mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 01:42:23 +00:00
Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a42352081c | ||
|
|
070f4c5678 | ||
|
|
4b2df89935 |
@@ -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
@@ -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
|
||||
|
||||
|
||||
@@ -1743,7 +1743,15 @@ async function extractStaleFromDB(
|
||||
// `page.updated_at.toISOString()` — the JS Date is ms-truncated, so the
|
||||
// µs-precision DB updated_at stayed strictly greater and the page never
|
||||
// cleared on Postgres. Stamping the exact value makes them equal.
|
||||
processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: page.updated_at_iso });
|
||||
//
|
||||
// Version-arm floor: a page last edited BEFORE LINK_EXTRACTOR_VERSION_TS
|
||||
// would otherwise be stamped below the version watermark and stay
|
||||
// permanently stale (`links_extracted_at < versionTs` re-fires every run).
|
||||
// Stamp max(updated_at, versionTs) — versionTs is always a past release
|
||||
// date, so a concurrent edit's now() still exceeds the stamp and D4 holds.
|
||||
// Tie at ms precision picks updated_at_iso (its µs ≥ versionTs's .000000).
|
||||
const stampTs = new Date(page.updated_at_iso) >= new Date(versionTs) ? page.updated_at_iso : versionTs;
|
||||
processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: stampTs });
|
||||
}
|
||||
|
||||
// Flush NON-swallowing (CDX-4): a throw here propagates out of the sweep so
|
||||
|
||||
@@ -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;
|
||||
}
|
||||
|
||||
@@ -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',
|
||||
|
||||
@@ -28,7 +28,7 @@ import { ensureWellFormed } from './text-safe.ts';
|
||||
* OR updated_at > links_extracted_at`. It is an ISO-8601 string (NOT a number) —
|
||||
* the column is TIMESTAMPTZ and the predicate binds it as `::timestamptz`.
|
||||
*/
|
||||
export const LINK_EXTRACTOR_VERSION_TS = '2026-05-31T00:00:00Z';
|
||||
export const LINK_EXTRACTOR_VERSION_TS = '2026-07-21T00:00:00Z';
|
||||
|
||||
// ─── Entity references ──────────────────────────────────────────
|
||||
|
||||
@@ -80,10 +80,10 @@ export type LinkResolutionType = 'qualified' | 'unqualified';
|
||||
* Directory prefix whitelist. These are the top-level slug dirs the extractor
|
||||
* recognizes as entity references. Upstream canonical + our extensions:
|
||||
* - Gbrain canonical: people, companies, meetings, concepts, deal, civic, project, source, media, yc, projects
|
||||
* - Our domain extensions: tech, finance, personal, openclaw (domain-organized wikis)
|
||||
* - Our domain extensions: tech, finance, personal, openclaw, ops (domain-organized wikis)
|
||||
* - Our entity prefix: entities (we kept some legacy entities/projects/ pages)
|
||||
*/
|
||||
const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities)';
|
||||
const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities|ops)';
|
||||
|
||||
/**
|
||||
* Match `[Name](path)` markdown links pointing to entity directories.
|
||||
@@ -865,7 +865,16 @@ export function queryBasenameIndex(idx: Map<string, string[]>, name: string): st
|
||||
if (!name || typeof name !== 'string') return [];
|
||||
const trimmed = name.trim();
|
||||
if (!trimmed) return [];
|
||||
const hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
|
||||
let hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
|
||||
// Issue #2576 bug 2: path-style refs (`runbooks/2026-05-01-x`) from dirs
|
||||
// outside DIR_PATTERN reach here, but normalizeBasename strips slashes
|
||||
// into a garbage key (`runbooks2026-05-01-x`) that can never hit the
|
||||
// tail-keyed index. Fall back to the path tail so qualified refs resolve
|
||||
// by basename like everything else.
|
||||
if (!hit && trimmed.includes('/')) {
|
||||
const tail = trimmed.slice(trimmed.lastIndexOf('/') + 1).trim();
|
||||
if (tail) hit = idx.get(tail) ?? idx.get(tail.toLowerCase()) ?? idx.get(normalizeBasename(tail));
|
||||
}
|
||||
return hit ? [...hit].sort(basenameSort) : [];
|
||||
}
|
||||
|
||||
|
||||
@@ -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);
|
||||
});
|
||||
|
||||
@@ -209,6 +209,24 @@ describe('gbrain extract --stale', () => {
|
||||
expect(usRows[0]?.eq).toBe(true);
|
||||
});
|
||||
|
||||
test('version-arm floor: page edited BEFORE LINK_EXTRACTOR_VERSION_TS clears after --stale (issue #2576 bug 3)', async () => {
|
||||
// A page whose updated_at predates the version watermark used to be
|
||||
// stamped at its updated_at (< versionTs), so the version arm re-fired
|
||||
// every run — permanently stale. The sweep now floors the stamp at
|
||||
// versionTs. (The #1768 test above also covers this since the v0.42.x
|
||||
// VERSION_TS bump moved its date below the watermark, but this pins the
|
||||
// behavior explicitly so a date "repair" there can't drop coverage.)
|
||||
await engine.putPage('people/alice', personPage('Alice'));
|
||||
await engine.executeRaw(`UPDATE pages SET updated_at = '2000-01-01T00:00:00Z' WHERE slug = 'people/alice'`);
|
||||
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(1);
|
||||
|
||||
await runExtract(engine, ['--stale']);
|
||||
// Pre-floor this stayed 1 forever (stamp < versionTs → version arm re-fires).
|
||||
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
|
||||
await runExtract(engine, ['--stale']);
|
||||
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
|
||||
});
|
||||
|
||||
test('CDX-4 (D2): a link-flush throw aborts the sweep and leaves pages UNSTAMPED', async () => {
|
||||
await engine.putPage('people/alice', personPage('Alice'));
|
||||
await engine.putPage('companies/acme', companyPage('Acme', '[Alice](people/alice) founded [Acme](companies/acme).'));
|
||||
|
||||
@@ -140,6 +140,15 @@ describe('extractEntityRefs', () => {
|
||||
expect(wikiRefs[0].needsResolution).toBe(true);
|
||||
});
|
||||
|
||||
test('recognizes ops/ qualified wikilinks (issue #2576 bug 2)', () => {
|
||||
// `ops` was missing from DIR_PATTERN, so [[ops/...]] fell through to
|
||||
// the generic 2c pass (needsResolution) instead of being a real ref.
|
||||
const refs = extractEntityRefs('Deployed via [[ops/services/pointer-agent]].');
|
||||
expect(refs.length).toBe(1);
|
||||
expect(refs[0].slug).toBe('ops/services/pointer-agent');
|
||||
expect(refs[0].needsResolution).toBeUndefined();
|
||||
});
|
||||
|
||||
test('skips qualified-syntax tokens (those belong to 2a)', () => {
|
||||
// [[wiki:topics/ai]] looks like 2a's qualified shape — even though
|
||||
// it wouldn't satisfy DIR_PATTERN, 2c must not claim it either
|
||||
@@ -1069,6 +1078,15 @@ describe('makeResolver — fallback chain', () => {
|
||||
]);
|
||||
});
|
||||
|
||||
test('resolveBasenameMatches: path-style ref falls back to the tail (issue #2576 bug 2)', async () => {
|
||||
// normalizeBasename strips slashes, so `runbooks/2026-05-01-pointer-agent`
|
||||
// used to normalize to a garbage key that never hit the tail-keyed index.
|
||||
const engine = makeFakeEngineWithSlugs(['ops/changes/2026-05-01-pointer-agent']);
|
||||
const r = makeResolver(engine);
|
||||
expect(await r.resolveBasenameMatches!('runbooks/2026-05-01-pointer-agent'))
|
||||
.toEqual(['ops/changes/2026-05-01-pointer-agent']);
|
||||
});
|
||||
|
||||
test('resolveBasenameMatches: case-insensitive fallback', async () => {
|
||||
const engine = makeFakeEngineWithSlugs(['companies/fast-weigh']);
|
||||
const r = makeResolver(engine);
|
||||
|
||||
Reference in New Issue
Block a user