"""Cached-evidence representative ablation; serial cost projections, not wall time.
Selection uses appearance-only groups; unavailable matcher evidence is masked.
"""
from pathlib import Path
import json
import sys
import statistics
import time
from collections import Counter

ROOT=Path(__file__).resolve().parents[3];sys.path.insert(0,str(ROOT/'code'))
from identity_lanes import DecisionPolicy
from analyze import decide,metrics,propagate,infer_groups
DIR=Path(__file__).resolve().parent;OUT=DIR/'evidence'


def main():
    observations=json.loads((OUT/'observations.json').read_text());analysis=json.loads((OUT/'analysis.json').read_text());family=json.loads((DIR/'group-truth.json').read_text())['families'];summary={}
    for res,d in observations['resolutions'].items():
        rows=d['observations'];lookup={x['id']:x for x in rows}; groups=analysis['resolutions'][res]['appearance_groups']; sig=observations['signatures']
        baseline={o['id']:decide(o,'coverage-first',sig) for o in rows}
        arms={}
        for arm in ('sharpest-one','sharpest-two','all'):
            selected=set()
            for group in groups:
                ordered=sorted(group,key=lambda i:lookup[i]['sharpness'],reverse=True)
                selected.update(ordered[:len(group) if arm=='all' else 2 if arm=='sharpest-two' else 1])
            # Unlike the OCR-representative arm, unselected members have no
            # matcher observation. Their individually read OCR may still speak.
            masked=[]
            for o in rows:
                clone=dict(o)
                if o['id'] not in selected:clone['rank']=[];clone['local']={}
                masked.append(clone)
            individual={o['id']:decide(o,'coverage-first',sig) for o in masked}
            available_groups=infer_groups(d,analysis['resolutions'][res]['guarded_edges'],{o['id']:decide(o,'strict',sig) for o in masked})
            inferred,changes=propagate(masked,available_groups,individual,sig,guarded=True)
            matcher_ms=sum(lookup[i]['local_ms'] for i in selected)
            descriptor_ms=sum(lookup[i]['pair_features_ms'] for i in lookup) # group prep retains descriptor extraction
            pair_ms=sum(p['pair_ms'] for p in d['pairs'])
            arms[arm]={'matcher_calls':len(selected),'matcher_ms_serial_projection':round(matcher_ms,1),'group_descriptor_ms':round(descriptor_ms,1),'pair_match_ms':round(pair_ms,1),'total_identity_and_group_ms_serial_projection':round(matcher_ms+descriptor_ms+pair_ms,1),'individual':metrics(masked,individual,family,baseline),'inferred':metrics(masked,inferred,family,baseline),'changes':changes}
        summary[res]=arms
        for arm,v in arms.items():print(res,arm,v['matcher_calls'],v['inferred']['correct'],v['inferred']['wrong'],v['total_identity_and_group_ms_serial_projection'])
    (OUT/'representative.json').write_text(json.dumps({'provenance':observations['provenance'],'arms':summary},ensure_ascii=False,indent=2))

if __name__=='__main__':main()