Files
lmxopcua/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Calculation/CalculationDriverFactoryExtensions.cs
T
Joseph Doherty 6aa5edaf30 fix(scripting): only timeouts are quarantine strikes; alarm Bad annotation once per bucket change (fix round 1 I1, I3)
- I1 ScriptRunGuard: a run refused because the previous one is still
  executing is a Bad publish plus otopcua.script.run_refused, and no longer
  a quarantine strike. Only a timeout (and an allocation breach) counts;
  a refusal neither adds to nor resets the timeout streak; a completed run
  (value or throw) resets it. On a 1 Hz trigger with a 2 s budget a single
  4 s overrun is one timeout plus two refusals and must not quarantine.
  Tests updated across the guard, the alarm engine, the Calculation
  evaluator and the VT evaluator, plus
  Refusals_neither_count_toward_nor_reset_the_timeout_streak.
- I3 ScriptedAlarmEngine: the quality bucket is tracked only after the
  predicate completes (or in the inputs-not-ready path), so the tracked
  bucket is the last one annotated. A refused or quarantined predicate
  used to re-track the input bucket Good before the attempt and then flip
  it Bad, emitting QualityChanged on every push. The run-guard tests now
  count emissions (exactly 1 across N pushes, refused and quarantined
  cases), with a healthy sibling's dispatch count as the positive control
  that every push was processed. Both were red before the fix.

Refs #734

Claude-Session: https://claude.ai/code/session_01Ub9hGmYLQvn9XETzw7CMsT
2026-10-22 13:26:12 -04:00

114 lines
6.3 KiB
C#

using System.Text.Json;
using System.Text.Json.Serialization;
using Microsoft.Extensions.Logging;
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
using ZB.MOM.WW.OtOpcUa.Core.Hosting;
using ZB.MOM.WW.OtOpcUa.Core.Scripting;
namespace ZB.MOM.WW.OtOpcUa.Driver.Calculation;
/// <summary>
/// Static factory registration helper for <see cref="CalculationDriver"/>. The Server's
/// <c>DriverFactoryBootstrap</c> calls <see cref="Register"/> once at startup; the bootstrapper then
/// materialises <c>Calculation</c> DriverInstance rows into live driver instances. Mirrors
/// <c>ModbusDriverFactoryExtensions</c>, with the addition of a <see cref="ScriptRootLogger"/> so a
/// script failure fans out onto the <c>script-logs</c> topic (via the root logger's
/// <c>ScriptLogTopicSink</c>) — the calc driver has no Akka access of its own.
/// </summary>
public static class CalculationDriverFactoryExtensions
{
/// <summary>The <c>DriverInstance.DriverType</c> string this factory registers under.</summary>
public const string DriverTypeName = "Calculation";
private static readonly JsonSerializerOptions JsonOptions = new()
{
PropertyNameCaseInsensitive = true,
ReadCommentHandling = JsonCommentHandling.Skip,
AllowTrailingCommas = true,
Converters = { new JsonStringEnumConverter() },
};
/// <summary>
/// Register the Calculation factory with the driver registry. The optional
/// <paramref name="loggerFactory"/> + <paramref name="scriptRoot"/> are captured at registration
/// time; both may be null (the guard test invokes <c>Register(registry)</c> reflectively with the
/// trailing parameters defaulted), in which case the driver runs with the null logger + a no-op
/// script-logger.
/// </summary>
/// <param name="registry">The driver factory registry to register with.</param>
/// <param name="loggerFactory">Optional logger factory for per-instance diagnostics loggers.</param>
/// <param name="scriptRoot">Optional root script logger (fans failure entries onto the <c>script-logs</c> topic).</param>
public static void Register(
DriverFactoryRegistry registry,
ILoggerFactory? loggerFactory = null,
ScriptRootLogger? scriptRoot = null)
{
ArgumentNullException.ThrowIfNull(registry);
registry.Register(DriverTypeName, (id, json) => CreateInstance(id, json, loggerFactory, scriptRoot));
}
/// <summary>Public overload for the Server-side bootstrapper + test consumers.</summary>
/// <param name="driverInstanceId">The unique identifier for the driver instance.</param>
/// <param name="driverConfigJson">The merged driver config JSON (carries the <c>RawTags</c> array).</param>
/// <returns>The constructed <see cref="CalculationDriver"/>.</returns>
public static CalculationDriver CreateInstance(string driverInstanceId, string driverConfigJson)
=> CreateInstance(driverInstanceId, driverConfigJson, loggerFactory: null, scriptRoot: null);
/// <summary>Logger/script-logger-aware overload — used by <see cref="Register"/>'s closure via DI.</summary>
/// <param name="driverInstanceId">The unique identifier for the driver instance.</param>
/// <param name="driverConfigJson">The merged driver config JSON (carries the <c>RawTags</c> array).</param>
/// <param name="loggerFactory">Optional logger factory for per-instance diagnostics loggers.</param>
/// <param name="scriptRoot">Optional root script logger for failure fan-out.</param>
/// <returns>The constructed <see cref="CalculationDriver"/>.</returns>
public static CalculationDriver CreateInstance(
string driverInstanceId, string driverConfigJson,
ILoggerFactory? loggerFactory, ScriptRootLogger? scriptRoot)
{
ArgumentException.ThrowIfNullOrWhiteSpace(driverInstanceId);
ArgumentException.ThrowIfNullOrWhiteSpace(driverConfigJson);
var dto = JsonSerializer.Deserialize<CalculationDriverConfigDto>(driverConfigJson, JsonOptions)
?? throw new InvalidOperationException(
$"Calculation driver config for '{driverInstanceId}' deserialised to null");
// Run-guard knobs are optional and default to the node-wide ScriptingOptions defaults; only an
// explicitly authored key overrides one (so a config carrying neither binds Scripting = null).
ScriptingOptions? scripting = null;
if (dto.MaxAllocBytesPerRun is not null || dto.QuarantineAfterConsecutiveTimeouts is not null)
{
scripting = new ScriptingOptions();
if (dto.MaxAllocBytesPerRun is { } alloc) scripting.MaxAllocBytesPerRun = alloc;
if (dto.QuarantineAfterConsecutiveTimeouts is { } n) scripting.QuarantineAfterConsecutiveTimeouts = n;
}
var options = new CalculationDriverOptions
{
RawTags = dto.RawTags is { Count: > 0 } ? [.. dto.RawTags] : [],
RunTimeout = dto.RunTimeoutMs is { } ms && ms > 0
? TimeSpan.FromMilliseconds(ms) : TimeSpan.FromSeconds(2),
Scripting = scripting,
};
return new CalculationDriver(
options, driverInstanceId, scriptRoot,
logger: loggerFactory?.CreateLogger<CalculationDriver>());
}
/// <summary>The merged-config DTO the calc factory binds from. The Calculation driver has no
/// backend/endpoint config — only the injected raw tags (+ an optional evaluation-timeout override).</summary>
internal sealed class CalculationDriverConfigDto
{
/// <summary>The driver's authored raw calc tags (RawPath + TagConfig blob + WriteIdempotent + DeviceName).</summary>
public List<RawTagEntry>? RawTags { get; init; }
/// <summary>Optional per-script evaluation wall-clock budget override, in milliseconds (default 2000).</summary>
public int? RunTimeoutMs { get; init; }
/// <summary>Optional run-guard allocation budget per script run, in bytes (default 64 MB; ≤ 0 disables).</summary>
public long? MaxAllocBytesPerRun { get; init; }
/// <summary>Optional run-guard quarantine threshold: consecutive timeouts (refusals do not count) before a tag's script stops being evaluated (default 3).</summary>
public int? QuarantineAfterConsecutiveTimeouts { get; init; }
}
}