Load the KVM ssh material on first use instead of at startup

The kvm-ssh Secret is mounted optional, but kvm.New read the key and
known_hosts eagerly and registry.Build aborts the whole provider set on a
constructor error, so a missing or misnamed Secret exited the manager
before any controller started and took the kubernetes and gcp providers
down with it.

lazyAuth loads the material on the first connection and caches it once it
works, so a Secret created after the manager starts heals the affected
proxies on the next reconcile with no restart. A missing file classifies
transient for that reason; a key that does not parse is permanent.

New still checks both files and logs a WARNING: line when they are
unreadable, keeping the startup diagnostic the eager load was there for.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

internal/provider/kvm/conn.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"io/fs"
 	"net"
 	"os"
 	"sync"
@@ -180,14 +181,17 @@ func awaitOrCancel(ctx context.Context, fn func() error, abort func()) error {
 }
 
 // sshAuth holds the pieces of the SSH client config shared by every host:
-// the private key and the host-key policy, both loaded once at startup so a
-// missing or unreadable file fails the operator fast rather than on the
-// first Create.
+// the private key and the host-key policy. Both are loaded on the first
+// connection rather than at startup — see lazyDialer.
 type sshAuth struct {
 	signer  ssh.Signer
 	hostKey ssh.HostKeyCallback
 }
 
+// newSSHAuth loads the key material. A file that is not there yet stays
+// unclassified, so the provider treats it as transient and heals when the
+// Secret appears; content that will never parse is permanent, since
+// retrying cannot fix it.
 func newSSHAuth(cfg provider.KVMConfig) (*sshAuth, error) {
 	key, err := os.ReadFile(cfg.SSHKeyFile)
 	if err != nil {
@@ -195,18 +199,57 @@ func newSSHAuth(cfg provider.KVMConfig) (*sshAuth, error) {
 	}
 	signer, err := ssh.ParsePrivateKey(key)
 	if err != nil {
-		return nil, fmt.Errorf("parsing kvm.sshKeyFile: %w", err)
+		return nil, fmt.Errorf("%w: parsing kvm.sshKeyFile: %v", provider.ErrPermanent, err)
 	}
 	hostKey := ssh.InsecureIgnoreHostKey() //nolint:gosec // opt-in via config, documented as insecure
 	if !cfg.InsecureIgnoreHostKey {
 		hostKey, err = knownhosts.New(cfg.KnownHostsFile)
-		if err != nil {
+		if err != nil && errors.Is(err, fs.ErrNotExist) {
 			return nil, fmt.Errorf("loading kvm.knownHostsFile: %w", err)
 		}
+		if err != nil {
+			return nil, fmt.Errorf("%w: loading kvm.knownHostsFile: %v", provider.ErrPermanent, err)
+		}
 	}
 	return &sshAuth{signer: signer, hostKey: hostKey}, nil
 }
 
+// lazyAuth defers loading the SSH material to the first connection and
+// caches it once it works. The kvm-ssh Secret is an optional mount: the
+// manager has to start without it and keep every other provider running,
+// and a Secret created afterwards has to heal the KVM proxies on the next
+// reconcile rather than needing a restart.
+func lazyAuth(cfg provider.KVMConfig) func() (*sshAuth, error) {
+	var (
+		mu     sync.Mutex
+		cached *sshAuth
+	)
+	return func() (*sshAuth, error) {
+		mu.Lock()
+		defer mu.Unlock()
+		if cached != nil {
+			return cached, nil
+		}
+		auth, err := newSSHAuth(cfg)
+		if err != nil {
+			return nil, err
+		}
+		cached = auth
+		return auth, nil
+	}
+}
+
+func lazyDialer(cfg provider.KVMConfig) hostDialer {
+	auth := lazyAuth(cfg)
+	return func(ctx context.Context, host provider.KVMHost) (*hostClient, error) {
+		a, err := auth()
+		if err != nil {
+			return nil, err
+		}
+		return a.dialer()(ctx, host)
+	}
+}
+
 // dialer returns the production hostDialer: SSH to the host, forward its
 // libvirt unix socket through the connection, and open a libvirt session
 // over that.

internal/provider/kvm/conn_test.go

@@ -525,6 +525,97 @@ func TestNewSSHAuth_missingFiles(t *testing.T) {
 	}
 }
 
+// The kvm-ssh Secret is an optional mount, so the provider has to be
+// constructible without it and has to start working once it appears — the
+// alternative was a constructor error that crash-looped the whole manager.
+func TestLazyAuth_healsWhenTheKeyAppears(t *testing.T) {
+	t.Parallel()
+	f := newSSHFixture(t, true)
+	keyPEM, err := os.ReadFile(f.keyFile)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := os.Remove(f.keyFile); err != nil {
+		t.Fatal(err)
+	}
+	auth := lazyAuth(f.cfg)
+
+	if _, err := auth(); err == nil {
+		t.Fatal("loading with no key file succeeded, want an error")
+	} else if class := classify(err); class != provider.ErrTransient {
+		t.Errorf("class = %v, want ErrTransient so the proxy retries once the Secret lands", class)
+	}
+	if err := os.WriteFile(f.keyFile, keyPEM, 0o600); err != nil {
+		t.Fatal(err)
+	}
+	loaded, err := auth()
+	if err != nil {
+		t.Fatalf("loading after the key appeared: %v", err)
+	}
+	// Cached from here on: the file may vanish again (a Secret rotated out)
+	// without breaking connections that already work.
+	if err := os.Remove(f.keyFile); err != nil {
+		t.Fatal(err)
+	}
+	if again, err := auth(); err != nil || again != loaded {
+		t.Errorf("auth() = %v, %v; want the cached value reused", again, err)
+	}
+}
+
+func TestLazyAuth_unparseableKeyIsPermanent(t *testing.T) {
+	t.Parallel()
+	f := newSSHFixture(t, true)
+	if err := os.WriteFile(f.keyFile, []byte("not a key"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	_, err := lazyAuth(f.cfg)()
+	if classify(err) != provider.ErrPermanent {
+		t.Errorf("class = %v, want ErrPermanent: retrying cannot fix a key that does not parse", classify(err))
+	}
+}
+
+// The dialer must authenticate with the material the lazy loader produced,
+// not a stale or empty one. The echo socket is not a libvirt server, so the
+// call gets as far as the libvirt handshake and no further; what matters is
+// that it is past SSH by then.
+func TestLazyDialer_authenticatesOverSSH(t *testing.T) {
+	t.Parallel()
+	f := newSSHFixture(t, true)
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	_, err := lazyDialer(f.cfg)(ctx, f.host)
+	if err == nil {
+		t.Fatal("dial to an echo socket succeeded, want a libvirt handshake error")
+	}
+	if strings.Contains(err.Error(), "sshKeyFile") || strings.Contains(err.Error(), "ssh handshake") {
+		t.Errorf("dial failed before libvirt: %v", err)
+	}
+	if paths := f.server.requestedPaths(); len(paths) != 1 || paths[0] != f.host.Socket {
+		t.Errorf("server saw forward requests %v, want [%s]", paths, f.host.Socket)
+	}
+}
+
+// New must not fail on missing key material, or one misconfigured provider
+// aborts registry.Build and the manager exits before any controller starts.
+func TestNew_missingSSHMaterialStillBuilds(t *testing.T) {
+	t.Parallel()
+	p, err := New(context.Background(), provider.ProviderConfig{
+		Name: "kvm-home", Type: "kvm",
+		KVM: &provider.KVMConfig{
+			SSHKeyFile:     filepath.Join(t.TempDir(), "absent"),
+			KnownHostsFile: filepath.Join(t.TempDir(), "absent"),
+			Hosts:          []provider.KVMHost{{Name: "nas1", Address: "nas1:22", User: "virt", Bridge: "br0"}},
+		},
+	})
+	if err != nil || p == nil {
+		t.Fatalf("New() = %v, %v; want a usable provider", p, err)
+	}
+	if _, err := p.Get(context.Background(), "hosts/nas1/domains/proxy-x"); provider.Class(err) != provider.ErrTransient {
+		t.Errorf("Get class = %v, want ErrTransient", provider.Class(err))
+	}
+}
+
 func TestKeepalive_closesClientWhenServerStalls(t *testing.T) {
 	t.Parallel()
 	f := newSSHFixture(t, false)

internal/provider/kvm/kvm.go

@@ -77,18 +77,22 @@ type Provider struct {
 }
 
 // New builds a Provider that reaches its hosts over SSH. The key and
-// known_hosts files are read here so a bad path fails at startup rather
-// than on the first Create. Satisfies registry.Constructor.
-func New(_ context.Context, pc provider.ProviderConfig) (provider.Provider, error) {
+// known_hosts files are read on the first connection, not here: they come
+// from an optional Secret mount, and a constructor that failed without it
+// would abort the whole provider set and crash-loop the manager, taking
+// the kubernetes and gcp providers down with it. Unreadable files are
+// still reported at startup, as a warning. Satisfies registry.Constructor.
+func New(ctx context.Context, pc provider.ProviderConfig) (provider.Provider, error) {
 	cfg := provider.KVMConfig{}
 	if pc.KVM != nil {
 		cfg = *pc.KVM
 	}
-	auth, err := newSSHAuth(cfg)
-	if err != nil {
-		return nil, fmt.Errorf("kvm provider %q: %w", pc.Name, err)
+	if _, err := newSSHAuth(cfg); err != nil {
+		logf.FromContext(ctx).WithName("kvm").WithValues("provider", pc.Name).Info(
+			"WARNING: kvm ssh material is not usable; proxies on this provider will fail until it is",
+			"error", err.Error())
 	}
-	return newWithDialer(pc, auth.dialer(), nil), nil
+	return newWithDialer(pc, lazyDialer(cfg), nil), nil
 }
 
 // newWithDialer is the test seam: the dialer decides what libvirtAPI each

internal/provider/kvm/kvm_test.go

@@ -906,12 +906,20 @@ func TestMapState(t *testing.T) {
 	}
 }
 
-func TestNew_badKeyPathFailsFast(t *testing.T) {
+// A bad key path no longer fails the constructor: registry.Build aborts the
+// whole provider set on a constructor error, so that took the manager down
+// with every other provider. It degrades per-proxy instead — see
+// TestNew_missingSSHMaterialStillBuilds and TestLazyAuth_healsWhenTheKeyAppears.
+func TestNew_badKeyPathDefersToFirstUse(t *testing.T) {
 	t.Parallel()
 	cfg := testConfig("nas1")
 	cfg.KVM.SSHKeyFile = t.TempDir() + "/missing"
-	if _, err := New(context.Background(), cfg); err == nil {
-		t.Fatal("New succeeded with a missing key file")
+	p, err := New(context.Background(), cfg)
+	if err != nil {
+		t.Fatalf("New() error = %v, want a provider that fails only when used", err)
+	}
+	if err := p.Delete(context.Background(), "hosts/nas1/domains/proxy-x"); provider.Class(err) != provider.ErrTransient {
+		t.Errorf("Delete class = %v, want ErrTransient", provider.Class(err))
 	}
 }