datadoom 0.1.0.dev0__tar.gz

datadoom-0.1.0.dev0/.claude/settings.local.json

@@ -0,0 +1,212 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(curl -s -o /dev/null -w \"%{http_code}\\\\n\" https://pypi.org/pypi/datadoom/json)",
+      "Bash(curl -s -o /dev/null -w \"%{http_code}\\\\n\" https://pypi.org/pypi/data-doom/json)",
+      "Bash(curl -s -o /dev/null -w \"%{http_code}\\\\n\" https://github.com/datadoom)",
+      "Bash(curl -s \"https://api.github.com/search/repositories?q=datadoom\" -H \"Accept: application/vnd.github+json\")",
+      "Bash(curl -s \"https://api.github.com/users/datadoom\")",
+      "Bash(curl -s -o /dev/null -w \"%{http_code}\\\\n\" https://test.pypi.org/pypi/datadoom/json)",
+      "Bash(git remote *)",
+      "Bash(git branch *)",
+      "Bash(git -C 'd:/Hack Forge' remote -v)",
+      "Bash(git -C 'd:/Hack Forge' branch --show-current)",
+      "Bash(git -C 'd:/Hack Forge' status -s)",
+      "Bash(git config *)",
+      "Bash(py -3.12 --version)",
+      "Bash(py -3.11 --version)",
+      "Bash(python -m pip --version)",
+      "Bash(py -3.12 -m pip --version)",
+      "Bash(py -3.12 -c \"import venv; print\\('venv ok'\\)\")",
+      "Bash(curl -sL https://www.apache.org/licenses/LICENSE-2.0.txt -o LICENSE)",
+      "Bash(pip install *)",
+      "Bash(python -c \"import datadoom; print\\('version', datadoom.__version__\\)\")",
+      "Bash(datadoom validate *)",
+      "Bash(datadoom run *)",
+      "Bash(datadoom verify *)",
+      "Bash(python -c \"import sys; print\\(sys.executable\\)\")",
+      "Bash(pip show *)",
+      "Bash(python -c \"import datadoom\")",
+      "Bash(python -m pip install -e \".[dev]\" import-linter)",
+      "Read(//c/Users/santh/AppData/Local/Python/pythoncore-3.14-64/**)",
+      "Bash(\"C:\\\\Users\\\\santh\\\\AppData\\\\Local\\\\Python\\\\pythoncore-3.14-64\\\\python.exe\" --version)",
+      "Bash(\"C:\\\\Users\\\\santh\\\\AppData\\\\Local\\\\Python\\\\pythoncore-3.14-64\\\\python.exe\" -c \"import datadoom, numpy, scipy, pandas; print\\('datadoom', datadoom.__version__, '| numpy', numpy.__version__, '| pandas', pandas.__version__\\)\")",
+      "Bash(.venv/Scripts/python.exe -m pip install --upgrade pip -q)",
+      "Bash(.venv/Scripts/python.exe -m pip install -e \".[dev]\")",
+      "Bash(.venv/Scripts/datadoom.exe version *)",
+      "Bash(.venv/Scripts/lint-imports.exe)",
+      "Bash(echo \"lint-imports exit=$?\")",
+      "WebSearch",
+      "PowerShell(& \".\\\\.venv\\\\Scripts\\\\python.exe\" -m pytest tests/unit/test_dist_correctness.py tests/unit/test_hashing.py tests/unit/test_spec_validate.py tests/unit/test_metadata.py -q)",
+      "PowerShell(& \".\\\\.venv\\\\Scripts\\\\python.exe\" -m pytest -q 2>&1)",
+      "Bash(.venv/Scripts/python.exe -m pip install -e \".[dev]\" --quiet)",
+      "Bash(.venv/Scripts/python.exe -c \"import fastapi, sqlalchemy, alembic, uvicorn, httpx; print\\('ok', fastapi.__version__, sqlalchemy.__version__\\)\")",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_pipeline.py tests/determinism -q)",
+      "Bash(.venv/Scripts/python.exe -c ' *)",
+      "Bash(.venv/Scripts/ruff.exe check *)",
+      "Bash(.venv/Scripts/mypy.exe)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/api tests/unit/test_store.py -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest)",
+      "Bash(npm --version)",
+      "Bash(npm install *)",
+      "Bash(npm run *)",
+      "Bash(.venv/Scripts/python.exe -m datadoom.cli.main --help)",
+      "Bash(.venv/Scripts/python.exe -c \"import networkx; print\\('networkx', networkx.__version__\\)\")",
+      "Bash(echo \"exit:$?\")",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_causal.py tests/unit/test_pipeline.py tests/determinism -q)",
+      "Bash(.venv/Scripts/datadoom.exe run *)",
+      "Bash(.venv/Scripts/datadoom.exe verify *)",
+      "Bash(.venv/Scripts/python.exe -c \"import pandas as pd; df=pd.read_csv\\('.tmp_causal/data.csv'\\); print\\(df.head\\(\\)\\); print\\('is_fraud rate', df['is_fraud'].mean\\(\\)\\); print\\('corr age-income', df['age'].corr\\(df['income']\\)\\)\")",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/determinism tests/unit/test_causal.py tests/api -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_causal.py -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_causal.py)",
+      "Bash(.venv/Scripts/python.exe .tmp_analyze.py)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_dist.py tests/unit/test_dist_correctness.py tests/unit/test_pipeline.py tests/unit/test_metadata.py tests/api -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_causal.py tests/unit/test_dist.py)",
+      "Bash(.venv/Scripts/python.exe -c \"import json; d=json.load\\(open\\('.tmp_run/metadata.json'\\)\\); c=d['compliance']; print\\('score', round\\(c['compliance_score'],3\\), '| applicable', c['applicable_features'], 'of', c['assessed_features']\\); [print\\('  ', f['feature'], f['dist'], 'p=%.3f'%f['p_value'], \\('applicable, '+\\('pass' if f['passed'] else 'FAIL'\\)\\) if f['applicable'] else 'n/a', 'clamped=%.2f'%f['clamped_fraction']\\) for f in c['features']]\")",
+      "Bash(rm -rf .tmp_run)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_dataset_audit.py -q)",
+      "Bash(.venv/Scripts/python.exe -c \"from datadoom.engine import load_spec, generate; import numpy as np, pandas as pd; r=generate\\(load_spec\\('examples/tabular-basic.datadoom.yaml'\\), seed=42\\); d=r.frame; print\\('age   mean=%.2f std=%.2f min=%d max=%d int=%s'%\\(d['age'].mean\\(\\), d['age'].std\\(\\), d['age'].min\\(\\), d['age'].max\\(\\), str\\(d['age'].dtype\\)\\)\\); print\\('income median=%.0f \\(target %.0f\\)  mean=%.0f \\(target %.0f\\)'%\\(d['income'].median\\(\\), np.exp\\(10.5\\), d['income'].mean\\(\\), np.exp\\(10.5+0.4**2/2\\)\\)\\); print\\('visits mean=%.2f var=%.2f \\(lam=3\\)'%\\(d['visits'].mean\\(\\), d['visits'].var\\(\\)\\)\\); print\\('edu   '+str\\({c: round\\(\\(d['education']==c\\).mean\\(\\),3\\) for c in ['hs','college','grad']}\\)\\); print\\('member rate=%.3f'%d['is_member'].mean\\(\\)\\); print\\('note  tokens %d..%d'%\\(d['note'].map\\(lambda s: len\\(s.split\\(\\)\\)\\).min\\(\\), d['note'].map\\(lambda s: len\\(s.split\\(\\)\\)\\).max\\(\\)\\)\\); print\\('compliance %.3f  applicable=%d of %d'%\\(r.compliance.score, r.compliance.to_dict\\(\\)['applicable_features'], r.compliance.to_dict\\(\\)['assessed_features']\\)\\)\")",
+      "Bash(.venv/Scripts/python.exe -c \"from datadoom.engine import load_spec, generate; import numpy as np; r=generate\\(load_spec\\('examples/causal-fraud.datadoom.yaml'\\), seed=42\\); d=r.frame; age=d['age'].to_numpy\\(float\\); edu=d['education'].map\\({'hs':0.,'college':15000.,'grad':40000.}\\).to_numpy\\(\\); inc=d['income'].to_numpy\\(\\); X=np.column_stack\\([np.ones\\(len\\(d\\)\\),age,edu]\\); b,aw,ew=np.linalg.lstsq\\(X,inc,rcond=None\\)[0]; print\\('OLS  age_w=%.1f bias=%.0f edu_w=%.3f'%\\(aw,b,ew\\)\\); print\\('noise std=%.0f'%\\(inc-\\(10000+800*age+edu\\)\\).std\\(\\)\\); fr=d['is_fraud'].to_numpy\\(float\\); p=1/\\(1+np.exp\\(-\\(-0.00002*inc+1.0\\)\\)\\); print\\('fraud rate=%.3f theory=%.3f corr=%.3f'%\\(fr.mean\\(\\),p.mean\\(\\),np.corrcoef\\(inc,fr\\)[0,1]\\)\\)\")",
+      "Bash(node -e \"console.log\\('reactflow', require\\('reactflow/package.json'\\).version\\)\")",
+      "Bash(npx tsc *)",
+      "Bash(echo \"tsc-exit:$?\")",
+      "Bash(rm -f src/store/theme.ts src/components/ThemeToggle.tsx)",
+      "Bash(rmdir src/store)",
+      "Bash(npx vite *)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests -q -k \"run or migrat or dataset or api\")",
+      "Bash(DATADOOM_DB_URL=sqlite:///./.tmp_migtest.db .venv/Scripts/python.exe -c ' *)",
+      "Bash(git check-ignore *)",
+      "Bash(ls .venv/Scripts/python.exe)",
+      "Bash(.venv/Scripts/python.exe -c \"import datadoom, networkx, scipy; print\\('ok', datadoom.__version__\\)\")",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_failure.py -q)",
+      "Bash(.venv/Scripts/python.exe -c \"from datadoom.engine import load_spec, generate; r=generate\\(load_spec\\('examples/failure-fraud.datadoom.yaml'\\), seed=42\\); c,i=r.frame,r.injected; print\\('clean NaN total      =', int\\(c.isna\\(\\).sum\\(\\).sum\\(\\)\\)\\); print\\('injected income NaN  = %.3f'%i['income'].isna\\(\\).mean\\(\\)\\); print\\('injected age NaN     = %.3f'%i['age'].isna\\(\\).mean\\(\\)\\); print\\('is_fraud flipped     = %.3f'%\\(c['is_fraud'].to_numpy\\(\\)!=i['is_fraud'].to_numpy\\(\\)\\).mean\\(\\)\\); print\\('leakage corr         = %.3f'%__import__\\('numpy'\\).corrcoef\\(i['fraud_score'], c['is_fraud'].to_numpy\\(float\\)\\)[0,1]\\); [print\\(' diff:', m['type'], {k:v for k,v in m.items\\(\\) if k in \\('realized_rate','flipped_fraction','realized_noise_std','total_shift','realized_correlation'\\)}\\) for m in r.report.failures['modes']]\")",
+      "Bash(.venv/Scripts/python.exe -c 'from datadoom.engine import parse_spec, generate *)",
+      "Bash(.venv/Scripts/python.exe -c 'from datadoom.engine import parse_spec *)",
+      "Bash(.venv/Scripts/python.exe -c \"import sklearn; print\\('sklearn', sklearn.__version__\\)\")",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe .tmp_eval.py)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_failure_audit.py -v)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_failure_audit.py --no-header -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_failure_audit.py --collect-only -q)",
+      "Bash(xargs grep -ln \"preview\")",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -c ' *)",
+      "Bash(.venv/Scripts/python.exe -c \"import mimesis; print\\(mimesis.__version__\\)\")",
+      "Bash(.venv/Scripts/python.exe -m pip install \"mimesis\")",
+      "Bash(.venv/Scripts/python.exe -m pip install -e \".[dev]\" -q)",
+      "Bash(.venv/Scripts/python.exe -c \"import datadoom, importlib.metadata as m; print\\('import ok'\\); print\\('dist:', m.version\\('datadoom'\\)\\)\")",
+      "PowerShell(Get-CimInstance Win32_Process | Where-Object { $_.CommandLine -match 'datadoom|uvicorn|datadoom.exe' } | Select-Object ProcessId, Name, CommandLine | Format-List)",
+      "PowerShell(Stop-Process -Id 31788,29824,29312 -Force -ErrorAction SilentlyContinue)",
+      "PowerShell(\"stopped\")",
+      "Bash(.venv/Scripts/python.exe -c \"import datadoom, importlib.metadata as m; print\\('import ok', m.version\\('datadoom'\\)\\)\")",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_providers.py tests/determinism/ -q)",
+      "Bash(.venv/Scripts/python.exe -c \"import csv; rows=list\\(csv.reader\\(open\\('.tmp_people/data.csv',encoding='utf-8'\\)\\)\\); [print\\(r\\) for r in rows[:4]]\")",
+      "PowerShell(\"cleaned\")",
+      "Bash(.venv/Scripts/datadoom.exe serve *)",
+      "Bash(.venv/Scripts/python.exe -c \"print\\(open\\('status.md',encoding='utf-8'\\).read\\(\\)[-1200:]\\)\")",
+      "Bash(curl -s -o /dev/null -w \"%{http_code}\" http://127.0.0.1:8000/)",
+      "Bash(node -e \"console.log\\(require\\('./package.json'\\).scripts.build\\)\")",
+      "Bash(.venv/Scripts/python.exe -m pip install \"scikit-learn>=1.4,<2\")",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_difficulty.py -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_difficulty_audit.py tests/determinism/test_determinism.py -q)",
+      "Bash(.venv/Scripts/python.exe -)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_failure_audit.py -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_failure_audit.py -q -W error::FutureWarning)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/api/test_api.py::test_difficulty_report_round_trips -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_latent.py tests/unit/test_hashing.py tests/determinism/ -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/api/test_api.py -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/api/test_api.py)",
+      "Bash(xargs grep -ln \"plugin\")",
+      "Bash(sed -n '1,60p' src/datadoom/engine/export/base.py)",
+      "Bash(sed -n '1,108p' src/datadoom/engine/failure/base.py)",
+      "Bash(ls tests/*.py)",
+      "Bash(find tests *)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/plugin_contract/ -q)",
+      "Bash(.venv/Scripts/datadoom.exe plugin *)",
+      "Bash(.venv/Scripts/python.exe -c \"import tempfile,os; print\\(tempfile.mkdtemp\\(\\)\\)\")",
+      "Bash(set /p PDIR=)",
+      "Bash(mktemp -d)",
+      "Bash(DATADOOM_HOME=__CMDSUB_OUTPUT__ .venv/Scripts/python.exe -c ' *)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/plugin_contract tests/api -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/plugin_contract tests/api)",
+      "Bash(.venv/Scripts/python.exe -c \"import importlib.util as u; print\\('pyarrow:', bool\\(u.find_spec\\('pyarrow'\\)\\)\\)\")",
+      "Bash(.venv/Scripts/python.exe -m pip install \"pyarrow>=15,<19\" -q)",
+      "Bash(.venv/Scripts/python.exe -c \"import pyarrow; print\\('pyarrow', pyarrow.__version__\\)\")",
+      "Bash(sed -n '/interface Spec\\\\b/,/^}/p' frontend/src/lib/types.ts)",
+      "Bash(sed -n '40,90p' frontend/src/components/ExportModal.tsx)",
+      "Bash(grep -n \"useSpecHistory\\\\|const {\\\\|present\\\\|set\\(\\\\|mutate\\\\|=> set\\\\|commit\\\\|pushSpec\\\\|spec,\" frontend/src/pages/Canvas.tsx)",
+      "Bash(sed -n '1,30p')",
+      "Bash(sed -n '1,40p' frontend/src/lib/useHistory.ts)",
+      "Bash(.venv/Scripts/datadoom.exe template *)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/determinism tests/golden tests/unit/test_export_formats.py tests/unit/test_templates.py)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_templates.py tests/api/test_api.py -q)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/unit/test_templates.py tests/api/test_api.py)",
+      "Bash(ls src/datadoom/templates/builtin/)",
+      "Bash(find src/datadoom/templates -name \"*.yaml\")",
+      "Bash(.venv/Scripts/datadoom.exe validate *)",
+      "Bash(.venv/Scripts/python.exe -m pytest tests/ -q -k \"template or api\")",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m pytest tests/unit/test_profile.py -q)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m ruff check src tests)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/lint-imports.exe)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m mypy)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m pytest -q)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m pytest)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -c \"print\\(open\\('status.md',encoding='utf-8'\\).read\\(\\)[:3500]\\)\")",
+      "Bash(echo \"ruff: $?\")",
+      "Bash(echo \"lint-imports: $?\")",
+      "Bash(echo \"mypy: $?\")",
+      "Bash(echo \"pytest: $?\")",
+      "Read(//tmp/**)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m pytest tests/api tests/determinism tests/unit/test_metadata.py tests/unit/test_export_formats.py tests/unit/test_store.py -q)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m pytest tests/api/test_api.py::test_resolved_spec_is_locked_and_downloadable -q)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m pytest tests/api/test_api.py::test_resolved_spec_is_locked_and_downloadable)",
+      "Bash(echo \"ruff:$?\")",
+      "Bash(echo \"lint-imports:$?\")",
+      "Bash(echo \"mypy:$?\")",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m pytest tests/api tests/determinism tests/unit/test_metadata.py tests/unit/test_export_formats.py -q)",
+      "Bash(PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m pytest tests/unit/test_audit.py -q)",
+      "Bash(./.venv/Scripts/python.exe -m pytest -q)",
+      "Bash(./.venv/Scripts/ruff.exe check *)",
+      "Bash(./.venv/Scripts/lint-imports.exe)",
+      "Bash(./.venv/Scripts/python.exe -m pytest)",
+      "Bash(ls README.md CHANGELOG.md CONTRIBUTING.md)",
+      "Bash(head -20 README.md)",
+      "Bash(./.venv/Scripts/python.exe -c \"from datadoom.templates import CATALOG; [print\\(t.id, '|', t.level, '|', t.domain, '|', t.title\\) for t in CATALOG]\")",
+      "Bash(./.venv/Scripts/python.exe -c \"from datadoom.templates import CATALOG; t=CATALOG[0]; print\\([f for f in t.__dict__]\\); print\\('---'\\); [print\\(f'{x.id} | {getattr\\(x,\\\\\"level\\\\\",\\\\\"?\\\\\"\\)} | {x.domain} | {x.name}'\\) for x in CATALOG]\")",
+      "Bash(./.venv/Scripts/python.exe -m pip install -e \".[docs]\")",
+      "Bash(./.venv/Scripts/python.exe -c \"import datadoom; print\\('datadoom OK', datadoom.__version__\\)\")",
+      "Bash(./.venv/Scripts/python.exe -c \"import mkdocs, material; print\\('mkdocs OK'\\)\")",
+      "Bash(./.venv/Scripts/python.exe -m mkdocs build --strict)",
+      "Bash(echo \"exit=$?\")",
+      "Bash(./.venv/Scripts/python.exe -m pip install -e . --no-deps)",
+      "Bash(grep -nE \"^/?site|^site/|webdist|\\\\.tmp\" .gitignore)",
+      "Bash(echo \"---exit $?---\")",
+      "Bash(./.venv/Scripts/python.exe -m ruff check src tests)",
+      "Bash(./.venv/Scripts/python.exe -m importlinter.cli lint)",
+      "Bash(./.venv/Scripts/datadoom.exe version *)",
+      "Bash(ls -d .venv/Lib/site-packages/~*)",
+      "Bash(rm -rf .venv/Lib/site-packages/~*)",
+      "Bash(./.venv/Scripts/python.exe -c \"import datadoom; print\\('import OK', datadoom.__version__\\)\")",
+      "Bash(./.venv/Scripts/python.exe -c \"import build; print\\('build', build.__version__\\)\")",
+      "Bash(./.venv/Scripts/python.exe -m pip install -q build)",
+      "Bash(./.venv/Scripts/python.exe -m build)",
+      "Bash(./.venv/Scripts/python.exe -c \"import zipfile; z=zipfile.ZipFile\\([f for f in __import__\\('glob'\\).glob\\('dist/*.whl'\\)][0]\\); n=z.namelist\\(\\); print\\('webdist/index.html:', any\\(x.endswith\\('webdist/index.html'\\) for x in n\\)\\); print\\('templates yaml count:', sum\\(1 for x in n if x.endswith\\('.yaml'\\) and 'templates' in x\\)\\); print\\('total files:', len\\(n\\)\\)\")",
+      "Bash(./.venv/Scripts/python.exe -m pip install -q twine)",
+      "Bash(./.venv/Scripts/python.exe -m twine check dist/*)",
+      "Bash(./.venv/Scripts/python.exe -c \"import zipfile,glob; z=zipfile.ZipFile\\(glob.glob\\('dist/*.whl'\\)[0]\\); n=z.namelist\\(\\); print\\('webdist/index.html in wheel:', any\\(x.endswith\\('webdist/index.html'\\) for x in n\\)\\); print\\('webdist asset files:', sum\\(1 for x in n if 'webdist/assets/' in x\\)\\); import tarfile; t=tarfile.open\\(glob.glob\\('dist/*.tar.gz'\\)[0]\\); tn=t.getnames\\(\\); print\\('webdist/index.html in sdist:', any\\(x.endswith\\('webdist/index.html'\\) for x in tn\\)\\)\")",
+      "Bash(./.tmp_smoke/Scripts/datadoom.exe version *)",
+      "Bash(./.tmp_smoke/Scripts/datadoom.exe run *)",
+      "Bash(./.tmp_smoke/Scripts/python.exe -c \"import importlib.resources as r; print\\('web Canvas bundled OK' if \\(r.files\\('datadoom'\\)/'webdist'/'index.html'\\).is_file\\(\\) else 'MISSING'\\)\")",
+      "Bash(rm -rf .tmp_smoke .tmp_smoke_run)",
+      "Bash(docker --version)",
+      "Bash(docker build *)",
+      "Bash(./.venv/Scripts/mypy.exe)",
+      "Bash(./.venv/Scripts/python.exe -c \"import platform, numpy as np; print\\(f'{platform.system\\(\\)}-{platform.machine\\(\\)}-numpy-{np.__version__}'\\)\")",
+      "Bash(./.venv/Scripts/python.exe -c \"from datadoom.engine import generate, load_spec; import tempfile; r=generate\\(load_spec\\('tests/golden/fraud_numeric.datadoom.yaml'\\), seed=12345, out_dir=tempfile.mkdtemp\\(\\)\\); print\\(r.artifacts[0].checksum_sha256\\)\")",
+      "Bash(./.venv/Scripts/python.exe -m pytest tests/determinism -q)",
+      "Bash(./.venv/Scripts/python.exe -m pytest tests/perf -q)",
+      "Bash(./.venv/Scripts/python.exe -m pytest -m perf -q)",
+      "Bash(./.venv/Scripts/python.exe -m pytest -m perf)"
+    ]
+  }
+}

datadoom-0.1.0.dev0/.dockerignore

@@ -0,0 +1,29 @@
+# Keep the build context small and the image clean.
+.git
+.gitignore
+.github
+.venv
+**/__pycache__
+**/*.pyc
+*.egg-info
+src/*.egg-info
+
+# Frontend build inputs/outputs are produced fresh in the Node stage.
+frontend/node_modules
+frontend/dist
+src/datadoom/webdist
+
+# Docs site build output + legacy doc sets (not needed at runtime).
+site
+docs
+Docs
+
+# Tests and scratch/run output.
+tests
+.tmp_run
+.tmp_*
+out
+tmp
+dist
+build
+*.local.yaml

datadoom-0.1.0.dev0/.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,12 @@
+## What & why
+
+<!-- A short description of the change and the motivation. Link the issue/DDEP. -->
+
+## Checklist
+
+- [ ] Tests added/updated (unit, and determinism tests for any stochastic code)
+- [ ] Docs updated if user-facing (`docs_v2/` and/or `CHANGELOG.md`)
+- [ ] Local gates pass: `ruff check`, `mypy`, `lint-imports`, `pytest`
+- [ ] Architecture upheld: `engine/` stays framework-free; all randomness via `engine.rng`
+- [ ] Spec changes are additive within `datadoom_version: 1`
+- [ ] Commits are DCO **signed off** (`git commit -s`)

datadoom-0.1.0.dev0/.github/workflows/ci.yml

@@ -0,0 +1,82 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  # Pin BLAS to a single thread so the determinism guarantee holds on CI.
+  OMP_NUM_THREADS: "1"
+  OPENBLAS_NUM_THREADS: "1"
+  MKL_NUM_THREADS: "1"
+
+jobs:
+  quality:
+    name: lint + type + import-lint (${{ matrix.os }}, py${{ matrix.python }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python: ["3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python }}
+      - name: Install
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[dev]"
+      - name: Ruff (lint)
+        run: ruff check src tests
+      - name: Mypy (type-check engine strict)
+        run: mypy
+      - name: Import boundaries
+        run: lint-imports
+      - name: Tests
+        run: pytest
+
+  perf:
+    name: perf budget
+    runs-on: ubuntu-latest
+    # Non-gating: wall-clock budgets are informational and must not block a merge
+    # on runner jitter, but a real regression (e.g. an O(n^2) hot path) shows red.
+    continue-on-error: true
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Install
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[dev]"
+      - name: Perf budget
+        run: pytest -m perf -v
+
+  docker:
+    name: docker image build + smoke
+    runs-on: ubuntu-latest
+    # Non-gating: a Docker/registry hiccup must not block a code merge, but a
+    # broken Dockerfile still shows up red on the PR.
+    continue-on-error: true
+    steps:
+      - uses: actions/checkout@v4
+      - uses: docker/setup-buildx-action@v3
+      - name: Build image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: false
+          load: true
+          tags: datadoom:ci
+      - name: Smoke (CLI + bundled web Canvas)
+        run: |
+          docker run --rm datadoom:ci datadoom version
+          docker run --rm datadoom:ci python -c "import importlib.resources as r; assert (r.files('datadoom') / 'webdist' / 'index.html').is_file(); print('web Canvas bundled OK')"

datadoom-0.1.0.dev0/.github/workflows/docs.yml

@@ -0,0 +1,50 @@
+name: Docs
+
+# Builds the mkdocs-material site. On pull requests it only *builds* (a broken
+# build fails the check); on a push to main it builds and publishes to GitHub
+# Pages via the gh-pages branch. Enable Pages once (Settings → Pages → Deploy
+# from branch: gh-pages) — see docs_v2/22_Release_and_Publishing_Runbook.md.
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - "docs_site/**"
+      - "docs_v2/**"
+      - "mkdocs.yml"
+      - ".github/workflows/docs.yml"
+  pull_request:
+    paths:
+      - "docs_site/**"
+      - "docs_v2/**"
+      - "mkdocs.yml"
+      - ".github/workflows/docs.yml"
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+concurrency:
+  group: docs-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    name: build site
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Install docs tooling
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[docs]"
+      - name: Build (verify)
+        run: mkdocs build --strict
+      - name: Deploy to GitHub Pages
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+        run: mkdocs gh-deploy --force

datadoom-0.1.0.dev0/.github/workflows/release.yml

@@ -0,0 +1,144 @@
+name: Release
+
+# Tag-driven, tokenless release. Cutting a release is just:
+#   git tag -s vX.Y.Z && git push origin main --tags
+# See docs_v2/22_Release_and_Publishing_Runbook.md for the one-time PyPI Trusted
+# Publisher + GitHub Environment setup. There are NO long-lived secrets — PyPI
+# upload and provenance signing both use short-lived GitHub OIDC tokens.
+
+on:
+  push:
+    tags: ["v*"]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+env:
+  OMP_NUM_THREADS: "1"
+  OPENBLAS_NUM_THREADS: "1"
+  MKL_NUM_THREADS: "1"
+
+jobs:
+  build:
+    name: build sdist + wheel (with web Canvas) + smoke
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      # The web Canvas is compiled into src/datadoom/webdist/ and shipped inside
+      # the wheel (gitignored in source), so the release build must build it first.
+      - uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+          cache: npm
+          cache-dependency-path: frontend/package-lock.json
+      - name: Build web Canvas -> webdist
+        working-directory: frontend
+        run: |
+          npm ci
+          npm run build
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Build distributions
+        run: |
+          python -m pip install --upgrade pip build twine
+          python -m build
+          python -m twine check dist/*
+
+      - name: Smoke-test the built wheel in a clean venv
+        run: |
+          python -m venv /tmp/smoke
+          /tmp/smoke/bin/python -m pip install --upgrade pip
+          /tmp/smoke/bin/python -m pip install dist/*.whl
+          /tmp/smoke/bin/datadoom version
+          # The shipped wheel must regenerate deterministically and include the SPA.
+          /tmp/smoke/bin/datadoom run examples/tabular-basic.datadoom.yaml --seed 7 --out /tmp/smoke_run
+          /tmp/smoke/bin/python -c "import datadoom, importlib.resources as r; assert (r.files('datadoom') / 'webdist' / 'index.html').is_file(), 'webdist missing from wheel'; print('web Canvas bundled OK')"
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  provenance:
+    name: sign build provenance (keyless)
+    needs: build
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write       # mint the OIDC token Sigstore signs with
+      attestations: write   # write the attestation to the repo
+      contents: read
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist
+      - uses: actions/attest-build-provenance@v1
+        with:
+          subject-path: "dist/*"
+
+  github-release:
+    name: GitHub Release
+    needs: build
+    if: startsWith(github.ref, 'refs/tags/')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist
+      - uses: softprops/action-gh-release@v2
+        with:
+          files: dist/*
+          generate_release_notes: true
+
+  pypi:
+    name: publish to PyPI (OIDC trusted publishing)
+    needs: build
+    if: startsWith(github.ref, 'refs/tags/')
+    runs-on: ubuntu-latest
+    environment: pypi          # register this env + the trusted publisher on PyPI
+    permissions:
+      id-token: write          # tokenless upload via OIDC
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist
+      - uses: pypa/gh-action-pypi-publish@release/v1
+
+  docker:
+    name: build + push image (GHCR)
+    needs: build
+    if: startsWith(github.ref, 'refs/tags/')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: docker/setup-buildx-action@v3
+      - uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ghcr.io/${{ github.repository }}
+          tags: |
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,value=latest
+      - uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

datadoom-0.1.0.dev0/.github/workflows/repro-matrix.yml

@@ -0,0 +1,68 @@
+name: Reproducibility Matrix
+
+# Proves the headline guarantee: on the pinned path, the same (spec_hash, seed)
+# yields a bitwise-identical artifact. Runs the determinism gate across OSes and
+# Python versions. See docs_v2/13_Testing_and_Reproducibility_Strategy.md.
+#
+# Scope (per doc 13): the BITWISE guarantee holds within a single OS/arch on the
+# pinned dependency set; across OS/arch we claim statistical (not bitwise)
+# equivalence. So numpy is pinned to the version the golden checksum was recorded
+# against, and the golden checksum is keyed per platform. Cells whose platform is
+# not yet recorded SKIP and print the value to record (see the job summary).
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+  workflow_dispatch:
+
+env:
+  OMP_NUM_THREADS: "1"
+  OPENBLAS_NUM_THREADS: "1"
+  MKL_NUM_THREADS: "1"
+  # Pin numpy to the version the golden checksums are recorded against so the
+  # golden gate asserts (rather than skipping on version drift). numpy's random
+  # streams are the determinism-critical dependency for the numeric golden spec.
+  DATADOOM_PINNED_NUMPY: "2.4.6"
+
+jobs:
+  repro:
+    name: determinism (${{ matrix.os }}, py${{ matrix.python }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python: ["3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python }}
+      - name: Install (pinned numpy)
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[dev]" "numpy==${{ env.DATADOOM_PINNED_NUMPY }}"
+      - name: Determinism gate
+        run: pytest tests/determinism -v
+      - name: CLI verify round-trip
+        run: |
+          datadoom run examples/tabular-basic.datadoom.yaml --seed 7 --out _run
+          datadoom verify examples/tabular-basic.datadoom.yaml --seed 7 --against _run
+      - name: Report golden checksum for this cell
+        if: always()
+        shell: bash
+        run: |
+          python - <<'PY' | tee -a "$GITHUB_STEP_SUMMARY"
+          import platform, tempfile
+          import numpy as np
+          from datadoom.engine import generate, load_spec
+          r = generate(load_spec("tests/golden/fraud_numeric.datadoom.yaml"),
+                       seed=12345, out_dir=tempfile.mkdtemp())
+          key = f"{platform.system()}-{platform.machine()}-numpy-{np.__version__}"
+          print(f"### Golden checksum")
+          print(f'`"{key}": "{r.artifacts[0].checksum_sha256}"`')
+          print("")
+          print("Add the line above to `tests/golden/checksums.json` to turn this "
+                "cell's golden test from a skip into a bitwise assertion.")
+          PY

datadoom-0.1.0.dev0/.gitignore

@@ -0,0 +1,44 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+.eggs/
+# Anchor build-output dirs to the repo root so they don't swallow source
+# packages like src/datadoom/engine/dist/.
+/build/
+/dist/
+.venv/
+venv/
+env/
+.import_linter_cache/
+
+# Tooling
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+htmlcov/
+coverage.xml
+
+# DataDoom local data / generated artifacts
+.datadoom/
+/out/
+/tmp/
+.tmp_run/
+*.local.yaml
+
+# Frontend (added in a later phase)
+frontend/node_modules/
+frontend/dist/
+src/datadoom/webdist/
+
+# Docs site build output (mkdocs)
+/site/
+
+# OS / editor
+.DS_Store
+Thumbs.db
+.idea/
+.vscode/
+
+t.py