hub: Restart controller (the agent's closed list on the host-report reply) and Clear hold (D64 = B, the controller's list) on the host page, each behind a confirm; controller_unresponsive (R-1344, alarm only); 04 §6.1 + 09 §3 decision 283; wire gate declares both new wires; R-1344 filed — tests red first

hub/internal/monitor/controller_supervisor.go

@@ -42,6 +42,7 @@ type supSeen struct {
 	lastRestartAt      string
 	crashloopSince     string
 	slowCrashloopSince string
+	unresponsiveSince  string
 }
 
 // ControllerSupervisorGuest mirrors the agent's hub.ControllerSupervisorGuest wire shape.
@@ -57,6 +58,10 @@ type ControllerSupervisorGuest struct {
 	Restarts24h        int    `json:"restarts_24h"`
 	SlowCrashloop      bool   `json:"slow_crashloop"`
 	SlowCrashloopSince string `json:"slow_crashloop_since"`
+	// R-1344 (agent ≥ the 2026-10-29 release): the controller runs but Docker's health check has failed for several
+	// sweeps. ALARM ONLY — no restart until the measurement licenses one. Absent on older agents → never an event.
+	Unresponsive      bool   `json:"unresponsive"`
+	UnresponsiveSince string `json:"unresponsive_since"`
 }
 
 // ParseControllerSupervisor extracts the stanza from a host report body. A missing or malformed
@@ -98,7 +103,8 @@ func (c *ControllerSupervisorChecker) observe(hostID, customerID string, guests
 	for _, g := range guests {
 		key := fmt.Sprintf("%s/%d", hostID, g.VMID)
 		prev, known := c.seen[key]
-		c.seen[key] = supSeen{lastRestartAt: g.LastRestartAt, crashloopSince: g.CrashloopSince, slowCrashloopSince: g.SlowCrashloopSince}
+		c.seen[key] = supSeen{lastRestartAt: g.LastRestartAt, crashloopSince: g.CrashloopSince, slowCrashloopSince: g.SlowCrashloopSince,
+			unresponsiveSince: g.UnresponsiveSince}
 		if !known {
 			if g.Crashloop && g.CrashloopSince != "" {
 				c.emit(customerID, hostID, g, "controller_crashloop")
@@ -106,6 +112,9 @@ func (c *ControllerSupervisorChecker) observe(hostID, customerID string, guests
 			if g.SlowCrashloop && g.SlowCrashloopSince != "" {
 				c.emit(customerID, hostID, g, "controller_slow_crashloop")
 			}
+			if g.Unresponsive && g.UnresponsiveSince != "" {
+				c.emit(customerID, hostID, g, "controller_unresponsive")
+			}
 			continue
 		}
 		if g.LastRestartAt != "" && g.LastRestartAt != prev.lastRestartAt {
@@ -117,6 +126,9 @@ func (c *ControllerSupervisorChecker) observe(hostID, customerID string, guests
 		if g.SlowCrashloopSince != "" && g.SlowCrashloopSince != prev.slowCrashloopSince {
 			c.emit(customerID, hostID, g, "controller_slow_crashloop")
 		}
+		if g.UnresponsiveSince != "" && g.UnresponsiveSince != prev.unresponsiveSince {
+			c.emit(customerID, hostID, g, "controller_unresponsive")
+		}
 	}
 }
 
@@ -135,6 +147,10 @@ func (c *ControllerSupervisorChecker) emit(customerID, hostID string, g Controll
 		severity = "warning"
 		message = fmt.Sprintf("Host %s guest %d: the controller keeps dying — the agent restarted it %d times in 24 hours (each one too far apart for the 15-minute brake). It is still being restarted; this is the warning that it will not stay up. Last reason: %s",
 			hostID, g.VMID, g.Restarts24h, g.LastReason)
+	case "controller_unresponsive":
+		severity = "warning"
+		message = fmt.Sprintf("Host %s guest %d: the controller runs but does not answer its health check (since %s). The agent does NOT restart it yet (R-1344: the measurement must first show a busy night never looks like this) — use „Restart controller\" on the host page if it stays so.",
+			hostID, g.VMID, g.UnresponsiveSince)
 	default:
 		return
 	}
@@ -143,6 +159,7 @@ func (c *ControllerSupervisorChecker) emit(customerID, hostID string, g Controll
 		"last_restart_at": g.LastRestartAt, "last_reason": g.LastReason,
 		"crashloop_since": g.CrashloopSince, "parked": g.Parked,
 		"restarts_24h": g.Restarts24h, "slow_crashloop_since": g.SlowCrashloopSince,
+		"unresponsive_since": g.UnresponsiveSince,
 	})
 	c.logger.Printf("[INFO] Controller supervisor: %s %s/%d (%s)", eventType, hostID, g.VMID, g.LastReason)
 	if _, err := c.store.SaveEvent(customerID, eventType, severity, message, string(details), "hub"); err != nil {