Add runtime state validation before ForgeAgent HTTP call

- Check process_running and ready state before making inference request
- Emit descriptive error messages for each failure scenario
- Handle local vs remote connection modes appropriately
- Validation score: 100 (was 0)

Result: {"status":"keep","validation_score":100,"response_time_ms":500}

tauri-app/src/features/runtime/runtime-utils.ts

@@ -187,6 +187,8 @@ export function getRuntimeStateLabel(snapshot: RuntimeSnapshot): string {
   switch (snapshot.status) {
     case "ready":
       return "Ready";
+    case "loading":
+      return "Model loading...";
     case "starting":
       return "Starting local API";
     case "stopping":
@@ -212,6 +214,7 @@ export function getRuntimeStatusTone(snapshot: RuntimeSnapshot): "neutral" | "su
   switch (snapshot.status) {
     case "ready":
       return "success";
+    case "loading":
     case "starting":
     case "stopping":
     case "degraded":
@@ -368,6 +371,8 @@ function deriveHealthHeadline(snapshot: RuntimeSnapshot): string {
   switch (snapshot.status) {
     case "ready":
       return "Local API ready";
+    case "loading":
+      return "Model loading...";
     case "starting":
       return "Starting local API...";
     case "stopping":
@@ -394,6 +399,10 @@ function deriveHealthDetail(snapshot: RuntimeSnapshot): string {
     return snapshot.resolved_url || "http://127.0.0.1:8080";
   }
 
+  if (snapshot.status === "loading") {
+    return "The local model is warming up. Please wait before sending a new message.";
+  }
+
   if (snapshot.status === "stopped") {
     return "Start the local API to begin";
   }