Update app.py

app.py

@@ -1,75 +1,143 @@
 import os
-import gradio as gr
+import tempfile
 import requests
-import inspect
+from typing import Dict, Any, Annotated
+from typing_extensions import TypedDict
+import gradio as gr
 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
+# Your constants + imports stay
 
-    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)
+# New imports for the stack
+from smolagents import CodeAgent, HfApiModel  # Smolagents for code/web agents
+from smolagents.tools import DuckDuckGoSearchResults  # Built-in web tool
+from langgraph.graph import StateGraph, END
+from langgraph.prebuilt import ToolNode, tools_condition
+from langchain_core.tools import tool
+from langchain_core.messages import HumanMessage, AIMessage
+from transformers import pipeline  # For lightweight LLM routing
 
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+# --- Enhanced Agent with LangGraph + Smolagents ---
+class CrmAgent:
+    def __init__(self):
+        print("CrmAgent initialized with LangGraph + Smolagents.")
+        # Lightweight router LLM (free HF inference)
+        self.router = pipeline("text-generation", model="gpt2", device=-1)  # CPU for hack
+        # Smolagents CodeAgent with web tool
+        self.llm = HfApiModel(model_id="microsoft/DialoGPT-medium")  # Free HF model
+        search_tool = DuckDuckGoSearchResults(num_results=3)  # Quick web hits
+        self.code_agent = CodeAgent(llm=self.llm, tools=[search_tool])
+        # Temp dir for files
+        self.temp_dir = tempfile.mkdtemp()
+
+    # Tool: Download file if needed (GAIA questions may have attachments)
+    @tool
+    def download_file(self, task_id: str) -> str:
+        """Downloads file for task_id if exists, returns path."""
+        url = f"{DEFAULT_API_URL}/files/{task_id}"
+        try:
+            resp = requests.get(url, timeout=10)
+            if resp.status_code == 200:
+                file_path = os.path.join(self.temp_dir, f"{task_id}_file")
+                with open(file_path, "wb") as f:
+                    f.write(resp.content)
+                return f"File downloaded: {file_path}"
+            return "No file found."
+        except Exception as e:
+            return f"Download error: {e}"
+
+    # Router Node: Decide path with LLM
+    def router_node(self, state: Dict[str, Any]) -> Dict[str, str]:
+        question = state["question"]
+        prompt = f"Given question: '{question[:100]}...'. Respond with route: 'search' if needs web info, 'code' if math/file/code, 'both' if both, 'direct' if obvious."
+        response = self.router(prompt, max_length=20, num_return_sequences=1)[0]["generated_text"]
+        route = response.strip().lower().split()[-1]  # Crude parse, tweak as needed
+        state["route"] = route
+        print(f"Routed to: {route}")
+        return state
+
+    # Search Node: Use smolagents web
+    def search_node(self, state: Dict[str, Any]) -> Dict[str, Any]:
+        question = state["question"]
+        try:
+            # Smolagents call (it handles tool selection internally)
+            result = self.code_agent.run(question)  # Runs code/web as needed
+            state["search_results"] = result
+            print(f"Search/code output: {result[:100]}...")
+        except Exception as e:
+            state["search_results"] = f"Error: {e}"
+        return state
+
+    # Direct Node: Simple guess or pass
+    def direct_node(self, state: Dict[str, Any]) -> Dict[str, Any]:
+        # Fallback: Basic heuristic or empty
+        state["final_answer"] = "Direct answer needed—implement heuristic here."
+        return state
+
+    # Conditional Edge: Based on route
+    def conditional_route(self, state: Dict[str, Any]) -> str:
+        route = state.get("route", "direct")
+        if route in ["search", "both"]:
+            return "search"
+        elif route == "code":
+            return "search"  # Smolagents handles code too
+        return "direct"
+
+    # Build the Graph
+    def build_graph(self):
+        # State
+        class AgentState(TypedDict):
+            question: str
+            route: str
+            search_results: str
+            final_answer: str
+
+        # Graph
+        workflow = StateGraph(AgentState)
+        workflow.add_node("router", self.router_node)
+        workflow.add_node("search", self.search_node)
+        workflow.add_node("direct", self.direct_node)
+
+        # Edges
+        workflow.set_entry_point("router")
+        workflow.add_conditional_edges("router", self.conditional_route, {"search": "search", "direct": "direct"})
+        workflow.add_edge("search", END)
+        workflow.add_edge("direct", END)
+
+        # Compile
+        self.graph = workflow.compile()
+
+    def __call__(self, question: str, task_id: str = None) -> str:
+        if not hasattr(self, "graph"):
+            self.build_graph()
+        # Download file if task_id
+        if task_id:
+            file_info = self.download_file.invoke({"task_id": task_id})
+            question += f" [File info: {file_info}]"  # Append to prompt
+
+        # Run graph
+        initial_state = {"question": question, "route": "", "search_results": "", "final_answer": ""}
+        final_state = self.graph.invoke(initial_state)
+        
+        # Extract clean answer (smolagents outputs code-thought → result)
+        answer = final_state.get("search_results", final_state.get("final_answer", "No answer generated."))
+        # Strip to exact (no extras)
+        if "final answer" in answer.lower():
+            answer = answer.split("final answer")[-1].strip().split()[0] if answer.split("final answer")[-1].strip() else answer
+        print(f"Agent final: {answer}")
+        return answer
+
+# --- Update run_and_submit_all (minor tweak for task_id) ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    # ... (keep all your existing code up to agent init)
+    
+    # 1. Instantiate Agent
     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
+        agent = CrmAgent()  # Our new beast
     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 your Agent (pass task_id)
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -77,120 +145,12 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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
+            # ...
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text, task_id)  # Pass task_id for files
             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})
+            results_log.append({"Task ID": task_id, "Question": question_text[:50] + "...", "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:
-        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:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
-
-# --- 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.
-
-        ---
-        **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.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]
-    )
-
-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)
+            # ...
+    
+    # ... (rest unchanged—submit as before)