"""Cluster 내 LLM 입력 선정 — top-k + MMR diversity + ai_summary truncate.

순수 top-relevance 는 동일 사건 중복 요약문에 편향되므로 MMR 로 다양성 확보.
ai_summary 길이는 LLM 토큰 보호를 위해 SUMMARY_TRUNCATE 로 제한.
"""

import numpy as np

K_PER_CLUSTER = 5
LAMBDA_MMR = 0.7         # relevance 70% / diversity 30%
SUMMARY_TRUNCATE = 300   # long tail ai_summary 방어


def _normalize(v: np.ndarray) -> np.ndarray:
    norm = float(np.linalg.norm(v))
    if norm == 0.0:
        return v
    return v / norm


def select_for_llm(cluster: dict, k: int = K_PER_CLUSTER) -> list[dict]:
    """cluster 내 LLM 호출용 대표 article 들 선정.

    Args:
        cluster: clustering.cluster_country 결과 단일 cluster
        k: 선정 개수 (기본 5)

    Returns:
        선정된 doc dict 리스트. 각 항목에 ai_summary_truncated 필드가 추가됨.
    """
    members = cluster["members"]
    if len(members) <= k:
        selected = list(members)
    else:
        centroid = cluster["centroid"]
        # relevance = centroid 유사도 × decay weight
        for m in members:
            v = _normalize(m["embedding"])
            m["_rel"] = float(np.dot(centroid, v)) * m["weight"]

        first = max(members, key=lambda x: x["_rel"])
        selected = [first]
        candidates = [m for m in members if m is not first]

        while len(selected) < k and candidates:
            def mmr_score(c: dict) -> float:
                v = _normalize(c["embedding"])
                max_sim = max(
                    float(np.dot(v, _normalize(s["embedding"])))
                    for s in selected
                )
                return LAMBDA_MMR * c["_rel"] - (1.0 - LAMBDA_MMR) * max_sim

            pick = max(candidates, key=mmr_score)
            selected.append(pick)
            candidates.remove(pick)

    # LLM 입력 토큰 보호
    for m in selected:
        m["ai_summary_truncated"] = (m.get("ai_summary") or "")[:SUMMARY_TRUNCATE]

    return selected