mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 18:32:41 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ba6b5d4690 | ||
|
|
827c1619ac |
@@ -3,7 +3,11 @@
|
||||
*
|
||||
* 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)
|
||||
*/
|
||||
|
||||
@@ -11,9 +15,9 @@ 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 } from 'fs';
|
||||
import { writeFileSync, readFileSync, existsSync, unlinkSync, mkdirSync, chmodSync } from 'fs';
|
||||
import { createHash } from 'crypto';
|
||||
import { resolve } from 'path';
|
||||
import { resolve, join } from 'path';
|
||||
import { createProgress } from '../core/progress.ts';
|
||||
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
|
||||
|
||||
@@ -59,6 +63,31 @@ 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 ?? ''
|
||||
@@ -352,6 +381,25 @@ 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();
|
||||
|
||||
|
||||
@@ -5565,78 +5565,30 @@ export class PostgresEngine implements BrainEngine {
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* perf (#1694 by @Omerbahari): process-lifetime config cache. A single
|
||||
* search fires ~85 getConfig() reads (loadConfigWithEngine x2, plus
|
||||
* mode/cache/intent/rerank/graph-signals resolvers). On a remote pooler
|
||||
* each read is a round-trip; serial they dominate query latency and can
|
||||
* push the op handler past cli.ts's 10s disconnect force-exit, truncating
|
||||
* stdout. First read batch-loads the whole `config` table into this Map
|
||||
* (inside the same connRetry posture as the per-key read — #1603/#1891);
|
||||
* setConfig/unsetConfig write through. TTL bounds staleness for
|
||||
* multi-writer processes; GBRAIN_CONFIG_CACHE_TTL_MS=0 disables.
|
||||
* Only present keys are stored — Map.has() distinguishes known-absent.
|
||||
*/
|
||||
private _configCache: Map<string, string> | null = null;
|
||||
private _configCacheLoadedAt = 0;
|
||||
private _configCacheLoad: Promise<void> | null = null;
|
||||
private get _configCacheTtlMs(): number {
|
||||
const raw = process.env.GBRAIN_CONFIG_CACHE_TTL_MS;
|
||||
if (raw !== undefined) {
|
||||
const n = parseInt(raw, 10);
|
||||
if (Number.isFinite(n) && n >= 0) return n;
|
||||
}
|
||||
return 30_000;
|
||||
}
|
||||
|
||||
async getConfig(key: string): Promise<string | null> {
|
||||
// #1603: a transient pooler drop on this read used to throw / fall through
|
||||
// to defaults silently — which on remote Postgres surfaces as the wrong
|
||||
// search mode/knobs and empty-stdout queries. Both the batch load and the
|
||||
// cache-off per-key read keep the connRetry reconnect posture.
|
||||
const ttl = this._configCacheTtlMs;
|
||||
if (ttl === 0) {
|
||||
return this.connRetry(async () => {
|
||||
const rows = await this.sql`SELECT value FROM config WHERE key = ${key}`;
|
||||
return rows.length > 0 ? (rows[0].value as string) : null;
|
||||
});
|
||||
}
|
||||
if (this._configCache === null || Date.now() - this._configCacheLoadedAt >= ttl) {
|
||||
// Single-flight: concurrent cold reads share one batch load.
|
||||
this._configCacheLoad ??= this.connRetry(async () => {
|
||||
const rows = await this.sql`SELECT key, value FROM config` as unknown as
|
||||
Array<{ key: string; value: string | null }>;
|
||||
const map = new Map<string, string>();
|
||||
for (const r of rows) if (r.value != null) map.set(r.key, r.value);
|
||||
this._configCache = map;
|
||||
this._configCacheLoadedAt = Date.now();
|
||||
}).finally(() => {
|
||||
this._configCacheLoad = null;
|
||||
});
|
||||
await this._configCacheLoad;
|
||||
}
|
||||
return this._configCache!.has(key) ? this._configCache!.get(key)! : null;
|
||||
// search mode/knobs and empty-stdout queries.
|
||||
return this.connRetry(async () => {
|
||||
const rows = await this.sql`SELECT value FROM config WHERE key = ${key}`;
|
||||
return rows.length > 0 ? (rows[0].value as string) : null;
|
||||
});
|
||||
}
|
||||
|
||||
async setConfig(key: string, value: string): Promise<void> {
|
||||
await this.connRetry(async () => {
|
||||
return this.connRetry(async () => {
|
||||
await this.sql`
|
||||
INSERT INTO config (key, value) VALUES (${key}, ${value})
|
||||
ON CONFLICT (key) DO UPDATE SET value = EXCLUDED.value
|
||||
`;
|
||||
});
|
||||
// Write-through so a long-lived process never serves stale config.
|
||||
this._configCache?.set(key, value);
|
||||
}
|
||||
|
||||
async unsetConfig(key: string): Promise<number> {
|
||||
const count = await this.connRetry(async () => {
|
||||
return this.connRetry(async () => {
|
||||
const result = await this.sql`DELETE FROM config WHERE key = ${key}` as unknown as { count: number };
|
||||
return result.count ?? 0;
|
||||
});
|
||||
// Write-through: known-absent, so the cache doesn't serve a stale value.
|
||||
this._configCache?.delete(key);
|
||||
return count;
|
||||
}
|
||||
|
||||
async listConfigKeys(prefix: string): Promise<string[]> {
|
||||
|
||||
@@ -29,13 +29,6 @@ if (existsSync(envPath)) {
|
||||
}
|
||||
}
|
||||
|
||||
// E2E suites seed/rewrite the config table via raw SQL and expect engine
|
||||
// reads to see it immediately; disable the process-lifetime config cache
|
||||
// (#1694) so read semantics match pre-cache behavior. Spawned CLI
|
||||
// subprocesses inherit this. Cache semantics are pinned by
|
||||
// test/postgres-engine-config-cache.test.ts.
|
||||
process.env.GBRAIN_CONFIG_CACHE_TTL_MS ??= '0';
|
||||
|
||||
const DATABASE_URL = process.env.DATABASE_URL;
|
||||
const FIXTURES_DIR = resolve(import.meta.dir, 'fixtures');
|
||||
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
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');
|
||||
});
|
||||
});
|
||||
@@ -1,112 +0,0 @@
|
||||
/**
|
||||
* Process-lifetime config cache (#1694 takeover, by @Omerbahari).
|
||||
*
|
||||
* A single search fires ~85 getConfig() reads; on a remote pooler each is a
|
||||
* round-trip. The first read now batch-loads the whole `config` table into a
|
||||
* Map; setConfig/unsetConfig write through; TTL bounds multi-writer
|
||||
* staleness; GBRAIN_CONFIG_CACHE_TTL_MS=0 restores per-key reads.
|
||||
*
|
||||
* Pure: stubs `_sql` with a call-counting fake; no real DB.
|
||||
*/
|
||||
|
||||
import { describe, it, expect } from 'bun:test';
|
||||
import { PostgresEngine } from '../src/core/postgres-engine.ts';
|
||||
import { withEnv } from './helpers/with-env.ts';
|
||||
|
||||
const FAST_RETRY = { maxRetries: 3, delayMs: 1, delayMaxMs: 1, jitter: 'none' as const };
|
||||
|
||||
/** Engine whose `sql` records every query's template strings and returns `rows`. */
|
||||
function makeEngine(rows: unknown[]) {
|
||||
const e = new PostgresEngine();
|
||||
const calls: string[] = [];
|
||||
(e as unknown as { _connectionStyle: string })._connectionStyle = 'instance';
|
||||
(e as unknown as { _bulkRetryOptsCache: unknown })._bulkRetryOptsCache = FAST_RETRY;
|
||||
(e as unknown as { _sql: unknown })._sql = (strings: TemplateStringsArray) => {
|
||||
calls.push(strings.join('?'));
|
||||
return Promise.resolve(rows);
|
||||
};
|
||||
return { engine: e, calls };
|
||||
}
|
||||
|
||||
/** Run `fn` with GBRAIN_CONFIG_CACHE_TTL_MS set (or cleared when undefined). */
|
||||
const withTtl = (ttl: string | undefined, fn: () => Promise<void>) =>
|
||||
withEnv({ GBRAIN_CONFIG_CACHE_TTL_MS: ttl }, fn);
|
||||
|
||||
describe('PostgresEngine config cache (#1694)', () => {
|
||||
it('batch-loads once and serves repeat reads from the cache', () => withTtl(undefined, async () => {
|
||||
const { engine, calls } = makeEngine([
|
||||
{ key: 'search.mode', value: 'balanced' },
|
||||
{ key: 'embedding_multimodal', value: 'true' },
|
||||
]);
|
||||
expect(await engine.getConfig('search.mode')).toBe('balanced');
|
||||
expect(await engine.getConfig('embedding_multimodal')).toBe('true');
|
||||
expect(await engine.getConfig('search.mode')).toBe('balanced');
|
||||
// One SELECT total — this is the whole point of the fix.
|
||||
expect(calls.length).toBe(1);
|
||||
expect(calls[0]).toContain('SELECT key, value FROM config');
|
||||
}));
|
||||
|
||||
it('returns null for a known-absent key without an extra round-trip', () => withTtl(undefined, async () => {
|
||||
const { engine, calls } = makeEngine([{ key: 'a', value: '1' }]);
|
||||
expect(await engine.getConfig('missing.key')).toBeNull();
|
||||
expect(await engine.getConfig('missing.key')).toBeNull();
|
||||
expect(calls.length).toBe(1);
|
||||
}));
|
||||
|
||||
it('setConfig writes through so subsequent reads see the new value', () => withTtl(undefined, async () => {
|
||||
const { engine, calls } = makeEngine([{ key: 'k', value: 'old' }]);
|
||||
expect(await engine.getConfig('k')).toBe('old');
|
||||
await engine.setConfig('k', 'new');
|
||||
expect(await engine.getConfig('k')).toBe('new');
|
||||
expect(calls.length).toBe(2); // batch load + upsert; no re-read
|
||||
}));
|
||||
|
||||
it('unsetConfig writes through so subsequent reads see absence', () => withTtl(undefined, async () => {
|
||||
const { engine } = makeEngine([{ key: 'k', value: 'v' }]);
|
||||
expect(await engine.getConfig('k')).toBe('v');
|
||||
await engine.unsetConfig('k');
|
||||
expect(await engine.getConfig('k')).toBeNull();
|
||||
}));
|
||||
|
||||
it('concurrent cold reads share a single batch load (single-flight)', () => withTtl(undefined, async () => {
|
||||
const { engine, calls } = makeEngine([{ key: 'k', value: 'v' }]);
|
||||
const [a, b, c] = await Promise.all([
|
||||
engine.getConfig('k'),
|
||||
engine.getConfig('k'),
|
||||
engine.getConfig('other'),
|
||||
]);
|
||||
expect([a, b, c]).toEqual(['v', 'v', null]);
|
||||
expect(calls.length).toBe(1);
|
||||
}));
|
||||
|
||||
it('GBRAIN_CONFIG_CACHE_TTL_MS=0 disables the cache (per-key reads)', () => withTtl('0', async () => {
|
||||
const { engine, calls } = makeEngine([{ value: 'v' }]);
|
||||
expect(await engine.getConfig('k')).toBe('v');
|
||||
expect(await engine.getConfig('k')).toBe('v');
|
||||
expect(calls.length).toBe(2);
|
||||
expect(calls[0]).toContain('SELECT value FROM config WHERE key =');
|
||||
}));
|
||||
|
||||
it('an expired TTL reloads from the database', () => withTtl('1', async () => {
|
||||
const { engine, calls } = makeEngine([{ key: 'k', value: 'v' }]);
|
||||
expect(await engine.getConfig('k')).toBe('v');
|
||||
await new Promise((r) => setTimeout(r, 5));
|
||||
expect(await engine.getConfig('k')).toBe('v');
|
||||
expect(calls.length).toBe(2); // two batch loads
|
||||
}));
|
||||
|
||||
it('the batch load keeps the connRetry reconnect posture (#1603/#1891)', () => withTtl(undefined, async () => {
|
||||
const e = new PostgresEngine();
|
||||
(e as unknown as { _connectionStyle: string })._connectionStyle = 'instance';
|
||||
(e as unknown as { _sql: unknown })._sql = null; // torn-down pool → retryable
|
||||
(e as unknown as { _bulkRetryOptsCache: unknown })._bulkRetryOptsCache = FAST_RETRY;
|
||||
let reconnects = 0;
|
||||
(e as unknown as { reconnect: () => Promise<void> }).reconnect = async () => {
|
||||
reconnects++;
|
||||
(e as unknown as { _sql: unknown })._sql = () =>
|
||||
Promise.resolve([{ key: 'k', value: 'v' }]);
|
||||
};
|
||||
expect(await e.getConfig('k')).toBe('v');
|
||||
expect(reconnects).toBe(1);
|
||||
}));
|
||||
});
|
||||
@@ -43,9 +43,7 @@ function makeTornDownEngine(poolResult: unknown): { engine: PostgresEngine; reco
|
||||
|
||||
describe('PostgresEngine non-batch config accessors self-heal (PR #1891 takeover)', () => {
|
||||
it('getConfig reconnects + retries a null instance pool, then returns the value', async () => {
|
||||
// Rows carry `key` too: getConfig's default cached path batch-loads
|
||||
// `SELECT key, value FROM config` (#1694) through the same connRetry.
|
||||
const { engine, reconnects } = makeTornDownEngine([{ key: 'some.key', value: 'live-value' }]);
|
||||
const { engine, reconnects } = makeTornDownEngine([{ value: 'live-value' }]);
|
||||
expect(await engine.getConfig('some.key')).toBe('live-value');
|
||||
expect(reconnects()).toBe(1); // exactly one reconnect closed the gap
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user