Heartbeat-first dispatch: retire WoL-as-default, add WaitingReboot

Every supported host runs vetting-reporter in-OS and heartbeats every
30s. WoL was never the thing that started vetting — the heartbeat
response's reboot_for_vetting command was. Firing WoL first only
crowded the run log with misleading diagnostics when the real failure
mode is "reporter isn't installed."

- StartRun 409s if the host hasn't heartbeated within 60s, pointing
  the operator at /register/quick.sh.
- Dispatcher re-checks LastSeenAt at dispatch time (run may sit in
  Queued long enough for the host to go offline); stale hosts mark
  the run Failed with failed_stage=dispatch instead of looping.
- New StateWaitingReboot + TriggerRebootCommanded capture the actual
  semantics. StateWaitingWoL kept as the hook point for a future
  manual-override button.
- Tile disables the Start button with a quick.sh tooltip when the
  host is offline, matching the server-side 409.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

internal/web/templates/host_tile_templ.go

@@ -176,7 +176,7 @@ func HostTile(t TileData) templ.Component {
 		if templ_7745c5c3_Err != nil {
 			return templ_7745c5c3_Err
 		}
-		if canStart(t.Latest) {
+		if canStart(t) {
 			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 12, "<form method=\"post\" action=\"")
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
@@ -194,26 +194,31 @@ func HostTile(t TileData) templ.Component {
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
+		} else if canStartIfOnline(t.Latest) {
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 14, "<button type=\"button\" disabled title=\"host is not heartbeating — install the reporter via /register/quick.sh on the target host\">Start vetting</button>")
+			if templ_7745c5c3_Err != nil {
+				return templ_7745c5c3_Err
+			}
 		} else if hasReport(t.Latest) {
-			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 14, "<a class=\"button-like\" href=\"")
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 15, "<a class=\"button-like\" href=\"")
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
 			var templ_7745c5c3_Var14 templ.SafeURL
 			templ_7745c5c3_Var14, templ_7745c5c3_Err = templ.JoinURLErrs(templ.SafeURL(fmt.Sprintf("/reports/%d", t.Latest.ID)))
 			if templ_7745c5c3_Err != nil {
-				return templ.Error{Err: templ_7745c5c3_Err, FileName: `internal/web/templates/host_tile.templ`, Line: 36, Col: 88}
+				return templ.Error{Err: templ_7745c5c3_Err, FileName: `internal/web/templates/host_tile.templ`, Line: 38, Col: 88}
 			}
 			_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var14))
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
-			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 15, "\" target=\"_blank\" rel=\"noopener\">View report</a>")
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 16, "\" target=\"_blank\" rel=\"noopener\">View report</a>")
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
 		}
-		templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 16, "</div></article>")
+		templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 17, "</div></article>")
 		if templ_7745c5c3_Err != nil {
 			return templ_7745c5c3_Err
 		}
@@ -235,12 +240,29 @@ func hasReport(r *model.Run) bool {
 	return r != nil && r.State == model.StateCompleted
 }
 
-func canStart(r *model.Run) bool {
+// canStart gates the Start button on two things: the run is in a state
+// that accepts a fresh start, AND the host is currently heartbeating.
+// The heartbeat check mirrors the StartRun handler's preflight so the
+// button never offers a click that the server would reject with 409.
+func canStart(t TileData) bool {
+	if !canStartIfOnline(t.Latest) {
+		return false
+	}
+	if t.LastSeenAt == nil {
+		return false
+	}
+	return time.Since(*t.LastSeenAt) <= 60*time.Second
+}
+
+// canStartIfOnline is the run-state half of canStart, split out so the
+// template can distinguish "waiting on run to end" (no button) from
+// "run is done but host is offline" (disabled button with tooltip).
+func canStartIfOnline(r *model.Run) bool {
 	if r == nil {
 		return true
 	}
 	switch r.State {
-	case model.StateCompleted, model.StateReleased, model.StateFailedHolding:
+	case model.StateCompleted, model.StateReleased, model.StateFailed, model.StateFailedHolding:
 		return true
 	}
 	return false
@@ -250,6 +272,10 @@ func tileStatus(r *model.Run) string {
 	if r == nil {
 		return "Idle"
 	}
+	switch r.State {
+	case model.StateWaitingReboot:
+		return "Waiting for reboot"
+	}
 	return string(r.State)
 }