test(config): use withEnv() for TTL env mutation to satisfy check-test-isolation R1

CI verify failed: test/postgres-engine-config-cache.test.ts mutated
process.env.GBRAIN_CONFIG_CACHE_TTL_MS directly in beforeEach/afterEach.
Wrap each test body in withEnv() (test/helpers/with-env.ts) instead.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docs/guides/live-sync.md

@@ -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
 

llms-full.txt

@@ -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
 

src/commands/init.ts

@@ -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;
     }

src/core/connection-manager.ts

@@ -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',

src/core/postgres-engine.ts

@@ -5565,30 +5565,78 @@ 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.
-    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;
-    });
+    // 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;
   }
 
   async setConfig(key: string, value: string): Promise<void> {
-    return this.connRetry(async () => {
+    await 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> {
-    return this.connRetry(async () => {
+    const count = await 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[]> {

test/connection-manager.serial.test.ts

@@ -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);
-});

test/e2e/helpers.ts

@@ -29,6 +29,13 @@ 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');
 

test/postgres-engine-config-cache.test.ts

@@ -0,0 +1,112 @@
+/**
+ * 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);
+  }));
+});

test/postgres-engine-config-reconnect.test.ts

@@ -43,7 +43,9 @@ 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 () => {
-    const { engine, reconnects } = makeTornDownEngine([{ value: 'live-value' }]);
+    // 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' }]);
     expect(await engine.getConfig('some.key')).toBe('live-value');
     expect(reconnects()).toBe(1); // exactly one reconnect closed the gap
   });