"""Learning-only query cache. No validation/test labels or fitted selection.""" import json from pathlib import Path import numpy as np from phase2_h1_worker_v2 import checked, sha, save from phase2_h2_data import cached from s2_custody_common import prediction_inputs from phase3_item_c_loss import candidates def require_learning(view, case): f = view['folds'][0] if case not in f['learning'] or case in f['validation'] or case in f['test']: raise PermissionError('Location truth restricted to learning role') def prepare_queries(view, rows, output): output = Path(output) output.mkdir(exist_ok=False) manifest = {} by_case = {r['case']: r for r in rows} if len(by_case) != len(rows): raise ValueError('Repeated roster case') for case in view['folds'][0]['learning']: require_learning(view, case) # before ANY case array access row = by_case[case] q = prediction_inputs(row) # existing label-free query recipe full = cached(view, case, 'raw_ids') idx = np.searchsorted(full, q['raw_ids']) if np.any(idx >= len(full)) or not np.array_equal(full[idx], q['raw_ids']): raise ValueError('Original query/full-node identity') if q['t_set'] != view['parts'][case]['t_set']: raise ValueError('Original process-time identity') # The original scorer uses physical seconds with exact equality ties. # FP32 residual reconstruction is not an acceptable true-peak source. digest = view['parts'][case]['output_sha256']['seconds.npy'] with (output/'learning-location-target-access.jsonl').open('a') as f: f.write(json.dumps(dict(case=case, role='learning', seconds_sha256=digest))+'\n') seconds = cached(view, case, 'seconds') d = candidates(full, q['raw_ids'], q['counts'], q['coordinates_over_Rg'], seconds[idx]) p = output/(case+'.npz') np.savez(p, **d, original_raw_ids=q['raw_ids'], original_counts=q['counts'], original_anchor_ids=q['ids'], original_near_wall=q['near_wall'], original_coordinates_over_Rg=q['coordinates_over_Rg']) manifest[case] = dict(path=str(p), sha256=sha(p), seconds_sha256=digest, queries_sha256=row['preparation']['output_sha256']['queries.npz'], unique_candidates=len(d['indices']), true_peak_raw_id=d['true_peak_raw_id'], true_peak_ties=d['true_peak_ties'], undefined=False) save(output/'manifest.json', manifest) return manifest def query_data(view, case, manifest): require_learning(view, case) r = manifest[case] with np.load(checked(r['path'], r['sha256']), allow_pickle=False) as z: return {k:z[k].copy() for k in ('indices', 'distances')}