Compare commits

..

14 Commits

Author SHA1 Message Date
Joseph Doherty 192607ab8c fix(gateway): detect Certificate:Thumbprint and cover more KestrelTlsInspector cases 2026-06-01 07:22:24 -04:00
Joseph Doherty ba82afe669 fix(client-java): keep Temurin 21 toolchain, auto-provision instead of bumping to 26 2026-06-01 07:20:04 -04:00
Joseph Doherty fe7d1ce1ec feat(gateway): validate MxGateway:Tls options 2026-06-01 07:19:22 -04:00
Joseph Doherty b8a6695612 feat(gateway): generate self-signed ECDSA cert with SANs 2026-06-01 07:18:39 -04:00
Joseph Doherty 6f9188bc8d test(client-python): update TLS default-channel test for TOFU behavior 2026-06-01 07:17:36 -04:00
Joseph Doherty a276f46f81 feat(client-java): accept gateway cert by default over TLS 2026-06-01 07:13:45 -04:00
Joseph Doherty 572b268d81 feat(client-rust): accept gateway cert by default over TLS (or documented pin-only fallback) 2026-06-01 07:11:09 -04:00
Joseph Doherty 4c093a64fa feat(client-python): accept gateway cert by default via TOFU pre-fetch 2026-06-01 07:10:55 -04:00
Joseph Doherty f47bbaea95 feat(client-dotnet): accept gateway cert by default over TLS 2026-06-01 07:08:55 -04:00
Joseph Doherty c463b49f46 feat(client-go): accept gateway cert by default over TLS 2026-06-01 07:08:47 -04:00
Joseph Doherty 87f86503ef feat(gateway): add MxGateway:Tls options block 2026-06-01 07:08:19 -04:00
Joseph Doherty e912ef960c feat(gateway): detect HTTPS endpoints missing a certificate 2026-06-01 07:08:12 -04:00
Joseph Doherty c4e7ddea70 docs: implementation plan for gateway TLS auto-cert and lenient client trust 2026-06-01 07:01:58 -04:00
Joseph Doherty 6bfa4fe884 docs: design for gateway TLS auto-cert and lenient client trust 2026-06-01 06:54:23 -04:00
38 changed files with 2705 additions and 301 deletions
@@ -0,0 +1,42 @@
using System.Net.Http;
using ZB.MOM.WW.MxGateway.Client;
namespace ZB.MOM.WW.MxGateway.Client.Tests;
public sealed class MxGatewayClientTlsHandlerTests
{
/// <summary>
/// Verifies that when TLS is used with no pinned CA and RequireCertificateValidation is false (default),
/// the handler installs an accept-all callback so the gateway's self-signed cert is trusted.
/// </summary>
[Fact]
public void Handler_SkipsVerification_WhenTlsAndNoCaPinned()
{
MxGatewayClientOptions options = new()
{
Endpoint = new Uri("https://localhost:5120"),
ApiKey = "k",
UseTls = true,
};
using SocketsHttpHandler handler = MxGatewayClient.CreateHttpHandlerForTests(options);
Assert.NotNull(handler.SslOptions.RemoteCertificateValidationCallback);
}
/// <summary>
/// Verifies that when RequireCertificateValidation is true, the callback is left null
/// so the OS trust store performs validation.
/// </summary>
[Fact]
public void Handler_KeepsDefaultVerification_WhenRequireCertificateValidation()
{
MxGatewayClientOptions options = new()
{
Endpoint = new Uri("https://localhost:5120"),
ApiKey = "k",
UseTls = true,
RequireCertificateValidation = true,
};
using SocketsHttpHandler handler = MxGatewayClient.CreateHttpHandlerForTests(options);
Assert.Null(handler.SslOptions.RemoteCertificateValidationCallback);
}
}
@@ -315,7 +315,10 @@ public sealed class MxGatewayClient : IAsyncDisposable
.ConfigureAwait(false); .ConfigureAwait(false);
} }
private static HttpMessageHandler CreateHttpHandler(MxGatewayClientOptions options) private static HttpMessageHandler CreateHttpHandler(MxGatewayClientOptions options) =>
CreateHttpHandlerForTests(options);
internal static SocketsHttpHandler CreateHttpHandlerForTests(MxGatewayClientOptions options)
{ {
SocketsHttpHandler handler = new() SocketsHttpHandler handler = new()
{ {
@@ -350,6 +353,10 @@ public sealed class MxGatewayClient : IAsyncDisposable
return customChain.Build(certificateToValidate); return customChain.Build(certificateToValidate);
}; };
} }
else if (!options.RequireCertificateValidation)
{
handler.SslOptions.RemoteCertificateValidationCallback = (_, _, _, _) => true;
}
} }
return handler; return handler;
@@ -27,6 +27,14 @@ public sealed class MxGatewayClientOptions
/// </summary> /// </summary>
public string? CaCertificatePath { get; init; } public string? CaCertificatePath { get; init; }
/// <summary>
/// When true, TLS connections without a pinned <see cref="CaCertificatePath"/>
/// use the OS trust store. When false (default), the gateway certificate is
/// accepted without verification — appropriate for this internal tool's
/// auto-generated self-signed certificate. Pinning a CA always verifies.
/// </summary>
public bool RequireCertificateValidation { get; init; }
/// <summary> /// <summary>
/// Gets the server name override for SNI during TLS handshake. /// Gets the server name override for SNI during TLS handshake.
/// </summary> /// </summary>
@@ -27,4 +27,10 @@
<None Include="..\README.md" Pack="true" PackagePath="\" /> <None Include="..\README.md" Pack="true" PackagePath="\" />
</ItemGroup> </ItemGroup>
<ItemGroup>
<AssemblyAttribute Include="System.Runtime.CompilerServices.InternalsVisibleTo">
<_Parameter1>ZB.MOM.WW.MxGateway.Client.Tests</_Parameter1>
</AssemblyAttribute>
</ItemGroup>
</Project> </Project>
+16 -2
View File
@@ -222,10 +222,24 @@ func resolveTransportCredentials(opts Options) (credentials.TransportCredentials
return credentials.NewTLS(cfg), nil return credentials.NewTLS(cfg), nil
} }
return credentials.NewTLS(&tls.Config{ return credentials.NewTLS(tlsConfigForOptions(opts)), nil
}
// tlsConfigForOptions returns the *tls.Config for the no-CA, no-custom-config TLS path.
// It returns nil when the caller should use a different credentials path (CA file or custom TLSConfig).
// Exposed as an internal helper so unit tests can assert the InsecureSkipVerify posture.
func tlsConfigForOptions(opts Options) *tls.Config {
// CA file and custom TLSConfig take their own paths in resolveTransportCredentials.
if opts.CACertFile != "" || opts.TLSConfig != nil {
return nil
}
return &tls.Config{
MinVersion: tls.VersionTLS12, MinVersion: tls.VersionTLS12,
ServerName: opts.ServerNameOverride, ServerName: opts.ServerNameOverride,
}), nil //nolint:gosec // internal tool; self-signed cert is the expected gateway default;
// opt-in to strict verification via RequireCertificateValidation.
InsecureSkipVerify: !opts.RequireCertificateValidation,
}
} }
// OpenSessionOptions describes fields used to create an OpenSessionRequest. // OpenSessionOptions describes fields used to create an OpenSessionRequest.
+59
View File
@@ -0,0 +1,59 @@
package mxgateway
import (
"crypto/tls"
"testing"
)
// tlsConfigFromOptions is the internal helper under test.
// It extracts the *tls.Config from the no-CA TLS path of resolveTransportCredentials.
// We exercise it directly to avoid needing a real dial target.
func TestTLSInsecureSkipVerify_DefaultTrue(t *testing.T) {
cfg := tlsConfigForOptions(Options{
Endpoint: "localhost:5120",
})
if cfg == nil {
t.Fatal("expected non-nil tls.Config")
}
if !cfg.InsecureSkipVerify {
t.Error("InsecureSkipVerify should be true by default when no CA is pinned")
}
}
func TestTLSInsecureSkipVerify_FalseWhenRequireCertificateValidation(t *testing.T) {
cfg := tlsConfigForOptions(Options{
Endpoint: "localhost:5120",
RequireCertificateValidation: true,
})
if cfg == nil {
t.Fatal("expected non-nil tls.Config")
}
if cfg.InsecureSkipVerify {
t.Error("InsecureSkipVerify should be false when RequireCertificateValidation is true")
}
}
func TestTLSInsecureSkipVerify_FalseWhenCACertFileSet(t *testing.T) {
// When a CA file is pinned, the CA-verification path is taken instead.
// tlsConfigForOptions should return nil (the CA path does not use our helper).
cfg := tlsConfigForOptions(Options{
Endpoint: "localhost:5120",
CACertFile: "/some/ca.pem",
})
if cfg != nil {
t.Error("expected nil tls.Config when CACertFile is set (CA path taken)")
}
}
func TestTLSInsecureSkipVerify_FalseWhenCustomTLSConfig(t *testing.T) {
// When TLSConfig is supplied explicitly, our default skip-verify must not overwrite it.
custom := &tls.Config{MinVersion: tls.VersionTLS13}
cfg := tlsConfigForOptions(Options{
Endpoint: "localhost:5120",
TLSConfig: custom,
})
if cfg != nil {
t.Error("expected nil tls.Config when TLSConfig is already set (custom config path taken)")
}
}
+4
View File
@@ -34,6 +34,10 @@ type Options struct {
TransportCredentials credentials.TransportCredentials TransportCredentials credentials.TransportCredentials
// DialOptions are appended to the gRPC dial options after the defaults. // DialOptions are appended to the gRPC dial options after the defaults.
DialOptions []grpc.DialOption DialOptions []grpc.DialOption
// RequireCertificateValidation forces TLS certificate verification even when
// no CACertFile is pinned. Default false: the gateway's self-signed cert is
// accepted without verification (internal-tool posture).
RequireCertificateValidation bool
} }
// BrowseChildrenOptions configures lazy Galaxy hierarchy walks performed by // BrowseChildrenOptions configures lazy Galaxy hierarchy walks performed by
+4
View File
@@ -9,6 +9,10 @@ pluginManagement {
} }
} }
plugins {
id 'org.gradle.toolchains.foojay-resolver-convention' version '1.0.0'
}
dependencyResolutionManagement { dependencyResolutionManagement {
repositoriesMode.set(RepositoriesMode.FAIL_ON_PROJECT_REPOS) repositoriesMode.set(RepositoriesMode.FAIL_ON_PROJECT_REPOS)
repositories { repositories {
@@ -384,6 +384,15 @@ public final class MxGatewayClient implements AutoCloseable {
} catch (SSLException error) { } catch (SSLException error) {
throw new MxGatewayException("failed to configure gateway TLS", error); throw new MxGatewayException("failed to configure gateway TLS", error);
} }
} else if (!options.requireCertificateValidation()) {
try {
builder.sslContext(GrpcSslContexts.forClient()
.trustManager(io.grpc.netty.shaded.io.netty.handler.ssl.util
.InsecureTrustManagerFactory.INSTANCE)
.build());
} catch (SSLException error) {
throw new MxGatewayException("failed to configure lenient gateway TLS", error);
}
} else { } else {
builder.useTransportSecurity(); builder.useTransportSecurity();
} }
@@ -393,6 +402,19 @@ public final class MxGatewayClient implements AutoCloseable {
return builder.build(); return builder.build();
} }
/**
* Package-visible test seam — creates a raw {@link ManagedChannel} from the
* given options without attaching auth interceptors. Used by TLS fixture
* tests to verify channel construction behaviour without a full
* {@link MxGatewayClient} wrapper.
*
* @param options the client options
* @return a new {@link ManagedChannel}
*/
static ManagedChannel createChannelForTests(MxGatewayClientOptions options) {
return createChannel(options);
}
private <T extends io.grpc.stub.AbstractStub<T>> T withDeadline(T stub) { private <T extends io.grpc.stub.AbstractStub<T>> T withDeadline(T stub) {
if (options.callTimeout().isNegative()) { if (options.callTimeout().isNegative()) {
return stub; return stub;
@@ -20,6 +20,7 @@ public final class MxGatewayClientOptions {
private final String apiKey; private final String apiKey;
private final boolean plaintext; private final boolean plaintext;
private final Path caCertificatePath; private final Path caCertificatePath;
private final boolean requireCertificateValidation;
private final String serverNameOverride; private final String serverNameOverride;
private final Duration connectTimeout; private final Duration connectTimeout;
private final Duration callTimeout; private final Duration callTimeout;
@@ -31,6 +32,7 @@ public final class MxGatewayClientOptions {
apiKey = builder.apiKey == null ? "" : builder.apiKey; apiKey = builder.apiKey == null ? "" : builder.apiKey;
plaintext = builder.plaintext; plaintext = builder.plaintext;
caCertificatePath = builder.caCertificatePath; caCertificatePath = builder.caCertificatePath;
requireCertificateValidation = builder.requireCertificateValidation;
serverNameOverride = builder.serverNameOverride == null ? "" : builder.serverNameOverride; serverNameOverride = builder.serverNameOverride == null ? "" : builder.serverNameOverride;
connectTimeout = builder.connectTimeout == null ? DEFAULT_CONNECT_TIMEOUT : builder.connectTimeout; connectTimeout = builder.connectTimeout == null ? DEFAULT_CONNECT_TIMEOUT : builder.connectTimeout;
callTimeout = builder.callTimeout == null ? DEFAULT_CALL_TIMEOUT : builder.callTimeout; callTimeout = builder.callTimeout == null ? DEFAULT_CALL_TIMEOUT : builder.callTimeout;
@@ -95,6 +97,18 @@ public final class MxGatewayClientOptions {
return caCertificatePath; return caCertificatePath;
} }
/**
* Returns whether TLS certificate verification is required even when no CA is pinned.
* When {@code false} (default), the gateway's self-signed certificate is accepted
* without verification. When {@code true}, the OS trust store is used.
* Pinning a CA via {@link #caCertificatePath()} always verifies regardless of this flag.
*
* @return {@code true} if strict certificate verification is required
*/
public boolean requireCertificateValidation() {
return requireCertificateValidation;
}
/** /**
* Returns the TLS server-name override, or an empty string when none was supplied. * Returns the TLS server-name override, or an empty string when none was supplied.
* *
@@ -148,6 +162,8 @@ public final class MxGatewayClientOptions {
+ plaintext + plaintext
+ ", caCertificatePath=" + ", caCertificatePath="
+ caCertificatePath + caCertificatePath
+ ", requireCertificateValidation="
+ requireCertificateValidation
+ ", serverNameOverride='" + ", serverNameOverride='"
+ serverNameOverride + serverNameOverride
+ '\'' + '\''
@@ -177,6 +193,7 @@ public final class MxGatewayClientOptions {
private String apiKey; private String apiKey;
private boolean plaintext; private boolean plaintext;
private Path caCertificatePath; private Path caCertificatePath;
private boolean requireCertificateValidation;
private String serverNameOverride; private String serverNameOverride;
private Duration connectTimeout; private Duration connectTimeout;
private Duration callTimeout; private Duration callTimeout;
@@ -230,6 +247,21 @@ public final class MxGatewayClientOptions {
return this; return this;
} }
/**
* When {@code true}, TLS connections without a pinned CA use the OS trust store
* and will reject the gateway's self-signed certificate. When {@code false}
* (default), the gateway certificate is accepted without verification —
* appropriate for this internal tool's auto-generated self-signed certificate.
* Pinning a CA via {@link #caCertificatePath(Path)} always verifies.
*
* @param value {@code true} to require certificate validation, {@code false} to accept any cert
* @return this builder
*/
public Builder requireCertificateValidation(boolean value) {
requireCertificateValidation = value;
return this;
}
/** /**
* Overrides the TLS server name used during the handshake. * Overrides the TLS server name used during the handshake.
* *
@@ -0,0 +1,198 @@
package com.zb.mom.ww.mxgateway.client;
import static org.junit.jupiter.api.Assertions.assertThrows;
import static org.junit.jupiter.api.Assertions.assertTrue;
import io.grpc.ManagedChannel;
import io.grpc.Server;
import io.grpc.StatusRuntimeException;
import io.grpc.netty.shaded.io.grpc.netty.GrpcSslContexts;
import io.grpc.netty.shaded.io.grpc.netty.NettyServerBuilder;
import io.grpc.stub.StreamObserver;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.net.InetSocketAddress;
import java.nio.file.Files;
import java.security.KeyStore;
import java.security.PrivateKey;
import java.security.cert.Certificate;
import java.security.cert.X509Certificate;
import java.time.Duration;
import java.util.Base64;
import java.util.concurrent.TimeUnit;
import javax.net.ssl.SSLException;
import mxaccess_gateway.v1.MxAccessGatewayGrpc;
import mxaccess_gateway.v1.MxaccessGateway.OpenSessionReply;
import mxaccess_gateway.v1.MxaccessGateway.OpenSessionRequest;
import mxaccess_gateway.v1.MxaccessGateway.ProtocolStatus;
import mxaccess_gateway.v1.MxaccessGateway.ProtocolStatusCode;
import org.junit.jupiter.api.AfterEach;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
/**
* Verifies that the Java client connects to a Netty TLS server with a
* self-signed certificate when no CA is pinned (lenient default), and that
* setting {@code requireCertificateValidation(true)} causes a TLS failure.
*
* <p>A self-signed certificate is generated using {@code keytool} (always
* available in the JDK) to avoid dependencies on internal JDK APIs or
* BouncyCastle, and so the test works on all JDK versions used by the project.
*/
final class MxGatewayClientTlsTests {
private Server server;
private int port;
private File certPemFile;
private File keyPemFile;
private File keystoreFile;
@BeforeEach
void startTlsServer() throws Exception {
keystoreFile = File.createTempFile("gw-test-ks", ".p12");
certPemFile = File.createTempFile("gw-test-cert", ".pem");
keyPemFile = File.createTempFile("gw-test-key", ".pem");
// keytool refuses to write to a pre-existing (even empty) file; delete it first.
keystoreFile.delete();
// Use keytool to generate a self-signed PKCS12 keystore.
String keytool = ProcessHandle.current().info().command()
.map(cmd -> cmd.replace("java", "keytool"))
.orElse("keytool");
// Fall back to just "keytool" on PATH if the resolved path doesn't exist.
if (!new File(keytool).exists()) {
keytool = "keytool";
}
Process p = new ProcessBuilder(
keytool,
"-genkeypair",
"-alias", "server",
"-keyalg", "RSA",
"-keysize", "2048",
"-sigalg", "SHA256withRSA",
"-validity", "1",
"-dname", "CN=localhost",
"-storetype", "PKCS12",
"-storepass", "changeit",
"-keypass", "changeit",
"-keystore", keystoreFile.getAbsolutePath())
.redirectErrorStream(true)
.start();
int exit = p.waitFor();
if (exit != 0) {
String out = new String(p.getInputStream().readAllBytes());
throw new IllegalStateException("keytool failed (exit " + exit + "): " + out);
}
// Export cert and private key from the PKCS12 keystore to PEM files.
KeyStore ks = KeyStore.getInstance("PKCS12");
try (var is = Files.newInputStream(keystoreFile.toPath())) {
ks.load(is, "changeit".toCharArray());
}
X509Certificate cert = (X509Certificate) ks.getCertificate("server");
PrivateKey privateKey = (PrivateKey) ks.getKey("server", "changeit".toCharArray());
try (FileOutputStream out = new FileOutputStream(certPemFile)) {
out.write("-----BEGIN CERTIFICATE-----\n".getBytes());
out.write(Base64.getMimeEncoder(64, new byte[]{'\n'}).encode(cert.getEncoded()));
out.write("\n-----END CERTIFICATE-----\n".getBytes());
}
try (FileOutputStream out = new FileOutputStream(keyPemFile)) {
out.write("-----BEGIN PRIVATE KEY-----\n".getBytes());
out.write(Base64.getMimeEncoder(64, new byte[]{'\n'}).encode(privateKey.getEncoded()));
out.write("\n-----END PRIVATE KEY-----\n".getBytes());
}
server = NettyServerBuilder
.forAddress(new InetSocketAddress("127.0.0.1", 0))
.sslContext(GrpcSslContexts.forServer(certPemFile, keyPemFile).build())
.addService(new MinimalGatewayService())
.build()
.start();
port = server.getPort();
}
@AfterEach
void stopTlsServer() throws InterruptedException {
if (server != null) {
server.shutdown();
server.awaitTermination(5, TimeUnit.SECONDS);
}
if (certPemFile != null) {
certPemFile.delete();
}
if (keyPemFile != null) {
keyPemFile.delete();
}
if (keystoreFile != null) {
keystoreFile.delete();
}
}
@Test
void connectsToSelfSignedServer_WhenRequireCertificateValidationIsFalse() throws SSLException {
// Default options — requireCertificateValidation defaults to false.
MxGatewayClientOptions options = MxGatewayClientOptions.builder()
.endpoint("127.0.0.1:" + port)
.apiKey("test-key")
.connectTimeout(Duration.ofSeconds(5))
.callTimeout(Duration.ofSeconds(5))
.build();
ManagedChannel channel = MxGatewayClient.createChannelForTests(options);
try {
MxAccessGatewayGrpc.MxAccessGatewayBlockingStub stub =
MxAccessGatewayGrpc.newBlockingStub(channel);
OpenSessionReply reply = stub.openSession(
OpenSessionRequest.newBuilder()
.setClientSessionName("tls-test")
.build());
assertTrue(reply.getProtocolStatus().getCode()
== ProtocolStatusCode.PROTOCOL_STATUS_CODE_OK);
} finally {
channel.shutdownNow();
}
}
@Test
void failsToConnect_WhenRequireCertificateValidationIsTrue() throws SSLException {
MxGatewayClientOptions options = MxGatewayClientOptions.builder()
.endpoint("127.0.0.1:" + port)
.apiKey("test-key")
.requireCertificateValidation(true)
.connectTimeout(Duration.ofSeconds(5))
.callTimeout(Duration.ofSeconds(5))
.build();
ManagedChannel channel = MxGatewayClient.createChannelForTests(options);
try {
MxAccessGatewayGrpc.MxAccessGatewayBlockingStub stub =
MxAccessGatewayGrpc.newBlockingStub(channel);
assertThrows(StatusRuntimeException.class, () ->
stub.openSession(OpenSessionRequest.newBuilder()
.setClientSessionName("tls-strict-test")
.build()));
} finally {
channel.shutdownNow();
}
}
/** Minimal gateway stub that succeeds any OpenSession call. */
private static final class MinimalGatewayService
extends MxAccessGatewayGrpc.MxAccessGatewayImplBase {
@Override
public void openSession(
OpenSessionRequest request,
StreamObserver<OpenSessionReply> responseObserver) {
responseObserver.onNext(OpenSessionReply.newBuilder()
.setSessionId("tls-test-session")
.setProtocolStatus(ProtocolStatus.newBuilder()
.setCode(ProtocolStatusCode.PROTOCOL_STATUS_CODE_OK)
.build())
.build());
responseObserver.onCompleted();
}
}
}
@@ -2,6 +2,7 @@
from __future__ import annotations from __future__ import annotations
import ssl
from collections.abc import Sequence from collections.abc import Sequence
from dataclasses import dataclass, field from dataclasses import dataclass, field
from pathlib import Path from pathlib import Path
@@ -9,6 +10,7 @@ from pathlib import Path
import grpc import grpc
from .auth import REDACTED, ApiKey from .auth import REDACTED, ApiKey
from .errors import MxGatewayTransportError
@dataclass(frozen=True) @dataclass(frozen=True)
@@ -19,6 +21,7 @@ class ClientOptions:
api_key: str | ApiKey | None = None api_key: str | ApiKey | None = None
plaintext: bool = False plaintext: bool = False
ca_file: str | None = None ca_file: str | None = None
require_certificate_validation: bool = False
server_name_override: str | None = None server_name_override: str | None = None
call_timeout: float | None = 30.0 call_timeout: float | None = 30.0
stream_timeout: float | None = None stream_timeout: float | None = None
@@ -45,6 +48,7 @@ class ClientOptions:
f"{type(self).__name__}(endpoint={self.endpoint!r}, " f"{type(self).__name__}(endpoint={self.endpoint!r}, "
f"api_key={api_key!r}, plaintext={self.plaintext!r}, " f"api_key={api_key!r}, plaintext={self.plaintext!r}, "
f"ca_file={self.ca_file!r}, " f"ca_file={self.ca_file!r}, "
f"require_certificate_validation={self.require_certificate_validation!r}, "
f"server_name_override={self.server_name_override!r}, " f"server_name_override={self.server_name_override!r}, "
f"call_timeout={self.call_timeout!r}, " f"call_timeout={self.call_timeout!r}, "
f"stream_timeout={self.stream_timeout!r}, " f"stream_timeout={self.stream_timeout!r}, "
@@ -69,8 +73,22 @@ class BrowseChildrenOptions:
historized_only: bool = False historized_only: bool = False
def _split_authority(endpoint: str) -> tuple[str, int]:
"""Split a gRPC target (optionally scheme-prefixed) into (host, port)."""
target = endpoint.split("://", 1)[-1]
host, _, port = target.rpartition(":")
return (host or "localhost", int(port) if port else 443)
def create_channel(options: ClientOptions) -> grpc.aio.Channel: def create_channel(options: ClientOptions) -> grpc.aio.Channel:
"""Create a plaintext or TLS `grpc.aio` channel from client options.""" """Create a plaintext or TLS `grpc.aio` channel from client options.
The TLS default is lenient: grpc-python has no per-channel skip-verify, so
the server's presented certificate is fetched once (unverified) and pinned
as the channel's only trust root (trust-on-first-use). Set
`require_certificate_validation=True` to force system-trust verification, or
pass `ca_file` to verify against a specific CA — both bypass the TOFU path.
"""
channel_options: list[tuple[str, str | int]] = [ channel_options: list[tuple[str, str | int]] = [
("grpc.max_receive_message_length", options.max_grpc_message_bytes), ("grpc.max_receive_message_length", options.max_grpc_message_bytes),
@@ -82,11 +100,28 @@ def create_channel(options: ClientOptions) -> grpc.aio.Channel:
if options.plaintext: if options.plaintext:
return grpc.aio.insecure_channel(options.endpoint, options=channel_options) return grpc.aio.insecure_channel(options.endpoint, options=channel_options)
root_certificates = None
if options.ca_file: if options.ca_file:
root_certificates = Path(options.ca_file).read_bytes() root_certificates = Path(options.ca_file).read_bytes()
credentials = grpc.ssl_channel_credentials(root_certificates=root_certificates)
elif options.require_certificate_validation:
credentials = grpc.ssl_channel_credentials()
else:
# Lenient default: grpc-python has no per-channel skip-verify, so fetch the
# server's certificate (unverified) and pin it for this channel (TOFU).
host, port = _split_authority(options.endpoint)
try:
presented = ssl.get_server_certificate((host, port))
except OSError as error:
raise MxGatewayTransportError(
f"failed to fetch TLS certificate from {options.endpoint}: {error}"
) from error
credentials = grpc.ssl_channel_credentials(root_certificates=presented.encode("ascii"))
# The gateway self-signed cert always carries a "localhost" SAN, so default
# the SNI/target-name override to it when none was supplied, tolerating
# dial-by-IP or hostname mismatch.
if not options.server_name_override:
channel_options.append(("grpc.ssl_target_name_override", "localhost"))
credentials = grpc.ssl_channel_credentials(root_certificates=root_certificates)
return grpc.aio.secure_channel( return grpc.aio.secure_channel(
options.endpoint, options.endpoint,
credentials, credentials,
+186 -23
View File
@@ -72,27 +72,83 @@ def test_create_channel_uses_plaintext_channel(monkeypatch: pytest.MonkeyPatch)
] ]
def test_create_channel_uses_tls_channel(monkeypatch: pytest.MonkeyPatch) -> None: def test_create_channel_uses_tls_channel_tofu_default(monkeypatch: pytest.MonkeyPatch) -> None:
calls: list[tuple[str, object, object]] = [] """Default TLS (no ca_file, no require_certificate_validation) uses TOFU:
fetches the server cert unverified, pins it as root_certificates, and adds
grpc.ssl_target_name_override = "localhost" automatically.
"""
_DUMMY_PEM = "-----BEGIN CERTIFICATE-----\nZmFrZQ==\n-----END CERTIFICATE-----\n"
get_cert_calls: list[tuple[str, int]] = []
def fake_credentials(*, root_certificates: object) -> str: def fake_get_server_certificate(addr: tuple[str, int]) -> str:
assert root_certificates is None get_cert_calls.append(addr)
return _DUMMY_PEM
cred_calls: list[object] = []
def fake_credentials(*, root_certificates: object = None) -> str:
cred_calls.append(root_certificates)
return "creds" return "creds"
channel_calls: list[tuple[str, object, object]] = []
def fake_secure_channel(endpoint: str, credentials: object, *, options: object) -> str: def fake_secure_channel(endpoint: str, credentials: object, *, options: object) -> str:
calls.append((endpoint, credentials, options)) channel_calls.append((endpoint, credentials, options))
return "tls-channel" return "tls-channel"
monkeypatch.setattr( monkeypatch.setattr(options_module.ssl, "get_server_certificate", fake_get_server_certificate)
options_module.grpc, monkeypatch.setattr(options_module.grpc, "ssl_channel_credentials", fake_credentials)
"ssl_channel_credentials", monkeypatch.setattr(options_module.grpc.aio, "secure_channel", fake_secure_channel)
fake_credentials,
channel = create_channel(
ClientOptions(endpoint="gateway.example:5001"),
) )
assert channel == "tls-channel"
# TOFU: should have fetched the cert from the server (host, port)
assert get_cert_calls == [("gateway.example", 5001)]
# Pinned the fetched PEM bytes as root_certificates
assert cred_calls == [_DUMMY_PEM.encode("ascii")]
# Auto-injected localhost override (no server_name_override supplied)
assert channel_calls == [
(
"gateway.example:5001",
"creds",
[
("grpc.max_receive_message_length", 16 * 1024 * 1024),
("grpc.max_send_message_length", 16 * 1024 * 1024),
("grpc.ssl_target_name_override", "localhost"),
],
),
]
def test_create_channel_uses_tls_channel_tofu_respects_server_name_override(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""When server_name_override is set, TOFU still runs but does NOT add the
auto-localhost override (the explicit override is already in channel_options).
"""
_DUMMY_PEM = "-----BEGIN CERTIFICATE-----\nZmFrZQ==\n-----END CERTIFICATE-----\n"
monkeypatch.setattr( monkeypatch.setattr(
options_module.grpc.aio, options_module.ssl,
"secure_channel", "get_server_certificate",
fake_secure_channel, lambda addr: _DUMMY_PEM,
) )
cred_calls: list[object] = []
def fake_credentials(*, root_certificates: object = None) -> str:
cred_calls.append(root_certificates)
return "creds"
channel_calls: list[tuple[str, object, object]] = []
def fake_secure_channel(endpoint: str, credentials: object, *, options: object) -> str:
channel_calls.append((endpoint, credentials, options))
return "tls-channel"
monkeypatch.setattr(options_module.grpc, "ssl_channel_credentials", fake_credentials)
monkeypatch.setattr(options_module.grpc.aio, "secure_channel", fake_secure_channel)
channel = create_channel( channel = create_channel(
ClientOptions( ClientOptions(
@@ -102,14 +158,121 @@ def test_create_channel_uses_tls_channel(monkeypatch: pytest.MonkeyPatch) -> Non
) )
assert channel == "tls-channel" assert channel == "tls-channel"
assert calls == [ assert cred_calls == [_DUMMY_PEM.encode("ascii")]
( assert channel_calls == [
"gateway.example:5001", (
"creds", "gateway.example:5001",
[ "creds",
("grpc.max_receive_message_length", 16 * 1024 * 1024), [
("grpc.max_send_message_length", 16 * 1024 * 1024), ("grpc.max_receive_message_length", 16 * 1024 * 1024),
("grpc.ssl_target_name_override", "gateway.test"), ("grpc.max_send_message_length", 16 * 1024 * 1024),
], # Explicit override from ClientOptions — not the auto-localhost one
), ("grpc.ssl_target_name_override", "gateway.test"),
] ],
),
]
def test_create_channel_uses_tls_channel_require_cert_validation(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""require_certificate_validation=True uses system trust (no TOFU, no root_certificates)."""
get_cert_called = False
def fake_get_server_certificate(addr: object) -> str: # pragma: no cover
nonlocal get_cert_called
get_cert_called = True
return "SHOULD_NOT_BE_CALLED"
cred_calls: list[object] = []
def fake_credentials(**kwargs: object) -> str:
cred_calls.append(kwargs)
return "creds"
channel_calls: list[tuple[str, object, object]] = []
def fake_secure_channel(endpoint: str, credentials: object, *, options: object) -> str:
channel_calls.append((endpoint, credentials, options))
return "tls-channel"
monkeypatch.setattr(options_module.ssl, "get_server_certificate", fake_get_server_certificate)
monkeypatch.setattr(options_module.grpc, "ssl_channel_credentials", fake_credentials)
monkeypatch.setattr(options_module.grpc.aio, "secure_channel", fake_secure_channel)
channel = create_channel(
ClientOptions(
endpoint="gateway.example:5001",
require_certificate_validation=True,
),
)
assert channel == "tls-channel"
# Must NOT call TOFU prefetch
assert not get_cert_called
# ssl_channel_credentials() called with NO keyword args (system trust)
assert cred_calls == [{}]
assert channel_calls == [
(
"gateway.example:5001",
"creds",
[
("grpc.max_receive_message_length", 16 * 1024 * 1024),
("grpc.max_send_message_length", 16 * 1024 * 1024),
],
),
]
def test_create_channel_uses_tls_channel_ca_file(
monkeypatch: pytest.MonkeyPatch,
tmp_path: pytest.TempPathFactory,
) -> None:
"""ca_file path: reads the PEM file, passes bytes as root_certificates, skips TOFU."""
ca_pem = b"-----BEGIN CERTIFICATE-----\nY2FkYXRh\n-----END CERTIFICATE-----\n"
ca_file = tmp_path / "ca.pem"
ca_file.write_bytes(ca_pem)
get_cert_called = False
def fake_get_server_certificate(addr: object) -> str: # pragma: no cover
nonlocal get_cert_called
get_cert_called = True
return "SHOULD_NOT_BE_CALLED"
cred_calls: list[object] = []
def fake_credentials(*, root_certificates: object = None) -> str:
cred_calls.append(root_certificates)
return "creds"
channel_calls: list[tuple[str, object, object]] = []
def fake_secure_channel(endpoint: str, credentials: object, *, options: object) -> str:
channel_calls.append((endpoint, credentials, options))
return "tls-channel"
monkeypatch.setattr(options_module.ssl, "get_server_certificate", fake_get_server_certificate)
monkeypatch.setattr(options_module.grpc, "ssl_channel_credentials", fake_credentials)
monkeypatch.setattr(options_module.grpc.aio, "secure_channel", fake_secure_channel)
channel = create_channel(
ClientOptions(
endpoint="gateway.example:5001",
ca_file=str(ca_file),
),
)
assert channel == "tls-channel"
assert not get_cert_called
assert cred_calls == [ca_pem]
assert channel_calls == [
(
"gateway.example:5001",
"creds",
[
("grpc.max_receive_message_length", 16 * 1024 * 1024),
("grpc.max_send_message_length", 16 * 1024 * 1024),
],
),
]
+154
View File
@@ -0,0 +1,154 @@
"""TLS behaviour tests for ``create_channel``.
These spin up a real loopback ``grpc.aio`` server with a freshly generated
self-signed certificate (carrying a ``localhost`` SAN, mirroring the gateway's
auto-generated cert) and assert the lenient TOFU default lets a client connect
without any CA configured.
Marked ``tls`` and skipped unless ``MXGATEWAY_RUN_TLS_TESTS=1`` because loopback
TLS handshakes can be timing-flaky on shared CI runners. This mirrors how the
suite gates anything that depends on real sockets rather than fakes.
"""
from __future__ import annotations
import os
import shutil
import socket
import ssl
import subprocess
import tempfile
from collections.abc import AsyncIterator
from pathlib import Path
import grpc
import pytest
import pytest_asyncio
from zb_mom_ww_mxgateway import ClientOptions
from zb_mom_ww_mxgateway.errors import MxGatewayTransportError
from zb_mom_ww_mxgateway.generated import mxaccess_gateway_pb2 as pb
from zb_mom_ww_mxgateway.generated import mxaccess_gateway_pb2_grpc as pb_grpc
from zb_mom_ww_mxgateway.options import create_channel
pytestmark = pytest.mark.tls
_RUN_TLS_TESTS = os.environ.get("MXGATEWAY_RUN_TLS_TESTS") == "1"
_OPENSSL = shutil.which("openssl")
requires_tls = pytest.mark.skipif(
not _RUN_TLS_TESTS,
reason="set MXGATEWAY_RUN_TLS_TESTS=1 to run loopback TLS tests",
)
requires_openssl = pytest.mark.skipif(
_OPENSSL is None,
reason="openssl CLI is required to generate a self-signed test certificate",
)
def _generate_self_signed_cert(directory: Path) -> tuple[Path, Path]:
"""Generate a self-signed cert/key pair with a ``localhost`` SAN."""
key_path = directory / "server.key"
cert_path = directory / "server.crt"
subprocess.run(
[
str(_OPENSSL),
"req",
"-x509",
"-newkey",
"rsa:2048",
"-nodes",
"-keyout",
str(key_path),
"-out",
str(cert_path),
"-days",
"1",
"-subj",
"/CN=mxgateway-test",
"-addext",
"subjectAltName=DNS:localhost,IP:127.0.0.1",
],
check=True,
capture_output=True,
)
return cert_path, key_path
def _free_port() -> int:
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock:
sock.bind(("127.0.0.1", 0))
return int(sock.getsockname()[1])
class _StaticGatewayServicer(pb_grpc.MxAccessGatewayServicer):
"""Minimal servicer answering ``OpenSession`` with a fixed session id."""
async def OpenSession( # noqa: N802 - generated gRPC method name
self, request: pb.OpenSessionRequest, context: object
) -> pb.OpenSessionReply:
return pb.OpenSessionReply(session_id="tls-session-1")
@pytest_asyncio.fixture
async def tls_server() -> AsyncIterator[int]:
with tempfile.TemporaryDirectory() as tmp:
cert_path, key_path = _generate_self_signed_cert(Path(tmp))
credentials = grpc.ssl_server_credentials(
[(key_path.read_bytes(), cert_path.read_bytes())]
)
server = grpc.aio.server()
pb_grpc.add_MxAccessGatewayServicer_to_server(_StaticGatewayServicer(), server)
port = _free_port()
server.add_secure_port(f"127.0.0.1:{port}", credentials)
await server.start()
try:
yield port
finally:
await server.stop(grace=None)
@requires_tls
@requires_openssl
@pytest.mark.asyncio
async def test_default_tls_connects_via_tofu(tls_server: int) -> None:
"""Default TLS options (no CA) connect by pinning the presented cert."""
options = ClientOptions(
endpoint=f"127.0.0.1:{tls_server}",
api_key="mxgw_test_secret",
)
channel = create_channel(options)
try:
stub = pb_grpc.MxAccessGatewayStub(channel)
reply = await stub.OpenSession(pb.OpenSessionRequest(), timeout=10)
assert reply.session_id == "tls-session-1"
finally:
await channel.close()
def test_split_authority_parses_host_and_port() -> None:
from zb_mom_ww_mxgateway.options import _split_authority
assert _split_authority("https://10.0.0.5:5120") == ("10.0.0.5", 5120)
assert _split_authority("localhost:5120") == ("localhost", 5120)
assert _split_authority(":5120") == ("localhost", 5120)
def test_tofu_connect_failure_raises_transport_error() -> None:
"""A failed cert pre-fetch surfaces the client's transport error type."""
options = ClientOptions(endpoint=f"127.0.0.1:{_free_port()}")
with pytest.raises(MxGatewayTransportError) as excinfo:
create_channel(options)
assert options.endpoint in str(excinfo.value)
def test_require_certificate_validation_uses_system_trust() -> None:
"""``require_certificate_validation`` must not attempt a TOFU pre-fetch."""
# Pointing at a closed port: with system-trust the channel is created lazily
# (no eager pre-fetch), so create_channel must succeed without connecting.
options = ClientOptions(
endpoint=f"127.0.0.1:{_free_port()}",
require_certificate_validation=True,
)
channel = create_channel(options)
assert isinstance(channel, grpc.aio.Channel)
+20
View File
@@ -89,6 +89,26 @@ impl GatewayClient {
detail: format!("failed to read CA file {}: {source}", ca_file.display()), detail: format!("failed to read CA file {}: {source}", ca_file.display()),
})?; })?;
tls = tls.ca_certificate(Certificate::from_pem(certificate)); tls = tls.ca_certificate(Certificate::from_pem(certificate));
} else if !options.require_certificate_validation() {
// Lenient-default fallback (Rust pin-only exception): tonic
// 0.13's `ClientTlsConfig` builds its rustls verifier inside a
// crate-private connector and exposes no hook for a custom
// `ServerCertVerifier`, so — unlike the other clients — the
// Rust client cannot accept an arbitrary self-signed cert. Pin
// the gateway's CA instead, or opt into strict verification
// against the system trust roots. We reject here rather than
// silently verifying against system roots (which would fail a
// self-signed gateway with a confusing handshake error).
return Err(Error::InvalidEndpoint {
endpoint: options.endpoint().to_owned(),
detail: "TLS requested without a pinned CA. The Rust client cannot accept an \
arbitrary self-signed certificate (tonic 0.13 exposes no custom \
rustls verifier). Pin the gateway certificate with \
ClientOptions::with_ca_file, or call \
ClientOptions::with_require_certificate_validation(true) to verify \
against the system trust roots."
.to_owned(),
});
} }
endpoint = endpoint.tls_config(tls)?; endpoint = endpoint.tls_config(tls)?;
} }
+28
View File
@@ -22,6 +22,7 @@ pub struct ClientOptions {
api_key: Option<ApiKey>, api_key: Option<ApiKey>,
plaintext: bool, plaintext: bool,
ca_file: Option<PathBuf>, ca_file: Option<PathBuf>,
require_certificate_validation: bool,
server_name_override: Option<String>, server_name_override: Option<String>,
connect_timeout: Duration, connect_timeout: Duration,
call_timeout: Duration, call_timeout: Duration,
@@ -38,6 +39,7 @@ impl ClientOptions {
api_key: None, api_key: None,
plaintext: true, plaintext: true,
ca_file: None, ca_file: None,
require_certificate_validation: false,
server_name_override: None, server_name_override: None,
connect_timeout: Duration::from_secs(10), connect_timeout: Duration::from_secs(10),
call_timeout: Duration::from_secs(30), call_timeout: Duration::from_secs(30),
@@ -67,6 +69,22 @@ impl ClientOptions {
self self
} }
/// Require TLS certificate verification even without a pinned CA. Default
/// false: the gateway's self-signed certificate is accepted (internal-tool
/// posture). Setting a CA file always verifies.
///
/// Note for Rust: tonic 0.13's `ClientTlsConfig` exposes no hook for a
/// custom rustls verifier, so the Rust client cannot accept an arbitrary
/// self-signed certificate the way the other clients do. With the default
/// (false) and no pinned CA, [`crate::client::GatewayClient::connect`]
/// rejects the TLS connection and asks for a CA file. Either pin a CA via
/// [`ClientOptions::with_ca_file`] (the supported lenient path on Rust) or
/// set this `true` to verify against the system trust roots.
pub fn with_require_certificate_validation(mut self, require: bool) -> Self {
self.require_certificate_validation = require;
self
}
/// Override the SNI/server name used during the TLS handshake. Useful /// Override the SNI/server name used during the TLS handshake. Useful
/// when the dial-target host name does not match the certificate. /// when the dial-target host name does not match the certificate.
pub fn with_server_name_override(mut self, server_name_override: impl Into<String>) -> Self { pub fn with_server_name_override(mut self, server_name_override: impl Into<String>) -> Self {
@@ -121,6 +139,12 @@ impl ClientOptions {
self.ca_file.as_ref() self.ca_file.as_ref()
} }
/// Whether TLS certificate verification is required even without a pinned
/// CA. See [`ClientOptions::with_require_certificate_validation`].
pub fn require_certificate_validation(&self) -> bool {
self.require_certificate_validation
}
/// Optional SNI / server-name override for TLS handshakes. /// Optional SNI / server-name override for TLS handshakes.
pub fn server_name_override(&self) -> Option<&str> { pub fn server_name_override(&self) -> Option<&str> {
self.server_name_override.as_deref() self.server_name_override.as_deref()
@@ -161,6 +185,10 @@ impl fmt::Debug for ClientOptions {
.field("api_key", &self.api_key.as_ref().map(|_| "<redacted>")) .field("api_key", &self.api_key.as_ref().map(|_| "<redacted>"))
.field("plaintext", &self.plaintext) .field("plaintext", &self.plaintext)
.field("ca_file", &self.ca_file) .field("ca_file", &self.ca_file)
.field(
"require_certificate_validation",
&self.require_certificate_validation,
)
.field("server_name_override", &self.server_name_override) .field("server_name_override", &self.server_name_override)
.field("connect_timeout", &self.connect_timeout) .field("connect_timeout", &self.connect_timeout)
.field("call_timeout", &self.call_timeout) .field("call_timeout", &self.call_timeout)
+103
View File
@@ -0,0 +1,103 @@
//! TLS posture coverage for the Rust client.
//!
//! tonic 0.13.1's `ClientTlsConfig` exposes no hook for a custom rustls
//! `ServerCertVerifier` (the verifier is built internally inside the
//! crate-private `TlsConnector`), so the Rust client cannot implement the
//! "accept any server certificate" lenient default the other clients use.
//! Rust is therefore the documented **pin-only exception**: TLS without a
//! pinned CA is rejected up front with a clear, actionable error, and
//! supplying a CA file is the supported path. These tests pin that contract.
use std::time::Duration;
use zb_mom_ww_mxgateway_client::{ClientOptions, Error, GatewayClient};
/// Drive `connect` to its error without requiring `GatewayClient: Debug`
/// (the success arm is dropped explicitly so `unwrap_err` is unnecessary).
async fn connect_err(options: ClientOptions) -> Error {
match GatewayClient::connect(options).await {
Ok(_client) => panic!("connect unexpectedly succeeded against a dead TLS address"),
Err(error) => error,
}
}
#[tokio::test]
async fn tls_without_ca_is_rejected_with_actionable_error_by_default() {
let options = ClientOptions::new("https://127.0.0.1:1")
.with_plaintext(false)
.with_connect_timeout(Duration::from_millis(200));
let error = connect_err(options).await;
let Error::InvalidEndpoint { detail, .. } = error else {
panic!("expected InvalidEndpoint, got {error:?}");
};
// The message must point the caller at the supported remedy (pin a CA)
// and name the opt-in escape hatch.
assert!(
detail.contains("ca_file") || detail.contains("CA"),
"error should instruct the user to pass a CA file: {detail}"
);
assert!(
detail.contains("require_certificate_validation"),
"error should mention the require_certificate_validation opt-in: {detail}"
);
}
#[tokio::test]
async fn tls_with_require_certificate_validation_does_not_short_circuit() {
// With strict verification opted in, the no-CA guard must not fire; the
// connect attempt instead proceeds to the transport (and fails to reach
// the dead address) rather than returning the "CA required" guard error.
let options = ClientOptions::new("https://127.0.0.1:1")
.with_plaintext(false)
.with_require_certificate_validation(true)
.with_connect_timeout(Duration::from_millis(200));
let error = connect_err(options).await;
assert!(
!matches!(&error, Error::InvalidEndpoint { detail, .. }
if detail.contains("require_certificate_validation")),
"strict verification must bypass the no-CA guard, got {error:?}"
);
}
#[tokio::test]
async fn tls_with_ca_file_is_permitted_and_proceeds_past_the_guard() {
// Pinning a CA is the supported TLS path: the no-CA guard must not fire.
// We hand it a readable PEM file; construction proceeds past the guard
// and only fails later at the transport (dead address / handshake).
let ca_path = std::env::temp_dir().join("mxgw-rust-tls-ca-fixture.pem");
std::fs::write(&ca_path, SELF_SIGNED_CA_PEM).unwrap();
let options = ClientOptions::new("https://127.0.0.1:1")
.with_plaintext(false)
.with_ca_file(&ca_path)
.with_connect_timeout(Duration::from_millis(200));
let error = connect_err(options).await;
let _ = std::fs::remove_file(&ca_path);
assert!(
!matches!(&error, Error::InvalidEndpoint { detail, .. }
if detail.contains("require_certificate_validation")),
"pinning a CA must bypass the no-CA guard, got {error:?}"
);
}
/// A throwaway self-signed CA certificate (PEM). Only needs to parse as a
/// PEM trust root so the CA-pinning path is exercised past the guard.
const SELF_SIGNED_CA_PEM: &str = "-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
";
@@ -0,0 +1,156 @@
# Gateway TLS Auto-Certificate and Lenient Client Trust — Design
Date: 2026-06-01
Status: Approved (brainstorming), pending implementation plan
## Problem
The gateway can serve gRPC and the dashboard over TLS, but only if an operator
supplies a certificate via the Kestrel `https://` endpoint config. With no cert,
an `https` endpoint fails at startup with Kestrel's opaque "No server certificate
was specified" error. Both current deployments therefore run plaintext (`h2c`),
exposing the API key and request payloads on the wire.
`mxaccessgw` is an internal tool. The goal is for TLS to "just work" with zero PKI
management: the gateway fabricates its own long-lived certificate when an HTTPS
endpoint is configured without one, and clients accept whatever certificate is
presented unless an operator explicitly opts into pinning.
## Decisions
1. **Gateway = fill-missing-cert-only.** No new "enable TLS" switch. TLS is still
driven by configuring a Kestrel `https://` endpoint. New behavior: when an
HTTPS endpoint has no `Certificate` section, the gateway generates/loads a
persisted self-signed cert instead of failing. Plaintext-only hosts are
untouched — no certificate or key material is ever written for them.
2. **Persist & reuse.** The self-signed cert is saved as a PFX under
`C:\ProgramData\MxGateway\certs`, reused across restarts, regenerated only if
missing, expired, or unreadable. Stable thumbprint; survives restarts; any
CA-pinning client keeps working.
3. **Clients = lenient TLS, plaintext default.** When a client connects over TLS
without a pinned CA, it skips verification (accepts any cert). Pinning a CA file
restores full verification. The per-client connection default (mostly
plaintext/`http`) does not change — TLS is still opt-in via the endpoint scheme.
**Scope boundary:** the gateway↔worker named-pipe IPC is unchanged (local,
OS-secured by the pipe ACL). This work touches only the public gRPC/dashboard
transport and the five language clients.
## Gateway component
New type `SelfSignedCertificateProvider` in
`src/ZB.MOM.WW.MxGateway.Server/Security/Tls/`.
1. **Detect need.** Inspect `Kestrel:Endpoints:*` configuration at startup. If any
endpoint has an `https://` URL and no `Certificate` subsection, a default cert
is needed. If none do, the provider is a no-op (no file written).
2. **Load-or-create.** Look for the persisted PFX. If present, valid, and
unexpired, load it. Otherwise generate and persist.
3. **Generate.** `CertificateRequest` with **ECDSA P-256**, `notBefore = now - 1
day` (clock-skew slack), `notAfter = now + ValidityYears`. SANs: `DNS=localhost`,
`DNS=<MachineName>`, `DNS=<MachineName.FQDN>` when resolvable, plus
`IP=127.0.0.1` and `IP=::1`. Server-auth EKU.
4. **Persist securely.** Write the PFX with an **empty** export password (a random
in-memory password cannot be reused across restarts, which the persist-and-reuse
decision requires); protect the private key with a restrictive ACL (SYSTEM +
Administrators + service account) on the `certs` directory and file on Windows,
and `0600` on non-Windows; atomic write (temp + rename). After generating, the
cert is reloaded from the persisted PFX so Kestrel always serves the on-disk key.
5. **Wire into Kestrel.** In `GatewayApplication.CreateBuilder`, add
`builder.WebHost.ConfigureKestrel(o => o.ConfigureHttpsDefaults(h =>
h.ServerCertificate = cert))`. `ConfigureHttpsDefaults` supplies the cert only
for HTTPS endpoints that did not specify their own, so an operator-configured
`Kestrel:Endpoints:*:Certificate` transparently overrides it. One hook covers
both the gRPC and dashboard ports.
### New config block `MxGateway:Tls`
All optional; the zero-config path needs none of them.
| Option | Default | Purpose |
|---|---|---|
| `Tls:SelfSignedCertPath` | `C:\ProgramData\MxGateway\certs\gateway-selfsigned.pfx` | Where the generated cert lives |
| `Tls:ValidityYears` | `10` | Lifetime of the generated cert |
| `Tls:AdditionalDnsNames` | `[]` | Extra SANs (e.g. a load-balancer name) |
| `Tls:RegenerateIfExpired` | `true` | Auto-replace an expired persisted cert |
Validated by `GatewayOptionsValidator`: `ValidityYears` in 1100,
`SelfSignedCertPath` is a valid path shape when non-blank, and
`AdditionalDnsNames` entries are non-blank. (The "https endpoint exists but cert
path is blank" fail-fast lives in the bootstrap/provider, not the validator,
because the validator only sees the `MxGateway` section, not `Kestrel:Endpoints`.)
**Logging:** on generate/load, log thumbprint + SAN list + `notAfter` at
Information. Never log the PFX password or private key.
## Client lenient-TLS behavior
Uniform rule: **TLS on + no CA pinned ⇒ skip verification; CA pinned ⇒ full
verification.** No transport default changes. Each client also exposes an explicit
switch to force-disable leniency (strict-without-pinning) for the future.
| Client | Mechanism | Effort |
|---|---|---|
| .NET | In `CreateHttpHandler`, when `UseTls` and `CaCertificatePath` empty, set `SslOptions.RemoteCertificateValidationCallback = (_,_,_,_) => true`. CA path keeps existing custom-root validation. | trivial |
| Go | In `buildCredentials`, when TLS and no `CACertFile`/`TLSConfig`, use `tls.Config{InsecureSkipVerify: true, ServerName: override}`. | trivial |
| Java | grpc-netty-shaded 1.76.0 ships `InsecureTrustManagerFactory`. When TLS and no CA, build `GrpcSslContexts.forClient().trustManager(InsecureTrustManagerFactory.INSTANCE)`. | easy |
| Python | grpc-python has no per-channel skip-verify. Fetch the server leaf cert at connect via `ssl.get_server_certificate((host, port))`, pass it as `root_certificates` to `ssl_channel_credentials`, plus `grpc.ssl_target_name_override`. Effectively trusts what is presented (TOFU). | moderate, special-cased |
| Rust | tonic 0.13.1 + rustls (`tls-ring`). Implement a custom `rustls::client::danger::ServerCertVerifier` that accepts everything, build a `rustls::ClientConfig` via `.dangerous().with_custom_certificate_verifier(...)`, feed it to the channel. May require a custom hyper-rustls connector if `ClientTlsConfig` will not take a raw rustls config. **Needs an API spike.** | highest |
### Honesty caveats
- **Python** is not literally "ignore the cert"; it pins whatever the server
presents on first contact via a separate unverified TLS probe. For a self-signed
internal cert this is the intended outcome. Documented as a difference.
- **Rust** leniency depends on the tonic 0.13 TLS surface. If a custom verifier is
disproportionately invasive, the fallback is to require a CA file for Rust TLS
(pin-only) and document Rust as the exception.
## Error handling
Gateway:
- Cert dir not writable / ACL fails ⇒ fail fast at startup with a diagnostic naming
the path and required permission. No silent in-memory fallback.
- Persisted PFX corrupt/unreadable ⇒ warn, regenerate, overwrite.
- Persisted cert expired ⇒ regenerate if `RegenerateIfExpired` (default), else fail
fast instructing the operator to delete it or enable regeneration.
- HTTPS endpoint configured but generation disabled / path empty ⇒ validator
rejects at startup rather than letting Kestrel throw its opaque error.
Clients: surface unchanged. Skip-verify cannot itself raise. Python's pre-fetch
wraps connect failure into the existing connect-error type with the endpoint in the
message. Rust pin-only fallback surfaces the existing CA-file error.
## Documentation (same commit as source, per CLAUDE.md)
- `docs/GatewayConfiguration.md` — extend the TLS section: auto-generation, the
`MxGateway:Tls:*` block, persistence location/ACL, thumbprint logging, operator
override via `Kestrel:Endpoints:*:Certificate`.
- Each client README + `*ClientDesign.md` — "TLS is lenient by default; pin a CA to
verify," with Python TOFU and any Rust caveat noted.
- `docs/DesignDecisions.md` — record both posture choices and the why (internal
tool, no PKI) so they are not mistaken for an oversight.
## Testing
Gateway (`MxGateway.Tests`, no MXAccess):
- `SelfSignedCertificateProvider`: SANs, server-auth EKU, `notAfter ≈ now +
ValidityYears`, ECDSA P-256.
- Load-or-create: valid persisted PFX reused (same thumbprint); expired regenerates
when enabled; corrupt regenerates with a warning.
- Detection: HTTPS-without-cert engages; all-plaintext no-ops and writes no file;
endpoint with its own cert is not overridden.
- `GatewayOptionsValidator`: new `Tls:*` rules.
- Host integration: `Kestrel:Endpoints:Http:Url=https://127.0.0.1:0` builds and
binds (today it throws "no certificate specified").
Clients: each test project gets a lenient-TLS test against a throwaway self-signed
cert — connect with no CA succeeds; pinning a wrong CA fails (proves pinning still
verifies). Python exercises the pre-fetch path; mark opt-in if loopback timing is
flaky. Standard (non-live) tests; no MXAccess or external services.
Cross-language: add a TLS variant note to `docs/CrossLanguageSmokeMatrix.md`;
running the matrix over TLS stays manual/opt-in, consistent with the existing gate.
Per-component verification follows CLAUDE.md's source-update table (build + test
each touched component independently).
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,18 @@
{
"planPath": "docs/plans/2026-06-01-gateway-cert-autogen-implementation.md",
"tasks": [
{"id": 1, "subject": "Task 1: Add TlsOptions config + bind into GatewayOptions", "status": "pending"},
{"id": 2, "subject": "Task 2: Validate MxGateway:Tls in GatewayOptionsValidator", "status": "pending", "blockedBy": [1]},
{"id": 3, "subject": "Task 3: SelfSignedCertificateProvider.GenerateCertificate", "status": "pending", "blockedBy": [1]},
{"id": 4, "subject": "Task 4: SelfSignedCertificateProvider.LoadOrCreate (persist/reuse/regenerate/ACL)", "status": "pending", "blockedBy": [3]},
{"id": 5, "subject": "Task 5: KestrelTlsInspector (detect HTTPS-without-cert)", "status": "pending"},
{"id": 6, "subject": "Task 6: Wire auto-cert into GatewayApplication.CreateBuilder", "status": "pending", "blockedBy": [1, 4, 5]},
{"id": 7, "subject": "Task 7: .NET client lenient TLS by default", "status": "pending"},
{"id": 8, "subject": "Task 8: Go client lenient TLS by default", "status": "pending"},
{"id": 9, "subject": "Task 9: Java client lenient TLS by default", "status": "pending"},
{"id": 10, "subject": "Task 10: Python client lenient TLS via TOFU pre-fetch", "status": "pending"},
{"id": 11, "subject": "Task 11: Rust client lenient TLS via rustls verifier (spike + fallback)", "status": "pending"},
{"id": 12, "subject": "Task 12: Documentation", "status": "pending", "blockedBy": [6, 7, 8, 9, 10, 11]}
],
"lastUpdated": "2026-06-01"
}
@@ -43,4 +43,7 @@ public sealed class GatewayOptions
/// behaviour (alarms disabled). /// behaviour (alarms disabled).
/// </summary> /// </summary>
public AlarmsOptions Alarms { get; init; } = new(); public AlarmsOptions Alarms { get; init; } = new();
/// <summary>Gets self-signed TLS certificate auto-generation options.</summary>
public TlsOptions Tls { get; init; } = new();
} }
@@ -26,6 +26,7 @@ public sealed class GatewayOptionsValidator : IValidateOptions<GatewayOptions>
ValidateDashboard(options.Dashboard, failures); ValidateDashboard(options.Dashboard, failures);
ValidateProtocol(options.Protocol, failures); ValidateProtocol(options.Protocol, failures);
ValidateAlarms(options.Alarms, failures); ValidateAlarms(options.Alarms, failures);
ValidateTls(options.Tls, failures);
return failures.Count == 0 return failures.Count == 0
? ValidateOptionsResult.Success ? ValidateOptionsResult.Success
@@ -262,6 +263,31 @@ public sealed class GatewayOptionsValidator : IValidateOptions<GatewayOptions>
} }
} }
private const int MinimumCertValidityYears = 1;
private const int MaximumCertValidityYears = 100;
private static void ValidateTls(TlsOptions options, List<string> failures)
{
if (options.ValidityYears is < MinimumCertValidityYears or > MaximumCertValidityYears)
{
failures.Add(
$"MxGateway:Tls:ValidityYears must be between {MinimumCertValidityYears} and {MaximumCertValidityYears}.");
}
AddIfInvalidPath(
options.SelfSignedCertPath,
"MxGateway:Tls:SelfSignedCertPath must be a valid filesystem path.",
failures);
foreach (string dns in options.AdditionalDnsNames)
{
if (string.IsNullOrWhiteSpace(dns))
{
failures.Add("MxGateway:Tls:AdditionalDnsNames entries must be non-blank.");
}
}
}
private static void ValidateProtocol(ProtocolOptions options, List<string> failures) private static void ValidateProtocol(ProtocolOptions options, List<string> failures)
{ {
if (options.WorkerProtocolVersion != GatewayContractInfo.WorkerProtocolVersion) if (options.WorkerProtocolVersion != GatewayContractInfo.WorkerProtocolVersion)
@@ -0,0 +1,22 @@
namespace ZB.MOM.WW.MxGateway.Server.Configuration;
/// <summary>
/// Options controlling the gateway's self-signed certificate auto-generation.
/// Only consulted when a Kestrel HTTPS endpoint is configured without its own
/// certificate; plaintext deployments never trigger generation.
/// </summary>
public sealed class TlsOptions
{
/// <summary>Path to the persisted self-signed PFX. Reused across restarts.</summary>
public string SelfSignedCertPath { get; init; } =
@"C:\ProgramData\MxGateway\certs\gateway-selfsigned.pfx";
/// <summary>Lifetime in years of a freshly generated certificate.</summary>
public int ValidityYears { get; init; } = 10;
/// <summary>Extra DNS SANs to embed (e.g. a load-balancer name).</summary>
public IReadOnlyList<string> AdditionalDnsNames { get; init; } = [];
/// <summary>Regenerate the persisted certificate when it has expired.</summary>
public bool RegenerateIfExpired { get; init; } = true;
}
@@ -1,64 +0,0 @@
using ZB.MOM.WW.Telemetry.Serilog;
namespace ZB.MOM.WW.MxGateway.Server.Diagnostics;
/// <summary>
/// Bridges the gateway's <see cref="GatewayLogRedactor"/> policy onto the shared
/// <see cref="ILogRedactor"/> seam consumed by <c>ZB.MOM.WW.Telemetry.Serilog</c>'s redaction
/// enricher. Applied to every Serilog log event before it reaches a sink, it masks the same
/// secrets the original MEL-scope path masked: API-key bearer tokens / client identities
/// (<c>mxgw_*</c>) and command values for credential-bearing MXAccess commands. All masking
/// decisions delegate to <see cref="GatewayLogRedactor"/> — this type adds no new policy.
/// </summary>
public sealed class GatewayLogRedactorAdapter : ILogRedactor
{
/// <summary>Property name carrying a client identity / authorization header value.</summary>
private const string ClientIdentityProperty = "ClientIdentity";
/// <summary>Property name carrying a raw authorization header value.</summary>
private const string AuthorizationProperty = "Authorization";
/// <summary>Property name carrying the MXAccess command method, used to gate value redaction.</summary>
private const string CommandMethodProperty = "CommandMethod";
/// <summary>Property name carrying a command payload value that may bear credentials.</summary>
private const string CommandValueProperty = "CommandValue";
/// <summary>
/// Masks any sensitive values in <paramref name="properties"/> in place using the shared
/// <see cref="GatewayLogRedactor"/> policy. Identity/authorization properties have their API-key
/// secret stripped; a command value is redacted when its associated command method bears
/// credentials.
/// </summary>
/// <param name="properties">The mutable log-event property dictionary for the current event.</param>
public void Redact(IDictionary<string, object?> properties)
{
ArgumentNullException.ThrowIfNull(properties);
RedactIdentity(properties, ClientIdentityProperty);
RedactIdentity(properties, AuthorizationProperty);
RedactCommandValue(properties);
}
private static void RedactIdentity(IDictionary<string, object?> properties, string propertyName)
{
if (properties.TryGetValue(propertyName, out object? value) && value is string identity)
{
properties[propertyName] = GatewayLogRedactor.RedactClientIdentity(identity);
}
}
private static void RedactCommandValue(IDictionary<string, object?> properties)
{
if (!properties.TryGetValue(CommandValueProperty, out object? value) || value is null)
{
return;
}
string? commandMethod = properties.TryGetValue(CommandMethodProperty, out object? method)
? method as string
: null;
properties[CommandValueProperty] = GatewayLogRedactor.RedactCommandValue(commandMethod, value);
}
}
@@ -0,0 +1,20 @@
using Microsoft.Extensions.Logging;
namespace ZB.MOM.WW.MxGateway.Server.Diagnostics;
public static class GatewayLoggerExtensions
{
/// <summary>Begins a gateway log scope with the specified scope properties.</summary>
/// <param name="logger">Logger used for diagnostic output.</param>
/// <param name="scope">Scope properties to apply.</param>
/// <returns>A disposable that ends the scope when disposed.</returns>
public static IDisposable? BeginGatewayScope(
this ILogger logger,
GatewayLogScope scope)
{
ArgumentNullException.ThrowIfNull(logger);
ArgumentNullException.ThrowIfNull(scope);
return logger.BeginScope(scope.ToDictionary());
}
}
@@ -1,5 +1,4 @@
using Microsoft.Extensions.Primitives; using Microsoft.Extensions.Primitives;
using Serilog.Context;
namespace ZB.MOM.WW.MxGateway.Server.Diagnostics; namespace ZB.MOM.WW.MxGateway.Server.Diagnostics;
@@ -18,12 +17,7 @@ public static class GatewayRequestLoggingMiddlewareExtensions
/// <summary>Header name for the command method name.</summary> /// <summary>Header name for the command method name.</summary>
public const string CommandMethodHeaderName = "x-command-method"; public const string CommandMethodHeaderName = "x-command-method";
/// <summary> /// <summary>Adds gateway request logging scope middleware that reads correlation headers and redacts sensitive data.</summary>
/// Adds gateway request logging middleware that reads the correlation headers and pushes them
/// as Serilog <see cref="LogContext"/> properties for the duration of the request. The pushed
/// properties (SessionId / WorkerProcessId / CorrelationId / CommandMethod / ClientIdentity)
/// are disposed when the request completes; the shared redaction enricher masks any secrets.
/// </summary>
/// <param name="app">Application builder.</param> /// <param name="app">Application builder.</param>
public static IApplicationBuilder UseGatewayRequestLoggingScope(this IApplicationBuilder app) public static IApplicationBuilder UseGatewayRequestLoggingScope(this IApplicationBuilder app)
{ {
@@ -31,56 +25,21 @@ public static class GatewayRequestLoggingMiddlewareExtensions
return app.Use(async (context, next) => return app.Use(async (context, next) =>
{ {
GatewayLogScope scope = new( ILogger logger = context.RequestServices
.GetRequiredService<ILoggerFactory>()
.CreateLogger("MxGateway.Request");
using IDisposable? scope = logger.BeginGatewayScope(new GatewayLogScope(
SessionId: ReadHeader(context, SessionIdHeaderName), SessionId: ReadHeader(context, SessionIdHeaderName),
WorkerProcessId: ReadInt32Header(context, WorkerProcessIdHeaderName), WorkerProcessId: ReadInt32Header(context, WorkerProcessIdHeaderName),
CorrelationId: ReadUInt64Header(context, CorrelationIdHeaderName), CorrelationId: ReadUInt64Header(context, CorrelationIdHeaderName),
CommandMethod: ReadHeader(context, CommandMethodHeaderName), CommandMethod: ReadHeader(context, CommandMethodHeaderName),
ClientIdentity: ReadHeader(context, "authorization")); ClientIdentity: ReadHeader(context, "authorization")));
using IDisposable correlationScope = PushCorrelationProperties(scope);
await next(context); await next(context);
}); });
} }
/// <summary>
/// Pushes the populated <paramref name="scope"/> properties onto the Serilog
/// <see cref="LogContext"/>, returning a single disposable that pops them all when the request
/// completes. Only the properties present in <see cref="GatewayLogScope.ToDictionary"/> (which
/// already applies the client-identity redaction policy) are pushed.
/// </summary>
/// <param name="scope">The correlation properties for the current request.</param>
/// <returns>A disposable that removes the pushed properties on disposal.</returns>
private static IDisposable PushCorrelationProperties(GatewayLogScope scope)
{
Stack<IDisposable> pushed = new();
foreach (KeyValuePair<string, object?> property in scope.ToDictionary())
{
pushed.Push(LogContext.PushProperty(property.Key, property.Value));
}
return new CorrelationPropertyScope(pushed);
}
/// <summary>
/// Disposes the pushed <see cref="LogContext"/> property bindings in reverse order, restoring
/// the ambient context to its pre-request state.
/// </summary>
private sealed class CorrelationPropertyScope(Stack<IDisposable> bindings) : IDisposable
{
private readonly Stack<IDisposable> _bindings = bindings;
public void Dispose()
{
while (_bindings.Count > 0)
{
_bindings.Pop().Dispose();
}
}
}
private static string? ReadHeader(HttpContext context, string headerName) private static string? ReadHeader(HttpContext context, string headerName)
{ {
return context.Request.Headers.TryGetValue(headerName, out StringValues values) return context.Request.Headers.TryGetValue(headerName, out StringValues values)
@@ -1,5 +1,4 @@
using Microsoft.AspNetCore.Hosting.StaticWebAssets; using Microsoft.AspNetCore.Hosting.StaticWebAssets;
using Serilog;
using ZB.MOM.WW.MxGateway.Contracts; using ZB.MOM.WW.MxGateway.Contracts;
using ZB.MOM.WW.MxGateway.Server.Alarms; using ZB.MOM.WW.MxGateway.Server.Alarms;
using ZB.MOM.WW.MxGateway.Server.Configuration; using ZB.MOM.WW.MxGateway.Server.Configuration;
@@ -12,7 +11,6 @@ using ZB.MOM.WW.MxGateway.Server.Security.Authentication;
using ZB.MOM.WW.MxGateway.Server.Security.Authorization; using ZB.MOM.WW.MxGateway.Server.Security.Authorization;
using ZB.MOM.WW.MxGateway.Server.Sessions; using ZB.MOM.WW.MxGateway.Server.Sessions;
using ZB.MOM.WW.MxGateway.Server.Workers; using ZB.MOM.WW.MxGateway.Server.Workers;
using ZB.MOM.WW.Telemetry.Serilog;
namespace ZB.MOM.WW.MxGateway.Server; namespace ZB.MOM.WW.MxGateway.Server;
@@ -33,10 +31,7 @@ public static class GatewayApplication
WebApplicationBuilder builder = CreateBuilder(args); WebApplicationBuilder builder = CreateBuilder(args);
WebApplication app = builder.Build(); WebApplication app = builder.Build();
// Push the per-request correlation properties (via Serilog LogContext) before the
// request-logging middleware emits its completion event, so those properties appear on it.
app.UseGatewayRequestLoggingScope(); app.UseGatewayRequestLoggingScope();
app.UseSerilogRequestLogging();
app.UseStaticFiles(); app.UseStaticFiles();
app.UseAuthentication(); app.UseAuthentication();
app.UseAuthorization(); app.UseAuthorization();
@@ -60,8 +55,6 @@ public static class GatewayApplication
}); });
StaticWebAssetsLoader.UseStaticWebAssets(builder.Environment, builder.Configuration); StaticWebAssetsLoader.UseStaticWebAssets(builder.Environment, builder.Configuration);
ConfigureSerilog(builder);
builder.Services.AddGatewayConfiguration(); builder.Services.AddGatewayConfiguration();
builder.Services.AddSqliteAuthStore(); builder.Services.AddSqliteAuthStore();
builder.Services.AddGatewayGrpcAuthorization(); builder.Services.AddGatewayGrpcAuthorization();
@@ -79,30 +72,6 @@ public static class GatewayApplication
return builder; return builder;
} }
/// <summary>
/// Replaces the default Microsoft.Extensions.Logging provider with the shared
/// <c>ZB.MOM.WW.Telemetry.Serilog</c> bootstrap (<see cref="ZbSerilogExtensions.AddZbSerilog"/>).
/// Sinks and minimum level come from the <c>Serilog</c> configuration section; identity
/// (<c>SiteId</c>/<c>NodeRole</c>) is read from <c>MxGateway:Telemetry</c> when present.
/// Also registers the project's <see cref="ILogRedactor"/> adapter so the shared redaction
/// enricher masks gateway secrets on every event.
/// </summary>
/// <param name="builder">The web application builder being configured.</param>
private static void ConfigureSerilog(WebApplicationBuilder builder)
{
string? siteId = builder.Configuration["MxGateway:Telemetry:SiteId"];
string? nodeRole = builder.Configuration["MxGateway:Telemetry:NodeRole"];
builder.Services.AddSingleton<ILogRedactor, GatewayLogRedactorAdapter>();
builder.AddZbSerilog(options =>
{
options.ServiceName = "mxgateway";
options.SiteId = string.IsNullOrWhiteSpace(siteId) ? null : siteId;
options.NodeRole = string.IsNullOrWhiteSpace(nodeRole) ? null : nodeRole;
});
}
private static string ResolveContentRootPath() private static string ResolveContentRootPath()
{ {
string? configuredContentRootPath = Environment.GetEnvironmentVariable("ASPNETCORE_CONTENTROOT"); string? configuredContentRootPath = Environment.GetEnvironmentVariable("ASPNETCORE_CONTENTROOT");
@@ -0,0 +1,45 @@
using Microsoft.Extensions.Configuration;
namespace ZB.MOM.WW.MxGateway.Server.Security.Tls;
/// <summary>
/// Inspects the Kestrel configuration to decide whether the gateway must supply
/// a generated default certificate (an HTTPS endpoint exists with no certificate
/// of its own).
/// </summary>
public static class KestrelTlsInspector
{
/// <summary>
/// Returns <see langword="true"/> when at least one HTTPS endpoint in
/// <c>Kestrel:Endpoints</c> has no certificate of its own (no
/// <c>Certificate:Path</c>, <c>Certificate:Subject</c>, or
/// <c>Certificate:Thumbprint</c>), meaning the gateway must supply a
/// generated fallback certificate.
/// </summary>
public static bool RequiresGeneratedCertificate(IConfiguration configuration)
{
IConfigurationSection endpoints = configuration.GetSection("Kestrel:Endpoints");
foreach (IConfigurationSection endpoint in endpoints.GetChildren())
{
string? url = endpoint["Url"];
if (string.IsNullOrWhiteSpace(url) ||
!url.StartsWith("https://", StringComparison.OrdinalIgnoreCase))
{
continue;
}
IConfigurationSection certificate = endpoint.GetSection("Certificate");
bool hasOwnCertificate =
!string.IsNullOrWhiteSpace(certificate["Path"]) ||
!string.IsNullOrWhiteSpace(certificate["Subject"]) ||
!string.IsNullOrWhiteSpace(certificate["Thumbprint"]);
if (!hasOwnCertificate)
{
return true;
}
}
return false;
}
}
@@ -0,0 +1,71 @@
using System.Net;
using System.Security.Cryptography;
using System.Security.Cryptography.X509Certificates;
using Microsoft.Extensions.Logging;
using ZB.MOM.WW.MxGateway.Server.Configuration;
namespace ZB.MOM.WW.MxGateway.Server.Security.Tls;
/// <summary>
/// Generates and persists a long-lived self-signed certificate used as the
/// Kestrel HTTPS default when no operator certificate is configured.
/// </summary>
public sealed class SelfSignedCertificateProvider
{
private const string ServerAuthOid = "1.3.6.1.5.5.7.3.1";
private readonly TlsOptions _options;
private readonly ILogger<SelfSignedCertificateProvider> _logger;
private readonly TimeProvider _timeProvider;
public SelfSignedCertificateProvider(
TlsOptions options,
ILogger<SelfSignedCertificateProvider> logger,
TimeProvider timeProvider)
{
_options = options;
_logger = logger;
_timeProvider = timeProvider;
}
/// <summary>Creates a fresh in-memory ECDSA P-256 self-signed certificate.</summary>
public X509Certificate2 GenerateCertificate()
{
using ECDsa key = ECDsa.Create(ECCurve.NamedCurves.nistP256);
CertificateRequest request = new(
new X500DistinguishedName("CN=MxAccessGateway Self-Signed"),
key,
HashAlgorithmName.SHA256);
request.CertificateExtensions.Add(new X509BasicConstraintsExtension(false, false, 0, true));
request.CertificateExtensions.Add(new X509KeyUsageExtension(
X509KeyUsageFlags.DigitalSignature | X509KeyUsageFlags.KeyEncipherment,
critical: true));
request.CertificateExtensions.Add(new X509EnhancedKeyUsageExtension(
[new Oid(ServerAuthOid, "Server Authentication")],
critical: false));
SubjectAlternativeNameBuilder san = new();
san.AddDnsName("localhost");
string machine = Environment.MachineName;
if (!string.IsNullOrWhiteSpace(machine))
{
san.AddDnsName(machine);
}
foreach (string extra in _options.AdditionalDnsNames)
{
if (!string.IsNullOrWhiteSpace(extra))
{
san.AddDnsName(extra);
}
}
san.AddIpAddress(IPAddress.Loopback);
san.AddIpAddress(IPAddress.IPv6Loopback);
request.CertificateExtensions.Add(san.Build());
DateTimeOffset now = _timeProvider.GetUtcNow();
return request.CreateSelfSigned(now.AddDays(-1), now.AddYears(_options.ValidityYears));
}
}
@@ -15,13 +15,6 @@
<ItemGroup> <ItemGroup>
<ProjectReference Include="..\ZB.MOM.WW.MxGateway.Contracts\ZB.MOM.WW.MxGateway.Contracts.csproj" /> <ProjectReference Include="..\ZB.MOM.WW.MxGateway.Contracts\ZB.MOM.WW.MxGateway.Contracts.csproj" />
<!--
Shared structured-logging bootstrap (ZB.MOM.WW.Telemetry.Serilog) lives in the sibling
scadaproj workspace. Cross-repo ProjectReference: the referenced project resolves its own
Directory.Build.props / Directory.Packages.props from its own tree, so it does not perturb
this repo's build settings. It transitively brings the ZB.MOM.WW.Telemetry core package.
-->
<ProjectReference Include="..\..\..\scadaproj\ZB.MOM.WW.Telemetry\src\ZB.MOM.WW.Telemetry.Serilog\ZB.MOM.WW.Telemetry.Serilog.csproj" />
</ItemGroup> </ItemGroup>
</Project> </Project>
@@ -1,10 +1,8 @@
{ {
"Serilog": { "Logging": {
"MinimumLevel": { "LogLevel": {
"Default": "Information", "Default": "Information",
"Override": { "Microsoft.AspNetCore": "Warning"
"Microsoft.AspNetCore": "Warning"
}
} }
} }
} }
@@ -1,30 +1,9 @@
{ {
"Serilog": { "Logging": {
"Using": [ "LogLevel": {
"Serilog.Sinks.Console",
"Serilog.Sinks.File"
],
"MinimumLevel": {
"Default": "Information", "Default": "Information",
"Override": { "Microsoft.AspNetCore": "Warning"
"Microsoft.AspNetCore": "Warning" }
}
},
"WriteTo": [
{
"Name": "Console",
"Args": {
"outputTemplate": "[{Timestamp:HH:mm:ss} {Level:u3}] [{NodeRole}/{NodeHostname}] {Message:lj} {Properties:j}{NewLine}{Exception}"
}
},
{
"Name": "File",
"Args": {
"path": "logs/mxgateway-.log",
"rollingInterval": "Day"
}
}
]
}, },
"AllowedHosts": "*", "AllowedHosts": "*",
"MxGateway": { "MxGateway": {
@@ -0,0 +1,59 @@
using Microsoft.Extensions.Options;
using ZB.MOM.WW.MxGateway.Server.Configuration;
namespace ZB.MOM.WW.MxGateway.Tests.Configuration;
public sealed class GatewayOptionsValidatorTests
{
// Constructs the minimal valid GatewayOptions by relying on each sub-option's
// design-default values; those defaults are validated separately in GatewayOptionsTests.
private static GatewayOptions ValidOptions() => new();
private static GatewayOptions CloneWithTls(GatewayOptions source, TlsOptions tls)
=> new()
{
Authentication = source.Authentication,
Ldap = source.Ldap,
Worker = source.Worker,
Sessions = source.Sessions,
Events = source.Events,
Dashboard = source.Dashboard,
Protocol = source.Protocol,
Alarms = source.Alarms,
Tls = tls,
};
[Fact]
public void Validate_Succeeds_WithDefaultTlsOptions()
{
ValidateOptionsResult result = new GatewayOptionsValidator().Validate(null, ValidOptions());
Assert.True(result.Succeeded);
}
[Fact]
public void Validate_Fails_WhenTlsValidityYearsOutOfRange()
{
GatewayOptions withBadTls = CloneWithTls(ValidOptions(), new TlsOptions { ValidityYears = 0 });
ValidateOptionsResult result = new GatewayOptionsValidator().Validate(null, withBadTls);
Assert.True(result.Failed);
Assert.Contains(result.Failures!, f => f.Contains("MxGateway:Tls:ValidityYears"));
}
[Fact]
public void Validate_Fails_WhenTlsValidityYearsTooLarge()
{
GatewayOptions withBadTls = CloneWithTls(ValidOptions(), new TlsOptions { ValidityYears = 101 });
ValidateOptionsResult result = new GatewayOptionsValidator().Validate(null, withBadTls);
Assert.True(result.Failed);
Assert.Contains(result.Failures!, f => f.Contains("MxGateway:Tls:ValidityYears"));
}
[Fact]
public void Validate_Fails_WhenAdditionalDnsNameBlank()
{
GatewayOptions options = CloneWithTls(ValidOptions(), new TlsOptions { AdditionalDnsNames = [" "] });
ValidateOptionsResult result = new GatewayOptionsValidator().Validate(null, options);
Assert.True(result.Failed);
Assert.Contains(result.Failures!, f => f.Contains("MxGateway:Tls:AdditionalDnsNames"));
}
}
@@ -0,0 +1,39 @@
using Microsoft.Extensions.Configuration;
using ZB.MOM.WW.MxGateway.Server.Configuration;
using Xunit;
namespace ZB.MOM.WW.MxGateway.Tests.Configuration;
public sealed class TlsOptionsBindingTests
{
[Fact]
public void Defaults_AreApplied_WhenSectionAbsent()
{
TlsOptions options = new();
Assert.Equal(10, options.ValidityYears);
Assert.True(options.RegenerateIfExpired);
Assert.Empty(options.AdditionalDnsNames);
Assert.False(string.IsNullOrWhiteSpace(options.SelfSignedCertPath));
}
[Fact]
public void Binds_FromMxGatewayTlsSection()
{
IConfiguration config = new ConfigurationBuilder()
.AddInMemoryCollection(new Dictionary<string, string?>
{
["MxGateway:Tls:ValidityYears"] = "5",
["MxGateway:Tls:SelfSignedCertPath"] = @"C:\tmp\gw.pfx",
["MxGateway:Tls:RegenerateIfExpired"] = "false",
["MxGateway:Tls:AdditionalDnsNames:0"] = "gw.internal",
})
.Build();
GatewayOptions options = config.GetSection(GatewayOptions.SectionName).Get<GatewayOptions>()!;
Assert.Equal(5, options.Tls.ValidityYears);
Assert.Equal(@"C:\tmp\gw.pfx", options.Tls.SelfSignedCertPath);
Assert.False(options.Tls.RegenerateIfExpired);
Assert.Equal("gw.internal", Assert.Single(options.Tls.AdditionalDnsNames));
}
}
@@ -1,92 +0,0 @@
using ZB.MOM.WW.MxGateway.Server.Diagnostics;
using ZB.MOM.WW.Telemetry.Serilog;
namespace ZB.MOM.WW.MxGateway.Tests.Diagnostics;
/// <summary>
/// Pins that <see cref="GatewayLogRedactorAdapter"/> applies the gateway's redaction policy through
/// the shared <see cref="ILogRedactor"/> seam — the same secrets the former MEL-scope path masked
/// must still be masked once events flow through the Serilog redaction enricher.
/// </summary>
public sealed class GatewayLogRedactorAdapterTests
{
private readonly ILogRedactor _redactor = new GatewayLogRedactorAdapter();
/// <summary>Verifies the client identity property has its API-key secret stripped in place.</summary>
[Fact]
public void Redact_StripsApiKeySecretFromClientIdentity()
{
Dictionary<string, object?> properties = new()
{
["ClientIdentity"] = "Bearer mxgw_operator01_super-secret",
};
_redactor.Redact(properties);
Assert.Equal("Bearer mxgw_operator01_[redacted]", properties["ClientIdentity"]);
Assert.DoesNotContain("super-secret", (string?)properties["ClientIdentity"]);
}
/// <summary>Verifies a raw authorization header property is redacted too.</summary>
[Fact]
public void Redact_StripsApiKeySecretFromAuthorizationProperty()
{
Dictionary<string, object?> properties = new()
{
["Authorization"] = "Bearer mxgw_admin_top-secret",
};
_redactor.Redact(properties);
Assert.Equal("Bearer mxgw_admin_[redacted]", properties["Authorization"]);
}
/// <summary>Verifies a command value is redacted for a credential-bearing command method.</summary>
[Fact]
public void Redact_RedactsCommandValueForCredentialBearingCommand()
{
Dictionary<string, object?> properties = new()
{
["CommandMethod"] = "WriteSecured",
["CommandValue"] = "credential-bearing-value",
};
_redactor.Redact(properties);
Assert.Equal(GatewayLogRedactor.RedactedValue, properties["CommandValue"]);
}
/// <summary>Verifies a command value is redacted by default (value logging disabled) for any command.</summary>
[Fact]
public void Redact_RedactsCommandValueByDefault()
{
Dictionary<string, object?> properties = new()
{
["CommandMethod"] = "Write",
["CommandValue"] = "plaintext-tag-value",
};
_redactor.Redact(properties);
Assert.Equal(GatewayLogRedactor.RedactedValue, properties["CommandValue"]);
}
/// <summary>Verifies non-sensitive properties are left untouched.</summary>
[Fact]
public void Redact_LeavesNonSensitivePropertiesUnchanged()
{
Dictionary<string, object?> properties = new()
{
["SessionId"] = "session-1",
["CorrelationId"] = (ulong)99,
["ClientIdentity"] = "Bearer plain-token-no-marker",
};
_redactor.Redact(properties);
Assert.Equal("session-1", properties["SessionId"]);
Assert.Equal((ulong)99, properties["CorrelationId"]);
// No mxgw_ marker — identity passes through unchanged.
Assert.Equal("Bearer plain-token-no-marker", properties["ClientIdentity"]);
}
}
@@ -0,0 +1,61 @@
using Microsoft.Extensions.Configuration;
using ZB.MOM.WW.MxGateway.Server.Security.Tls;
using Xunit;
namespace ZB.MOM.WW.MxGateway.Tests.Security.Tls;
public sealed class KestrelTlsInspectorTests
{
private static IConfiguration Config(params (string Key, string Value)[] entries)
=> new ConfigurationBuilder()
.AddInMemoryCollection(entries.ToDictionary(e => e.Key, e => (string?)e.Value))
.Build();
[Fact]
public void RequiresGeneratedCertificate_True_WhenHttpsEndpointHasNoCertificate()
=> Assert.True(KestrelTlsInspector.RequiresGeneratedCertificate(
Config(("Kestrel:Endpoints:Http:Url", "https://0.0.0.0:5120"))));
[Fact]
public void RequiresGeneratedCertificate_False_WhenAllEndpointsPlaintext()
=> Assert.False(KestrelTlsInspector.RequiresGeneratedCertificate(
Config(("Kestrel:Endpoints:Http:Url", "http://0.0.0.0:5120"))));
[Fact]
public void RequiresGeneratedCertificate_False_WhenHttpsEndpointHasOwnCertificate()
=> Assert.False(KestrelTlsInspector.RequiresGeneratedCertificate(
Config(
("Kestrel:Endpoints:Http:Url", "https://0.0.0.0:5120"),
("Kestrel:Endpoints:Http:Certificate:Path", @"C:\certs\real.pfx"))));
[Fact]
public void RequiresGeneratedCertificate_False_WhenNoEndpointsConfigured()
=> Assert.False(KestrelTlsInspector.RequiresGeneratedCertificate(Config()));
[Fact]
public void RequiresGeneratedCertificate_False_WhenHttpsEndpointHasThumbprintOnly()
=> Assert.False(KestrelTlsInspector.RequiresGeneratedCertificate(
Config(
("Kestrel:Endpoints:Https:Url", "https://0.0.0.0:5120"),
("Kestrel:Endpoints:Https:Certificate:Thumbprint", "AABBCCDDEEFF00112233445566778899AABBCCDD"))));
[Fact]
public void RequiresGeneratedCertificate_False_WhenHttpsEndpointHasSubjectOnly()
=> Assert.False(KestrelTlsInspector.RequiresGeneratedCertificate(
Config(
("Kestrel:Endpoints:Https:Url", "https://0.0.0.0:5120"),
("Kestrel:Endpoints:Https:Certificate:Subject", "CN=myserver"))));
[Fact]
public void RequiresGeneratedCertificate_True_WhenHttpsUrlIsUppercase()
=> Assert.True(KestrelTlsInspector.RequiresGeneratedCertificate(
Config(("Kestrel:Endpoints:Https:Url", "HTTPS://0.0.0.0:5120"))));
[Fact]
public void RequiresGeneratedCertificate_True_WhenMixedEndpointsAndOneHttpsHasNoCert()
=> Assert.True(KestrelTlsInspector.RequiresGeneratedCertificate(
Config(
("Kestrel:Endpoints:Grpc:Url", "https://0.0.0.0:5120"),
("Kestrel:Endpoints:Grpc:Certificate:Thumbprint", "AABBCCDDEEFF00112233445566778899AABBCCDD"),
("Kestrel:Endpoints:Dashboard:Url", "https://0.0.0.0:5130"))));
}
@@ -0,0 +1,40 @@
using System.Security.Cryptography.X509Certificates;
using Microsoft.Extensions.Logging.Abstractions;
using Microsoft.Extensions.Time.Testing;
using ZB.MOM.WW.MxGateway.Server.Configuration;
using ZB.MOM.WW.MxGateway.Server.Security.Tls;
using Xunit;
namespace ZB.MOM.WW.MxGateway.Tests.Security.Tls;
public sealed class SelfSignedCertificateProviderTests
{
private static SelfSignedCertificateProvider CreateProvider(TlsOptions options, FakeTimeProvider time)
=> new(options, NullLogger<SelfSignedCertificateProvider>.Instance, time);
[Fact]
public void GenerateCertificate_HasExpectedSansEkuAndValidity()
{
FakeTimeProvider time = new(new DateTimeOffset(2026, 1, 1, 0, 0, 0, TimeSpan.Zero));
TlsOptions options = new() { ValidityYears = 7, AdditionalDnsNames = ["gw.internal"] };
using X509Certificate2 cert = CreateProvider(options, time).GenerateCertificate();
Assert.Equal(time.GetUtcNow().AddYears(7).UtcDateTime.Date, cert.NotAfter.ToUniversalTime().Date);
Assert.True(cert.NotBefore.ToUniversalTime() < time.GetUtcNow().UtcDateTime);
Assert.True(cert.HasPrivateKey);
string sans = ReadSubjectAltNames(cert);
Assert.Contains("localhost", sans);
Assert.Contains("gw.internal", sans);
X509EnhancedKeyUsageExtension eku = cert.Extensions.OfType<X509EnhancedKeyUsageExtension>().Single();
Assert.Contains(eku.EnhancedKeyUsages.Cast<System.Security.Cryptography.Oid>(),
o => o.Value == "1.3.6.1.5.5.7.3.1"); // serverAuth
}
private static string ReadSubjectAltNames(X509Certificate2 cert)
=> cert.Extensions
.First(e => e.Oid?.Value == "2.5.29.17")
.Format(false);
}
@@ -7,6 +7,7 @@
<ItemGroup> <ItemGroup>
<PackageReference Include="coverlet.collector" Version="6.0.4" /> <PackageReference Include="coverlet.collector" Version="6.0.4" />
<PackageReference Include="Microsoft.Extensions.TimeProvider.Testing" Version="10.0.0" />
<PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.14.1" /> <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.14.1" />
<PackageReference Include="xunit" Version="2.9.3" /> <PackageReference Include="xunit" Version="2.9.3" />
<PackageReference Include="xunit.runner.visualstudio" Version="3.1.4" /> <PackageReference Include="xunit.runner.visualstudio" Version="3.1.4" />