{ "run_id": "TayHCode--sysone-cpu-claude-haiku-5-5-1792649286403655136", "date": "2026-10-22T06:24:38.927983+00:00", "repo": "TayHCode/sysone-cpu", "kind": "repo", "source": "https://github.com/TayHCode/sysone-cpu", "commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-1924d8f529c6fc4500abb29916f5c9ac942027957e7b82d725d5610040cd3b4a", "pass": true, "outcome": "pass", "time_to_working_s": 913.9999509740155, "total_s": 992.5243020057678, "steps": [ "cd C:\\coldpass\\workspace; Get-ChildItem -Force | Select-Object Name,Length | Format-Table; Get-Content README.md -TotalCount 200; & C:\\coldpass\\python\\python.exe --version", "cd C:\\coldpass\\workspace; git --version; Get-ChildItem -Force -Recurse -Depth 2 | Select-Object FullName | Format-Table -HideTableHeaders | Out-String -Width 300", "cd C:\\coldpass\\workspace; Get-Command uv -ErrorAction SilentlyContinue | Format-List Source; if (Test-Path \"$env:USERPROFILE\\.local\\bin\\uv.exe\") {\"user uv present\"}; Get-Content docs\\setup.md -Raw | Select-Object -First 1 | Out-Null; Select-String -Path docs\\setup.md -Pattern 'uv|install|Execution|powershell' | ForEach-Object { $_.Line } | Select-Object -First 60; Get-ChildItem .coldpass -Force | Select-Object Name", "cd C:\\coldpass\\workspace; New-Item -ItemType Directory -Force .scratch,.tools,.cache | Out-Null; $env:TEMP = \"$PWD\\.scratch\"; $env:TMP = \"$PWD\\.scratch\"; $env:UV_PYTHON_PREFERENCE = \"only-managed\"; $env:UV_CACHE_DIR = \"$PWD\\.cache\\uv\"; $env:UV_PYTHON_INSTALL_DIR = \"$PWD\\.tools\\python\"; $env:HF_HOME = \"$PWD\\.cache\\huggingface\"; $env:UV_INSTALL_DIR = \"$PWD\\.tools\"; $env:UV_NO_MODIFY_PATH = \"1\"; $env:NODE_USE_ENV_PROXY=\"1\"; Invoke-WebRequest https://astral.sh/uv/install.ps1 -OutFile .scratch/install-uv.ps1; powershell -NoProfile -ExecutionPolicy Bypass -File .scratch\\install-uv.ps1; & .\\.tools\\uv.exe --version", "cd C:\\coldpass\\workspace; $env:TEMP = \"$PWD\\.scratch\"; $env:TMP = \"$PWD\\.scratch\"; $env:UV_PYTHON_PREFERENCE = \"only-managed\"; $env:UV_CACHE_DIR = \"$PWD\\.cache\\uv\"; $env:UV_PYTHON_INSTALL_DIR = \"$PWD\\.tools\\python\"; $env:HF_HOME = \"$PWD\\.cache\\huggingface\"; $env:UV_INSTALL_DIR = \"$PWD\\.tools\"; $env:UV_NO_MODIFY_PATH = \"1\"; $env:NODE_USE_ENV_PROXY=\"1\"; if (!(Test-Path .scratch\\install-uv.ps1)) { Invoke-WebRequest https://astral.sh/uv/install.ps1 -OutFile .scratch\\install-uv.ps1 }; & \"$PSHOME\\powershell.exe\" -NoProfile -ExecutionPolicy Bypass -File .scratch\\install-uv.ps1; & .\\.tools\\uv.exe --version", "cd C:\\coldpass\\workspace; $env:TEMP = \"$PWD\\.scratch\"; $env:TMP = \"$PWD\\.scratch\"; $env:UV_PYTHON_PREFERENCE = \"only-managed\"; $env:UV_CACHE_DIR = \"$PWD\\.cache\\uv\"; $env:UV_PYTHON_INSTALL_DIR = \"$PWD\\.tools\\python\"; $env:HF_HOME = \"$PWD\\.cache\\huggingface\"; $uv = \"$PWD\\.tools\\uv.exe\"; & $uv venv --python 3.12; if ($LASTEXITCODE -ne 0) { \"VENV FAILED $LASTEXITCODE\" } else { & $uv pip install --python .venv --only-binary :all: torch==2.14.0 --index-url https://download.pytorch.org/whl/cpu; \"torch exit $LASTEXITCODE\" }", "cd C:\\coldpass\\workspace; $env:TEMP = \"$PWD\\.scratch\"; $env:TMP = \"$PWD\\.scratch\"; $env:UV_PYTHON_PREFERENCE = \"only-managed\"; $env:UV_CACHE_DIR = \"$PWD\\.cache\\uv\"; $env:UV_PYTHON_INSTALL_DIR = \"$PWD\\.tools\\python\"; $env:HF_HOME = \"$PWD\\.cache\\huggingface\"; $uv = \"$PWD\\.tools\\uv.exe\"; & $uv pip install --python .venv --only-binary :all: laya==0.3.4 transformers==5.17.0 tokenizers==0.23.3 safetensors==0.8.0 huggingface_hub==1.32.0 numpy==2.5.3 psutil==7.2.2 2>&1 | Select-Object -Last 15; \"exit $LASTEXITCODE\"", "cd C:\\coldpass\\workspace; $env:TEMP = \"$PWD\\.scratch\"; $env:TMP = \"$PWD\\.scratch\"; $env:UV_PYTHON_PREFERENCE = \"only-managed\"; $env:UV_CACHE_DIR = \"$PWD\\.cache\\uv\"; $env:UV_PYTHON_INSTALL_DIR = \"$PWD\\.tools\\python\"; $env:HF_HOME = \"$PWD\\.cache\\huggingface\"; $env:NODE_USE_ENV_PROXY=\"1\"; $uv = \"$PWD\\.tools\\uv.exe\"; & $uv run --no-project --python .venv python scripts/download_model.py 2>&1 | Select-Object -Last 30; \"exit $LASTEXITCODE\"; Get-ChildItem -Recurse .cache\\model | Select-Object FullName,Length | Format-Table -AutoSize | Out-String -Width 250", "cd C:\\coldpass\\workspace; $env:TEMP = \"$PWD\\.scratch\"; $env:TMP = \"$PWD\\.scratch\"; $env:UV_PYTHON_PREFERENCE = \"only-managed\"; $env:UV_CACHE_DIR = \"$PWD\\.cache\\uv\"; $env:UV_PYTHON_INSTALL_DIR = \"$PWD\\.tools\\python\"; $env:HF_HOME = \"$PWD\\.cache\\huggingface\"; $uv = \"$PWD\\.tools\\uv.exe\"; Test-Path .cache\\first-run.json; & $uv run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/first-run.json 2>&1 | Select-Object -Last 30; \"exit $LASTEXITCODE\"; if (Test-Path .cache\\first-run.json) { Get-Content .cache\\first-run.json -Raw | Select-Object -First 1 | ForEach-Object { $_.Substring(0,[Math]::Min(1500,$_.Length)) } }", "Get-ChildItem C:\\Windows\\System32\\vcruntime140*.dll,C:\\Windows\\System32\\msvcp140*.dll -ErrorAction SilentlyContinue | Select-Object Name | Format-Table -HideTableHeaders | Out-String; ([Security.Principal.WindowsPrincipal][Security.Principal.WindowsIdentity]::GetCurrent()).IsInRole([Security.Principal.WindowsBuiltInRole]::Administrator); whoami", "cd C:\\coldpass\\workspace; $ErrorActionPreference=\"Continue\"; Invoke-WebRequest https://aka.ms/vs/17/release/vc_redist.x64.exe -OutFile .scratch\\vc_redist.x64.exe; \"download exit $LASTEXITCODE\"; $p = Start-Process -FilePath \"$PWD\\.scratch\\vc_redist.x64.exe\" -ArgumentList \"/install\",\"/quiet\",\"/norestart\" -Wait -PassThru; \"vc install exit $($p.ExitCode)\"; Test-Path C:\\Windows\\System32\\vcruntime140.dll", "cd C:\\coldpass\\workspace; $ErrorActionPreference=\"Continue\"; Get-ChildItem .scratch | Select-Object Name,Length | Format-Table -HideTableHeaders | Out-String; try { Invoke-WebRequest https://aka.ms/vs/17/release/vc_redist.x64.exe -OutFile \"$PWD\\.scratch\\vc_redist.x64.exe\" -MaximumRedirection 10 -UseBasicParsing; \"ok\" } catch { \"ERR: \" + $_.Exception.Message }; Get-ChildItem .scratch\\vc_redist.x64.exe -ErrorAction SilentlyContinue | Select-Object FullName,Length | Out-String", "$ErrorActionPreference=\"Continue\"; $exe = \"C:\\coldpass\\workspace\\.scratch\\vc_redist.x64.exe\"; $p = Start-Process -FilePath $exe -ArgumentList \"/install\",\"/quiet\",\"/norestart\" -Wait -PassThru; \"vc install exit $($p.ExitCode)\"; Test-Path C:\\Windows\\System32\\vcruntime140.dll; Test-Path C:\\Windows\\System32\\msvcp140.dll", "$ErrorActionPreference=\"Continue\"; New-Item -ItemType Directory -Force C:\\coldpass\\workspace\\.scratch\\vclog | Out-Null; $exe = \"C:\\coldpass\\workspace\\.scratch\\vc_redist.x64.exe\"; $p = Start-Process -FilePath $exe -ArgumentList \"/install\",\"/quiet\",\"/norestart\",\"/log\",\"C:\\coldpass\\workspace\\.scratch\\vclog\\vc.log\" -Wait -PassThru; \"exit $($p.ExitCode)\"; Get-ChildItem C:\\coldpass\\workspace\\.scratch\\vclog -Recurse | Select-Object FullName,Length | Out-String; Get-ChildItem C:\\coldpass\\workspace\\.scratch\\vc*.log -ErrorAction SilentlyContinue | Select-Object -First 1 | ForEach-Object { Get-Content $_.FullName -Tail 25 }", "$ErrorActionPreference=\"Continue\"; \"TEMP=$env:TEMP\"; Get-ChildItem C:\\coldpass\\workspace\\.scratch\\854344f3-97ef-4dbb-b4b2-151857893636 -Recurse -ErrorAction SilentlyContinue | Select-Object FullName,Length | Out-String -Width 250; Get-ChildItem $env:TEMP -ErrorAction SilentlyContinue | Select-Object -First 5 Name | Out-String; $p = Start-Process -FilePath \"C:\\coldpass\\workspace\\.scratch\\vc_redist.x64.exe\" -ArgumentList \"/quiet\",\"/norestart\" -Wait -PassThru -ErrorAction Continue; \"exit $($p.ExitCode)\"", "$ErrorActionPreference=\"Continue\"; $t=\"C:\\coldpass\\workspace\\.scratch\\tmp\"; New-Item -ItemType Directory -Force $t | Out-Null; $env:TEMP=$t; $env:TMP=$t; & \"C:\\coldpass\\workspace\\.scratch\\vc_redist.x64.exe\" /install /quiet /norestart; \"exit $LASTEXITCODE\"; Test-Path C:\\Windows\\System32\\vcruntime140.dll; Get-ChildItem $t -Recurse -ErrorAction SilentlyContinue | Select-Object -First 10 FullName | Out-String", "Get-Content C:\\coldpass\\workspace\\.scratch\\tmp\\Setup_*_Failed.txt -Raw | Out-String -Width 300 | ForEach-Object { $_.Substring(0,[Math]::Min(3000,$_.Length)) }", "$ErrorActionPreference=\"Continue\"; \"ProgramData=$env:ProgramData\"; \"ALLUSERS=$env:ALLUSERSPROFILE\"; \"APPDATA=$env:APPDATA\"; if (-not (Test-Path C:\\ProgramData)) { New-Item -ItemType Directory C:\\ProgramData | Out-Null }; if (-not $env:ProgramData) { $env:ProgramData = \"C:\\ProgramData\" }; $env:ALLUSERSPROFILE = \"C:\\ProgramData\"; $t=\"C:\\coldpass\\workspace\\.scratch\\tmp2\"; New-Item -ItemType Directory -Force $t | Out-Null; $env:TEMP=$t; $env:TMP=$t; & \"C:\\coldpass\\workspace\\.scratch\\vc_redist.x64.exe\" /install /quiet /norestart; \"exit $LASTEXITCODE\"; Test-Path C:\\Windows\\System32\\vcruntime140.dll; Test-Path C:\\Windows\\System32\\msvcp140.dll", "$ErrorActionPreference=\"Continue\"; Get-ChildItem C:\\coldpass\\workspace\\.scratch\\tmp2 -Recurse -ErrorAction SilentlyContinue | Select-Object -First 3 FullName | Out-String; $f = Get-ChildItem C:\\coldpass\\workspace\\.scratch\\tmp2 -Filter \"Setup_*\" -ErrorAction SilentlyContinue | Select-Object -First 1; if ($f) { Get-Content $f.FullName -Raw | ForEach-Object { $_.Substring(0,[Math]::Min(2500,$_.Length)) } }; Get-ChildItem C:\\coldpass\\workspace\\.scratch\\tmp -Filter \"Setup_*\" | ForEach-Object { Get-Content $_.FullName -Raw | ForEach-Object { $_.Substring(0,[Math]::Min(1200,$_.Length)) } }", "$ErrorActionPreference=\"Continue\"; Get-ItemProperty 'HKLM:\\SOFTWARE\\Microsoft\\Windows NT\\CurrentVersion\\ProfileList' -ErrorAction SilentlyContinue | Select-Object ProgramData,ProfilesDirectory | Format-List | Out-String; Get-ItemProperty 'HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Explorer\\User Shell Folders' -ErrorAction SilentlyContinue | Select-Object 'Common AppData' | Out-String; Get-ItemProperty 'HKLM:\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Shell Folders' -ErrorAction SilentlyContinue | Select-Object 'Common AppData' | Out-String", "$ErrorActionPreference=\"Continue\"; \"SystemDrive=$env:SystemDrive SystemRoot=$env:SystemRoot\"; $env:SystemDrive=\"C:\"; $env:ProgramData=\"C:\\ProgramData\"; $env:ALLUSERSPROFILE=\"C:\\ProgramData\"; $t=\"C:\\coldpass\\workspace\\.scratch\\tmp3\"; New-Item -ItemType Directory -Force $t | Out-Null; $env:TEMP=$t; $env:TMP=$t; & \"C:\\coldpass\\workspace\\.scratch\\vc_redist.x64.exe\" /install /quiet /norestart; \"exit $LASTEXITCODE\"; Test-Path C:\\Windows\\System32\\vcruntime140.dll; Get-ChildItem $t -Filter \"Setup_*\" | ForEach-Object { Get-Content $_.FullName -Raw | Select-Object -Last 3 }", "$ErrorActionPreference=\"Continue\"; Get-ChildItem C:\\coldpass\\workspace\\.scratch\\tmp3 -Recurse | Select-Object FullName | Out-String; Get-ChildItem C:\\coldpass\\workspace\\.scratch\\tmp3 -Filter \"*.txt\" -Recurse | ForEach-Object { \"== $($_.Name)\"; Get-Content $_.FullName -Raw | ForEach-Object { $_.Substring(0,[Math]::Min(1500,$_.Length)) } }; Get-Process | Where-Object { $_.ProcessName -like '*vc*' -or $_.ProcessName -like '*Setup*' } | Select-Object ProcessName | Out-String", "$ErrorActionPreference=\"Continue\"; Get-ChildItem C:\\coldpass\\workspace\\.scratch\\tmp3 -Filter \"*.log\" | ForEach-Object { \"== $($_.Name)\"; Get-Content $_.FullName | Select-String -Pattern 'Error|error|return value|Result|0x' | Select-Object -Last 8 | ForEach-Object { $_.Line } }", "cd C:\\coldpass\\workspace; Test-Path C:\\Windows\\System32\\vcruntime140.dll; $env:TEMP = \"$PWD\\.scratch\"; $env:TMP = \"$PWD\\.scratch\"; $env:UV_PYTHON_PREFERENCE = \"only-managed\"; $env:UV_CACHE_DIR = \"$PWD\\.cache\\uv\"; $env:UV_PYTHON_INSTALL_DIR = \"$PWD\\.tools\\python\"; $env:HF_HOME = \"$PWD\\.cache\\huggingface\"; $uv = \"$PWD\\.tools\\uv.exe\"; & $uv run --no-project --python .venv python -c \"import torch; print(torch.__version__)\" 2>&1 | Select-Object -Last 3; \"torch exit $LASTEXITCODE\"", "cd C:\\coldpass\\workspace; $env:TEMP = \"$PWD\\.scratch\"; $env:TMP = \"$PWD\\.scratch\"; $env:UV_PYTHON_PREFERENCE = \"only-managed\"; $env:UV_CACHE_DIR = \"$PWD\\.cache\\uv\"; $env:UV_PYTHON_INSTALL_DIR = \"$PWD\\.tools\\python\"; $env:HF_HOME = \"$PWD\\.cache\\huggingface\"; $uv = \"$PWD\\.tools\\uv.exe\"; Test-Path .cache\\first-run.json; & $uv run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/first-run.json 2>&1 | Select-Object -Last 30; \"exit $LASTEXITCODE\"; if (Test-Path .cache\\first-run.json) { (Get-Content .cache\\first-run.json -Raw).Substring(0,1200) }", "cd C:\\coldpass\\workspace; Select-String -Path scripts\\*.py,benchmarks\\*.py,tests\\*.py,formal\\*.py -Pattern 'schedul|cron|--once|--now|while True|sleep\\(|webhook|interval' | ForEach-Object { \"$($_.Path):$($_.LineNumber): $($_.Line.Trim())\" } | Select-Object -First 30; \"---checker\"; Select-String -Path C:\\coldpass\\checker\\check.py -Pattern 'expected_file|env|cwd|returncode|fresh|exists' | ForEach-Object { \"$($_.LineNumber): $($_.Line.Trim())\" } | Select-Object -First 40", "cd C:\\coldpass\\workspace; & C:\\coldpass\\workspace\\.venv\\Scripts\\python.exe -m unittest discover -s tests -q 2>&1 | Select-Object -Last 8; \"unittest exit $LASTEXITCODE\"; & C:\\coldpass\\workspace\\.venv\\Scripts\\python.exe scripts\\check_syntax.py 2>&1 | Select-Object -Last 8; \"syntax exit $LASTEXITCODE\"", "cd C:\\coldpass\\workspace; $env:TEMP = \"$PWD\\.scratch\"; $env:TMP = \"$PWD\\.scratch\"; $env:UV_PYTHON_PREFERENCE = \"only-managed\"; $env:UV_CACHE_DIR = \"$PWD\\.cache\\uv\"; $env:UV_PYTHON_INSTALL_DIR = \"$PWD\\.tools\\python\"; $env:HF_HOME = \"$PWD\\.cache\\huggingface\"; $uv = \"$PWD\\.tools\\uv.exe\"; Test-Path .cache\\example-parity-reference.json; $sw=[Diagnostics.Stopwatch]::StartNew(); & $uv run --no-project --python .venv python scripts/parity.py collect --backend pytorch --output .cache/example-parity-reference.json 2>&1 | Select-Object -Last 12; \"exit $LASTEXITCODE secs $($sw.Elapsed.TotalSeconds)\"; if (Test-Path .cache\\example-parity-reference.json) { (Get-Item .cache\\example-parity-reference.json).Length; (Get-Content .cache\\example-parity-reference.json -Raw).Substring(0,400) }", "cd C:\\coldpass\\workspace; Remove-Item -Force .cache\\first-run.json,.cache\\example-parity-reference.json -ErrorAction SilentlyContinue; New-Item -ItemType Directory -Force .coldpass | Out-Null; $ws='C:\\coldpass\\workspace'; $uv='C:\\coldpass\\workspace\\.tools\\uv.exe'; $envb = '{\"UV_PYTHON_PREFERENCE\":\"only-managed\",\"UV_CACHE_DIR\":\"C:\\\\coldpass\\\\workspace\\\\.cache\\\\uv\",\"UV_PYTHON_INSTALL_DIR\":\"C:\\\\coldpass\\\\workspace\\\\.tools\\\\python\",\"HF_HOME\":\"C:\\\\coldpass\\\\workspace\\\\.cache\\\\huggingface\"}'\n$probe = @\"\n{\"kind\":\"cli\",\"argv\":[\"$uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"benchmarks/bench_laya_cpu.py\",\"--model\",\".cache/model/typed-decisions\",\"--threads\",\"4\",\"--warmup\",\"1\",\"--repeats\",\"1\",\"--counts\",\"1,3\",\"--output\",\".cache/probe-bench.json\"],\"cwd\":\"$ws\",\"env\":$envb,\"expected_file\":\".cache/probe-bench.json\",\"expected_text\":\"\\\"device\\\": \\\"cpu\\\"\"}\n\"@\n$claims = @\"\n[\n{\"kind\":\"claim\",\"claim\":\"The quickstart benchmark writes its result file on CPU\",\"source\":\"memory to ``.cache/first-run.json``. Expect ``meta.device`` to be ``\\\"cpu\\\"``, finite\",\"input\":\"bench_laya_cpu.py with counts 1,3 and a fresh output file\",\"expected\":\"JSON output with device cpu\",\"probe_kind\":\"cli\",\"argv\":[\"$uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"benchmarks/bench_laya_cpu.py\",\"--model\",\".cache/model/typed-decisions\",\"--threads\",\"4\",\"--warmup\",\"1\",\"--repeats\",\"1\",\"--counts\",\"1,3\",\"--output\",\".cache/claim-bench.json\"],\"env\":$envb,\"expected_file\":\".cache/claim-bench.json\",\"expected_text\":\"\\\"device\\\": \\\"cpu\\\"\",\"cwd\":\"$ws\"},\n{\"kind\":\"claim\",\"claim\":\"The local checks need only Python's standard library and run offline\",\"source\":\"These checks need only Python's standard library and do not download a model:\",\"input\":\"unittest discover over tests\",\"expected\":\"all 19 tests pass\",\"probe_kind\":\"cli\",\"argv\":[\"$uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"-m\",\"unittest\",\"discover\",\"-s\",\"tests\",\"-q\"],\"env\":$envb,\"expected_text\":\"Ran 19 tests\",\"cwd\":\"$ws\"},\n{\"kind\":\"claim\",\"claim\":\"The syntax check passes on the repository\",\"source\":\"python3 scripts/check_syntax.py\",\"input\":\"scripts/check_syntax.py\",\"expected\":\"Python syntax checked.\",\"probe_kind\":\"cli\",\"argv\":[\"$uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"scripts/check_syntax.py\"],\"env\":$envb,\"expected_text\":\"Python syntax checked.\",\"cwd\":\"$ws\"}\n]\n\"@\n$examples = @\"\n[\n{\"kind\":\"example\",\"claim\":\"Collect PyTorch reference answers for the parity suite\",\"source\":\"README.md: Check any ONNX build against the reference\",\"input\":\"parity.py collect --backend pytorch on the pinned checkpoint\",\"expected\":\"60 cases collected with pytorch-fp32\",\"argv\":[\"$uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"scripts/parity.py\",\"collect\",\"--backend\",\"pytorch\",\"--output\",\".cache/example-parity-reference.json\"],\"cwd\":\"$ws\",\"env\":$envb,\"expected_file\":\".cache/example-parity-reference.json\",\"expected_text\":\"\\\"backend\\\": \\\"pytorch-fp32\\\"\"},\n{\"kind\":\"example\",\"claim\":\"Download and verify the pinned typed-decisions checkpoint\",\"source\":\"README.md: Quickstart: PyTorch FP32\",\"input\":\"scripts/download_model.py\",\"expected\":\"checkpoint verified\",\"argv\":[\"$uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"scripts/download_model.py\"],\"cwd\":\"$ws\",\"env\":$envb,\"expected_text\":\"Pinned typed-decisions checkpoint verified.\"},\n{\"kind\":\"example\",\"claim\":\"Collect ONNX candidate answers for the parity suite\",\"source\":\"README.md: Check any ONNX build against the reference\",\"reason\":\"Not run: requires the separate .venv-onnx environment and the 1.69 GB ONNX graph download, which were outside this quickstart run.\"}\n]\n\"@\n$cycles = @\"\n{\"detected\":false,\"reason\":\"Entry points inspected: scripts/download_model.py, scripts/download_onnx.py, scripts/parity.py, scripts/check_syntax.py and benchmarks/*.py are one-shot CLIs with no cron, loop, watch, --once/--now or webhook. grep for schedule/cron/--once/--now/webhook found none. The product runs once per command when a user starts it.\",\"checks\":[]}\n\"@\n$enc = New-Object System.Text.UTF8Encoding($false)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\probe.json\", $probe.Trim(), $enc)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\claims.json\", $claims.Trim(), $enc)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\examples.json\", $examples.Trim(), $enc)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\cycles.json\", $cycles.Trim(), $enc)\nforeach ($f in 'probe.json','claims.json','examples.json','cycles.json') { \"--- $f\"; Get-Content \"$ws\\.coldpass\\$f\" -Raw | ForEach-Object { $_.Length } }\n& \"$PSHOME\\..\\..\\..\\..\\..\\\" 2>$null | Out-Null\nGet-Content \"$ws\\.coldpass\\probe.json\" -Raw | ConvertFrom-Json | Out-Null; Get-Content \"$ws\\.coldpass\\claims.json\" -Raw | ConvertFrom-Json | Out-Null; Get-Content \"$ws\\.coldpass\\examples.json\" -Raw | ConvertFrom-Json | Out-Null; Get-Content \"$ws\\.coldpass\\cycles.json\" -Raw | ConvertFrom-Json | Out-Null; \"all parse ok\"", "$ws='C:\\coldpass\\workspace'; $uv='C:\\coldpass\\workspace\\.tools\\uv.exe'; $envb=@{UV_PYTHON_PREFERENCE='only-managed';UV_CACHE_DIR='C:\\coldpass\\workspace\\.cache\\uv';UV_PYTHON_INSTALL_DIR='C:\\coldpass\\workspace\\.tools\\python';HF_HOME='C:\\coldpass\\workspace\\.cache\\huggingface'}\n$base=@($uv,'run','--no-project','--python','.venv','python')\n$bench=@('benchmarks/bench_laya_cpu.py','--model','.cache/model/typed-decisions','--threads','4','--warmup','1','--repeats','1','--counts','1,3','--output')\n$probe=[ordered]@{kind='cli';argv=@($base+$bench+@('.cache/probe-bench.json'));cwd=$ws;env=$envb;expected_file='.cache/probe-bench.json';expected_text='\"device\": \"cpu\"'}\n$claims=@(\n [ordered]@{kind='claim';claim='The quickstart benchmark writes its result file on CPU';source='memory to `.cache/first-run.json`. Expect `meta.device` to be `\"cpu\"`, finite';input='bench_laya_cpu.py with counts 1,3 and a fresh output file';expected='JSON output with device cpu';probe_kind='cli';argv=@($base+$bench+@('.cache/claim-bench.json'));env=$envb;expected_file='.cache/claim-bench.json';expected_text='\"device\": \"cpu\"';cwd=$ws},\n [ordered]@{kind='claim';claim='The local checks need only Python standard library and run offline';source=\"These checks need only Python's standard library and do not download a model:\";input='unittest discover over tests';expected='all 19 tests pass';probe_kind='cli';argv=@($base+@('-m','unittest','discover','-s','tests','-q'));env=$envb;expected_text='Ran 19 tests';cwd=$ws},\n [ordered]@{kind='claim';claim='The syntax check passes on the repository';source='python3 scripts/check_syntax.py';input='scripts/check_syntax.py';expected='Python syntax checked.';probe_kind='cli';argv=@($base+@('scripts/check_syntax.py'));env=$envb;expected_text='Python syntax checked.';cwd=$ws}\n)\n$examples=@(\n [ordered]@{kind='example';claim='Collect PyTorch reference answers for the parity suite';source='README.md: Check any ONNX build against the reference';input='parity.py collect --backend pytorch on the pinned checkpoint';expected='60 cases collected with pytorch-fp32';argv=@($base+@('scripts/parity.py','collect','--backend','pytorch','--output','.cache/example-parity-reference.json'));cwd=$ws;env=$envb;expected_file='.cache/example-parity-reference.json';expected_text='\"backend\": \"pytorch-fp32\"'},\n [ordered]@{kind='example';claim='Download and verify the pinned typed-decisions checkpoint';source='README.md: Quickstart: PyTorch FP32';input='scripts/download_model.py';expected='checkpoint verified';argv=@($base+@('scripts/download_model.py'));cwd=$ws;env=$envb;expected_text='Pinned typed-decisions checkpoint verified.'},\n [ordered]@{kind='example';claim='Collect ONNX candidate answers for the parity suite';source='README.md: Check any ONNX build against the reference';reason='Not run: requires the separate .venv-onnx environment and the 1.69 GB ONNX graph download, which were outside this quickstart run.'}\n)\n$cycles=[ordered]@{detected=$false;reason='Entry points inspected: scripts/download_model.py, scripts/download_onnx.py, scripts/parity.py, scripts/check_syntax.py and benchmarks/*.py are one-shot CLIs with no cron, loop, watch, --once/--now or webhook. A search for schedule/cron/--once/--now/webhook found none. The product runs once per command when a user starts it.';checks=@()}\n$enc=New-Object System.Text.UTF8Encoding($false)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\probe.json\",(ConvertTo-Json $probe -Depth 8),$enc)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\claims.json\",(ConvertTo-Json $claims -Depth 8),$enc)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\examples.json\",(ConvertTo-Json $examples -Depth 8),$enc)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\cycles.json\",(ConvertTo-Json $cycles -Depth 8),$enc)\nforeach($f in 'probe.json','claims.json','examples.json','cycles.json'){ $t=Get-Content \"$ws\\.coldpass\\$f\" -Raw; $null=$t | ConvertFrom-Json; \"$f ok\" }\nGet-Content \"$ws\\.coldpass\\claims.json\" -Raw | Select-String 'source' | ForEach-Object { $_.Line.Trim() }", "$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay; \"EXIT=$LASTEXITCODE\"", "$ws='C:\\coldpass\\workspace'; $p=\"$ws\\.coldpass\\claims.json\"; $c=@(Get-Content $p -Raw | ConvertFrom-Json | Where-Object { $_.claim -notlike '*standard library*' }); $enc=New-Object System.Text.UTF8Encoding($false); [IO.File]::WriteAllText($p,(ConvertTo-Json $c -Depth 8),$enc); \"claims kept: $($c.Count)\"; $env:COLDPASS_WORKSPACE=$ws; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | ForEach-Object { $_.Substring(0,[Math]::Min(600,$_.Length)) }; \"EXIT=$LASTEXITCODE\"", "$ws='C:\\coldpass\\workspace'; Select-String -Path \"$ws\\README.md\" -Pattern 'meta.device|python3 scripts/check_syntax|Python.s standard' | ForEach-Object { \"$($_.LineNumber): [$($_.Line)]\" }; \"---\"; Get-Content \"$ws\\.coldpass\\claims.json\" -Raw", "$ws='C:\\coldpass\\workspace'; $uv=\"$ws\\.tools\\uv.exe\"; $envb=[ordered]@{UV_PYTHON_PREFERENCE='only-managed';UV_CACHE_DIR=\"$ws\\.cache\\uv\";UV_PYTHON_INSTALL_DIR=\"$ws\\.tools\\python\";HF_HOME=\"$ws\\.cache\\huggingface\"}\n$base=@($uv,'run','--no-project','--python','.venv','python')\n$c1=[ordered]@{kind='claim';claim='The quickstart benchmark writes its result file on CPU';source='Expect `meta.device` to be `\"cpu\"`, finite';input='bench_laya_cpu.py with counts 1,3 and a fresh output file';expected='JSON output with device cpu';probe_kind='cli';argv=@($base+@('benchmarks/bench_laya_cpu.py','--model','.cache/model/typed-decisions','--threads','4','--warmup','1','--repeats','1','--counts','1,3','--output','.cache/claim-bench.json'));env=$envb;expected_file='.cache/claim-bench.json';expected_text='\"device\": \"cpu\"';cwd=$ws}\n$c2=[ordered]@{kind='claim';claim='The syntax check passes on the repository';source='python3 scripts/check_syntax.py';input='scripts/check_syntax.py';expected='Python syntax checked.';probe_kind='cli';argv=@($base+@('scripts/check_syntax.py'));env=$envb;expected_text='Python syntax checked.';cwd=$ws}\n$arr=@($c1,$c2)\n$json=ConvertTo-Json -InputObject $arr -Depth 8\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\claims.json\",$json,(New-Object System.Text.UTF8Encoding($false)))\n$chk=Get-Content \"$ws\\.coldpass\\claims.json\" -Raw | ConvertFrom-Json; \"claims parsed: $(@($chk).Count)\"\n$env:COLDPASS_WORKSPACE=$ws; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | ForEach-Object { $_.Substring(0,[Math]::Min(700,$_.Length)) }; \"EXIT=$LASTEXITCODE\"", "$ws='C:\\coldpass\\workspace'; New-Item -ItemType Directory -Force -Path \"$ws\\.coldpass\" | Out-Null\n$r=[ordered]@{outcome='working';fault_owner=$null;operation='PyTorch FP32 CPU quickstart: install, download pinned typed-decisions checkpoint, run CPU benchmark, parity collect, local syntax check';steps=@('Install uv via README install.ps1 (absolute powershell path used)','uv venv --python 3.12 .venv (CPython 3.12.15)','Install PyTorch 2.14.0+cpu and laya 0.3.4 per README quickstart','scripts/download_model.py: pinned typed-decisions checkpoint downloaded and verified','benchmarks/bench_laya_cpu.py --counts 1,3 wrote CPU result JSON (exit 0)','scripts/parity.py collect --backend pytorch: 60 cases collected, backend pytorch-fp32','scripts/check_syntax.py passed');deviations=@('python3 replaced by uv run --python .venv python on Windows guest','Visual C++ 2022 x64 redistributable installed as prerequisite for torch; installer needed per-machine AppData/ProgramData env workaround','ONNX route not run (needs separate .venv-onnx and 1.69 GB graphs)','Unit test suite not used as a claim (checker does not count it as a product operation)');stuck_step=$null;main_blocker=$null;plain_failure=$null;suggested_fix='Guest images for Windows should include the Visual C++ 2022 x64 runtime so torch imports without a manual install.'}\n$json=ConvertTo-Json -InputObject $r -Depth 6\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\report.json\",$json,(New-Object System.Text.UTF8Encoding($false)))\n(Get-Content \"$ws\\.coldpass\\report.json\" -Raw | ConvertFrom-Json).outcome\nif (Test-Path 'C:\\inputs\\coldpass-preflight.py') {'preflight present'} else {'preflight not at C:\\inputs'}\nif (Test-Path '/inputs/coldpass-preflight.py') {'preflight present at /inputs'} else {'no /inputs preflight'}", "$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | ForEach-Object { $_.Substring(0,[Math]::Min(300,$_.Length)) }; \"EXIT=$LASTEXITCODE\"" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "PyTorch FP32 CPU quickstart: install, download pinned typed-decisions checkpoint, run CPU benchmark, parity collect, local syntax check", "suggested_fix": null, "tokens_in": 1055456, "tokens_out": 32206, "cost_usd": 0.04699171500000002, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "C:\\coldpass\\workspace\\.tools\\uv.exe", "run", "--no-project", "--python", ".venv", "python", "benchmarks/bench_laya_cpu.py", "--model", ".cache/model/typed-decisions", "--threads", "4", "--warmup", "1", "--repeats", "1", "--counts", "1,3", "--output", ".cache/probe-bench.json-checker-cd5cb4bb7eb1424eb6745c483e03ccca" ], "kind": "cli", "returncode": 0, "stdout": "timing 1 questions ...\n p50=351.6 ms p95=351.6 ms 2.84 q/s RSS=1973.3 MiB CPU=191.0%\ntiming 3 questions ...\n p50=959.1 ms p95=959.1 ms 3.13 q/s RSS=1984.3 MiB CPU=190.3%\nwrote .cache\\probe-bench.json-checker-cd5cb4bb7eb1424eb6745c483e03ccca\n[excerpt truncated]", "stderr": "", "expected_file": ".cache/probe-bench.json-checker-cd5cb4bb7eb1424eb6745c483e03ccca", "file_checked": true, "file_excerpt": "\"device\": \"cpu\",\r\n \"model_path\": \"\",\r\n \"model_config\": {\r\n \"encoder\": \"answerdotai/ModernBERT-large\",\r\n \"head_layers\": 2,\r\n \"max_len\": 1024,\r\n \"head_max_len\": 256,\r\n \"max_prefixes\": 6,\r\n \"act_costs\": {\r\n \"escalate\": 0.5\r\n },\r\n \"cost_wrong_act\": 3.0,\r\n \"amp_dtype\": \"bf16\",\r\n \"model_name\": \"laya-typed-decisions\",\r\n \"training\": {\r\n \"updates\": 7313,\r\n \"epochs_completed\": 1,\r\n \"hours\": 1.96,\r\n \"world_size\": 1,\r\n \"fine_tuned_from_checkpoint\": true\r\n },\r\n \"gradient_checkpointing\": true,\r\n \"max_tokens_per_batch\": 4096,\r\n \"fine_tuned\": true\r\n },\r\n \"calibration_source\": \"pinned upstream rl_agent_config.json\",\r\n \"cold_load_ms\": 16787.829,\r\n \"rss_before_mib\": 193.77,\r\n \"rss_after_load_mib\": 1974.8\r\n },\r\n \"workloads\": {\r\n \"1\": {\r\n \"p50_ms\": 351.584,\r\n \"p95_ms\": 351.584,\r\n \"min_ms\": 351.584,\r\n \"max_ms\": 351.584,\r\n \"mean_ms\": 351.584,\r\n \"questions\": 1,\r\n \"questions_per_second_p50\": 2.844,\r\n \"rss_peak_mib\": 1973.27,\r\n \"cpu_percent_mean_sampled\": 191.0,\r\n \"output_sha256_first\": \"615045d6d0cc8bcc75c059903638b8198377b74f90ab179d89f8f006b21cecdf\",\r\n \"output_sha256_last\": \"615045d6d0cc8bcc75c059903638b8198377b74f90ab179d89f8f006b21cecdf\",\r\n \"deterministic_repeated_output\": true,\r\n \"sample_ms\": [\r\n 351.584\r\n ]\r\n },\r\n \"3\": {\r\n \"p50_ms\": 959.092,\r\n \"p95_ms\": 959.092,\r\n \"min_ms\": 959.092,\r\n \"max_ms\": 959.092,\r\n \"mean_ms\": 959.092,\r\n \"questions\": 3,\r\n \"questions_per_second_p50\": 3.128,\r\n \"rss_peak_mib\": 1984.32,\r\n \"cpu_percent_mean_sampled\": 190.3,\r\n \"output_sha256_first\": \"62e8e2041019b6894716c30d3050e0beec1e70ea2b9c0e0405e80fb01a4e3aa4\",\r\n \"output_sha256_last\": \"62e8e2041019b6894716c30d3050e0beec1e70ea2b9c0e0405e80fb01a4e3aa4\",\r\n \"deterministic_repeated_output\": true,\r\n \"sample_ms\": [\r\n 959.092\r\n ]\r\n }\r\n },\r\n \"batch_equivalence\": {\r\n \"same_public_answers\": true,\r\n \"batched_digest\": \"9b003fbe3501b995d7d9255fe97b2044dec65b44825b40302b949c40eb2ed62d\",\r\n \"singles_digest\": \"9b003fbe3501b995d7d9255fe97b2044dec65b44825b40302b949c40eb2ed62d\",\r\n \"batched_answers\": {\r\n \"department\": {\r\n \"type\": \"choice\",\r\n \"choice\": \"billing\",\r\n \"probabilities\": {\r\n \"billing\": 0.6989,\r\n \"technical\": 0.0814,\r\n \"sales\": 0.1338,\r\n \"other\": 0.086\r\n },\r\n \"confidence\": 0.3258,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n },\r\n \"urgency\": {\r\n \"type\": \"score\",\r\n \"score\": 1.6111,\r\n \"legend\": {\r\n \"0\": \"not urgent\",\r\n \"1\": \"soon\",\r\n \"2\": \"critical or blocking\"\r\n },\r\n \"probabilities\": {\r\n \"0\": 0.0408,\r\n \"1\": 0.3073,\r\n \"2\": 0.6519\r\n },\r\n \"confidence\": 0.2972,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n },\r\n \"refund\": {\r\n \"type\": \"noul\",\r\n \"noul\": 0.68,\r\n \"confidence\": 0.68,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n }\r\n },\r\n \"single_answers\": {\r\n \"department\": {\r\n \"type\": \"choice\",\r\n \"choice\": \"billing\",\r\n \"probabilities\": {\r\n \"billing\": 0.6989,\r\n \"technical\": 0.0814,\r\n \"sales\": 0.1338,\r\n \"other\": 0.086\r\n },\r\n \"confidence\": 0.3258,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n },\r\n \"urgency\": {\r\n \"type\": \"score\",\r\n \"score\": 1.6111,\r\n \"legend\": {\r\n \"0\": \"not urgent\",\r\n \"1\": \"soon\",\r\n \"2\": \"critical or blocking\"\r\n },\r\n \"probabilities\": {\r\n \"0\": 0.0408,\r\n \"1\": 0.3073,\r\n \"2\": 0.6519\r\n },\r\n \"confidence\": 0.2972,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n },\r\n \"refund\": {\r\n \"type\": \"noul\",\r\n \"noul\": 0.68,\r\n \"confidence\": 0.68,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n }\r\n }\r\n },\r\n \"fixture\": {\r\n \"state\": {\r\n \"ticket\": {\r\n \"subject\": \"Duplicate charge\",\r\n \"body\": \"The customer was billed twice for invoice 4411 and asks for a refund today. They say the duplicate charge is blocking month-end close.\"\r\n }\r\n },\r\n \"questions\": {\r\n \"department\": {\r\n \"type\": \"choice\",\r\n \"instructions\": \"Which team should handle this ticket?\",\r\n \"criteria\": {\r\n \"billing\": \"invoices, payments, refunds\",\r\n \"technical\": \"bugs, outages, integrations\",\r\n \"sales\": \"pricing, demos, new purchases\",\r\n \"other\": \"everything else\"\r\n }\r\n },\r\n \"urgency\": {\r\n \"type\": \"score\",\r\n \"instructions\": \"How urgent is this ticket?\",\r\n \"criteria\": [\r\n \"not urgent\",\r\n \"soon\",\r\n \"critical or blocking\"\r\n ]\r\n },\r\n \"refund\": {\r\n \"type\": \"noul\",\r\n \"instructions\": \"Does the customer ask for money back?\"\r\n }\r\n },\r\n \"answers\": {\r\n \"department\": {\r\n \"type\": \"choice\",\r\n \"choice\": \"billing\",\r\n \"probabilities\": {\r\n \"billing\": 0.6989,\r\n \"technical\": 0.0814,\r\n \"sales\": 0.1338,\r\n \"other\": 0.086\r\n },\r\n \"confidence\": 0.3258,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n },\r\n \"urgency\": {\r\n \"type\": \"score\",\r\n \"score\": 1.6111,\r\n \"legend\": {\r\n \"0\": \"not urgent\",\r\n \"1\": \"soon\",\r\n \"2\": \"critical or blocking\"\r\n },\r\n \"probabilities\": {\r\n \"0\": 0.0408,\r\n \"1\": 0.3073,\r\n \"2\": 0.6519\r\n },\r\n \"confidence\": 0.2972,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n },\r\n \"refund\": {\r\n \"type\": \"noul\",\r\n \"noul\": 0.68,\r\n \"confidence\": 0.68,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n }\r\n }\r\n }\r\n}\r\n", "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--sysone-cpu-claude-haiku-5-5-1792649286403655136", "evidence_file": "/data/safety/TayHCode--sysone-cpu-claude-haiku-5-5-1792649286403655136.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": 36, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "windows" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "url": "https://github.com/TayHCode/sysone-cpu" }, "purpose": "initial", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": null, "status": "resolved", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 36, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "readme_checked", "works": "yes", "install_s": null, "first_use_s": null, "mcp": "none", "needs": [], "needs_which": null, "agent_interface": [ "cli" ], "license": "MIT", "repo_url": "https://github.com/TayHCode/sysone-cpu", "cost_to_try": "free", "hardware": "GPU", "what_failed": null, "local_or_hosted": "local", "cycle_checks": [ { "kind": "cycle", "claim": "Scheduled or looping main behavior", "source": "repository entry points", "input": "source inspection", "expected": "identify the product trigger", "verdict": "yes", "outcome": "Entry points inspected: scripts/download_model.py, scripts/download_onnx.py, scripts/parity.py, scripts/check_syntax.py and benchmarks/*.py are one-shot CLIs with no cron, loop, watch, --once/--now or webhook. A search for schedule/cron/--once/--now/webhook found none. The product runs once per command when a user starts it.", "evidence": "Entry points inspected: scripts/download_model.py, scripts/download_onnx.py, scripts/parity.py, scripts/check_syntax.py and benchmarks/*.py are one-shot CLIs with no cron, loop, watch, --once/--now or webhook. A search for schedule/cron/--once/--now/webhook found none. The product runs once per command when a user starts it.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "The quickstart benchmark writes its result file on CPU", "source": "Expect `meta.device` to be `\"cpu\"`, finite", "input": "bench_laya_cpu.py with counts 1,3 and a fresh output file", "expected": "JSON output with device cpu", "command": "'C:\\coldpass\\workspace\\.tools\\uv.exe' run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/claim-bench.json-checker-b1cd51be3c914d7791f6153aa070b924", "verdict": "yes", "outcome": "Real input produced the expected result: \"device\": \"cpu\"", "evidence": "\"device\": \"cpu\",\r\n \"model_path\": \"\",\r\n \"model_config\": {\r\n \"encoder\": \"answerdotai/ModernBERT-large\",\r\n \"head_layers\": 2,\r\n \"max_len\": 1024,\r\n \"head_max_len\": 256,\r\n \"max_prefixes\": 6,\r\n \"act_costs\": {\r\n \"escalate\": 0.5\r\n },\r\n \"cost_wrong_act\": 3.0,\r\n \"amp_dtype\": \"bf16\",\r\n \"model_name\": \"laya-typed-decisions\",\r\n \"training\": {\r\n \"updates\": 7313,\r\n \"epochs_completed\": 1,\r\n \"hours\": 1.96,\r\n \"world_size\": 1,\r\n \"fine_tuned_from_checkpoint\": true\r\n },\r\n ", "returncode": 0, "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "The syntax check passes on the repository", "source": "python3 scripts/check_syntax.py", "input": "scripts/check_syntax.py", "expected": "Python syntax checked.", "command": "'C:\\coldpass\\workspace\\.tools\\uv.exe' run --no-project --python .venv python scripts/check_syntax.py", "verdict": "yes", "outcome": "Real input produced the expected result: Python syntax checked.", "evidence": "Python syntax checked.\r\n", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Collect PyTorch reference answers for the parity suite", "source": "README.md: Check any ONNX build against the reference", "input": "parity.py collect --backend pytorch on the pinned checkpoint", "command": "'C:\\coldpass\\workspace\\.tools\\uv.exe' run --no-project --python .venv python scripts/parity.py collect --backend pytorch --output .cache/example-parity-reference.json-checker-27a7baa54c3a46aa86d4e37fc948d878", "evidence": "\"refund\": {\r\n \"type\": \"noul\",\r\n \"noul\": 0.1578,\r\n \"confidence\": 0.8422,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n },\r\n \"urgency\": {\r\n \"type\": \"score\",\r\n \"score\": 1.0602,\r\n \"legend\": {\r\n \"0\": \"not urgent\",\r\n \"1\": \"soon\",\r\n \"2\": \"critical or blocking\"\r\n },\r\n \"probabilities\": {\r\n \"0\": 0.2235,\r\n \"1\": 0.4927,\r\n \"2\": 0.2838\r\n },\r\n \"confidence\": 0.0524,\r\n \"action\": {\r\n \"act_probability\": 1.0\r\n }\r\n }\r\n }\r\n ]\r\n}\r\n", "deferred": false, "expected": "60 cases collected with pytorch-fp32", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Download and verify the pinned typed-decisions checkpoint", "source": "README.md: Quickstart: PyTorch FP32", "input": "scripts/download_model.py", "command": "'C:\\coldpass\\workspace\\.tools\\uv.exe' run --no-project --python .venv python scripts/download_model.py", "evidence": "Downloading about 846 MB of public upstream files; no account required.\r\nPinned typed-decisions checkpoint verified.\r\n\rFetching 5 files: 0%| | 0/5 [00:00