mesh-host/internal/identity/identity_test.go

package identity

import (
	"crypto/ed25519"
	"encoding/base64"
	"encoding/json"
	"errors"
	"os"
	"path/filepath"
	"strings"
	"testing"
)

func TestAMachineThatHasNotJoinedHasNoIdentityAndThatIsNotAFault(t *testing.T) {
	// A hosted machine has a host running and no identity. That is a real state, and confusing
	// it with a fault would have every fresh install look broken.
	_, err := Load(Path(filepath.Join(t.TempDir(), "state.json")))
	if !errors.Is(err, ErrNoIdentity) {
		t.Fatalf("a machine that never joined gave %v", err)
	}
}

func TestAnUnreadableIdentityIsNotTheSameAsHavingNone(t *testing.T) {
	// The distinction that matters most here. "None" leads to enrolling; if an unreadable
	// identity took that path, a node would discard the identity the mesh still believes and
	// need a person with a new token to get back.
	dir := t.TempDir()
	path := Path(filepath.Join(dir, "state.json"))
	if err := os.WriteFile(path, []byte("{"), 0o600); err != nil {
		t.Fatal(err)
	}

	_, err := Load(path)
	if err == nil {
		t.Fatal("a corrupt identity loaded")
	}
	if errors.Is(err, ErrNoIdentity) {
		t.Fatal("a corrupt identity was reported as having none; this node would re-enrol and " +
			"throw away the identity the mesh believes")
	}
}

// joined is an identity as it exists after enrolment, which is the only kind ever saved:
// Generate makes the keypair, and the mesh supplies everything under Membership.
func joined(t *testing.T, name string) Identity {
	t.Helper()
	made, err := Generate(name)
	if err != nil {
		t.Fatal(err)
	}
	signer, _, err := ed25519.GenerateKey(nil)
	if err != nil {
		t.Fatal(err)
	}
	made.Membership = Membership{
		Broker:      "192.0.2.10:5671",
		Fingerprint: "sha256:" + strings.Repeat("ab", 32),
		Signer:      signer,
		Password:    "this node's own",
	}
	return made
}

func TestSaveRefusesWhatLoadWouldRefuse(t *testing.T) {
	// The two must agree, or a caller can write a file that cannot be read back — and it would
	// be read back on the next start, on a machine nobody is watching, by which time the token
	// that could have fixed it is spent.
	path := Path(filepath.Join(t.TempDir(), "state.json"))
	unenrolled, err := Generate("workstation")
	if err != nil {
		t.Fatal(err)
	}
	if err := Save(path, unenrolled); err == nil {
		t.Fatal("an identity with no membership was saved; Load will not accept it")
	}
	if _, err := os.Stat(path); err == nil {
		t.Error("the refused identity was written anyway")
	}
}

func TestWhatIsSavedIsWhatIsLoaded(t *testing.T) {
	path := Path(filepath.Join(t.TempDir(), "state.json"))
	made := joined(t, "workstation")
	if err := Save(path, made); err != nil {
		t.Fatal(err)
	}

	back, err := Load(path)
	if err != nil {
		t.Fatal(err)
	}
	if back.Node != made.Node || string(back.Public) != string(made.Public) ||
		string(back.Private) != string(made.Private) {
		t.Error("the identity changed across a save and load")
	}
	if back.Membership.Broker != made.Membership.Broker ||
		back.Membership.Fingerprint != made.Membership.Fingerprint ||
		back.Membership.Password != made.Membership.Password ||
		string(back.Membership.Signer) != string(made.Membership.Signer) {
		t.Error("the membership changed across a save and load; this node could not come back")
	}
}

func TestTheIdentityIsNotReadableByAnybodyElse(t *testing.T) {
	// It is the only secret on the machine that identifies it. A mode that let another user on
	// this machine read it would make "compromise of a node is compromise of that node" false in
	// the other direction — any local user could become the node.
	path := Path(filepath.Join(t.TempDir(), "state.json"))
	if err := Save(path, joined(t, "workstation")); err != nil {
		t.Fatal(err)
	}

	info, err := os.Stat(path)
	if err != nil {
		t.Fatal(err)
	}
	if info.Mode().Perm()&0o077 != 0 {
		t.Errorf("the identity is mode %04o; anything but 0600 lets another local user become "+
			"this node", info.Mode().Perm())
	}
}

func TestSavingLeavesNoHalfWrittenIdentity(t *testing.T) {
	// Written and renamed, so power lost mid-write keeps the old identity rather than producing
	// half of one. A node cannot regenerate its way out of a broken identity — the mesh believes
	// the old public key, and a new one needs a person with a new token.
	dir := t.TempDir()
	path := Path(filepath.Join(dir, "state.json"))
	made := joined(t, "workstation")
	for i := 0; i < 3; i++ {
		if err := Save(path, made); err != nil {
			t.Fatal(err)
		}
	}

	entries, err := os.ReadDir(dir)
	if err != nil {
		t.Fatal(err)
	}
	for _, e := range entries {
		if strings.HasPrefix(e.Name(), ".identity-") {
			t.Errorf("a temporary file survived: %s", e.Name())
		}
	}
}

func TestAnIdentityOfTheWrongShapeIsRefused(t *testing.T) {
	// The one that would load happily and fail at the moment it signs, which is during enrolment
	// against a mesh, far from here.
	path := Path(filepath.Join(t.TempDir(), "state.json"))
	raw, err := json.Marshal(Identity{Node: "workstation", Public: []byte("short"), Private: []byte("also short")})
	if err != nil {
		t.Fatal(err)
	}
	if err := os.WriteFile(path, raw, 0o600); err != nil {
		t.Fatal(err)
	}
	if _, err := Load(path); err == nil {
		t.Fatal("an identity with a truncated key loaded")
	}
}

func TestSigningProvesTheNodeIsThatNode(t *testing.T) {
	made, err := Generate("workstation")
	if err != nil {
		t.Fatal(err)
	}
	challenge := []byte("prove it")
	if !ed25519.Verify(ed25519.PublicKey(made.Public), challenge, made.Sign(challenge)) {
		t.Fatal("a node's own signature did not verify against the half it publishes")
	}
}

// --- the token, which the control plane writes and this parses ---

func encodeToken(t *testing.T, body string) string {
	t.Helper()
	return base64.RawURLEncoding.EncodeToString([]byte(body))
}

func completeToken(t *testing.T) string {
	t.Helper()
	public, _, err := ed25519.GenerateKey(nil)
	if err != nil {
		t.Fatal(err)
	}
	raw, err := json.Marshal(Token{
		Version: 1, Broker: "192.0.2.10:5671",
		Fingerprint: "sha256:" + strings.Repeat("ab", 32),
		Signer:      public, Secret: "one-time",
	})
	if err != nil {
		t.Fatal(err)
	}
	return base64.RawURLEncoding.EncodeToString(raw)
}

func TestTheWireFormatIsExactlyTheseFieldNames(t *testing.T) {
	// The contract with the control plane, which defines this format separately because the host
	// requires nothing present and does not import it (novox/hq ADR 0005). There is a matching
	// test on the other side. Rename a field on either and both fail, which is the point — the
	// alternative is a rename that only breaks at enrolment, on a real machine.
	public, _, err := ed25519.GenerateKey(nil)
	if err != nil {
		t.Fatal(err)
	}
	raw, err := json.Marshal(Token{Version: 1, Broker: "b", Fingerprint: "f", Signer: public, Secret: "s"})
	if err != nil {
		t.Fatal(err)
	}
	var fields map[string]any
	if err := json.Unmarshal(raw, &fields); err != nil {
		t.Fatal(err)
	}
	for _, want := range []string{"v", "broker", "fingerprint", "signer", "secret"} {
		if _, ok := fields[want]; !ok {
			t.Errorf("the token has no %q field; the control plane writes that name", want)
		}
	}
	if len(fields) != 5 {
		t.Errorf("the token has %d fields, expected 5: %v", len(fields), fields)
	}

	// novox/hq ADR 0100: an adopted node's token says so, and a converged one's is unchanged.
	raw, err = json.Marshal(Token{Version: 1, Secret: "s", Adopted: true})
	if err != nil {
		t.Fatal(err)
	}
	fields = map[string]any{}
	if err := json.Unmarshal(raw, &fields); err != nil {
		t.Fatal(err)
	}
	if fields["adopted"] != true {
		t.Errorf("an adopted token does not say \"adopted\": %v", fields)
	}
}

func TestACompleteTokenParses(t *testing.T) {
	got, err := ParseToken(completeToken(t))
	if err != nil {
		t.Fatal(err)
	}
	if got.Broker != "192.0.2.10:5671" || len(got.SignerKey()) != ed25519.PublicKeySize {
		t.Errorf("parsed %+v", got)
	}
}

func TestAPastedTokenTolerantOfWhitespace(t *testing.T) {
	if _, err := ParseToken("  " + completeToken(t) + "\n"); err != nil {
		t.Errorf("a pasted token was refused: %v", err)
	}
}

func TestAnIncompleteTokenIsRefusedWholeAndSaysWhatIsMissing(t *testing.T) {
	// Not a reduced capability — an unsafe one. Without the fingerprint this node would connect
	// to whatever answers; without the signing key it could not tell a declaration from a
	// forgery, and it applies whatever the link delivers.
	for _, c := range []struct{ body, expect string }{
		{`{"v":1,"fingerprint":"f","signer":"` + base64Key(t) + `","secret":"s"}`, "broker's address"},
		{`{"v":1,"broker":"b","signer":"` + base64Key(t) + `","secret":"s"}`, "fingerprint"},
		{`{"v":1,"broker":"b","fingerprint":"f","secret":"s"}`, "signing key"},
		{`{"v":1,"broker":"b","fingerprint":"f","signer":"` + base64Key(t) + `"}`, "one-time secret"},
	} {
		_, err := ParseToken(encodeToken(t, c.body))
		if err == nil {
			t.Errorf("a token missing %s was accepted", c.expect)
			continue
		}
		if !strings.Contains(err.Error(), c.expect) {
			t.Errorf("the refusal does not name %s: %v", c.expect, err)
		}
	}
}

func TestATokenFromAnotherVersionIsRefused(t *testing.T) {
	if _, err := ParseToken(encodeToken(t, `{"v":99,"broker":"b","fingerprint":"f","secret":"s"}`)); err == nil {
		t.Fatal("a token from an unknown version was accepted")
	}
}

func TestGarbageIsRefused(t *testing.T) {
	for _, bad := range []string{"", "!!!not base64!!!", "aGVsbG8"} {
		if _, err := ParseToken(bad); err == nil {
			t.Errorf("%q parsed as a token", bad)
		}
	}
}

func base64Key(t *testing.T) string {
	t.Helper()
	public, _, err := ed25519.GenerateKey(nil)
	if err != nil {
		t.Fatal(err)
	}
	return base64.StdEncoding.EncodeToString(public)
}

func TestAnIdentityThatCannotBeReadIsNotReportedAsAbsent(t *testing.T) {
	// The other half of the distinction above, and the one that was untested: a file that exists
	// and cannot be read. The corrupt case is caught when it fails to parse; this one never gets
	// that far, so it needs its own check — and without it a permissions accident would look
	// exactly like a machine that has never joined, and the node would enrol again and discard
	// the identity the mesh still believes.
	if os.Geteuid() == 0 {
		t.Skip("running as root, which can read anything")
	}
	path := Path(filepath.Join(t.TempDir(), "state.json"))
	if err := Save(path, joined(t, "workstation")); err != nil {
		t.Fatal(err)
	}
	if err := os.Chmod(path, 0o000); err != nil {
		t.Fatal(err)
	}

	_, err := Load(path)
	if err == nil {
		t.Fatal("an unreadable identity loaded")
	}
	if errors.Is(err, ErrNoIdentity) {
		t.Fatal("an unreadable identity was reported as having none; this node would re-enrol " +
			"and throw away the identity the mesh believes")
	}
	if !strings.Contains(err.Error(), "not the same as") {
		t.Errorf("the error does not say why this is different from having none: %v", err)
	}
}

func TestASealingKeyOpensOnlyWhatWasSealedToIt(t *testing.T) {
	mine, err := GenerateSealingKey()
	if err != nil {
		t.Fatal(err)
	}
	theirs, err := GenerateSealingKey()
	if err != nil {
		t.Fatal(err)
	}
	sealed, err := Seal(mine.Public, []byte("hunter2"))
	if err != nil {
		t.Fatal(err)
	}
	got, err := mine.Unseal(sealed)
	if err != nil {
		t.Fatal(err)
	}
	if string(got) != "hunter2" {
		t.Fatalf("got %q", got)
	}
	if _, err := theirs.Unseal(sealed); err == nil {
		t.Fatal("another node opened it")
	}
}

func TestSealingTheSameValueTwiceLooksDifferent(t *testing.T) {
	// Sealed boxes are randomised, so an observer cannot tell that two nodes were given the same
	// password, nor that a rotation changed nothing. Worth asserting because the alternative is
	// a subtle leak nobody would look for.
	key, _ := GenerateSealingKey()
	first, _ := Seal(key.Public, []byte("same"))
	second, _ := Seal(key.Public, []byte("same"))
	if first == second {
		t.Fatal("sealing is deterministic, so equal secrets are visible as equal blobs")
	}
}

func TestANodeWithNoSealingKeySaysWhatToDo(t *testing.T) {
	// Rather than making one. A key the mesh was never told about is a key nothing can be sealed
	// to, so a node that quietly created one would look fine and receive nothing for ever.
	_, err := LoadSealingKey(t.TempDir() + "/absent.key")
	if err == nil {
		t.Fatal("a sealing key appeared out of nowhere")
	}
	if !strings.Contains(err.Error(), "join again") {
		t.Fatalf("the failure does not say what to do: %v", err)
	}
}

func TestASealingKeyOnDiskSurvivesATrailingNewline(t *testing.T) {
	// It is written with one, the way every other key file here is, and reading it back has to
	// cope — otherwise the key works until the first restart.
	key, _ := GenerateSealingKey()
	path := t.TempDir() + "/sealing.key"
	if err := os.WriteFile(path, []byte(key.Private+"\n"), 0o600); err != nil {
		t.Fatal(err)
	}
	back, err := LoadSealingKey(path)
	if err != nil {
		t.Fatal(err)
	}
	if back.Public != key.Public {
		t.Fatalf("a round trip through the disk changed the key")
	}
}

func TestATokenSaysWhatTheMeshCallsThisMachine(t *testing.T) {
	// The node cannot work its own name out. The broker account it authenticates as is named
	// after it and exists before this machine has been told anything — so without the name in the
	// token, enrolment is a connection refused with an empty username, which names nothing about
	// the cause. That is exactly how the first end-to-end raise went.
	raw := base64.RawURLEncoding.EncodeToString([]byte(
		`{"v":1,"node":"anchor","broker":"192.0.2.10:5671",` +
			`"fingerprint":"sha256:` + strings.Repeat("ab", 32) + `",` +
			`"signer":"` + base64.StdEncoding.EncodeToString(make([]byte, 32)) + `",` +
			`"secret":"a-one-time-secret"}`))
	token, err := ParseToken(raw)
	if err != nil {
		t.Fatal(err)
	}
	if token.Node != "anchor" {
		t.Fatalf("the name did not survive the token: %q", token.Node)
	}
}