -q)",
      "input": "python -m unittest discover -s tests -q",
      "command": "'C:\\coldpass\\python\\python.exe' -m unittest discover -s tests -q",
      "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)",
      "deferred": false,
      "expected": "OK with skipped POSIX tests",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    },
    {
      "kind": "example",
      "claim": "Offline demo from the Windows quickstart writes a before/after evidence folder",
      "source": "README.md: Windows PowerShell (py -3 -m readtrial demo --out trial-results\\demo)",
      "input": "demo --out trial-results\\example-demo",
      "command": "'C:\\coldpass\\python\\python.exe' -m readtrial demo --out 'trial-results\\example-demo-checker-2df444435f4c4777943978077318066c'",
      "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/.",
      "deferred": false,
      "expected": "Before FAIL, after PASS, diff written",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    }
  ],
  "does_what_it_says": "partly",
  "maintenance": {
    "archived": false,
    "commits_90d": 7,
    "last_commit_at": "2026-10-17T18:01:24Z",
    "last_release_at": null,
    "median_reply_hours": null,
    "merged_prs_90d": 3,
    "note": "actively maintained: last commit 4 days ago; 7 commits and 3 merged PRs in 90 days; 0 open issues, 1 open PRs; no releases",
    "open_issues": 0,
    "open_prs": 1,
    "reply_share": null,
    "reply_threads": 0,
    "verdict": "maintained"
  },
  "maintenance_verdict": "maintained",
  "maintenance_note": "actively maintained: last commit 4 days ago; 7 commits and 3 merged PRs in 90 days; 0 open issues, 1 open PRs; no releases",
  "maintained": "active",
  "maintained_note": "last commit 0 days ago",
  "last_commit_at": "2026-10-22T02:16:13Z",
  "last_release_at": null,
  "open_issues": null,
  "answered_issues": null,
  "platforms_claimed": [
    "linux",
    "mac",
    "windows"
  ],
  "topic": "agent-harness",
  "agent_interfaces": [
    {
      "interface": "cli",
      "evidence": "independent checker",
      "observed": true,
      "operation_checked": false
    }
  ],
  "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.",
  "mcp_context": null,
  "tested_at": "2026-10-22T02:50:08.507035+00:00",
  "tested_commit": "1662f23f8b0d88c1fe3d028265786f3f3b141171",
  "tested_with": {
    "agent": "claude-code",
    "agent_version": "2.1.300 (Claude Code)",
    "model": "claude-haiku-5-5",
    "model_route": "claude-haiku-5-5",
    "reasoning": "low",
    "os": "windows",
    "backend": "hyperv",
    "transport": "mcp-assigned-vm"
  },
  "setup_identity": {
    "repo": "TayHCode/readtrial",
    "source": "https://github.com/TayHCode/readtrial",
    "commit": "1662f23f8b0d88c1fe3d028265786f3f3b141171",
    "source_revision": null,
    "os": "windows",
    "architecture": null,
    "backend": "hyperv",
    "model": "claude-haiku-5-5",
    "model_version": "claude-haiku-5-5",
    "agent_execution": "native_agent",
    "agent_runtime": "claude-code",
    "agent_runtime_version": "2.1.300 (Claude Code)",
    "tool_transport": "mcp-assigned-vm",
    "runtime": null,
    "runtime_version": null,
    "runtime_revision": null,
    "sandbox_source": null,
    "guest_setup": null,
    "source_pin": {
      "commit": "1662f23f8b0d88c1fe3d028265786f3f3b141171",
      "url": "https://github.com/TayHCode/readtrial"
    },
    "platform_details": {
      "os": "windows",
      "backend": "hyperv"
    },
    "platform_conflicts": null,
    "reasoning": "low",
    "service_tier": null,
    "resources": {
      "cpus": 2,
      "memory_mib": 4096,
      "disk_mib": 32768
    },
    "operation": "Run readtrial's documented offline demo (FAIL then PASS learning loop) and its documented unit-test suite on Windows, using the README's Windows PowerShell commands with the absolute Python path",
    "operation_scope": "product operation",
    "hosting": null,
    "kind": "repo",
    "test_version": "readme-1924d8f529c6fc4500abb29916f5c9ac942027957e7b82d725d5610040cd3b4a",
    "evidence_version": null
  },
  "other_model": null,
  "other_run_id": null,
  "models_agree": null,
  "furthest_model": null,
  "transcript_url": "/transcripts/TayHCode--readtrial-claude-haiku-5-5-1792637142222214564.txt",
  "report_url": "/reports/TayHCode--readtrial-claude-haiku-5-5-1792637142222214564.json"
}