wip basic agent works

agents/basic_agent.py

@@ -0,0 +1,14 @@
+"""Base Agent"""
+
+
+class BasicAgent:  # pylint: disable=too-few-public-methods
+    """Base Agent for Evaluation"""
+
+    def __init__(self):
+        print("BasicAgent initialized.")
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        fixed_answer = "This is a default answer."
+        print(f"Agent returning fixed answer: {fixed_answer}")
+        return fixed_answer

app.py

@@ -2,7 +2,6 @@
 
 import os
 import gradio as gr
-import pandas as pd
 
 from questions import get_questions_data
 from submit import submit_answers
@@ -53,11 +52,11 @@ def run_and_submit_all(
         return "Questions list is empty or invalid format.", None
     print(f"Retrieved {len(questions_data)} questions.")
 
-    answers_payload, results_log, error_message = get_answer_payload_results_log(
+    answers_payload, results_df, error_message = get_answer_payload_results_log(
         questions_data=questions_data
     )
     if error_message:
-        return error_message, None
+        return error_message, results_df
 
     submission_data = {
         "username": username.strip(),
@@ -66,7 +65,6 @@ def run_and_submit_all(
     }
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."  # pylint: disable=line-too-long
     print(status_update)
-    results_df = pd.DataFrame(results_log)
     print(f"Submitting {len(answers_payload)} answers to: {SUBMIT_URL}")
 
     if SAFETY_OFF:

payload.py

@@ -1,11 +1,17 @@
 """Runner for Agents to output answers"""
 
+import pandas as pd
+
+from agents.basic_agent import BasicAgent
+
+agent = BasicAgent()
+
 
 def get_answer_payload_results_log(questions_data: dict) -> tuple:
     """Get Answer Payload, Results Log or Error Message"""
     results_log = []
     answers_payload = []
-    submitted_answer = "Mock Final Answer Test Data"
+    print(f"Running agent on {len(questions_data)} questions...")
 
     for item in questions_data:
         task_id = item.get("task_id")
@@ -13,14 +19,32 @@ def get_answer_payload_results_log(questions_data: dict) -> tuple:
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
-        answers_payload.append(
-            {"task_id": task_id, "submitted_answer": submitted_answer}
-        )
-        results_log.append(
-            {
-                "Task ID": task_id,
-                "Question": question_text,
-                "Submitted Answer": submitted_answer,
-            }
-        )
-    return answers_payload, results_log, None
+        try:
+            submitted_answer = agent(question_text)
+            answers_payload.append(
+                {"task_id": task_id, "submitted_answer": submitted_answer}
+            )
+            results_log.append(
+                {
+                    "Task ID": task_id,
+                    "Question": question_text,
+                    "Submitted Answer": submitted_answer,
+                }
+            )
+        except Exception as e:  # pylint: disable=broad-exception-caught
+            print(f"Error running agent on task {task_id}: {e}")
+            results_log.append(
+                {
+                    "Task ID": task_id,
+                    "Question": question_text,
+                    "Submitted Answer": f"AGENT ERROR: {e}",
+                }
+            )
+    results_df = pd.DataFrame(results_log)
+
+    if not answers_payload:
+        error_message = "Agent did not produce any answers to submit."
+        print(error_message)
+        return None, results_df, error_message
+
+    return answers_payload, results_df, None