update a few files

app.py

@@ -4,21 +4,106 @@ import requests
 import inspect
 import pandas as pd
 import json
+import yaml
+
+from smolagents import ToolCallingAgent, Tool, InferenceClientModel, DuckDuckGoSearchTool 
+from smolagents import WikipediaSearchTool, PythonInterpreterTool
+from smolagents import OpenAIServerModel
+from tools import fetch_file
+
+from phoenix.otel import register
+from openinference.instrumentation.smolagents import SmolagentsInstrumentor
+
+register()
+SmolagentsInstrumentor().instrument()
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+import os
+token = os.getenv("HF_TOKEN")
+
+if token is None:
+    raise ValueError('You must set the HF_TOKEN environment variable')
+else:
+    print('Token was found')
+
+
+#model = InferenceClientModel(model_id="Qwen/Qwen3-32B", provider="nscale")
+#model = InferenceClientModel(model_id="deepseek-ai/DeepSeek-R1", provider="nebius")
+
+# Set your Gemini API key in the environment variable GEMINI_API_KEY_1
+model = OpenAIServerModel(
+    model_id="gemini-2.5-flash", 
+    api_base="https://generativelanguage.googleapis.com/v1beta", 
+    api_key=os.getenv("GEMINI_API_KEY_1")
+    ) 
+print('GEMINI_API_KEY_1 was found:', os.getenv("GEMINI_API_KEY_1") is not None)
+
 # --- 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:
+
+    def __call__(self, taskid: str, 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
+        #fixed_answer = "This is a default answer."
+        #print(f"Agent returning fixed answer: {fixed_answer}")
+
+        # Define the prompt for the agent
+        # Report your thoughts, and finish your answer with the following template: 
+
+        prompt = f"""
+        
+        You are a general AI assistant. 
+        I will ask you a question and you can use 10 steps to answer the question.
+        You can use the tools I provide you to answer my question. Every tool call reduces the number 
+        of remaining steps available to answer the question. 
+
+        YOUR FINAL ANSWER has be a number OR as few words as possible OR a comma separated list of numbers and/or strings.
+        If you are asked for a number, do not use comma to write your number neither use units such as $ or percent sign unless specified otherwise.
+        If you are asked for a string, do not use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.
+        If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string. 
+
+        Finish your answer with the following template: 
+        FINAL ANSWER: [YOUR FINAL ANSWER].        
+                
+        The taskid is {taskid}. If you need to download a file that comes with the question then use 
+        the taskid to fetch the file
+        The question is '{question}'.
+
+        """
+
+        agent = ToolCallingAgent(
+            tools=[
+                DuckDuckGoSearchTool(), 
+                WikipediaSearchTool(),
+                fetch_file,
+            ], 
+            model=model,
+            max_steps=10,
+            #tool_choice="auto",
+         )
+
+        # Run the agent with the prompt
+        fixed_answer = agent.run(prompt)
+        # Clean the answer
+        cleaned_answer = self.clean_answer(fixed_answer)
+
+        print(f"Agent returned cleaned answer: {cleaned_answer}")
+        return cleaned_answer
+    
+    def clean_answer(self, answer: str) -> str:
+        # Remove "FINAL ANSWER:" (with or without trailing space)
+        answer = answer.replace("FINAL ANSWER:", "").strip()
+        # Remove last character if it is a period
+        if answer.endswith("."):
+            answer = answer[:-1]
+        return answer
+        
+
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -76,19 +161,23 @@ def run_and_submit_all( profile: gr.OAuthProfile | 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
-        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})
-        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}"})
+
+    item = questions_data[0] if questions_data else None
+    #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
+    try:
+        submitted_answer = agent(task_id, question_text)
+        answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
+        print(f"Task ID: {task_id}, Question: {question_text[:50]}..., 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}"})
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
@@ -102,18 +191,21 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 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.')}"
-        )
+        #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)
+        # delete this the next line
+        final_status = "Dummy status"
+
         return final_status, results_df
     except requests.exceptions.HTTPError as e:
         error_detail = f"Server responded with status {e.response.status_code}."

notebook.ipynb

@@ -10,10 +10,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "id": "6cff8644",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Token was found\n"
+     ]
+    }
+   ],
    "source": [
     "import os\n",
     "token = os.getenv(\"HF_TOKEN\")\n",
@@ -27,19 +35,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 21,
    "id": "a414cce1",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BasicAgent initialized.\n"
+     ]
+    }
+   ],
    "source": [
+    "import os\n",
+    "import requests\n",
+    "import inspect\n",
+    "import pandas as pd\n",
+    "import json\n",
     "import yaml\n",
     "\n",
-    "from smolagents import CodeAgent, Tool, InferenceClientModel, DuckDuckGoSearchTool, WikipediaSearchTool\n",
+    "from smolagents import ToolCallingAgent, Tool, InferenceClientModel, DuckDuckGoSearchTool, WikipediaSearchTool\n",
     "from smolagents import OpenAIServerModel\n",
     "from tools import fetch_file\n",
     "\n",
     "#model = InferenceClientModel(model_id=\"Qwen/Qwen3-32B\", provider=\"nscale\")\n",
-    "model = InferenceClientModel(model_id=\"deepseek-ai/DeepSeek-R1-Distill-Llama-70B\", provider=\"nscale\")\n",
+    "model = InferenceClientModel(model_id=\"deepseek-ai/DeepSeek-R1\", provider=\"nebius\")\n",
     "\n",
     "# Set your Gemini API key in the environment variable GEMINI_API_KEY_1\n",
     "#model = OpenAIServerModel(\n",
@@ -49,25 +70,53 @@
     "#    ) \n",
     "#print('API key was found:', os.getenv(\"GEMINI_API_KEY_1\") is not None)\n",
     "\n",
-    "#from app import BasicAgent\n",
+    "# --- Basic Agent Definition ---\n",
+    "# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------\n",
+    "class BasicAgent:\n",
+    "    def __init__(self):\n",
+    "        print(\"BasicAgent initialized.\")\n",
+    "    def __call__(self, taskid: str, question: str) -> str:\n",
+    "        print(f\"Agent received question (first 50 chars): {question[:50]}...\")\n",
+    "        #fixed_answer = \"This is a default answer.\"\n",
+    "        #print(f\"Agent returning fixed answer: {fixed_answer}\")\n",
+    "\n",
+    "        prompt = f\"\"\"\n",
+    "        \n",
+    "        You are a general AI assistant. \n",
+    "        I will ask you a question and you can use 9 steps to answer the question.\n",
+    "        You can use the tools I provide you to answer my question. Every tool call reduces the number \n",
+    "        of remaining steps available to answer the question. \n",
+    "        Report your thoughts, and finish your answer with the following template: \n",
+    "        FINAL ANSWER: [YOUR FINAL ANSWER]. \n",
+    "        \n",
+    "        YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings.\n",
+    "        If you are asked for a number, don’t use comma to write your number neither use units such as $ or percent sign unless specified otherwise.\n",
+    "        If you are asked for a string, don’t use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.\n",
+    "        If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string. \n",
+    "\n",
+    "        The taskid is {taskid}. If you need to download a file that comes with the question then use the taskid to fetch the file\n",
+    "        The question is '{question}'.\n",
+    "\n",
+    "        You have 9 steps to answer the question.\n",
+    "\n",
+    "        \"\"\"\n",
     "\n",
-    "system_prompt = \"\"\"You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: \n",
-    "FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings.\n",
-    "If you are asked for a number, don’t use comma to write your number neither use units such as $ or percent sign unless specified otherwise.\n",
-    "If you are asked for a string, don’t use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.\n",
-    "If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string. \n",
+    "        agent = ToolCallingAgent(\n",
+    "            tools=[\n",
+    "                fetch_file, \n",
+    "                DuckDuckGoSearchTool(), \n",
+    "                WikipediaSearchTool()\n",
+    "            ], \n",
+    "            model=model, \n",
+    "            max_steps=9,\n",
+    "         )\n",
     "\n",
-    "Here is the question: {question}\n",
-    "\"\"\"\n",
+    "        # Run the agent with the prompt\n",
+    "        fixed_answer = agent.run(prompt)\n",
     "\n",
-    "agent = CodeAgent(\n",
-    "    model=model, \n",
-    "    tools=[fetch_file, DuckDuckGoSearchTool(), WikipediaSearchTool()], \n",
-    "    add_base_tools=True,\n",
-    "    additional_authorized_imports=['requests', 'bs4'] \n",
-    "    )\n",
+    "        return fixed_answer\n",
     "\n",
-    "\n"
+    "agent = BasicAgent()\n"
    ]
   },
   {
@@ -80,10 +129,155 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 22,
    "id": "09b50aa1",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Agent received question (first 50 chars): How many studio albums were published by Mercedes ...\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d4b702; text-decoration-color: #d4b702\">╭──────────────────────────────────────────────────── </span><span style=\"color: #d4b702; text-decoration-color: #d4b702; font-weight: bold\">New run</span><span style=\"color: #d4b702; text-decoration-color: #d4b702\"> ────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>                                                                                                                 <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">You are a general AI assistant. </span>                                                                                <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        I will ask you a question and you can use 9 steps to answer the question.</span>                               <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        You can use the tools I provide you to answer my question. Every tool call reduces the number </span>          <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        of remaining steps available to answer the question. </span>                                                   <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        Report your thoughts, and finish your answer with the following template: </span>                              <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        FINAL ANSWER: [YOUR FINAL ANSWER\\]. </span>                                                                    <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        </span>                                                                                                        <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers </span>  <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">and/or strings.</span>                                                                                                 <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        If you are asked for a number, don’t use comma to write your number neither use units such as $ or </span>     <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">percent sign unless specified otherwise.</span>                                                                        <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        If you are asked for a string, don’t use articles, neither abbreviations (e.g. for cities), and write </span>  <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">the digits in plain text unless specified otherwise.</span>                                                            <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        If you are asked for a comma separated list, apply the above rules depending of whether the element to </span> <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">be put in the list is a number or a string. </span>                                                                    <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>                                                                                                                 <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        The taskid is 8e867cd7-cff9-4e6c-867a-ff5ddc2550be. If you need to download a file that comes with the </span> <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">question then use the taskid to fetch the file</span>                                                                  <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        The question is 'How many studio albums were published by Mercedes Sosa between 2000 and 2009 </span>          <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">(included)? You can use the latest 2022 version of english wikipedia.'.</span>                                         <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>                                                                                                                 <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span> <span style=\"font-weight: bold\">        You have 9 steps to answer the question.</span>                                                                <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>                                                                                                                 <span style=\"color: #d4b702; text-decoration-color: #d4b702\">│</span>\n",
+       "<span style=\"color: #d4b702; text-decoration-color: #d4b702\">╰─ InferenceClientModel - deepseek-ai/DeepSeek-R1 ────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[38;2;212;183;2m╭─\u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m \u001b[0m\u001b[1;38;2;212;183;2mNew run\u001b[0m\u001b[38;2;212;183;2m \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╮\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m                                                                                                                 \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mYou are a general AI assistant. \u001b[0m                                                                                \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        I will ask you a question and you can use 9 steps to answer the question.\u001b[0m                               \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        You can use the tools I provide you to answer my question. Every tool call reduces the number \u001b[0m          \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        of remaining steps available to answer the question. \u001b[0m                                                   \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        Report your thoughts, and finish your answer with the following template: \u001b[0m                              \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        FINAL ANSWER: [YOUR FINAL ANSWER\\]. \u001b[0m                                                                    \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        \u001b[0m                                                                                                        \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers \u001b[0m  \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mand/or strings.\u001b[0m                                                                                                 \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        If you are asked for a number, don’t use comma to write your number neither use units such as $ or \u001b[0m     \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mpercent sign unless specified otherwise.\u001b[0m                                                                        \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        If you are asked for a string, don’t use articles, neither abbreviations (e.g. for cities), and write \u001b[0m  \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mthe digits in plain text unless specified otherwise.\u001b[0m                                                            \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        If you are asked for a comma separated list, apply the above rules depending of whether the element to \u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mbe put in the list is a number or a string. \u001b[0m                                                                    \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m                                                                                                                 \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        The taskid is 8e867cd7-cff9-4e6c-867a-ff5ddc2550be. If you need to download a file that comes with the \u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mquestion then use the taskid to fetch the file\u001b[0m                                                                  \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        The question is 'How many studio albums were published by Mercedes Sosa between 2000 and 2009 \u001b[0m          \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m(included)? You can use the latest 2022 version of english wikipedia.'.\u001b[0m                                         \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m                                                                                                                 \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m        You have 9 steps to answer the question.\u001b[0m                                                                \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m│\u001b[0m                                                                                                                 \u001b[38;2;212;183;2m│\u001b[0m\n",
+       "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m InferenceClientModel - deepseek-ai/DeepSeek-R1 \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d4b702; text-decoration-color: #d4b702\">━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ </span><span style=\"font-weight: bold\">Step </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span><span style=\"color: #d4b702; text-decoration-color: #d4b702\"> ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[38;2;212;183;2m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ \u001b[0m\u001b[1mStep \u001b[0m\u001b[1;36m1\u001b[0m\u001b[38;2;212;183;2m ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">Error while generating output:</span>\n",
+       "<span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">(Request ID: </span><span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">Root</span><span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">=</span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span><span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">-686d606c-1f8bffb50e7ac4b077a26fe0;</span><span style=\"color: #ffff00; text-decoration-color: #ffff00\">2128d2d1-4e56-4788-a9eb-3015f54f1e44</span><span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">)</span>\n",
+       "\n",
+       "<span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">Bad request:</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1;31mError while generating output:\u001b[0m\n",
+       "\u001b[1;31m(\u001b[0m\u001b[1;31mRequest ID: \u001b[0m\u001b[1;33mRoot\u001b[0m\u001b[1;31m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;31m-686d606c-1f8bffb50e7ac4b077a26fe0;\u001b[0m\u001b[93m2128d2d1-4e56-4788-a9eb-3015f54f1e44\u001b[0m\u001b[1;31m)\u001b[0m\n",
+       "\n",
+       "\u001b[1;31mBad request:\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">[Step 1: Duration 0.80 seconds]</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[2m[Step 1: Duration 0.80 seconds]\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "ename": "AgentGenerationError",
+     "evalue": "Error while generating output:\n(Request ID: Root=1-686d606c-1f8bffb50e7ac4b077a26fe0;2128d2d1-4e56-4788-a9eb-3015f54f1e44)\n\nBad request:",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mHTTPError\u001b[0m                                 Traceback (most recent call last)",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\huggingface_hub\\utils\\_http.py:409\u001b[0m, in \u001b[0;36mhf_raise_for_status\u001b[1;34m(response, endpoint_name)\u001b[0m\n\u001b[0;32m    408\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 409\u001b[0m     \u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mraise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    410\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m HTTPError \u001b[38;5;28;01mas\u001b[39;00m e:\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\requests\\models.py:1024\u001b[0m, in \u001b[0;36mResponse.raise_for_status\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m   1023\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m http_error_msg:\n\u001b[1;32m-> 1024\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m HTTPError(http_error_msg, response\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m)\n",
+      "\u001b[1;31mHTTPError\u001b[0m: 400 Client Error: Bad Request for url: https://router.huggingface.co/nebius/v1/chat/completions",
+      "\nThe above exception was the direct cause of the following exception:\n",
+      "\u001b[1;31mBadRequestError\u001b[0m                           Traceback (most recent call last)",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\smolagents\\agents.py:1272\u001b[0m, in \u001b[0;36mToolCallingAgent._step_stream\u001b[1;34m(self, memory_step)\u001b[0m\n\u001b[0;32m   1271\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1272\u001b[0m     chat_message: ChatMessage \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1273\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_messages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1274\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstop_sequences\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mObservation:\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mCalling tools:\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1275\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtools_to_call_from\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtools_and_managed_agents\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1276\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1278\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlogger\u001b[38;5;241m.\u001b[39mlog_markdown(\n\u001b[0;32m   1279\u001b[0m         content\u001b[38;5;241m=\u001b[39mchat_message\u001b[38;5;241m.\u001b[39mcontent \u001b[38;5;28;01mif\u001b[39;00m chat_message\u001b[38;5;241m.\u001b[39mcontent \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mstr\u001b[39m(chat_message\u001b[38;5;241m.\u001b[39mraw),\n\u001b[0;32m   1280\u001b[0m         title\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOutput message of the LLM:\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m   1281\u001b[0m         level\u001b[38;5;241m=\u001b[39mLogLevel\u001b[38;5;241m.\u001b[39mDEBUG,\n\u001b[0;32m   1282\u001b[0m     )\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\smolagents\\models.py:1408\u001b[0m, in \u001b[0;36mInferenceClientModel.generate\u001b[1;34m(self, messages, stop_sequences, response_format, tools_to_call_from, **kwargs)\u001b[0m\n\u001b[0;32m   1399\u001b[0m completion_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepare_completion_kwargs(\n\u001b[0;32m   1400\u001b[0m     messages\u001b[38;5;241m=\u001b[39mmessages,\n\u001b[0;32m   1401\u001b[0m     stop_sequences\u001b[38;5;241m=\u001b[39mstop_sequences,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1406\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[0;32m   1407\u001b[0m )\n\u001b[1;32m-> 1408\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mchat_completion\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mcompletion_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1410\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_last_input_token_count \u001b[38;5;241m=\u001b[39m response\u001b[38;5;241m.\u001b[39musage\u001b[38;5;241m.\u001b[39mprompt_tokens\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\huggingface_hub\\inference\\_client.py:924\u001b[0m, in \u001b[0;36mInferenceClient.chat_completion\u001b[1;34m(self, messages, model, stream, frequency_penalty, logit_bias, logprobs, max_tokens, n, presence_penalty, response_format, seed, stop, stream_options, temperature, tool_choice, tool_prompt, tools, top_logprobs, top_p, extra_body)\u001b[0m\n\u001b[0;32m    917\u001b[0m request_parameters \u001b[38;5;241m=\u001b[39m provider_helper\u001b[38;5;241m.\u001b[39mprepare_request(\n\u001b[0;32m    918\u001b[0m     inputs\u001b[38;5;241m=\u001b[39mmessages,\n\u001b[0;32m    919\u001b[0m     parameters\u001b[38;5;241m=\u001b[39mparameters,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    922\u001b[0m     api_key\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtoken,\n\u001b[0;32m    923\u001b[0m )\n\u001b[1;32m--> 924\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_inner_post\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest_parameters\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    926\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stream:\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\huggingface_hub\\inference\\_client.py:280\u001b[0m, in \u001b[0;36mInferenceClient._inner_post\u001b[1;34m(self, request_parameters, stream)\u001b[0m\n\u001b[0;32m    279\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 280\u001b[0m     \u001b[43mhf_raise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresponse\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    281\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m response\u001b[38;5;241m.\u001b[39miter_lines() \u001b[38;5;28;01mif\u001b[39;00m stream \u001b[38;5;28;01melse\u001b[39;00m response\u001b[38;5;241m.\u001b[39mcontent\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\huggingface_hub\\utils\\_http.py:465\u001b[0m, in \u001b[0;36mhf_raise_for_status\u001b[1;34m(response, endpoint_name)\u001b[0m\n\u001b[0;32m    462\u001b[0m     message \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m    463\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mBad request for \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mendpoint_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m endpoint:\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m endpoint_name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mBad request:\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    464\u001b[0m     )\n\u001b[1;32m--> 465\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m _format(BadRequestError, message, response) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01me\u001b[39;00m\n\u001b[0;32m    467\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m response\u001b[38;5;241m.\u001b[39mstatus_code \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m403\u001b[39m:\n",
+      "\u001b[1;31mBadRequestError\u001b[0m: (Request ID: Root=1-686d606c-1f8bffb50e7ac4b077a26fe0;2128d2d1-4e56-4788-a9eb-3015f54f1e44)\n\nBad request:",
+      "\nThe above exception was the direct cause of the following exception:\n",
+      "\u001b[1;31mAgentGenerationError\u001b[0m                      Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[22], line 11\u001b[0m\n\u001b[0;32m      8\u001b[0m question_text \u001b[38;5;241m=\u001b[39m item[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mquestion\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[0;32m      9\u001b[0m task_id \u001b[38;5;241m=\u001b[39m item[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtask_id\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m---> 11\u001b[0m submitted_answer \u001b[38;5;241m=\u001b[39m \u001b[43magent\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtask_id\u001b[49m\u001b[43m,\u001b[49m\u001b[43mquestion_text\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     13\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSubmitted answer:\u001b[39m\u001b[38;5;124m\"\u001b[39m, submitted_answer)\n",
+      "Cell \u001b[1;32mIn[21], line 65\u001b[0m, in \u001b[0;36mBasicAgent.__call__\u001b[1;34m(self, taskid, question)\u001b[0m\n\u001b[0;32m     54\u001b[0m agent \u001b[38;5;241m=\u001b[39m ToolCallingAgent(\n\u001b[0;32m     55\u001b[0m     tools\u001b[38;5;241m=\u001b[39m[\n\u001b[0;32m     56\u001b[0m         fetch_file, \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     61\u001b[0m     max_steps\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m9\u001b[39m,\n\u001b[0;32m     62\u001b[0m  )\n\u001b[0;32m     64\u001b[0m \u001b[38;5;66;03m# Run the agent with the prompt\u001b[39;00m\n\u001b[1;32m---> 65\u001b[0m fixed_answer \u001b[38;5;241m=\u001b[39m \u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprompt\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     67\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fixed_answer\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\smolagents\\agents.py:442\u001b[0m, in \u001b[0;36mMultiStepAgent.run\u001b[1;34m(self, task, stream, reset, images, additional_args, max_steps)\u001b[0m\n\u001b[0;32m    439\u001b[0m run_start_time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime()\n\u001b[0;32m    440\u001b[0m \u001b[38;5;66;03m# Outputs are returned only at the end. We only look at the last step.\u001b[39;00m\n\u001b[1;32m--> 442\u001b[0m steps \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_run_stream\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtask\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_steps\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_steps\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mimages\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mimages\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    443\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(steps[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m], FinalAnswerStep)\n\u001b[0;32m    444\u001b[0m output \u001b[38;5;241m=\u001b[39m steps[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\u001b[38;5;241m.\u001b[39moutput\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\smolagents\\agents.py:530\u001b[0m, in \u001b[0;36mMultiStepAgent._run_stream\u001b[1;34m(self, task, max_steps, images)\u001b[0m\n\u001b[0;32m    527\u001b[0m             final_answer \u001b[38;5;241m=\u001b[39m output\u001b[38;5;241m.\u001b[39moutput\n\u001b[0;32m    528\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m AgentGenerationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    529\u001b[0m     \u001b[38;5;66;03m# Agent generation errors are not caused by a Model error but an implementation error: so we should raise them and exit.\u001b[39;00m\n\u001b[1;32m--> 530\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[0;32m    531\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m AgentError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    532\u001b[0m     \u001b[38;5;66;03m# Other AgentError types are caused by the Model, so we should log them and iterate.\u001b[39;00m\n\u001b[0;32m    533\u001b[0m     action_step\u001b[38;5;241m.\u001b[39merror \u001b[38;5;241m=\u001b[39m e\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\smolagents\\agents.py:517\u001b[0m, in \u001b[0;36mMultiStepAgent._run_stream\u001b[1;34m(self, task, max_steps, images)\u001b[0m\n\u001b[0;32m    515\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlogger\u001b[38;5;241m.\u001b[39mlog_rule(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mStep \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstep_number\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m, level\u001b[38;5;241m=\u001b[39mLogLevel\u001b[38;5;241m.\u001b[39mINFO)\n\u001b[0;32m    516\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 517\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43moutput\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_step_stream\u001b[49m\u001b[43m(\u001b[49m\u001b[43maction_step\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[0;32m    518\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;66;43;03m# Yield streaming deltas\u001b[39;49;00m\n\u001b[0;32m    519\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43misinstance\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43moutput\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43mActionOutput\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mToolOutput\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[0;32m    520\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43;01myield\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43moutput\u001b[49m\n",
+      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python313\\site-packages\\smolagents\\agents.py:1289\u001b[0m, in \u001b[0;36mToolCallingAgent._step_stream\u001b[1;34m(self, memory_step)\u001b[0m\n\u001b[0;32m   1287\u001b[0m     memory_step\u001b[38;5;241m.\u001b[39mtoken_usage \u001b[38;5;241m=\u001b[39m chat_message\u001b[38;5;241m.\u001b[39mtoken_usage\n\u001b[0;32m   1288\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m-> 1289\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m AgentGenerationError(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mError while generating output:\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlogger) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01me\u001b[39;00m\n\u001b[0;32m   1291\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chat_message\u001b[38;5;241m.\u001b[39mtool_calls \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(chat_message\u001b[38;5;241m.\u001b[39mtool_calls) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[0;32m   1292\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n",
+      "\u001b[1;31mAgentGenerationError\u001b[0m: Error while generating output:\n(Request ID: Root=1-686d606c-1f8bffb50e7ac4b077a26fe0;2128d2d1-4e56-4788-a9eb-3015f54f1e44)\n\nBad request:"
+     ]
+    }
+   ],
    "source": [
     "item = {\n",
     "    \"task_id\": \"8e867cd7-cff9-4e6c-867a-ff5ddc2550be\",\n",
@@ -93,12 +287,11 @@
     "  }\n",
     "\n",
     "question_text = item[\"question\"]\n",
-    "prompt_with_question = system_prompt.format(question=question_text)\n",
+    "task_id = item[\"task_id\"]\n",
     "\n",
-    "print(f\"Question: {prompt_with_question}\")\n",
+    "submitted_answer = agent(task_id,question_text)\n",
     "\n",
-    "#task_id = item[\"task_id\"]\n",
-    "submitted_answer = agent(prompt_with_question)\n"
+    "print(\"Submitted answer:\", submitted_answer)\n"
    ]
   }
  ],

tools.py

@@ -1,7 +1,25 @@
-from smolagents import tool
 import requests
 import json
 import os
+from smolagents import tool
+from typing import Any, Optional
+from smolagents.tools import Tool
+
+class FinalAnswerTool(Tool):
+    name = "final_answer"
+    description = "Provides a final answer to the given problem."
+    inputs = {'answer': {'type': 'any', 'description': 'The final answer to the problem'}}
+    output_type = "any"
+
+    def forward(self, answer: Any) -> Any:
+
+        # Returns the final answer provided by the agent.
+        # FINAL ANSWER: [YOUR FINAL ANSWER].
+        
+        return answer
+
+    def __init__(self, *args, **kwargs):
+        self.is_initialized = False
 
 @tool
 def fetch_questions(api_url: str) -> dict | None: