chore(ops): split /api/health (liveness) from /api/ready (readiness)

Previously /api/health did deep dependency probes (postgres + redis +
minio) and 503'd on any failure. That's readiness behavior, not
liveness — a transient Redis/MinIO blip would tell the orchestrator to
restart the pod when it should only be dropped from the load balancer.

Make /api/health a thin liveness check (returns 200 unconditionally if
the process is responding) and move the deep checks to a new
/api/ready endpoint with the canonical Kubernetes-style 200/503
contract. Docker-compose healthchecks keep pointing at /api/health,
which is now more conservative (no false-positive container restarts).

Documenso/SMTP are intentionally not probed in /api/ready: each tenant
configures its own credentials and a tenant misconfiguration shouldn't
deadline the entire shared CRM.

Also tighten the gdpr-bundle-builder casts: replace the scattered
`as unknown as Record<string, unknown>` double-casts with a small
`toJsonRow<T>()` helper that does the widen narrow→wide in one place
with one cast hop instead of two.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/app/api/health/route.ts

@@ -1,68 +1,15 @@
 import { NextResponse } from 'next/server';
-import { db } from '@/lib/db';
-import { redis } from '@/lib/redis';
-import { minioClient } from '@/lib/minio';
-import { env } from '@/lib/env';
-import { sql } from 'drizzle-orm';
 
-type CheckStatus = 'ok' | 'error';
-
-interface HealthChecks {
-  postgres: CheckStatus;
-  redis: CheckStatus;
-  minio: CheckStatus;
-}
-
-interface HealthResponse {
-  status: 'healthy' | 'degraded';
-  checks: HealthChecks;
-  timestamp: string;
-}
-
-export async function GET(): Promise<NextResponse<HealthResponse>> {
-  const checks: HealthChecks = {
-    postgres: 'error',
-    redis: 'error',
-    minio: 'error',
-  };
-
-  await Promise.allSettled([
-    db
-      .execute(sql`SELECT 1`)
-      .then(() => {
-        checks.postgres = 'ok';
-      })
-      .catch(() => {
-        checks.postgres = 'error';
-      }),
-
-    redis
-      .ping()
-      .then(() => {
-        checks.redis = 'ok';
-      })
-      .catch(() => {
-        checks.redis = 'error';
-      }),
-
-    minioClient
-      .bucketExists(env.MINIO_BUCKET)
-      .then(() => {
-        checks.minio = 'ok';
-      })
-      .catch(() => {
-        checks.minio = 'error';
-      }),
-  ]);
-
-  const allHealthy = Object.values(checks).every((s) => s === 'ok');
-  const status: HealthResponse['status'] = allHealthy ? 'healthy' : 'degraded';
-
-  const body: HealthResponse = {
-    status,
-    checks,
-    timestamp: new Date().toISOString(),
-  };
-
-  return NextResponse.json(body, { status: allHealthy ? 200 : 503 });
+/**
+ * Liveness probe — confirms the Next.js process is responding.
+ *
+ * Returns 200 unconditionally; if the process is wedged or has crashed
+ * the request never lands here at all. Do NOT include database/Redis/MinIO
+ * checks in this endpoint — a transient downstream blip should drop the
+ * pod from the load balancer (readiness), not restart the pod (liveness).
+ *
+ * For deep dependency checks, hit `/api/ready` instead.
+ */
+export async function GET() {
+  return NextResponse.json({ status: 'ok', timestamp: new Date().toISOString() });
 }

src/app/api/ready/route.ts

@@ -0,0 +1,82 @@
+import { NextResponse } from 'next/server';
+import { sql } from 'drizzle-orm';
+
+import { db } from '@/lib/db';
+import { redis } from '@/lib/redis';
+import { minioClient } from '@/lib/minio';
+import { env } from '@/lib/env';
+
+type CheckStatus = 'ok' | 'error';
+
+interface ReadyChecks {
+  postgres: CheckStatus;
+  redis: CheckStatus;
+  minio: CheckStatus;
+}
+
+interface ReadyResponse {
+  status: 'ready' | 'degraded';
+  checks: ReadyChecks;
+  timestamp: string;
+}
+
+/**
+ * Readiness probe — verifies that every backing service this process
+ * needs to serve traffic is reachable. A 503 should drop the pod from the
+ * load balancer until the next probe succeeds; it should not trigger a
+ * pod restart (that's what `/api/health` is for).
+ *
+ * Checks:
+ *   - postgres: `SELECT 1` against the primary
+ *   - redis:    `PING`
+ *   - minio:    `bucketExists(<configured-bucket>)`
+ *
+ * Documenso + SMTP are intentionally not probed here: they're optional
+ * integrations, and each tenant configures its own credentials. A
+ * tenant-misconfigured Documenso instance shouldn't deadline the entire
+ * shared CRM.
+ */
+export async function GET(): Promise<NextResponse<ReadyResponse>> {
+  const checks: ReadyChecks = {
+    postgres: 'error',
+    redis: 'error',
+    minio: 'error',
+  };
+
+  await Promise.allSettled([
+    db
+      .execute(sql`SELECT 1`)
+      .then(() => {
+        checks.postgres = 'ok';
+      })
+      .catch(() => {
+        checks.postgres = 'error';
+      }),
+
+    redis
+      .ping()
+      .then(() => {
+        checks.redis = 'ok';
+      })
+      .catch(() => {
+        checks.redis = 'error';
+      }),
+
+    minioClient
+      .bucketExists(env.MINIO_BUCKET)
+      .then(() => {
+        checks.minio = 'ok';
+      })
+      .catch(() => {
+        checks.minio = 'error';
+      }),
+  ]);
+
+  const allReady = Object.values(checks).every((s) => s === 'ok');
+  const status: ReadyResponse['status'] = allReady ? 'ready' : 'degraded';
+
+  return NextResponse.json(
+    { status, checks, timestamp: new Date().toISOString() },
+    { status: allReady ? 200 : 503 },
+  );
+}