Fix all baseline code-review findings across the six shared libraries

Resolves the 35 findings from the 2026-06-01 baseline (commit 26ba1c7), test-first for every behavioral change. +51 tests (331 -> 382 passing, 0 failed). - Telemetry-001 (HIGH): RedactionEnricher now honours property removal, so a redactor that drops a key actually scrubs the secret from the event. - Auth: LDAP validator ValidateOnStart; API-key verify no longer fails on a best-effort MarkUsed write or a corrupt scopes column (fail-closed); LDAP cert validation hook; KeyPrefix persistence aligned; README algorithm corrected. - Health: Akka checks return Degraded (not throw) when the cluster isn't up yet; GrpcDependencyHealthCheck catch-all; null 'description' rendered; composite endpoint builder; XML docs shipped. - Audit: CompositeAuditWriter no longer re-throws OperationCanceledException; TruncatingAuditRedactor over-redact scrubs Target + safe negative max; options record; XML docs shipped. - Configuration: TryAddEnumerable idempotent registration; consistent port quoting; strict invariant port parsing; XML docs + README packaged. - Theme: mobile toggle is now CSS-only (no Bootstrap JS); token/CSS hygiene; XML docs on the public parameter surface. Shared-contract/spec docs updated where the code was the source of truth (observability service.instance.id, MapZbMetrics, redactor reach). All changes additive/back-compatible at v0.1.0. code-reviews bookkeeping follows separately.
2026-06-01 11:22:14 -04:00
parent 26ba1c7215
commit 544a6ddb77
72 changed files with 1539 additions and 191 deletions
@@ -86,6 +86,50 @@ public sealed class ActiveNodeDecisionTests
        Assert.False(gate.IsActiveNode);
    }

+    [Fact]
+    public async Task HealthCheck_RoleLess_ClusterInaccessible_ReturnsDegraded()
+    {
+        // ActorSystem present but Akka.Cluster not configured → Cluster.Get throws. The check must
+        // return Degraded (startup-safety rule), not let the exception escape (→ Unhealthy).
+        using var system = ActorSystem.Create("plain-no-cluster-roleless");
+        try
+        {
+            var provider = new ServiceCollection()
+                .AddSingleton(system)
+                .BuildServiceProvider();
+            var check = new ActiveNodeHealthCheck(provider);
+
+            var result = await check.CheckHealthAsync(NewContext(check));
+
+            Assert.Equal(HealthStatus.Degraded, result.Status);
+        }
+        finally
+        {
+            await system.Terminate();
+        }
+    }
+
+    [Fact]
+    public async Task HealthCheck_RoleFiltered_ClusterInaccessible_ReturnsDegraded()
+    {
+        using var system = ActorSystem.Create("plain-no-cluster-rolefiltered");
+        try
+        {
+            var provider = new ServiceCollection()
+                .AddSingleton(system)
+                .BuildServiceProvider();
+            var check = new ActiveNodeHealthCheck(provider, "admin");
+
+            var result = await check.CheckHealthAsync(NewContext(check));
+
+            Assert.Equal(HealthStatus.Degraded, result.Status);
+        }
+        finally
+        {
+            await system.Terminate();
+        }
+    }
+
    private static HealthCheckContext NewContext(IHealthCheck check) => new()
    {
        Registration = new HealthCheckRegistration("active-node", check, HealthStatus.Unhealthy, tags: null),
@@ -1,3 +1,4 @@
+using Akka.Actor;
 using Akka.Cluster;
 using Microsoft.Extensions.DependencyInjection;
 using Microsoft.Extensions.Diagnostics.HealthChecks;
@@ -70,6 +71,30 @@ public sealed class AkkaClusterStatusPolicyTests
        Assert.Equal(HealthStatus.Degraded, result.Status);
    }

+    [Fact]
+    public async Task HealthCheck_ActorSystemPresentButClusterInaccessible_ReturnsDegraded()
+    {
+        // A plain (non-clustered) ActorSystem exists in DI, but Akka.Cluster is not configured,
+        // so Cluster.Get(system) throws a ConfigurationException — the startup race the spec calls
+        // out. The check must return Degraded, not let the exception escape (→ Unhealthy via the host).
+        using var system = ActorSystem.Create("plain-no-cluster");
+        try
+        {
+            var provider = new ServiceCollection()
+                .AddSingleton(system)
+                .BuildServiceProvider();
+            var check = new AkkaClusterHealthCheck(provider, AkkaClusterStatusPolicy.Default);
+
+            var result = await check.CheckHealthAsync(NewContext(check));
+
+            Assert.Equal(HealthStatus.Degraded, result.Status);
+        }
+        finally
+        {
+            await system.Terminate();
+        }
+    }
+
    private static HealthCheckContext NewContext(IHealthCheck check) => new()
    {
        Registration = new HealthCheckRegistration("akka-cluster", check, HealthStatus.Unhealthy, tags: null),
@@ -71,6 +71,21 @@ public sealed class GrpcDependencyHealthCheckTests
        Assert.Contains("mxaccessgw worker", result.Description);
    }

+    [Fact]
+    public async Task ProbeThrowsArbitraryException_Unhealthy()
+    {
+        // A non-RpcException / non-OperationCanceledException (e.g. the transport surfacing an
+        // InvalidOperationException) must be caught and mapped to Unhealthy, not allowed to escape.
+        var result = await RunAsync(new GrpcDependencyOptions
+        {
+            DependencyName = "mxaccessgw worker",
+            Probe = static (_, _) => throw new InvalidOperationException("channel disposed"),
+        });
+
+        Assert.Equal(HealthStatus.Unhealthy, result.Status);
+        Assert.Contains("mxaccessgw worker", result.Description);
+    }
+
    [Fact]
    public async Task ProbeExceedsTimeout_Unhealthy()
    {
@@ -31,7 +31,7 @@ public sealed class ResponseWriterTests
    }

    private static async Task<HttpResponseMessage> GetReadyAsync(
-        HealthStatus status, string description = "db reachable")
+        HealthStatus status, string? description = "db reachable")
    {
        var builder = WebApplication.CreateBuilder();
        builder.WebHost.UseTestServer();
@@ -66,6 +66,24 @@ public sealed class ResponseWriterTests
        Assert.Equal("db reachable", db.GetProperty("description").GetString());
    }

+    [Fact]
+    public async Task ReadyEndpoint_NullDescription_EmitsDescriptionKeyAsNull()
+    {
+        // A check that produces no description must still emit the "description" key with a JSON null
+        // value (matching the spec §3 example and the HealthChecks.UI.Client shape) rather than
+        // dropping the key — so consumers can read entries.<name>.description without handling a
+        // missing property.
+        var response = await GetReadyAsync(HealthStatus.Healthy, description: null);
+
+        Assert.Equal(HttpStatusCode.OK, response.StatusCode);
+
+        using var doc = JsonDocument.Parse(await response.Content.ReadAsStringAsync());
+        var db = doc.RootElement.GetProperty("entries").GetProperty("db");
+
+        Assert.True(db.TryGetProperty("description", out var description), "description key must be present");
+        Assert.Equal(JsonValueKind.Null, description.ValueKind);
+    }
+
    [Fact]
    public async Task ReadyEndpoint_Degraded_Returns200_WithDegradedStatus()
    {
@@ -127,6 +127,31 @@ public sealed class TierMappingTests
        Assert.Equal(0, active.Invocations);
    }

+    [Fact]
+    public async Task ChainedConvention_AppliesToAllThreeEndpoints()
+    {
+        // MapZbHealth returns a composite builder, so a convention chained onto its result
+        // (.RequireHost) must gate all three endpoints — not just readiness. With a host filter
+        // that does not match the default test-client host, every tier returns 404.
+        var builder = WebApplication.CreateBuilder();
+        builder.WebHost.UseTestServer();
+        builder.Services.AddHealthChecks()
+            .AddCheck("ready-check", new RecordingHealthCheck(HealthStatus.Healthy), tags: new[] { ZbHealthTags.Ready })
+            .AddCheck("active-check", new RecordingHealthCheck(HealthStatus.Healthy), tags: new[] { ZbHealthTags.Active });
+
+        await using var app = builder.Build();
+        app.MapZbHealth().RequireHost("health.internal");
+        await app.StartAsync();
+
+        var client = app.GetTestClient();
+
+        // The default test host does not match "health.internal", so the convention removed every
+        // endpoint from this host — confirming it fanned out to all three, not just readiness.
+        Assert.Equal(HttpStatusCode.NotFound, (await client.GetAsync("/health/ready")).StatusCode);
+        Assert.Equal(HttpStatusCode.NotFound, (await client.GetAsync("/health/active")).StatusCode);
+        Assert.Equal(HttpStatusCode.NotFound, (await client.GetAsync("/healthz")).StatusCode);
+    }
+
    [Fact]
    public async Task Options_OverrideRoutePaths()
    {