Add Fly.io deployment configuration

fly.toml

@@ -0,0 +1,32 @@
+# fly.toml - Fly.io deployment configuration
+# Deploy with: fly launch
+
+app = "cascade-llm-router"
+primary_region = "sjc"
+
+[build]
+  dockerfile = "Dockerfile"
+
+[env]
+  PORT = "8080"
+  PYTHONPATH = "/app/src"
+
+[http_service]
+  internal_port = 8080
+  force_https = true
+  auto_stop_machines = true
+  auto_start_machines = true
+  min_machines_running = 0
+  processes = ["app"]
+
+[[http_service.checks]]
+  grace_period = "10s"
+  interval = "30s"
+  method = "GET"
+  timeout = "5s"
+  path = "/health"
+
+[[vm]]
+  cpu_kind = "shared"
+  cpus = 1
+  memory_mb = 512