endorphin-tabularium-docs/apps/docs/src/lib/ai-research-store.ts

import seed from "../../../../content/research/ai-companies.seed.json";
import { createHash } from "node:crypto";
import { openSiteDatabase } from "./site-database";
import { validateResearch, type ResearchSnapshot } from "./ai-research";

// Each release selects an immutable research revision. New revisions are added
// transactionally, preserving both earlier research and all authentication rows.
export function readResearchSnapshot(snapshot = seed as ResearchSnapshot): ResearchSnapshot {
  validateResearch(snapshot);
  const digest = createHash("sha256").update(JSON.stringify(snapshot)).digest("hex");
  const db = openSiteDatabase();
  try {
    db.exec(`
      CREATE TABLE IF NOT EXISTS research_datasets (
        id TEXT PRIMARY KEY, as_of TEXT NOT NULL, metadata TEXT NOT NULL, content_hash TEXT NOT NULL
      );
      CREATE TABLE IF NOT EXISTS research_categories (
        dataset_id TEXT NOT NULL REFERENCES research_datasets(id),
        id TEXT NOT NULL, payload TEXT NOT NULL, PRIMARY KEY(dataset_id,id)
      );
      CREATE TABLE IF NOT EXISTS research_companies (
        dataset_id TEXT NOT NULL, id TEXT NOT NULL, category_id TEXT NOT NULL,
        name TEXT NOT NULL, founded_year INTEGER, team_size INTEGER,
        revenue_status TEXT NOT NULL, payload TEXT NOT NULL,
        PRIMARY KEY(dataset_id,id),
        FOREIGN KEY(dataset_id,category_id) REFERENCES research_categories(dataset_id,id)
      );
      CREATE TABLE IF NOT EXISTS research_evidence (
        dataset_id TEXT NOT NULL REFERENCES research_datasets(id),
        id TEXT NOT NULL, url TEXT NOT NULL, payload TEXT NOT NULL,
        PRIMARY KEY(dataset_id,id)
      );
      CREATE TABLE IF NOT EXISTS research_observations (
        dataset_id TEXT NOT NULL, id TEXT NOT NULL, company_id TEXT NOT NULL,
        evidence_id TEXT NOT NULL, kind TEXT NOT NULL, amount REAL NOT NULL,
        unit TEXT NOT NULL, record_use TEXT NOT NULL, payload TEXT NOT NULL,
        PRIMARY KEY(dataset_id,id),
        FOREIGN KEY(dataset_id,company_id) REFERENCES research_companies(dataset_id,id),
        FOREIGN KEY(dataset_id,evidence_id) REFERENCES research_evidence(dataset_id,id)
      );
      CREATE TABLE IF NOT EXISTS research_reviews (
        dataset_id TEXT NOT NULL REFERENCES research_datasets(id),
        id TEXT NOT NULL, payload TEXT NOT NULL, PRIMARY KEY(dataset_id,id)
      );
    `);
    // The database transaction also serializes first requests from two workers.
    db.exec("BEGIN IMMEDIATE");
    try {
      const exists = db.prepare("SELECT content_hash FROM research_datasets WHERE id=?")
        .get(snapshot.version) as { content_hash: string } | undefined;
      if (exists && exists.content_hash !== digest)
        throw new Error("Research data changed without a new revision identifier");
      if (!exists) {
        const { categories, companies, observations, evidence, reviews, ...metadata } = snapshot;
        db.prepare("INSERT INTO research_datasets VALUES (?,?,?,?)")
          .run(snapshot.version, snapshot.asOf, JSON.stringify(metadata), digest);
        const insertCategory = db.prepare("INSERT INTO research_categories VALUES (?,?,?)");
        for (const row of categories) insertCategory.run(snapshot.version, row.id, JSON.stringify(row));
        const insertCompany = db.prepare("INSERT INTO research_companies VALUES (?,?,?,?,?,?,?,?)");
        for (const row of companies) insertCompany.run(snapshot.version, row.id, row.cat,
          row.name, row.year, row.team, row.revenueStatus, JSON.stringify(row));
        const insertEvidence = db.prepare("INSERT INTO research_evidence VALUES (?,?,?,?)");
        for (const row of evidence) insertEvidence.run(snapshot.version, row.id, row.url, JSON.stringify(row));
        const insertObservation = db.prepare("INSERT INTO research_observations VALUES (?,?,?,?,?,?,?,?,?)");
        for (const row of observations) insertObservation.run(snapshot.version, row.id, row.company,
          row.evidence, row.kind, row.value, row.unit, row.selection, JSON.stringify(row));
        const insertReview = db.prepare("INSERT INTO research_reviews VALUES (?,?,?)");
        for (const row of reviews) insertReview.run(snapshot.version, row.id, JSON.stringify(row));
      }
      db.exec("COMMIT");
    } catch (error) {
      db.exec("ROLLBACK");
      throw error;
    }
    const meta = db.prepare("SELECT metadata FROM research_datasets WHERE id=?").get(snapshot.version) as { metadata: string };
    // All displayed records come from the site database, not the seed arrays.
    const rows = (table: string) => (db.prepare(
      `SELECT payload FROM ${table} WHERE dataset_id=? ORDER BY id`,
    ).all(snapshot.version) as { payload: string }[]).map((r) => JSON.parse(r.payload));
    const stored: ResearchSnapshot = { ...JSON.parse(meta.metadata),
      categories: rows("research_categories"), companies: rows("research_companies"),
      observations: rows("research_observations"), evidence: rows("research_evidence"),
      reviews: rows("research_reviews") };
    validateResearch(stored);
    return stored;
  } finally { db.close(); }
}