// distribution-stats.mjs — Statistical divergence utilities for behavioral drift detection.
// Zero external dependencies. <50 lines.
//
// Jensen-Shannon divergence measures how different two probability distributions are.
// Used by post-session-guard.mjs to detect tool distribution shifts within a session.
//
// OWASP: ASI01 (Excessive Agency — behavioral pattern changes may indicate hijacking)

/**
 * Kullback-Leibler divergence KL(P || Q).
 * @param {Map<string, number>} P
 * @param {Map<string, number>} Q
 * @returns {number}
 */
function klDivergence(P, Q) {
  let kl = 0;
  for (const [key, p] of P) {
    if (p === 0) continue;
    const q = Q.get(key) || 0;
    if (q === 0) return Infinity;
    kl += p * Math.log2(p / q);
  }
  return kl;
}

/**
 * Jensen-Shannon divergence. 0 = identical, 1 = fully disjoint (log2 basis).
 * Always finite, symmetric: JSD(P,Q) = JSD(Q,P).
 * @param {Map<string, number>} P - Normalized probability distribution
 * @param {Map<string, number>} Q - Normalized probability distribution
 * @returns {number}
 */
export function jensenShannonDivergence(P, Q) {
  const allKeys = new Set([...P.keys(), ...Q.keys()]);
  const M = new Map();
  for (const key of allKeys) {
    M.set(key, 0.5 * (P.get(key) || 0) + 0.5 * (Q.get(key) || 0));
  }
  return 0.5 * klDivergence(P, M) + 0.5 * klDivergence(Q, M);
}

/**
 * Build normalized probability distribution from category labels.
 * @param {string[]} labels
 * @returns {Map<string, number>} Values sum to 1.0 (empty input → empty map)
 */
export function buildDistribution(labels) {
  if (labels.length === 0) return new Map();
  const counts = new Map();
  for (const label of labels) {
    counts.set(label, (counts.get(label) || 0) + 1);
  }
  const dist = new Map();
  for (const [key, count] of counts) {
    dist.set(key, count / labels.length);
  }
  return dist;
}