Files
nebula/e2e/commands_output_test.go
T
Matt RichardsonandClaude Fable 5.1 8a4bd8b10f
smoke-extra / freebsd-amd64 (push) Failing after 14s
smoke-extra / linux-amd64-ipv6disable (push) Failing after 13s
smoke-extra / netbsd-amd64 (push) Failing after 14s
smoke-extra / openbsd-amd64 (push) Failing after 15s
smoke-extra / linux-386 (push) Failing after 14s
smoke / Run multi node smoke test (push) Failing after 1m46s
Build and test / Static checks (push) Successful in 2m38s
Build and test / Test linux (push) Failing after 1m12s
Build and test / Test linux-pkcs11 (push) Failing after 2m6s
Build and test / Test linux-boringcrypto (push) Failing after 3m0s
Build and test / Test linux-fips140 (push) Failing after 2m56s
Build and test / Cross-build linux-arm (push) Successful in 3m10s
Build and test / Cross-build linux-mips (push) Successful in 3m55s
Build and test / Cross-build linux-other (push) Successful in 3m15s
Build and test / Cross-build windows (push) Successful in 1m5s
Build and test / Cross-build freebsd (push) Successful in 1m37s
Build and test / Cross-build netbsd (push) Successful in 1m36s
Build and test / Cross-build openbsd (push) Successful in 1m35s
Build and test / Cross-build mobile (push) Successful in 3m32s
smoke-extra / Run windows smoke test (push) Canceled after 0s
smoke / Run self traffic smoke test on macOS (push) Canceled after 0s
Build and test / Test macos (push) Canceled after 0s
Build and test / Test windows (push) Canceled after 0s
Build and test / CI status (push) Canceled after 0s
Report ssh command failures to the surface (#1959)
Report ssh command failures to the surface (#1959)

The ssh debug commands told the user when something went wrong but
never told the surface that ran them, so `ssh host cmd` always exited 0
and a few failures were not reported at all. A failed command now
returns its error, a failure the user has already heard about is a
commands.Failure, and the ssh exec path exits 1 for either. The command
bodies also lose their ssh prefixes and the duplication they carried
over from ssh.go; both goldens pin that nothing else changed.

- Dispatch returns the callback's error, or shlex's; the ssh session
  logs it at debug, and not at all for a Failure the user already saw
- commands.Fail writes a message and returns it as a Failure in one step;
  an unknown command, `help` for a command that is not there, a failed
  reload and an unbalanced quote are failures
- ssh exec exit-status is 1 for a command, flag or failure error, 0
  otherwise; the e2e golden records the exit status for every case
- Clone rebinds help to the copy, so an ssh session's help lists logout
  and `help logout` and `logout -h` answer; sshd.LogoutCommand is the
  session's logout, exported for tests
- "did not understand" names the first word only, the one looked up;
  DispatchArgs takes just the tokens
- log-format writes its refusal to the user, as log-level does
- print-relays emits the relay error as a string and omits the key when
  there is none, where it printed {} or "Error":null
- list-hostmap and list-lighthouse-addrmap -json return the encode
  error; print-cert reports a certificate that will not marshal
- a flags type that is not the one registered is an internal error, not
  a silent success
- command functions and flag types are <name>Command and <name>Flags;
  parseVpnAddr and listHostMapFlagSet replace the repeated parse block
  and flag set; close-tunnel sends through sendCloseTunnel

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-19 10:48:26 -04:00

165 lines
6.2 KiB
Go

//go:build e2e_testing
package e2e
import (
"bytes"
"fmt"
"path/filepath"
"regexp"
"strings"
"testing"
"time"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/cert_test"
"github.com/slackhq/nebula/commands"
"github.com/slackhq/nebula/sshd"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/require"
)
// volatile lists everything in command output that legitimately differs between runs.
// Each run mints fresh certificates and indexes, so these are replaced with a marker
// before comparison. Keep the list short: anything added here is something the golden
// stops guarding.
var volatile = []struct {
re *regexp.Regexp
with string
}{
{regexp.MustCompile(`[0-9a-f]{40,}`), "<hex>"}, // fingerprints, keys, signatures
{regexp.MustCompile(`\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:\.\d+)?(?:Z|[+-]\d{2}:\d{2})`), "<time>"}, // RFC 3339
{regexp.MustCompile(`\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}(?:\.\d+)? [+-]\d{4} \w+`), "<time>"}, // time.Time.String()
{regexp.MustCompile(`(?s)(-----BEGIN [A-Z ]+-----\n).*?(\n-----END [A-Z ]+-----)`), "${1}<pem>${2}"}, // print-cert -raw
{regexp.MustCompile(`(-----BEGIN [A-Z ]+-----\\n).*?(\\n-----END [A-Z ]+-----)`), "${1}<pem>${2}"}, // the same, inside a JSON string
{regexp.MustCompile(`"(localIndex|remoteIndex|messageCounter)":\d+`), `"$1":<n>`},
{regexp.MustCompile(`(?m)^(\s*"?(?:LocalIndex|RemoteIndex|localIndex|remoteIndex|messageCounter)"?:?\s*)\d+`), "${1}<n>"}, // and the -pretty form
}
func normalise(s string) string {
for _, v := range volatile {
s = v.re.ReplaceAllString(s, v.with)
}
return s
}
// outputCase is one command line to run through the ssh dispatch path.
type outputCase struct {
name string
args []string
}
// TestCommandOutput pins the bytes every command produces, in every format, through the
// ssh dispatch path. It is the safety net for moving rendering out of the commands: a
// change here is a change someone at an ssh prompt would see. Regenerate with:
//
// go test -tags e2e_testing ./e2e -run TestCommandOutput -update
func TestCommandOutput(t *testing.T) {
ca, _, caKey, _ := cert_test.NewTestCaCert(
cert.Version1, cert.Curve_CURVE25519,
time.Now(), time.Now().Add(10*time.Minute),
nil, nil, []string{},
)
control, _, _, _ := newSimpleServer(cert.Version1, ca, caKey, "output-golden", "10.222.0.1/24", nil)
control.Start()
t.Cleanup(func() { control.Stop() })
// As an ssh session does: a clone of the daemon's registry with logout added, which
// help on the clone lists and describes. There is no session to end here.
reg := control.Commands().Clone()
reg.Register(sshd.LogoutCommand(func() {}))
// run dispatches as the ssh exec path does and returns the output and the error, which
// over ssh is exit status 1.
run := func(args ...string) (string, error) {
buf := &bytes.Buffer{}
err := reg.DispatchArgs(args, commands.NewStringWriter(buf))
return buf.String(), err
}
// Seed a pending tunnel so the listing and per-address commands have something to show.
seed, err := run("create-tunnel", "10.222.0.9")
require.NoError(t, err)
require.Equal(t, "Created\n", seed, "seeding a tunnel should succeed before anything else is recorded")
cases := []outputCase{
{"version", nil},
{"device-info", nil},
{"list-hostmap", nil},
{"list-hostmap", []string{"-by-index"}},
{"list-pending-hostmap", nil},
{"list-pending-hostmap", []string{"-by-index"}},
{"list-lighthouse-addrmap", nil},
{"print-cert", nil},
{"print-cert", []string{"-raw"}},
{"print-cert", []string{"10.222.0.9"}},
{"print-cert", []string{"10.222.0.250"}},
{"print-cert", []string{"not-an-address"}},
{"print-tunnel", nil},
{"print-tunnel", []string{"10.222.0.9"}},
{"print-tunnel", []string{"10.222.0.250"}},
{"print-relays", nil},
{"query-lighthouse", nil},
{"query-lighthouse", []string{"10.222.0.9"}},
{"query-lighthouse", []string{"not-an-address"}},
// The test logger cannot change level or format, so these cases record the
// refusal each command prints on it, not a successful change.
{"log-level", nil},
{"log-level", []string{"debug"}},
{"log-level", []string{"bogus"}},
{"log-level", []string{"info"}},
{"log-format", nil},
{"log-format", []string{"json"}},
{"log-format", []string{"text"}},
{"change-remote", nil},
{"change-remote", []string{"10.222.0.9"}},
{"change-remote", []string{"-address", "10.94.0.10:4242", "10.222.0.9"}},
{"change-remote", []string{"-address", "10.94.0.10:4242", "10.222.0.250"}},
{"create-tunnel", nil},
{"create-tunnel", []string{"10.222.0.9"}},
// A fresh address, so this exercises the handshake start with a remote attached
// rather than the "already handshaking" path above.
{"create-tunnel", []string{"-address", "10.94.0.10:4242", "10.222.0.10"}},
{"create-tunnel", []string{"not-an-address"}},
{"close-tunnel", nil},
{"close-tunnel", []string{"10.222.0.250"}},
{"close-tunnel", []string{"not-an-address"}},
{"help", nil},
{"help", []string{"print-cert"}},
{"help", []string{"logout"}},
{"logout", []string{"-h"}},
{"not-a-command", []string{"10.222.0.9"}},
// reload is last so that whatever a reload does to the daemon cannot leak into an
// earlier case. In this harness it fails: the config was loaded from a string and
// has no path to re-read, which is what the recorded result says.
{"reload", nil},
}
got := &strings.Builder{}
for _, c := range cases {
for _, fmtFlags := range [][]string{nil, {"-json"}, {"-pretty"}} {
args := append([]string{c.name}, fmtFlags...)
args = append(args, c.args...)
fmt.Fprintf(got, "$ %s\n", strings.Join(args, " "))
out, err := run(args...)
out = normalise(out)
got.WriteString(out)
// Output that does not end in a newline is recorded as such, the way diff marks
// it, so the golden sees that byte too and the next prompt still starts a line.
if out != "" && !strings.HasSuffix(out, "\n") {
got.WriteString("\\ No newline at end of output\n")
}
// A failed command is recorded as the exit status an ssh caller sees, so the
// golden pins which outcomes count as failures.
if err != nil {
got.WriteString("exit status 1\n")
}
got.WriteString("\n")
}
}
test.Golden(t, filepath.Join("testdata", "commands_output.golden"), got.String())
}