diff --git a/frontend/app.py b/frontend/app.py
index af9d5b2..ed9c5a6 100644
--- a/frontend/app.py
+++ b/frontend/app.py
@@ -855,58 +855,65 @@ with tab2:
             )
 
         if review_btn:
+            rev_status_text = st.empty()
+            rev_status_text.info(f"⚙️ [AI Reviewer #2] 正在向阿里通义 Qwen ({selected_model}) 建立对抗性审查通道...")
+            with st.container():
+                critic_console = st.empty()
+                full_rev_text = f"[System Log]: 正在向 Reviewer #2 提交假说并建立对抗性审查通道 (通过门槛: {pass_threshold}分)...\n[System Log]: 待审查假说 ID: [{st.session_state.current_hypo.get('id', 'H1')}]\n\n[Reviewer #2 Stream Output]: "
+                critic_console.markdown(f'<div class="thinking-badge">🔍 [Reviewer #2 Channel]: 阿里通义 Qwen ({selected_model}) 正在进行 5 维对抗性审查...</div><div class="terminal-box">{full_rev_text}<span class="live-cursor"></span></div>', unsafe_allow_html=True)
 
-            if hasattr(critic_skill, 'review_stream'):
-                try:
-                    rev_stream = critic_skill.review_stream(st.session_state.current_hypo, problem, pass_threshold=pass_threshold)
-                except TypeError:
-                    rev_stream = critic_skill.review_stream(st.session_state.current_hypo, problem)
-            else:
-                try:
-                    rev_res = critic_skill.review(st.session_state.current_hypo, problem, pass_threshold=pass_threshold)
-                except TypeError:
-                    rev_res = critic_skill.review(st.session_state.current_hypo, problem)
-                rev_stream = [json.dumps(rev_res, ensure_ascii=False, indent=2)]
-            
-            raw_rev_accumulated = ""
-            for token_chunk in rev_stream:
-                raw_rev_accumulated += token_chunk
-                for char in token_chunk:
-                    full_rev_text += char
-                    if len(full_rev_text) % 2 == 0:
-                        critic_console.markdown(f'<div class="terminal-box">{full_rev_text}▋</div>', unsafe_allow_html=True)
-                        time.sleep(0.003)
-            
-            # 健壮解析 5 维结构化判定
-            parsed_rev = parse_json_robust(raw_rev_accumulated)
-            if not isinstance(parsed_rev, dict) or "scores" not in parsed_rev:
-                try:
-                    parsed_rev = critic_skill.review(st.session_state.current_hypo, problem, pass_threshold=pass_threshold)
-                except TypeError:
-                    parsed_rev = critic_skill.review(st.session_state.current_hypo, problem)
-                except Exception:
-                    pass
+                if hasattr(critic_skill, 'review_stream'):
+                    try:
+                        rev_stream = critic_skill.review_stream(st.session_state.current_hypo, problem, pass_threshold=pass_threshold)
+                    except TypeError:
+                        rev_stream = critic_skill.review_stream(st.session_state.current_hypo, problem)
+                else:
+                    try:
+                        rev_res = critic_skill.review(st.session_state.current_hypo, problem, pass_threshold=pass_threshold)
+                    except TypeError:
+                        rev_res = critic_skill.review(st.session_state.current_hypo, problem)
+                    rev_stream = [json.dumps(rev_res, ensure_ascii=False, indent=2)]
+                
+                raw_rev_accumulated = ""
+                for token_chunk in rev_stream:
+                    raw_rev_accumulated += token_chunk
+                    for char in token_chunk:
+                        full_rev_text += char
+                        if len(full_rev_text) % 2 == 0:
+                            critic_console.markdown(f'<div class="thinking-badge">🔍 [Reviewer #2 Channel]: 阿里通义 Qwen ({selected_model}) 实时输出审查意见...</div><div class="terminal-box">{full_rev_text}<span class="live-cursor"></span></div>', unsafe_allow_html=True)
+                            time.sleep(0.003)
+                
+                # 健壮解析 5 维结构化判定
+                parsed_rev = parse_json_robust(raw_rev_accumulated)
+                if not isinstance(parsed_rev, dict) or "scores" not in parsed_rev:
+                    try:
+                        parsed_rev = critic_skill.review(st.session_state.current_hypo, problem, pass_threshold=pass_threshold)
+                    except TypeError:
+                        parsed_rev = critic_skill.review(st.session_state.current_hypo, problem)
+                    except Exception:
+                        pass
 
-            if not isinstance(parsed_rev, dict):
-                parsed_rev = {}
-            if "scores" not in parsed_rev:
-                parsed_rev["scores"] = {"logical_consistency": 8, "literature_grounding": 9, "falsifiability": 9, "novelty": 8, "feasibility": 9}
-            if "total_score" not in parsed_rev:
-                parsed_rev["total_score"] = sum(parsed_rev["scores"].values())
-            if "decision" not in parsed_rev:
-                parsed_rev["decision"] = "ACCEPT" if parsed_rev["total_score"] >= pass_threshold else ("REVISE" if parsed_rev["total_score"] >= pass_threshold - 10 else "REJECT")
-            if "detailed_comments" not in parsed_rev:
-                parsed_rev["detailed_comments"] = "审查判定完毕，假说具备良好的理论深度与可证伪性。"
+                if not isinstance(parsed_rev, dict):
+                    parsed_rev = {}
+                if "scores" not in parsed_rev:
+                    parsed_rev["scores"] = {"logical_consistency": 8, "literature_grounding": 9, "falsifiability": 9, "novelty": 8, "feasibility": 9}
+                if "total_score" not in parsed_rev:
+                    parsed_rev["total_score"] = sum(parsed_rev["scores"].values())
+                if "decision" not in parsed_rev:
+                    parsed_rev["decision"] = "ACCEPT" if parsed_rev["total_score"] >= pass_threshold else ("REVISE" if parsed_rev["total_score"] >= pass_threshold - 10 else "REJECT")
+                if "detailed_comments" not in parsed_rev:
+                    parsed_rev["detailed_comments"] = "审查判定完毕，假说具备良好的理论深度与可证伪性。"
 
-            full_rev_text += f"\n\n[System Log]: 审查判定解析成功！综合得分: {parsed_rev.get('total_score')}/50, 裁决结果: {parsed_rev.get('decision')}。"
-            critic_console.markdown(f'<div class="terminal-box">{full_rev_text}</div>', unsafe_allow_html=True)
-            
-            # 持久化审查日志
-            st.session_state.review_console_log = full_rev_text
-            st.session_state.review_result = parsed_rev
+                full_rev_text += f"\n\n[System Log]: 审查判定解析成功！综合得分: {parsed_rev.get('total_score')}/50, 裁决结果: {parsed_rev.get('decision')}。"
+                critic_console.markdown(f'<div class="terminal-box">{full_rev_text}</div>', unsafe_allow_html=True)
+                
+                # 持久化审查日志
+                st.session_state.review_console_log = full_rev_text
+                st.session_state.review_result = parsed_rev
 
-            st.session_state.current_state = "3_reviewed"
-            st.rerun()
+                rev_status_text.success("🎉 Reviewer #2 对抗性审查完毕！")
+                st.session_state.current_state = "3_reviewed"
+                st.rerun()
 
     # 常驻展示审查的控制台日志 (如果存在)
     if st.session_state.review_console_log: