fix(#2398): correct stale doc on handle_restart_scoped

argus caught it: the function-level /// comment still described the
old submit-await-submit graceful approach after the code moved to
one atomic GracefulRestart DAG.

docs/coordinator.md

@@ -78,6 +78,7 @@ container build:
 rebuild(a):        Prebuild(a) → StopForUpdate(a) → Swap(a) →(after-any) Reconcile(a)
 graceful-stop(a):  [wanted=Offline]  Signal(a) → Drain(a) → Reconcile(a)
 restart(a):        [wanted=Up]       StopForUpdate(a) → Reconcile(a)
+graceful-restart(a): [wanted=Up]     Signal(a) → Drain(a) → StopForUpdate(a) → Reconcile(a)
 start(a):          [wanted=Up]       Reconcile(a)     (stale rev ⇒ upgraded to rebuild)
 stop(a):           [wanted=Offline]  Reconcile(a)
 spawn(a):          [wanted=Up]  Create(a) → WriteDropin(a) → Reconcile(a)

hive-c0re/src/bin/hivectl.rs

@@ -1642,22 +1642,33 @@ async fn start(socket: &Path, scope: hive_host_sock::LifecycleScope, no_wait: bo
     rendered
 }
 
-/// Restart = `stop` then `start` over the same scope, composed client-side
-/// from the two daemon ops (no dedicated wire op). The stop phase honours
-/// `--graceful`; if it reports a failure (`stop` returns `Err`) the `?`
-/// short-circuits before the start phase, so a half-stopped hive isn't
-/// blindly started over — the operator sees the stop errors and can recover.
+/// Restart — one `RestartScoped` daemon call, server-side DAG-based (see
+/// issue tracker "dagify hivectl commands"). Each targeted agent rides
+/// exactly one atomic DAG queued up front — `Restart` (mechanical stop +
+/// reconcile), or `GracefulRestart` with `--graceful` (signal → drain →
+/// mechanical stop → reconcile); infra containers restart synchronously.
+/// No "submit one DAG, wait for it, submit another" composition on either
+/// side of the wire: unlike the old client-side stop-then-start compose, a
+/// dropped `hivectl` connection mid-restart no longer leaves an agent
+/// stopped with no automatic follow-up — the daemon owns the whole
+/// sequence once this call is made.
 ///
-/// No `--no-wait` here on purpose: the stop DAGs must complete before
-/// the start submits, otherwise the start's `wanted = Up` write would
-/// land before the queued stops execute and turn them into noops.
+/// No `--no-wait` here on purpose, same as before: the operator wants to
+/// see the restart actually land, not just get queued.
 async fn restart(
     socket: &Path,
     scope: hive_host_sock::LifecycleScope,
     graceful: bool,
 ) -> Result<()> {
-    stop(socket, scope.clone(), graceful, false).await?;
-    start(socket, scope, false).await
+    let resp = hive_c0re::client::request(
+        socket,
+        hive_host_sock::HostRequest::RestartScoped { scope, graceful },
+    )
+    .await
+    .with_context(|| format!("connect to daemon socket {}", socket.display()))?;
+    let rendered = render_lifecycle(&resp, "restart queued");
+    wait_for_dags(socket, resp.queued_dags.unwrap_or_default(), false).await?;
+    rendered
 }
 
 /// A [`LifecycleScope`](hive_host_sock::LifecycleScope) targeting exactly one

hive-c0re/src/job_queue/exec.rs

@@ -507,7 +507,11 @@ pub(super) async fn on_dag_terminal(coord: &Arc<Coordinator>, terminal: &Termina
     if terminal.state == State::Cancelled
         && matches!(
             terminal.template,
-            Template::Start | Template::Stop | Template::GracefulStop | Template::Restart
+            Template::Start
+                | Template::Stop
+                | Template::GracefulStop
+                | Template::Restart
+                | Template::GracefulRestart
         )
     {
         let running = crate::lifecycle::is_running(&terminal.agent).await;

hive-c0re/src/job_queue/submit.rs

@@ -100,6 +100,19 @@ pub fn graceful_stop(coord: &Arc<Coordinator>, agent: &str, source: Source, reas
     submit_and_emit(coord, templates::graceful_stop(agent, source, reason))
 }
 
+/// Graceful restart: persist `wanted = Up`, then signal → drain →
+/// mechanical stop → reconcile (starts it back up) — one atomic DAG,
+/// no client-side "await the stop DAG then submit a start DAG" split.
+pub fn graceful_restart(
+    coord: &Arc<Coordinator>,
+    agent: &str,
+    source: Source,
+    reason: String,
+) -> u64 {
+    set_wanted(coord, agent, Wanted::Up);
+    submit_and_emit(coord, templates::graceful_restart(agent, source, reason))
+}
+
 /// Perm change: commit the JSON file(s) then rebuild.
 pub fn perm_change(
     coord: &Arc<Coordinator>,

hive-c0re/src/job_queue/templates.rs

@@ -7,6 +7,7 @@
 //! rebuild(a):        Prebuild(a) → StopForUpdate(a) → Swap(a) →(any) Reconcile(a)
 //! graceful-stop(a):  [wanted=Offline]  Signal(a) → Drain(a) → Reconcile(a)
 //! restart(a):        [wanted=Up]       StopForUpdate(a) → Reconcile(a)
+//! graceful-restart(a): [wanted=Up]     Signal(a) → Drain(a) → StopForUpdate(a) → Reconcile(a)
 //! start(a):          [wanted=Up]       Reconcile(a)
 //! stop(a):           [wanted=Offline]  Reconcile(a)
 //! spawn(a):          [wanted=Up]  Provision(a) → Create(a) → WriteDropin(a) → Reconcile(a)
@@ -168,6 +169,46 @@ pub fn restart(agent: &str, source: Source, reason: String) -> DagSpec {
     }
 }
 
+/// Graceful restart: signal → drain → mechanical stop → converge to
+/// `wanted` — the caller writes `wanted = Up` first, same as `restart`.
+/// One atomic DAG start to finish (no client- or server-side "submit
+/// one DAG, await it, submit the next" composition): the `Drain` node
+/// is the same bounded harness-checkpoint wait `graceful_stop` uses,
+/// then `StopForUpdate` (mechanical, ignores `wanted`) and the tail
+/// `Reconcile` (converges to `wanted = Up`, i.e. starts it back up)
+/// chain exactly like `restart`'s tail.
+pub fn graceful_restart(agent: &str, source: Source, reason: String) -> DagSpec {
+    DagSpec {
+        template: Template::GracefulRestart,
+        agent: agent.to_owned(),
+        source,
+        reason,
+        parent_id: None,
+        approval_id: None,
+        inputs: Vec::new(),
+        perm_payload: None,
+        transient: Some(TransientKind::Restarting),
+        nodes: vec![
+            NodeSpec {
+                kind: NodeKind::Signal,
+                deps: Vec::new(),
+            },
+            NodeSpec {
+                kind: NodeKind::Drain,
+                deps: after_ok(0),
+            },
+            NodeSpec {
+                kind: NodeKind::StopForUpdate,
+                deps: after_ok(1),
+            },
+            NodeSpec {
+                kind: NodeKind::Reconcile,
+                deps: after_ok(2),
+            },
+        ],
+    }
+}
+
 /// Single-`Reconcile` DAG: `Start` / `Stop` (caller writes `wanted`
 /// first) and the boot-time `Reconcile` converge (wanted untouched).
 pub fn reconcile_only(

hive-c0re/src/server.rs

@@ -94,6 +94,9 @@ async fn dispatch(req: &HostRequest, coord: Arc<Coordinator>) -> HostResponse {
             HostRequest::Kill { name } => submit_single(&coord, name, Verb::Kill),
             HostRequest::Restart { name } => submit_single(&coord, name, Verb::Restart),
             HostRequest::RestartAll => handle_restart_all(&coord).await?,
+            HostRequest::RestartScoped { scope, graceful } => {
+                handle_restart_scoped(&coord, scope, *graceful).await?
+            }
             HostRequest::Stop { scope, graceful } => {
                 // Resolve the scope to explicit container names at the entry
                 // point, then operate on names — never pass the bare "all
@@ -631,6 +634,76 @@ async fn handle_start(
     Ok(resp)
 }
 
+/// Restart containers hive-wide (`hivectl restart`) — the DAG-based
+/// sibling of [`handle_stop`]/[`handle_start`], replacing the old
+/// client-side stop-then-start composition (issue tracker "dagify hivectl
+/// commands"). Each targeted agent gets exactly one atomic DAG submitted
+/// up front: the `Restart` template (mechanical stop + reconcile) in the
+/// common case, or `GracefulRestart` (signal → drain → mechanical stop →
+/// reconcile) with `graceful` set — no "submit a DAG, wait for it, submit
+/// another" composition on either path, so a dropped `hivectl` connection
+/// never strands an agent, the same way `handle_restart_all` already
+/// avoids it. Infra containers have no lease/DAG and restart
+/// synchronously (stop then start).
+async fn handle_restart_scoped(
+    coord: &Arc<Coordinator>,
+    scope: &LifecycleScope,
+    graceful: bool,
+) -> Result<HostResponse> {
+    tracing::info!(?scope, graceful, "restart");
+    let agents = scoped_agents(scope).await?;
+    let infra = scoped_infra(scope);
+    let mut ok_items: Vec<String> = Vec::new();
+    let mut errors: Vec<String> = Vec::new();
+    let mut queued: Vec<u64> = Vec::new();
+
+    // One atomic DAG per agent, submitted up front — `Restart`
+    // (mechanical stop + reconcile) or, with `--graceful`,
+    // `GracefulRestart` (signal → drain → mechanical stop → reconcile).
+    // No client- or server-side "submit a stop DAG, await it, then
+    // submit a start DAG" composition: that window is exactly the
+    // dropped-connection gap this DAG-based path exists to close.
+    for agent in &agents {
+        let id = if graceful {
+            crate::job_queue::submit::graceful_restart(
+                coord,
+                agent,
+                crate::job_queue::Source::Manual,
+                "manual via hivectl restart --graceful".to_owned(),
+            )
+        } else {
+            crate::job_queue::submit::restart(
+                coord,
+                agent,
+                crate::job_queue::Source::Manual,
+                "manual restart via hivectl restart".to_owned(),
+            )
+        };
+        queued.push(id);
+        ok_items.push(agent.clone());
+    }
+
+    for &container in &infra {
+        let name = container.unit_name();
+        let res = async {
+            crate::priv_client::control_infra_container(container, InfraAction::Stop).await?;
+            crate::priv_client::control_infra_container(container, InfraAction::Start).await
+        }
+        .await;
+        match res {
+            Ok(()) => ok_items.push(name.to_owned()),
+            Err(e) => {
+                tracing::warn!(%name, error = ?e, "restart: infra restart failed");
+                errors.push(format!("{name}: {e:#}"));
+            }
+        }
+    }
+
+    let mut resp = finish_lifecycle(ok_items, &errors);
+    resp.queued_dags = Some(queued);
+    Ok(resp)
+}
+
 /// Resolve which sub-agent logical names a scope targets: every live
 /// container (from `lifecycle::list`) when `agents` is set or the scope is
 /// "everything", plus any explicit `agent_names`. Returns de-duplicated

hive-host-sock/src/lib.rs

@@ -39,6 +39,28 @@ pub enum HostRequest {
     /// wrapper for `hivectl agents restart-all`; iterates the live
     /// container list and restarts each one.
     RestartAll,
+    /// Restart containers hive-wide (`hivectl restart`), scoped like
+    /// `Stop`/`Start`. Each targeted agent rides exactly one DAG
+    /// server-side — the `Restart` template (mechanical stop + reconcile),
+    /// or, when `graceful` is set, the `GracefulRestart` template (signal →
+    /// drain → mechanical stop → reconcile) — rather than the old
+    /// client-side stop-then-start composition (and, briefly, a server-side
+    /// "submit stop DAG, await it, submit start DAG" composition): a
+    /// dropped `hivectl` connection mid-way, or a crash between the two
+    /// submits, used to leave the agent stopped with no automatic
+    /// follow-up, since nothing durable remembered "finish the restart"
+    /// once the calling process/turn was gone. `GracefulRestart` closes
+    /// that gap the same way `Restart` already does — one DAG, queued up
+    /// front, that owns the whole sequence. Infra containers have no
+    /// lease/DAG and restart synchronously (stop then start), same as
+    /// before. Scope semantics match `Stop`/`Start` (all-false =
+    /// everything).
+    RestartScoped {
+        #[serde(default)]
+        scope: LifecycleScope,
+        #[serde(default)]
+        graceful: bool,
+    },
     /// Apply pending config to a managed container.
     Rebuild { name: String },
     /// List managed containers.

hive-sh4re/src/jobs.rs

@@ -29,6 +29,11 @@ pub enum Template {
     StartupSweep,
     /// Mechanical stop + converge to `wanted = Up` (a restart).
     Restart,
+    /// Signal → drain → mechanical stop → converge to `wanted = Up` — a
+    /// graceful restart as one atomic DAG (drains the harness before the
+    /// stop, same as `GracefulStop`, but then reconciles back up instead
+    /// of staying down).
+    GracefulRestart,
     /// Perm-file commit followed by the rebuild subgraph.
     PermChange,
     /// Quiesce the harness, drain, then stop (`wanted = Offline`).
@@ -56,6 +61,7 @@ impl Template {
             Template::Destroy => "destroy",
             Template::StartupSweep => "startup_sweep",
             Template::Restart => "restart",
+            Template::GracefulRestart => "graceful_restart",
             Template::PermChange => "perm_change",
             Template::GracefulStop => "graceful_stop",
             Template::Start => "start",