9cc0caff1e
Lands the protocol layer end-to-end: an agent can be enrolled through the operator UI, store credentials, dial back to the server over WS, complete the protocol_version handshake, and stay connected with periodic heartbeats. Server side: - P1-09 ws.Hub: one Conn per host_id, last-write-wins eviction, json envelope writer with a write mutex, reader, error envelopes. - P1-09 ws.AgentHandler: bearer-auth, accept upgrade, hello-stage (10s deadline, protocol_version checked against api.MinAgentProtocolVersion → ErrProtocolTooOld with help URL on reject), main read loop, defer hub register/unregister. - P1-10 POST /api/agents/enroll consumes a one-time token, mints a persistent agent bearer (sha-256 stored), creates a host row. - P1-10 POST /api/enrollment-tokens (operator, session-auth) issues a 1h one-time token. - P1-11 hello upserts agent_version + restic_version + protocol_version on the host row, flips status to online. - P1-12 heartbeat touches last_seen_at; background sweeper marks hosts offline after 90s without one. - store: hosts table accessors, host_schedule_version, enrollment_tokens FK on consumed_host dropped (audit-only field; the token gets burned before the host row exists). Agent side: - P1-13 internal/agent/config: yaml at /etc/restic-manager/agent.yaml, atomic Save (tmp+fsync+rename), Enrolled() helper. - P1-15 internal/agent/wsclient: dial with bearer + optional TLS cert pinning (sha-256 of leaf), exponential backoff with jitter (1s → 60s cap), heartbeat goroutine, fatal handling for ErrProtocolTooOld. - P1-15 wsclient.Enroll: HTTP POST /api/agents/enroll with sysinfo. - P1-17 internal/agent/sysinfo: hostname/OS/arch/restic-version collection. restic detected by `restic version` parse; absent restic doesn't block startup. - cmd/agent: -enroll-server / -enroll-token flags drive first-run enrollment then exit (so the install script can hand off to systemd to run the persistent service). End-to-end smoke verified: bootstrap → login → issue token → enroll → run agent → server logs `ws agent connected` with the right host_id and protocol_version 1. All tests still pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
169 lines
4.8 KiB
Go
169 lines
4.8 KiB
Go
package main
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"flag"
|
|
"fmt"
|
|
"log/slog"
|
|
"os"
|
|
"os/signal"
|
|
"path/filepath"
|
|
"syscall"
|
|
"time"
|
|
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/auth"
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/crypto"
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/server/config"
|
|
rmhttp "gitea.dcglab.co.uk/steve/restic-manager/internal/server/http"
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/server/ws"
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/store"
|
|
)
|
|
|
|
var version = "dev"
|
|
|
|
func main() {
|
|
if err := run(); err != nil {
|
|
slog.Error("server fatal", "err", err)
|
|
os.Exit(1)
|
|
}
|
|
}
|
|
|
|
func run() error {
|
|
configPath := flag.String("config", "", "path to YAML config (optional; env vars win regardless)")
|
|
showVersion := flag.Bool("version", false, "print version and exit")
|
|
flag.Parse()
|
|
|
|
if *showVersion {
|
|
fmt.Println("restic-manager-server", version)
|
|
return nil
|
|
}
|
|
|
|
logger := slog.New(slog.NewJSONHandler(os.Stdout, &slog.HandlerOptions{Level: slog.LevelInfo}))
|
|
slog.SetDefault(logger)
|
|
|
|
cfg, err := config.Load(*configPath)
|
|
if err != nil {
|
|
return fmt.Errorf("config: %w", err)
|
|
}
|
|
slog.Info("config resolved", "listen", cfg.Listen, "data_dir", cfg.DataDir,
|
|
"tls", cfg.TLSEnabled(), "trusted_proxies", cfg.TrustedProxies)
|
|
|
|
if err := os.MkdirAll(cfg.DataDir, 0o700); err != nil {
|
|
return fmt.Errorf("ensure data dir: %w", err)
|
|
}
|
|
|
|
// Mint or load the encryption key.
|
|
if _, err := os.Stat(cfg.SecretKeyFile); errors.Is(err, os.ErrNotExist) {
|
|
slog.Warn("no secret key found; generating a new one — back this up before continuing",
|
|
"path", cfg.SecretKeyFile)
|
|
if err := crypto.GenerateKeyFile(cfg.SecretKeyFile); err != nil {
|
|
return fmt.Errorf("generate secret key: %w", err)
|
|
}
|
|
}
|
|
keyBytes, err := crypto.LoadKeyFromFile(cfg.SecretKeyFile)
|
|
if err != nil {
|
|
return fmt.Errorf("load secret key: %w", err)
|
|
}
|
|
aead, err := crypto.NewAEAD(keyBytes)
|
|
if err != nil {
|
|
return fmt.Errorf("init AEAD: %w", err)
|
|
}
|
|
|
|
dbPath := filepath.Join(cfg.DataDir, "restic-manager.db")
|
|
st, err := store.Open(context.Background(), dbPath)
|
|
if err != nil {
|
|
return fmt.Errorf("open store: %w", err)
|
|
}
|
|
defer func() { _ = st.Close() }()
|
|
|
|
hub := ws.NewHub()
|
|
|
|
deps := rmhttp.Deps{
|
|
Cfg: cfg,
|
|
Store: st,
|
|
AEAD: aead,
|
|
Hub: hub,
|
|
}
|
|
|
|
// First-run bootstrap: if the users table is empty, mint a one-time
|
|
// token and print it. /api/bootstrap accepts it to create the first
|
|
// admin user, then becomes a no-op.
|
|
n, err := st.CountUsers(context.Background())
|
|
if err != nil {
|
|
return fmt.Errorf("count users: %w", err)
|
|
}
|
|
if n == 0 {
|
|
token, err := auth.NewToken()
|
|
if err != nil {
|
|
return fmt.Errorf("mint bootstrap token: %w", err)
|
|
}
|
|
deps.BootstrapToken = token
|
|
// Stable, easy-to-grep marker so an operator finds this in
|
|
// scrolling logs without spelunking. Token is shown in plain
|
|
// text exactly once; we hash it into BootstrapToken on the
|
|
// server-side handler.
|
|
fmt.Fprintln(os.Stderr, "================================================================")
|
|
fmt.Fprintln(os.Stderr, " FIRST RUN — bootstrap token (use within 1 hour, then it's gone):")
|
|
fmt.Fprintln(os.Stderr, " "+token)
|
|
fmt.Fprintln(os.Stderr, " POST it to /api/bootstrap with {token, username, password}.")
|
|
fmt.Fprintln(os.Stderr, "================================================================")
|
|
}
|
|
|
|
srv := rmhttp.New(deps)
|
|
|
|
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
|
|
defer stop()
|
|
|
|
errCh := make(chan error, 1)
|
|
go func() {
|
|
slog.Info("server listening", "addr", cfg.Listen, "version", version)
|
|
errCh <- srv.Start()
|
|
}()
|
|
|
|
// Background sweepers:
|
|
// - sessions/tokens purge: 15 min
|
|
// - host offline-after-90s mark: every 30s (matches heartbeat
|
|
// cadence — agent sends every 30s, P1-12)
|
|
purgeTick := time.NewTicker(15 * time.Minute)
|
|
defer purgeTick.Stop()
|
|
offlineTick := time.NewTicker(30 * time.Second)
|
|
defer offlineTick.Stop()
|
|
go func() {
|
|
for {
|
|
select {
|
|
case <-ctx.Done():
|
|
return
|
|
case <-purgeTick.C:
|
|
if n, err := st.PurgeExpiredSessions(ctx); err == nil && n > 0 {
|
|
slog.Info("purged expired sessions", "n", n)
|
|
}
|
|
if n, err := st.PurgeExpiredEnrollmentTokens(ctx); err == nil && n > 0 {
|
|
slog.Info("purged expired enrollment tokens", "n", n)
|
|
}
|
|
case <-offlineTick.C:
|
|
cutoff := time.Now().Add(-90 * time.Second)
|
|
if n, err := st.MarkHostsOfflineStale(ctx, cutoff); err == nil && n > 0 {
|
|
slog.Info("marked hosts offline (stale heartbeat)", "n", n)
|
|
}
|
|
}
|
|
}
|
|
}()
|
|
|
|
select {
|
|
case err := <-errCh:
|
|
if err != nil {
|
|
return fmt.Errorf("listen: %w", err)
|
|
}
|
|
case <-ctx.Done():
|
|
slog.Info("shutting down")
|
|
}
|
|
|
|
shutCtx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
|
|
defer cancel()
|
|
if err := srv.Shutdown(shutCtx); err != nil {
|
|
return fmt.Errorf("shutdown: %w", err)
|
|
}
|
|
return nil
|
|
}
|