Update app.py

app.py

@@ -1,34 +1,203 @@
+#!/usr/bin/env python3
+# app.py - Minimal GAIA-ready agent + runner (Gradio UI)
 import os
-import gradio as gr
+import re
+import json
+import ast
+import operator
+import subprocess
+import sys
+import importlib
+import datetime
+import pytz
+import yaml
 import requests
-import inspect
 import pandas as pd
+import gradio as gr
+
+# Ensure import helper (optional; mostly for local dev if you want auto-install)
+def ensure_import(pkg_name, import_name=None):
+    import_name = import_name or pkg_name
+    try:
+        return importlib.import_module(import_name)
+    except ImportError:
+        # don't auto-install in production spaces; keep simple behavior
+        raise
+
+# ---- smolagents & local tool imports ----
+# Assumes smolagents and tools.final_answer are available in your environment
+from smolagents import CodeAgent, HfApiModel, tool, DuckDuckGoSearchTool
+from tools.final_answer import FinalAnswerTool
+
+# -------------------------
+# Minimal toolset for GAIA
+# -------------------------
+
+# Safe calculator using ast (no eval)
+_allowed_ops = {
+    ast.Add: operator.add, ast.Sub: operator.sub, ast.Mult: operator.mul,
+    ast.Div: operator.truediv, ast.Pow: operator.pow, ast.USub: operator.neg,
+    ast.Mod: operator.mod,
+}
+
+def _eval_node(node):
+    if isinstance(node, ast.Constant):  # Python 3.8+: ast.Num replaced by ast.Constant
+        return node.value
+    if isinstance(node, ast.Num):  # fallback for some versions
+        return node.n
+    if isinstance(node, ast.UnaryOp) and type(node.op) in _allowed_ops:
+        return _allowed_ops[type(node.op)](_eval_node(node.operand))
+    if isinstance(node, ast.BinOp) and type(node.op) in _allowed_ops:
+        return _allowed_ops[type(node.op)](_eval_node(node.left), _eval_node(node.right))
+    raise ValueError("Unsupported or unsafe expression")
+
+def safe_calc(expr: str):
+    tree = ast.parse(expr, mode='eval')
+    return _eval_node(tree.body)
+
+@tool
+def calculator(expr: str) -> str:
+    """Compute numeric expressions safely (no eval). Returns JSON string."""
+    try:
+        # clean expression (allow digits, operators, parentheses, spaces)
+        expr_clean = expr.strip()
+        val = safe_calc(expr_clean)
+        return json.dumps({"expression": expr_clean, "result": float(val)})
+    except Exception as e:
+        return json.dumps({"error": f"Calc error: {e}"})
+
+@tool
+def get_current_time_in_timezone(timezone: str) -> str:
+    """Return current time in timezone as JSON string."""
+    try:
+        tz = pytz.timezone(timezone)
+        local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
+        return json.dumps({"timezone": timezone, "local_time": local_time})
+    except Exception as e:
+        return json.dumps({"error": f"Timezone error: {e}"})
+
+# FinalAnswerTool (exists in repo)
+final_answer = FinalAnswerTool()
+
+# Load prompts if present (optional)
+prompt_templates = None
+try:
+    with open("prompts.yaml", "r") as fh:
+        prompt_templates = yaml.safe_load(fh)
+except Exception:
+    prompt_templates = None
+
+# Instantiate a compact CodeAgent (adjust model_id if needed)
+code_agent = CodeAgent(
+    model=HfApiModel(
+        max_tokens=1024,
+        temperature=0.15,
+        model_id='Qwen/Qwen2.5-Coder-32B-Instruct'  # change if overloaded or unavailable
+    ),
+    tools=[final_answer, calculator, get_current_time_in_timezone],
+    max_steps=6,
+    verbosity_level=0,
+    prompt_templates=prompt_templates
+)
+
+# Try to create a DuckDuckGo search tool for web fallback (may fail depending on smolagents version)
+search_tool = None
+try:
+    search_tool = DuckDuckGoSearchTool()
+except Exception:
+    search_tool = None  # fallback gracefully if unavailable
+
+# -------------------------
+# Minimal GaiaAgent wrapper
+# -------------------------
+class GaiaAgentMinimal:
+    def __init__(self, code_agent, search_tool=None):
+        self.code_agent = code_agent
+        self.search_tool = search_tool
 
-# (Keep Constants as is)
-# --- Constants ---
+    def _is_calc(self, q: str) -> bool:
+        # heuristics: contains digits and math operators
+        return bool(re.search(r'[\d]', q)) and any(op in q for op in ['+', '-', '*', '/', '%', '^'])
+
+    def _is_time(self, q: str) -> bool:
+        ql = q.lower()
+        return "time" in ql or "heure" in ql or "quelle heure" in ql or "what time" in ql
+
+    def run(self, question: str) -> str:
+        """Return a string (or JSON string) answer for the GAIA runner."""
+        try:
+            q = question.strip()
+
+            # 1) calculator
+            if self._is_calc(q):
+                # extract the first expression-like substring
+                m = re.search(r'([0-9\.\s\+\-\*\/\^\%\(\)]+)', q)
+                expr = m.group(1) if m else q
+                return calculator(expr)
+
+            # 2) time requests
+            if self._is_time(q):
+                # quick timezone guess
+                if "paris" in q.lower() or "france" in q.lower():
+                    tz = "Europe/Paris"
+                else:
+                    # try to extract "in X" patterns (e.g., in London)
+                    m = re.search(r'in\s+([A-Za-z_\/]+)', q, re.I)
+                    tz = m.group(1) if m else "UTC"
+                return get_current_time_in_timezone(tz)
+
+            # 3) quick web search fallback (if available)
+            if self.search_tool:
+                try:
+                    if hasattr(self.search_tool, "search"):
+                        res = self.search_tool.search(q, top_k=1)
+                    elif hasattr(self.search_tool, "run"):
+                        res = self.search_tool.run(q)
+                    else:
+                        res = self.search_tool(q)
+                    # Return as JSON string to be stable for scoring parsing
+                    return json.dumps({"source": "web_search", "snippet": str(res)})
+                except Exception:
+                    pass
+
+            # 4) fallback to LLM CodeAgent
+            try:
+                resp = None
+                # Try typical call signatures (some smolagents versions use call directly)
+                if hasattr(self.code_agent, "run"):
+                    resp = self.code_agent.run(q)
+                else:
+                    resp = self.code_agent(q)
+                # Normalize response
+                if isinstance(resp, dict):
+                    for key in ("final_answer", "answer", "result", "output"):
+                        if key in resp:
+                            return str(resp[key])
+                    return json.dumps(resp)
+                return str(resp)
+            except Exception as e:
+                # last-resort fallback
+                return json.dumps({"error": f"LLM error: {e}"})
+        except Exception as e:
+            return json.dumps({"error": f"Agent internal error: {e}"})
+
+# Instantiate gaia_agent for the runner to use
+gaia_agent = GaiaAgentMinimal(code_agent, search_tool)
+
+# -------------------------
+# GAIA runner (unchanged logic, uses gaia_agent)
+# -------------------------
 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):
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Fetches all questions, runs gaia_agent on them, submits all answers,
+    and returns status and results table.
     """
-    # --- 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.")
@@ -38,15 +207,14 @@ 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. Agent is ready (we use gaia_agent defined above)
     try:
-        agent = BasicAgent()
+        agent = gaia_agent
     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)
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "unknown"
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -55,21 +223,17 @@ 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
     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
+    # 3. Run agent on each question
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -80,18 +244,18 @@ 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.run(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}"})
+            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)
@@ -117,7 +281,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         try:
             error_json = e.response.json()
             error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
+        except Exception:
             error_detail += f" Response: {e.response.text[:500]}"
         status_message = f"Submission Failed: {error_detail}"
         print(status_message)
@@ -139,58 +303,42 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
-
-# --- Build Gradio Interface using Blocks ---
+# -------------------------
+# Gradio UI
+# -------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Minimal GAIA Agent 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.
-
-        ---
-        **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.
+        Instructions:
+        1. Log in to your Hugging Face account with the button below.
+        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run the agent, submit answers and get the score.
         """
     )
 
     gr.LoginButton()
 
     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]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 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
-
+    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 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("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)