Update app.py

app.py

@@ -1,15 +1,4 @@
-import gradio as gr
-from transformers import pipeline
-from simple_salesforce import Salesforce
-import os
-
-# ---------- Salesforce Login ----------
-sf = Salesforce(
-    username=os.getenv("SF_USERNAME"),
-    password=os.getenv("SF_PASSWORD"),
-    security_token=os.getenv("SF_SECURITY_TOKEN"),
-    domain="login"
-)
+import random
 
 # ---------- Define Mapping for Model Labels ----------
 label_to_issue_type = {
@@ -19,108 +8,46 @@ label_to_issue_type = {
     "LABEL_3": "Best Practice"
 }
 
-# ---------- Load Model ----------
-code_analyzer = pipeline("text-classification", model="microsoft/codebert-base")
-
-# ---------- Code Analyzer Function ----------
 def analyze_code(code):
     if not code.strip():
         return "No code provided.", "", ""
 
+    # --- Simulate classification labels for demo/testing ---
+    simulated_labels = ["LABEL_0", "LABEL_1", "LABEL_2", "LABEL_3"]
+    label = random.choice(simulated_labels)
+    issue_type = label_to_issue_type.get(label, "Error")
+
+    # Simulated suggestion/severity based on issue type
+    suggestions = {
+        "Performance": "Consider optimizing loops and database access.",
+        "Error": "Add proper error handling and null checks.",
+        "Security": "Avoid dynamic SOQL. Use binding variables.",
+        "Best Practice": "Refactor for readability and use bulk-safe patterns."
+    }
+    severities = {
+        "Performance": "Medium",
+        "Error": "High",
+        "Security": "High",
+        "Best Practice": "Low"
+    }
+
+    suggestion = suggestions.get(issue_type)
+    severity = severities.get(issue_type)
+
+    # Optional: Logging for debugging
+    print(f"[DEBUG] Label: {label} → Issue: {issue_type} | Severity: {severity}")
+
+    # Log to Salesforce
     try:
-        result = code_analyzer(code)
-        label = result[0]["label"].strip()
-        issue_type = label_to_issue_type.get(label, "Error")
-        suggestion = "Consider refactoring for better performance"
-        severity = "Medium"
-
-        try:
-            sf.CodeReviewResult__c.create({
-                "Name": f"Review_{issue_type}",
-                "CodeSnippet__c": code,
-                "IssueType__c": issue_type,
-                "Suggestion__c": suggestion,
-                "Severity__c": severity,
-            })
-        except Exception as sf_err:
-            suggestion += f" (⚠️ Failed to log to Salesforce: {str(sf_err)})"
-
-        return issue_type, suggestion, severity
-
-    except Exception as e:
-        return "Error", f"⚠️ Model failed: {str(e)}", "High"
-
-# ---------- Metadata Validator ----------
-def validate_metadata(metadata):
-    if not metadata.strip():
-        return "No metadata provided.", "", ""
-
-    mtype = "Field"
-    issue = "Unused field detected"
-    recommendation = "Remove it to improve performance"
-
-    try:
-        sf.MetadataAuditLog__c.create({
-            "Name": f"MetadataLog_{mtype}",
-            "MetadataType__c": mtype,
-            "IssueDescription__c": issue,
-            "Recommendation__c": recommendation,
-            "Status__c": "Open"
+        sf.CodeReviewResult__c.create({
+            "Name": f"Review_{issue_type}",
+            "CodeSnippet__c": code,
+            "IssueType__c": issue_type,
+            "Suggestion__c": suggestion,
+            "Severity__c": severity
+            # You can also add Developer__c here if needed
         })
     except Exception as e:
-        recommendation += f" (⚠️ Failed to log to Salesforce: {str(e)})"
-
-    return mtype, issue, recommendation
-
-# ---------- NLP Assistant (Flan-T5) ----------
-qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-xl")
-
-def process_nlp_query(query):
-    if not query.strip():
-        return "No question provided."
-
-    prompt = (
-        "You are a certified Salesforce Apex expert. "
-        "Answer the question below clearly and accurately using Salesforce best practices, terminology, and examples.\n\n"
-        f"Question: {query.strip()}\n\nAnswer:"
-    )
-
-    try:
-        result = qa_pipeline(
-            prompt,
-            max_new_tokens=256  # ✅ Fixed warning: avoids conflict with max_length
-        )
-
-        output = result[0]["generated_text"]
-        return output.split("Answer:")[-1].strip() if "Answer:" in output else output.strip()
-
-    except Exception as e:
-        return f"⚠️ AI failed to respond: {str(e)}"
-
-# ---------- Gradio UI ----------
-with gr.Blocks() as demo:
-    gr.Markdown("# 🤖 Salesforce AI Code Review & Q&A")
-
-    with gr.Tab("Code Review"):
-        code_input = gr.Textbox(label="Apex / LWC Code", lines=8)
-        issue_type = gr.Textbox(label="Issue Type")
-        suggestion = gr.Textbox(label="AI Suggestion")
-        severity = gr.Textbox(label="Severity")
-        code_button = gr.Button("Analyze Code")
-        code_button.click(analyze_code, inputs=code_input, outputs=[issue_type, suggestion, severity])
-
-    with gr.Tab("Metadata Validation"):
-        metadata_input = gr.Textbox(label="Metadata XML", lines=8)
-        mtype = gr.Textbox(label="Type")
-        issue = gr.Textbox(label="Issue")
-        recommendation = gr.Textbox(label="Recommendation")
-        metadata_button = gr.Button("Validate Metadata")
-        metadata_button.click(validate_metadata, inputs=metadata_input, outputs=[mtype, issue, recommendation])
-
-    with gr.Tab("Ask AI (Natural Language)"):
-        query_input = gr.Textbox(label="Your question", lines=2, placeholder="e.g. What is a trigger?")
-        response_output = gr.Textbox(label="AI Response", lines=8)
-        nlp_button = gr.Button("Ask")
-        nlp_button.click(process_nlp_query, inputs=query_input, outputs=response_output)
+        suggestion += f" (⚠️ Salesforce error: {str(e)})"
 
-demo.launch()
+    return issue_type, suggestion, severity