Move progress logs into thinking box alongside LLM reasoning

Both __meta (LangGraph/search progress) and __thinking (LLM reasoning)
tokens now stream into the thinking box instead of the chatbot.
Chatbot shows only the final answer. Thinking box shows the full
analysis pipeline: [LangGraph → ...], 문서 검색 중, thinking content.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app.py

@@ -105,9 +105,9 @@ async def respond(message, history, show_thinking, user_id, use_tts, run_ids):
     yield history, "", None, run_ids, gr.update(value="", visible=False)
 
     collected_run_id: str | None = None
-    tts_text = ""       # 순수 답변만 누적 (TTS용)
-    thinking_acc = ""   # 사고 과정 누적
-    thinking_active = False
+    tts_text = ""            # 순수 답변만 누적 (TTS용)
+    thinking_acc = ""        # 사고 과정 + 진행 로그 누적
+    thinking_finalized = False  # 첫 답변 토큰 도착 시 박스 완료 처리
 
     try:
         async for token, run_id in api_client.chat(message, user_id, show_thinking):
@@ -115,26 +115,31 @@ async def respond(message, history, show_thinking, user_id, use_tts, run_ids):
                 collected_run_id = run_id
                 break
 
+            # 사고 과정(LLM thinking) — 박스에 추가
             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)
+                yield history, "", None, run_ids, gr.update(
+                    value=f"🤔 **분석 중...**\n\n{thinking_acc}▌", visible=True
+                )
                 continue
 
-            if thinking_active:
-                # 첫 답변 토큰 도착 — 사고 완료 표시
-                thinking_active = False
+            # 진행 로그(LangGraph, 검색 등) — 박스에 추가 (챗봇에는 표시 안 함)
+            if isinstance(token, dict) and "__meta" in token:
+                thinking_acc += token["__meta"]
                 yield history, "", None, run_ids, gr.update(
-                    value=f"💭 **사고 완료**\n\n{thinking_acc}", visible=True
+                    value=f"🤔 **분석 중...**\n\n{thinking_acc}▌", visible=True
+                )
+                continue
+
+            # 첫 답변 토큰 도착 — 박스를 완료 상태로 전환
+            if thinking_acc and not thinking_finalized:
+                thinking_finalized = True
+                yield history, "", None, run_ids, gr.update(
+                    value=f"💭 **분석 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
+            tts_text += token
+            history[-1]["content"] += token
             yield history, "", None, run_ids, gr.update()
 
     except Exception as e: