Update app.py

app.py

@@ -27,30 +27,29 @@ def analyze_code(code):
     if not code.strip():
         return "No code provided.", "", ""
 
-    result = code_analyzer(code)
-    label = result[0]["label"]  # e.g., LABEL_0
-    score = result[0]["score"]
-
-    # Map raw label to issue type (no lower(), no mismatch)
-    issue_type = label_to_issue_type.get(label.strip(), "Error")
-
-    # Static suggestion and severity for now
-    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,  # Must match picklist
-            "Suggestion__c": suggestion,
-            "Severity__c": severity,
-            # Optional: add Developer__c if needed
-        })
-    except Exception as e:
-        suggestion += f" (⚠️ Failed to log to Salesforce: {str(e)})"
+        result = code_analyzer(code)
+        label = result[0]["label"].strip()  # e.g., LABEL_0
+        issue_type = label_to_issue_type.get(label, "Error")  # fallback to valid picklist
+
+        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
 
-    return issue_type, suggestion, severity
+    except Exception as e:
+        return "Error", f"⚠️ Model failed: {str(e)}", "High"
 
 # ---------- Metadata Validator ----------
 def validate_metadata(metadata):
@@ -88,12 +87,12 @@ def process_nlp_query(query):
         f"Question: {query.strip()}\n\nAnswer:"
     )
 
-    result = qa_pipeline(prompt, max_length=512, temperature=0.3, top_p=0.9, repetition_penalty=1.1, do_sample=False)
-    output = result[0]["generated_text"]
-
-    if "Answer:" in output:
-        return output.split("Answer:")[-1].strip()
-    return output.strip()
+    try:
+        result = qa_pipeline(prompt, max_length=512, temperature=0.3, top_p=0.9, repetition_penalty=1.1, do_sample=False)
+        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 answer: {str(e)}"
 
 # ---------- Gradio UI ----------
 with gr.Blocks() as demo: