Compare commits

..
Author SHA1 Message Date
97ddee0548 fix(schema-pack): narrow stats catch-all so masked errors surface, not fake 0 pages (#2466)
fetchCountRows and detectDeadPrefixes in src/core/schema-pack/stats.ts
swallowed EVERY engine error into empty results, so any real failure
printed 'Total pages: 0' + a vacuous 100% coverage on a populated brain.
Both catches now swallow only isUndefinedTableError (pre-init brain,
missing pages table) and rethrow everything else. Four regression tests:
real non-zero count on a populated PGLite brain, rethrow on non-missing-
table errors in both catch sites, and the missing-table degrade path.

Takeover of #2493.

Co-authored-by: javieraldape <javieraldape@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:41:12 -07:00
4 changed files with 102 additions and 96 deletions
+2 -50
View File
@@ -3,11 +3,7 @@
*
* Usage:
* gbrain migrate --to supabase [--url <connection_string>]
* (--url is persisted to config.json, mode 0600, so the migrated brain
* works without env — #1271)
* gbrain migrate --to pglite [--path <db_path>]
* (an explicit --path destination is bootstrapped with its own
* <path>/.gbrain/config.json so GBRAIN_HOME=<path> just works — #1271)
* gbrain migrate --to <engine> --force (overwrite non-empty target)
*/
@@ -15,9 +11,9 @@ import { createEngine } from '../core/engine-factory.ts';
import { loadConfig, saveConfig, toEngineConfig, gbrainPath, effectiveEnvDatabaseUrl, type GBrainConfig } from '../core/config.ts';
import type { BrainEngine } from '../core/engine.ts';
import type { EngineConfig } from '../core/types.ts';
import { writeFileSync, readFileSync, existsSync, unlinkSync, mkdirSync, chmodSync } from 'fs';
import { writeFileSync, readFileSync, existsSync, unlinkSync } from 'fs';
import { createHash } from 'crypto';
import { resolve, join } from 'path';
import { resolve } from 'path';
import { createProgress } from '../core/progress.ts';
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
@@ -63,31 +59,6 @@ export interface MigrateManifest {
started_at: string;
}
/**
* #1271 Finding 1: make an explicit `--to pglite --path P` destination usable
* as a standalone brain. Writes `P/.gbrain/config.json` (mode 0600, plus a
* `*` .gitignore) so `GBRAIN_HOME=P` resolves without a manual `gbrain init`.
* Never clobbers an existing config at the destination. Returns the written
* config path, or null when skipped.
*/
export function bootstrapDestinationConfig(dbPath: string): string | null {
const abs = resolve(dbPath);
const dir = join(abs, '.gbrain');
const file = join(dir, 'config.json');
if (existsSync(file)) return null;
mkdirSync(dir, { recursive: true });
const cfg: GBrainConfig = { engine: 'pglite', database_path: abs };
writeFileSync(file, JSON.stringify(cfg, null, 2) + '\n', { mode: 0o600 });
try { chmodSync(file, 0o600); } catch { /* platform-specific */ }
// Same worktree-safety pattern as saveConfig()'s ensureGitignore, scoped
// to the destination home. Don't clobber a user-customized .gitignore.
const gitignore = join(dir, '.gitignore');
if (!existsSync(gitignore)) {
writeFileSync(gitignore, '*\n', { mode: 0o600 });
}
return file;
}
export function migrationTargetId(config: EngineConfig): string {
const locator = config.engine === 'postgres'
? config.database_url ?? ''
@@ -381,25 +352,6 @@ export async function runMigrateEngine(sourceEngine: BrainEngine, args: string[]
};
saveConfig(newConfig);
// #1271 Finding 2 (by design, but say it out loud): the connection string
// is persisted so the migrated brain works without env. Mode 0600.
if (opts.targetEngine === 'postgres' && opts.targetUrl) {
console.error('Note: the --url connection string (including credentials) is persisted to config.json (mode 0600).');
}
// #1271 Finding 1: an explicit --path destination doubles as a standalone
// GBRAIN_HOME. Best-effort — never fail a completed migration over it.
if (opts.targetEngine === 'pglite' && opts.targetPath) {
try {
const written = bootstrapDestinationConfig(opts.targetPath);
if (written) {
console.log(`Destination bootstrapped: ${written} (usable via GBRAIN_HOME=${resolve(opts.targetPath)})`);
}
} catch (e) {
console.warn(` WARN could not bootstrap destination config: ${e instanceof Error ? e.message : String(e)}`);
}
}
// Clean up
clearManifest();
+17 -6
View File
@@ -18,6 +18,7 @@
import type { BrainEngine } from '../engine.ts';
import { loadActivePackBestEffort } from './best-effort.ts';
import type { OperationContext } from '../operations.ts';
import { isUndefinedTableError } from '../utils.ts';
export interface StatsOpts {
/** Single source scope. Omit + omit sourceIds for whole-brain aggregate. */
@@ -164,9 +165,17 @@ async function fetchCountRows(engine: BrainEngine, opts: StatsOpts): Promise<Raw
`;
try {
return await engine.executeRaw<RawCountRow>(sql, params);
} catch {
// Empty / pre-init brain: pages table may not exist yet.
return [];
} catch (err) {
// ONLY swallow the genuine "pages table doesn't exist yet" case
// (empty / pre-init brain). #2466: the old bare `catch {}` masked
// EVERY error — so any engine-level failure (connection, version
// skew, a query incompatibility) was silently converted to 0 rows,
// printing "Total pages: 0" on a populated brain and cascading into
// false "100% coverage" + a starved `schema suggest`. Surface
// everything that is not a missing-table error so the real failure
// is visible instead of hidden behind a fake zero.
if (isUndefinedTableError(err)) return [];
throw err;
}
}
@@ -204,9 +213,11 @@ async function detectDeadPrefixes(
if (cnt === 0) {
hints.push({ type: t.name, prefix });
}
} catch {
// Skip on engine error (no pages table yet, etc.).
continue;
} catch (err) {
// #2466: only skip on the genuine "no pages table yet" case;
// rethrow any other engine error so it isn't silently masked.
if (isUndefinedTableError(err)) continue;
throw err;
}
}
}
@@ -1,40 +0,0 @@
import { describe, expect, test } from 'bun:test';
import { mkdtempSync, mkdirSync, readFileSync, statSync, writeFileSync } from 'fs';
import { tmpdir } from 'os';
import { join, resolve } from 'path';
import { bootstrapDestinationConfig } from '../src/commands/migrate-engine.ts';
import { loadConfigFileOnly } from '../src/core/config.ts';
import { withEnv } from './helpers/with-env.ts';
describe('migrate --to pglite destination bootstrap (#1271)', () => {
test('writes <path>/.gbrain/config.json so GBRAIN_HOME=<path> resolves a brain', async () => {
const dest = mkdtempSync(join(tmpdir(), 'gbrain-dest-'));
const written = bootstrapDestinationConfig(dest);
const file = join(dest, '.gbrain', 'config.json');
expect(written).toBe(file);
const cfg = JSON.parse(readFileSync(file, 'utf-8'));
expect(cfg.engine).toBe('pglite');
expect(cfg.database_path).toBe(resolve(dest));
expect(statSync(file).mode & 0o777).toBe(0o600);
// worktree safety: destination home is git-ignored like saveConfig()'s home
expect(readFileSync(join(dest, '.gbrain', '.gitignore'), 'utf-8')).toBe('*\n');
// The exact failure mode from #1271: config resolution under
// GBRAIN_HOME=<path> used to find nothing ("No brain configured").
await withEnv({ GBRAIN_HOME: dest }, () => {
const loaded = loadConfigFileOnly();
expect(loaded?.engine).toBe('pglite');
expect(loaded?.database_path).toBe(resolve(dest));
});
});
test('never clobbers an existing destination config', () => {
const dest = mkdtempSync(join(tmpdir(), 'gbrain-dest-'));
mkdirSync(join(dest, '.gbrain'), { recursive: true });
writeFileSync(join(dest, '.gbrain', 'config.json'), '{"engine":"postgres"}\n');
expect(bootstrapDestinationConfig(dest)).toBe(null);
expect(JSON.parse(readFileSync(join(dest, '.gbrain', 'config.json'), 'utf-8')).engine).toBe('postgres');
});
});
+83
View File
@@ -222,6 +222,89 @@ describe('runStatsCore — JSON envelope shape', () => {
});
});
describe('runStatsCore — #2466 catch-narrowing (real count + error surfacing)', () => {
// #2466: `gbrain schema stats` reported "Total pages: 0" on a populated
// PGLite brain. The bug was a bare `catch {}` in fetchCountRows (and a
// sibling in detectDeadPrefixes) that converted ANY engine error into 0
// rows. The COUNT query itself is valid on PGLite (proven below), so the
// regression pins two things: (a) a populated brain reports the real,
// non-zero count through the full runStatsCore path; (b) a non-missing-
// table engine error is rethrown, not masked into a fake zero.
it('reports the real non-zero count on a populated PGLite brain (no false 0)', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
// Seed a realistic mix: typed, untyped, multiple types — like the
// 169-page brain in the bug report (scaled down).
for (let i = 0; i < 12; i++) {
const type = i % 3 === 0 ? '' : (i % 3 === 1 ? 'person' : 'company');
await seedPage(`notes/p${i}`, { type, sourcePath: `notes/p${i}.md` });
}
const result = await runStatsCore(ctxOf());
// The core regression: NOT zero.
expect(result.aggregate.total_pages).toBe(12);
expect(result.aggregate.typed_pages).toBe(8);
expect(result.aggregate.untyped_pages).toBe(4);
// And coverage is the honest ratio, not the vacuous 1.0 a 0/0 prints.
expect(result.aggregate.coverage).not.toBe(1.0);
});
});
it('fetchCountRows rethrows a non-missing-table engine error instead of masking it as 0 pages', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
// No pack → detectDeadPrefixes is skipped, isolating the throw to the
// fetchCountRows catch we narrowed. The count query (the GROUP BY one)
// throws a column-level error (SQLSTATE 42703) — the exact class the
// old bare `catch {}` swallowed into 0 rows; everything else succeeds.
__setPackLocatorForTests(() => null);
const boom = Object.assign(new Error('column "type" does not exist'), { code: '42703' });
const stubEngine = {
executeRaw: async (sql: string) => {
if (/GROUP BY source_id/.test(sql)) throw boom; // the fetchCountRows query
return [];
},
} as unknown as PGLiteEngine;
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
await expect(runStatsCore(ctx)).rejects.toThrow('column "type" does not exist');
});
});
it('fetchCountRows still degrades to empty (no throw) on a genuine missing pages table', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
// Pre-init brain shape: the count query hits a missing pages table
// (SQLSTATE 42P01). This is the ONLY case the narrowed catch swallows.
__setPackLocatorForTests(() => null);
const missing = Object.assign(new Error('relation "pages" does not exist'), { code: '42P01' });
const stubEngine = {
executeRaw: async (sql: string) => {
if (/GROUP BY source_id/.test(sql)) throw missing;
return [];
},
} as unknown as PGLiteEngine;
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
const result = await runStatsCore(ctx);
expect(result.aggregate.total_pages).toBe(0);
expect(result.per_source).toEqual([]);
});
});
it('detectDeadPrefixes rethrows a non-missing-table error (sibling catch)', async () => {
await withEnv({ GBRAIN_HOME: tmpDir, GBRAIN_SCHEMA_PACK: 'tiny' }, async () => {
seedTinyPack('tiny', [{ name: 'person', prefix: 'people/' }]);
// fetchCountRows (the GROUP BY query) succeeds → []; the per-prefix
// dead-prefix LIKE query then throws a non-missing-table error, which
// must surface through the narrowed sibling catch.
const stubEngine = {
executeRaw: async (sql: string) => {
if (/GROUP BY source_id/.test(sql)) return []; // count query: empty brain, fine
throw Object.assign(new Error('division by zero'), { code: '22012' }); // the LIKE query
},
} as unknown as PGLiteEngine;
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
await expect(runStatsCore(ctx)).rejects.toThrow('division by zero');
});
});
});
describe('runStatsCore — type/untyped split', () => {
it('treats empty-string type as untyped (not its own bucket)', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {