Update app.py

app.py

@@ -9,7 +9,7 @@ hf_token = os.getenv("HF_TOKEN")
 if hf_token:
     login(token=hf_token)
 
-# --- 2. TOOL LOADING ---
+# --- 2. LOAD TOOL ---
 print("Loading Mental-Longformer...")
 model_name = "avtak/erisk-longformer-depression-v1"
 classifier = pipeline("text-classification", model=model_name, truncation=True, max_length=4096, top_k=None)
@@ -23,7 +23,6 @@ def get_crisis_resources(location: str = "Global") -> str:
         "Malaysia": "🇲🇾 **Malaysia:** Befrienders KL: 03-76272929 | Talian Kasih: 15999",
         "Global": "🌍 **International:** [befrienders.org](https://www.befrienders.org)"
     }
-    # Fallback logic
     for key in resources:
         if location and key.lower() in location.lower():
             return resources[key]
@@ -31,28 +30,32 @@ def get_crisis_resources(location: str = "Global") -> str:
 
 def detect_depression_risk(text: str) -> dict:
     """Analyzes text using Mental-Longformer (eRisk 2025)."""
-    # Thesis Aggregation Logic: 
-    # We replace single newlines with double newlines so the model sees distinct posts
+    
+    # --- THESIS LOGIC: AGGREGATION ---
+    # Strictly preserving your requirement for double newlines
     processed_text = text.replace("\n", "\n\n")
     
     results = classifier(processed_text)[0]
     prob = next((r['score'] for r in results if r['label'] == 'LABEL_1'), 0)
     
-    if prob < 0.40: level = "Low Risk (Isolated Pattern)"
-    elif 0.40 <= prob < 0.60: level = "Moderate Risk (Interactive Echo Chamber Pattern)"
-    else: level = "High Risk (Depressed Pattern)"
+    if prob < 0.40: 
+        level = "Low Risk (Isolated Pattern)"
+    elif 0.40 <= prob < 0.60: 
+        level = "Moderate Risk (Interactive Echo Chamber Pattern)"
+    else: 
+        level = "High Risk (Depressed Pattern)"
         
     return {"probability": prob, "risk_level": level, "word_count": len(processed_text.split())}
 
-# --- 4. AGENT REASONING (UPDATED MODELS) ---
+# --- 4. AGENT REASONING (SambaNova/Nebius) ---
 def agent_reasoning(text, risk_data, provider="SambaNova"):
     """
-    Uses Sponsor APIs to interpret the clinical data.
+    Uses Sponsor APIs to generate the analysis report.
     """
     client = None
     model = None
     
-    # SYSTEM PROMPT (Thesis-Informed)
+    # SYSTEM PROMPT
     system_prompt = f"""
     You are 'Dr. Longformer', an empathetic Clinical AI Research Agent.
     
@@ -76,7 +79,6 @@ def agent_reasoning(text, risk_data, provider="SambaNova"):
             if not api_key: return "⚠️ Nebius API Key missing."
             
             client = OpenAI(base_url="https://api.tokenfactory.nebius.com/v1/", api_key=api_key)
-            # UPDATED MODEL ID
             model = "moonshotai/Kimi-K2-Thinking" 
 
         # --- SPONSOR 2: SAMBANOVA (Llama 3.3) ---
@@ -85,7 +87,6 @@ def agent_reasoning(text, risk_data, provider="SambaNova"):
             if not api_key: return "⚠️ SambaNova API Key missing."
             
             client = OpenAI(base_url="https://api.sambanova.ai/v1", api_key=api_key)
-            # UPDATED MODEL ID
             model = "Meta-Llama-3.3-70B-Instruct" 
 
         # EXECUTE
@@ -96,33 +97,40 @@ def agent_reasoning(text, risk_data, provider="SambaNova"):
                 {"role": "user", "content": "Analyze this."}
             ],
             temperature=0.6,
-            max_tokens=300
+            max_tokens=250
         )
         return response.choices[0].message.content
 
     except Exception as e:
         return f"Reasoning Error ({provider}): {str(e)}"
 
-# --- 5. PIPELINE ---
+# --- 5. PIPELINE (No Chatbot, Just Report) ---
 def full_analysis_pipeline(user_text, location, provider):
-    if not user_text.strip(): return "Please enter text.", "No data", "No data"
+    if not user_text.strip(): return "Please enter text."
     
+    # 1. Run Tool
     risk_data = detect_depression_risk(user_text)
+    
+    # 2. Get Resources
     resources = get_crisis_resources(location)
+    
+    # 3. Agent Reasoning
     explanation = agent_reasoning(user_text, risk_data, provider)
     
-    # Color logic
+    # 4. Color Logic
     color = "green" if risk_data['probability'] < 0.4 else "orange" if risk_data['probability'] < 0.6 else "red"
     
+    # 5. Build HTML/Markdown Report
     return f"""
-    <div style="border-left: 5px solid {color}; padding-left: 10px;">
+    <div style="border-left: 6px solid {color}; padding-left: 15px; background-color: {color}10; border-radius: 5px; padding: 20px;">
         <h2 style="color:{color}; margin:0;">{risk_data['risk_level']}</h2>
-        <h3 style="margin-top:0;">Probability: {risk_data['probability']*100:.1f}%</h3>
+        <h3 style="margin-top:5px;">Probability: {risk_data['probability']*100:.1f}%</h3>
     </div>
     
     ### 🧠 Agent Analysis ({provider})
     {explanation}
     
+    ---
     ### 🆘 Recommended Resources
     {resources}
     """