feat: enhance AIPlanner with loading spinner during Ollama requests and update print statements for clarity

ai_planner.py

@@ -15,7 +15,9 @@ LLM 백엔드: 로컬 Ollama (structured output으로 JSON 스키마 강제)
 import json
 import os
 import re
+import sys
 import time
+import threading
 import traceback
 import ollama
 
@@ -141,7 +143,7 @@ class AIPlanner:
             "⚠️ 제작은 재료가 있어야 합니다. 인벤토리를 확인하세요."
         )
 
-        print(f"\n[AI] 생각 중... (model={OLLAMA_MODEL}, host={OLLAMA_HOST})")
+        print(f"\n[AI] 요청 시작 (model={OLLAMA_MODEL})")
 
         try:
             plan = self._call_ollama(user_message)
@@ -177,36 +179,53 @@ class AIPlanner:
 
     def _call_ollama(self, user_message: str) -> dict:
         t0 = time.perf_counter()
-        client = ollama.Client(host=OLLAMA_HOST)
-        response = client.chat(
-            model=OLLAMA_MODEL,
-            messages=[
-                {"role": "system", "content": SYSTEM_PROMPT},
-                {"role": "user",   "content": user_message},
-            ],
-            format={
-                "type": "object",
-                "properties": {
-                    "thinking":     {"type": "string"},
-                    "current_goal": {"type": "string"},
-                    "actions": {
-                        "type": "array",
-                        "items": {
-                            "type": "object",
-                            "properties": {
-                                "action": {"type": "string"},
-                                "params": {"type": "object"},
-                                "reason": {"type": "string"},
+        stop_event = threading.Event()
+
+        def _spinner():
+            while not stop_event.is_set():
+                elapsed = time.perf_counter() - t0
+                print(f"\r[AI] 생각 중... {elapsed:.0f}s", end="", flush=True)
+                stop_event.wait(1.0)
+            print("\r", end="")
+
+        spinner = threading.Thread(target=_spinner, daemon=True)
+        spinner.start()
+
+        try:
+            client = ollama.Client(host=OLLAMA_HOST)
+            response = client.chat(
+                model=OLLAMA_MODEL,
+                messages=[
+                    {"role": "system", "content": SYSTEM_PROMPT},
+                    {"role": "user",   "content": user_message},
+                ],
+                format={
+                    "type": "object",
+                    "properties": {
+                        "thinking":     {"type": "string"},
+                        "current_goal": {"type": "string"},
+                        "actions": {
+                            "type": "array",
+                            "items": {
+                                "type": "object",
+                                "properties": {
+                                    "action": {"type": "string"},
+                                    "params": {"type": "object"},
+                                    "reason": {"type": "string"},
+                                },
+                                "required": ["action", "params"],
                             },
-                            "required": ["action", "params"],
                         },
+                        "after_this": {"type": "string"},
                     },
-                    "after_this": {"type": "string"},
+                    "required": ["actions"],
                 },
-                "required": ["actions"],
-            },
-            options={"temperature": 0.3},
-        )
+                options={"temperature": 0.3},
+            )
+        finally:
+            stop_event.set()
+            spinner.join()
+
         dt = time.perf_counter() - t0
         content = response.message.content
         print(f"[AI] 응답 수신 ({dt:.2f}s, {len(content)}자)")