Method getSegmentCoOccurrence

src/db/queries.ts:706–731

* Names whose segments cover at least `minWords` distinct PROMPT WORDS — * the co-occurrence probe behind the prompt hook's medium tier: the words * "state" and "machine" both being segments of `OrderStateMachine` is strong * evidence the prompt names that symbol in prose. Ordered by covera

(
    variants: Array<{ segment: string; word: string }>,
    minWords: number,
    limit: number,
  )

   * the LIMIT on vocab-heavy repos (#1146).
   */
  getSegmentCoOccurrence(
    variants: Array<{ segment: string; word: string }>,
    minWords: number,
    limit: number,
  ): Array<{ name: string; matches: number }> {
    if (variants.length === 0) return [];
    const placeholders = variants.map(() => '?').join(', ');
    const whens = variants.map(() => 'WHEN ? THEN ?').join(' ');
    const rows = this.db
      .prepare(
        `SELECT name, COUNT(DISTINCT CASE segment ${whens} END) AS matches
         FROM name_segment_vocab
         WHERE segment IN (${placeholders})
         GROUP BY name
         HAVING matches >= ?
         ORDER BY matches DESC, length(name) ASC
         LIMIT ?`,
      )
      .all(
        ...variants.flatMap((v) => [v.segment, v.word]),
        ...variants.map((v) => v.segment),
        minWords,
        limit,
      ) as Array<{ name: string; matches: number }>;
    return rows;
  }

  /** How many distinct names each segment appears in — the rarity signal that
   *  separates a discriminative word ("checkout") from a ubiquitous one ("state"). */