fix(llm_client): remove response_format json_object for local LLM compatibility

LM Studio and Ollama do not support response_format: json_object,
only json_schema or text. This causes errors when using local LLMs.

The existing markdown fence cleanup logic in chat_json() already
handles parsing JSON from raw LLM output, making response_format
unnecessary. This change follows the same pattern as commit 985f89f
which improved compatibility with diverse model outputs.

Tested with: LM Studio + qwen3.5-9b (full predict pipeline passes)

backend/app/utils/llm_client.py

@@ -88,7 +88,8 @@ class LLMClient:
             messages=messages,
             temperature=temperature,
             max_tokens=max_tokens,
-            response_format={"type": "json_object"}
+            # 不設 response_format 以相容 LM Studio / Ollama 等本地模型
+            # 依賴 prompt 中的 JSON 指示 + 下方的 markdown 清理邏輯
         )
         # 清理markdown代码块标记
         cleaned_response = response.strip()