Add thinking process visualization to WebUI

- Introduced "thinking box" UI to display intermediate thought processes.
- Added CSS styling for the thinking box with scrollable and formatted design.
- Updated response handling to show thinking progress and completion dynamically.
- Enhanced Gradio outputs to include the new thinking box component.

app.py

@@ -105,31 +105,53 @@ async def respond(message, history, show_thinking, user_id, use_tts, run_ids):
     yield history, "", None, run_ids
 
     collected_run_id: str | None = None
-    tts_text = ""  # 순수 답변만 누적 (메타 토큰 제외)
+    tts_text = ""       # 순수 답변만 누적 (TTS용)
+    thinking_acc = ""   # 사고 과정 누적
+    thinking_active = False
+
+    # 사고 과정 박스 초기화
+    yield history, "", None, run_ids, gr.update(value="", visible=False)
+
     try:
         async for token, run_id in api_client.chat(message, user_id, show_thinking):
             if run_id is not None:
                 collected_run_id = run_id
                 break
+
+            if isinstance(token, dict) and "__thinking" in token:
+                thinking_active = True
+                thinking_acc += token["__thinking"]
+                thinking_md = f"🤔 **사고 중...**\n\n{thinking_acc}▌"
+                yield history, "", None, run_ids, gr.update(value=thinking_md, visible=True)
+                continue
+
+            if thinking_active:
+                # 첫 답변 토큰 도착 — 사고 완료 표시
+                thinking_active = False
+                yield history, "", None, run_ids, gr.update(
+                    value=f"💭 **사고 완료**\n\n{thinking_acc}", visible=True
+                )
+
             if isinstance(token, dict) and "__meta" in token:
                 display_token = token["__meta"]
             else:
                 display_token = token
                 tts_text += display_token
             history[-1]["content"] += display_token
-            yield history, "", None, run_ids
+            yield history, "", None, run_ids, gr.update()
+
     except Exception as e:
         history[-1]["content"] += f"\n\n[오류: {e}]"
-        yield history, "", None, run_ids
+        yield history, "", None, run_ids, gr.update()
         return
 
     run_ids.append(collected_run_id)
 
     if use_tts:
         audio_path = await tts_speak(tts_text)
-        yield history, "", audio_path, run_ids
+        yield history, "", audio_path, run_ids, gr.update()
     else:
-        yield history, "", None, run_ids
+        yield history, "", None, run_ids, gr.update()
 
 
 def handle_feedback(like_data: gr.LikeData, history, run_ids, user_id):
@@ -205,7 +227,22 @@ def delete_doc(source):
 
 # ── UI 구성 ──────────────────────────────────────────────────────
 
-with gr.Blocks(title="율봇") as demo:
+_THINKING_CSS = """
+.thinking-box {
+    background: #f9f9f9;
+    border-left: 3px solid #bbb;
+    border-radius: 6px;
+    padding: 10px 14px;
+    margin-bottom: 6px;
+    max-height: 220px;
+    overflow-y: auto;
+    font-size: 0.85em;
+    color: #555;
+    white-space: pre-wrap;
+}
+"""
+
+with gr.Blocks(title="율봇", css=_THINKING_CSS) as demo:
     gr.Markdown("# 율봇\n육아·금융 전문 AI 상담 도우미")
 
     user_state = gr.State(DEFAULT_USER)
@@ -220,6 +257,11 @@ with gr.Blocks(title="율봇") as demo:
                 scale=1,
             )
 
+        thinking_box = gr.Markdown(
+            value="",
+            visible=False,
+            elem_classes=["thinking-box"],
+        )
         chatbot = gr.Chatbot(label="율봇", height=500)
         with gr.Row():
             msg_box = gr.Textbox(
@@ -260,12 +302,12 @@ with gr.Blocks(title="율봇") as demo:
         send_btn.click(
             respond,
             inputs=[msg_box, chatbot, show_thinking, user_state, use_tts, run_ids_state],
-            outputs=[chatbot, msg_box, tts_output, run_ids_state],
+            outputs=[chatbot, msg_box, tts_output, run_ids_state, thinking_box],
         )
         msg_box.submit(
             respond,
             inputs=[msg_box, chatbot, show_thinking, user_state, use_tts, run_ids_state],
-            outputs=[chatbot, msg_box, tts_output, run_ids_state],
+            outputs=[chatbot, msg_box, tts_output, run_ids_state, thinking_box],
         )
         reset_btn.click(reset_chat, inputs=[user_state], outputs=[chatbot, run_ids_state])