Files
vantage/server/cmd/main.go
T
mrhid6 0b7e55d301 fix(server): adopt the migrated org on bootstrap; survive fresh install
Two failures found by tracing the migration path against a real upgrade.

Bootstrap orphaned the entire dataset. On upgrade, 0001 creates the
Default org and stamps every legacy document with it, but the instance
has no users, so the operator must run /auth/bootstrap to get in — and
that unconditionally created a SECOND org and put the owner in it. Every
org-scoped read then filtered on the new org, so the operator would log
into an empty Vantage while all their data sat under "default". Nothing
errored and agents kept syncing, so it presented as total data loss.
Bootstrap now adopts the sole existing org, renaming and re-slugging it,
and only creates one when no org exists. More than one org with no users
is refused rather than guessed.

Fresh installs crash-looped. Nothing creates the settings collection
before EnsureSettingsIndexes, so DropOne returned NamespaceNotFound (26),
isIndexNotFound matched only IndexNotFound (27), and that check is fatal.
The same early return also skipped index creation in the secrets and
workflow ensures.

Also: only insert the backfill org on ErrNoDocuments, so a transient read
error can't race the fatal unique slug index; run 0002 before 0003 so the
settings migration can't be pushed into its ambiguous branch; fail 0002's
ambiguous case with a remedy instead of continuing into a fatal index
build; and skip non-string ids in the owner backfill rather than aborting.
2026-07-22 10:51:42 +01:00

135 lines
4.1 KiB
Go

package main
import (
"context"
"log"
"os"
"time"
"github.com/gin-gonic/gin"
"github.com/mrhid6/vantage/server/internal/api"
"github.com/mrhid6/vantage/server/internal/auth"
"github.com/mrhid6/vantage/server/internal/db"
grpcserver "github.com/mrhid6/vantage/server/internal/grpc"
"github.com/mrhid6/vantage/server/internal/monitorsched"
"github.com/mrhid6/vantage/server/internal/services"
)
func main() {
mongoURI := getEnv("MONGO_URI", "mongodb://localhost:27017")
dbName := getEnv("MONGO_DB", "vantage")
if err := db.Connect(mongoURI, dbName); err != nil {
log.Fatalf("failed to connect to MongoDB: %v", err)
}
log.Println("connected to MongoDB")
// The unique indexes are a security property: GetUserByEmail does an
// unscoped FindOne, so duplicate (or blank) emails let the OIDC callback's
// cross-org guard compare against an arbitrary user, and duplicate org slugs
// make host-based org resolution pick one at random.
if err := services.EnsureAuthIndexes(); err != nil {
log.Fatalf("failed to ensure auth indexes: %v", err)
}
if err := services.RunMigrations(); err != nil {
log.Fatalf("migration failed: %v", err)
}
// Must run before the unique settings indexes are built, and before 0003:
// 0003 can create a "default" org, which would push 0002 into its ambiguous
// multi-org branch and leave the settings doc unstamped.
if err := services.MigrateSettingsOrg(); err != nil {
log.Fatalf("settings org migration failed: %v", err)
}
if err := services.MigrateMissedOrgScopes(); err != nil {
log.Fatalf("missed org scope migration failed: %v", err)
}
if err := services.EnsureSecretIndexes(); err != nil {
log.Printf("warning: failed to ensure secret indexes: %v", err)
}
// The unique indexes are a security property: duplicate settings docs make
// GetSettings return an arbitrary one, and duplicate ESO token hashes make
// ResolveSecretsReadToken pick an arbitrary org.
if err := services.EnsureSettingsIndexes(); err != nil {
log.Fatalf("failed to ensure settings indexes: %v", err)
}
if err := services.EnsureWorkflowIndexes(); err != nil {
log.Printf("warning: failed to ensure workflow indexes: %v", err)
}
if orgIDs, err := services.ListOrgIDs(); err != nil {
log.Printf("warning: failed to list orgs for default step seeding: %v", err)
} else {
for _, orgID := range orgIDs {
if created, updated, err := services.SeedDefaultSteps(orgID); err != nil {
log.Printf("warning: failed to seed default steps for org %s: %v", orgID, err)
} else {
log.Printf("default steps seeded for org %s: %d created, %d updated", orgID, created, updated)
}
}
}
services.StartLogSweeper()
redisAddr := getEnv("REDIS_ADDR", "localhost:6379")
if err := auth.InitRedis(redisAddr); err != nil {
log.Fatalf("failed to connect to Redis: %v", err)
}
log.Println("connected to Redis")
// Background goroutine to mark offline servers
go func() {
ticker := time.NewTicker(2 * time.Minute)
defer ticker.Stop()
for range ticker.C {
if err := services.MarkOfflineServers(); err != nil {
log.Printf("mark offline error: %v", err)
}
}
}()
// Start gRPC server
go func() {
if err := grpcserver.StartGRPC(9090); err != nil {
log.Fatalf("gRPC server error: %v", err)
}
}()
// Start the server-side monitor scheduler.
monitorsched.Start(context.Background())
// Start REST server
r := gin.New()
r.Use(gin.Recovery())
r.Use(gin.LoggerWithConfig(gin.LoggerConfig{SkipPaths: []string{"/api/console/tunnel"}}))
r.Use(corsMiddleware())
api.RegisterRoutes(r)
log.Println("REST server listening on :8080")
if err := r.Run(":8080"); err != nil {
log.Fatalf("REST server error: %v", err)
}
}
func corsMiddleware() gin.HandlerFunc {
return func(c *gin.Context) {
c.Header("Access-Control-Allow-Origin", "*")
c.Header("Access-Control-Allow-Methods", "GET, POST, PUT, DELETE, OPTIONS")
c.Header("Access-Control-Allow-Headers", "Content-Type, Authorization")
if c.Request.Method == "OPTIONS" {
c.AbortWithStatus(204)
return
}
c.Next()
}
}
func getEnv(key, fallback string) string {
if v := os.Getenv(key); v != "" {
return v
}
return fallback
}