v0.42.21.0 fix(postgres): module-singleton ownership — canonical landing for the dream-cycle "connect() has not been called" class (#1404/#1471/#1619) (#1805)

* fix(postgres): module-singleton ownership — borrower disconnect no longer nulls the cycle's connection (#1404/#1471/#1619)

gbrain dream on Postgres failed every DB phase with "No database connection:
connect() has not been called": a short-lived borrower probe engine (lint/doctor
config-lift, no poolSize) called db.disconnect() in its own disconnect(), nulling
the shared module singleton the long-lived cycle owner was still using. The module
`sql` is only ever nulled by db.disconnect() (postgres.js auto-reconnects its own
pool), so the failure was always a borrower-disconnect, never an idle-pooler drop.

Fix: db.connect() returns whether THIS call created the singleton (atomic — no
await between the null-check and the sql=postgres() assignment), PostgresEngine
stores it as _ownsModuleSingleton, and disconnect() only calls db.disconnect()
when it owns the connection. Borrowers no-op. Hardening: db.disconnect() snapshots
+nulls sql before awaiting end(); reconnect() shares one in-flight _reconnectPromise.

Tests: new postgres-engine-singleton-ownership.test.ts; expanded DB-gated e2e
matrix (owner/borrower, creation-not-role, symmetric CLI-exit, owner-reconnect-
with-live-borrower); module-style getter asymmetry; #1570 shared-recovery
regression updated to assert the fixed contract.

Co-Authored-By: nullhex-io <noreply@github.com>
Co-Authored-By: joelwp <noreply@github.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v0.42.15.0)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: nullhex-io <noreply@github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

VERSION

@@ -1 +1 @@
-0.42.20.0
+0.42.21.0