Final run with gemini model

agent.py

@@ -46,7 +46,7 @@ llm_gemini = ChatGoogleGenerativeAI(
 llm_openai = ChatOpenAI(
     model="openai/gpt-oss-120b:together",
     temperature=0,
-    max_tokens=256, # type: ignore
+    max_tokens=None, # type: ignore
     timeout=60,
     max_retries=2,
     api_key=os.getenv("HF_TOKEN"),
@@ -54,7 +54,7 @@ llm_openai = ChatOpenAI(
 )
 
 if MODEL_PROVIDER == "gemini":
-    llm = llm_openai
+    llm = llm_gemini
 elif MODEL_PROVIDER == "openai":
     llm = llm_openai
 else:

app.py

@@ -1,4 +1,5 @@
 import os
+import time
 import gradio as gr
 import requests
 import inspect
@@ -6,7 +7,7 @@ import pandas as pd
 import json
 from logging_config import logger  # Import the shared logger
 from dotenv import load_dotenv
-from agent import MODEL_PROVIDER, graph
+from agent import MODEL_PROVIDER
 
 load_dotenv(".env")  
 # (Keep Constants as is)
@@ -20,6 +21,7 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
+        from agent import graph
         self.graph = graph
     def __call__(self, item: dict) -> str:
         """Process the input item and return a response.
@@ -98,27 +100,60 @@ def run_all(profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(item)
             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:
              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}"})
+        time.sleep(15)  # To avoid hitting rate limits or overwhelming the system
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+    
+    # save results log to a json file for debugging
+    with open(f"results_log_{MODEL_PROVIDER}.json", "w") as fh:
+        json.dump(results_log, fh, indent=2)
+        logger.info(f"Results log saved to results_log_{MODEL_PROVIDER}.json")
+    # save answers payload to a json file. Caching the answers to be able to submit them later 
+    with open(f"answers_payload_{MODEL_PROVIDER}.json", "w") as fh:
+        json.dump(answers_payload, fh, indent=2)
+        logger.info(f"Answers payload saved to answers_payload_{MODEL_PROVIDER}.json")
+    
+    message = f"Agent run completed. {len(answers_payload)} answers ready for submission."
+    results_df = pd.DataFrame(results_log) # type: ignore
+    return message, results_df
+  
+def submit_all(profile: gr.OAuthProfile | None):
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    if profile:
+        username= f"{profile.username}"
+        print(f"User logged in: {username}")
+    else:
+        print("User not logged in.")
+        return "Please Login to Hugging Face with the button.", None
+     # 4. Prepare Submission
+    try:
+        with open(f"answers_payload.json", "r") as fh:
+            answers_payload = json.load(fh)
+    except Exception as e:
+        print(f"Error loading answers payload: {e}")
+    try:
+        with open(f"results_log.json", "r") as fh:
+            results_log = json.load(fh)
+    except Exception as e:
+        print(f"Error loading results log: {e}")
 
-    # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload} # type: ignore
+    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..." # type: ignore
     print(status_update)
-
-    # 5. Submit
-def submit_all(profile: gr.OAuthProfile | None):
     api_url = DEFAULT_API_URL
     submit_url = f"{api_url}/submit"
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}") # type: ignore
+    # 5. Submit
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -131,7 +166,7 @@ def submit_all(profile: gr.OAuthProfile | None):
             f"Message: {result_data.get('message', 'No message received.')}"
         )
         print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
+        results_df = pd.DataFrame(results_log) # type: ignore
         return final_status, results_df
     except requests.exceptions.HTTPError as e:
         error_detail = f"Server responded with status {e.response.status_code}."
@@ -142,22 +177,22 @@ def submit_all(profile: gr.OAuthProfile | None):
             error_detail += f" Response: {e.response.text[:500]}"
         status_message = f"Submission Failed: {error_detail}"
         print(status_message)
-        results_df = pd.DataFrame(results_log)
+        results_df = pd.DataFrame(results_log) # type: ignore
         return status_message, results_df
     except requests.exceptions.Timeout:
         status_message = "Submission Failed: The request timed out."
         print(status_message)
-        results_df = pd.DataFrame(results_log)
+        results_df = pd.DataFrame(results_log) # type: ignore
         return status_message, results_df
     except requests.exceptions.RequestException as e:
         status_message = f"Submission Failed: Network error - {e}"
         print(status_message)
-        results_df = pd.DataFrame(results_log)
+        results_df = pd.DataFrame(results_log) # type: ignore
         return status_message, results_df
     except Exception as e:
         status_message = f"An unexpected error occurred during submission: {e}"
         print(status_message)
-        results_df = pd.DataFrame(results_log)
+        results_df = pd.DataFrame(results_log) # type: ignore
         return status_message, results_df
 
 
@@ -183,13 +218,18 @@ with gr.Blocks() as demo:
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
+    run_button = gr.Button("Run Evaluation & Cache Answers") # Renamed for clarity
+    submit_button = gr.Button("Submit Cached Answers") # New button for submission
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
     # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
+        fn=run_all, 
+        outputs=[status_output, results_table]
+    )
+    # Add the click event for the new submit_button
+    submit_button.click(
         fn=submit_all, 
         outputs=[status_output, results_table]
     )