import json,sys
SRC="/Users/timlingo/neuron-memory-backups/snapshot-pre-repair-20260806.json"
TSV,OUT=sys.argv[1],sys.argv[2]
emb={}
for line in open(TSV,encoding='utf-8',errors='surrogateescape'):
    p=line.rstrip("\n").rsplit("\t",1)
    if len(p)==2 and p[1].count(",")>100: emb[p[0]]=p[1]
print("vectors",len(emb),flush=True)
d=json.load(open(SRC,encoding='utf-8',errors='surrogateescape'))
hit=0
for n in d["nodes"]:
    v=emb.get(n.get("id") or "")
    if v: n["emb"]=v; hit+=1
print("attached",hit,"of",len(d["nodes"]),flush=True)
with open(OUT,"w",encoding='utf-8',errors='surrogateescape') as f:
    json.dump(d,f,ensure_ascii=False)
print("wrote",OUT,flush=True)