fix: Qwen3.5 thinking 모드 비활성화 (enable_thinking: false)

JSON 응답에 Thinking Process 텍스트가 섞이는 문제 해결.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

app/ai/client.py

@@ -125,6 +125,7 @@ class AIClient:
                     "model": model_config.model,
                     "messages": [{"role": "user", "content": prompt}],
                     "max_tokens": model_config.max_tokens,
+                    "chat_template_kwargs": {"enable_thinking": False},
                 },
                 timeout=model_config.timeout,
             )