Fix Shelly unreachable: roll back engine state on failed actions

Without this, a failed Execute() left engine state diverged from hardware.
SyncHardwareState would then misread the mismatch as a manual override and
apply a 1-hour lockout — causing either a stuck-on or stuck-off loop.

Now Execute() returns per-action []error. The control loop calls
Engine.RollbackAction() for each failed action, keeping engine state in
sync with hardware so the next cycle simply retries.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

internal/actuator/actuator.go

@@ -38,26 +38,30 @@ func NewActuator(cfg *config.Config, vc *viessmann.Client, logger *slog.Logger)
 	}
 }
 
-// Execute performs a list of switching actions.
-func (a *Actuator) Execute(ctx context.Context, actions []engine.Action) error {
-	for _, action := range actions {
+// Execute performs a list of switching actions and returns one error per action
+// (nil on success). Failed actions do not prevent subsequent actions from running.
+// The caller should roll back engine state for any failed action using
+// Engine.RollbackAction so that the next SyncHardwareState cycle does not mistake
+// the divergence for a manual override.
+func (a *Actuator) Execute(ctx context.Context, actions []engine.Action) []error {
+	errs := make([]error, len(actions))
+	for i, action := range actions {
 		if err := a.executeOne(ctx, action); err != nil {
 			a.logger.Error("action failed",
 				"consumer", action.Consumer,
 				"turn_on", action.TurnOn,
 				"error", err,
 			)
-			// Continue with other actions even if one fails
+			errs[i] = err
 			continue
 		}
-
 		a.logger.Info("action executed",
 			"consumer", action.Consumer,
 			"turn_on", action.TurnOn,
 			"reason", action.Reason,
 		)
 	}
-	return nil
+	return errs
 }
 
 func (a *Actuator) executeOne(ctx context.Context, action engine.Action) error {

internal/actuator/actuator_test.go

@@ -88,11 +88,11 @@ func TestExecuteTurnOnSGReady(t *testing.T) {
 
 	act := testActuator(t, ipFrom(sgSrv), ipFrom(dummySrv), ipFrom(dummySrv))
 
-	err := act.Execute(context.Background(), []engine.Action{
+	errs := act.Execute(context.Background(), []engine.Action{
 		{Consumer: engine.ConsumerSGReady, TurnOn: true, Reason: "test"},
 	})
-	if err != nil {
-		t.Fatalf("Execute failed: %v", err)
+	if errs[0] != nil {
+		t.Fatalf("Execute failed: %v", errs[0])
 	}
 
 	if !sg.state {
@@ -112,11 +112,11 @@ func TestExecuteTurnOffWallboxA(t *testing.T) {
 
 	act := testActuator(t, ipFrom(dummySrv), ipFrom(wbASrv), ipFrom(dummySrv))
 
-	err := act.Execute(context.Background(), []engine.Action{
+	errs := act.Execute(context.Background(), []engine.Action{
 		{Consumer: engine.ConsumerWallboxA, TurnOn: false, Reason: "import"},
 	})
-	if err != nil {
-		t.Fatalf("Execute failed: %v", err)
+	if errs[0] != nil {
+		t.Fatalf("Execute failed: %v", errs[0])
 	}
 
 	if wbA.state {
@@ -164,13 +164,14 @@ func TestExecuteMultipleActions(t *testing.T) {
 
 	act := testActuator(t, ipFrom(sgSrv), ipFrom(wbASrv), ipFrom(wbBSrv))
 
-	err := act.Execute(context.Background(), []engine.Action{
+	for i, err := range act.Execute(context.Background(), []engine.Action{
 		{Consumer: engine.ConsumerSGReady, TurnOn: true},
 		{Consumer: engine.ConsumerWallboxA, TurnOn: true},
 		{Consumer: engine.ConsumerWallboxB, TurnOn: true},
-	})
+	}) {
 		if err != nil {
-		t.Fatalf("Execute failed: %v", err)
+			t.Fatalf("Execute action %d failed: %v", i, err)
+		}
 	}
 
 	if !sg.state || !wbA.state || !wbB.state {

internal/engine/engine.go

@@ -755,6 +755,34 @@ func (e *Engine) ApplyOverride(consumer Consumer, on bool, duration time.Duratio
 	)
 }
 
+// RollbackAction reverts the engine's internal state for an action that the actuator
+// failed to execute. Without this, the engine believes the switch happened, diverges
+// from hardware, and SyncHardwareState will misinterpret the next read-back as a
+// manual override and apply a 1-hour lockout.
+//
+// After rollback the engine state matches hardware again, so the next cycle's
+// SyncHardwareState sees no mismatch and the action is simply retried.
+func (e *Engine) RollbackAction(action Action) {
+	cs, ok := e.consumers[action.Consumer]
+	if !ok {
+		return
+	}
+	e.logger.Warn("rolling back engine state after failed action",
+		"consumer", action.Consumer,
+		"turn_on", action.TurnOn,
+	)
+	cs.Active = !action.TurnOn
+	if action.TurnOn {
+		// Turn-on failed: undo activation side-effects
+		cs.ActivatedAt = time.Time{}
+		cs.ProactiveCharging = false
+		cs.ProbeStartGridW = 0
+		cs.LowPowerCycles = 0
+	}
+	// Turn-off failed: just restore Active=true. ActivatedAt is preserved
+	// (shutdown code doesn't reset it), so min-runtime stays correct.
+}
+
 // isHeatingPeriod returns true if heating is appropriate given the current month
 // and outdoor temperature. If HeatingMinAmbientC is configured (> 0), ambient
 // temperatures above that threshold suppress SG-Ready even within the heating months.

main.go

@@ -361,8 +361,10 @@ func runCycle(
 		return
 	}
 
-	if err := act.Execute(ctx, actions); err != nil {
-		logger.Error("execution failed", "error", err)
+	for i, err := range act.Execute(ctx, actions) {
+		if err != nil {
+			eng.RollbackAction(actions[i])
+		}
 	}
 }
 
@@ -520,8 +522,8 @@ func wwResetHandler(act *actuator.Actuator, eng *engine.Engine, cfg *config.Conf
 			TargetTempC: cfg.Strategic.WWBaseC,
 			Reason:      "manual WW reset via web UI",
 		}
-		if err := act.Execute(ctx, []engine.Action{action}); err != nil {
-			logger.Error("WW reset: actuator failed", "error", err)
+		if errs := act.Execute(ctx, []engine.Action{action}); errs[0] != nil {
+			logger.Error("WW reset: actuator failed", "error", errs[0])
 		} else {
 			logger.Info("WW boost reset", "base_c", cfg.Strategic.WWBaseC, "locked_until", midnight.Format("15:04"))
 		}
@@ -611,8 +613,8 @@ func overrideHandler(act *actuator.Actuator, eng *engine.Engine, logger *slog.Lo
 			TurnOn:   turnOn,
 			Reason:   fmt.Sprintf("manual override via web UI (%s)", duration),
 		}
-		if err := act.Execute(ctx, []engine.Action{action}); err != nil {
-			logger.Error("web UI override failed", "consumer", consumerKey, "state", stateVal, "error", err)
+		if errs := act.Execute(ctx, []engine.Action{action}); errs[0] != nil {
+			logger.Error("web UI override failed", "consumer", consumerKey, "state", stateVal, "error", errs[0])
 			http.Error(w, "switch failed — check logs", http.StatusInternalServerError)
 			return
 		}