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/lib/chatDebug.test.ts

@@ -0,0 +1,34 @@
+import { describe, expect, it } from "vitest";
+
+import { formatChatDebugTranscript } from "./chatDebug";
+
+describe("formatChatDebugTranscript", () => {
+  it("includes user and assistant details for a full chat export", () => {
+    const output = formatChatDebugTranscript({
+      chatId: 7,
+      messages: [
+        { id: 10, chat_id: 7, role: "user", content: "Pergunta", created_at: 1710000000 },
+        {
+          id: 11,
+          chat_id: 7,
+          role: "assistant",
+          content: "Resposta",
+          reasoning_content: "Rascunho interno",
+          prompt_tokens: 12,
+          completion_tokens: 34,
+          total_tokens: 46,
+          tokens_per_second: 19.4,
+          created_at: 1710000060,
+        },
+      ],
+    });
+
+    expect(output).toContain("Chat ID: 7");
+    expect(output).toContain("[USER] #10");
+    expect(output).toContain("Pergunta");
+    expect(output).toContain("[ASSISTANT] #11");
+    expect(output).toContain("Resposta");
+    expect(output).toContain("Reasoning:\nRascunho interno");
+    expect(output).toContain("Usage: prompt=12 completion=34 total=46 tps=19.4");
+  });
+});