feat(overview): poller, leader aggregation and the dashboard UI

Tasks 3.4-3.6 of the overview-dashboard plan. Polling (3.4/3.5): - OverviewPollerService: one timer at the fastest configured cadence, each target polled when its own interval is due, fan-out per sweep, no retries (the next tick is the retry, so damping stays the only place that decides whether a failure is worth showing). - OverviewSnapshotStore: atomic swap of a complete immutable graph plus a change event. Pages read it and never probe — the cache-first requirement. - LeaderResolver: per-group leader from akka-cluster data, with the split-brain flag scoped to members that are actually answering, so an ordinary failover is not misread as a disagreement. UI (3.6): ThemeShell + StatusPill/TechCard composition against the mockup; instance cards carry the status stripe (dashed for Unreachable), the check detail list and the raw ready/active signal line. Two defects found by verification rather than by review: - The active tier answers with a status code and an EMPTY body, but the client demanded parseable JSON on every probe — so a healthy pair rendered as "role unknown" instead of Active/Standby. Split into ProbeAsync (ready tier, body is the payload) and ProbeStatusAsync (active tier, code is the answer). Caught by a live smoke run against two fake health endpoints; the poller tests now serve an empty body so they hold the fix. - SweepAsync published even when cancellation was already requested, leaving a half-probed registry as the store's final state on shutdown. It now checks the token itself rather than relying on the transport to throw. Also: app.UseAntiforgery() is required despite the anonymous-by-design pipeline — AddRazorComponents stamps antiforgery metadata unconditionally and the endpoint middleware hard-fails without it (every page was 500). Chosen over DisableAntiforgery() so a future form is protected by default. 147 tests, 0 warnings. Live-verified end to end against fake endpoints: Up/Unreachable/Active/Standby, leader chip, cluster-data line, KPI counts.
2026-07-24 07:05:16 -04:00
parent 61fc88c8a8
commit 5fe7135e2c
24 changed files with 2829 additions and 11 deletions
@@ -0,0 +1,142 @@
+using System.Net;
+using System.Text;
+using System.Text.Json;
+using ZB.MOM.WW.Overview.Polling;
+
+namespace ZB.MOM.WW.Overview.Tests;
+
+/// <summary>A clock the test drives by hand.</summary>
+/// <remarks>
+/// Only <see cref="GetUtcNow"/> is overridden: the poller's sweep — the part with rules worth
+/// pinning — is exercised directly, so no test here needs a fake timer.
+/// </remarks>
+internal sealed class FakeTimeProvider(DateTimeOffset start) : TimeProvider
+{
+    private DateTimeOffset _now = start;
+
+    public override DateTimeOffset GetUtcNow() => _now;
+
+    public void Advance(TimeSpan by) => _now += by;
+}
+
+/// <summary>Serves canned responses per absolute URL and counts what was requested.</summary>
+internal sealed class RoutingHandler : HttpMessageHandler
+{
+    private readonly Dictionary<string, Func<HttpResponseMessage>> _routes = new(StringComparer.OrdinalIgnoreCase);
+
+    public List<string> Requests { get; } = [];
+
+    public RoutingHandler Json(string url, HttpStatusCode status, string body)
+    {
+        _routes[url] = () => new HttpResponseMessage(status)
+        {
+            Content = new StringContent(body, Encoding.UTF8, "application/json"),
+        };
+        return this;
+    }
+
+    /// <summary>
+    /// A status-code-only response with an EMPTY body — what the active tier actually returns when
+    /// it is a bare gate endpoint rather than a full health report.
+    /// </summary>
+    public RoutingHandler Status(string url, HttpStatusCode status)
+    {
+        _routes[url] = () => new HttpResponseMessage(status)
+        {
+            Content = new StringContent(string.Empty, Encoding.UTF8, "application/json"),
+        };
+        return this;
+    }
+
+    public RoutingHandler Fails(string url, string message)
+    {
+        _routes[url] = () => throw new HttpRequestException(message);
+        return this;
+    }
+
+    /// <summary>Lets a wrapping handler delegate here without re-entering the protected member.</summary>
+    public Task<HttpResponseMessage> HandleAsync(HttpRequestMessage request) =>
+        SendAsync(request, CancellationToken.None);
+
+    protected override Task<HttpResponseMessage> SendAsync(
+        HttpRequestMessage request, CancellationToken cancellationToken)
+    {
+        var url = request.RequestUri!.ToString();
+
+        lock (Requests)
+            Requests.Add(url);
+
+        if (!_routes.TryGetValue(url, out var factory))
+            return Task.FromException<HttpResponseMessage>(new HttpRequestException($"no route for {url}"));
+
+        try
+        {
+            return Task.FromResult(factory());
+        }
+        catch (HttpRequestException ex)
+        {
+            return Task.FromException<HttpResponseMessage>(ex);
+        }
+    }
+}
+
+/// <summary>Hands every named client the same test handler.</summary>
+internal sealed class StubHttpClientFactory(HttpMessageHandler handler) : IHttpClientFactory
+{
+    public HttpClient CreateClient(string name) =>
+        new(handler, disposeHandler: false) { Timeout = Timeout.InfiniteTimeSpan };
+}
+
+/// <summary>Builds canonical health bodies so tests state intent, not JSON.</summary>
+internal static class HealthBody
+{
+    public static string Ready(string status, params (string Name, string Status, string? Leader)[] entries)
+    {
+        var payload = new
+        {
+            status,
+            totalDurationMs = 1.5,
+            entries = entries.ToDictionary(
+                e => e.Name,
+                e => (object)new
+                {
+                    status = e.Status,
+                    description = $"{e.Name} says {e.Status}",
+                    durationMs = 0.5,
+                    data = e.Leader is null ? null : new Dictionary<string, object> { ["leader"] = e.Leader },
+                },
+                StringComparer.Ordinal),
+        };
+
+        return JsonSerializer.Serialize(payload);
+    }
+}
+
+/// <summary>Builds <see cref="InstanceSnapshot"/> values for the pure-logic tests.</summary>
+internal static class Snapshots
+{
+    public static InstanceSnapshot Instance(
+        string name,
+        string? group = null,
+        string baseUrl = "http://host:8080",
+        bool hasActiveRole = true,
+        InstanceStatus? status = InstanceStatus.Up,
+        string? leader = null) =>
+        new()
+        {
+            Application = "App",
+            Instance = name,
+            Group = group,
+            BaseUrl = baseUrl,
+            HasActiveRole = hasActiveRole,
+            Status = status,
+            Report = leader is null ? null : ReportWithLeader(leader),
+            StaleAfter = TimeSpan.FromSeconds(45),
+        };
+
+    private static ZbHealthReport ReportWithLeader(string leader)
+    {
+        var body = HealthBody.Ready("Healthy", ("akka-cluster", "Healthy", leader));
+        return JsonSerializer.Deserialize<ZbHealthReport>(body)!;
+    }
+}