gbrain/test/sync-walk-dispatch.test.ts

/**
 * v0.18.2.fork.1 — CR-7 (MANDATORY) — Patch #3 sync-walk-dispatch.
 *
 * Without this patch `gbrain sync --repo X` (no `--source` flag) silently
 * mis-dispatches every file to source `default` (or undefined → legacy global
 * config path), because resolveSourceId skips priority 5 (manifest slug-prefix)
 * when slug is undefined. Recon-verified against the fork's source-resolver.ts
 * line 117-125 comment.
 *
 * Patch #3 makes sync.ts performSync + import.ts runImport thread per-file
 * slug to `resolveBySlugPrefix(engine, slug)` so manifest priority 5 fires
 * once per file. Slug no-match falls back to `default-ambiguous` (tombstone).
 *
 * Coverage:
 *   - manifestMode=true: per-file dispatch via slug-prefix → correct source
 *   - cross-prefix collision: longest-prefix wins (TEN-6)
 *   - slug no-match → default-ambiguous tombstone
 *   - manifestMode=false: preserves explicit sourceId for all files (no
 *     regression on the existing repo-wide attribution path)
 *   - Allowlist gate (Patch #2) interacts cleanly: filtered files don't
 *     land at all, regardless of dispatch
 *
 * Failure mode this guards: HTTP 200 from sync, gbrain logs imported
 * successfully, but pages all land in `default`. User won't notice until
 * Stage 2 graph displays wrong groupings.
 */

import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
import { mkdtempSync, mkdirSync, writeFileSync, rmSync } from 'fs';
import { join } from 'path';
import { tmpdir } from 'os';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { runImport } from '../src/commands/import.ts';
import { __invalidateSlugPrefixCache } from '../src/core/source-resolver.ts';
import { __invalidateAllowlistCache } from '../src/core/allowlist-resolver.ts';

let engine: PGLiteEngine;
const cleanupDirs: string[] = [];

function mkRepoFixture(): string {
  const dir = mkdtempSync(join(tmpdir(), 'gbrain-cr7-'));
  cleanupDirs.push(dir);
  return dir;
}

function writeMd(repoRoot: string, relPath: string, body = 'content'): void {
  const full = join(repoRoot, relPath);
  mkdirSync(join(full, '..'), { recursive: true });
  writeFileSync(
    full,
    `---\ntitle: ${relPath}\ntype: note\n---\n${body}\n`,
  );
}

beforeAll(async () => {
  engine = new PGLiteEngine();
  await engine.connect({ type: 'pglite' } as never);
  await engine.initSchema();

  // Mirror the v26 post-migration source taxonomy. v26 already ran via
  // initSchema (it's in MIGRATIONS), creating gstack-meta + default-ambiguous.
  // Add per-project sources so manifest priority 5 has rules to match.
  await engine.executeRaw(
    `INSERT INTO sources (id, name, config) VALUES
      ('memory-dashboard', 'memory-dashboard',
       '{"federated": true, "slug_prefix_rules": ["memory-dashboard/", "projects/triton6564685-memory-dashboard/"]}'::jsonb),
      ('stock-dashboard',  'stock-dashboard',
       '{"federated": true, "slug_prefix_rules": ["stock-dashboard/", "projects/triton6564685-stock-dashboard/"]}'::jsonb)
     ON CONFLICT (id) DO UPDATE SET config = EXCLUDED.config`,
  );
});

afterAll(async () => {
  await engine.disconnect();
  for (const d of cleanupDirs) {
    try { rmSync(d, { recursive: true, force: true }); } catch { /* best-effort */ }
  }
});

beforeEach(() => {
  __invalidateSlugPrefixCache();
  __invalidateAllowlistCache();
});

describe('CR-7 — manifestMode=true dispatches per-file via slug-prefix', () => {
  test('three files in three different prefixes → three correct sources', async () => {
    const repo = mkRepoFixture();
    writeMd(repo, 'retros/2026-05-07-cr7-a.md');
    writeMd(repo, 'projects/triton6564685-stock-dashboard/checkpoints/cr7-a.md');
    writeMd(repo, 'projects/triton6564685-memory-dashboard/notes/cr7-a.md');

    await runImport(engine, [repo, '--no-embed'], { manifestMode: true });

    const rows = await engine.executeRaw<{ slug: string; source_id: string }>(
      `SELECT slug, source_id FROM pages WHERE slug LIKE '%cr7-a%' ORDER BY slug`,
    );
    const map = Object.fromEntries(rows.map((r) => [r.slug, r.source_id]));

    expect(map['retros/2026-05-07-cr7-a']).toBe('gstack-meta');
    expect(map['projects/triton6564685-stock-dashboard/checkpoints/cr7-a']).toBe('stock-dashboard');
    expect(map['projects/triton6564685-memory-dashboard/notes/cr7-a']).toBe('memory-dashboard');
  });

  test('slug-no-match → default-ambiguous (tombstone fallback)', async () => {
    const repo = mkRepoFixture();
    writeMd(repo, 'unknown-prefix/cr7-b.md');

    await runImport(engine, [repo, '--no-embed'], { manifestMode: true });

    const rows = await engine.executeRaw<{ source_id: string }>(
      `SELECT source_id FROM pages WHERE slug = 'unknown-prefix/cr7-b'`,
    );
    expect(rows.length).toBe(1);
    expect(rows[0].source_id).toBe('default-ambiguous');
  });

  test('cross-prefix collision: longest-prefix wins (TEN-6)', async () => {
    const repo = mkRepoFixture();
    // `projects/triton6564685-memory-dashboard/` (39 chars) wins over substring `retros/`
    writeMd(repo, 'projects/triton6564685-memory-dashboard/retros/cr7-c.md');

    await runImport(engine, [repo, '--no-embed'], { manifestMode: true });

    const rows = await engine.executeRaw<{ source_id: string }>(
      `SELECT source_id FROM pages WHERE slug = 'projects/triton6564685-memory-dashboard/retros/cr7-c'`,
    );
    expect(rows[0].source_id).toBe('memory-dashboard');
  });
});

describe('CR-7 — manifestMode=false preserves explicit sourceId (no regression)', () => {
  test('all files land in opts.sourceId regardless of slug', async () => {
    const repo = mkRepoFixture();
    writeMd(repo, 'retros/2026-05-07-cr7-d.md');
    writeMd(repo, 'projects/triton6564685-stock-dashboard/checkpoints/cr7-d.md');

    // No manifestMode flag → legacy attribution: explicit sourceId wins.
    await runImport(engine, [repo, '--no-embed'], { sourceId: 'memory-dashboard' });

    const rows = await engine.executeRaw<{ slug: string; source_id: string }>(
      `SELECT slug, source_id FROM pages WHERE slug LIKE '%cr7-d%' ORDER BY slug`,
    );
    expect(rows.length).toBe(2);
    for (const r of rows) {
      expect(r.source_id).toBe('memory-dashboard');
    }
  });
});

describe('CR-7 — allowlist (Patch #2) interaction', () => {
  test('non-allowlisted files dont land regardless of manifest dispatch', async () => {
    const repo = mkRepoFixture();
    // Strict allowlist: only retros/* allowed.
    writeFileSync(join(repo, '.gbrain-allowlist'), 'retros/*.md\n');
    writeMd(repo, 'retros/2026-05-07-cr7-e.md');
    writeMd(repo, 'projects/triton6564685-stock-dashboard/notes/cr7-e.md');

    await runImport(engine, [repo, '--no-embed'], { manifestMode: true });

    const allowed = await engine.executeRaw<{ source_id: string }>(
      `SELECT source_id FROM pages WHERE slug = 'retros/2026-05-07-cr7-e'`,
    );
    expect(allowed.length).toBe(1);
    expect(allowed[0].source_id).toBe('gstack-meta');

    const blocked = await engine.executeRaw<{ slug: string }>(
      `SELECT slug FROM pages WHERE slug = 'projects/triton6564685-stock-dashboard/notes/cr7-e'`,
    );
    expect(blocked.length).toBe(0);
  });
});