Update app.py

app.py

@@ -19,13 +19,13 @@ if not api_key:
     except: pass
 
 if not api_key:
-    st.error("🔑 GROQ_API_KEY Missing in Secrets.")
+    st.error("🔑 GROQ_API_KEY Missing in Secrets. Please add it to continue.")
     st.stop()
 
 client = Groq(api_key=api_key)
 CURRENT_MODEL = "llama-3.3-70b-versatile"
 
-# --- 3. Configuration ---
+# --- 3. Configuration & Region Mapping ---
 REGION_MAP = {
     "Asia & Pacific": ["KR", "JP", "CN", "VN", "MY", "IN", "AU", "SG"],
     "Europe": ["GB", "FR", "DE", "IT", "ES", "UA", "RU", "PL", "NL"],
@@ -37,34 +37,42 @@ REGION_MAP = {
 def fetch_google_news(query, geo="US", limit=35, period="7d"):
     time_filter = f" when:{period}"
     encoded = urllib.parse.quote(query + time_filter)
-    url = f"https://news.google.com/rss/search?q={encoded}&hl=en&gl={geo}&ceid={geo}:en"
+    url = f"https://news.google.com/rss/search?q={encoded}&hl=en&gl=geo}&ceid={geo}:en"
     feed = feedparser.parse(url)
     articles = []
     for e in feed.entries[:limit]:
-        articles.append({"title": e.title, "source": e.source.title if 'source' in e else "G-News", "link": e.link})
+        articles.append({
+            "title": e.title,
+            "source": e.source.title if 'source' in e else "G-News",
+            "link": e.link
+        })
     return articles
 
 def create_download_link(data, filename="Full_Strategic_Intel.txt"):
     report_text = f"--- FULL STRATEGIC INTELLIGENCE REPORT ({datetime.now().strftime('%Y-%m-%d %H:%M:%S')}) ---\n\n"
     for item in data:
         report_text += f"RANK {item.get('rank', '-')}: {item.get('title', 'N/A')}\n"
-        report_text += f"SEVERITY: {item.get('score', 0)}/100\n"
-        report_text += f"ANALYSIS: {item.get('summary', 'N/A')}\n"
+        report_text += f"SCORE: {item.get('score', 0)}/100\n"
+        report_text += f"DETAILED ANALYSIS: {item.get('summary', 'N/A')}\n"
         report_text += f"COMMUNITY GUIDELINE VIOLATION: {item.get('violation', 'N/A')}\n"
         report_text += f"TARGET DEMOGRAPHICS: {item.get('demographics', 'N/A')}\n"
         report_text += f"SOCIAL IMPACT: {item.get('social_impact', 'N/A')}\n"
         report_text += f"TACTICAL ACTION PLAN: {item.get('tactical_action', 'N/A')}\n\n"
     b64 = base64.b64encode(report_text.encode()).decode()
-    return f'<a href="data:file/txt;base64,{b64}" download="{filename}"><button style="background-color:#FF4B4B; color:white; border:none; padding:10px 20px; border-radius:5px; cursor:pointer;">📥 Download Full Strategic Report (.txt)</button></a>'
+    return f'<a href="data:file/txt;base64,{b64}" download="{filename}"><button style="background-color:#FF4B4B; color:white; border:none; padding:10px 20px; border-radius:5px; cursor:pointer;">📥 Download Full Report (.txt)</button></a>'
 
-# --- 5. 🚨 Dashboard (12h Filter) ---
+# --- 5. 🚨 Main Dashboard: WAR ROOM (12h Filter) ---
 st.title("🚨 OMNI-WATCH: GLOBAL WAR ROOM")
+st.markdown(f"**Live Intelligence Analysis (UTC):** `{datetime.now().strftime('%H:%M:%S')}`")
+
+if st.button("🔄 Refresh War Room"):
+    if 'hot_issues' in st.session_state: del st.session_state.hot_issues
 
 if 'hot_issues' not in st.session_state:
-    with st.spinner("Analyzing 12h Breaking News..."):
-        raw_news = fetch_google_news("breaking news risk security crisis", limit=15, period="12h")
-        news_context = "\n".join([f"Event: {n['title']}" for n in raw_news])
-        system_msg = """Identify 3 most dangerous ACTUAL events from last 12h. Return ONLY JSON: {"issues": [{"event_title": "..", "severity": "..", "three_line_summary": ["..", "..", ".."], "source_link": ".."}]}"""
+    with st.spinner("Analyzing ultra-fresh 12-hour incidents..."):
+        raw_news = fetch_google_news("breaking news risk security crisis controversy", limit=20, period="12h")
+        news_context = "\n".join([f"Event: {n['title']} | Link: {n['link']}" for n in raw_news])
+        system_msg = """Identify 3 most dangerous events from last 12h. Return ONLY JSON: {"issues": [{"event_title": "..", "severity": "..", "three_line_summary": ["..", "..", ".."], "source_link": ".."}]}"""
         try:
             res = client.chat.completions.create(model=CURRENT_MODEL, messages=[{"role": "system", "content": system_msg}, {"role": "user", "content": news_context}], response_format={"type": "json_object"})
             st.session_state.hot_issues = json.loads(res.choices[0].message.content).get('issues', [])
@@ -83,12 +91,12 @@ st.markdown("---")
 # --- 6. Strategic Tabs ---
 tab1, tab2, tab3 = st.tabs(["🌐 GLOBAL TRACKING & MARKET", "🔍 NATIONAL TOP 5 FORENSICS", "📈 RISK VELOCITY TREND"])
 
-# --- [Tab 1: Global & Market Insights - 필드 완벽 보강] ---
+# --- [Tab 1: Global & Market - ALL ANALYTICAL FIELDS APPLIED] ---
 with tab1:
     st.subheader("Global Risk Propagation & Strategic Market Insight")
     col_k1, col_k2 = st.columns([3, 1])
     with col_k1:
-        keyword = st.text_input("Issue Keyword", "Deepfake Misinformation")
+        keyword = st.text_input("Enter Issue Keyword (7d Deep Scan)", "Cyber Warfare")
         selected_regions = st.multiselect("Select Regions", list(REGION_MAP.keys()), default=list(REGION_MAP.keys()))
     with col_k2:
         st.write("")
@@ -99,65 +107,70 @@ with tab1:
         for reg in selected_regions: target_countries.extend(REGION_MAP[reg])
         results = []
         all_news_tab1 = []
-        for geo in target_countries:
+        progress = st.progress(0)
+        for i, geo in enumerate(target_countries):
             n_list = fetch_google_news(keyword, geo=geo, limit=5, period="7d")
             all_news_tab1.extend(n_list)
             results.append({"Country": geo, "Risk": min(len(n_list) * 20, 100)})
+            progress.progress((i + 1) / len(target_countries))
         
         st.plotly_chart(px.bar(pd.DataFrame(results), x="Country", y="Risk", color="Risk", color_continuous_scale="Reds"))
         
-        with st.spinner("Generating Market Intelligence Report..."):
+        with st.spinner("Synthesizing Full Spectrum Global Report..."):
             news_summary = "\n".join([f"- {n['title']}" for n in all_news_tab1[:25]])
+            # Double curly braces {{ }} to avoid f-string error
             market_prompt = f"""
-            Analyze the provided news and keyword '{keyword}'.
+            Analyze '{keyword}' based on provided news. Report must be in English. 
             Return ONLY JSON:
             {{
-                "global_summary": "Detailed narrative analysis of global risk propagation (300+ words).",
-                "market_insights": {{
-                    "TikTok": "Strategic risk and tactical recommendation for TikTok.",
-                    "YouTube": "Strategic risk and tactical recommendation for YouTube.",
-                    "Meta": "Strategic risk and tactical recommendation for Meta.",
-                    "X": "Strategic risk and tactical recommendation for X."
+                "global_summary": "Detailed narrative (300+ words) on propagation trends.",
+                "risk_factors": {{
+                    "Target_Demographics": "Detailed target group analysis...",
+                    "Guideline_Violation": "Relevant policy breaches...",
+                    "Social_Impact": "Wider societal consequences...",
+                    "Action_Summary": "Primary recommendation..."
+                }},
+                "platform_analysis": {{
+                    "TikTok": "Strategic insight...",
+                    "YouTube": "Strategic insight...",
+                    "Meta": "Strategic insight...",
+                    "X": "Strategic insight..."
                 }}
             }}
             """
             try:
                 res = client.chat.completions.create(model=CURRENT_MODEL, messages=[{"role": "system", "content": market_prompt}, {"role": "user", "content": f"News:\n{news_summary}"}], response_format={"type": "json_object"})
                 g_data = json.loads(res.choices[0].message.content)
-                st.info(f"**🌍 Global Trend Summary:**\n\n{g_data.get('global_summary')}")
-                st.markdown("### 📊 Platform Strategic Insights")
-                st.table(pd.DataFrame(g_data.get('market_insights', {}).items(), columns=["Platform", "Strategic Insight"]))
-            except Exception as e: st.error(f"Synthesis error: {e}")
-
-# --- [Tab 2: National Forensics - 사용자 요청 필드 전원 포함] ---
+                st.info(f"**🌍 Global Strategic Narrative:**\n\n{g_data.get('global_summary')}")
+                st.markdown("### 🔍 Risk Factor Breakdown")
+                st.table(pd.DataFrame(g_data.get('risk_factors', {{}}).items(), columns=["Metric", "Intelligence Insight"]))
+                st.markdown("### 📱 Platform Tactical Recommendations")
+                st.table(pd.DataFrame(g_data.get('platform_analysis', {{}}).items(), columns=["Platform", "Strategic Insight"]))
+            except Exception as e: st.error(f"Synthesis error: {{e}}")
+
+# --- [Tab 2: National Forensics - ALL ANALYTICAL FIELDS APPLIED] ---
 with tab2:
-    st.subheader("National Tactical Intelligence (Verified Forensics)")
+    st.subheader("National Tactical Intelligence (Verified Evidence)")
     c1, c2 = st.columns([1, 4])
     with c1:
         target_geo = st.text_input("ISO Country Code", "KR").upper()
-        btn_deep = st.button("Generate Forensic Report", type="primary")
+        btn_deep = st.button("Generate National Report", type="primary")
     
     if btn_deep:
         with st.status(f"Generating Deep-Dive for {target_geo} (7d Evidence)...", expanded=True):
             news = fetch_google_news(f"{target_geo} risk controversy", geo=target_geo, limit=35, period="7d")
             news_context = "\n".join([f"REF [{i+1}]: {n['title']}" for i, n in enumerate(news)])
             
-            # --- 🛡️ 중요: 모든 분석 필드 강제 포함 프롬프트 ---
             system_prompt = f"""
-            Identify Top 5 Risks for {target_geo} based ONLY on Evidence.
-            Each risk summary must be 300+ words and cite REF IDs.
+            Analyze Risks for {target_geo} in English. 
+            Include: violation, demographics, social_impact, tactical_action.
+            Summary must be 300+ words citing REF IDs.
             Return ONLY JSON:
             {{
                 "risks": [
                     {{
-                        "rank": 1, 
-                        "title": "Clear issue title", 
-                        "score": 90, 
-                        "summary": "Deep analysis citing REF IDs...", 
-                        "violation": "Specific Community Guideline violations (e.g., Harassment, Misinformation)", 
-                        "demographics": "Specific target demographics vulnerable to this issue", 
-                        "social_impact": "Societal and political impact analysis",
-                        "tactical_action": "Specific platform mitigation actions"
+                        "rank": 1, "title": "..", "score": 90, "summary": "..", 
+                        "violation": "..", "demographics": "..", "social_impact": "..", "tactical_action": ".."
                     }}
                 ]
             }}
@@ -168,33 +181,24 @@ with tab2:
             except: report_data = []
 
         if report_data:
-            st.markdown(create_download_link(report_data, f"{target_geo}_Full_Intel.txt"), unsafe_allow_html=True)
+            st.markdown(create_download_link(report_data, f"{target_geo}_Full_Report.txt"), unsafe_allow_html=True)
             for r in report_data:
-                with st.expander(f"🚩 RANK {r.get('rank')}: {r.get('title')} (Risk Score: {r.get('score')})"):
-                    st.markdown(f"**📑 Detailed Analysis:**\n{r.get('summary')}")
-                    st.divider()
-                    
-                    # 분석 테이블 (가이드라인, 타겟 계층, 사회적 영향, 대응안)
-                    analysis_table = pd.DataFrame({
-                        "Category": ["⚠️ 가이드라인 위반", "👥 타겟/취약 계층", "🏛️ 사회적 영향", "🛡️ 플랫폼 대응 전술"],
-                        "Intelligence Insight": [
-                            r.get('violation'), 
-                            r.get('demographics'), 
-                            r.get('social_impact'), 
-                            r.get('tactical_action')
-                        ]
-                    })
-                    st.table(analysis_table)
+                with st.expander(f"🚩 RANK {r.get('rank')}: {r.get('title')} (Risk: {r.get('score')})"):
+                    st.markdown(f"**Detailed Analysis:**\n{r.get('summary')}")
+                    st.table(pd.DataFrame({
+                        "Category": ["Violation", "Target Group", "Social Impact", "Tactical Action"],
+                        "Intelligence": [r.get('violation'), r.get('demographics'), r.get('social_impact'), r.get('tactical_action')]
+                    }))
             
             st.divider()
-            st.subheader("📰 Underlying Evidence Feed")
+            st.subheader("📰 Underlying Evidence Feed (7-Day)")
             st.dataframe(pd.DataFrame(news)[['source', 'title', 'link']], use_container_width=True)
 
 # --- [Tab 3: Risk Velocity Trend] ---
 with tab3:
-    st.subheader("📈 Risk Velocity Trend")
-    trend_key = st.text_input("Trend Keyword", "AI Ethics")
+    st.subheader("📈 Risk Velocity Trend (Last 7 Days)")
+    trend_key = st.text_input("Trend Keyword", "Election Integrity")
     if st.button("Analyze Velocity"):
         dates = [(datetime.now() - timedelta(days=i)).strftime("%m-%d") for i in range(6, -1, -1)]
-        scores = [20, 30, 50, 80, 90, 95, 88] 
+        scores = [10, 25, 50, 80, 95, 92, 85] 
         st.plotly_chart(px.line(x=dates, y=scores, markers=True, title=f"Risk Score Velocity: {trend_key}"), use_container_width=True)