Update app.py

app.py

@@ -9,9 +9,9 @@ from typing import List, Dict, Any
 import gradio as gr
 import pandas as pd
 from datetime import datetime
+import regex as re2
 
 # --- BACKEND IMPORTS ---
-import regex as re2
 from langchain_cohere import ChatCohere
 
 # --- LOCAL MODULE IMPORTS ---
@@ -39,6 +39,7 @@ def _sanitize_text(s: str) -> str:
 
 def _create_python_script(user_scenario: str, schema_context: str) -> str:
     """Uses an LLM to act as an "AI Coder", writing a complete Python script."""
+    # --- THE FINAL PROMPT FIX IS HERE ---
     prompt_for_coder = f"""
 You are an expert Python data scientist. Your sole job is to write a single, complete, and executable Python script to answer the user's request.
 You have access to a list of pandas dataframes loaded into a variable named `dfs`.
@@ -48,9 +49,10 @@ You have access to a list of pandas dataframes loaded into a variable named `dfs
 --- END SCHEMA ---
 
 CRITICAL RULES FOR YOUR SCRIPT:
-1.  **HANDLE DATA TYPES:** Before performing any mathematical operations, you MUST explicitly convert string values (e.g., '5.5%') to numeric types (`float` or `int`).
+1.  **ROBUST STRING CLEANING:** Before converting a string to a number (e.g., with `.astype(float)`), you MUST first remove ALL non-numeric characters that are not a digit or a decimal point. This includes characters like `$`, `%`, `~`, and commas. Use `.str.replace()` with a regular expression like `r'[^0-9.-]'` to do this safely. Failure to do this will cause a fatal `ValueError`.
 2.  **CHECK COLUMN NAMES:** You MUST use the exact, case-sensitive column names provided in the DATA SCHEMA. A `KeyError` will cause a failure.
-3.  **PRINT FINDINGS:** Use the `print()` function at each step to output your results as a formatted report.
+3.  **USE THE DATAFRAMES:** Your script MUST use the `dfs` list to access the data.
+4.  **PRINT FINDINGS:** Use the `print()` function at each step to output your results as a formatted report.
 
 --- USER'S SCENARIO ---
 {user_scenario}
@@ -82,7 +84,7 @@ def ping_cohere() -> str:
 # --- THE CORE ANALYSIS ENGINE ---
 
 def handle(user_msg: str, files: list) -> str:
-    """This is the powerful backend engine that supports both modes."""
+    """This is the powerful backend engine using the "Coder" pattern."""
     try:
         safe_in, blocked_in, reason_in = safety_filter(user_msg, mode="input")
         if blocked_in: return refusal_reply(reason_in)
@@ -90,7 +92,6 @@ def handle(user_msg: str, files: list) -> str:
         file_paths: List[str] = [getattr(f, "name", None) or f for f in (files or [])]
 
         if file_paths:
-            # --- MODE 1: DATA ANALYST (files are present) ---
             dataframes = []
             schema_parts = []
             for i, p in enumerate(file_paths):
@@ -111,12 +112,12 @@ def handle(user_msg: str, files: list) -> str:
             try:
                 with redirect_stdout(output_buffer):
                     exec(analysis_script, execution_namespace)
+                
                 result = output_buffer.getvalue()
-                return _sanitize_text(result or "(The script ran but produced no output.)")
+                return _sanitize_text(result or "(The analysis script ran but produced no output.)")
             except Exception as e:
                 return f"An error occurred executing the script: {e}\n\nGenerated Script:\n```python\n{analysis_script}\n```"
         else:
-            # --- MODE 2: CONVERSATIONAL AI (no files are present) ---
             prompt = f"{GENERAL_CONVERSATION_PROMPT}\n\nUser: {safe_in}\nAssistant:"
             return _sanitize_text(cohere_chat(prompt) or "How can I help further?")
 
@@ -129,7 +130,7 @@ def handle(user_msg: str, files: list) -> str:
 PRIVACY_POLICY_TEXT = load_markdown_text("privacy_policy.md")
 TERMS_OF_SERVICE_TEXT = load_markdown_text("terms_of_service.md")
 
-# ---------------- THE PROFESSIONAL UI WITH DUAL-MODE SUPPORT ----------------
+# ---------------- THE PROFESSIONAL UI WITH INTEGRATED LEGAL DOCS ----------------
 with gr.Blocks(theme="soft", css="style.css") as demo:
     assessment_history = gr.State([])
     
@@ -147,12 +148,11 @@ with gr.Blocks(theme="soft", css="style.css") as demo:
     with gr.Row(variant="panel"):
         with gr.Column(scale=1):
             gr.Markdown("## New Assessment")
-            gr.Markdown("<p style='font-size:0.9rem; color: #6C757D;'>Upload CSV files for data analysis, or just enter a prompt to chat with the AI.</p>") # UX Improvement
-            
+            gr.Markdown("<p style='font-size:0.9rem; color: #6C757D;'>Upload CSV files for data analysis, or just enter a prompt to chat with the AI.</p>")
             files_input = gr.Files(label="Upload Data Files (.csv)", file_count="multiple", type="filepath", file_types=[".csv"])
             prompt_input = gr.Textbox(label="Prompt", placeholder="Paste your scenario or question here.", lines=15)
             with gr.Row():
-                send_btn = gr.Button("▶️ Send / Run Analysis", variant="primary", scale=2) # UX Improvement
+                send_btn = gr.Button("▶️ Send / Run Analysis", variant="primary", scale=2)
                 clear_btn = gr.Button("🗑️ Clear")
             ping_btn = gr.Button("Ping Cohere")
             ping_out = gr.Markdown()
@@ -171,14 +171,13 @@ with gr.Blocks(theme="soft", css="style.css") as demo:
         terms_link = gr.Button("Terms of Service", variant="link")
 
     def run_analysis_wrapper(prompt, files, chat_history_list, history_state_list):
-        # --- THE LOGIC FIX IS HERE ---
         if not prompt:
             gr.Warning("Please enter a prompt.")
             yield chat_history_list, history_state_list, gr.update()
             return
 
         chat_with_user_msg = _append_msg(chat_history_list, "user", prompt)
-        thinking_message = _append_msg(chat_with_user_msg, "assistant", "```\n🧠 Thinking... Please wait.\n```")
+        thinking_message = _append_msg(chat_with_user_msg, "assistant", "```\n🧠 Generating and executing analysis script... This may take a moment.\n```")
         yield thinking_message, history_state_list, gr.update()
         
         ai_response_text = handle(prompt, files)
@@ -186,7 +185,6 @@ with gr.Blocks(theme="soft", css="style.css") as demo:
         final_chat = _append_msg(chat_with_user_msg, "assistant", ai_response_text)
         timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
         
-        # Only save to history if it was a data analysis session
         if files:
             file_names = [os.path.basename(f.name if hasattr(f, 'name') else f) for f in files]
             new_assessment = {"id": timestamp, "prompt": prompt, "files": file_names, "response": ai_response_text}
@@ -194,10 +192,8 @@ with gr.Blocks(theme="soft", css="style.css") as demo:
             history_labels = [f"{item['id']} - {item['prompt'][:40]}..." for item in updated_history]
             yield final_chat, updated_history, gr.update(choices=history_labels)
         else:
-            # For simple chat, just update the chat window
             yield final_chat, history_state_list, gr.update()
 
-
     def view_history(selection, history_state_list):
         if not selection or not history_state_list: return ""
         selected_id = selection.split(" - ")