mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 10:22:34 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b0185306e1 |
@@ -21,14 +21,17 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
|
||||
auto-disables prepared statements there and routes `engine.transaction()`
|
||||
(migrations, DDL, sync imports) to a derived **direct** connection
|
||||
(`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
|
||||
IPv4-only host, reads work but sync **silently skips most pages**. This is the
|
||||
number one cause of "sync ran but nothing happened."
|
||||
IPv4-only host it is unreachable. When that happens gbrain now falls back to
|
||||
the pooler automatically (one stderr warning, then single-pool mode for the
|
||||
rest of the process) — but the pooler's ~2-min statement timeout can truncate
|
||||
very long migrations or bulk imports.
|
||||
|
||||
Fix: make the direct connection reachable over IPv4. Either set
|
||||
`GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
|
||||
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
|
||||
running `gbrain sync` and checking that the page count in `gbrain stats` matches
|
||||
the syncable file count in the repo.
|
||||
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
|
||||
`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
|
||||
entirely. Verify by running `gbrain sync` and checking that the page count in
|
||||
`gbrain stats` matches the syncable file count in the repo.
|
||||
|
||||
### The Primitives
|
||||
|
||||
|
||||
+8
-5
@@ -2720,14 +2720,17 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
|
||||
auto-disables prepared statements there and routes `engine.transaction()`
|
||||
(migrations, DDL, sync imports) to a derived **direct** connection
|
||||
(`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
|
||||
IPv4-only host, reads work but sync **silently skips most pages**. This is the
|
||||
number one cause of "sync ran but nothing happened."
|
||||
IPv4-only host it is unreachable. When that happens gbrain now falls back to
|
||||
the pooler automatically (one stderr warning, then single-pool mode for the
|
||||
rest of the process) — but the pooler's ~2-min statement timeout can truncate
|
||||
very long migrations or bulk imports.
|
||||
|
||||
Fix: make the direct connection reachable over IPv4. Either set
|
||||
`GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
|
||||
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
|
||||
running `gbrain sync` and checking that the page count in `gbrain stats` matches
|
||||
the syncable file count in the repo.
|
||||
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
|
||||
`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
|
||||
entirely. Verify by running `gbrain sync` and checking that the page count in
|
||||
`gbrain stats` matches the syncable file count in the repo.
|
||||
|
||||
### The Primitives
|
||||
|
||||
|
||||
@@ -1551,24 +1551,6 @@ export async function checkRerankerHealth(engine: BrainEngine): Promise<Check> {
|
||||
};
|
||||
}
|
||||
|
||||
// Historical #2059 rows were logged as `unknown` before missing reranker
|
||||
// auth was classified at the gateway. Surface repeated unknowns instead of
|
||||
// reporting "ok" while every rerank fails open.
|
||||
const unknownFails = failures.filter((f) => f.reason === 'unknown');
|
||||
if (unknownFails.length >= 3) {
|
||||
const setupHint = unknownFails.some((f) => {
|
||||
const summary = String(f.error_summary ?? '');
|
||||
return summary.includes('ZEROENTROPY_API_KEY') || summary.toLowerCase().includes('api key');
|
||||
})
|
||||
? ' Fix: verify ZEROENTROPY_API_KEY and run `gbrain models doctor`.'
|
||||
: '';
|
||||
return {
|
||||
name: 'reranker_health',
|
||||
status: 'warn',
|
||||
message: `${unknownFails.length} unknown reranker failure(s) in last 7 days.${setupHint}`,
|
||||
};
|
||||
}
|
||||
|
||||
return {
|
||||
name: 'reranker_health',
|
||||
status: 'ok',
|
||||
|
||||
@@ -1078,6 +1078,9 @@ async function initPostgres(opts: {
|
||||
console.warn(' Direct connections are IPv6 only and fail in many environments.');
|
||||
console.warn(' Use the Transaction pooler connection string instead (port 6543):');
|
||||
console.warn(' Supabase Dashboard > Connect (top bar) > Connection String > Transaction pooler');
|
||||
console.warn(' (With a pooler URL, gbrain derives a direct connection for DDL and falls back');
|
||||
console.warn(' to the pooler automatically if that host is unreachable. Power users:');
|
||||
console.warn(' GBRAIN_DIRECT_DATABASE_URL overrides the derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables it.)');
|
||||
console.warn('');
|
||||
}
|
||||
|
||||
@@ -1091,6 +1094,9 @@ async function initPostgres(opts: {
|
||||
if (databaseUrl.includes('supabase.co') && (msg.includes('ECONNREFUSED') || msg.includes('ETIMEDOUT'))) {
|
||||
console.error('Connection failed. Supabase direct connections (db.*.supabase.co:5432) are IPv6 only.');
|
||||
console.error('Use the Transaction pooler connection string instead (port 6543).');
|
||||
console.error('(gbrain derives its own direct connection from pooler URLs for DDL; if that host is');
|
||||
console.error('unreachable it falls back to the pooler. GBRAIN_DIRECT_DATABASE_URL overrides the');
|
||||
console.error('derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables the direct pool entirely.)');
|
||||
}
|
||||
throw e;
|
||||
}
|
||||
|
||||
@@ -3656,15 +3656,7 @@ export async function rerank(input: RerankInput): Promise<RerankResult[]> {
|
||||
// whose request/response shape differs from ZE/llama.cpp (e.g. Voyage with
|
||||
// `top_k` / `data[]`) needs separate adapter hooks in a follow-up plan.
|
||||
const url = `${compat.baseURL.replace(/\/$/, '')}${tp.path ?? '/models/rerank'}`;
|
||||
let auth: { apiKey?: string; headers?: Record<string, string> };
|
||||
try {
|
||||
auth = applyResolveAuth(recipe, cfg, 'reranker');
|
||||
} catch (err) {
|
||||
if (err instanceof AIConfigError) {
|
||||
throw new RerankError(err.message, 'auth');
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
const auth = applyResolveAuth(recipe, cfg, 'reranker');
|
||||
// applyResolveAuth returns { apiKey } for Bearer-style auth (SDK's native
|
||||
// path) or { headers } for custom-header providers (Azure). v0.37.6.0:
|
||||
// recipes can ALSO declare default_headers (attribution etc.) which flow
|
||||
|
||||
@@ -167,6 +167,25 @@ export function deriveDirectUrl(url: string): string | null {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Error codes that mean "the direct host is unreachable from this network"
|
||||
* (#1641). The auto-derived db.<ref>.supabase.co host is IPv6-only without
|
||||
* the paid IPv4 add-on, so ENOTFOUND/ECONNREFUSED here is expected on
|
||||
* IPv4-only networks — we fall back to the pooler instead of failing init.
|
||||
*/
|
||||
const NETWORK_UNREACHABLE_CODES = [
|
||||
'ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH',
|
||||
'ETIMEDOUT', 'CONNECT_TIMEOUT',
|
||||
];
|
||||
|
||||
/** True when err looks like a network-unreachable failure (not auth/SQL). */
|
||||
export function isNetworkUnreachableError(err: unknown): boolean {
|
||||
const code = (err as { code?: unknown } | null)?.code;
|
||||
if (typeof code === 'string' && NETWORK_UNREACHABLE_CODES.includes(code)) return true;
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
return NETWORK_UNREACHABLE_CODES.some(c => msg.includes(c));
|
||||
}
|
||||
|
||||
/**
|
||||
* Read kill-switch state from env. Subordinate to parent manager's state
|
||||
* when present (A2 inheritance).
|
||||
@@ -319,7 +338,30 @@ export class ConnectionManager {
|
||||
throw err;
|
||||
});
|
||||
}
|
||||
const pool = await this._directInit;
|
||||
let pool: Sql | null;
|
||||
try {
|
||||
pool = await this._directInit;
|
||||
} catch (err) {
|
||||
// #1641: the derived direct host (db.<ref>.supabase.co) is IPv6-only
|
||||
// without Supabase's IPv4 add-on. On IPv4-only networks the direct
|
||||
// pool can never connect — permanently fall back to the read pool
|
||||
// (self-activating kill-switch) instead of failing init/migrations.
|
||||
// Non-network errors (auth, SQL) still throw: they mean misconfig,
|
||||
// not unreachability.
|
||||
if (isNetworkUnreachableError(err)) {
|
||||
const alreadyWarned = this._killSwitch;
|
||||
this._killSwitch = true;
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
if (!alreadyWarned) console.error(
|
||||
`gbrain: direct connection to ${this._directUrl ? this.hostOnly(this._directUrl) : 'unknown host'} unreachable (${msg}); ` +
|
||||
'falling back to the pooler for DDL/bulk (long migrations may hit the pooler statement timeout). ' +
|
||||
'Set GBRAIN_DIRECT_DATABASE_URL to a reachable direct URL (e.g. the Session pooler, port 5432) or enable the Supabase IPv4 add-on; ' +
|
||||
'GBRAIN_DISABLE_DIRECT_POOL=1 silences this.',
|
||||
);
|
||||
return this.getReadPool();
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
if (!pool) {
|
||||
// Defensive — initDirectPool should have thrown.
|
||||
throw new Error('connection-manager: direct pool init returned null');
|
||||
@@ -350,8 +392,9 @@ export class ConnectionManager {
|
||||
},
|
||||
};
|
||||
const t0 = Date.now();
|
||||
let pool: Sql | null = null;
|
||||
try {
|
||||
const pool = postgres(this._directUrl, opts);
|
||||
pool = postgres(this._directUrl, opts);
|
||||
// Probe to validate connectivity early.
|
||||
await pool`SELECT 1`;
|
||||
logConnectionEvent({
|
||||
@@ -362,6 +405,9 @@ export class ConnectionManager {
|
||||
});
|
||||
return pool;
|
||||
} catch (err) {
|
||||
// Don't leak the failed pool's sockets/timers (#1641 fallback keeps
|
||||
// the process running afterward).
|
||||
if (pool) await endPoolBounded(pool);
|
||||
logConnectionEvent({
|
||||
pool: 'ddl',
|
||||
op: 'error',
|
||||
|
||||
@@ -154,28 +154,6 @@ describe('gateway.rerank() — happy path', () => {
|
||||
describe('gateway.rerank() — error classification', () => {
|
||||
beforeEach(() => configureZE());
|
||||
|
||||
test('missing required reranker API key → RerankError(auth) before HTTP call', async () => {
|
||||
configureGateway({
|
||||
reranker_model: 'zeroentropyai:zerank-2',
|
||||
env: {},
|
||||
});
|
||||
let called = false;
|
||||
__setRerankTransportForTests(async () => {
|
||||
called = true;
|
||||
return mockResp({ results: [{ index: 0, relevance_score: 0.5 }] });
|
||||
});
|
||||
|
||||
try {
|
||||
await rerank({ query: 'q', documents: ['d'] });
|
||||
throw new Error('should have thrown');
|
||||
} catch (err) {
|
||||
expect(err).toBeInstanceOf(RerankError);
|
||||
expect((err as RerankError).reason).toBe('auth');
|
||||
expect((err as Error).message).toContain('ZEROENTROPY_API_KEY');
|
||||
expect(called).toBe(false);
|
||||
}
|
||||
});
|
||||
|
||||
test('401 → auth', async () => {
|
||||
__setRerankTransportForTests(async () => new Response('Unauthorized', { status: 401 }));
|
||||
try {
|
||||
|
||||
@@ -3,6 +3,7 @@ import {
|
||||
isSupabasePoolerUrl,
|
||||
deriveDirectUrl,
|
||||
readKillSwitchEnv,
|
||||
isNetworkUnreachableError,
|
||||
resolveDirectPoolSize,
|
||||
ConnectionManager,
|
||||
DEFAULT_DIRECT_POOL_SIZE,
|
||||
@@ -238,3 +239,65 @@ describe('ConnectionManager — parent inheritance (A2)', () => {
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('isNetworkUnreachableError (#1641)', () => {
|
||||
test('classifies network codes as unreachable', () => {
|
||||
for (const code of ['ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH', 'ETIMEDOUT', 'CONNECT_TIMEOUT']) {
|
||||
const err = Object.assign(new Error('connect failed'), { code });
|
||||
expect(isNetworkUnreachableError(err)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
test('classifies by message when code absent', () => {
|
||||
expect(isNetworkUnreachableError(new Error('getaddrinfo ENOTFOUND db.abc.supabase.co'))).toBe(true);
|
||||
});
|
||||
|
||||
test('auth/SQL errors are NOT unreachable', () => {
|
||||
expect(isNetworkUnreachableError(new Error('password authentication failed for user "postgres"'))).toBe(false);
|
||||
expect(isNetworkUnreachableError(new Error('syntax error at or near "SELEC"'))).toBe(false);
|
||||
expect(isNetworkUnreachableError(null)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe('ConnectionManager — direct-pool fallback on unreachable host (#1641)', () => {
|
||||
let originalKillSwitch: string | undefined;
|
||||
let originalError: typeof console.error;
|
||||
let errLines: string[];
|
||||
beforeEach(() => {
|
||||
originalKillSwitch = process.env.GBRAIN_DISABLE_DIRECT_POOL;
|
||||
delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
|
||||
originalError = console.error;
|
||||
errLines = [];
|
||||
console.error = (...args: unknown[]) => { errLines.push(args.join(' ')); };
|
||||
});
|
||||
afterEach(() => {
|
||||
console.error = originalError;
|
||||
if (originalKillSwitch === undefined) delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
|
||||
else process.env.GBRAIN_DISABLE_DIRECT_POOL = originalKillSwitch;
|
||||
});
|
||||
|
||||
test('ddl() falls back to the read pool when the direct host is unreachable', async () => {
|
||||
const cm = new ConnectionManager({
|
||||
url: 'postgresql://postgres.abc:p@aws.pooler.supabase.com:6543/db',
|
||||
// 127.0.0.1:9 (discard) → instant ECONNREFUSED, the IPv4-only-network shape.
|
||||
directUrl: 'postgresql://postgres:p@127.0.0.1:9/db',
|
||||
});
|
||||
const fakeReadPool = {} as ReturnType<typeof ConnectionManager.prototype.read>;
|
||||
cm.setReadPool(fakeReadPool);
|
||||
expect(cm.isDualPoolActive()).toBe(true);
|
||||
|
||||
const pool = await cm.ddl(); // without the fix this throws ECONNREFUSED
|
||||
expect(pool).toBe(fakeReadPool);
|
||||
// Self-activating kill-switch: subsequent calls skip the direct pool.
|
||||
expect(cm.isKillSwitchActive()).toBe(true);
|
||||
expect(cm.isDualPoolActive()).toBe(false);
|
||||
expect(cm.describeMode().mode).toBe('single (kill-switch)');
|
||||
// One stderr line mentioning the power-user override.
|
||||
const warning = errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL'));
|
||||
expect(warning.length).toBe(1);
|
||||
|
||||
const again = await cm.ddl();
|
||||
expect(again).toBe(fakeReadPool);
|
||||
expect(errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL')).length).toBe(1);
|
||||
}, 20000);
|
||||
});
|
||||
|
||||
@@ -2,11 +2,6 @@ import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:tes
|
||||
import { mkdirSync, rmSync, writeFileSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { tmpdir } from 'os';
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { withEnv } from './helpers/with-env.ts';
|
||||
import { logRerankFailure } from '../src/core/rerank-audit.ts';
|
||||
|
||||
describe('doctor command', () => {
|
||||
test('doctor module exports runDoctor', async () => {
|
||||
@@ -52,34 +47,6 @@ describe('doctor command', () => {
|
||||
expect(check.issues![0].action).toContain('trigger');
|
||||
});
|
||||
|
||||
test('reranker_health warns on repeated unknown rerank failures', async () => {
|
||||
const { checkRerankerHealth } = await import('../src/commands/doctor.ts');
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-rerank-doctor-'));
|
||||
try {
|
||||
await withEnv({ GBRAIN_AUDIT_DIR: tmpDir }, async () => {
|
||||
for (let i = 0; i < 3; i++) {
|
||||
logRerankFailure({
|
||||
model: 'zeroentropyai:zerank-2',
|
||||
reason: 'unknown',
|
||||
query_hash: `unknown${i}`,
|
||||
doc_count: 30,
|
||||
error_summary: 'ZeroEntropy reranker requires ZEROENTROPY_API_KEY.',
|
||||
});
|
||||
}
|
||||
const check = await checkRerankerHealth({
|
||||
async getConfig(key: string): Promise<string | null> {
|
||||
return key === 'search.reranker.enabled' ? 'true' : null;
|
||||
},
|
||||
} as any);
|
||||
expect(check.status).toBe('warn');
|
||||
expect(check.message).toContain('unknown');
|
||||
expect(check.message).toContain('ZEROENTROPY_API_KEY');
|
||||
});
|
||||
} finally {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test('runDoctor accepts null engine for filesystem-only mode', async () => {
|
||||
const { runDoctor } = await import('../src/commands/doctor.ts');
|
||||
// runDoctor should accept null engine — it runs filesystem checks only.
|
||||
|
||||
@@ -12,14 +12,9 @@
|
||||
*/
|
||||
|
||||
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { applyReranker, type RerankerOpts } from '../../src/core/search/rerank.ts';
|
||||
import { RerankError, type RerankResult } from '../../src/core/ai/gateway.ts';
|
||||
import { readRecentRerankFailures } from '../../src/core/rerank-audit.ts';
|
||||
import type { SearchResult } from '../../src/core/types.ts';
|
||||
import { withEnv } from '../helpers/with-env.ts';
|
||||
|
||||
function makeResult(slug: string, score: number, chunk: string): SearchResult {
|
||||
return {
|
||||
@@ -165,36 +160,6 @@ describe('applyReranker — fail-open on every RerankError reason', () => {
|
||||
expect(out).toEqual(results);
|
||||
});
|
||||
|
||||
test('missing gateway reranker API key fail-opens and audits auth', async () => {
|
||||
const { configureGateway } = await import('../../src/core/ai/gateway.ts');
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-rerank-search-'));
|
||||
try {
|
||||
await withEnv({ GBRAIN_AUDIT_DIR: tmpDir }, async () => {
|
||||
configureGateway({
|
||||
reranker_model: 'zeroentropyai:zerank-2',
|
||||
env: {},
|
||||
});
|
||||
|
||||
const results = [makeResult('a', 1.0, 'doc a')];
|
||||
const out = await applyReranker('q', results, {
|
||||
enabled: true,
|
||||
topNIn: 1,
|
||||
topNOut: null,
|
||||
model: 'zeroentropyai:zerank-2',
|
||||
});
|
||||
|
||||
expect(out).toEqual(results);
|
||||
const failures = readRecentRerankFailures(1);
|
||||
expect(failures).toHaveLength(1);
|
||||
expect(failures[0]!.reason).toBe('auth');
|
||||
expect(failures[0]!.error_summary).toContain('ZEROENTROPY_API_KEY');
|
||||
});
|
||||
} finally {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
configureGateway({ env: { ZEROENTROPY_API_KEY: 'test-key' } });
|
||||
}
|
||||
});
|
||||
|
||||
test('fail-open on non-RerankError throw too', async () => {
|
||||
const results = [makeResult('a', 1.0, 'a')];
|
||||
const opts: RerankerOpts = {
|
||||
|
||||
Reference in New Issue
Block a user