Update app.py

app.py

@@ -1,118 +1,194 @@
 import os
+import inspect
 import gradio as gr
 import requests
 import pandas as pd
-from smolagents import CodeAgent, InferenceClientModel
+from langchain_core.messages import HumanMessage
+from agent import build_graph
 
+
+
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+
 class BasicAgent:
+    """A langgraph agent."""
     def __init__(self):
-        # We use Qwen2.5-72B for its strong reasoning and code generation
-        self.model = InferenceClientModel(model_id="Qwen/Qwen2.5-72B-Instruct")
-        
-        # CodeAgent natively handles Python code execution
-        self.agent = CodeAgent(
-            tools=[], 
-            model=self.model,
-            add_base_tools=False 
-        )
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
 
     def __call__(self, question: str) -> str:
-        # This prompt is the 'gold standard' for GAIA exact-match scoring
-        strict_prompt = (
-            f"You are a general AI assistant. Solve this task: {question}\n\n"
-            "Report your thoughts, and finish your answer with the following template: "
-            "FINAL ANSWER: [YOUR FINAL ANSWER]\n\n"
-            "YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list. "
-            "If the answer is a number, do not use units ($, %, kg). "
-            "If the answer is a string, don't use articles (a, an, the) or abbreviations."
-        )
-        
-        try:
-            # Run the agent
-            raw_result = self.agent.run(strict_prompt)
-            
-            # --- Strict Post-Processing ---
-            # Extract only the content after 'FINAL ANSWER:' if it exists
-            result_str = str(raw_result)
-            if "FINAL ANSWER:" in result_str:
-                result_str = result_str.split("FINAL ANSWER:")[-1]
-            
-            # Remove markdown, quotes, and trailing punctuation
-            clean_ans = result_str.replace("`", "").replace('"', "").replace("'", "").strip()
-            return clean_ans.rstrip('.')
-        except Exception as e:
-            print(f"Agent Error: {e}")
-            return "Error"
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        messages = [HumanMessage(content=question)]
+        result = self.graph.invoke({"messages": messages})
+        answer = result['messages'][-1].content
+        return answer  # kein [14:] mehr nötig!
+
+
 
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    if not profile:
+def run_and_submit_all( profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    and displays the results.
+    """
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+
+    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
 
-    username = profile.username
-    space_id = os.getenv("SPACE_ID")
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    # 1. Instantiate Agent ( modify this part to create your agent)
+    try:
+        agent = BasicAgent()
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
 
-    # 1. Fetch Questions
+    # 2. Fetch Questions
+    print(f"Fetching questions from: {questions_url}")
     try:
-        response = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
+        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:
-        return f"Fetch Error: {e}", None
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
 
-    # 2. Setup Agent
-    agent = BasicAgent()
-    answers_payload = []
+    # 3. Run your Agent
     results_log = []
-
-    print(f"Starting evaluation for {len(questions_data)} questions...")
-
+    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")
-        
-        # --- File Download Logic ---
-        # Some GAIA questions refer to a file. We download it so the Python tool can read it.
-        file_url = f"{DEFAULT_API_URL}/files/{task_id}"
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
         try:
-            file_res = requests.get(file_url, timeout=5)
-            if file_res.status_code == 200:
-                # Save the file with its task_id as the name
-                with open(task_id, "wb") as f:
-                    f.write(file_res.content)
-                question_text += f"\n\n[System Note: A file for this task has been downloaded to your directory as '{task_id}'. Use Python to read/analyze it.]"
-        except:
-            pass # No file for this task
-
-        # 3. Generate Answer
-        ans = agent(question_text)
-        
-        answers_payload.append({"task_id": task_id, "submitted_answer": ans})
-        results_log.append({"Task ID": task_id, "Answer": ans})
-
-    # 4. Submit
+            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:
+             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:
-        sub_res = requests.post(f"{DEFAULT_API_URL}/submit", json={
-            "username": username,
-            "agent_code": agent_code,
-            "answers": answers_payload
-        })
-        data = sub_res.json()
-        status = f"Success! Score: {data.get('score')}% ({data.get('correct_count')}/{data.get('total_attempted')})"
-        return status, pd.DataFrame(results_log)
+        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:
-        return f"Submission Failed: {e}", pd.DataFrame(results_log)
+        status_message = f"An unexpected error occurred during submission: {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
 
-# --- Gradio UI ---
+
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# GAIA Pro Solver")
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown(
+
+    )
+
     gr.LoginButton()
-    run_btn = gr.Button("Run & Submit", variant="primary")
-    status = gr.Textbox(label="Result")
-    table = gr.DataFrame(label="Log")
-    run_btn.click(fn=run_and_submit_all, outputs=[status, table])
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    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_and_submit_all,
+        outputs=[status_output, results_table]
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    # Check for SPACE_HOST and SPACE_ID at startup for information
+    space_host_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+
+    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 repo URLs if SPACE_ID is found
+        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 Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)