Add host registration, heartbeat, and multi-host management

Implements the full host ↔ control plane connection flow:

- Host CRUD endpoints (POST/GET/DELETE /v1/hosts) with role-based access:
  regular hosts admin-only, BYOC hosts for admins and team owners
- One-time registration token flow: admin creates host → gets token (1hr TTL
  in Redis + Postgres audit trail) → host agent registers with specs → gets
  long-lived JWT (1yr)
- Host agent registration client with automatic spec detection (arch, CPU,
  memory, disk) and token persistence to disk
- Periodic heartbeat (30s) via POST /v1/hosts/{id}/heartbeat with X-Host-Token
  auth and host ID cross-check
- Token regeneration endpoint (POST /v1/hosts/{id}/token) for retry after
  failed registration
- Tag management (add/remove/list) with team-scoped access control
- Host JWT with typ:"host" claim, cross-use prevention in both VerifyJWT and
  VerifyHostJWT
- requireHostToken middleware for host agent authentication
- DB-level race protection: RegisterHost uses AND status='pending' with
  rows-affected check; Redis GetDel for atomic token consume
- Migration for future mTLS support (cert_fingerprint, mtls_enabled columns)
- Host agent flags: --register (one-time token), --address (required ip:port)
- serviceErrToHTTP extended with "forbidden" → 403 mapping
- OpenAPI spec, .env.example, and README updated
This commit is contained in:
2026-03-17 05:51:28 +06:00
parent e4ead076e3
commit 2c66959b92
20 changed files with 1636 additions and 25 deletions

View File

@ -66,8 +66,6 @@ func main() {
}
slog.Info("connected to redis")
_ = rdb // TODO: pass to services that need it (host registration)
// Connect RPC client for the host agent.
agentHTTP := &http.Client{Timeout: 10 * time.Minute}
agentClient := hostagentv1connect.NewHostAgentServiceClient(
@ -89,7 +87,7 @@ func main() {
}
// API server.
srv := api.New(queries, agentClient, pool, []byte(cfg.JWTSecret), oauthRegistry, cfg.OAuthRedirectURL)
srv := api.New(queries, agentClient, pool, rdb, []byte(cfg.JWTSecret), oauthRegistry, cfg.OAuthRedirectURL)
// Start reconciler.
reconciler := api.NewReconciler(queries, agentClient, "default", 5*time.Second)

View File

@ -2,6 +2,7 @@ package main
import (
"context"
"flag"
"log/slog"
"net/http"
"os"
@ -16,6 +17,10 @@ import (
)
func main() {
registrationToken := flag.String("register", "", "One-time registration token from the control plane")
advertiseAddr := flag.String("address", "", "Externally-reachable address (ip:port) for this host agent")
flag.Parse()
slog.SetDefault(slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{
Level: slog.LevelDebug,
})))
@ -38,6 +43,8 @@ func main() {
imagesPath := envOrDefault("AGENT_IMAGES_PATH", "/var/lib/wrenn/images")
sandboxesPath := envOrDefault("AGENT_SANDBOXES_PATH", "/var/lib/wrenn/sandboxes")
snapshotsPath := envOrDefault("AGENT_SNAPSHOTS_PATH", "/var/lib/wrenn/snapshots")
cpURL := os.Getenv("AGENT_CP_URL")
tokenFile := envOrDefault("AGENT_TOKEN_FILE", "/var/lib/wrenn/host-token")
cfg := sandbox.Config{
KernelPath: kernelPath,
@ -53,6 +60,34 @@ func main() {
mgr.StartTTLReaper(ctx)
if *advertiseAddr == "" {
slog.Error("--address flag is required (externally-reachable ip:port)")
os.Exit(1)
}
// Register with the control plane (if configured).
if cpURL != "" {
hostToken, err := hostagent.Register(ctx, hostagent.RegistrationConfig{
CPURL: cpURL,
RegistrationToken: *registrationToken,
TokenFile: tokenFile,
Address: *advertiseAddr,
})
if err != nil {
slog.Error("host registration failed", "error", err)
os.Exit(1)
}
hostID, err := hostagent.HostIDFromToken(hostToken)
if err != nil {
slog.Error("failed to extract host ID from token", "error", err)
os.Exit(1)
}
slog.Info("host registered", "host_id", hostID)
hostagent.StartHeartbeat(ctx, cpURL, hostID, hostToken, 30*time.Second)
}
srv := hostagent.NewServer(mgr)
path, handler := hostagentv1connect.NewHostAgentServiceHandler(srv)