Create app.py

app.py

@@ -0,0 +1,277 @@
+import os
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+import aiohttp
+import asyncio
+import json
+from agent import MagAgent
+from token_bucket import Limiter, MemoryStorage
+import aiofiles
+from typing import Optional
+
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# Rate limiting configuration
+MAX_MODEL_CALLS_PER_MINUTE = 14  # Conservative buffer below 15 RPM
+RATE_LIMIT = MAX_MODEL_CALLS_PER_MINUTE
+TOKEN_BUCKET_CAPACITY = RATE_LIMIT
+TOKEN_BUCKET_REFILL_RATE = RATE_LIMIT / 60.0  # Tokens per second
+
+# Initialize global token bucket with MemoryStorage
+storage = MemoryStorage()
+token_bucket = Limiter(rate=TOKEN_BUCKET_REFILL_RATE, capacity=TOKEN_BUCKET_CAPACITY, storage=storage)
+
+async def check_n_load_attach(session: aiohttp.ClientSession, task_id: str, api_url: str = DEFAULT_API_URL) -> Optional[str]:
+    file_url = f"{api_url}/files/{task_id}"
+    try:
+        async with session.get(file_url, timeout=15) as response:
+            if response.status == 200:
+                # Get filename from Content-Disposition
+                filename = None
+                content_disposition = response.headers.get("Content-Disposition")
+                if content_disposition and "filename=" in content_disposition:
+                    filename = content_disposition.split("filename=")[-1].strip('"')
+                if not filename:
+                    # Determine extension from Content-Type
+                    content_type = str(response.headers.get("Content-Type", "")).lower()
+                    extension = ""
+                    if "image/png" in content_type:
+                        extension = ".png"
+                    elif "image/jpeg" in content_type:
+                        extension = ".jpg"
+                    elif "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" in content_type:
+                        extension = ".xlsx"
+                    elif "audio/mpeg" in content_type:
+                        extension = ".mp3"
+                    elif "application/pdf" in content_type:
+                        extension = ".pdf"
+                    elif "text/x-python" in content_type:
+                        extension = ".py"
+                    else:
+                        extension = ""
+                    filename = f"{task_id}{extension}"
+                
+                # Save the file
+                local_file_path = os.path.join("downloads", filename)
+                os.makedirs("downloads", exist_ok=True)
+                async with aiofiles.open(local_file_path, "wb") as file:
+                    async for chunk in response.content.iter_chunked(8192):
+                        await file.write(chunk)
+                print(f"File downloaded successfully: {local_file_path}")
+                return local_file_path
+            else:
+                print(f"No attachment found for task {task_id}")
+                return None
+    except aiohttp.ClientError as e:
+        print(f"Error downloading attachment for task {task_id}: {str(e)}")
+        return None
+
+async def fetch_questions(session: aiohttp.ClientSession, questions_url: str) -> list:
+    """Fetch questions asynchronously."""
+    try:
+        async with session.get(questions_url, timeout=15) as response:
+            response.raise_for_status()
+            questions_data = await response.json()
+            if not questions_data:
+                print("Fetched questions list is empty.")
+                return []
+            print(f"Fetched {len(questions_data)} questions.")
+            return questions_data
+    except aiohttp.ClientError as e:
+        print(f"Error fetching questions: {e}")
+        return None
+    except Exception as e:
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return None
+
+async def submit_answers(session: aiohttp.ClientSession, submit_url: str, submission_data: dict) -> dict:
+    """Submit answers asynchronously."""
+    try:
+        async with session.post(submit_url, json=submission_data, timeout=60) as response:
+            response.raise_for_status()
+            return await response.json()
+    except aiohttp.ClientResponseError as e:
+        print(f"Submission Failed: Server responded with status {e.status}. Detail: {e.message}")
+        return None
+    except aiohttp.ClientError as e:
+        print(f"Submission Failed: Network error - {e}")
+        return None
+    except Exception as e:
+        print(f"An unexpected error occurred during submission: {e}")
+        return None
+
+async def process_question(agent, question_text: str, task_id: str, file_path: Optional[str], results_log: list):
+    """Process a single question with global rate limiting."""
+    submitted_answer = None
+    max_retries = 3
+    retry_delay = 4  # seconds
+
+    for attempt in range(max_retries):
+        try:
+            while not token_bucket.consume(1):
+                print(f"Rate limit reached for task {task_id}. Waiting to retry...")
+                await asyncio.sleep(retry_delay)
+            print(f"Processing task {task_id} (attempt {attempt + 1})...")
+            submitted_answer = await asyncio.wait_for(
+                agent(question_text, file_path),
+                timeout=60
+            )
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            print(f"Completed task {task_id} with answer: {submitted_answer[:50]}...")
+            return {"task_id": task_id, "submitted_answer": submitted_answer}
+        except aiohttp.ClientResponseError as e:
+            if e.status == 429:
+                print(f"Rate limit hit for task {task_id}. Retrying after {retry_delay}s...")
+                retry_delay *= 2
+                await asyncio.sleep(retry_delay)
+                continue
+            else:
+                submitted_answer = f"AGENT ERROR: {e}"
+                results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+                print(f"Failed task {task_id}: {submitted_answer}")
+                return None
+        except asyncio.TimeoutError:
+            submitted_answer = f"AGENT ERROR: Timeout after 60 seconds"
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            print(f"Failed task {task_id}: {submitted_answer}")
+            return None
+        except Exception as e:
+            submitted_answer = f"AGENT ERROR: {e}"
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            print(f"Failed task {task_id}: {submitted_answer}")
+            return None
+
+async def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions asynchronously, runs the MagAgent 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"
+
+    try:
+        agent = MagAgent(rate_limiter=token_bucket)
+    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)
+
+    async with aiohttp.ClientSession() as session:
+        questions_data = await fetch_questions(session, questions_url)
+        if questions_data is None:
+            return "Error fetching questions.", None
+        if not questions_data:
+            return "Fetched questions list is empty or invalid format.", None
+
+        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
+            if "1ht" in question_text.lower():
+                file_path = await check_n_load_attach(session, task_id)
+                result = await process_question(agent, question_text, task_id, file_path, results_log)
+                if result:
+                    answers_payload.append(result)
+            else:
+                print(f"Skipping not related question: {task_id}")
+                results_log.append({
+                    "Task ID": task_id,
+                    "Question": question_text,
+                    "Submitted Answer": "Question skipped - not related"
+                })
+
+        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)
+
+        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)
+
+        result_data = await submit_answers(session, submit_url, submission_data)
+        if result_data is None:
+            status_message = "Submission Failed."
+            print(status_message)
+            results_df = pd.DataFrame(results_log)
+            return status_message, results_df
+
+        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
+
+# --- Build Gradio Interface using Blocks ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Magus 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 your agent, and submit answers.
+        ---
+        **Notes:**
+        The agent uses asynchronous operations for efficiency. Answers are processed and submitted asynchronously.
+        """
+    )
+
+    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__":
+    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 Mag Agent Evaluation...")
+    demo.launch(debug=True, share=False)