Files
doormile_backend/main.go
Suriya 2c26cbe4ba fix: panic recovery, rate limiting, transaction error handling, pagination
Hardening pass over the API surface. No route's auth requirements change.

Resilience:
- Add recover middleware. There was none, so an unhandled panic in any
  handler propagated out of the process instead of becoming a 500.
- Add a centralized ErrorHandler so errors and recovered panics return the
  same {success,message} envelope as the utils helpers, not Fiber's default
  plain-text body. 5xx responses are logged with method and path.

Rate limiting:
- Global 300/min per IP as an abuse backstop, exempting health/readiness
  probes and websocket upgrades.
- 10/min shared across every credential endpoint (customer/miler/admin/hub
  login, verify-pin, reset-pin, email OTP). PINs are 4 digits, so the whole
  keyspace was previously walkable in seconds. One shared limiter instance
  means rotating between endpoints doesn't reset the budget.
- Add TRUSTED_PROXIES config. Limits key on c.IP(), which behind a TLS
  terminator is the proxy, collapsing every client into one bucket. When set,
  X-Forwarded-For is honoured only from those proxies so the header can't be
  spoofed to dodge the limit. Logs a warning when unset.

Transactions:
- Check the error on all 51 previously-unchecked tx.Save/Create/Delete/
  Model(...).Update/Commit calls across 6 controllers. A failed write inside
  a transaction was silently ignored and the request still reported success;
  an unchecked Commit could fail with the caller told everything worked.
  Each site now rolls back and returns a specific message.

Pagination:
- Add utils.ParsePage/Paginated, reusing the pageno/pagesize convention
  GetAdminBookings already established. Default 500, hard cap 1000.
- Apply to the previously unbounded consignments, tripsheets, exceptions,
  app-users and clients endpoints. Defaults are high so existing consoles
  that don't paginate keep working; the cap only stops a growing table from
  being loaded wholesale. total is now a real COUNT, not len(data).
- GetClients also loaded the entire auth table to join in memory; it now
  fetches only the current page's rows.

Tests (first in the repo):
- Extract the hyperlocal pincode rule out of BookingPickupComplete into
  isHyperlocal so it is testable, covering the short/empty pincode fallback.
- Cover calculateVolumetricWeight and the ParsePage clamping rules.

Repo hygiene:
- Tag scratch/*.go with //go:build ignore. Each declared its own main(), so
  `go build ./...` failed on redeclaration; it now passes repo-wide.
- Untrack scratch/node_modules (216 files) and ignore node_modules, test
  artifacts, and the `doormile` binary `go build .` emits.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-27 12:13:39 +05:30

177 lines
5.3 KiB
Go

package main
import (
"errors"
"os"
"os/signal"
"strings"
"syscall"
"time"
"doormile/config"
"doormile/controllers"
"doormile/db"
"doormile/internal/notify"
"doormile/internal/worker"
"doormile/middlewares"
"doormile/migrations"
"doormile/routes"
"doormile/utils"
"github.com/gofiber/fiber/v2"
"github.com/gofiber/fiber/v2/middleware/cors"
"github.com/gofiber/fiber/v2/middleware/limiter"
"github.com/gofiber/fiber/v2/middleware/recover"
"github.com/joho/godotenv"
)
// errorHandler converts anything a handler returns — including a panic already
// turned into an error by the recover middleware — into the same
// {success, message} envelope the utils helpers emit, so clients never receive
// Fiber's default plain-text error body.
func errorHandler(c *fiber.Ctx, err error) error {
code := fiber.StatusInternalServerError
msg := "internal server error"
var fe *fiber.Error
if errors.As(err, &fe) {
code = fe.Code
msg = fe.Message
}
// 5xx means we broke, not the caller — log it with the route for triage.
if code >= fiber.StatusInternalServerError {
utils.Error("request failed",
"method", c.Method(),
"path", c.Path(),
"status", code,
"error", err.Error(),
)
}
return c.Status(code).JSON(fiber.Map{"success": false, "message": msg})
}
func main() {
// 1. Load configuration env variables
_ = godotenv.Load()
cfg := config.Load()
utils.Info("Starting Doormile Backend...")
// 2. Connect to Postgres, Redis & NATS
db.Connect(cfg)
db.InitRedis(cfg)
db.InitNATS(cfg)
notify.InitFCM()
// 3. Run GORM migrations for logistics tables
if db.DB != nil {
err := migrations.Migrate(db.DB)
if err != nil {
utils.Error("⚠️ Migration failed, continuing server boot...", "error", err.Error())
}
}
// 4. Initialize Fiber App
fiberCfg := fiber.Config{
AppName: "Doormile Logistics Service API v1",
ErrorHandler: errorHandler,
}
// Rate limiting keys on c.IP(). Behind a TLS-terminating reverse proxy the
// socket peer is the proxy, so without this every caller shares a single
// limit bucket and the whole fleet gets throttled together. Only honour
// X-Forwarded-For from proxies we explicitly trust — otherwise any client
// could spoof the header to dodge the limit entirely.
if cfg.TrustedProxies != "" {
proxies := strings.Split(cfg.TrustedProxies, ",")
for i := range proxies {
proxies[i] = strings.TrimSpace(proxies[i])
}
fiberCfg.EnableTrustedProxyCheck = true
fiberCfg.TrustedProxies = proxies
fiberCfg.ProxyHeader = fiber.HeaderXForwardedFor
utils.Info("Trusting X-Forwarded-For from configured proxies", "proxies", proxies)
} else {
utils.Warn("TRUSTED_PROXIES is unset — rate limits key on the socket peer address. " +
"If this service runs behind a reverse proxy, set TRUSTED_PROXIES or all clients will share one limit bucket.")
}
app := fiber.New(fiberCfg)
// Panic recovery — must be the outermost middleware so it also catches
// panics raised inside the ones registered below. Without this a single
// nil-pointer dereference in any handler takes the whole process down.
app.Use(recover.New(recover.Config{EnableStackTrace: true}))
// CORS policy
app.Use(cors.New(cors.Config{
AllowHeaders: "Origin,Content-Type,Accept,Authorization",
AllowOrigins: "http://localhost:5173,http://localhost:5174,http://localhost:3000,http://localhost:3001,http://localhost:3002,http://localhost:8080,http://localhost:8081,https://doormile.com,https://www.doormile.com,https://admin.doormile.com,https://api.doormile.com,https://crm.doormile.com,https://console.doormile.com,https://app.doormile.com",
AllowCredentials: true,
AllowMethods: "GET,POST,PUT,DELETE,PATCH,OPTIONS",
}))
// Structured Zap logger middleware
app.Use(middlewares.ZapLogger())
// Global per-IP rate limit. Deliberately generous — this is an abuse
// backstop, not a quota. Auth endpoints get a much tighter limit of their
// own in routes.go. Health probes and websocket upgrades are exempt so
// orchestrator checks and long-lived tracking sockets are never throttled.
app.Use(limiter.New(limiter.Config{
Max: 300,
Expiration: 1 * time.Minute,
Next: func(c *fiber.Ctx) bool {
p := c.Path()
return strings.HasSuffix(p, "/health") ||
strings.HasSuffix(p, "/ready") ||
strings.HasPrefix(p, "/ws/")
},
LimitReached: func(c *fiber.Ctx) error {
return c.Status(fiber.StatusTooManyRequests).
JSON(fiber.Map{"success": false, "message": "too many requests, please slow down"})
},
}))
// 5. Register routes
routes.RegisterRoutes(app, cfg)
// 6. Pre-warm Redis pricing cache from Postgres
controllers.WarmPricingCache()
// 7. Start NATS booking worker in background
go worker.StartBookingWorker()
// 7. Startup server in a background thread
go func() {
utils.Info("Server starting", "port", cfg.Port)
if err := app.Listen(":" + cfg.Port); err != nil {
utils.Logger.Fatalf("Server failed to bind: %v", err)
}
}()
// Graceful shutdown listener
gracefulShutdown(app)
}
func gracefulShutdown(app *fiber.App) {
c := make(chan os.Signal, 1)
signal.Notify(c, os.Interrupt, syscall.SIGTERM)
<-c
utils.Info("Shutting down Doormile Backend...")
// Shutdown fiber
if err := app.Shutdown(); err != nil {
utils.Error("Fiber shutdown failed", "error", err)
}
// Close database pools
db.CloseDB()
time.Sleep(1 * time.Second)
utils.Info("Shutdown completed cleanly.")
}