Compare commits

..
Author SHA1 Message Date
00ebc5bb61 fix(doctor): register onboard check names in doctor-categories to stop unknown-check warnings
doctor.ts pushes runAllOnboardChecks results into the checks list, but the
7 onboard check names (embed_staleness, entity_link_coverage,
timeline_coverage, takes_count, dangling_aliases, pack_upgrade_available,
type_proliferation) were never added to doctor-categories.ts, so every
doctor run emitted an 'unknown check name' stderr warn per onboard check.

Registers the 5 data-quality names under BRAIN and the 2 schema-pack names
under META (alphabetical order preserved), and widens the drift-guard test
to scan src/core/onboard/checks.ts alongside src/commands/doctor.ts so
future onboard checks can't drift uncategorized.

Takeover of #1839, rebased onto master (keeps master's timeline_dedup_index).

Co-authored-by: mvanhorn <mvanhorn@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:19:28 -07:00
7 changed files with 71 additions and 154 deletions
+5 -8
View File
@@ -21,17 +21,14 @@ 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 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.
IPv4-only host, reads work but sync **silently skips most pages**. This is the
number one cause of "sync ran but nothing happened."
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.
`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.
`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.
### The Primitives
+5 -8
View File
@@ -2720,17 +2720,14 @@ 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 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.
IPv4-only host, reads work but sync **silently skips most pages**. This is the
number one cause of "sync ran but nothing happened."
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.
`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.
`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.
### The Primitives
-6
View File
@@ -1078,9 +1078,6 @@ 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('');
}
@@ -1094,9 +1091,6 @@ 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;
}
+2 -48
View File
@@ -167,25 +167,6 @@ 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).
@@ -338,30 +319,7 @@ export class ConnectionManager {
throw err;
});
}
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;
}
const pool = await this._directInit;
if (!pool) {
// Defensive — initDirectPool should have thrown.
throw new Error('connection-manager: direct pool init returned null');
@@ -392,9 +350,8 @@ export class ConnectionManager {
},
};
const t0 = Date.now();
let pool: Sql | null = null;
try {
pool = postgres(this._directUrl, opts);
const pool = postgres(this._directUrl, opts);
// Probe to validate connectivity early.
await pool`SELECT 1`;
logConnectionEvent({
@@ -405,9 +362,6 @@ 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',
+11 -3
View File
@@ -35,10 +35,11 @@
*
* The doctor renders both side by side.
*
* Drift contract: every check name that ships in doctor.ts MUST appear in
* Drift contract: every check name that ships through doctor MUST appear in
* exactly one set below. The drift-guard test in
* `test/doctor-categories.test.ts` enforces this by reading doctor.ts source
* via a tagged-string scan and asserting set membership exactly.
* `test/doctor-categories.test.ts` enforces this by reading doctor check
* emitter sources via a tagged-string scan and asserting set membership
* exactly.
*
* If you add a new doctor check, you MUST add its name to the appropriate
* set here. The categorize step in `src/commands/doctor.ts` falls through
@@ -67,12 +68,15 @@ export const BRAIN_CHECK_NAMES: ReadonlySet<string> = new Set([
'conversation_parser_probe_health',
'cross_modal_modality_backfill',
'cycle_freshness',
'dangling_aliases',
'effective_date_health',
'embed_staleness',
'embedding_column_registry',
'embedding_env_override',
'embedding_provider',
'embedding_width_consistency',
'embeddings',
'entity_link_coverage',
'eval_drift',
'extract_atoms_backlog',
'extract_health',
@@ -102,7 +106,9 @@ export const BRAIN_CHECK_NAMES: ReadonlySet<string> = new Set([
'stub_guard_24h',
'sync_failures',
'sync_freshness',
'takes_count',
'takes_weight_grid',
'timeline_coverage',
'unified_multimodal_coverage',
'voice_gate_health',
]);
@@ -170,12 +176,14 @@ export const META_CHECK_NAMES: ReadonlySet<string> = new Set([
'eval_capture',
'minions_migration',
'multi_source_drift',
'pack_upgrade_available',
'schema_pack_active',
'schema_pack_consistency',
'schema_pack_source_drift',
'schema_version',
'slug_fallback_audit',
'timeline_dedup_index',
'type_proliferation',
'upgrade_errors',
]);
-63
View File
@@ -3,7 +3,6 @@ import {
isSupabasePoolerUrl,
deriveDirectUrl,
readKillSwitchEnv,
isNetworkUnreachableError,
resolveDirectPoolSize,
ConnectionManager,
DEFAULT_DIRECT_POOL_SIZE,
@@ -239,65 +238,3 @@ 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);
});
+48 -18
View File
@@ -1,10 +1,10 @@
/**
* Drift guard for src/core/doctor-categories.ts.
*
* Reads src/commands/doctor.ts source via a literal-string scan, enumerates
* every `name: '<...>'` Check name, and asserts each appears in exactly ONE
* category set. The union of the four sets must equal the discovered names
* exactly — no orphans, no extras.
* Reads doctor check emitter source via a literal-string scan, enumerates every
* `name: '<...>'` Check name, and asserts each appears in exactly ONE category
* set. The union of the four sets must equal the discovered names exactly —
* no orphans, no extras.
*
* This is the structural failure the v0.41.19.0 plan-eng-review caught:
* doctor.ts grows new checks regularly; without this guard, the
@@ -25,26 +25,30 @@ import {
} from '../src/core/doctor-categories.ts';
const DOCTOR_TS_PATH = join(import.meta.dir, '..', 'src', 'commands', 'doctor.ts');
const ONBOARD_CHECKS_TS_PATH = join(import.meta.dir, '..', 'src', 'core', 'onboard', 'checks.ts');
const CHECK_SOURCE_PATHS = [DOCTOR_TS_PATH, ONBOARD_CHECKS_TS_PATH];
function enumerateCheckNames(): Set<string> {
const source = readFileSync(DOCTOR_TS_PATH, 'utf-8');
const names = new Set<string>();
// 1) Inline object-literal form: `{ name: 'foo', ... }`.
for (const m of source.matchAll(/name:\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
names.add(m[1]);
}
// 2) Helper-function form: `const name = 'foo';` inside a check helper.
// Catches checks like `nightly_quality_probe_health` and
// `conversation_facts_backlog` that build the Check from a captured
// name constant.
for (const m of source.matchAll(/const\s+name\s*=\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
names.add(m[1]);
for (const path of CHECK_SOURCE_PATHS) {
const source = readFileSync(path, 'utf-8');
// 1) Inline object-literal form: `{ name: 'foo', ... }`.
for (const m of source.matchAll(/name:\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
names.add(m[1]);
}
// 2) Helper-function form: `const name = 'foo';` inside a check helper.
// Catches checks like `nightly_quality_probe_health` and
// `conversation_facts_backlog` that build the Check from a captured
// name constant.
for (const m of source.matchAll(/const\s+name\s*=\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
names.add(m[1]);
}
}
return names;
}
describe('doctor-categories drift guard', () => {
test('every check name in doctor.ts source belongs to exactly one category set', () => {
test('every doctor-emitted check name belongs to exactly one category set', () => {
const discovered = enumerateCheckNames();
const allCategorized = new Set<string>([
...BRAIN_CHECK_NAMES,
@@ -59,7 +63,7 @@ describe('doctor-categories drift guard', () => {
}
if (missing.length > 0) {
throw new Error(
`These check names appear in doctor.ts but are not categorized in ` +
`These check names appear in doctor check emitters but are not categorized in ` +
`src/core/doctor-categories.ts: ${missing.sort().join(', ')}. ` +
`Add each to BRAIN/SKILL/OPS/META_CHECK_NAMES.`,
);
@@ -86,7 +90,7 @@ describe('doctor-categories drift guard', () => {
expect(dupes).toEqual([]);
});
test('every categorized name is currently used in doctor.ts source (no stale entries)', () => {
test('every categorized name is currently used in doctor check emitters (no stale entries)', () => {
const discovered = enumerateCheckNames();
const allCategorized = new Set<string>([
...BRAIN_CHECK_NAMES,
@@ -124,6 +128,14 @@ describe('categorizeCheck', () => {
expect(categorizeCheck('sync_freshness')).toBe('brain');
});
test('returns the right category for onboard data-quality check names', () => {
expect(categorizeCheck('embed_staleness')).toBe('brain');
expect(categorizeCheck('entity_link_coverage')).toBe('brain');
expect(categorizeCheck('timeline_coverage')).toBe('brain');
expect(categorizeCheck('takes_count')).toBe('brain');
expect(categorizeCheck('dangling_aliases')).toBe('brain');
});
test('returns the right category for a known skill name', () => {
expect(categorizeCheck('resolver_health')).toBe('skill');
expect(categorizeCheck('skill_conformance')).toBe('skill');
@@ -140,6 +152,24 @@ describe('categorizeCheck', () => {
expect(categorizeCheck('upgrade_errors')).toBe('meta');
});
test('returns the right category for onboard schema-pack check names without warning', () => {
const originalWrite = process.stderr.write.bind(process.stderr);
const captured: string[] = [];
(process.stderr as { write: typeof process.stderr.write }).write = ((
chunk: string | Uint8Array,
) => {
captured.push(typeof chunk === 'string' ? chunk : Buffer.from(chunk).toString());
return true;
}) as typeof process.stderr.write;
try {
expect(categorizeCheck('pack_upgrade_available')).toBe('meta');
expect(categorizeCheck('type_proliferation')).toBe('meta');
expect(captured.filter((c) => c.includes('[doctor-categories]'))).toEqual([]);
} finally {
(process.stderr as { write: typeof process.stderr.write }).write = originalWrite;
}
});
test('unknown check name falls through to meta with a stderr warn (once per process)', () => {
const originalWrite = process.stderr.write.bind(process.stderr);
const captured: string[] = [];