#!/usr/bin/env python3
"""c4: conditional subset + objective signals + anonymized 3-file split."""
import json, random, os
os.chdir(os.path.expanduser("~/Documents/code/hyungi_Document_Server"))
recs = [json.loads(l) for l in open("reports/passage_rag_capture_2026-05-25.jsonl")]
by = {}
for r in recs:
    by.setdefault(r["q_id"], {})[r["variant"]] = r

def nonempty(r):
    return (r.get("answer_len_chars") or 0) > 0 and r.get("synthesis_status") == "completed"

# conditional subset: both variants retrieved a target-g2 doc AND both produced an answer
cond, excluded = [], []
for qid, vs in by.items():
    p, h = vs.get("prehier"), vs.get("hier_sim_clean")
    if not p or not h:
        excluded.append((qid, "missing variant")); continue
    if not (p["target_doc_present"] and h["target_doc_present"]):
        excluded.append((qid, f"tgt_present p={p['target_doc_present']} h={h['target_doc_present']}")); continue
    if not (nonempty(p) and nonempty(h)):
        excluded.append((qid, f"empty/skip p={p.get('answer_len_chars')}/{p.get('synthesis_status')} h={h.get('answer_len_chars')}/{h.get('synthesis_status')}")); continue
    cond.append(qid)

print(f"=== CONDITIONAL SUBSET (둘 다 tgt_present + non-empty) N={len(cond)} ===")
print("  ", sorted(cond))
print(f"=== EXCLUDED {len(excluded)} ===")
for qid, why in sorted(excluded): print(f"   {qid}: {why}")

def halluc(r): return len((r.get("debug") or {}).get("hallucination_flags") or [])
def grounding_weak(r):
    g = ((r.get("debug") or {}).get("defense_layers") or {}).get("grounding") or {}
    return len(g.get("weak") or [])
def grounding_strong(r):
    g = ((r.get("debug") or {}).get("defense_layers") or {}).get("grounding") or {}
    return len(g.get("strong") or [])

print(f"\n=== OBJECTIVE SIGNALS on conditional subset (N={len(cond)}) ===")
for v in ["prehier", "hier_sim_clean"]:
    rs = [by[q][v] for q in cond]
    print(f"  {v}: halluc_flags={sum(halluc(r) for r in rs)} "
          f"grounding_weak={sum(grounding_weak(r) for r in rs)} "
          f"grounding_strong={sum(grounding_strong(r) for r in rs)} "
          f"avg_answer_len={sum(r['answer_len_chars'] for r in rs)//len(rs)} "
          f"completeness={[r.get('completeness') for r in rs].count('full')}full/"
          f"{[r.get('completeness') for r in rs].count('partial')}part/"
          f"{[r.get('completeness') for r in rs].count('insufficient')}insuf "
          f"refused={sum(1 for r in rs if r.get('refused'))}")

# anonymized 3-file split (conditional only)
rng = random.Random(42)
pairs, key = [], {}
for i, qid in enumerate(sorted(cond)):
    p, h = by[qid]["prehier"], by[qid]["hier_sim_clean"]
    swap = rng.random() < 0.5
    a, b = (p, h) if not swap else (h, p)
    pid = f"pair_{i+1:02d}"
    def spans(r): return [e.get("span_text") for e in (r.get("evidence") or []) if e.get("span_text")]
    pairs.append({
        "pair_id": pid,
        "question": p["query"],
        "answer_A": a["ai_answer"], "evidence_A": spans(a),
        "answer_B": b["ai_answer"], "evidence_B": spans(b),
    })
    key[pid] = {"q_id": qid, "A": a["variant"], "B": b["variant"]}

with open("reports/passage_rag_judge_pairs_2026-05-25.jsonl", "w") as f:
    for pr in pairs: f.write(json.dumps(pr, ensure_ascii=False) + "\n")
with open("reports/passage_rag_judge_key_2026-05-25.json", "w") as f:
    json.dump(key, f, ensure_ascii=False, indent=2)
print(f"\nwrote {len(pairs)} anonymized pairs → passage_rag_judge_pairs_2026-05-25.jsonl")
print("wrote key → passage_rag_judge_key_2026-05-25.json (judge 미제공)")