Phase 1 Streams B–E scaffold + Phase 2 Streams A–C scaffold — 8 new projects with ~70 new tests, all green alongside the 494 v1 IntegrationTests baseline (parity preserved: no v1 tests broken; legacy OtOpcUa.Host untouched). Phase 1 finish: Configuration project (16 entities + 10 enums + DbContext + DesignTimeDbContextFactory + InitialSchema/StoredProcedures/AuthorizationGrants migrations — 8 procs including sp_PublishGeneration with MERGE on ExternalIdReservation per decision #124, sp_RollbackToGeneration cloning rows into a new published generation, sp_ValidateDraft with cross-cluster-namespace + EquipmentUuid-immutability + ZTag/SAPID reservation pre-flight, sp_ComputeGenerationDiff with CHECKSUM-based row signature — plus OtOpcUaNode/OtOpcUaAdmin SQL roles with EXECUTE grants scoped to per-principal-class proc sets and DENY UPDATE/DELETE/INSERT/SELECT on dbo schema); managed DraftValidator covering UNS segment regex, path length, EquipmentUuid immutability across generations, same-cluster namespace binding (decision #122), reservation pre-flight, EquipmentId derivation (decision #125), driver↔namespace compatibility — returning every failing rule in one pass; LiteDB local cache with round-trip + ring pruning + corruption-fast-fail; GenerationApplier with per-entity Added/Removed/Modified diff and dependency-ordered callbacks (namespace → driver → device → equipment → poll-group → tag, Removed before Added); Core project with GenericDriverNodeManager (scaffold for the Phase 2 Galaxy port) and DriverHost lifecycle registry; Server project using Microsoft.Extensions.Hosting BackgroundService replacing TopShelf, with NodeBootstrap that falls back to LiteDB cache when the central DB is unreachable (decision #79); Admin project scaffolded as Blazor Server with Bootstrap 5 sidebar layout, cookie auth, three admin roles (ConfigViewer/ConfigEditor/FleetAdmin), Cluster + Generation services fronting the stored procs. Phase 2 scaffold: Driver.Galaxy.Shared (netstandard2.0) with full MessagePack IPC contract surface — Hello version negotiation, Open/CloseSession, Heartbeat, DiscoverHierarchy + GalaxyObjectInfo/GalaxyAttributeInfo, Read/WriteValues, Subscribe/Unsubscribe/OnDataChange, AlarmSubscribe/Event/Ack, HistoryRead, HostConnectivityStatus, Recycle — plus length-prefixed framing (decision #28) with a 16 MiB cap and thread-safe FrameWriter/FrameReader; Driver.Galaxy.Host (net48) implementing the Tier C cross-cutting protections from driver-stability.md — strict PipeAcl (allow configured server SID only, explicit deny on LocalSystem + Administrators), PipeServer with caller-SID verification via pipe.RunAsClient + WindowsIdentity.GetCurrent and per-process shared-secret Hello, Galaxy-specific MemoryWatchdog (warn at max(1.5×baseline, +200 MB), soft-recycle at max(2×baseline, +200 MB), hard ceiling 1.5 GB, slope ≥5 MB/min over 30-min rolling window), RecyclePolicy (1 soft recycle per hour cap + 03:00 local daily scheduled), PostMortemMmf (1000-entry ring buffer in %ProgramData%\OtOpcUa\driver-postmortem\galaxy.mmf, survives hard crash, readable cross-process), MxAccessHandle : SafeHandle (ReleaseHandle loops Marshal.ReleaseComObject until refcount=0 then calls optional unregister callback), StaPump with responsiveness probe (BlockingCollection dispatcher for Phase 1 — real Win32 GetMessage/DispatchMessage pump slots in with the same semantics when the Galaxy code lift happens), IsExternalInit shim for init setters on .NET 4.8; Driver.Galaxy.Proxy (net10) implementing IDriver + ITagDiscovery forwarding over the IPC channel with MX data-type and security-classification mapping, plus Supervisor pieces — Backoff (5s → 15s → 60s capped, reset-on-stable-run), CircuitBreaker (3 crashes per 5 min opens; 1h → 4h → manual cooldown escalation; sticky alert doesn't auto-clear), HeartbeatMonitor (2s cadence, 3 consecutive misses = host dead per driver-stability.md). Infrastructure: docker SQL Server remapped to host port 14330 to coexist with the native MSSQL14 Galaxy ZB DB instance on 1433; NuGetAuditSuppress applied per-project for two System.Security.Cryptography.Xml advisories that only reach via EF Core Design with PrivateAssets=all (fix ships in 11.0.0-preview); .slnx gains 14 project registrations. Deferred with explicit TODOs in docs/v2/implementation/phase-2-partial-exit-evidence.md: Phase 1 Stream E Admin UI pages (Generations listing + draft-diff-publish, Equipment CRUD with OPC 40010 fields, UNS Areas/Lines tabs, ACLs + permission simulator, Generic JSON config editor, SignalR real-time, Release-Reservation + Merge-Equipment workflows, LDAP login page, AppServer smoke test per decision #142), Phase 2 Stream D (Galaxy MXAccess code lift out of legacy OtOpcUa.Host, dual-service installer, appsettings → DriverConfig migration script, legacy Host deletion — blocked by parity), Phase 2 Stream E (v1 IntegrationTests against v2 topology, Client.CLI walkthrough diff, four 2026-04-13 stability findings regression tests, adversarial review — requires live MXAccess runtime).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-17 21:35:25 -04:00
parent fc0ce36308
commit 01fd90c178
128 changed files with 12352 additions and 4 deletions
--- a/src/ZB.MOM.WW.OtOpcUa.Configuration/LocalCache/LiteDbConfigCache.cs
+++ b/src/ZB.MOM.WW.OtOpcUa.Configuration/LocalCache/LiteDbConfigCache.cs
@@ -0,0 +1,89 @@
+using LiteDB;
+
+namespace ZB.MOM.WW.OtOpcUa.Configuration.LocalCache;
+
+/// <summary>
+///     LiteDB-backed <see cref="ILocalConfigCache"/>. One file per node (default
+///     <c>config_cache.db</c>), one collection per snapshot. Corruption surfaces as
+///     <see cref="LocalConfigCacheCorruptException"/> on construction or read — callers should
+///     delete and re-fetch from the central DB (decision #80).
+/// </summary>
+public sealed class LiteDbConfigCache : ILocalConfigCache, IDisposable
+{
+    private const string CollectionName = "generations";
+    private readonly LiteDatabase _db;
+    private readonly ILiteCollection<GenerationSnapshot> _col;
+
+    public LiteDbConfigCache(string dbPath)
+    {
+        // LiteDB can be tolerant of header-only corruption at construction time (it may overwrite
+        // the header and "recover"), so we force a write + read probe to fail fast on real corruption.
+        try
+        {
+            _db = new LiteDatabase(new ConnectionString { Filename = dbPath, Upgrade = true });
+            _col = _db.GetCollection<GenerationSnapshot>(CollectionName);
+            _col.EnsureIndex(s => s.ClusterId);
+            _col.EnsureIndex(s => s.GenerationId);
+            _ = _col.Count();
+        }
+        catch (Exception ex) when (ex is LiteException or InvalidDataException or IOException
+                                      or NotSupportedException or UnauthorizedAccessException
+                                      or ArgumentOutOfRangeException or FormatException)
+        {
+            _db?.Dispose();
+            throw new LocalConfigCacheCorruptException(
+                $"LiteDB cache at '{dbPath}' is corrupt or unreadable — delete the file and refetch from the central DB.",
+                ex);
+        }
+    }
+
+    public Task<GenerationSnapshot?> GetMostRecentAsync(string clusterId, CancellationToken ct = default)
+    {
+        ct.ThrowIfCancellationRequested();
+        var snapshot = _col
+            .Find(s => s.ClusterId == clusterId)
+            .OrderByDescending(s => s.GenerationId)
+            .FirstOrDefault();
+        return Task.FromResult<GenerationSnapshot?>(snapshot);
+    }
+
+    public Task PutAsync(GenerationSnapshot snapshot, CancellationToken ct = default)
+    {
+        ct.ThrowIfCancellationRequested();
+        // upsert by (ClusterId, GenerationId) — replace in place if already cached
+        var existing = _col
+            .Find(s => s.ClusterId == snapshot.ClusterId && s.GenerationId == snapshot.GenerationId)
+            .FirstOrDefault();
+
+        if (existing is null)
+            _col.Insert(snapshot);
+        else
+        {
+            snapshot.Id = existing.Id;
+            _col.Update(snapshot);
+        }
+
+        return Task.CompletedTask;
+    }
+
+    public Task PruneOldGenerationsAsync(string clusterId, int keepLatest = 10, CancellationToken ct = default)
+    {
+        ct.ThrowIfCancellationRequested();
+        var doomed = _col
+            .Find(s => s.ClusterId == clusterId)
+            .OrderByDescending(s => s.GenerationId)
+            .Skip(keepLatest)
+            .Select(s => s.Id)
+            .ToList();
+
+        foreach (var id in doomed)
+            _col.Delete(id);
+
+        return Task.CompletedTask;
+    }
+
+    public void Dispose() => _db.Dispose();
+}
+
+public sealed class LocalConfigCacheCorruptException(string message, Exception inner)
+    : Exception(message, inner);