docs/changelog.d/fix-deploy-healthcheck-race.bugfix.md

@@ -0,0 +1 @@
+Fix 502 errors during Fly.io proxy deploys by deferring health check until Tailscale is connected.

fly/nginx.conf

@@ -76,6 +76,9 @@ http {
         listen 8080 default_server;
 
         location /healthz {
+            if (!-f /tmp/tailscale-ready) {
+                return 503 "starting\n";
+            }
             return 200 "ok\n";
         }
 

fly/start.sh

@@ -1,9 +1,9 @@
 #!/bin/sh
 set -e
 
-# Start nginx immediately so port 8080 is bound before Fly's deploy checks.
-# Upstream DNS resolution is deferred via resolver + variable in nginx.conf,
-# so nginx starts cleanly even before Tailscale connects.
+# Start nginx immediately so port 8080 is bound (avoids connection refused).
+# Health check returns 503 until /tmp/tailscale-ready exists, so Fly.io
+# keeps the old machine serving traffic until Tailscale connects.
 nginx -g "daemon off;" &
 NGINX_PID=$!
 echo "Nginx started (waiting for Tailscale before proxying)"
@@ -16,8 +16,9 @@ sleep 2
 # Authenticate and join tailnet
 tailscale up --authkey="${TS_AUTHKEY}" --hostname=flyio-proxy
 
-# Wait for tailscale to be ready
+# Wait for tailscale to be ready, then signal nginx health check
 until tailscale status > /dev/null 2>&1; do sleep 1; done
+touch /tmp/tailscale-ready
 echo "Tailscale connected"
 
 # Start Alloy for observability (logs → Loki, metrics → Prometheus)