fix(api): add timeouts for OIDC discovery fetch and DB connection

- OIDC discovery fetch in initAuth() now has a 5s AbortSignal.timeout
  to fail fast instead of hanging indefinitely when the auth server is unreachable.
  This was identified as a root cause of startup ECONNRESET crashes on UAT
  where ztunnel drops TCP connections before headers arrive.

- DB postgres client now sets connect_timeout: 5 so failed connection attempts
  fail fast rather than hanging the startup sequence.

- Graceful shutdown timeout tightened to 8s (from 10s) to avoid
  getting killed by Kubernetes liveness-probe deadline while draining.

Fixes GRO-1678.

Co-Authored-By: Paperclip <noreply@paperclip.ing>

packages/db/src/index.ts

@@ -12,7 +12,7 @@ export function getDb() {
   if (_db) return _db;
   const url = process.env.DATABASE_URL;
   if (!url) throw new Error("DATABASE_URL is not set");
-  const client = postgres(url, { max: 10 });
+  const client = postgres(url, { max: 10, connect_timeout: 5 });
   _db = drizzle(client, { schema });
   return _db;
 }

pnpm-lock.yaml

@@ -970,79 +970,66 @@ packages:
     resolution: {integrity: sha512-DV6fJoxEYWJOvaZIsok7KrYl0tPvga5OZ2yvKHNNYyk/2roMLqQAbGhr78EQ5YhHpnhLKJD3S1WFusAkmUuV5g==}
     cpu: [arm]
     os: [linux]
-    libc: [glibc]
 
   '@rollup/rollup-linux-arm-musleabihf@4.60.3':
     resolution: {integrity: sha512-mQKoJAzvuOs6F+TZybQO4GOTSMUu7v0WdxEk24krQ/uUxXoPTtHjuaUuPmFhtBcM4K0ons8nrE3JyhTuCFtT/w==}
     cpu: [arm]
     os: [linux]
-    libc: [musl]
 
   '@rollup/rollup-linux-arm64-gnu@4.60.3':
     resolution: {integrity: sha512-Whjj2qoiJ6+OOJMGptTYazaJvjOJm+iKHpXQM1P3LzGjt7Ff++Tp7nH4N8J/BUA7R9IHfDyx4DJIflifwnbmIA==}
     cpu: [arm64]
     os: [linux]
-    libc: [glibc]
 
   '@rollup/rollup-linux-arm64-musl@4.60.3':
     resolution: {integrity: sha512-4YTNHKqGng5+yiZt3mg77nmyuCfmNfX4fPmyUapBcIk+BdwSwmCWGXOUxhXbBEkFHtoN5boLj/5NON+u5QC9tg==}
     cpu: [arm64]
     os: [linux]
-    libc: [musl]
 
   '@rollup/rollup-linux-loong64-gnu@4.60.3':
     resolution: {integrity: sha512-SU3kNlhkpI4UqlUc2VXPGK9o886ZsSeGfMAX2ba2b8DKmMXq4AL7KUrkSWVbb7koVqx41Yczx6dx5PNargIrEA==}
     cpu: [loong64]
     os: [linux]
-    libc: [glibc]
 
   '@rollup/rollup-linux-loong64-musl@4.60.3':
     resolution: {integrity: sha512-6lDLl5h4TXpB1mTf2rQWnAk/LcXrx9vBfu/DT5TIPhvMhRWaZ5MxkIc8u4lJAmBo6klTe1ywXIUHFjylW505sg==}
     cpu: [loong64]
     os: [linux]
-    libc: [musl]
 
   '@rollup/rollup-linux-ppc64-gnu@4.60.3':
     resolution: {integrity: sha512-BMo8bOw8evlup/8G+cj5xWtPyp93xPdyoSN16Zy90Q2QZ0ZYRhCt6ZJSwbrRzG9HApFabjwj2p25TUPDWrhzqQ==}
     cpu: [ppc64]
     os: [linux]
-    libc: [glibc]
 
   '@rollup/rollup-linux-ppc64-musl@4.60.3':
     resolution: {integrity: sha512-E0L8X1dZN1/Rph+5VPF6Xj2G7JJvMACVXtamTJIDrVI44Y3K+G8gQaMEAavbqCGTa16InptiVrX6eM6pmJ+7qA==}
     cpu: [ppc64]
     os: [linux]
-    libc: [musl]
 
   '@rollup/rollup-linux-riscv64-gnu@4.60.3':
     resolution: {integrity: sha512-oZJ/WHaVfHUiRAtmTAeo3DcevNsVvH8mbvodjZy7D5QKvCefO371SiKRpxoDcCxB3PTRTLayWBkvmDQKTcX/sw==}
     cpu: [riscv64]
     os: [linux]
-    libc: [glibc]
 
   '@rollup/rollup-linux-riscv64-musl@4.60.3':
     resolution: {integrity: sha512-Dhbyh7j9FybM3YaTgaHmVALwA8AkUwTPccyCQ79TG9AJUsMQqgN1DDEZNr4+QUfwiWvLDumW5vdwzoeUF+TNxQ==}
     cpu: [riscv64]
     os: [linux]
-    libc: [musl]
 
   '@rollup/rollup-linux-s390x-gnu@4.60.3':
     resolution: {integrity: sha512-cJd1X5XhHHlltkaypz1UcWLA8AcoIi1aWhsvaWDskD1oz2eKCypnqvTQ8ykMNI0RSmm7NkTdSqSSD7zM0xa6Ig==}
     cpu: [s390x]
     os: [linux]
-    libc: [glibc]
 
   '@rollup/rollup-linux-x64-gnu@4.60.3':
     resolution: {integrity: sha512-DAZDBHQfG2oQuhY7mc6I3/qB4LU2fQCjRvxbDwd/Jdvb9fypP4IJ4qmtu6lNjes6B531AI8cg1aKC2di97bUxA==}
     cpu: [x64]
     os: [linux]
-    libc: [glibc]
 
   '@rollup/rollup-linux-x64-musl@4.60.3':
     resolution: {integrity: sha512-cRxsE8c13mZOh3vP+wLDxpQBRrOHDIGOWyDL93Sy0Ga8y515fBcC2pjUfFwUe5T7tqvTvWbCpg1URM/AXdWIXA==}
     cpu: [x64]
     os: [linux]
-    libc: [musl]
 
   '@rollup/rollup-openbsd-x64@4.60.3':
     resolution: {integrity: sha512-QaWcIgRxqEdQdhJqW4DJctsH6HCmo5vHxY0krHSX4jMtOqfzC+dqDGuHM87bu4H8JBeibWx7jFz+h6/4C8wA5Q==}

src/index.ts

@@ -282,14 +282,16 @@ startReminderScheduler();
 
 function shutdown() {
   console.log("Shutting down gracefully...");
+  // SIGTERM/SIGINT → server.close() → callback → process.exit(0)
+  // If graceful close takes >8s, force-exit to avoid being killed undrained
+  setTimeout(() => {
+    console.error("Graceful close timeout — forcing exit");
+    process.exit(1);
+  }, 8_000);
   server.close(() => {
     console.log("HTTP server closed");
     process.exit(0);
   });
-  setTimeout(() => {
-    console.error("Forced shutdown after timeout");
-    process.exit(1);
-  }, 10_000);
 }
 
 process.on("SIGTERM", shutdown);

src/lib/auth.ts

@@ -186,7 +186,9 @@ export async function initAuth(): Promise<void> {
     const discoveryUrlStr = `${providerConfig.issuerUrl}/.well-known/openid-configuration`;
     let oidcConfig: Record<string, string> = {};
     try {
-      const discoveryRes = await fetch(discoveryUrlStr);
+      const discoveryRes = await fetch(discoveryUrlStr, {
+        signal: AbortSignal.timeout(5000),
+      });
       if (discoveryRes.ok) {
         const discovery = await discoveryRes.json() as {
           authorization_endpoint?: string;