feat(mesh-phase5): fail-closed bearer interceptor for the telemetry stream

Claude-Session: https://claude.ai/code/session_01GASWkNEi68FSCtvr6rLoEW

src/Server/ZB.MOM.WW.OtOpcUa.Host/Configuration/TelemetryStreamAuthInterceptor.cs

@@ -0,0 +1,165 @@
+using System.Security.Cryptography;
+using System.Text;
+using Grpc.Core;
+using Grpc.Core.Interceptors;
+using Microsoft.Extensions.Logging;
+using Microsoft.Extensions.Options;
+using ZB.MOM.WW.OtOpcUa.Cluster;
+
+namespace ZB.MOM.WW.OtOpcUa.Host.Configuration;
+
+/// <summary>
+///     Gates the driver-node telemetry stream endpoint (per-cluster mesh Phase 5). The
+///     <c>TelemetryStreamService.Subscribe</c> RPC streams a node's live alerts / script-logs /
+///     driver-health / driver-resilience-status to whoever dials it; anything able to reach a driver
+///     node's telemetry port could otherwise pull that live feed out-of-band. This interceptor is the
+///     ONLY inbound auth on that endpoint.
+/// </summary>
+/// <remarks>
+///     <para>
+///         <b>Scoped by method path.</b> Only calls under
+///         <c>/telemetry.v1.TelemetryStreamService/</c> are gated; every other method on the shared
+///         gRPC pipeline (config-serve, LocalDb sync) passes through untouched, so this can share one
+///         <c>AddGrpc</c> registration with <see cref="ConfigServeAuthInterceptor"/> and
+///         <see cref="LocalDbSyncAuthInterceptor"/>.
+///     </para>
+///     <para>
+///         <b>Fail-closed.</b> With no <c>Telemetry:ApiKey</c> configured, NO dial is accepted,
+///         authenticated or not. Treating "no key" as "no auth required" would expose the live
+///         telemetry feed on exactly the default shape most nodes ship with. The caller dialing in
+///         must present the same <c>TelemetryDial:ApiKey</c> (the shared node key), so a key typo
+///         stops telemetry delivery outright rather than degrading to unauthenticated.
+///     </para>
+///     <para>
+///         Comparison is <see cref="CryptographicOperations.FixedTimeEquals"/> over UTF-8 bytes, so a
+///         wrong key cannot be recovered byte-by-byte from response timing. Length differences are
+///         unavoidably observable and are not sensitive.
+///     </para>
+///     <para>
+///         <b>Exactly one public constructor.</b> <c>Grpc.AspNetCore</c> silently stops invoking an
+///         interceptor that has more than one public ctor — see
+///         <c>TelemetryStreamAuthInterceptorTests.HasExactlyOnePublicConstructor</c>.
+///     </para>
+/// </remarks>
+public sealed class TelemetryStreamAuthInterceptor : Interceptor
+{
+    private const string ServicePrefix = "/telemetry.v1.TelemetryStreamService/";
+    private const string AuthorizationHeader = "authorization";
+    private const string BearerPrefix = "Bearer ";
+
+    private readonly IOptions<TelemetryOptions> _options;
+    private readonly ILogger<TelemetryStreamAuthInterceptor> _logger;
+
+    /// <summary>Creates the interceptor.</summary>
+    /// <param name="options">Telemetry options; <c>ApiKey</c> is the expected bearer token.</param>
+    /// <param name="logger">Logger for denial diagnostics.</param>
+    public TelemetryStreamAuthInterceptor(
+        IOptions<TelemetryOptions> options,
+        ILogger<TelemetryStreamAuthInterceptor> logger)
+    {
+        ArgumentNullException.ThrowIfNull(options);
+        ArgumentNullException.ThrowIfNull(logger);
+
+        _options = options;
+        _logger = logger;
+    }
+
+    /// <inheritdoc />
+    public override Task<TResponse> UnaryServerHandler<TRequest, TResponse>(
+        TRequest request,
+        ServerCallContext context,
+        UnaryServerMethod<TRequest, TResponse> continuation)
+    {
+        Authorize(context);
+        return continuation(request, context);
+    }
+
+    /// <inheritdoc />
+    public override Task DuplexStreamingServerHandler<TRequest, TResponse>(
+        IAsyncStreamReader<TRequest> requestStream,
+        IServerStreamWriter<TResponse> responseStream,
+        ServerCallContext context,
+        DuplexStreamingServerMethod<TRequest, TResponse> continuation)
+    {
+        Authorize(context);
+        return continuation(requestStream, responseStream, context);
+    }
+
+    /// <inheritdoc />
+    public override Task<TResponse> ClientStreamingServerHandler<TRequest, TResponse>(
+        IAsyncStreamReader<TRequest> requestStream,
+        ServerCallContext context,
+        ClientStreamingServerMethod<TRequest, TResponse> continuation)
+    {
+        Authorize(context);
+        return continuation(requestStream, context);
+    }
+
+    /// <inheritdoc />
+    public override Task ServerStreamingServerHandler<TRequest, TResponse>(
+        TRequest request,
+        IServerStreamWriter<TResponse> responseStream,
+        ServerCallContext context,
+        ServerStreamingServerMethod<TRequest, TResponse> continuation)
+    {
+        Authorize(context);
+        return continuation(request, responseStream, context);
+    }
+
+    /// <summary>
+    ///     Throws <see cref="RpcException"/> with <see cref="StatusCode.PermissionDenied"/> if this is
+    ///     a telemetry-stream call that does not carry the configured bearer token. Non-telemetry
+    ///     calls return immediately.
+    /// </summary>
+    private void Authorize(ServerCallContext context)
+    {
+        if (!context.Method.StartsWith(ServicePrefix, StringComparison.Ordinal))
+            return;
+
+        var expected = _options.Value.ApiKey;
+        if (string.IsNullOrEmpty(expected))
+        {
+            _logger.LogWarning(
+                "Rejected a telemetry stream call to {Method}: no Telemetry:ApiKey is configured, so " +
+                "the telemetry endpoint is closed. Configure the shared node key on this node and every " +
+                "dialing caller.",
+                context.Method);
+            throw new RpcException(new Status(
+                StatusCode.PermissionDenied,
+                "Telemetry stream is not accepting connections: no API key is configured on this node."));
+        }
+
+        var presented = ExtractBearerToken(context.RequestHeaders);
+        if (presented is null || !FixedTimeEquals(presented, expected))
+        {
+            _logger.LogWarning(
+                "Rejected a telemetry stream call to {Method}: {Reason}.",
+                context.Method,
+                presented is null ? "no bearer token presented" : "bearer token did not match");
+            throw new RpcException(new Status(
+                StatusCode.PermissionDenied,
+                "Telemetry stream authentication failed."));
+        }
+    }
+
+    private static string? ExtractBearerToken(Metadata headers)
+    {
+        // gRPC lowercases header keys on the wire; compare case-insensitively anyway so a hand-built
+        // Metadata in a test behaves the same as a real request.
+        foreach (var entry in headers)
+        {
+            if (!string.Equals(entry.Key, AuthorizationHeader, StringComparison.OrdinalIgnoreCase))
+                continue;
+
+            var value = entry.Value;
+            if (value is not null && value.StartsWith(BearerPrefix, StringComparison.OrdinalIgnoreCase))
+                return value[BearerPrefix.Length..];
+        }
+
+        return null;
+    }
+
+    private static bool FixedTimeEquals(string presented, string expected)
+        => CryptographicOperations.FixedTimeEquals(
+            Encoding.UTF8.GetBytes(presented), Encoding.UTF8.GetBytes(expected));
+}

tests/Server/ZB.MOM.WW.OtOpcUa.Host.Tests/Configuration/TelemetryStreamAuthInterceptorTests.cs

@@ -0,0 +1,199 @@
+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>
+///     Per-cluster mesh Phase 5 — the telemetry stream endpoint's inbound gate. Wiring this
+///     interceptor into the <c>AddGrpc</c> pipeline + Kestrel is a separate, later task; this test
+///     covers only the interceptor's own authorization behavior.
+/// </summary>
+/// <remarks>
+///     Same contract as <see cref="ConfigServeAuthInterceptor"/> / <see cref="LocalDbSyncAuthInterceptor"/>,
+///     scoped to <c>/telemetry.v1.TelemetryStreamService/</c> — fail-closed on an unconfigured key,
+///     constant-time comparison, gated on every handler shape so scoping holds regardless of RPC shape.
+/// </remarks>
+public sealed class TelemetryStreamAuthInterceptorTests
+{
+    private const string SubscribeMethod = "/telemetry.v1.TelemetryStreamService/Subscribe";
+    private const string OtherMethod = "/deployment_artifact.v1.DeploymentArtifactService/Fetch";
+
+    private static TelemetryStreamAuthInterceptor CreateInterceptor(string? apiKey)
+        => new(
+            Options.Create(new TelemetryOptions { ApiKey = apiKey ?? string.Empty }),
+            NullLogger<TelemetryStreamAuthInterceptor>.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 server-streaming path (how <c>Subscribe</c> actually runs).</summary>
+    private static Task Invoke(TelemetryStreamAuthInterceptor interceptor, ServerCallContext context)
+        => interceptor.ServerStreamingServerHandler<string, string>(
+            "request", responseStream: null!, context, (_, _, _) => Task.CompletedTask);
+
+    [Fact]
+    public async Task NonTelemetryMethod_PassesThrough_EvenWithNoKeyConfigured()
+    {
+        // The interceptor shares the AddGrpc pipeline with other gRPC services, so it sees every
+        // call. It must be scoped strictly to the telemetry service.
+        var interceptor = CreateInterceptor(apiKey: null);
+        var context = CreateContext(OtherMethod, authorizationHeader: null);
+
+        await Invoke(interceptor, context); // no throw
+    }
+
+    [Fact]
+    public async Task SubscribeMethod_WithNoKeyConfigured_IsDenied_EvenWithABearerToken()
+    {
+        // Fail-closed. "No key configured" is the DEFAULT — treating it as "no auth required" would
+        // expose live telemetry on exactly the shape most nodes ship with. A token must not help.
+        var interceptor = CreateInterceptor(apiKey: null);
+        var context = CreateContext(SubscribeMethod, "Bearer anything-at-all");
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task SubscribeMethod_WithNoBearerToken_IsDenied()
+    {
+        var interceptor = CreateInterceptor("the-shared-key");
+        var context = CreateContext(SubscribeMethod, authorizationHeader: null);
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task SubscribeMethod_WithMalformedAuthorizationHeader_IsDenied()
+    {
+        // No "Bearer " prefix at all — must be treated the same as a missing header.
+        var interceptor = CreateInterceptor("the-shared-key");
+        var context = CreateContext(SubscribeMethod, "the-shared-key");
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task SubscribeMethod_WithWrongBearerToken_IsDenied()
+    {
+        var interceptor = CreateInterceptor("the-shared-key");
+        var context = CreateContext(SubscribeMethod, "Bearer the-wrong-key");
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task SubscribeMethod_WithCorrectBearerToken_PassesThrough()
+    {
+        var interceptor = CreateInterceptor("the-shared-key");
+        var context = CreateContext(SubscribeMethod, "Bearer the-shared-key");
+
+        await Invoke(interceptor, context); // no throw
+    }
+
+    [Fact]
+    public async Task SubscribeMethod_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-shared-key");
+        var context = CreateContext(SubscribeMethod, "Bearer the-shared-ke");
+
+        var ex = await Should.ThrowAsync<RpcException>(() => Invoke(interceptor, context));
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task UnaryPath_IsAlsoGated()
+    {
+        // Subscribe is server-streaming today, but gating only that path would leave any future
+        // unary method on the same service open. Gate every handler shape.
+        var interceptor = CreateInterceptor("the-shared-key");
+        var context = CreateContext(SubscribeMethod, "Bearer the-wrong-key");
+
+        var ex = await Should.ThrowAsync<RpcException>(() =>
+            interceptor.UnaryServerHandler<string, string>(
+                "request", context, (_, _) => Task.FromResult("ok")));
+
+        ex.StatusCode.ShouldBe(StatusCode.PermissionDenied);
+    }
+
+    [Fact]
+    public async Task ClientStreamingPath_IsAlsoGated()
+    {
+        var interceptor = CreateInterceptor("the-shared-key");
+        var context = CreateContext(SubscribeMethod, "Bearer the-wrong-key");
+
+        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-shared-key");
+        var context = CreateContext(SubscribeMethod, "Bearer the-wrong-key");
+
+        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(TelemetryStreamAuthInterceptor).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;
+    }
+}