Merge pull request 'Allowed IPs take the full settings reload after a write' (#42) from fix/allowed-ip-reload into main

write_reload_target sent AllowedIp writes to the blocked-IP reload, but
that reload rebuilds only BlockedIps. Allowed IPs are parsed into the
core's security settings (Security::parse), which only a full reload
rebuilds, so an AllowedIp write reported x:settingsReload applied: true
while the change wasn't live until the next full reload.

AllowedIp now maps to the full reload, like the other settings objects;
BlockedIp keeps its targeted reload.

system::auto_reload::settings_reload_tests now creates an allowed IP
over JMAP and checks that is_ip_allowed sees it with no ReloadSettings,
and that destroying it takes it out again. On main it fails ("allowed
IP not in the running settings").

crates/common/src/cache/reload.rs

@@ -13,7 +13,7 @@ use crate::{
         storage::Storage,
         telemetry::Telemetry,
     },
-    ipc::{QueueEvent, RegistryChange},
+    ipc::{BroadcastEvent, QueueEvent, RegistryChange},
     network::security::{BlockedIps, IpWithTtl},
 };
 use ahash::AHashMap;
@@ -232,3 +232,206 @@ fn error_object(error: &Error) -> Option<ObjectId> {
         Error::Internal { object_id, .. } => *object_id,
     }
 }
+
+// inbuxa: upstream applied a registry write to the running settings only on
+// an explicit x:Action ReloadSettings (Directory and Authentication aside), so
+// a new MtaDeliverySchedule, say, stayed unknown ("Queue strategy not found")
+// until someone reloaded. Writes to objects the settings are built from now
+// reload them, here and across the cluster, as ReloadSettings does.
+
+/// Coalesces the full reloads that registry writes trigger: a write waits for
+/// a reload that started after it was stored, and joins one if it can, so a
+/// burst of writes costs a reload or two rather than one each.
+#[derive(Default)]
+pub struct SettingsReloadGate {
+    requested: std::sync::atomic::AtomicU64,
+    state: tokio::sync::Mutex<SettingsReloadState>,
+}
+
+#[derive(Default)]
+struct SettingsReloadState {
+    completed: u64,
+    refused: Option<String>,
+}
+
+/// The reload a write to `object` calls for: the object to reload, or None
+/// when the running settings don't hold that object (accounts, domains and
+/// other data read as needed, stores, which take a restart, and objects with
+/// reload actions of their own, such as applications). Blocked IPs have a
+/// reload of their own; allowed IPs take the full one.
+pub fn write_reload_target(object: ObjectType) -> Option<ObjectType> {
+    match object {
+        ObjectType::Certificate => Some(ObjectType::Certificate),
+        ObjectType::MemoryLookupKey
+        | ObjectType::MemoryLookupKeyValue
+        | ObjectType::HttpLookup
+        | ObjectType::StoreLookup => Some(ObjectType::StoreLookup),
+        ObjectType::BlockedIp => Some(ObjectType::BlockedIp),
+        // Allowed IPs are part of the core's security settings
+        // (Security::parse), which only a full reload rebuilds; the blocked-IP
+        // reload doesn't touch them
+        ObjectType::AllowedIp
+        | ObjectType::AcmeProvider
+        | ObjectType::AddressBook
+        | ObjectType::AiModel
+        | ObjectType::Asn
+        | ObjectType::Authentication
+        | ObjectType::Cache
+        | ObjectType::Calendar
+        | ObjectType::CalendarAlarm
+        | ObjectType::CalendarScheduling
+        | ObjectType::ClusterRole
+        | ObjectType::DataRetention
+        | ObjectType::Directory
+        | ObjectType::DkimReportSettings
+        | ObjectType::DmarcReportSettings
+        | ObjectType::DnsResolver
+        | ObjectType::DsnReportSettings
+        | ObjectType::Email
+        | ObjectType::EventTracingLevel
+        | ObjectType::FileStorage
+        | ObjectType::Http
+        | ObjectType::HttpForm
+        | ObjectType::Imap
+        | ObjectType::Jmap
+        | ObjectType::Metrics
+        | ObjectType::MtaConnectionStrategy
+        | ObjectType::MtaDeliverySchedule
+        | ObjectType::MtaExtensions
+        | ObjectType::MtaHook
+        | ObjectType::MtaInboundSession
+        | ObjectType::MtaInboundThrottle
+        | ObjectType::MtaMilter
+        | ObjectType::MtaOutboundStrategy
+        | ObjectType::MtaOutboundThrottle
+        | ObjectType::MtaQueueQuota
+        | ObjectType::MtaRoute
+        | ObjectType::MtaStageAuth
+        | ObjectType::MtaStageConnect
+        | ObjectType::MtaStageData
+        | ObjectType::MtaStageEhlo
+        | ObjectType::MtaStageMail
+        | ObjectType::MtaStageRcpt
+        | ObjectType::MtaSts
+        | ObjectType::MtaTlsStrategy
+        | ObjectType::MtaVirtualQueue
+        | ObjectType::NetworkListener
+        | ObjectType::OidcProvider
+        | ObjectType::ReportSettings
+        | ObjectType::Search
+        | ObjectType::Security
+        | ObjectType::SenderAuth
+        | ObjectType::Sharing
+        | ObjectType::SieveSystemInterpreter
+        | ObjectType::SieveSystemScript
+        | ObjectType::SieveUserInterpreter
+        | ObjectType::SieveUserScript
+        | ObjectType::SpamClassifier
+        | ObjectType::SpamDnsblServer
+        | ObjectType::SpamDnsblSettings
+        | ObjectType::SpamFileExtension
+        | ObjectType::SpamPyzor
+        | ObjectType::SpamRule
+        | ObjectType::SpamSettings
+        | ObjectType::SpamTag
+        | ObjectType::SpfReportSettings
+        | ObjectType::SystemSettings
+        | ObjectType::TaskManager
+        | ObjectType::TlsReportSettings
+        | ObjectType::Tracer
+        | ObjectType::WebDav
+        | ObjectType::WebHook => Some(object),
+        _ => None,
+    }
+}
+
+impl Server {
+    /// Applies a stored registry write to `object` to the running settings,
+    /// and on success tells the other nodes to do the same. Returns None when
+    /// the write needs no reload, Some(Ok(())) when it was applied, and
+    /// Some(Err(reason)) when the reload was refused (the write stays stored;
+    /// ReloadSettings reports the same errors).
+    pub async fn reload_after_write(&self, object: ObjectType) -> Option<Result<(), String>> {
+        let target = write_reload_target(object)?;
+        let change = RegistryChange::Reload(target);
+
+        if matches!(
+            target,
+            ObjectType::Certificate | ObjectType::StoreLookup | ObjectType::BlockedIp
+        ) {
+            // Cheap, and limited to their own objects
+            let result = self.reload_and_broadcast(change).await;
+            return Some(result);
+        }
+
+        let gate = &self.inner.data.settings_reload;
+        let ticket = gate
+            .requested
+            .fetch_add(1, std::sync::atomic::Ordering::SeqCst)
+            + 1;
+        let mut state = gate.state.lock().await;
+        if state.completed >= ticket {
+            // A reload that started after this write was stored has run
+            return Some(state.refused.clone().map_or(Ok(()), Err));
+        }
+        let covers = gate.requested.load(std::sync::atomic::Ordering::SeqCst);
+        let result = self.reload_and_broadcast(change).await;
+        state.completed = covers;
+        state.refused = result.clone().err();
+        Some(result)
+    }
+
+    async fn reload_and_broadcast(&self, change: RegistryChange) -> Result<(), String> {
+        match Box::pin(self.reload_registry(change)).await {
+            Ok(reload) if !reload.has_errors() => {
+                reload.log();
+                self.cluster_broadcast(BroadcastEvent::RegistryChange(change))
+                    .await;
+                Ok(())
+            }
+            Ok(reload) => {
+                reload.log();
+                let reason = describe_reload_errors(&reload.errors);
+                trc::event!(
+                    Registry(trc::RegistryEvent::BuildWarning),
+                    Details = "Settings didn't reload after a registry write",
+                    Reason = reason.clone(),
+                );
+                Err(reason)
+            }
+            Err(err) => {
+                let reason = err.to_string();
+                trc::error!(err.details("Failed to reload settings after a registry write"));
+                Err(reason)
+            }
+        }
+    }
+}
+
+/// inbuxa: a refused reload's errors in a sentence: the first one, naming its
+/// object, and how many more there are.
+pub fn describe_reload_errors(errors: &[Error]) -> String {
+    let mut description = match errors.first() {
+        Some(Error::Build { object_id, message }) => format!("{object_id}: {message}"),
+        Some(Error::Validation { object_id, errors }) => format!(
+            "{object_id}: {}",
+            errors
+                .iter()
+                .map(|err| err.to_string())
+                .collect::<Vec<_>>()
+                .join("; ")
+        ),
+        Some(Error::Internal {
+            object_id: Some(object_id),
+            error,
+        }) => format!("{object_id}: {error}"),
+        Some(Error::Internal { error, .. }) => error.to_string(),
+        Some(Error::NotFound { object_id }) => format!("{object_id} was not found"),
+        None => String::new(),
+    };
+    let more = errors.len().saturating_sub(1);
+    if more > 0 {
+        description.push_str(&format!(" ({more} more in the server log.)"));
+    }
+    description
+}

crates/common/src/config/inner.rs

@@ -93,6 +93,7 @@ impl Data {
             registry_id_gen: id_generator.clone(),
             span_id_gen: id_generator,
             queue_status: true.into(),
+            settings_reload: Default::default(),
             applications,
             logos: Default::default(),
             smtp_connectors: TlsConnectors::try_new().failed("Failed to build TLS connectors"),
@@ -235,6 +236,7 @@ impl Default for Data {
             span_id_gen: Default::default(),
             registry_id_gen: Default::default(),
             queue_status: true.into(),
+            settings_reload: Default::default(),
             applications: WebApplications::new(),
             logos: Default::default(),
             smtp_connectors: TlsConnectors::try_new().unwrap(),

crates/common/src/ipc.rs

@@ -345,8 +345,13 @@ pub struct TaskLocks {
 }
 
 impl TaskLocks {
-    /// How long a task lock lasts, in seconds, unless it is released first.
+    /// How long a task lock lasts, in seconds, unless it is released first
-    pub const DEFAULT_EXPIRY: u64 = 60 * 60;
+    /// or renewed. inbuxa: upstream held a lock for an hour, so a killed
+    /// node's tasks waited that long; the lock is now a five-minute lease
+    /// that the task manager renews every third of it while the task runs
+    /// (renew_task_locks), so a dead node's tasks run elsewhere within
+    /// minutes.
+    pub const DEFAULT_EXPIRY: u64 = 5 * 60;
 
     pub fn is_stopping(&self) -> bool {
         self.stopping.load(Ordering::Acquire)
@@ -370,6 +375,16 @@ impl TaskLocks {
         self.held.lock().len()
     }
 
+    /// inbuxa: the tasks this node holds, to renew their locks.
+    pub fn held_ids(&self) -> Vec<u64> {
+        self.held.lock().iter().copied().collect()
+    }
+
+    /// inbuxa: whether this node holds (and is running) the task.
+    pub fn is_held(&self, id: u64) -> bool {
+        self.held.lock().contains(&id)
+    }
+
     pub fn expiry(&self) -> u64 {
         self.expiry.load(Ordering::Relaxed)
     }

crates/common/src/lib.rs

@@ -161,6 +161,8 @@ pub struct Data {
     pub span_id_gen: SnowflakeIdGenerator,
     pub registry_id_gen: SnowflakeIdGenerator,
     pub queue_status: AtomicBool,
+    // inbuxa: coalesces the settings reloads registry writes trigger
+    pub settings_reload: cache::reload::SettingsReloadGate,
 
     pub applications: WebApplications,
     pub logos: Mutex<AHashMap<Box<str>, LogoCache>>,

crates/jmap-proto/src/method/set.rs

@@ -2,6 +2,8 @@
  * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
  *
  * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
+ *
+ * Modified by Coffey Labs in 2026 for INBUXA.
  */
 
 use super::ahash_is_empty;
@@ -71,6 +73,23 @@ pub struct SetResponse<T: JmapObject> {
     #[serde(rename = "notDestroyed")]
     #[serde(skip_serializing_if = "VecMap::is_empty")]
     pub not_destroyed: VecMap<MaybeInvalid<Id>, SetError<T::Property>>,
+
+    // inbuxa: on a registry write that changes the running settings, whether
+    // the server applied it
+    #[serde(rename = "x:settingsReload")]
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub settings_reload: Option<SettingsReload>,
+}
+
+/// inbuxa: the settings reload that followed a registry write.
+#[derive(Debug, Clone, serde::Serialize)]
+pub struct SettingsReload {
+    /// The running settings (here and, through the cluster, on every node)
+    /// include the write.
+    pub applied: bool,
+    /// Why they don't, when they don't.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
 }
 
 impl<'de, T: JmapObject> DeserializeArguments<'de> for SetRequest<'de, T> {
@@ -199,6 +218,7 @@ impl<T: JmapObject> SetResponse<T> {
                 not_created: VecMap::new(),
                 not_updated: VecMap::new(),
                 not_destroyed: VecMap::new(),
+                settings_reload: None,
             })
         } else {
             Err(trc::JmapEvent::RequestTooLarge.into_err())

crates/jmap/src/registry/mapping/action.rs

@@ -580,29 +580,9 @@ async fn dmarc_troubleshoot(
 /// settings weren't applied; upstream passed on the first error's bare message
 /// ("Invalid address: ..."), which read like a problem with the request.
 fn reload_refused(errors: Vec<registry::types::error::Error>) -> SetError<Property> {
-    use registry::types::error::Error;
+    let description = format!(
-    let more = errors.len().saturating_sub(1);
+        "Settings were not reloaded. {}",
-    let mut description = match errors.first() {
+        common::cache::reload::describe_reload_errors(&errors)
-        Some(Error::Build { object_id, message }) => format!("{object_id}: {message}"),
+    );
-        Some(Error::Validation { object_id, errors }) => format!(
-            "{object_id}: {}",
-            errors
-                .iter()
-                .map(|err| err.to_string())
-                .collect::<Vec<_>>()
-                .join("; ")
-        ),
-        Some(Error::Internal {
-            object_id: Some(object_id),
-            error,
-        }) => format!("{object_id}: {error}"),
-        Some(Error::Internal { error, .. }) => error.to_string(),
-        Some(Error::NotFound { object_id }) => format!("{object_id} was not found"),
-        None => String::new(),
-    };
-    description.insert_str(0, "Settings were not reloaded. ");
-    if more > 0 {
-        description.push_str(&format!(" ({more} more in the server log.)"));
-    }
     map_bootstrap_error(errors).with_description(description)
 }

crates/jmap/src/registry/set.rs

@@ -38,7 +38,7 @@ use directory::core::secret::{hash_secret, is_password_hash};
 use http_proto::HttpSessionData;
 use jmap_proto::{
     error::set::{SetError, SetErrorType},
-    method::set::{SetRequest, SetResponse},
+    method::set::{SetRequest, SetResponse, SettingsReload},
     object::registry::Registry,
     references::resolve::ResolveCreatedReference,
     request::{IntoValid, MaybeInvalid},
@@ -931,34 +931,28 @@ impl RegistrySet for Server {
             }
         };
 
-        // inbuxa: DIR-17: a directory or the server default applies on the
+        // inbuxa: a write to an object the running settings are built from
-        // next request, here and on every node
+        // applies at once, here and on every node (DIR-17 did this for
-        if matches!(
+        // directories and the server default; now it covers every such object)
-            object_type,
+        let mut result = result;
-            ObjectType::Directory | ObjectType::Authentication
+        if let Ok(response) = &mut result
-        ) && let Ok(response) = &result
             && (!response.created.is_empty()
                 || !response.updated.is_empty()
                 || !response.destroyed.is_empty())
+            && let Some(reload) = self.reload_after_write(object_type).await
         {
-            let change = common::ipc::RegistryChange::Reload(ObjectType::Directory);
+            response.settings_reload = Some(match reload {
-            match Box::pin(self.reload_registry(change)).await {
+                Ok(()) => SettingsReload {
-                Ok(reload) if !reload.has_errors() => {
+                    applied: true,
-                    self.cluster_broadcast(common::ipc::BroadcastEvent::RegistryChange(change))
+                    description: None,
-                        .await;
+                },
-                }
+                Err(reason) => SettingsReload {
-                Ok(reload) => {
+                    applied: false,
-                    // inbuxa: name what stopped it
+                    description: Some(format!(
-                    reload.log();
+                        "Saved, but the running settings were not reloaded. {reason}"
-                    trc::event!(
+                    )),
-                        Registry(trc::RegistryEvent::BuildWarning),
+                },
-                        Details = "Settings didn't reload after a directory change",
+            });
-                    )
-                }
-                Err(err) => {
-                    trc::error!(err.details("Failed to reload directories"));
-                }
-            }
         }
         result
     }

crates/services/src/task_manager/lock.rs

@@ -82,3 +82,42 @@ pub async fn release_task_locks(server: &Server) -> usize {
     }
     ids.len()
 }
+
+/// inbuxa: renews the lease on every task this node is running, so it stays
+/// claimed for as long as it runs while a node that dies loses its claims
+/// within one lock lifetime. Returns how many leases were renewed and how
+/// many were found lost (expired, perhaps taken by another node).
+pub async fn renew_task_locks(server: &Server) -> (usize, usize) {
+    let locks = &server.inner.ipc.task_locks;
+    let expiry = locks.expiry();
+    let (mut renewed, mut lost) = (0, 0);
+    for id in locks.held_ids() {
+        match server
+            .in_memory_store()
+            .renew_lock(KV_LOCK_TASK, &id.to_be_bytes(), expiry)
+            .await
+        {
+            Ok(true) => renewed += 1,
+            Ok(false) => {
+                // Still held here as far as this node knows; the task
+                // finishes and its lock is removed as usual
+                if locks.is_held(id) {
+                    lost += 1;
+                    trc::event!(
+                        TaskManager(TaskManagerEvent::TaskLocked),
+                        Id = id,
+                        Details = "Task lock expired while the task was running",
+                    );
+                }
+            }
+            Err(err) => {
+                trc::error!(
+                    err.details("Failed to renew task lock")
+                        .ctx(trc::Key::Id, id)
+                        .caused_by(trc::location!())
+                );
+            }
+        }
+    }
+    (renewed, lost)
+}

crates/services/src/task_manager/manager.rs

@@ -13,7 +13,7 @@ use crate::task_manager::dkim::DkimManagementTask;
 use crate::task_manager::dns::DnsManagementTask;
 use crate::task_manager::imip::SendImipTask;
 use crate::task_manager::index::SearchIndexTask;
-use crate::task_manager::lock::TaskLockManager;
+use crate::task_manager::lock::{TaskLockManager, renew_task_locks};
 use crate::task_manager::maintenance::MaintenanceTask;
 use crate::task_manager::merge_threads::MergeThreadsTask;
 use crate::task_manager::report::{self, SubmitReportTask};
@@ -24,6 +24,7 @@ use crate::task_manager::{
     TaskJob, TaskManagerIpc, TaskResult,
 };
 use common::BuildServer;
+use common::config::network::ClusterRoles;
 use common::config::server::{DEFAULT_TLS_TIMEOUT, ServerProtocol};
 use common::network::limiter::ConcurrencyLimiter;
 use common::network::{ServerInstance, TcpAcceptor};
@@ -58,10 +59,12 @@ pub fn spawn_task_manager(inner: Arc<Inner>) {
         let server = inner.build_server();
         let roles = &server.core.network.roles;
 
+        // inbuxa: outbound_mta too, which now governs report tasks
         if !roles.account_maintenance
             && !roles.store_maintenance
             && !roles.search_indexing
             && !roles.spam_training
+            && !roles.outbound_mta
             && !roles.task_manager
         {
             return;
@@ -72,6 +75,28 @@ pub fn spawn_task_manager(inner: Arc<Inner>) {
 
     trc::event!(TaskManager(TaskManagerEvent::ManagerStarted));
 
+    // inbuxa: keep the leases of running tasks alive, every third of a lock
+    // lifetime, until the node stops
+    {
+        let inner = inner.clone();
+        tokio::spawn(async move {
+            let mut renewed_at = Instant::now();
+            loop {
+                tokio::time::sleep(Duration::from_secs(1)).await;
+                let locks = &inner.ipc.task_locks;
+                if locks.is_stopping() {
+                    break;
+                }
+                if renewed_at.elapsed() >= Duration::from_secs((locks.expiry() / 3).max(1)) {
+                    renewed_at = Instant::now();
+                    if locks.held() > 0 {
+                        renew_task_locks(&inner.build_server()).await;
+                    }
+                }
+            }
+        });
+    }
+
     // Create dummy server instance for alarms
     let server_instance = Arc::new(ServerInstance {
         id: "_local".to_string(),
@@ -289,26 +314,13 @@ impl TaskQueueManager for Server {
                                     .caused_by(trc::location!())
                                     .ctx(trc::Key::Value, value)
                             })?;
-                            let enabled = match task_type {
+                            // inbuxa: running here under a lease this node
-                                TaskType::IndexDocument
+                            // renews; don't hand it to a worker again
-                                | TaskType::UnindexDocument
+                            if task_locks.is_held(task_id) {
-                                | TaskType::IndexTrace => roles.search_indexing,
+                                return Ok(true);
-                                TaskType::AccountMaintenance
+                            }
-                                | TaskType::TenantMaintenance
+
-                                | TaskType::DestroyAccount => roles.account_maintenance,
+                            let enabled = task_enabled(roles, task_type);
-                                TaskType::StoreMaintenance => roles.store_maintenance,
-                                TaskType::SpamFilterMaintenance => roles.spam_training,
-                                TaskType::CalendarAlarmEmail
-                                | TaskType::CalendarAlarmNotification
-                                | TaskType::CalendarItipMessage
-                                | TaskType::MergeThreads
-                                | TaskType::DmarcReport
-                                | TaskType::TlsReport
-                                | TaskType::RestoreArchivedItem
-                                | TaskType::AcmeRenewal
-                                | TaskType::DkimManagement
-                                | TaskType::DnsManagement => true,
-                            };
 
                             if !enabled {
                                 trc::event!(
@@ -437,6 +449,48 @@ impl TaskQueueManager for Server {
     }
 }
 
+/// inbuxa: whether this node's cluster role lets it run a task type. Upstream
+/// checked the dedicated roles (search indexing, account and store
+/// maintenance, spam training) and let every node with a task manager run
+/// the rest, whatever its taskQueueProcessing setting. Every task type now
+/// answers to one ClusterTaskType:
+///
+/// - IndexDocument, UnindexDocument, IndexTrace: searchIndexing
+/// - AccountMaintenance, TenantMaintenance, DestroyAccount: accountMaintenance
+/// - StoreMaintenance: storeMaintenance
+/// - SpamFilterMaintenance: spamClassifierTraining
+/// - DmarcReport, TlsReport: outboundMta. They build and send reports to
+///   other domains (TLS reports can go straight to an HTTPS endpoint), which
+///   is the outbound MTA's business.
+/// - CalendarAlarmEmail, CalendarAlarmNotification, CalendarItipMessage,
+///   MergeThreads, RestoreArchivedItem, AcmeRenewal, DkimManagement,
+///   DnsManagement: taskQueueProcessing, the role for queue tasks with no
+///   role of their own.
+///
+/// A node that may not run a task leaves it unclaimed, so a node that may
+/// picks it up.
+pub fn task_enabled(roles: &ClusterRoles, task_type: TaskType) -> bool {
+    match task_type {
+        TaskType::IndexDocument | TaskType::UnindexDocument | TaskType::IndexTrace => {
+            roles.search_indexing
+        }
+        TaskType::AccountMaintenance | TaskType::TenantMaintenance | TaskType::DestroyAccount => {
+            roles.account_maintenance
+        }
+        TaskType::StoreMaintenance => roles.store_maintenance,
+        TaskType::SpamFilterMaintenance => roles.spam_training,
+        TaskType::DmarcReport | TaskType::TlsReport => roles.outbound_mta,
+        TaskType::CalendarAlarmEmail
+        | TaskType::CalendarAlarmNotification
+        | TaskType::CalendarItipMessage
+        | TaskType::MergeThreads
+        | TaskType::RestoreArchivedItem
+        | TaskType::AcmeRenewal
+        | TaskType::DkimManagement
+        | TaskType::DnsManagement => roles.task_manager,
+    }
+}
+
 async fn run_task(
     server: &Server,
     task: &Task,

crates/store/src/backend/mysql/blob.rs

@@ -2,6 +2,8 @@
  * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
  *
  * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
+ *
+ * Modified by Coffey Labs in 2026 for INBUXA.
  */
 
 use std::ops::Range;
@@ -16,7 +18,7 @@ impl MysqlStore {
         key: &[u8],
         range: Range<usize>,
     ) -> trc::Result<Option<Vec<u8>>> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let s = conn
             .prep("SELECT v FROM t WHERE k = ?")
             .await
@@ -39,7 +41,7 @@ impl MysqlStore {
     }
 
     pub(crate) async fn put_blob(&self, key: &[u8], data: &[u8]) -> trc::Result<()> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let s = conn
             .prep("INSERT INTO t (k, v) VALUES (?, ?) ON DUPLICATE KEY UPDATE v = VALUES(v)")
             .await
@@ -51,7 +53,7 @@ impl MysqlStore {
     }
 
     pub(crate) async fn delete_blob(&self, key: &[u8]) -> trc::Result<bool> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let s = conn
             .prep("DELETE FROM t WHERE k = ?")
             .await

crates/store/src/backend/mysql/lookup.rs

@@ -2,6 +2,8 @@
  * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
  *
  * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
+ *
+ * Modified by Coffey Labs in 2026 for INBUXA.
  */
 
 use mysql_async::{Params, Row, prelude::Queryable};
@@ -16,7 +18,7 @@ impl MysqlStore {
         query: &str,
         params: &[Value<'_>],
     ) -> trc::Result<T> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let s = conn.prep(query).await.map_err(into_error)?;
         let params = Params::Positional(params.iter().map(Into::into).collect());
 

crates/store/src/backend/mysql/main.rs

@@ -32,6 +32,9 @@ impl MysqlStore {
             .max_allowed_packet(config.max_allowed_packet.map(|v| v as usize))
             .wait_timeout(config.timeout.map(|t| t.as_secs() as usize))
             .client_found_rows(true)
+            // inbuxa: notice a server that went away without closing the
+            // connection in minutes, not the system default of two hours
+            .tcp_keepalive(Some(super::POOL_KEEPALIVE_IDLE))
             .tcp_port(config.port as u16);
 
         if config.use_tls {
@@ -95,7 +98,7 @@ impl MysqlStore {
     }
 
     pub(crate) async fn create_storage_tables(&self) -> trc::Result<()> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
 
         for table in [
             SUBSPACE_ACL,
@@ -169,7 +172,7 @@ impl MysqlStore {
     }
 
     pub(crate) async fn create_search_tables(&self) -> trc::Result<()> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
 
         create_search_tables::<EmailSearchField>(&mut conn).await?;
         create_search_tables::<CalendarSearchField>(&mut conn).await?;

crates/store/src/backend/mysql/mod.rs

@@ -27,6 +27,33 @@ pub struct MysqlStore {
     pub(crate) conn_pool: Pool,
 }
 
+/// inbuxa: how long a request waits for a pooled connection (including
+/// opening one). mysql_async's pool has no wait timeout, so upstream waited
+/// forever when the server stopped answering.
+pub(crate) const POOL_WAIT_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(30);
+/// inbuxa: idle time before TCP keepalive probes start.
+pub(crate) const POOL_KEEPALIVE_IDLE: std::time::Duration = std::time::Duration::from_secs(60);
+
+impl MysqlStore {
+    /// inbuxa: a pooled connection, or an error once POOL_WAIT_TIMEOUT has
+    /// passed without one.
+    pub(crate) async fn conn(&self) -> trc::Result<mysql_async::Conn> {
+        pool_conn(&self.conn_pool, POOL_WAIT_TIMEOUT).await
+    }
+}
+
+pub(crate) async fn pool_conn(
+    pool: &Pool,
+    wait: std::time::Duration,
+) -> trc::Result<mysql_async::Conn> {
+    match tokio::time::timeout(wait, pool.get_conn()).await {
+        Ok(result) => result.map_err(into_error),
+        Err(_) => Err(trc::StoreEvent::MysqlError
+            .reason("Timed out waiting for a database connection")
+            .details(format!("No connection within {} s", wait.as_secs()))),
+    }
+}
+
 #[inline(always)]
 pub(crate) fn into_error(err: impl Display) -> trc::Error {
     trc::StoreEvent::MysqlError.reason(err)

crates/store/src/backend/mysql/read.rs

@@ -2,6 +2,8 @@
  * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
  *
  * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
+ *
+ * Modified by Coffey Labs in 2026 for INBUXA.
  */
 
 use super::{MysqlStore, into_error, is_timeout_error};
@@ -14,7 +16,7 @@ impl MysqlStore {
     where
         U: Deserialize + 'static,
     {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let s = conn
             .prep(format!(
                 "SELECT v FROM {} WHERE k = ?",
@@ -36,7 +38,7 @@ impl MysqlStore {
     }
 
     pub(crate) async fn key_exists(&self, key: impl Key) -> trc::Result<bool> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let s = conn
             .prep(format!(
                 "SELECT 1 FROM {} WHERE k = ?",
@@ -56,7 +58,7 @@ impl MysqlStore {
         params: IterateParams<T>,
         mut cb: impl for<'x> FnMut(&'x [u8], &'x [u8]) -> trc::Result<bool> + Sync + Send,
     ) -> trc::Result<()> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let table = char::from(params.begin.subspace());
         let begin = params.begin.serialize(0);
         let end = params.end.serialize(0);
@@ -155,7 +157,7 @@ impl MysqlStore {
         let key = key.into();
         let table = char::from(key.subspace());
         let key = key.serialize(0);
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let s = conn
             .prep(format!("SELECT v FROM {table} WHERE k = ?"))
             .await

crates/store/src/backend/mysql/search.rs

@@ -26,7 +26,7 @@ use std::fmt::Write;
 
 impl MysqlStore {
     pub async fn index(&self, documents: Vec<IndexDocument>) -> trc::Result<()> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let mut tx_opts = TxOpts::default();
         tx_opts
             .with_consistent_snapshot(false)
@@ -96,7 +96,7 @@ impl MysqlStore {
             build_sort(&mut query, sort);
         }
 
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let s = conn.prep(query).await.map_err(into_error)?;
 
         conn.exec::<i64, _, _>(s, params)
@@ -110,7 +110,7 @@ impl MysqlStore {
         let mut query = format!("DELETE FROM {table} ");
         let params = build_filter(&mut query, &filter.filters);
 
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let s = conn.prep(&query).await.map_err(into_error)?;
 
         match conn.exec_drop(s, params.clone()).await {

crates/store/src/backend/mysql/write.rs

@@ -2,6 +2,8 @@
  * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
  *
  * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
+ *
+ * Modified by Coffey Labs in 2026 for INBUXA.
  */
 
 use super::{DELETE_CHUNK_SIZE, MIN_DELETE_CHUNK_SIZE, MysqlStore, into_error, is_timeout_error};
@@ -29,7 +31,7 @@ impl MysqlStore {
     pub(crate) async fn write(&self, mut batch: Batch<'_>) -> trc::Result<AssignedIds> {
         let start = Instant::now();
         let mut retry_count = 0;
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
 
         loop {
             let err = match self.write_trx(&mut conn, &mut batch).await {
@@ -382,7 +384,7 @@ impl MysqlStore {
     }
 
     pub(crate) async fn purge_store(&self) -> trc::Result<()> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         for subspace in [SUBSPACE_QUOTA, SUBSPACE_COUNTER, SUBSPACE_IN_MEMORY_COUNTER] {
             purge_table(&mut conn, char::from(subspace)).await?;
         }
@@ -391,7 +393,7 @@ impl MysqlStore {
     }
 
     pub(crate) async fn delete_range(&self, from: impl Key, to: impl Key) -> trc::Result<()> {
-        let mut conn = self.conn_pool.get_conn().await.map_err(into_error)?;
+        let mut conn = self.conn().await?;
         let table = char::from(from.subspace());
         let mut from = from.serialize(0);
         let to = to.serialize(0);

crates/store/src/backend/postgres/main.rs

@@ -22,11 +22,34 @@ use crate::{
 use ::registry::schema::{enums::PostgreSqlRecyclingMethod, structs};
 use ahash::AHashSet;
 use deadpool_postgres::{
-    Config, ManagerConfig, Object, Pool, PoolConfig, RecyclingMethod, Runtime,
+    Config, ManagerConfig, Object, Pool, PoolConfig, RecyclingMethod, Runtime, Timeouts,
 };
+use std::time::Duration;
 use tokio_postgres::NoTls;
 use utils::tls::rustls_client_config;
 
+/// inbuxa: how long a request waits for a pooled connection.
+pub(crate) const POOL_WAIT_TIMEOUT: Duration = Duration::from_secs(30);
+/// inbuxa: how long opening a connection may take when the store sets no
+/// timeout of its own.
+pub(crate) const POOL_CREATE_TIMEOUT: Duration = Duration::from_secs(15);
+/// inbuxa: how long checking a pooled connection before reuse may take.
+pub(crate) const POOL_RECYCLE_TIMEOUT: Duration = Duration::from_secs(10);
+/// inbuxa: idle time before TCP keepalive probes start.
+pub(crate) const POOL_KEEPALIVE_IDLE: Duration = Duration::from_secs(60);
+
+/// inbuxa: the pool's timeouts. Opening a connection is bounded by the
+/// store's own timeout when it has one; waiting for one covers at least that
+/// long, so a slow connect isn't cut short by the wait.
+pub(crate) fn pool_timeouts(connect_timeout: Option<Duration>) -> Timeouts {
+    let create = connect_timeout.unwrap_or(POOL_CREATE_TIMEOUT);
+    Timeouts {
+        wait: POOL_WAIT_TIMEOUT.max(create).into(),
+        create: create.into(),
+        recycle: POOL_RECYCLE_TIMEOUT.into(),
+    }
+}
+
 impl PostgresStore {
     pub async fn open(config: structs::PostgreSqlStore) -> Result<Store, String> {
         // inbuxa: ST-15: where the primary is, to tell a replica from it
@@ -46,9 +69,20 @@ impl PostgresStore {
                 PostgreSqlRecyclingMethod::Clean => RecyclingMethod::Clean,
             },
         });
-        if let Some(max_conn) = config.pool_max_connections {
+        // inbuxa: upstream set no pool timeouts, so a request waited for a
-            cfg.pool = PoolConfig::new(max_conn as usize).into();
+        // free connection, or for one to be made or recycled, for as long as
-        }
+        // it took: forever when the server stopped answering. A worker now
+        // gets an error instead and the task or request is retried.
+        let mut pool = config
+            .pool_max_connections
+            .map(|max_conn| PoolConfig::new(max_conn as usize))
+            .unwrap_or_default();
+        pool.timeouts = pool_timeouts(cfg.connect_timeout);
+        cfg.pool = pool.into();
+        // Notice a server that went away without closing the connection in
+        // minutes rather than the system default of two hours
+        cfg.keepalives = true.into();
+        cfg.keepalives_idle = POOL_KEEPALIVE_IDLE.into();
 
         let primary_pool = if config.use_tls {
             cfg.create_pool(

crates/store/src/backend/redis/lookup.rs

@@ -2,6 +2,8 @@
  * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
  *
  * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
+ *
+ * Modified by Coffey Labs in 2026 for INBUXA.
  */
 
 use super::{RedisPool, RedisStore, into_error};
@@ -79,6 +81,30 @@ impl RedisStore {
         }
     }
 
+    // inbuxa: see InMemoryStore::renew_lock
+    pub async fn renew_lock(&self, key: &[u8], expires: u64) -> trc::Result<bool> {
+        match &self.pool {
+            RedisPool::Single(pool) => {
+                with_conn(pool, async |conn| {
+                    Self::renew_lock_(conn, key, expires).await
+                })
+                .await
+            }
+            RedisPool::Cluster(pool) => {
+                with_conn(pool, async |conn| {
+                    Self::renew_lock_(conn, key, expires).await
+                })
+                .await
+            }
+            RedisPool::Sentinel(pool) => {
+                with_conn(pool, async |conn| {
+                    Self::renew_lock_(conn, key, expires).await
+                })
+                .await
+            }
+        }
+    }
+
     pub async fn key_delete(&self, key: &[u8]) -> trc::Result<()> {
         match &self.pool {
             RedisPool::Single(pool) => {
@@ -226,6 +252,22 @@ impl RedisStore {
             .map(|reply| reply.is_some())
     }
 
+    async fn renew_lock_(
+        conn: &mut impl AsyncCommands,
+        key: &[u8],
+        expires: u64,
+    ) -> RedisResult<bool> {
+        redis::cmd("SET")
+            .arg(key)
+            .arg(now() + expires)
+            .arg("XX")
+            .arg("EX")
+            .arg(expires as i64)
+            .query_async::<Option<String>>(conn)
+            .await
+            .map(|reply| reply.is_some())
+    }
+
     async fn key_delete_(conn: &mut impl AsyncCommands, key: &[u8]) -> RedisResult<()> {
         conn.del(key).await
     }

crates/store/src/dispatch/lookup.rs

@@ -401,6 +401,57 @@ impl InMemoryStore {
         }
     }
 
+    /// inbuxa: extends a lock this node holds to `duration` seconds from now.
+    /// Returns false when the lock is gone or has expired: it may have been
+    /// taken by someone else since, so it is left alone.
+    pub async fn renew_lock(&self, prefix: u8, key: &[u8], duration: u64) -> trc::Result<bool> {
+        match self {
+            InMemoryStore::Store(store) => {
+                let key = KeyValue::<()>::build_key(prefix, key);
+                let key = ValueClass::InMemory(InMemoryClass::Key(key));
+                let Some(lock_expiry) = store
+                    .get_value::<u64>(ValueKey::from(key.clone()))
+                    .await
+                    .caused_by(trc::location!())?
+                else {
+                    return Ok(false);
+                };
+                let now = now();
+                if lock_expiry <= now {
+                    return Ok(false);
+                }
+
+                let mut batch = BatchBuilder::new();
+                batch.assert_value(key.clone(), AssertValue::U64(lock_expiry));
+                batch.set(key, (now + duration).serialize());
+                match store.write(batch.build_all()).await {
+                    Ok(_) => Ok(true),
+                    Err(err) if err.is_assertion_failure() => Ok(false),
+                    Err(err) => Err(err
+                        .details("Failed to renew lock.")
+                        .caused_by(trc::location!())),
+                }
+            }
+            InMemoryStore::Sharded(store) => {
+                Box::pin(
+                    store
+                        .member(&KeyValue::<()>::build_key(prefix, key))
+                        .renew_lock(prefix, key, duration),
+                )
+                .await
+            }
+            #[cfg(feature = "redis")]
+            InMemoryStore::Redis(store) => {
+                store
+                    .renew_lock(&KeyValue::<()>::build_key(prefix, key), duration)
+                    .await
+            }
+            InMemoryStore::Static(_) | InMemoryStore::Http(_) => {
+                Err(trc::StoreEvent::NotSupported.into_err())
+            }
+        }
+    }
+
     pub async fn remove_lock(&self, prefix: u8, key: &[u8]) -> trc::Result<()> {
         self.key_delete(KeyValue::<()>::build_key(prefix, key))
             .await

tests/src/cluster/broadcast.rs

@@ -2,6 +2,8 @@
  * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
  *
  * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
+ *
+ * Modified by Coffey Labs in 2026 for INBUXA.
  */
 
 use crate::{
@@ -11,6 +13,7 @@ use crate::{
         server::TestServerBuilder,
     },
 };
+use common::BuildServer;
 use imap_proto::ResponseType;
 use registry::{
     schema::{
@@ -18,7 +21,8 @@ use registry::{
         prelude::{ObjectType, Property, SocketAddr},
         structs::{
             ClusterListenerGroup, ClusterListenerGroupProperties, ClusterRole, ClusterTaskGroup,
-            Coordinator, Imap, NatsCoordinator, NetworkListener, RedisStore,
+            Coordinator, Imap, MtaDeliverySchedule, MtaVirtualQueue, NatsCoordinator,
+            NetworkListener, RedisStore,
         },
     },
     types::map::Map,
@@ -209,6 +213,45 @@ pub async fn cluster_tests() {
         Some("John Doe")
     );
 
+    // inbuxa: a settings write applies on every node, no ReloadSettings
+    let queue_id = admin
+        .registry_create_object(MtaVirtualQueue {
+            name: "clusterq".into(),
+            threads_per_node: 1,
+            description: None,
+        })
+        .await;
+    admin
+        .registry_create_object(MtaDeliverySchedule {
+            name: "cluster-autoreload".into(),
+            queue_id,
+            ..Default::default()
+        })
+        .await;
+    for (node_id, test) in servers.iter().enumerate() {
+        let started = std::time::Instant::now();
+        while !test
+            .server
+            .inner
+            .build_server()
+            .core
+            .smtp
+            .queue
+            .queue_strategy
+            .contains_key("cluster-autoreload")
+        {
+            assert!(
+                started.elapsed() < std::time::Duration::from_secs(5),
+                "node {node_id} didn't pick up the new delivery schedule"
+            );
+            tokio::time::sleep(std::time::Duration::from_millis(50)).await;
+        }
+        println!(
+            "Node {node_id} has the new delivery schedule after {} ms",
+            started.elapsed().as_millis()
+        );
+    }
+
     // Run IMAP idle tests across nodes
     let mut node1_client = imap_client("[email protected]", "this is john's secret", 1).await;
     let mut node2_client = imap_client("[email protected]", "this is john's secret", 2).await;

tests/src/cluster/mod.rs

@@ -10,3 +10,4 @@ pub mod broadcast;
 #[cfg(feature = "nats")]
 pub mod coordinator; // inbuxa: coordinator reconnects
 pub mod stress;
+pub mod task_roles; // inbuxa: task types follow cluster roles

tests/src/cluster/task_roles.rs

@@ -0,0 +1,218 @@
+/*
+ * SPDX-FileCopyrightText: 2026 Coffey Labs
+ *
+ * SPDX-License-Identifier: AGPL-3.0-only
+ */
+
+//! Two task managers with different cluster roles over one shared store:
+//! each runs only the task types its role allows, and a task one node may
+//! not run is left for the node that may. Needs a store both nodes can open
+//! (STORE=PostgreSql or MySql).
+
+use crate::utils::server::TestServerBuilder;
+use common::Server;
+use registry::{
+    schema::{
+        enums::{ClusterTaskType, IndexDocumentType},
+        structs::{
+            ClusterListenerGroup, ClusterRole, ClusterTaskGroup, ClusterTaskGroupProperties, Task,
+            TaskDnsManagement, TaskIndexDocument, TaskStatus, TaskTlsReport,
+        },
+    },
+    types::map::Map,
+};
+use std::time::{Duration, Instant};
+use store::{
+    ValueKey,
+    write::{BatchBuilder, TaskQueueClass, ValueClass},
+};
+use utils::snowflake::SnowflakeIdGenerator;
+
+const QUEUE_ROLE: &str = "tasks_queue";
+const INDEX_MTA_ROLE: &str = "tasks_index_mta";
+
+#[tokio::test(flavor = "multi_thread")]
+pub async fn task_role_tests() {
+    if matches!(
+        std::env::var("STORE").as_deref(),
+        Ok("RocksDb" | "Sqlite") | Err(_)
+    ) {
+        println!("Skipping task role tests: they need a store both nodes can open.");
+        return;
+    }
+    println!(
+        "Running task role tests on {}...",
+        std::env::var("STORE").unwrap_or_default()
+    );
+
+    // The roles, stored by a node that runs no services of its own (a node
+    // looks its role up when it starts)
+    let seed = TestServerBuilder::new("task_roles_seed")
+        .await
+        .with_object(role(QUEUE_ROLE, &[ClusterTaskType::TaskQueueProcessing]))
+        .await
+        .with_object(role(
+            INDEX_MTA_ROLE,
+            &[
+                ClusterTaskType::SearchIndexing,
+                ClusterTaskType::OutboundMta,
+            ],
+        ))
+        .await
+        .disable_services()
+        .build()
+        .await;
+
+    // Node A runs queue tasks (taskQueueProcessing) only
+    let node_a = TestServerBuilder::new_with_role(
+        "task_roles_a",
+        "node-a.example.com".into(),
+        Some(QUEUE_ROLE.into()),
+        false,
+    )
+    .await
+    .build_with_opts(false)
+    .await;
+    let server_a = node_a.server.clone();
+    let roles = &server_a.core.network.roles;
+    assert!(roles.task_manager && !roles.search_indexing && !roles.outbound_mta);
+
+    // A DNS task (taskQueueProcessing), an unindex task (searchIndexing) and
+    // a TLS report (outboundMta), all due now
+    let [dns, unindex, report] = new_task_ids();
+    let mut batch = BatchBuilder::new();
+    batch
+        .schedule_task_with_id(
+            dns,
+            Task::DnsManagement(TaskDnsManagement {
+                status: TaskStatus::now(),
+                ..Default::default()
+            }),
+        )
+        .schedule_task_with_id(
+            unindex,
+            Task::UnindexDocument(TaskIndexDocument {
+                account_id: 0u32.into(),
+                document_id: u32::MAX.into(),
+                document_type: IndexDocumentType::File,
+                status: TaskStatus::now(),
+            }),
+        )
+        .schedule_task_with_id(
+            report,
+            Task::TlsReport(TaskTlsReport {
+                report_id: u64::MAX.into(),
+                status: TaskStatus::now(),
+            }),
+        );
+    server_a.store().write(batch.build_all()).await.unwrap();
+    server_a.notify_task_queue();
+
+    // Node A runs the DNS task and leaves the other two alone. Upstream ran
+    // the TLS report here too: report tasks ran on any node with a task
+    // manager.
+    wait_until_run(&server_a, &[dns], Duration::from_secs(20)).await;
+    tokio::time::sleep(Duration::from_secs(3)).await;
+    server_a.notify_task_queue();
+    tokio::time::sleep(Duration::from_secs(2)).await;
+    assert!(
+        is_pending(&server_a, unindex).await,
+        "unindex ran on node A"
+    );
+    assert!(
+        is_pending(&server_a, report).await,
+        "TLS report ran on node A"
+    );
+
+    // Node B (search indexing and outbound MTA) comes up and picks up what
+    // node A left
+    let node_b = TestServerBuilder::new_with_role(
+        "task_roles_b",
+        "node-b.example.com".into(),
+        Some(INDEX_MTA_ROLE.into()),
+        false,
+    )
+    .await
+    .build_with_opts(false)
+    .await;
+    let server_b = node_b.server.clone();
+    let roles = &server_b.core.network.roles;
+    assert!(!roles.task_manager && roles.search_indexing && roles.outbound_mta);
+    server_b.notify_task_queue();
+    wait_until_run(&server_b, &[unindex, report], Duration::from_secs(20)).await;
+
+    // A queue task scheduled now still runs, on node A: node B may not
+    // claim it
+    let [dns] = new_task_ids();
+    let mut batch = BatchBuilder::new();
+    batch.schedule_task_with_id(
+        dns,
+        Task::DnsManagement(TaskDnsManagement {
+            status: TaskStatus::now(),
+            ..Default::default()
+        }),
+    );
+    server_b.store().write(batch.build_all()).await.unwrap();
+    server_b.notify_task_queue();
+    tokio::time::sleep(Duration::from_secs(3)).await;
+    assert!(is_pending(&server_b, dns).await, "DNS task ran on node B");
+    server_a.notify_task_queue();
+    wait_until_run(&server_a, &[dns], Duration::from_secs(20)).await;
+
+    if seed.is_reset() {
+        seed.temp_dir.delete();
+        node_a.temp_dir.delete();
+        node_b.temp_dir.delete();
+    }
+}
+
+fn role(name: &str, tasks: &[ClusterTaskType]) -> ClusterRole {
+    ClusterRole {
+        name: name.into(),
+        description: None,
+        listeners: ClusterListenerGroup::EnableAll,
+        tasks: ClusterTaskGroup::EnableSome(ClusterTaskGroupProperties {
+            task_types: Map::new(tasks.to_vec()),
+        }),
+    }
+}
+
+fn new_task_ids<const N: usize>() -> [u64; N] {
+    std::array::from_fn(|_| SnowflakeIdGenerator::global_id().unwrap())
+}
+
+/// Still due and never run: present, and pending.
+async fn is_pending(server: &Server, id: u64) -> bool {
+    matches!(
+        server
+            .store()
+            .get_value::<Task>(ValueKey::from(ValueClass::TaskQueue(
+                TaskQueueClass::Task { id },
+            )))
+            .await
+            .unwrap()
+            .map(|task| task.status().clone()),
+        Some(TaskStatus::Pending(_))
+    )
+}
+
+async fn wait_until_run(server: &Server, ids: &[u64], within: Duration) {
+    let started = Instant::now();
+    loop {
+        let mut left = 0;
+        for id in ids {
+            if is_pending(server, *id).await {
+                left += 1;
+            }
+        }
+        if left == 0 {
+            return;
+        }
+        assert!(
+            started.elapsed() < within,
+            "{left} task(s) still pending after {:?}",
+            started.elapsed()
+        );
+        tokio::time::sleep(Duration::from_millis(250)).await;
+    }
+}

tests/src/smtp/inbound/mod.rs

@@ -2,6 +2,8 @@
  * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
  *
  * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
+ *
+ * Modified by Coffey Labs in 2026 for INBUXA.
  */
 
 use crate::utils::server::TestServer;
@@ -40,15 +42,23 @@ pub mod vrfy;
 const EVENT_TIMEOUT: Duration = Duration::from_secs(5);
 
 impl TestServer {
+    // inbuxa: registry writes reload the settings, and each reload sends the
+    // queue a ReloadSettings; read_event, try_read_event and assert_no_events
+    // pass over those (expect_reload_settings still waits for one)
     pub async fn read_event(&mut self) -> QueueEvent {
-        if let Some(event) = self.queue_events.pop_front() {
+        while let Some(event) = self.queue_events.pop_front() {
-            return event;
+            if !event.is_reload_settings() {
+                return event;
+            }
         }
 
-        match tokio::time::timeout(EVENT_TIMEOUT, self.queue_rx.recv()).await {
+        loop {
-            Ok(Some(event)) => event,
+            match tokio::time::timeout(EVENT_TIMEOUT, self.queue_rx.recv()).await {
-            Ok(None) => panic!("Channel closed."),
+                Ok(Some(event)) if event.is_reload_settings() => (),
-            Err(_) => panic!("No queue event received."),
+                Ok(Some(event)) => return event,
+                Ok(None) => panic!("Channel closed."),
+                Err(_) => panic!("No queue event received."),
+            }
         }
     }
 
@@ -78,26 +88,39 @@ impl TestServer {
     }
 
     pub async fn try_read_event(&mut self) -> Option<QueueEvent> {
-        if let Some(event) = self.queue_events.pop_front() {
+        while let Some(event) = self.queue_events.pop_front() {
-            return Some(event);
+            if !event.is_reload_settings() {
+                return Some(event);
+            }
         }
 
-        match tokio::time::timeout(EVENT_TIMEOUT, self.queue_rx.recv()).await {
+        loop {
-            Ok(Some(event)) => Some(event),
+            match tokio::time::timeout(EVENT_TIMEOUT, self.queue_rx.recv()).await {
-            Ok(None) => panic!("Channel closed."),
+                Ok(Some(event)) if event.is_reload_settings() => (),
-            Err(_) => None,
+                Ok(Some(event)) => return Some(event),
+                Ok(None) => panic!("Channel closed."),
+                Err(_) => return None,
+            }
         }
     }
 
     pub fn assert_no_events(&mut self) {
-        if let Some(event) = self.queue_events.pop_front() {
+        if let Some(event) = self
+            .queue_events
+            .iter()
+            .find(|event| !event.is_reload_settings())
+        {
             panic!("Expected empty queue but got {event:?}");
         }
+        self.queue_events.clear();
 
-        match self.queue_rx.try_recv() {
+        loop {
-            Err(TryRecvError::Empty) => (),
+            match self.queue_rx.try_recv() {
-            Ok(event) => panic!("Expected empty queue but got {event:?}"),
+                Ok(event) if event.is_reload_settings() => (),
-            Err(err) => panic!("Queue error: {err:?}"),
+                Err(TryRecvError::Empty) => break,
+                Ok(event) => panic!("Expected empty queue but got {event:?}"),
+                Err(err) => panic!("Queue error: {err:?}"),
+            }
         }
     }
 

tests/src/store/mod.rs

@@ -10,6 +10,8 @@ pub mod blob;
 pub mod import_export;
 pub mod lookup;
 pub mod ops;
+#[cfg(any(feature = "postgres", feature = "mysql"))]
+pub mod pool_timeout; // inbuxa: SQL pools give up instead of hanging
 pub mod query;
 pub mod registry;
 #[cfg(feature = "postgres")]

tests/src/store/pool_timeout.rs

@@ -0,0 +1,96 @@
+/*
+ * SPDX-FileCopyrightText: 2026 Coffey Labs
+ *
+ * SPDX-License-Identifier: AGPL-3.0-only
+ */
+
+//! A database that accepts connections and then says nothing (a hung or
+//! half-dead server, a black-holed failover) gives a worker an error within
+//! the pool's timeouts. Upstream's pools had none, so the worker waited for
+//! good. No database is needed: a local listener that never answers plays
+//! the server.
+
+use registry::schema::structs::DataStore;
+use std::time::{Duration, Instant};
+use store::{Store, ValueKey, write::ValueClass};
+use tokio::net::TcpListener;
+
+/// Accepts connections on a local port and never sends a byte.
+async fn silent_server() -> u16 {
+    let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
+    let port = listener.local_addr().unwrap().port();
+    tokio::spawn(async move {
+        let mut held = Vec::new();
+        while let Ok((socket, _)) = listener.accept().await {
+            held.push(socket);
+        }
+    });
+    port
+}
+
+/// Builds the store and reads a key; both must end, with an error for the
+/// read, well within `limit`.
+async fn assert_times_out(data_store: DataStore, limit: Duration) {
+    let started = Instant::now();
+    let result = tokio::time::timeout(limit, async {
+        match Store::build(data_store).await {
+            Ok(store) => store
+                .get_value::<u64>(ValueKey::from(ValueClass::Property(0)))
+                .await
+                .map(|_| ())
+                .map_err(|err| err.to_string()),
+            Err(err) => Err(err.to_string()),
+        }
+    })
+    .await;
+    let elapsed = started.elapsed();
+    match result {
+        Ok(Err(err)) => println!("Got {err} after {elapsed:?}"),
+        Ok(Ok(())) => panic!("a silent server answered?"),
+        Err(_) => panic!("still waiting for a connection after {elapsed:?}"),
+    }
+}
+
+#[cfg(feature = "postgres")]
+#[tokio::test(flavor = "multi_thread")]
+pub async fn postgres_pool_timeout() {
+    use registry::schema::structs::PostgreSqlStore;
+
+    let port = silent_server().await;
+    println!("Running PostgreSQL pool timeout test...");
+    // The store's own timeout bounds opening a connection, handshake
+    // included (tokio-postgres's connect_timeout covers only the TCP connect)
+    assert_times_out(
+        DataStore::PostgreSql(PostgreSqlStore {
+            host: "127.0.0.1".into(),
+            port: port as u64,
+            database: "none".into(),
+            timeout: Some(Duration::from_secs(2).into()),
+            use_tls: false,
+            ..Default::default()
+        }),
+        Duration::from_secs(20),
+    )
+    .await;
+}
+
+#[cfg(feature = "mysql")]
+#[tokio::test(flavor = "multi_thread")]
+pub async fn mysql_pool_timeout() {
+    use registry::schema::structs::MySqlStore;
+
+    let port = silent_server().await;
+    println!("Running MySQL pool timeout test...");
+    // mysql_async has no pool timeout; the store waits 30 s for a connection
+    assert_times_out(
+        DataStore::MySql(MySqlStore {
+            host: "127.0.0.1".into(),
+            port: port as u64,
+            database: "none".into(),
+            use_tls: false,
+            ..Default::default()
+        }),
+        Duration::from_secs(60),
+    )
+    .await;
+}

tests/src/store/task_locks.rs

@@ -79,7 +79,33 @@ pub async fn task_lock_tests() {
         "ran before the other node's locks expired: {elapsed:?}"
     );
 
-    // 3. A graceful stop releases the locks this node holds: another node
+    // 3. A task that runs longer than a lock lifetime keeps its claim: the
+    // task manager renews the lease while this node holds it, and the claim
+    // ends when the task does. (Before, a lock simply lasted an hour.)
+    let [id] = new_task_ids(1)[..] else {
+        unreachable!()
+    };
+    assert!(server.try_lock_task(id).await, "claim {id}");
+    tokio::time::sleep(Duration::from_secs(LOCK_EXPIRY + LOCK_EXPIRY / 2)).await;
+    assert!(
+        !foreign_lock(&server, id, LOCK_EXPIRY).await,
+        "lease lapsed while the task ran"
+    );
+    server.remove_index_lock(id).await;
+    assert!(
+        foreign_lock(&server, id, LOCK_EXPIRY).await,
+        "released when the task ended"
+    );
+    let _ = server
+        .in_memory_store()
+        .remove_lock(KV_LOCK_TASK, &id.to_be_bytes())
+        .await;
+    assert!(
+        common::ipc::TaskLocks::DEFAULT_EXPIRY <= 5 * 60,
+        "a dead node's tasks wait no more than a few minutes"
+    );
+
+    // 4. A graceful stop releases the locks this node holds: another node
     // can claim those tasks at once, and this one claims nothing more
     let ids = new_task_ids(3);
     for id in &ids {

tests/src/system/auto_reload.rs

@@ -0,0 +1,220 @@
+/*
+ * SPDX-FileCopyrightText: 2026 Coffey Labs
+ *
+ * SPDX-License-Identifier: AGPL-3.0-only
+ */
+
+// inbuxa: a registry write to an object the running settings are built from
+// applies without an x:Action ReloadSettings, and the set response says so.
+
+use crate::utils::{
+    jmap::JmapResponse,
+    server::{TestServer, TestServerBuilder},
+};
+use common::BuildServer;
+use registry::{
+    schema::{
+        enums::TracingLevel,
+        prelude::ObjectType,
+        structs::{
+            AllowedIp, CertificateManagement, DkimManagement, DnsManagement, Domain, Expression,
+            MtaDeliverySchedule, MtaStageAuth, MtaVirtualQueue, Tracer, TracerStdout,
+        },
+    },
+    types::ipmask::IpAddrOrMask,
+};
+use serde_json::Value;
+
+#[tokio::test(flavor = "multi_thread")]
+pub async fn settings_reload_tests() {
+    let mut test = TestServerBuilder::new("settings_reload_tests")
+        .await
+        .with_default_listeners()
+        .await
+        .with_object(MtaStageAuth {
+            require: Expression {
+                else_: "false".to_string(),
+                ..Default::default()
+            },
+            ..Default::default()
+        })
+        .await
+        .build()
+        .await;
+
+    let admin = test
+        .create_user_account(
+            "admin",
+            "[email protected]",
+            "these_pretzels_are_making_me_thirsty",
+            &[],
+            "Admin",
+        )
+        .await;
+    test.account("admin")
+        .assign_roles_to_account(admin.id(), &["user", "system"])
+        .await;
+    test.insert_account(admin);
+
+    test_write_applies(&test).await;
+
+    if test.is_reset() {
+        test.temp_dir.delete();
+    }
+}
+
+async fn test_write_applies(test: &TestServer) {
+    println!("Running settings reload after registry writes...");
+    let admin = test.account("[email protected]");
+
+    // A delivery schedule is in use as soon as it is saved
+    let response = admin
+        .registry_create([MtaVirtualQueue {
+            name: "autorld".into(),
+            threads_per_node: 2,
+            description: None,
+        }])
+        .await;
+    assert_applied(&response);
+    let queue_id = response.created_id(0);
+    assert!(!has_schedule(test, "autoreload-schedule"));
+    let response = admin
+        .registry_create([MtaDeliverySchedule {
+            name: "autoreload-schedule".into(),
+            queue_id,
+            ..Default::default()
+        }])
+        .await;
+    assert_applied(&response);
+    assert!(has_schedule(test, "autoreload-schedule"));
+
+    // Destroyed, it's gone at once too
+    let schedule_id = response.created_id(0);
+    let response = admin
+        .registry_destroy(ObjectType::MtaDeliverySchedule, [schedule_id])
+        .await;
+    assert_applied(&response);
+    assert!(!has_schedule(test, "autoreload-schedule"));
+
+    // Concurrent writes all end up in the running settings
+    let names = (0..8)
+        .map(|i| format!("autoreload-{i}"))
+        .collect::<Vec<_>>();
+    let mut writes = Vec::new();
+    for name in &names {
+        writes.push(admin.registry_create([MtaDeliverySchedule {
+            name: name.clone(),
+            queue_id,
+            ..Default::default()
+        }]));
+    }
+    let mut schedule_ids = Vec::new();
+    for response in futures::future::join_all(writes).await {
+        assert_applied(&response);
+        schedule_ids.push(response.created_id(0));
+    }
+    for name in &names {
+        assert!(has_schedule(test, name), "{name} missing");
+    }
+    // Several objects in one request: one reload
+    let response = admin
+        .registry_destroy(ObjectType::MtaDeliverySchedule, schedule_ids.iter())
+        .await;
+    assert_applied(&response);
+    for name in &names {
+        assert!(!has_schedule(test, name), "{name} still present");
+    }
+
+    // A write whose reload fails is stored, and the response says the
+    // settings weren't reloaded: only one console tracer is allowed.
+    let response = admin
+        .registry_create([
+            Tracer::Stdout(TracerStdout {
+                enable: true,
+                level: TracingLevel::Error,
+                ..Default::default()
+            }),
+            Tracer::Stdout(TracerStdout {
+                enable: true,
+                level: TracingLevel::Error,
+                ..Default::default()
+            }),
+        ])
+        .await;
+    let reload = settings_reload(&response).expect("x:settingsReload missing");
+    assert_eq!(reload["applied"], Value::Bool(false), "{response:?}");
+    let description = reload["description"].as_str().unwrap_or_default();
+    assert!(
+        description.starts_with("Saved, but the running settings were not reloaded. ")
+            && description.contains("Only one console tracer is allowed"),
+        "{description}"
+    );
+    let tracer_ids = [response.created_id(0), response.created_id(1)];
+    let response = admin
+        .registry_destroy(ObjectType::Tracer, tracer_ids.iter())
+        .await;
+    assert_applied(&response);
+
+    // An allowed IP is live as soon as it is saved, and gone once
+    // destroyed. It lives in the core's security settings, which the
+    // blocked-IP reload it used to get doesn't rebuild.
+    let ip: std::net::IpAddr = "198.51.100.7".parse().unwrap();
+    assert!(!is_allowed(test, ip));
+    let response = admin
+        .registry_create([AllowedIp {
+            address: IpAddrOrMask::from_ip(ip),
+            reason: Some("autoreload".into()),
+            ..Default::default()
+        }])
+        .await;
+    assert_applied(&response);
+    assert!(
+        is_allowed(test, ip),
+        "allowed IP not in the running settings"
+    );
+    let allowed_id = response.created_id(0);
+    let response = admin
+        .registry_destroy(ObjectType::AllowedIp, [allowed_id])
+        .await;
+    assert_applied(&response);
+    assert!(!is_allowed(test, ip), "destroyed allowed IP still live");
+
+    // Data that isn't part of the running settings doesn't reload them
+    let response = admin
+        .registry_create([Domain {
+            name: "autoreload.example.org".into(),
+            certificate_management: CertificateManagement::Manual,
+            dns_management: DnsManagement::Manual,
+            dkim_management: DkimManagement::Manual,
+            ..Default::default()
+        }])
+        .await;
+    assert!(settings_reload(&response).is_none(), "{response:?}");
+}
+
+fn settings_reload(response: &JmapResponse) -> Option<&Value> {
+    response.pointer("/methodResponses/0/1/x:settingsReload")
+}
+
+fn assert_applied(response: &JmapResponse) {
+    assert_eq!(
+        settings_reload(response),
+        Some(&serde_json::json!({"applied": true})),
+        "{response:?}"
+    );
+}
+
+fn has_schedule(test: &TestServer, name: &str) -> bool {
+    test.server
+        .inner
+        .build_server()
+        .core
+        .smtp
+        .queue
+        .queue_strategy
+        .contains_key(name)
+}
+
+fn is_allowed(test: &TestServer, ip: std::net::IpAddr) -> bool {
+    test.server.inner.build_server().is_ip_allowed(ip)
+}

tests/src/system/mod.rs

@@ -11,6 +11,7 @@ pub mod authentication;
 pub mod ai;
 pub mod ai_calibration;
 pub mod authorization;
+pub mod auto_reload; // inbuxa: registry writes apply at once
 pub mod branding;
 pub mod crypto;
 pub mod delivery;