"""New branch only. Old files are hash-anchored read-only inputs.""" import hashlib import importlib.util import json import sys from pathlib import Path sys.dont_write_bytecode = True ROOT = Path('/data/digital-drosophila') MODEL = Path(__file__).resolve().parent EXP = ROOT / 'experiments/phase4am-wholebrain-plastic-interface' AK = ROOT / 'experiments/phase4ak-apl-timing-validation' AL = ROOT / 'experiments/phase4al-mb-credit-transfer' AL_MODEL = ROOT / 'models/male-cns-lif/mb-credit-transfer-audit-v1' AJ_MODEL = ROOT / 'models/male-cns-lif/apl-timing-lab-v1' AG = ROOT / 'experiments/phase4ag-author-apl-r2' H = ROOT / 'experiments/phase4h-dopamine-plasticity' META = ROOT / 'datasets/male-cns-v1.0/processed/neuron-only/neuron-index/unified-metadata.parquet' CFG = json.loads((MODEL / 'config.json').read_text(encoding='utf-8')) PINS = { 'models/male-cns-lif/mb-credit-transfer-audit-v1/context.py': '1626873baa224fab5d427a1fab1d6f840f14814152914ac4c2d6aa7a4f0bb1f6', 'models/male-cns-lif/mb-credit-transfer-audit-v1/manifest.json': '72e4b4e2c53c258939ca355f31eeba2cd6381e126a61efeea651d8bac8df5328', 'experiments/phase4al-mb-credit-transfer/manifest.json': 'a22de7d85cbfe760070ff55f5666e74475a3335c63bbd37b41241a94be7e3eea', 'experiments/phase4al-mb-credit-transfer/audit/final-status.json': 'ec846137531d3bea357f57364857b5de5ca2381a01aac3ebb1b7ade79059209e', 'models/male-cns-lif/apl-timing-lab-v1/gpu_timing.py': 'af1975ba5e5e700208c0a598d3cbe648a3cf10885c6231239b6e4b28f76d173b', 'models/male-cns-lif/apl-timing-lab-v1/compare_timing.py': '9010f070fba9b7c9cf2d86187ee2abc57f3ac606ebc08a42baad4f3922b51734', 'models/male-cns-lif/phase4c.py': '5ec83a132deb8ba20e62dab485537c2414016fe2fece546198d61c0668d75b6b', 'models/male-cns-lif/mb-physiology-v1/phase4j.py': 'abb4574da85f00bd9ef61024c65993ef81d42651ff8d8d63c15dd69c6222471e', 'experiments/phase4h-dopamine-plasticity/plastic-mask/plastic-edge-candidates.parquet': 'e5075ee3e5a0edf3a4d197453847163cc295b254f21c67203159bba204b12a76', 'experiments/phase4h-dopamine-plasticity/plastic-mask/plastic-edge-ids.int64.npy': '8b0fb6eb2e6c31da4d17dc20d890aa3f367e514f05642de5bad6b42a1611c05b', 'experiments/phase4h-dopamine-plasticity/plastic-mask/plastic-edge-mask.bool.npy': 'e8b7a439f07eae6e36729d6577a2c5e4a4c7aa4b15e97fc5266d7278db9e150e', 'datasets/male-cns-v1.0/processed/neuron-only/neuron-index/unified-metadata.parquet': '922af16846a065c3dbfca7c11146b83ca217fcbd7392edc745f444a04eae8c63' } def digest(path): h = hashlib.sha256() with Path(path).open('rb') as f: for block in iter(lambda: f.read(8 << 20), b''): h.update(block) return h.hexdigest() def read(path): return json.loads(Path(path).read_text(encoding='utf-8')) def save(path, value): path = Path(path); path.parent.mkdir(parents=True, exist_ok=True) with path.open('x', encoding='utf-8') as f: json.dump(value, f, indent=2, ensure_ascii=False, allow_nan=False) f.write('\n') def write_npz(path, **values): import numpy as np with Path(path).open('xb') as f: np.savez_compressed(f, **values) def load_module(name, path, expected_hash): data = Path(path).read_bytes() assert hashlib.sha256(data).hexdigest() == expected_hash, str(path) spec = importlib.util.spec_from_file_location(name, path) module = importlib.util.module_from_spec(spec) sys.modules[name] = module exec(compile(data, str(path), 'exec'), module.__dict__) return module def sources(): return {p.relative_to(MODEL).as_posix(): digest(p) for p in sorted(MODEL.rglob('*')) if p.is_file() and '__pycache__' not in p.parts and p.name not in ('manifest.json', 'checksums.sha256')} def integrity(): old = load_module('sealed_al_context_am', AL_MODEL / 'context.py', PINS['models/male-cns-lif/mb-credit-transfer-audit-v1/context.py']) result = old.integrity() sys.path.insert(0, str(ROOT / 'models/male-cns-lif/terminal-scope-diagnostic-v1')) from diagnostic import manifest_check for path in (AL_MODEL, AL): result[path.relative_to(ROOT).as_posix()] = manifest_check(path, digest) assert all(row['pass'] for row in result.values()) return result def check(full=False): reg = read(EXP / 'protocol/preregistered.json') assert reg['sources'] == sources() and reg['config'] == CFG for row in reg['inputs'] if full else []: assert digest(ROOT / row['path']) == row['sha256'], row['path'] for row in read(EXP / 'protocol/prepared-hashes.json'): assert digest(EXP / row['path']) == row['sha256'], row['path'] return reg def bit_equal(a, b): return a.dtype == b.dtype and a.shape == b.shape and a.tobytes() == b.tobytes() def budget(): size = sum(p.stat().st_size for p in EXP.rglob('*') if p.is_file()) assert size < CFG['output_budget_bytes'], 'Output budget exceeded; stop and preserve all partials' return size def seal(root): rows = [dict(path=p.relative_to(root).as_posix(), bytes=p.stat().st_size, sha256=digest(p)) for p in sorted(root.rglob('*')) if p.is_file() and '__pycache__' not in p.parts] save(root / 'manifest.json', dict(root=str(root), files=rows)) with (root / 'checksums.sha256').open('x', encoding='utf-8') as f: for row in rows: f.write(row['sha256'] + ' ' + row['path'] + '\n') f.write(digest(root / 'manifest.json') + ' manifest.json\n')