fix(r2-06): GREEN — ServerHistorianOptionsValidator (consumer-gated fail-fast on bad Endpoint) (06/S-11)

archreview/plans/R2-06-serverhistorian-failfast-plan.md.tasks.json

@@ -27,7 +27,7 @@
     {
       "id": "T4",
       "subject": "GREEN: implement ServerHistorianOptionsValidator (OptionsValidatorBase, ctor IConfiguration, consumed = Enabled || AlarmHistorian:Enabled, fail on empty/non-absolute/non-http(s) Endpoint)",
-      "status": "pending",
+      "status": "completed",
       "blockedBy": [
         "T3"
       ]

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

@@ -0,0 +1,66 @@
+using Microsoft.Extensions.Configuration;
+using ZB.MOM.WW.Configuration;
+using ZB.MOM.WW.OtOpcUa.Runtime.Historian;
+
+namespace ZB.MOM.WW.OtOpcUa.Host.Configuration;
+
+/// <summary>
+///     Fail-fast startup validator for <see cref="ServerHistorianOptions"/> (archreview 06/S-11),
+///     built on the shared <c>ZB.MOM.WW.Configuration</c> <see cref="OptionsValidatorBase{TOptions}"/>.
+///     Wired via <c>AddValidatedOptions</c> so a provably-crashing historian config fails host startup
+///     with a named, aggregated <c>OptionsValidationException</c> instead of the raw
+///     <see cref="System.UriFormatException"/> the gateway client factory's <c>new Uri(...)</c> would
+///     otherwise throw at first resolution (a crash-loop under a service/docker restart policy).
+/// </summary>
+/// <remarks>
+///     <para>
+///         <b>Consumer-gated, not section-gated.</b> The load-bearing question is not "is
+///         <c>ServerHistorian</c> enabled?" but "is its gateway connection <em>consumed</em> by anything
+///         enabled?". The alarm-history sink (<c>AlarmHistorian:Enabled=true</c>) sources its
+///         endpoint/key/TLS from the <c>ServerHistorian</c> section independently of
+///         <see cref="ServerHistorianOptions.Enabled"/>, so it must also gate this check — otherwise the
+///         <c>AlarmHistorian:Enabled=true</c> / <c>ServerHistorian:Enabled=false</c> corner crashes with
+///         zero warning. Continuous historization is already co-gated on
+///         <see cref="ServerHistorianOptions.Enabled"/> in the Host, so <c>Enabled</c> covers it.
+///     </para>
+///     <para>
+///         <b>Fail tier = provably-crashing configs only.</b> Only an empty / non-absolute / non-http(s)
+///         <c>Endpoint</c> fails here (it throws in the factory). Empty <c>ApiKey</c> and non-positive
+///         <c>MaxTieClusterOverfetch</c> degrade rather than crash (the gateway rejects calls / the node
+///         manager surfaces a Bad read), so they stay operator warnings in
+///         <see cref="ServerHistorianOptions.Validate"/>. The <c>Endpoint</c> value is not a secret and
+///         is echoed to make the error actionable; the <c>ApiKey</c> is never surfaced.
+///     </para>
+/// </remarks>
+public sealed class ServerHistorianOptionsValidator : OptionsValidatorBase<ServerHistorianOptions>
+{
+    private readonly IConfiguration _configuration;
+
+    /// <summary>Creates the validator over the app configuration (read to resolve the consumer gate).</summary>
+    /// <param name="configuration">The app configuration; used to read <c>AlarmHistorian:Enabled</c>.</param>
+    public ServerHistorianOptionsValidator(IConfiguration configuration) =>
+        _configuration = configuration ?? throw new ArgumentNullException(nameof(configuration));
+
+    /// <inheritdoc />
+    protected override void Validate(ValidationBuilder builder, ServerHistorianOptions options)
+    {
+        var alarmHistorianEnabled = _configuration.GetValue<bool>("AlarmHistorian:Enabled");
+        var consumed = options.Enabled || alarmHistorianEnabled;
+
+        // A section nobody consumes may legitimately be empty (the docker-dev default) — no checks.
+        if (!consumed) return;
+
+        var endpointValid = Uri.TryCreate(options.Endpoint, UriKind.Absolute, out var uri)
+            && (uri.Scheme == Uri.UriSchemeHttp || uri.Scheme == Uri.UriSchemeHttps);
+
+        // Name the DRIVING section(s) so the operator knows why an empty/malformed endpoint fails —
+        // especially in the alarm-only corner where ServerHistorian itself is disabled.
+        var reason = options.Enabled
+            ? "required because ServerHistorian:Enabled=true"
+            : "required because AlarmHistorian:Enabled=true sources its gateway connection (endpoint/key/TLS) from the ServerHistorian section";
+
+        builder.RequireThat(
+            endpointValid,
+            $"ServerHistorian:Endpoint is empty or not an absolute http(s) URI ('{options.Endpoint}') — {reason}.");
+    }
+}