linkder/packages/db/src/queries/stats.ts

import { sql, type SQL } from 'drizzle-orm';
import type { Db } from '../client';

/**
 * Recompute the denormalised ranking counters on `pro_profiles`.
 *
 * `rating_avg`, `rating_count`, `completed_jobs`, `response_rate` and
 * `avg_response_minutes` are inputs to `score()` in @linkdr/shared, and until
 * this existed nothing ever wrote them after the seed. The deck ranked on
 * numbers that were invented once and never moved, and the card told customers
 * "usually replies in 25 min" on the strength of it.
 *
 * They stay denormalised rather than being computed per query: the deck scores
 * every candidate pro on every load, and four correlated subqueries per card is
 * the kind of cost that only shows up once a city is full. The trade is that
 * they must be refreshed when their inputs change — see the callers.
 *
 * Written as one statement over a filtered set so a single pro and a full
 * backfill cannot drift apart. It is idempotent by construction: it derives
 * every value from source rows rather than incrementing anything, so running it
 * twice is the same as running it once, and running it after a missed event
 * repairs the counter rather than compounding the mistake.
 */
function recomputeWhere(where: SQL): SQL {
  return sql`
    UPDATE pro_profiles p SET
      -- Multi-column assignment so each source table is scanned once rather
      -- than once per column. An aggregate with no GROUP BY always returns a
      -- row, so a pro with no history gets (NULL, 0) and not a failed update.
      (rating_avg, rating_count) = (
        SELECT round(avg(rating)::numeric, 2), count(*)::int
        FROM reviews
        -- Published only, and the same predicate pro.reviews reads with. A
        -- count that included embargoed reviews would put a number in the
        -- header that the list underneath it can never reach.
        WHERE subject_id = p.user_id
          AND published_at IS NOT NULL
          AND published_at <= now()
      ),
      completed_jobs = (
        SELECT count(*)::int
        FROM bookings bk
        JOIN matches m ON m.id = bk.match_id
        WHERE m.pro_id = p.user_id
          AND bk.status = 'completed'
      ),
      (response_rate, avg_response_minutes) = (
        SELECT
          /*
           * Answered over decided — NOT over sent.
           *
           * A request still inside its window has not been ignored yet, so
           * counting it as a miss would punish a pro for work that just
           * arrived and let them recover only once it expired. The ones that
           * count against them are those past their expiry with no response,
           * whether or not the lazy sweeper has relabelled the row yet.
           */
          CASE WHEN count(*) FILTER (
                 WHERE responded_at IS NOT NULL OR expires_at < now()
               ) = 0
               THEN NULL
               ELSE round(
                 count(*) FILTER (WHERE responded_at IS NOT NULL)::numeric
                 / count(*) FILTER (WHERE responded_at IS NOT NULL OR expires_at < now()),
                 3)
          END,
          round(avg(
            EXTRACT(EPOCH FROM (responded_at - created_at)) / 60
          ) FILTER (WHERE responded_at IS NOT NULL))::int
        FROM requests
        WHERE pro_id = p.user_id
      ),
      updated_at = now()
    WHERE ${where}
  `;
}

/** Refresh one pro. Call after anything that changes their history. */
export async function recomputeProStats(db: Db, proId: string): Promise<void> {
  await db.execute(recomputeWhere(sql`p.user_id = ${proId}`));
}

/**
 * Refresh every pro. For the seed, for a backfill, and for a nightly sweep that
 * repairs anything a missed event left behind.
 */
export async function recomputeAllProStats(db: Db): Promise<void> {
  await db.execute(recomputeWhere(sql`true`));
}