fix(review): full code-review remediation — 5 High + Medium/Low across 16 modules
Remediation from the full per-module code review at 4307c381 (findings recorded
separately in code-reviews/).
Highs fixed:
- DeploymentManager-025/SiteRuntime-031: stop broadcasting notification lists + SMTP
configs (incl. credentials) to sites; site purges already-persisted rows on apply
(enforces the central-only delivery design; clears plaintext SMTP creds at rest).
- DataConnectionLayer-023: guard the native-alarm subscribe path against the
mid-flight-unsubscribe adapter-feed leak (mirrors the DCL-021 tag-path fix).
- SiteEventLogging-024: normalize From/To query bounds to UTC (the -016 fix the
audit trail claimed but never committed).
- KpiHistory-001: add an in-flight guard to the recorder sample tick.
- ScriptAnalysis-001: harden the trust analyzer's TPA-absent fallback (resolve
forbidden anchors in the minimal reference set; warn on degraded mode) — anchors
added to validation references only, never the compile gate.
(InboundAPI-026 left to the feat/ipsen-movein effort per owner decision.)
Medium/Low: DM-026 deterministic deploy-status tiebreaker; SR-027/028/029/030
native-alarm leak/phantom-active/delete-during-redeploy fixes; AL-013/014/016;
TE-024 (folder-mutation audit rows now persisted)/025; SF-025 gauge-provider
clear-on-stop; ESG-025/026; SEC-023/024/025; SCA-007/008/009; plus doc/test
accuracy COM-023/024, HOST-025/026, HM-024/025, NS-027/028.
Full-solution build 0 warnings; ~3560 tests across 18 touched suites green.
This commit is contained in:
@@ -528,7 +528,28 @@ public class DeploymentManagerActor : ReceiveActor, IWithTimers
|
||||
{
|
||||
var instanceName = command.InstanceUniqueName;
|
||||
|
||||
if (_instanceActors.TryGetValue(instanceName, out var actor))
|
||||
// SiteRuntime-029: a disable arriving mid-redeploy must cancel the buffered
|
||||
// redeploy. Otherwise HandleTerminated re-creates the Instance Actor and
|
||||
// re-stores its config with isEnabled: true when the predecessor terminates,
|
||||
// silently reverting the operator's disable back to enabled. Mirror the
|
||||
// last-write-wins handling in HandleDeploy/HandleDelete: drop the pending
|
||||
// command (so HandleTerminated returns early), clear the shadow, and tell the
|
||||
// displaced deployer it was superseded. The disable itself still persists
|
||||
// is_enabled = false below, which becomes the durable state.
|
||||
if (_terminatingActorsByName.TryGetValue(instanceName, out var terminatingRef))
|
||||
{
|
||||
if (_pendingRedeploys.Remove(terminatingRef, out var pending))
|
||||
{
|
||||
pending.OriginalSender.Tell(new DeploymentStatusResponse(
|
||||
pending.Command.DeploymentId,
|
||||
instanceName,
|
||||
DeploymentStatus.Failed,
|
||||
$"superseded by disable of {instanceName} before redeploy finished terminating",
|
||||
DateTimeOffset.UtcNow));
|
||||
}
|
||||
_terminatingActorsByName.Remove(instanceName);
|
||||
}
|
||||
else if (_instanceActors.TryGetValue(instanceName, out var actor))
|
||||
{
|
||||
Context.Stop(actor);
|
||||
_instanceActors.Remove(instanceName);
|
||||
@@ -628,12 +649,45 @@ public class DeploymentManagerActor : ReceiveActor, IWithTimers
|
||||
{
|
||||
var instanceName = command.InstanceUniqueName;
|
||||
|
||||
if (_instanceActors.TryGetValue(instanceName, out var actor))
|
||||
// SiteRuntime-029: a delete arriving while a redeploy is still terminating must
|
||||
// be authoritative over the mid-redeploy bookkeeping. HandleDeploy already
|
||||
// removed the instance from _instanceActors and buffered a PendingRedeploy
|
||||
// keyed by the terminating ref. If we fall straight through to the
|
||||
// _instanceActors miss + unconditional decrement, the buffered redeploy is
|
||||
// left intact — so when Terminated fires, HandleTerminated calls
|
||||
// ApplyDeployment(isRedeploy: true) and RESURRECTS the just-deleted instance,
|
||||
// with the counter now inconsistent. Cancel the pending redeploy first.
|
||||
var wasPresent = false;
|
||||
if (_terminatingActorsByName.TryGetValue(instanceName, out var terminatingRef))
|
||||
{
|
||||
// Drop the buffered command so HandleTerminated's _pendingRedeploys.Remove
|
||||
// misses and it returns early (no resurrection). Clear the shadow too.
|
||||
if (_pendingRedeploys.Remove(terminatingRef, out var pending))
|
||||
{
|
||||
pending.OriginalSender.Tell(new DeploymentStatusResponse(
|
||||
pending.Command.DeploymentId,
|
||||
instanceName,
|
||||
DeploymentStatus.Failed,
|
||||
$"superseded by delete of {instanceName} before redeploy finished terminating",
|
||||
DateTimeOffset.UtcNow));
|
||||
}
|
||||
_terminatingActorsByName.Remove(instanceName);
|
||||
// The terminating predecessor is already being stopped by HandleDeploy;
|
||||
// no Context.Stop needed here.
|
||||
wasPresent = true;
|
||||
}
|
||||
else if (_instanceActors.TryGetValue(instanceName, out var actor))
|
||||
{
|
||||
Context.Stop(actor);
|
||||
_instanceActors.Remove(instanceName);
|
||||
wasPresent = true;
|
||||
}
|
||||
_totalDeployedCount = Math.Max(0, _totalDeployedCount - 1);
|
||||
|
||||
// SiteRuntime-029: only decrement when the instance was actually present
|
||||
// (live in _instanceActors OR mid-redeploy in _terminatingActorsByName).
|
||||
// A delete for a wholly-unknown instance must not drive the count negative.
|
||||
if (wasPresent)
|
||||
_totalDeployedCount = Math.Max(0, _totalDeployedCount - 1);
|
||||
UpdateInstanceCounts();
|
||||
|
||||
var sender = Sender;
|
||||
@@ -1379,14 +1433,15 @@ public class DeploymentManagerActor : ReceiveActor, IWithTimers
|
||||
}
|
||||
}
|
||||
|
||||
// WP-33: Store notification lists
|
||||
if (command.NotificationLists != null)
|
||||
{
|
||||
foreach (var nl in command.NotificationLists)
|
||||
{
|
||||
await _storage.StoreNotificationListAsync(nl.Name, nl.RecipientEmails);
|
||||
}
|
||||
}
|
||||
// DeploymentManager-025 / SiteRuntime-031: notification lists and SMTP
|
||||
// configuration are central-only — sites store-and-forward notifications
|
||||
// to central and never deliver over SMTP. Central no longer ships these
|
||||
// (the DeployArtifactsCommand fields stay for additive compatibility but
|
||||
// are always null), so the site neither persists them nor reads them.
|
||||
// Purge any rows a prior (pre-fix) build may have written — including the
|
||||
// plaintext SMTP password — so existing exposure is cleared, not just
|
||||
// future writes. Purge is idempotent and runs on every artifact apply.
|
||||
await _storage.PurgeCentralOnlyNotificationConfigAsync();
|
||||
|
||||
// Store data connection definitions (OPC UA endpoints, etc.)
|
||||
if (command.DataConnections != null)
|
||||
@@ -1413,16 +1468,8 @@ public class DeploymentManagerActor : ReceiveActor, IWithTimers
|
||||
self.Tell(new ApplyArtifactDataConnectionsToDcl(command.DataConnections));
|
||||
}
|
||||
|
||||
// Store SMTP configurations
|
||||
if (command.SmtpConfigurations != null)
|
||||
{
|
||||
foreach (var smtp in command.SmtpConfigurations)
|
||||
{
|
||||
await _storage.StoreSmtpConfigurationAsync(
|
||||
smtp.Name, smtp.Server, smtp.Port, smtp.AuthMode,
|
||||
smtp.FromAddress, smtp.Username, smtp.Password, smtp.OAuthConfig);
|
||||
}
|
||||
}
|
||||
// DeploymentManager-025 / SiteRuntime-031: SMTP configuration is
|
||||
// central-only and is never stored on a site (see the purge above).
|
||||
|
||||
// Replicate artifacts to standby node
|
||||
_replicationActor?.Tell(new ReplicateArtifacts(command));
|
||||
|
||||
Reference in New Issue
Block a user