// Recency-intent detection for the retrieval layer.
//
// Keyword search cannot answer a question about WHEN. bm25 ranks by term
// overlap, so "what was the last mail I received" matches documents that
// happen to contain the word "last", and "summarise everything from July"
// matches documents containing "July" — not documents dated in July. Both were
// asked by a real user against a correctly-populated index and both returned
// nothing useful, which is what this module exists to fix: it decides when a
// question is really a date question, and turns it into a date RANGE the index
// can answer with an ordered scan over `occurred_at`.
//
// Deliberately a heuristic on English/German keywords rather than an LLM call:
// it runs on every question, must be instant, and a false positive is cheap
// (the recency hits are fused with the keyword hits, not substituted for them).

// TIMEZONE NOTE: all bounds are built from LOCAL calendar boundaries and then
// serialised as UTC instants. That is deliberate — "July" means the user's
// July, so a mail received 00:30 local on 1 July belongs to it even though its
// stored UTC timestamp reads 30 June. Building the bounds in UTC instead would
// silently drop the first/last hours of every named period for anyone not on
// UTC.
export interface RecencyIntent {
  /** ISO lower bound, if the question named one. */
  since?: string;
  /** ISO upper bound, if the question named a closed period. */
  until?: string;
  /** How many documents the recency leg should contribute. */
  limit: number;
}

const RECENCY_WORDS = [
  // English
  'last', 'latest', 'recent', 'recently', 'newest', 'new', 'today', 'yesterday',
  'this week', 'this month', 'past week', 'past month', 'so far', 'just now', 'current',
  // German — the app ships a German UI and users mix languages freely
  'letzte', 'letzten', 'letzter', 'neueste', 'neuesten', 'neu', 'heute', 'gestern',
  'diese woche', 'diesen monat', 'kürzlich', 'zuletzt', 'aktuell',
];

const MONTHS: Record<string, number> = {
  january: 0, february: 1, march: 2, april: 3, may: 4, june: 5,
  july: 6, august: 7, september: 8, october: 9, november: 10, december: 11,
  januar: 0, februar: 1, märz: 2, maerz: 2, mai: 4, juni: 5,
  juli: 6, oktober: 9, dezember: 11,
};

function startOfDay(d: Date): Date {
  const c = new Date(d);
  c.setHours(0, 0, 0, 0);
  return c;
}

/**
 * @param now injected so the behaviour is testable and deterministic — the
 *   month-name branch depends on "which year is it" and must not be a coin
 *   flip in a test suite.
 */
export function detectRecencyIntent(question: string, now: Date = new Date()): RecencyIntent | null {
  const q = question.toLowerCase();

  // A named month wins over generic recency words: "everything from July" is a
  // bounded range, which is far more useful than "the newest N".
  for (const [name, monthIndex] of Object.entries(MONTHS)) {
    if (!new RegExp(`\\b${name}\\b`).test(q)) continue;
    // A month later than the current one must mean LAST year — "July" asked in
    // March means the July that already happened, not one nine months away.
    const year = monthIndex > now.getMonth() ? now.getFullYear() - 1 : now.getFullYear();
    const since = new Date(year, monthIndex, 1, 0, 0, 0, 0);
    const until = new Date(year, monthIndex + 1, 1, 0, 0, 0, 0);
    return { since: since.toISOString(), until: until.toISOString(), limit: 40 };
  }

  if (/\btoday\b|\bheute\b/.test(q)) {
    return { since: startOfDay(now).toISOString(), limit: 25 };
  }
  if (/\byesterday\b|\bgestern\b/.test(q)) {
    const start = startOfDay(new Date(now.getTime() - 86_400_000));
    return { since: start.toISOString(), until: startOfDay(now).toISOString(), limit: 25 };
  }
  if (/this week|past week|diese woche|letzte woche/.test(q)) {
    return { since: startOfDay(new Date(now.getTime() - 7 * 86_400_000)).toISOString(), limit: 40 };
  }
  if (/this month|past month|diesen monat|letzten monat/.test(q)) {
    return { since: startOfDay(new Date(now.getTime() - 30 * 86_400_000)).toISOString(), limit: 40 };
  }

  if (RECENCY_WORDS.some((w) => (w.includes(' ') ? q.includes(w) : new RegExp(`\\b${w}\\b`).test(q)))) {
    // No period named — "the last mail", "what's new". Unbounded top-N.
    return { limit: 15 };
  }
  return null;
}