lmxopcua/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.MTConnect.Tests/MTConnectReadPathTests.cs

using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;

namespace ZB.MOM.WW.OtOpcUa.Driver.MTConnect.Tests;

/// <summary>
///     Review 2026-10-21 R06:T-4 and T-2 on the read path.
///     <list type="bullet">
///         <item>T-4 — every <c>ReadAsync</c> batch fetched + parsed the whole device <c>/current</c> even while the
///         <c>/sample</c> pump held a live, healthy index. A read now answers from that index (READ only — the pump
///         stays its single writer) while the pump is live and not degraded, and keeps <c>/current</c> as the
///         fallback.</item>
///         <item>T-2 — Agent-restart detection lived only on the pump, and the read path discarded the
///         <c>/current</c> answer's <c>instanceId</c>: a browse-only driver kept a cached <c>/probe</c> model across an
///         Agent restart and never raised rediscovery. The fallback read now checks it.</item>
///     </list>
/// </summary>
public sealed class MTConnectReadPathTests
{
    private const long RestartedInstance = 1655000777L;
    private static readonly TimeSpan Watchdog = TimeSpan.FromSeconds(30);

    private static CancellationToken Ct => TestContext.Current.CancellationToken;

    private static MTConnectDriverOptions Opts() => new()
    {
        AgentUri = "http://fixture-agent:5000",
        RequestTimeoutMs = 5000,
        Tags = [new MTConnectTagDefinition("dev1_pos", DriverDataType.Float64)],
    };

    /// <summary>T-4: with a live, healthy pump the read is answered from its index — no /current round trip.</summary>
    [Fact]
    public async Task A_read_with_a_live_pump_answers_from_the_index_without_a_current_call()
    {
        var client = CannedAgentClient.FromFixtures();
        var driver = new MTConnectDriver(Opts(), "mt-t4", _ => client);
        await driver.InitializeAsync("{}", Ct);
        try
        {
            await driver.SubscribeAsync(["dev1_pos"], TimeSpan.FromMilliseconds(50), Ct);
            await client.PumpAsync(MTConnectPumpGenerationChunks.Pos(108, 113, "7.25")).WaitAsync(Watchdog, Ct);
            var currentCalls = client.CurrentCallCount;

            var result = (await driver.ReadAsync(["dev1_pos"], Ct)).Single();

            result.Value.ShouldBe(7.25d, "the read must serve the pump's newest value");
            client.CurrentCallCount.ShouldBe(currentCalls, "no /current while the pump's index is live");
        }
        finally
        {
            await driver.ShutdownAsync(CancellationToken.None);
        }
    }

    /// <summary>Positive control for T-4: with no pump the read still issues exactly one /current.</summary>
    [Fact]
    public async Task A_read_with_no_pump_falls_back_to_one_current_call()
    {
        var client = CannedAgentClient.FromFixtures();
        var driver = new MTConnectDriver(Opts(), "mt-t4-fallback", _ => client);
        await driver.InitializeAsync("{}", Ct);
        try
        {
            var currentCalls = client.CurrentCallCount;

            await driver.ReadAsync(["dev1_pos"], Ct);

            client.CurrentCallCount.ShouldBe(currentCalls + 1);
        }
        finally
        {
            await driver.ShutdownAsync(CancellationToken.None);
        }
    }

    /// <summary>T-4: a pump whose stream is failing does not serve reads — they fall back to /current.</summary>
    [Fact]
    public async Task A_read_with_a_degraded_pump_falls_back_to_current()
    {
        var client = CannedAgentClient.FromFixtures();
        // Every /sample fails: the pump stays alive (reconnecting under backoff) but its stream is degraded.
        client.SampleFailure = new IOException("connection refused");
        var options = new MTConnectDriverOptions
        {
            AgentUri = "http://fixture-agent:5000",
            RequestTimeoutMs = 5000,
            Tags = [new MTConnectTagDefinition("dev1_pos", DriverDataType.Float64)],
            Reconnect = new MTConnectReconnectOptions { MinBackoffMs = 1000, MaxBackoffMs = 1000 },
        };
        var driver = new MTConnectDriver(options, "mt-t4-degraded", _ => client);
        await driver.InitializeAsync("{}", Ct);
        try
        {
            await driver.SubscribeAsync(["dev1_pos"], TimeSpan.FromMilliseconds(50), Ct);
            await client.WaitForSampleCallsAsync(1).WaitAsync(Watchdog, Ct);
            var deadline = DateTime.UtcNow + Watchdog;
            while (driver.GetHealth().State != DriverState.Degraded && DateTime.UtcNow < deadline)
                await Task.Delay(20, Ct);
            driver.GetHealth().State.ShouldBe(DriverState.Degraded);
            var currentCalls = client.CurrentCallCount;

            await driver.ReadAsync(["dev1_pos"], Ct);

            client.CurrentCallCount.ShouldBe(currentCalls + 1, "a degraded stream's index is not trusted for reads");
        }
        finally
        {
            await driver.ShutdownAsync(CancellationToken.None);
        }
    }

    /// <summary>T-2: a browse-only driver's read sees the Agent restart — once — and drops the stale model.</summary>
    [Fact]
    public async Task A_read_that_sees_a_new_instance_id_raises_rediscovery_once_and_drops_the_probe_model()
    {
        var client = CannedAgentClient.FromFixtures();
        var driver = new MTConnectDriver(Opts(), "mt-t2", _ => client);
        await driver.InitializeAsync("{}", Ct);
        var raised = 0;
        driver.OnRediscoveryNeeded += (_, _) => Interlocked.Increment(ref raised);
        try
        {
            driver.CachedProbeModel.ShouldNotBeNull("positive control: initialize cached the model");
            client.Current = new MTConnectStreamsResult(RestartedInstance, 5, 1, client.Current.Observations);

            await driver.ReadAsync(["dev1_pos"], Ct);
            await driver.ReadAsync(["dev1_pos"], Ct);

            raised.ShouldBe(1, "once per distinct instanceId, not once per read");
            driver.CachedProbeModel.ShouldBeNull("the model describes a process that no longer exists");
            // Review m6: the session's cursor moves to the new process, so a later subscription does not open at the
            // dead instance's sequence (and flicker through a clear + re-baseline on its first chunk).
            driver.AgentInstanceId.ShouldBe(RestartedInstance);
            driver.AgentNextSequence.ShouldBe(5);
        }
        finally
        {
            await driver.ShutdownAsync(CancellationToken.None);
        }
    }

    /// <summary>T-2 control: reads against the same Agent process never raise rediscovery.</summary>
    [Fact]
    public async Task Reads_against_the_same_instance_raise_nothing()
    {
        var client = CannedAgentClient.FromFixtures();
        var driver = new MTConnectDriver(Opts(), "mt-t2-same", _ => client);
        await driver.InitializeAsync("{}", Ct);
        var raised = 0;
        driver.OnRediscoveryNeeded += (_, _) => Interlocked.Increment(ref raised);
        try
        {
            await driver.ReadAsync(["dev1_pos"], Ct);
            await driver.ReadAsync(["dev1_pos"], Ct);

            raised.ShouldBe(0);
            driver.CachedProbeModel.ShouldNotBeNull();
        }
        finally
        {
            await driver.ShutdownAsync(CancellationToken.None);
        }
    }

    private const string NoDeviceError =
        """
        <?xml version="1.0" encoding="UTF-8"?>
        <MTConnectError xmlns="urn:mtconnect.org:MTConnectError:1.3">
          <Header creationTime="2026-10-22T12:00:00Z" sender="stub-agent" instanceId="1" version="1.3.0.12" bufferSize="1"/>
          <Errors><Error errorCode="NO_DEVICE">Could not find the device 'VMC-9'</Error></Errors>
        </MTConnectError>
        """;

    private static Exception ParseFailure(string xml)
    {
        try
        {
            MTConnectStreamsParser.Parse(xml);
        }
        catch (Exception ex)
        {
            return ex;
        }

        throw new InvalidOperationException("expected the parse to fail");
    }

    /// <summary>
    ///     Health contract: an MTConnectError answer to /current is the Agent REFUSING (it answered) — the batch is Bad,
    ///     but health is restored / kept Healthy with the stamp advanced, and the refusal is logged once, not per read.
    /// </summary>
    [Fact]
    public async Task An_agent_refusal_of_current_is_a_reply_not_a_comms_fault()
    {
        var logger = new RecordingDriverLogger();
        var client = CannedAgentClient.FromFixtures();
        var driver = new MTConnectDriver(Opts(), "mt-refusal", _ => client, logger);
        await driver.InitializeAsync("{}", Ct);
        try
        {
            // A comms fault first, so the refusal has a Degraded to restore.
            client.CurrentFailure = new HttpRequestException("connection refused");
            await driver.ReadAsync(["dev1_pos"], Ct);
            driver.GetHealth().State.ShouldBe(DriverState.Degraded, "positive control: a comms fault does degrade");
            var stamp = driver.GetHealth().LastSuccessfulRead.ShouldNotBeNull();

            var refusal = ParseFailure(NoDeviceError);
            MTConnectXml.IsAgentRefusal(refusal).ShouldBeTrue();
            client.CurrentFailure = refusal;
            var deadline = DateTime.UtcNow + TimeSpan.FromSeconds(5);
            while (DateTime.UtcNow <= stamp && DateTime.UtcNow < deadline) await Task.Yield();

            var first = await driver.ReadAsync(["dev1_pos"], Ct);
            await driver.ReadAsync(["dev1_pos"], Ct);

            first.Single().StatusCode.ShouldBe(0x80050000u, "the batch is still Bad");
            var h = driver.GetHealth();
            h.State.ShouldBe(DriverState.Healthy);
            h.LastSuccessfulRead.ShouldNotBeNull().ShouldBeGreaterThan(stamp);
            logger.WarningsSnapshot().Count(w => w.Contains("NO_DEVICE")).ShouldBe(1, "a persistent refusal warns once");
        }
        finally
        {
            client.CurrentFailure = null;
            await driver.ShutdownAsync(CancellationToken.None);
        }
    }

    /// <summary>An answer that is not an MTConnect document at all is NOT marked a refusal (it stays a comms fault).</summary>
    [Fact]
    public void A_garbage_answer_is_not_an_agent_refusal() =>
        MTConnectXml.IsAgentRefusal(ParseFailure("<html><body>proxy error</body></html>")).ShouldBeFalse();

    /// <summary>Review m7: a refusal that recurs AFTER a good read is news again and is logged again.</summary>
    [Fact]
    public async Task A_refusal_recurring_after_a_good_read_is_logged_again()
    {
        var logger = new RecordingDriverLogger();
        var client = CannedAgentClient.FromFixtures();
        var driver = new MTConnectDriver(Opts(), "mt-refusal-again", _ => client, logger);
        await driver.InitializeAsync("{}", Ct);
        try
        {
            var refusal = ParseFailure(NoDeviceError);
            client.CurrentFailure = refusal;
            await driver.ReadAsync(["dev1_pos"], Ct);
            await driver.ReadAsync(["dev1_pos"], Ct);
            logger.WarningsSnapshot().Count(w => w.Contains("NO_DEVICE")).ShouldBe(1, "positive control: deduplicated while it persists");

            client.CurrentFailure = null;
            await driver.ReadAsync(["dev1_pos"], Ct);
            client.CurrentFailure = refusal;
            await driver.ReadAsync(["dev1_pos"], Ct);

            logger.WarningsSnapshot().Count(w => w.Contains("NO_DEVICE")).ShouldBe(2);
        }
        finally
        {
            client.CurrentFailure = null;
            await driver.ShutdownAsync(CancellationToken.None);
        }
    }
}