feat(mesh): node-side PSK interceptor

2026-08-06 03:37:02 -04:00
parent f8325373ef
commit fbda015c6e
3 changed files with 407 additions and 0 deletions
@@ -0,0 +1,227 @@
+using Grpc.Core;
+using Microsoft.Extensions.Logging.Abstractions;
+using Microsoft.Extensions.Options;
+using Shouldly;
+using Xunit;
+using ZB.MOM.WW.OtOpcUa.Cluster;
+using ZB.MOM.WW.OtOpcUa.Host.Configuration;
+
+namespace ZB.MOM.WW.OtOpcUa.Host.Tests.Configuration;
+
+/// <summary>
+///     ClusterClient→gRPC Phase 0 — the node-side command endpoint's inbound gate. Mapping
+///     <c>NodeCommandService</c> onto the pipeline is a Phase 1 task; this test covers only the
+///     interceptor's own authorization behavior.
+/// </summary>
+/// <remarks>
+///     Same contract as <see cref="TelemetryStreamAuthInterceptor"/>, scoped to
+///     <c>/mesh_transport.v1.NodeCommandService/</c> — fail-closed on an unconfigured key,
+///     constant-time comparison, gated on every handler shape so scoping holds regardless of RPC
+///     shape. Deliberately NO <c>x-otopcua-cluster</c> requirement: that header is a central-side
+///     routing hint, and requiring it here would gate on a value the caller chooses.
+/// </remarks>
+public sealed class MeshCommandAuthInterceptorTests
+{
+    private const string ExecuteMethod = "/mesh_transport.v1.NodeCommandService/Execute";
+    private const string OtherMethod = "/telemetry.v1.TelemetryStreamService/Subscribe";
+
+    private static MeshCommandAuthInterceptor CreateInterceptor(string? psk)
+        => new(
+            Options.Create(new MeshTransportOptions { GrpcPsk = psk }),
+            NullLogger<MeshCommandAuthInterceptor>.Instance);
+
+    private static ServerCallContext CreateContext(string method, string? authorizationHeader)
+    {
+        var headers = new Metadata();
+        if (authorizationHeader is not null)
+            headers.Add("authorization", authorizationHeader);
+
+        return new FakeServerCallContext(method, headers);
+    }
+
+    /// <summary>Invokes the interceptor's unary path (how <c>Execute</c> actually runs).</summary>
+    private static Task Invoke(MeshCommandAuthInterceptor interceptor, ServerCallContext context)
+        => interceptor.UnaryServerHandler<string, string>(
+            "request", context, (_, _) => Task.FromResult("ok"));
+
+    [Fact]
+    public async Task NonMeshCommandMethod_PassesThrough_EvenWithNoPskConfigured()
+    {
+        // The interceptor shares the AddGrpc pipeline with the sync / config-serve / telemetry
+        // services, so it sees every call. It must be scoped strictly to the node command service.
+        var interceptor = CreateInterceptor(psk: null);
+        var context = CreateContext(OtherMethod, authorizationHeader: null);
+
+        await Invoke(interceptor, context); // no throw
+    }
+
+    [Fact]
+    public async Task ExecuteMethod_WithNoPskConfigured_IsDenied_EvenWithABearerToken()
+    {
+        // Fail-closed. "No PSK configured" is the DEFAULT — treating it as "no auth required" would
+        // let anything that can reach the port drive RestartDriver / AlarmCommand / deployment
+        // dispatch on this node. A token must not help.
+        var interceptor = CreateInterceptor(psk: null);
+        var context = CreateContext(ExecuteMethod, "Bearer anything-at-all");
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task ExecuteMethod_WithBlankPskConfigured_IsDenied()
+    {
+        // Blank is distinct from unset in the options (GrpcPsk is nullable on purpose) but must be
+        // treated identically here: an empty expected token would be satisfied by an empty bearer.
+        var interceptor = CreateInterceptor("   ");
+        var context = CreateContext(ExecuteMethod, "Bearer    ");
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task ExecuteMethod_WithNoBearerToken_IsDenied()
+    {
+        var interceptor = CreateInterceptor("the-cluster-psk");
+        var context = CreateContext(ExecuteMethod, authorizationHeader: null);
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task ExecuteMethod_WithMalformedAuthorizationHeader_IsDenied()
+    {
+        // No "Bearer " prefix at all — must be treated the same as a missing header.
+        var interceptor = CreateInterceptor("the-cluster-psk");
+        var context = CreateContext(ExecuteMethod, "the-cluster-psk");
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task ExecuteMethod_WithWrongBearerToken_IsDenied()
+    {
+        // This is also the isolation proof: a node holding SITE-A's PSK rejects a caller presenting
+        // SITE-B's. Nothing about the cluster id is consulted — only whether the key matches.
+        var interceptor = CreateInterceptor("dev-mesh-psk-SITE-A");
+        var context = CreateContext(ExecuteMethod, "Bearer dev-mesh-psk-SITE-B");
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task ExecuteMethod_WithCorrectBearerToken_PassesThrough()
+    {
+        var interceptor = CreateInterceptor("the-cluster-psk");
+        var context = CreateContext(ExecuteMethod, "Bearer the-cluster-psk");
+
+        await Invoke(interceptor, context); // no throw
+    }
+
+    [Fact]
+    public async Task ExecuteMethod_WithCorrectBearerToken_AndNoClusterHeader_PassesThrough()
+    {
+        // x-otopcua-cluster is a central-side routing hint. Requiring it here would gate on a value
+        // the caller supplies about itself, which proves nothing the PSK has not already proven.
+        var interceptor = CreateInterceptor("the-cluster-psk");
+        var context = CreateContext(ExecuteMethod, "Bearer the-cluster-psk");
+
+        await Invoke(interceptor, context); // no throw
+    }
+
+    [Fact]
+    public async Task ExecuteMethod_TokenComparison_IsNotAPrefixMatch()
+    {
+        // A prefix/StartsWith comparison would accept a truncated key and make the secret
+        // recoverable one character at a time.
+        var interceptor = CreateInterceptor("the-cluster-psk");
+        var context = CreateContext(ExecuteMethod, "Bearer the-cluster-ps");
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task ServerStreamingPath_IsAlsoGated()
+    {
+        // Execute is unary today, but gating only that path would leave any future streaming method
+        // on the same service open. Gate every handler shape.
+        var interceptor = CreateInterceptor("the-cluster-psk");
+        var context = CreateContext(ExecuteMethod, "Bearer the-wrong-psk");
+
+        var ex = await Should.ThrowAsync<RpcException>(() =>
+            interceptor.ServerStreamingServerHandler<string, string>(
+                "request", responseStream: null!, context, (_, _, _) => Task.CompletedTask));
+
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task ClientStreamingPath_IsAlsoGated()
+    {
+        var interceptor = CreateInterceptor("the-cluster-psk");
+        var context = CreateContext(ExecuteMethod, "Bearer the-wrong-psk");
+
+        var ex = await Should.ThrowAsync<RpcException>(() =>
+            interceptor.ClientStreamingServerHandler<string, string>(
+                requestStream: null!, context, (_, _) => Task.FromResult("ok")));
+
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task DuplexStreamingPath_IsAlsoGated()
+    {
+        var interceptor = CreateInterceptor("the-cluster-psk");
+        var context = CreateContext(ExecuteMethod, "Bearer the-wrong-psk");
+
+        var ex = await Should.ThrowAsync<RpcException>(() =>
+            interceptor.DuplexStreamingServerHandler<string, string>(
+                requestStream: null!, responseStream: null!, context, (_, _, _) => Task.CompletedTask));
+
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public void HasExactlyOnePublicConstructor()
+    {
+        // Grpc.AspNetCore silently stops invoking an interceptor with more than one public ctor —
+        // this pins the shape so a well-meaning overload doesn't quietly disable auth in production.
+        var publicCtors = typeof(MeshCommandAuthInterceptor).GetConstructors();
+
+        publicCtors.Length.ShouldBe(1);
+    }
+
+    /// <summary>
+    ///     Minimal <see cref="ServerCallContext"/> carrying just a method name and request headers —
+    ///     the only two things the interceptor reads. Hand-rolled because
+    ///     <c>Grpc.Core.Testing.TestServerCallContext</c> ships only in the retired native package.
+    /// </summary>
+    private sealed class FakeServerCallContext(string method, Metadata requestHeaders)
+        : ServerCallContext
+    {
+        protected override string MethodCore => method;
+        protected override string HostCore => "localhost";
+        protected override string PeerCore => "ipv4:127.0.0.1:12345";
+        protected override DateTime DeadlineCore => DateTime.UtcNow.AddMinutes(1);
+        protected override Metadata RequestHeadersCore => requestHeaders;
+        protected override CancellationToken CancellationTokenCore => CancellationToken.None;
+        protected override Metadata ResponseTrailersCore { get; } = [];
+        protected override Status StatusCore { get; set; }
+        protected override WriteOptions? WriteOptionsCore { get; set; }
+
+        protected override AuthContext AuthContextCore { get; } =
+            new(null, new Dictionary<string, List<AuthProperty>>());
+
+        protected override ContextPropagationToken CreatePropagationTokenCore(
+            ContextPropagationOptions? options)
+            => throw new NotSupportedException();
+
+        protected override Task WriteResponseHeadersAsyncCore(Metadata responseHeaders)
+            => Task.CompletedTask;
+    }
+}