Update app.py

app.py

@@ -149,22 +149,26 @@ def homePage():
 
 @app.route("/medical", methods=["GET", "POST"])
 def medical_page():
-    # Use session for history and document context
     if request.method == "GET":
-        # Load all latest data from session (or default to empty if not found)
-        latest_response = session.pop('latest_medical_response', {}) # POP to clear it after one display
+        # ✅ USE .get() instead of .pop() - don't remove it yet
+        latest_response = session.get('latest_medical_response', {})
         
         answer = latest_response.get('answer', "")
         thoughts = latest_response.get('thoughts', "")
         validation = latest_response.get('validation', "")
         source = latest_response.get('source', "")
 
-        # Clear history only when a user first navigates (not on redirect)
-        if not latest_response and 'medical_history' not in session:
-            session.pop('current_medical_document', None)
+        # ✅ NOW clear it after reading (for next request)
+        if latest_response:
+            session.pop('latest_medical_response', None)
+            session.modified = True
+        
+        # Load history
+        raw_history_list = session.get('medical_history', [])
+        history = hydrate_history(raw_history_list)
         
         return render_template("medical_page.html", 
-                               history=session.get('medical_history', []),
+                               history=history,  # ✅ Pass hydrated history
                                answer=answer,
                                thoughts=thoughts,
                                validation=validation,
@@ -172,15 +176,12 @@ def medical_page():
     
     # POST Request
     answer, thoughts, validation, source = "", "", "", ""
-    # 1. Get raw history (list of dicts) from session
     raw_history_list = session.get('medical_history', [])
-    # 2. Hydrate it for the agent
     history_for_agent = hydrate_history(raw_history_list)
     current_medical_document = session.get('current_medical_document', "")
     
-    
     try:
-        query=standardize_query(request.form.get("query", ""))
+        query = standardize_query(request.form.get("query", ""))
         has_image = 'image' in request.files and request.files['image'].filename
         has_document = 'document' in request.files and request.files['document'].filename
         has_query = request.form.get("query") or request.form.get("question", "")
@@ -188,14 +189,12 @@ def medical_page():
         logger.info(f"POST request received: has_image={has_image}, has_document={has_document}, has_query={has_query}")
             
         if has_document:
-            # Scenario 3: Query + Document
             logger.info("Processing Scenario 3: Query + Document with Medical Swarm")
             file = request.files['document']
             try:
-                # Store the new document text in the session
                 document_text = file.read().decode("utf-8")
                 session['current_medical_document'] = document_text
-                current_medical_document = document_text # Use the new document for this turn
+                current_medical_document = document_text
             except UnicodeDecodeError:
                 answer = "Error: Could not decode the uploaded document. Please ensure it is a valid text or PDF file."
                 logger.error("Scenario 3: Document decode error")
@@ -205,15 +204,14 @@ def medical_page():
             answer = markdown_bold_to_html(swarm_answer)
                 
             thoughts = "Swarm analysis complete. The process is orchestrated and does not use the ReAct thought process. You can now ask follow-up questions."
-            source= "Medical Swarm"
-            validation = (True, "Swarm output generated.") # Swarm has its own validation logic
+            source = "Medical Swarm"
+            validation = "Swarm output generated."
+            
             history_for_agent.append(HumanMessage(content=f"[Document Uploaded] Query: '{query}'"))
             history_for_agent.append(AIMessage(content=answer))
             
-        elif has_image :
-            #Scenario 1 
+        elif has_image:
             logger.info("Processing Multimodal RAG: Query + Image")
-            # --- Step 1 & 2: Image Setup & Vision Analysis ---
             file = request.files['image']
             upload_dir = "Uploads"
             os.makedirs(upload_dir, exist_ok=True)
@@ -226,7 +224,6 @@ def medical_page():
                 with open(image_path, "rb") as img_file:
                     img_data = base64.b64encode(img_file.read()).decode("utf-8")
                 
-            
                 vision_prompt = f"Analyze this image and identify the main subject in a single, concise sentence. The user's query is: '{query}'"
                 message = HumanMessage(content=[
                     {"type": "text", "text": vision_prompt},
@@ -236,18 +233,20 @@ def medical_page():
                 visual_prediction = vision_response.content
                 logger.info(f"Vision Prediction: {visual_prediction}")
 
-                # --- Create an Enhanced Query ---
                 enhanced_query = (
                     f'User Query: "{query}" '
                     f'Context from an image provided by the LLM: "{visual_prediction}" '
                     'Based on the user\'s query and the context from LLM, provide a comprehensive answer.'
                 )
-                logger.info(f"Enhanced query : {enhanced_query}")
+                logger.info(f"Enhanced query: {enhanced_query}")
             
                 agent = rag_systems['medical']
-                if not agent: raise Exception("Medical RAG system is not loaded.")
+                if not agent: 
+                    raise Exception("Medical RAG system is not loaded.")
+                
                 response_dict = agent.answer(enhanced_query, chat_history=history_for_agent)
                 answer, thoughts, validation, source = parse_agent_response(response_dict)
+                
                 history_for_agent.append(HumanMessage(content=query))
                 history_for_agent.append(AIMessage(content=answer))
             
@@ -257,12 +256,10 @@ def medical_page():
                         os.remove(image_path)
                         logger.info(f"Successfully deleted temporary image file: {image_path}")
                     except PermissionError as e:
-                        logger.warning(f"Could not remove {image_path} after processing. "
-                                       f"File may be locked by another process. Error: {e}")
+                        logger.warning(f"Could not remove {image_path}: {e}")
             
         elif query:
-            # --- SCENARIO 2: TEXT-ONLY QUERY OR SWARM FOLLOW-UP ---
-            history_doc_context = history_for_agent # Use hydrated list
+            history_doc_context = history_for_agent
             if current_medical_document:
                 logger.info("Processing Follow-up Query for Document")
                 history_doc_context = [HumanMessage(content=f"We are discussing this document:\n{current_medical_document}")] + history_for_agent
@@ -270,12 +267,13 @@ def medical_page():
                 logger.info("Processing Text RAG query for Medical domain")
             
             logger.info(f"Original Query: '{query}'")
-            print(f"📚 Using chat history with {len(history_doc_context)} previous messages to create standalone query")
-            standalone_query = get_standalone_question(query, history_doc_context,llm)
+            standalone_query = get_standalone_question(query, history_doc_context, llm)
             logger.info(f"Standalone Query: '{standalone_query}'")
             
             agent = rag_systems['medical']
-            if not agent: raise Exception("Medical RAG system is not loaded.")
+            if not agent: 
+                raise Exception("Medical RAG system is not loaded.")
+            
             response_dict = agent.answer(standalone_query, chat_history=history_doc_context)
             answer, thoughts, validation, source = parse_agent_response(response_dict)
 
@@ -284,14 +282,16 @@ def medical_page():
 
         else:
             raise ValueError("No query or file provided.")
+            
     except Exception as e:
         logger.error(f"Error on /medical page: {e}", exc_info=True)
         answer = f"An error occurred: {e}"
         thoughts = traceback.format_exc()
     
-    # 4. DEHYDRATE the full history back into dicts for session saving
+    # ✅ DEHYDRATE history back to dicts
     session['medical_history'] = dehydrate_history(history_for_agent)
-    # This (latest_response) is ALREADY JSON-serializable, so it's fine.
+    
+    # ✅ Save the response
     session['latest_medical_response'] = {
         'answer': answer, 
         'thoughts': thoughts, 
@@ -300,9 +300,10 @@ def medical_page():
     }
     session.modified = True
     
-    logger.info(f"DEBUG: Saving to session: ANSWER='{answer[:50]}...', THOUGHTS='{thoughts[:50]}...'")
+    # ✅ ADD DEBUG LOG
+    logger.info(f"💾 SAVED TO SESSION - Answer length: {len(answer)}, First 100 chars: {answer[:100]}")
+    logger.info(f"💾 Session ID: {session.get('_id', 'NO ID')}")
                              
-    logger.debug(f"Redirecting after saving latest response.")
     return redirect(url_for('medical_page'))
 
 @app.route("/medical/clear")