Update app.py

app.py

@@ -1,196 +1,642 @@
 import os
+import json
+import re
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
 
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    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
-
-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
-
-    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)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+from huggingface_hub import InferenceClient
+
+from prompt import SYSTEM_PROMPT
+
+from tools import (
+    execute_tool,
+    download_file
+)
+
+import requests
+
+
+# ============================================================
+# CONFIG
+# ============================================================
+
+SCORING_API = (
+    "https://agents-course-unit4-scoring.hf.space"
+)
+
+MODEL_ID = os.getenv(
+    "TEXT_MODEL",
+    "Qwen/Qwen2.5-72B-Instruct"
+)
+
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+MAX_STEPS = 10
+
+
+client = InferenceClient(
+    token=HF_TOKEN
+)
+
+
+# ============================================================
+# ANSWER CLEANING
+# ============================================================
+
+def clean_answer(answer):
+
+    answer = str(answer).strip()
+
+    # Remove markdown code fences.
+    answer = re.sub(
+        r"^```(?:text)?\s*",
+        "",
+        answer,
+        flags=re.IGNORECASE
+    )
+
+    answer = re.sub(
+        r"\s*```$",
+        "",
+        answer
+    )
+
+    # Remove accidental prefixes.
+    answer = re.sub(
+        r"^\s*FINAL ANSWER\s*:?\s*",
+        "",
+        answer,
+        flags=re.IGNORECASE
+    )
+
+    answer = re.sub(
+        r"^\s*THE ANSWER IS\s*:?\s*",
+        "",
+        answer,
+        flags=re.IGNORECASE
+    )
+
+    return answer.strip()
+
+
+# ============================================================
+# MODEL CALL
+# ============================================================
+
+def call_model(messages):
+
+    response = client.chat.completions.create(
+        model=MODEL_ID,
+        messages=messages,
+        max_tokens=1200,
+        temperature=0
+    )
+
+    return response.choices[0].message.content
+
+
+# ============================================================
+# AGENT
+# ============================================================
+
+def solve_question(
+    task_id,
+    question
+):
+
+    messages = [
+        {
+            "role": "system",
+            "content": SYSTEM_PROMPT
+        },
+        {
+            "role": "user",
+            "content": (
+                f"GAIA TASK ID: {task_id}\n\n"
+                f"QUESTION:\n{question}\n\n"
+                "Solve this question."
+            )
+        }
+    ]
+
+    # Cache downloaded attachment path if needed.
+    attachment_path = None
+
+    for step in range(MAX_STEPS):
+
+        print(
+            f"    Agent step {step + 1}/{MAX_STEPS}"
+        )
+
+        raw = call_model(messages)
+
+        print(
+            f"    Model: {raw[:500]}"
+        )
+
+        # ----------------------------------------------------
+        # Parse JSON
+        # ----------------------------------------------------
+
+        try:
+
+            decision = json.loads(
+                raw.strip()
+            )
+
+        except json.JSONDecodeError:
+
+            # Sometimes models put JSON inside markdown.
+            match = re.search(
+                r"\{.*\}",
+                raw,
+                re.DOTALL
+            )
+
+            if match:
+
+                try:
+                    decision = json.loads(
+                        match.group(0)
+                    )
+
+                except json.JSONDecodeError:
+                    decision = None
+
+            else:
+                decision = None
+
+        # ----------------------------------------------------
+        # Invalid model response
+        # ----------------------------------------------------
+
+        if not decision:
+
+            messages.append({
+                "role": "assistant",
+                "content": raw
+            })
+
+            messages.append({
+                "role": "user",
+                "content": (
+                    "Your response was not valid JSON.\n"
+                    "Return ONLY one of these formats:\n\n"
+                    '{"action":"tool","tool":"TOOL_NAME","input":"..."}\n'
+                    '{"action":"final","answer":"..."}'
+                )
+            })
+
+            continue
+
+        # ----------------------------------------------------
+        # FINAL ANSWER
+        # ----------------------------------------------------
+
+        if decision.get("action") == "final":
+
+            answer = decision.get(
+                "answer",
+                ""
+            )
+
+            return clean_answer(
+                answer
+            )
+
+        # ----------------------------------------------------
+        # TOOL CALL
+        # ----------------------------------------------------
+
+        if decision.get("action") == "tool":
+
+            tool_name = decision.get(
+                "tool"
+            )
+
+            tool_input = decision.get(
+                "input",
+                ""
+            )
+
+            # -----------------------------------------------
+            # Automatically download attachment
+            # -----------------------------------------------
+
+            if (
+                tool_name == "download_file"
+                and not attachment_path
+            ):
+
+                attachment_path = (
+                    download_file(task_id)
+                )
+
+                tool_result = (
+                    f"FILE_PATH:\n"
+                    f"{attachment_path}\n\n"
+                    f"The file has been downloaded."
+                )
+
+            # -----------------------------------------------
+            # Inspect downloaded file
+            # -----------------------------------------------
+
+            elif (
+                tool_name == "inspect_file"
+                and tool_input == "CURRENT_FILE"
+            ):
+
+                if not attachment_path:
+
+                    attachment_path = (
+                        download_file(task_id)
+                    )
+
+                tool_result = execute_tool(
+                    "inspect_file",
+                    attachment_path,
+                    task_id,
+                    question
+                )
+
+            # -----------------------------------------------
+            # Audio
+            # -----------------------------------------------
+
+            elif (
+                tool_name == "transcribe_audio"
+                and tool_input == "CURRENT_FILE"
+            ):
+
+                if not attachment_path:
+
+                    attachment_path = (
+                        download_file(task_id)
+                    )
+
+                tool_result = execute_tool(
+                    "transcribe_audio",
+                    attachment_path,
+                    task_id,
+                    question
+                )
+
+            # -----------------------------------------------
+            # Image
+            # -----------------------------------------------
+
+            elif (
+                tool_name == "analyze_image"
+                and tool_input == "CURRENT_FILE"
+            ):
+
+                if not attachment_path:
+
+                    attachment_path = (
+                        download_file(task_id)
+                    )
+
+                tool_result = execute_tool(
+                    "analyze_image",
+                    attachment_path,
+                    task_id,
+                    question
+                )
+
+            # -----------------------------------------------
+            # Normal tool
+            # -----------------------------------------------
+
+            else:
+
+                tool_result = execute_tool(
+                    tool_name,
+                    tool_input,
+                    task_id,
+                    question
+                )
+
+            # Don't let huge tool outputs destroy context.
+            tool_result = str(
+                tool_result
+            )[:40000]
+
+            messages.append({
+                "role": "assistant",
+                "content": raw
+            })
+
+            messages.append({
+                "role": "user",
+                "content": (
+                    f"TOOL RESULT ({tool_name}):\n"
+                    f"{tool_result}\n\n"
+                    "Continue solving the original question. "
+                    "Use another tool if necessary, otherwise "
+                    "return the final JSON answer."
+                )
+            })
+
+            continue
+
+    return "Unable to determine the answer."
+
+
+# ============================================================
+# FETCH QUESTIONS
+# ============================================================
+
+def get_questions():
+
+    response = requests.get(
+        f"{SCORING_API}/questions",
+        timeout=30
+    )
+
+    response.raise_for_status()
+
+    return response.json()
+
+
+# ============================================================
+# SUBMIT
+# ============================================================
+
+def submit(
+    username,
+    agent_code,
+    answers
+):
+
+    payload = {
+        "username": username,
+        "agent_code": agent_code,
+        "answers": answers
+    }
+
+    response = requests.post(
+        f"{SCORING_API}/submit",
+        json=payload,
+        timeout=180
+    )
+
+    response.raise_for_status()
+
+    return response.json()
+
+
+# ============================================================
+# MAIN EVALUATION
+# ============================================================
+
+def run_and_submit_all(
+    profile: gr.OAuthProfile | None
+):
+
+    if profile is None:
+
+        return (
+            "Please login to Hugging Face.",
+            None
+        )
+
+    username = profile.username
+
+    space_id = os.getenv(
+        "SPACE_ID"
+    )
+
+    if not space_id:
+
+        return (
+            "SPACE_ID was not found.",
+            None
+        )
+
+    agent_code = (
+        "https://huggingface.co/spaces/"
+        f"{space_id}/tree/main"
+    )
+
+    print("=" * 70)
+    print("GAIA UNIT 4 AGENT")
+    print("=" * 70)
+
+    print(
+        f"Username: {username}"
+    )
+
+    print(
+        f"Agent code: {agent_code}"
+    )
+
+    # --------------------------------------------------------
+    # Fetch questions
+    # --------------------------------------------------------
+
     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
+
+        questions = get_questions()
+
     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
+
+        return (
+            f"Could not fetch questions: {e}",
+            None
+        )
+
+    print(
+        f"Fetched {len(questions)} questions."
+    )
+
+    answers = []
+    results = []
+
+    # --------------------------------------------------------
+    # Solve questions
+    # --------------------------------------------------------
+
+    for index, item in enumerate(
+        questions,
+        start=1
+    ):
+
+        task_id = item.get(
+            "task_id"
+        )
+
+        question = item.get(
+            "question"
+        )
+
+        print("\n" + "=" * 70)
+
+        print(
+            f"QUESTION {index}/{len(questions)}"
+        )
+
+        print(
+            f"TASK ID: {task_id}"
+        )
+
+        print(
+            question[:500]
+        )
+
+        print("=" * 70)
+
         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})
+
+            answer = solve_question(
+                task_id,
+                question
+            )
+
+            answer = clean_answer(
+                answer
+            )
+
+            print(
+                f"FINAL ANSWER: {answer}"
+            )
+
+            answers.append({
+                "task_id": task_id,
+                "submitted_answer": answer
+            })
+
+            results.append({
+                "Task ID": task_id,
+                "Submitted Answer": 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)
+            print(
+                f"ERROR: {e}"
+            )
+
+            results.append({
+                "Task ID": task_id,
+                "Submitted Answer":
+                    f"ERROR: {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}'..."
-    print(status_update)
+    # --------------------------------------------------------
+    # Submit
+    # --------------------------------------------------------
+
+    if not answers:
+
+        return (
+            "No answers were generated.",
+            pd.DataFrame(results)
+        )
+
+    print("\n" + "=" * 70)
+    print("SUBMITTING")
+    print("=" * 70)
 
-    # 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
+
+        result = submit(
+            username,
+            agent_code,
+            answers
+        )
+
+        score = result.get(
+            "score",
+            "N/A"
+        )
+
+        correct = result.get(
+            "correct_count",
+            "?"
+        )
+
+        total = result.get(
+            "total_attempted",
+            "?"
+        )
+
+        message = result.get(
+            "message",
+            ""
+        )
+
+        status = (
+            "Submission Successful!\n\n"
+            f"User: {username}\n"
+            f"Score: {score}%\n"
+            f"Correct: {correct}/{total}\n"
+            f"Message: {message}"
+        )
+
+        print(status)
+
+        return (
+            status,
+            pd.DataFrame(results)
+        )
+
     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
 
+        status = (
+            f"Submission failed: {e}"
+        )
+
+        print(status)
+
+        return (
+            status,
+            pd.DataFrame(results)
+        )
+
+
+# ============================================================
+# MINIMAL UI
+# ============================================================
 
-# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
 
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+    gr.Markdown(
+        "# GAIA Unit 4 Agent"
+    )
 
-        ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
-        """
+    gr.Markdown(
+        "Login and click the button to run all GAIA questions."
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_button = gr.Button(
+        "Run Evaluation & Submit"
+    )
+
+    status = gr.Textbox(
+        label="Result",
+        lines=6
+    )
 
-    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)
+    results = gr.DataFrame(
+        label="Answers"
+    )
 
     run_button.click(
         fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+        outputs=[
+            status,
+            results
+        ]
     )
 
+
 if __name__ == "__main__":
-    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)
+
+    demo.launch(
+        debug=True,
+        share=False
+    )