Update app.py

app.py

@@ -1,9 +1,12 @@
+import os
+import inspect
 import yaml
+import requests
+import gradio as gr
+import pandas as pd
 
 from smolagents import CodeAgent, OpenAIServerModel, LiteLLMModel, Tool
 
-from Gradio_UI import GradioUI
-
 from tools.calculator import Calculator
 from tools.final_answer import FinalAnswerTool
 from tools.visit_webpage import VisitWebpageTool
@@ -11,12 +14,13 @@ from tools.web_search import DuckDuckGoSearchTool
 
 from research_state import ResearchState
 from verifier import verify_research
-import os
 
 # =========================================================
-# Configuration
+# Constants
 # =========================================================
 
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
 MODEL_ID = "gemini/gemini-2.5-flash"
 
 MAX_STEPS = 10
@@ -31,7 +35,6 @@ TEMPERATURE = 0.2
 class ResearchContext:
     """
     Holds the state for a single research run.
-
     The context is shared by the research tools so that
     searches, webpages, claims, and verification results
     belong to the same research session.
@@ -254,7 +257,7 @@ visit_webpage = StatefulVisitWebpageTool()
 
 calculator = Calculator()
 
-verify_research = VerifyResearchTool()
+verify_research_tool = VerifyResearchTool()
 
 final_answer = FinalAnswerTool()
 
@@ -262,7 +265,7 @@ tools = [
     web_search,
     visit_webpage,
     calculator,
-    verify_research,
+    verify_research_tool,
     final_answer,
 ]
 
@@ -301,9 +304,199 @@ agent = CodeAgent(
 )
 
 
+class ResearchAgentWrapper:
+    """
+    Thin wrapper so the research agent can be called like
+    BasicAgent: agent(question) -> answer string.
+    Resets the shared research context for every new question
+    so state doesn't leak between questions.
+    """
+
+    def __init__(self, agent: CodeAgent):
+        self.agent = agent
+        print("ResearchAgentWrapper initialized.")
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        research_context.reset()
+        research_context.start(question)
+        answer = self.agent.run(question)
+        print(f"Agent returning answer (first 50 chars): {str(answer)[:50]}...")
+        return str(answer)
+
+
+# =========================================================
+# Evaluation Runner
+# =========================================================
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the research agent on them,
+    submits all answers, and displays the results.
+    """
+    space_id = os.getenv("SPACE_ID")
+
+    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
+
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    # 1. Instantiate Agent
+    try:
+        agent_runner = ResearchAgentWrapper(agent)
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
+
+    # 2. Fetch Questions
+    print(f"Fetching questions from: {questions_url}")
+    try:
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
+        questions_data = response.json()
+        if not questions_data:
+            print("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
+        print(f"Fetched {len(questions_data)} questions.")
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching questions: {e}")
+        return f"Error fetching questions: {e}", None
+    except requests.exceptions.JSONDecodeError as e:
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        return f"Error decoding server response for questions: {e}", None
+    except Exception as e:
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
+
+    # 3. Run your Agent
+    results_log = []
+    answers_payload = []
+    print(f"Running agent on {len(questions_data)} questions...")
+    for item in questions_data:
+        task_id = item.get("task_id")
+        question_text = item.get("question")
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
+        try:
+            submitted_answer = agent_runner(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:
+            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}"})
+
+    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)
+
+    # 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}'..."
+    print(status_update)
+
+    # 5. Submit
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    try:
+        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response.raise_for_status()
+        result_data = response.json()
+        final_status = (
+            f"Submission Successful!\n"
+            f"User: {result_data.get('username')}\n"
+            f"Overall Score: {result_data.get('score', 'N/A')}% "
+            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
+            f"Message: {result_data.get('message', 'No message received.')}"
+        )
+        print("Submission successful.")
+        results_df = pd.DataFrame(results_log)
+        return final_status, results_df
+    except requests.exceptions.HTTPError as e:
+        error_detail = f"Server responded with status {e.response.status_code}."
+        try:
+            error_json = e.response.json()
+            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
+        except requests.exceptions.JSONDecodeError:
+            error_detail += f" Response: {e.response.text[:500]}"
+        status_message = f"Submission Failed: {error_detail}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        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)
+        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)
+        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)
+        return status_message, results_df
+
+
 # =========================================================
-# Launch
+# Gradio Interface
 # =========================================================
 
+with gr.Blocks() as demo:
+    gr.Markdown("# Web Research Agent Evaluation Runner")
+    gr.Markdown(
+        """
+        **Instructions:**
+        1.  Log in to your Hugging Face account using the button below.
+        2.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run the research agent, submit answers, and see the score.
+        ---
+        **Disclaimers:**
+        Once clicking the submit button, it can take some time (the agent must search, read sources, and verify claims for every question).
+        """
+    )
+
+    gr.LoginButton()
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+
+    run_button.click(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
+    )
+
 if __name__ == "__main__":
-    GradioUI(agent).launch()
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
+    space_host_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID")
+
+    if space_host_startup:
+        print(f"✅ SPACE_HOST found: {space_host_startup}")
+        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+    else:
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+
+    if space_id_startup:
+        print(f"✅ SPACE_ID found: {space_id_startup}")
+        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
+    else:
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+
+    print("-" * (60 + len(" App Starting ")) + "\n")
+
+    print("Launching Gradio Interface for Web Research Agent Evaluation...")
+    demo.launch(debug=True, share=False)