Update app.py

app.py

@@ -1,34 +1,106 @@
 import os
+import re
 import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from io import BytesIO
+
+from smolagents import CodeAgent, DuckDuckGoSearchTool, VisitWebpageTool, InferenceClientModel
 
-# (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:
+    """
+    Agent logic:
+    - CodeAgent (not ToolCallingAgent) because chained multi-step reasoning
+      (search -> extract -> compute -> format) survives code execution far
+      better than JSON tool-call chains, which fail silently on malformed
+      structured output.
+    - DuckDuckGoSearchTool + VisitWebpageTool cover the web-lookup questions
+      (e.g. "Mercedes Sosa albums 2000-2009").
+    - _fetch_file pulls any attached file for a task from {api_url}/files/{task_id}
+      and hands the raw bytes into the CodeAgent's execution namespace via
+      additional_args, so generated code can parse it (pandas/openpyxl etc.)
+      if the question needs it.
+    - _format_answer is a safety net, not the primary defense. The prompt
+      instructs exact-match-aware output; this regex cleanup just strips
+      stray quotes/periods/whitespace that slip through.
+    - Known gap: questions that require actual video frame analysis (e.g. the
+      YouTube bird-count question) are NOT solved by this tool set. Search
+      can find a video's title/description but not analyze its frames. That
+      would need a separate vision-capable step - deliberately out of scope
+      for this baseline.
+    """
+
     def __init__(self):
         print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
+        self.model = InferenceClientModel()
+        self.agent = CodeAgent(
+            tools=[DuckDuckGoSearchTool(), VisitWebpageTool()],
+            model=self.model,
+        )
+
+    def _fetch_file(self, task_id: str, api_url: str = DEFAULT_API_URL):
+        """Fetch any file attached to this task. Returns raw bytes or None."""
+        if not task_id:
+            return None
+        try:
+            resp = requests.get(f"{api_url}/files/{task_id}", timeout=15)
+            if resp.status_code == 404:
+                # No file attached to this task - not an error.
+                return None
+            resp.raise_for_status()
+            return resp.content
+        except requests.exceptions.RequestException as e:
+            print(f"File fetch failed for task {task_id}: {e}")
+            return None
+
+    def _format_answer(self, raw: str) -> str:
+        """Strip surrounding quotes/whitespace/trailing punctuation - safety net only."""
+        answer = str(raw).strip()
+        answer = re.sub(r'^["\']|["\']$', '', answer).strip()
+        if answer.endswith('.') and not answer.replace('.', '').isdigit():
+            answer = answer.rstrip('.')
+        return answer.strip()
+
+    def __call__(self, question: str, task_id: str = None) -> 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
+        try:
+            file_bytes = self._fetch_file(task_id)
+
+            prompt = question
+            additional_args = {}
+            if file_bytes is not None:
+                additional_args["file_bytes"] = file_bytes
+                prompt += (
+                    "\n\n(An attached file for this task is available in your "
+                    "execution namespace as the variable `file_bytes` (raw bytes). "
+                    "Use pandas/openpyxl/BytesIO as needed to parse it if it's "
+                    "relevant to answering the question.)"
+                )
+
+            result = self.agent.run(prompt, additional_args=additional_args or None)
+            answer = self._format_answer(result)
+            print(f"Agent returning answer: {answer}")
+            return answer
+        except Exception as e:
+            print(f"Agent error on task {task_id}: {e}")
+            return f"AGENT_ERROR: {e}"
+
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+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
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,13 +110,12 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate 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)
 
@@ -55,16 +126,16 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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("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
+        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
@@ -80,18 +151,18 @@ def run_and_submit_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(question_text, task_id)
             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}"})
+            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 
+    # 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)
@@ -163,7 +234,6 @@ with gr.Blocks() as demo:
     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(
@@ -172,10 +242,9 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -183,14 +252,14 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    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("-" * (60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)