Auto: ablegacy-12 — auto-demote on comm failure

Closes #255

scripts/e2e/test-ablegacy.ps1

@@ -39,6 +39,21 @@
   client may have bumped it by more, so the comparison is `>=`). NodeId form:
   ns=<n>;s=AbLegacy/<gateway>/_Diagnostics/RequestCount. Mirrors the
   -SystemConnectionStatusNodeId knob on test-abcip.ps1.
+
+.PARAMETER DiagnosticsDemoteCountNodeId
+  Optional NodeId for the synthetic _Diagnostics/<host>/DemoteCount variable
+  emitted by AB Legacy discovery (PR ablegacy-12 / #255). When supplied, the
+  script runs the auto-demote assertion: kills the simulator container so
+  reads start failing, hammers the user-tag BridgeNodeId at least
+  FailureThreshold times to trip the demotion, then reads the diagnostic
+  counter and asserts the value increased by >= 1. NodeId form:
+  ns=<n>;s=AbLegacy/<gateway>/_Diagnostics/DemoteCount. The simulator
+  must support `docker stop otopcua-ab-server-slc500` for the kill stage.
+
+.PARAMETER FailureThresholdForDemote
+  Failure threshold the server is configured with (default 3). The
+  demote assertion writes/reads N+1 times against the killed simulator
+  to guarantee the threshold trips even if some reads beat the kill.
 #>
 
 param(
@@ -47,7 +62,9 @@ param(
     [string]$Address = "N7:5",
     [string]$OpcUaUrl = "opc.tcp://localhost:4840",
     [Parameter(Mandatory)] [string]$BridgeNodeId,
-    [string]$DiagnosticsRequestCountNodeId
+    [string]$DiagnosticsRequestCountNodeId,
+    [string]$DiagnosticsDemoteCountNodeId,
+    [int]$FailureThresholdForDemote = 3
 )
 
 $ErrorActionPreference = "Stop"
@@ -245,5 +262,67 @@ finally {
     Remove-Item -Path $importJsonPath -ErrorAction SilentlyContinue
 }
 
+# PR ablegacy-12 / #255 — auto-demote round-trip. Kill the simulator container,
+# hammer the bridge NodeId past the failure threshold, then assert the
+# DemoteCount diagnostic incremented. Restart the simulator at the end so the
+# next run gets a clean baseline. Gated on -DiagnosticsDemoteCountNodeId so
+# environments without docker-side control of the simulator can opt out.
+if ($DiagnosticsDemoteCountNodeId) {
+    Write-Header "AutoDemote (kill simulator + observe DemoteCount from $DiagnosticsDemoteCountNodeId)"
+    $baselineDemoteOut = & $opcUaCli.File @($opcUaCli.PrefixArgs) `
+        @("read", "-u", $OpcUaUrl, "-n", $DiagnosticsDemoteCountNodeId) 2>&1
+    $baselineDemote = 0
+    if (($baselineDemoteOut -join "`n") -match '(\d+)') { $baselineDemote = [int64]$Matches[1] }
+
+    # Best-effort container kill — prefer the slc500 profile name; fall back to
+    # micrologix / plc5 in case the operator pointed the e2e at a different family.
+    $simContainers = @("otopcua-ab-server-slc500", "otopcua-ab-server-micrologix", "otopcua-ab-server-plc5")
+    $killed = $false
+    foreach ($c in $simContainers) {
+        $stop = docker stop $c 2>$null
+        if ($LASTEXITCODE -eq 0 -and $stop) {
+            Write-Host "Stopped $c"
+            $killed = $true
+            break
+        }
+    }
+    if (-not $killed) {
+        Write-Fail "AutoDemote: no ab_server container found via 'docker stop' — skipping demote assertion"
+        $results += @{ Passed = $false; Reason = "no simulator container to kill" }
+    }
+    else {
+        # Hammer past the threshold. Each read against a now-unreachable simulator
+        # surfaces BadCommunicationError; FailureThreshold consecutive ones trip
+        # the demotion. We add 2 extra to absorb timing slack (one read may be
+        # in-flight when the kill lands).
+        $hammerCount = $FailureThresholdForDemote + 2
+        for ($i = 0; $i -lt $hammerCount; $i++) {
+            & $opcUaCli.File @($opcUaCli.PrefixArgs) `
+                @("read", "-u", $OpcUaUrl, "-n", $BridgeNodeId) 2>&1 | Out-Null
+        }
+
+        Start-Sleep -Seconds 1
+
+        $afterDemoteOut = & $opcUaCli.File @($opcUaCli.PrefixArgs) `
+            @("read", "-u", $OpcUaUrl, "-n", $DiagnosticsDemoteCountNodeId) 2>&1
+        $afterDemote = 0
+        if (($afterDemoteOut -join "`n") -match '(\d+)') { $afterDemote = [int64]$Matches[1] }
+
+        $deltaDemote = $afterDemote - $baselineDemote
+        if ($deltaDemote -ge 1) {
+            Write-Pass "AutoDemote DemoteCount delta $deltaDemote >= 1 after $hammerCount failed reads"
+            $results += @{ Passed = $true }
+        } else {
+            Write-Fail "AutoDemote DemoteCount delta $deltaDemote < 1 (baseline=$baselineDemote after=$afterDemote)"
+            $results += @{ Passed = $false; Reason = "demote delta $deltaDemote" }
+        }
+
+        # Restart the simulator so subsequent test runs have a clean baseline.
+        # Best-effort — if docker-compose isn't on the path the operator can
+        # bring it back manually via the Docker/docker-compose.yml profile.
+        try { docker start (docker ps -aq -f "name=otopcua-ab-server-") | Out-Null } catch { }
+    }
+}
+
 Write-Summary -Title "AB Legacy e2e" -Results $results
 if ($results | Where-Object { -not $_.Passed }) { exit 1 }

scripts/smoke/seed-ablegacy-smoke.sql

@@ -96,7 +96,12 @@ VALUES (@Gen, @DrvId, @ClusterId, @NsId, 'ablegacy-smoke', 'AbLegacy', N'{
       "PlcFamily": "Slc500",
       "DeviceName": "slc-500",
       "TimeoutMs": 500,
-      "Retries": 1
+      "Retries": 1,
+      "Demote": {
+        "FailureThreshold": 3,
+        "DemoteForMs": 30000,
+        "Enabled": true
+      }
     }
   ],
   "Probe": { "Enabled": true, "IntervalMs": 5000, "TimeoutMs": 2000, "ProbeAddress": "S:0" },
@@ -155,7 +160,15 @@ PRINT '      e.g. "ab://<plc-ip>:44818/" and re-run this seed.';
 PRINT '';
 PRINT 'PR ablegacy-10 / #253 — diagnostic counters auto-emit per device under';
 PRINT '   AbLegacy/<host>/_Diagnostics/<name>. No dbo.Tag rows needed — the';
-PRINT '   driver registers them at DiscoverAsync time. Seven counters per device:';
+PRINT '   driver registers them at DiscoverAsync time. Nine counters per device:';
 PRINT '   RequestCount, ResponseCount, ErrorCount, RetryCount, LastErrorCode,';
-PRINT '   LastErrorMessage, CommFailures. See docs/drivers/AbLegacy-Diagnostics.md';
-PRINT '   for the full surface + reset semantics.';
+PRINT '   LastErrorMessage, CommFailures, DemoteCount, LastDemotedUtc. See';
+PRINT '   docs/drivers/AbLegacy-Diagnostics.md for the full surface + reset';
+PRINT '   semantics.';
+PRINT '';
+PRINT 'PR ablegacy-12 / #255 — auto-demote on comm failure: 3 consecutive';
+PRINT '   failed reads / probes mark the device Demoted for DemoteFor=PT30S';
+PRINT '   (30 s); reads against a demoted device short-circuit with';
+PRINT '   BadCommunicationError so one slow PLC can''t starve the driver.';
+PRINT '   Tune via the Demote block on each Devices[] row. DemoteCount +';
+PRINT '   LastDemotedUtc on the _Diagnostics folder surface flapping links.';