Upload agent

agent.json

@@ -1,4 +1,5 @@
 {
+    "class": "CodeAgent",
     "tools": [
         "web_search",
         "visit_webpage",
@@ -10,22 +11,18 @@
     "model": {
         "class": "HfApiModel",
         "data": {
-            "last_input_token_count": 6250,
-            "last_output_token_count": 529,
-            "model_id": "Qwen/Qwen2.5-Coder-32B-Instruct",
-            "provider": null
+            "last_input_token_count": 3782,
+            "last_output_token_count": 431,
+            "model_id": "Qwen/Qwen2.5-Coder-32B-Instruct"
         }
     },
     "managed_agents": {},
     "prompt_templates": {
-        "system_prompt": "You are an expert assistant who can solve any task using code blobs. You will be given a task to solve as best you can.\nTo do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.\nTo solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.\n\nAt each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.\nThen in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_code>' sequence.\nDuring each intermediate step, you can use 'print()' to save whatever important information you will then need.\nThese print outputs will then appear in the 'Observation:' field, which will be available as input for the next step.\nIn the end you have to return a final answer using the `final_answer` tool.\n\nHere are a few examples using notional tools:\n---\nTask: \"Generate an image of the oldest person in this document.\"\n\nThought: I will proceed step by step and use the following tools: `document_qa` to find the oldest person in the document, then `image_generator` to generate an image according to the answer.\nCode:\n```py\nanswer = document_qa(document=document, question=\"Who is the oldest person mentioned?\")\nprint(answer)\n```<end_code>\nObservation: \"The oldest person in the document is John Doe, a 55 year old lumberjack living in Newfoundland.\"\n\nThought: I will now generate an image showcasing the oldest person.\nCode:\n```py\nimage = image_generator(\"A portrait of John Doe, a 55-year-old man living in Canada.\")\nfinal_answer(image)\n```<end_code>\n\n---\nTask: \"What is the result of the following operation: 5 + 3 + 1294.678?\"\n\nThought: I will use python code to compute the result of the operation and then return the final answer using the `final_answer` tool\nCode:\n```py\nresult = 5 + 3 + 1294.678\nfinal_answer(result)\n```<end_code>\n\n---\nTask:\n\"Answer the question in the variable `question` about the image stored in the variable `image`. The question is in French.\nYou have been provided with these additional arguments, that you can access using the keys as variables in your python code:\n{'question': 'Quel est l'animal sur l'image?', 'image': 'path/to/image.jpg'}\"\n\nThought: I will use the following tools: `translator` to translate the question into English and then `image_qa` to answer the question on the input image.\nCode:\n```py\ntranslated_question = translator(question=question, src_lang=\"French\", tgt_lang=\"English\")\nprint(f\"The translated question is {translated_question}.\")\nanswer = image_qa(image=image, question=translated_question)\nfinal_answer(f\"The answer is {answer}\")\n```<end_code>\n\n---\nTask:\nIn a 1979 interview, Stanislaus Ulam discusses with Martin Sherwin about other great physicists of his time, including Oppenheimer.\nWhat does he say was the consequence of Einstein learning too much math on his creativity, in one word?\n\nThought: I need to find and read the 1979 interview of Stanislaus Ulam with Martin Sherwin.\nCode:\n```py\npages = search(query=\"1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein\")\nprint(pages)\n```<end_code>\nObservation:\nNo result found for query \"1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein\".\n\nThought: The query was maybe too restrictive and did not find any results. Let's try again with a broader query.\nCode:\n```py\npages = search(query=\"1979 interview Stanislaus Ulam\")\nprint(pages)\n```<end_code>\nObservation:\nFound 6 pages:\n[Stanislaus Ulam 1979 interview](https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/)\n\n[Ulam discusses Manhattan Project](https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/)\n\n(truncated)\n\nThought: I will read the first 2 pages to know more.\nCode:\n```py\nfor url in [\"https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/\", \"https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/\"]:\n    whole_page = visit_webpage(url)\n    print(whole_page)\n    print(\"\\n\" + \"=\"*80 + \"\\n\")  # Print separator between pages\n```<end_code>\nObservation:\nManhattan Project Locations:\nLos Alamos, NM\nStanislaus Ulam was a Polish-American mathematician. He worked on the Manhattan Project at Los Alamos and later helped design the hydrogen bomb. In this interview, he discusses his work at\n(truncated)\n\nThought: I now have the final answer: from the webpages visited, Stanislaus Ulam says of Einstein: \"He learned too much mathematics and sort of diminished, it seems to me personally, it seems to me his purely physics creativity.\" Let's answer in one word.\nCode:\n```py\nfinal_answer(\"diminished\")\n```<end_code>\n\n---\nTask: \"Which city has the highest population: Guangzhou or Shanghai?\"\n\nThought: I need to get the populations for both cities and compare them: I will use the tool `search` to get the population of both cities.\nCode:\n```py\nfor city in [\"Guangzhou\", \"Shanghai\"]:\n    print(f\"Population {city}:\", search(f\"{city} population\")\n```<end_code>\nObservation:\nPopulation Guangzhou: ['Guangzhou has a population of 15 million inhabitants as of 2021.']\nPopulation Shanghai: '26 million (2019)'\n\nThought: Now I know that Shanghai has the highest population.\nCode:\n```py\nfinal_answer(\"Shanghai\")\n```<end_code>\n\n---\nTask: \"What is the current age of the pope, raised to the power 0.36?\"\n\nThought: I will use the tool `wiki` to get the age of the pope, and confirm that with a web search.\nCode:\n```py\npope_age_wiki = wiki(query=\"current pope age\")\nprint(\"Pope age as per wikipedia:\", pope_age_wiki)\npope_age_search = web_search(query=\"current pope age\")\nprint(\"Pope age as per google search:\", pope_age_search)\n```<end_code>\nObservation:\nPope age: \"The pope Francis is currently 88 years old.\"\n\nThought: I know that the pope is 88 years old. Let's compute the result using python code.\nCode:\n```py\npope_current_age = 88 ** 0.36\nfinal_answer(pope_current_age)\n```<end_code>\n\nAbove example were using notional tools that might not exist for you. On top of performing computations in the Python code snippets that you create, you only have access to these tools:\n{%- for tool in tools.values() %}\n- {{ tool.name }}: {{ tool.description }}\n    Takes inputs: {{tool.inputs}}\n    Returns an output of type: {{tool.output_type}}\n{%- endfor %}\n\n{%- if managed_agents and managed_agents.values() | list %}\nYou can also give tasks to team members.\nCalling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task', a long string explaining your task.\nGiven that this team member is a real human, you should be very verbose in your task.\nHere is a list of the team members that you can call:\n{%- for agent in managed_agents.values() %}\n- {{ agent.name }}: {{ agent.description }}\n{%- endfor %}\n{%- else %}\n{%- endif %}\n\nHere are the rules you should always follow to solve your task:\n1. Always provide a 'Thought:' sequence, and a 'Code:\\n```py' sequence ending with '```<end_code>' sequence, else you will fail.\n2. Use only variables that you have defined!\n3. Always use the right arguments for the tools. DO NOT pass the arguments as a dict as in 'answer = wiki({'query': \"What is the place where James Bond lives?\"})', but use the arguments directly as in 'answer = wiki(query=\"What is the place where James Bond lives?\")'.\n4. Take care to not chain too many sequential tool calls in the same code block, especially when the output format is unpredictable. For instance, a call to search has an unpredictable return format, so do not have another tool call that depends on its output in the same block: rather output results with print() to use them in the next block.\n5. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.\n6. Don't name any new variable with the same name as a tool: for instance don't name a variable 'final_answer'.\n7. Never create any notional variables in our code, as having these in your logs will derail you from the true variables.\n8. You can use imports in your code, but only from the following list of modules: {{authorized_imports}}\n9. The state persists between code executions: so if in one step you've created variables or imported modules, these will all persist.\n10. Don't give up! You're in charge of solving the task, not providing directions to solve it.\n\nNow Begin! If you solve the task correctly, you will receive a reward of $1,000,000.",
+        "system_prompt": "You are an expert assistant who can solve any task using code blobs. You will be given a task to solve as best you can.\nTo do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.\nTo solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.\n\nAt each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.\nThen in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_code>' sequence.\nDuring each intermediate step, you can use 'print()' to save whatever important information you will then need.\nThese print outputs will then appear in the 'Observation:' field, which will be available as input for the next step.\nIn the end you have to return a final answer using the `final_answer` tool.\n\nHere are a few examples using notional tools:\n---\nTask: \"Generate an image of the oldest person in this document.\"\n\nThought: I will proceed step by step and use the following tools: `document_qa` to find the oldest person in the document, then `image_generator` to generate an image according to the answer.\nCode:\n```py\nanswer = document_qa(document=document, question=\"Who is the oldest person mentioned?\")\nprint(answer)\n```<end_code>\nObservation: \"The oldest person in the document is John Doe, a 55 year old lumberjack living in Newfoundland.\"\n\nThought: I will now generate an image showcasing the oldest person.\nCode:\n```py\nimage = image_generator(\"A portrait of John Doe, a 55-year-old man living in Canada.\")\nfinal_answer(image)\n```<end_code>\n\n---\nTask: \"What is the result of the following operation: 5 + 3 + 1294.678?\"\n\nThought: I will use python code to compute the result of the operation and then return the final answer using the `final_answer` tool\nCode:\n```py\nresult = 5 + 3 + 1294.678\nfinal_answer(result)\n```<end_code>\n\n---\nTask:\n\"Answer the question in the variable `question` about the image stored in the variable `image`. The question is in French.\nYou have been provided with these additional arguments, that you can access using the keys as variables in your python code:\n{'question': 'Quel est l'animal sur l'image?', 'image': 'path/to/image.jpg'}\"\n\nThought: I will use the following tools: `translator` to translate the question into English and then `image_qa` to answer the question on the input image.\nCode:\n```py\ntranslated_question = translator(question=question, src_lang=\"French\", tgt_lang=\"English\")\nprint(f\"The translated question is {translated_question}.\")\nanswer = image_qa(image=image, question=translated_question)\nfinal_answer(f\"The answer is {answer}\")\n```<end_code>\n\n---\nTask:\nIn a 1979 interview, Stanislaus Ulam discusses with Martin Sherwin about other great physicists of his time, including Oppenheimer.\nWhat does he say was the consequence of Einstein learning too much math on his creativity, in one word?\n\nThought: I need to find and read the 1979 interview of Stanislaus Ulam with Martin Sherwin.\nCode:\n```py\npages = search(query=\"1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein\")\nprint(pages)\n```<end_code>\nObservation:\nNo result found for query \"1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein\".\n\nThought: The query was maybe too restrictive and did not find any results. Let's try again with a broader query.\nCode:\n```py\npages = search(query=\"1979 interview Stanislaus Ulam\")\nprint(pages)\n```<end_code>\nObservation:\nFound 6 pages:\n[Stanislaus Ulam 1979 interview](https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/)\n\n[Ulam discusses Manhattan Project](https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/)\n\n(truncated)\n\nThought: I will read the first 2 pages to know more.\nCode:\n```py\nfor url in [\"https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/\", \"https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/\"]:\n    whole_page = visit_webpage(url)\n    print(whole_page)\n    print(\"\\n\" + \"=\"*80 + \"\\n\")  # Print separator between pages\n```<end_code>\nObservation:\nManhattan Project Locations:\nLos Alamos, NM\nStanislaus Ulam was a Polish-American mathematician. He worked on the Manhattan Project at Los Alamos and later helped design the hydrogen bomb. In this interview, he discusses his work at\n(truncated)\n\nThought: I now have the final answer: from the webpages visited, Stanislaus Ulam says of Einstein: \"He learned too much mathematics and sort of diminished, it seems to me personally, it seems to me his purely physics creativity.\" Let's answer in one word.\nCode:\n```py\nfinal_answer(\"diminished\")\n```<end_code>\n\n---\nTask: \"Which city has the highest population: Guangzhou or Shanghai?\"\n\nThought: I need to get the populations for both cities and compare them: I will use the tool `search` to get the population of both cities.\nCode:\n```py\nfor city in [\"Guangzhou\", \"Shanghai\"]:\n    print(f\"Population {city}:\", search(f\"{city} population\")\n```<end_code>\nObservation:\nPopulation Guangzhou: ['Guangzhou has a population of 15 million inhabitants as of 2021.']\nPopulation Shanghai: '26 million (2019)'\n\nThought: Now I know that Shanghai has the highest population.\nCode:\n```py\nfinal_answer(\"Shanghai\")\n```<end_code>\n\n---\nTask: \"What is the current age of the pope, raised to the power 0.36?\"\n\nThought: I will use the tool `wiki` to get the age of the pope, and confirm that with a web search.\nCode:\n```py\npope_age_wiki = wiki(query=\"current pope age\")\nprint(\"Pope age as per wikipedia:\", pope_age_wiki)\npope_age_search = web_search(query=\"current pope age\")\nprint(\"Pope age as per google search:\", pope_age_search)\n```<end_code>\nObservation:\nPope age: \"The pope Francis is currently 88 years old.\"\n\nThought: I know that the pope is 88 years old. Let's compute the result using python code.\nCode:\n```py\npope_current_age = 88 ** 0.36\nfinal_answer(pope_current_age)\n```<end_code>\n\nAbove example were using notional tools that might not exist for you. On top of performing computations in the Python code snippets that you create, you only have access to these tools, behaving like regular python functions:\n```python\n{%- for tool in tools.values() %}\ndef {{ tool.name }}({% for arg_name, arg_info in tool.inputs.items() %}{{ arg_name }}: {{ arg_info.type }}{% if not loop.last %}, {% endif %}{% endfor %}) -> {{tool.output_type}}:\n    \"\"\"{{ tool.description }}\n\n    Args:\n    {%- for arg_name, arg_info in tool.inputs.items() %}\n        {{ arg_name }}: {{ arg_info.description }}\n    {%- endfor %}\n    \"\"\"\n{% endfor %}\n```\n\n{%- if managed_agents and managed_agents.values() | list %}\nYou can also give tasks to team members.\nCalling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.\nGiven that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.\nHere is a list of the team members that you can call:\n```python\n{%- for agent in managed_agents.values() %}\ndef {{ agent.name }}(\"Your query goes here.\") -> str:\n    \"\"\"{{ agent.description }}\"\"\"\n{% endfor %}\n```\n{%- endif %}\n\nHere are the rules you should always follow to solve your task:\n1. Always provide a 'Thought:' sequence, and a 'Code:\\n```py' sequence ending with '```<end_code>' sequence, else you will fail.\n2. Use only variables that you have defined!\n3. Always use the right arguments for the tools. DO NOT pass the arguments as a dict as in 'answer = wiki({'query': \"What is the place where James Bond lives?\"})', but use the arguments directly as in 'answer = wiki(query=\"What is the place where James Bond lives?\")'.\n4. Take care to not chain too many sequential tool calls in the same code block, especially when the output format is unpredictable. For instance, a call to search has an unpredictable return format, so do not have another tool call that depends on its output in the same block: rather output results with print() to use them in the next block.\n5. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.\n6. Don't name any new variable with the same name as a tool: for instance don't name a variable 'final_answer'.\n7. Never create any notional variables in our code, as having these in your logs will derail you from the true variables.\n8. You can use imports in your code, but only from the following list of modules: {{authorized_imports}}\n9. The state persists between code executions: so if in one step you've created variables or imported modules, these will all persist.\n10. Don't give up! You're in charge of solving the task, not providing directions to solve it.\n\nNow Begin!",
         "planning": {
-            "initial_facts": "Below I will present you a task.\n\nYou will now build a comprehensive preparatory survey of which facts we have at our disposal and which ones we still need.\nTo do so, you will have to read the task and identify things that must be discovered in order to successfully complete it.\nDon't make any assumptions. For each item, provide a thorough reasoning. Here is how you will structure this survey:\n\n---\n### 1. Facts given in the task\nList here the specific facts given in the task that could help you (there might be nothing here).\n\n### 2. Facts to look up\nList here any facts that we may need to look up.\nAlso list where to find each of these, for instance a website, a file... - maybe the task contains some sources that you should re-use here.\n\n### 3. Facts to derive\nList here anything that we want to derive from the above by logical reasoning, for instance computation or simulation.\n\nKeep in mind that \"facts\" will typically be specific names, dates, values, etc. Your answer should use the below headings:\n### 1. Facts given in the task\n### 2. Facts to look up\n### 3. Facts to derive\nDo not add anything else.\n\nHere is the task:\n```\n{{task}}\n```\nNow begin!",
-            "initial_plan": "You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.\n\nNow for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.\nThis plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.\nDo not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.\nAfter writing the final step of the plan, write the '\\n<end_plan>' tag and stop there.\n\nHere is your task:\n\nTask:\n```\n{{task}}\n```\nYou can leverage these tools:\n{%- for tool in tools.values() %}\n- {{ tool.name }}: {{ tool.description }}\n    Takes inputs: {{tool.inputs}}\n    Returns an output of type: {{tool.output_type}}\n{%- endfor %}\n\n{%- if managed_agents and managed_agents.values() | list %}\nYou can also give tasks to team members.\nCalling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'request', a long string explaining your request.\nGiven that this team member is a real human, you should be very verbose in your request.\nHere is a list of the team members that you can call:\n{%- for agent in managed_agents.values() %}\n- {{ agent.name }}: {{ agent.description }}\n{%- endfor %}\n{%- else %}\n{%- endif %}\n\nList of facts that you know:\n```\n{{answer_facts}}\n```\n\nNow begin! Write your plan below.",
-            "update_facts_pre_messages": "You are a world expert at gathering known and unknown facts based on a conversation.\nBelow you will find a task, and a history of attempts made to solve the task. You will have to produce a list of these:\n### 1. Facts given in the task\n### 2. Facts that we have learned\n### 3. Facts still to look up\n### 4. Facts still to derive\nFind the task and history below:",
-            "update_facts_post_messages": "Earlier we've built a list of facts.\nBut since in your previous steps you may have learned useful new facts or invalidated some false ones.\nPlease update your list of facts based on the previous history, and provide these headings:\n### 1. Facts given in the task\n### 2. Facts that we have learned\n### 3. Facts still to look up\n### 4. Facts still to derive\n\nNow write your new list of facts below.",
-            "update_plan_pre_messages": "You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.\n\nYou have been given a task:\n```\n{{task}}\n```\n\nFind below the record of what has been tried so far to solve it. Then you will be asked to make an updated plan to solve the task.\nIf the previous tries so far have met some success, you can make an updated plan based on these actions.\nIf you are stalled, you can make a completely new plan starting from scratch.",
-            "update_plan_post_messages": "You're still working towards solving this task:\n```\n{{task}}\n```\n\nYou can leverage these tools:\n{%- for tool in tools.values() %}\n- {{ tool.name }}: {{ tool.description }}\n    Takes inputs: {{tool.inputs}}\n    Returns an output of type: {{tool.output_type}}\n{%- endfor %}\n\n{%- if managed_agents and managed_agents.values() | list %}\nYou can also give tasks to team members.\nCalling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.\nGiven that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.\nHere is a list of the team members that you can call:\n{%- for agent in managed_agents.values() %}\n- {{ agent.name }}: {{ agent.description }}\n{%- endfor %}\n{%- else %}\n{%- endif %}\n\nHere is the up to date list of facts that you know:\n```\n{{facts_update}}\n```\n\nNow for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.\nThis plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.\nBeware that you have {remaining_steps} steps remaining.\nDo not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.\nAfter writing the final step of the plan, write the '\\n<end_plan>' tag and stop there.\n\nNow write your new plan below."
+            "initial_plan": "You are a world expert at analyzing a situation to derive facts, and plan accordingly towards solving a task.\nBelow I will present you a task. You will need to 1. build a survey of facts known or needed to solve the task, then 2. make a plan of action to solve the task.\n\n## 1. Facts survey\nYou will build a comprehensive preparatory survey of which facts we have at our disposal and which ones we still need.\nThese \"facts\" will typically be specific names, dates, values, etc. Your answer should use the below headings:\n### 1.1. Facts given in the task\nList here the specific facts given in the task that could help you (there might be nothing here).\n\n### 1.2. Facts to look up\nList here any facts that we may need to look up.\nAlso list where to find each of these, for instance a website, a file... - maybe the task contains some sources that you should re-use here.\n\n### 1.3. Facts to derive\nList here anything that we want to derive from the above by logical reasoning, for instance computation or simulation.\n\nDon't make any assumptions. For each item, provide a thorough reasoning. Do not add anything else on top of three headings above.\n\n## 2. Plan\nThen for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.\nThis plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.\nDo not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.\nAfter writing the final step of the plan, write the '\\n<end_plan>' tag and stop there.\n\nYou can leverage these tools, behaving like regular python functions:\n```python\n{%- for tool in tools.values() %}\ndef {{ tool.name }}({% for arg_name, arg_info in tool.inputs.items() %}{{ arg_name }}: {{ arg_info.type }}{% if not loop.last %}, {% endif %}{% endfor %}) -> {{tool.output_type}}:\n    \"\"\"{{ tool.description }}\n\n    Args:\n    {%- for arg_name, arg_info in tool.inputs.items() %}\n        {{ arg_name }}: {{ arg_info.description }}\n    {%- endfor %}\n    \"\"\"\n{% endfor %}\n```\n\n{%- if managed_agents and managed_agents.values() | list %}\nYou can also give tasks to team members.\nCalling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.\nGiven that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.\nHere is a list of the team members that you can call:\n```python\n{%- for agent in managed_agents.values() %}\ndef {{ agent.name }}(\"Your query goes here.\") -> str:\n    \"\"\"{{ agent.description }}\"\"\"\n{% endfor %}\n```\n{%- endif %}\n\n---\nNow begin! Here is your task:\n```\n{{task}}\n```\nFirst in part 1, write the facts survey, then in part 2, write your plan.",
+            "update_plan_pre_messages": "You are a world expert at analyzing a situation, and plan accordingly towards solving a task.\nYou have been given the following task:\n```\n{{task}}\n```\n\nBelow you will find a history of attempts made to solve this task.\nYou will first have to produce a survey of known and unknown facts, then propose a step-by-step high-level plan to solve the task.\nIf the previous tries so far have met some success, your updated plan can build on these results.\nIf you are stalled, you can make a completely new plan starting from scratch.\n\nFind the task and history below:",
+            "update_plan_post_messages": "Now write your updated facts below, taking into account the above history:\n## 1. Updated facts survey\n### 1.1. Facts given in the task\n### 1.2. Facts that we have learned\n### 1.3. Facts still to look up\n### 1.4. Facts still to derive\n\nThen write a step-by-step high-level plan to solve the task above.\n## 2. Plan\n### 2. 1. ...\nEtc.\nThis plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.\nBeware that you have {remaining_steps} steps remaining.\nDo not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.\nAfter writing the final step of the plan, write the '\\n<end_plan>' tag and stop there.\n\nYou can leverage these tools, behaving like regular python functions:\n```python\n{%- for tool in tools.values() %}\ndef {{ tool.name }}({% for arg_name, arg_info in tool.inputs.items() %}{{ arg_name }}: {{ arg_info.type }}{% if not loop.last %}, {% endif %}{% endfor %}) -> {{tool.output_type}}:\n    \"\"\"{{ tool.description }}\n\n    Args:\n    {%- for arg_name, arg_info in tool.inputs.items() %}\n        {{ arg_name }}: {{ arg_info.description }}\n    {%- endfor %}\"\"\"\n{% endfor %}\n```\n\n{%- if managed_agents and managed_agents.values() | list %}\nYou can also give tasks to team members.\nCalling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.\nGiven that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.\nHere is a list of the team members that you can call:\n```python\n{%- for agent in managed_agents.values() %}\ndef {{ agent.name }}(\"Your query goes here.\") -> str:\n    \"\"\"{{ agent.description }}\"\"\"\n{% endfor %}\n```\n{%- endif %}\n\nNow write your updated facts survey below, then your new plan."
         },
         "managed_agent": {
             "task": "You're a helpful agent named '{{name}}'.\nYou have been submitted this task by your manager.\n---\nTask:\n{{task}}\n---\nYou're helping your manager solve a wider task: so make sure to not provide a one-line answer, but give as much information as possible to give them a clear understanding of the answer.\n\nYour final_answer WILL HAVE to contain these parts:\n### 1. Task outcome (short version):\n### 2. Task outcome (extremely detailed version):\n### 3. Additional context (if relevant):\n\nPut all these in your final_answer tool, everything that you do not pass as an argument to final_answer will be lost.\nAnd even if your task resolution is not successful, please return as much context as possible, so that your manager can act upon this feedback.",
@@ -33,7 +30,7 @@
         },
         "final_answer": {
             "pre_messages": "An agent tried to answer a user query but it got stuck and failed to do so. You are tasked with providing an answer instead. Here is the agent's memory:",
-            "post_messages": "Based on the above, please provide an answer to the following user request:\n{{task}}"
+            "post_messages": "Based on the above, please provide an answer to the following user task:\n{{task}}"
         }
     },
     "max_steps": 10,
@@ -43,22 +40,25 @@
     "name": null,
     "description": null,
     "requirements": [
-        "requests",
         "duckduckgo_search",
-        "smolagents",
-        "markdownify"
+        "markdownify",
+        "requests",
+        "smolagents"
     ],
     "authorized_imports": [
-        "itertools",
-        "stat",
         "collections",
-        "unicodedata",
+        "datetime",
+        "itertools",
         "math",
+        "queue",
         "random",
         "re",
+        "stat",
+        "statistics",
         "time",
-        "datetime",
-        "queue",
-        "statistics"
-    ]
+        "unicodedata"
+    ],
+    "executor_type": "local",
+    "executor_kwargs": {},
+    "max_print_outputs_length": null
 }

app.py

@@ -16,7 +16,6 @@ from tools.final_answer import FinalAnswerTool as FinalAnswer
 
 model = HfApiModel(
 model_id='Qwen/Qwen2.5-Coder-32B-Instruct',
-provider=None,
 )
 
 web_search = WebSearch()
@@ -34,12 +33,16 @@ agent = CodeAgent(
     model=model,
     tools=[web_search, visit_webpage, suggest_menu, catering_service_tool, superhero_party_theme_generator],
     managed_agents=[],
+    class='CodeAgent',
     max_steps=10,
     verbosity_level=2,
     grammar=None,
     planning_interval=None,
     name=None,
     description=None,
+    executor_type='local',
+    executor_kwargs={},
+    max_print_outputs_length=None,
     prompt_templates=prompt_templates
 )
 if __name__ == "__main__":

prompts.yaml

@@ -141,22 +141,31 @@
   final_answer(pope_current_age)
   ```<end_code>
 
-  Above example were using notional tools that might not exist for you. On top of performing computations in the Python code snippets that you create, you only have access to these tools:
+  Above example were using notional tools that might not exist for you. On top of performing computations in the Python code snippets that you create, you only have access to these tools, behaving like regular python functions:
+  ```python
   {%- for tool in tools.values() %}
-  - {{ tool.name }}: {{ tool.description }}
-      Takes inputs: {{tool.inputs}}
-      Returns an output of type: {{tool.output_type}}
-  {%- endfor %}
+  def {{ tool.name }}({% for arg_name, arg_info in tool.inputs.items() %}{{ arg_name }}: {{ arg_info.type }}{% if not loop.last %}, {% endif %}{% endfor %}) -> {{tool.output_type}}:
+      """{{ tool.description }}
+
+      Args:
+      {%- for arg_name, arg_info in tool.inputs.items() %}
+          {{ arg_name }}: {{ arg_info.description }}
+      {%- endfor %}
+      """
+  {% endfor %}
+  ```
 
   {%- if managed_agents and managed_agents.values() | list %}
   You can also give tasks to team members.
-  Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task', a long string explaining your task.
-  Given that this team member is a real human, you should be very verbose in your task.
+  Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.
+  Given that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.
   Here is a list of the team members that you can call:
+  ```python
   {%- for agent in managed_agents.values() %}
-  - {{ agent.name }}: {{ agent.description }}
-  {%- endfor %}
-  {%- else %}
+  def {{ agent.name }}("Your query goes here.") -> str:
+      """{{ agent.description }}"""
+  {% endfor %}
+  ```
   {%- endif %}
 
   Here are the rules you should always follow to solve your task:
@@ -171,140 +180,123 @@
   9. The state persists between code executions: so if in one step you've created variables or imported modules, these will all persist.
   10. Don't give up! You're in charge of solving the task, not providing directions to solve it.
 
-  Now Begin! If you solve the task correctly, you will receive a reward of $1,000,000.
+  Now Begin!
 "planning":
-  "initial_facts": |-
-    Below I will present you a task.
-
-    You will now build a comprehensive preparatory survey of which facts we have at our disposal and which ones we still need.
-    To do so, you will have to read the task and identify things that must be discovered in order to successfully complete it.
-    Don't make any assumptions. For each item, provide a thorough reasoning. Here is how you will structure this survey:
+  "initial_plan": |-
+    You are a world expert at analyzing a situation to derive facts, and plan accordingly towards solving a task.
+    Below I will present you a task. You will need to 1. build a survey of facts known or needed to solve the task, then 2. make a plan of action to solve the task.
 
-    ---
-    ### 1. Facts given in the task
+    ## 1. Facts survey
+    You will build a comprehensive preparatory survey of which facts we have at our disposal and which ones we still need.
+    These "facts" will typically be specific names, dates, values, etc. Your answer should use the below headings:
+    ### 1.1. Facts given in the task
     List here the specific facts given in the task that could help you (there might be nothing here).
 
-    ### 2. Facts to look up
+    ### 1.2. Facts to look up
     List here any facts that we may need to look up.
     Also list where to find each of these, for instance a website, a file... - maybe the task contains some sources that you should re-use here.
 
-    ### 3. Facts to derive
+    ### 1.3. Facts to derive
     List here anything that we want to derive from the above by logical reasoning, for instance computation or simulation.
 
-    Keep in mind that "facts" will typically be specific names, dates, values, etc. Your answer should use the below headings:
-    ### 1. Facts given in the task
-    ### 2. Facts to look up
-    ### 3. Facts to derive
-    Do not add anything else.
+    Don't make any assumptions. For each item, provide a thorough reasoning. Do not add anything else on top of three headings above.
 
-    Here is the task:
-    ```
-    {{task}}
-    ```
-    Now begin!
-  "initial_plan": |-
-    You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.
-
-    Now for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.
+    ## 2. Plan
+    Then for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.
     This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.
     Do not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.
     After writing the final step of the plan, write the '\n<end_plan>' tag and stop there.
 
-    Here is your task:
-
-    Task:
-    ```
-    {{task}}
-    ```
-    You can leverage these tools:
+    You can leverage these tools, behaving like regular python functions:
+    ```python
     {%- for tool in tools.values() %}
-    - {{ tool.name }}: {{ tool.description }}
-        Takes inputs: {{tool.inputs}}
-        Returns an output of type: {{tool.output_type}}
-    {%- endfor %}
+    def {{ tool.name }}({% for arg_name, arg_info in tool.inputs.items() %}{{ arg_name }}: {{ arg_info.type }}{% if not loop.last %}, {% endif %}{% endfor %}) -> {{tool.output_type}}:
+        """{{ tool.description }}
+
+        Args:
+        {%- for arg_name, arg_info in tool.inputs.items() %}
+            {{ arg_name }}: {{ arg_info.description }}
+        {%- endfor %}
+        """
+    {% endfor %}
+    ```
 
     {%- if managed_agents and managed_agents.values() | list %}
     You can also give tasks to team members.
-    Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'request', a long string explaining your request.
-    Given that this team member is a real human, you should be very verbose in your request.
+    Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.
+    Given that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.
     Here is a list of the team members that you can call:
+    ```python
     {%- for agent in managed_agents.values() %}
-    - {{ agent.name }}: {{ agent.description }}
-    {%- endfor %}
-    {%- else %}
+    def {{ agent.name }}("Your query goes here.") -> str:
+        """{{ agent.description }}"""
+    {% endfor %}
+    ```
     {%- endif %}
 
-    List of facts that you know:
+    ---
+    Now begin! Here is your task:
     ```
-    {{answer_facts}}
+    {{task}}
     ```
-
-    Now begin! Write your plan below.
-  "update_facts_pre_messages": |-
-    You are a world expert at gathering known and unknown facts based on a conversation.
-    Below you will find a task, and a history of attempts made to solve the task. You will have to produce a list of these:
-    ### 1. Facts given in the task
-    ### 2. Facts that we have learned
-    ### 3. Facts still to look up
-    ### 4. Facts still to derive
-    Find the task and history below:
-  "update_facts_post_messages": |-
-    Earlier we've built a list of facts.
-    But since in your previous steps you may have learned useful new facts or invalidated some false ones.
-    Please update your list of facts based on the previous history, and provide these headings:
-    ### 1. Facts given in the task
-    ### 2. Facts that we have learned
-    ### 3. Facts still to look up
-    ### 4. Facts still to derive
-
-    Now write your new list of facts below.
+    First in part 1, write the facts survey, then in part 2, write your plan.
   "update_plan_pre_messages": |-
-    You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.
-
-    You have been given a task:
+    You are a world expert at analyzing a situation, and plan accordingly towards solving a task.
+    You have been given the following task:
     ```
     {{task}}
     ```
 
-    Find below the record of what has been tried so far to solve it. Then you will be asked to make an updated plan to solve the task.
-    If the previous tries so far have met some success, you can make an updated plan based on these actions.
+    Below you will find a history of attempts made to solve this task.
+    You will first have to produce a survey of known and unknown facts, then propose a step-by-step high-level plan to solve the task.
+    If the previous tries so far have met some success, your updated plan can build on these results.
     If you are stalled, you can make a completely new plan starting from scratch.
+
+    Find the task and history below:
   "update_plan_post_messages": |-
-    You're still working towards solving this task:
-    ```
-    {{task}}
-    ```
+    Now write your updated facts below, taking into account the above history:
+    ## 1. Updated facts survey
+    ### 1.1. Facts given in the task
+    ### 1.2. Facts that we have learned
+    ### 1.3. Facts still to look up
+    ### 1.4. Facts still to derive
+
+    Then write a step-by-step high-level plan to solve the task above.
+    ## 2. Plan
+    ### 2. 1. ...
+    Etc.
+    This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.
+    Beware that you have {remaining_steps} steps remaining.
+    Do not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.
+    After writing the final step of the plan, write the '\n<end_plan>' tag and stop there.
 
-    You can leverage these tools:
+    You can leverage these tools, behaving like regular python functions:
+    ```python
     {%- for tool in tools.values() %}
-    - {{ tool.name }}: {{ tool.description }}
-        Takes inputs: {{tool.inputs}}
-        Returns an output of type: {{tool.output_type}}
-    {%- endfor %}
+    def {{ tool.name }}({% for arg_name, arg_info in tool.inputs.items() %}{{ arg_name }}: {{ arg_info.type }}{% if not loop.last %}, {% endif %}{% endfor %}) -> {{tool.output_type}}:
+        """{{ tool.description }}
+
+        Args:
+        {%- for arg_name, arg_info in tool.inputs.items() %}
+            {{ arg_name }}: {{ arg_info.description }}
+        {%- endfor %}"""
+    {% endfor %}
+    ```
 
     {%- if managed_agents and managed_agents.values() | list %}
     You can also give tasks to team members.
     Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.
     Given that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.
     Here is a list of the team members that you can call:
+    ```python
     {%- for agent in managed_agents.values() %}
-    - {{ agent.name }}: {{ agent.description }}
-    {%- endfor %}
-    {%- else %}
-    {%- endif %}
-
-    Here is the up to date list of facts that you know:
+    def {{ agent.name }}("Your query goes here.") -> str:
+        """{{ agent.description }}"""
+    {% endfor %}
     ```
-    {{facts_update}}
-    ```
-
-    Now for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.
-    This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.
-    Beware that you have {remaining_steps} steps remaining.
-    Do not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.
-    After writing the final step of the plan, write the '\n<end_plan>' tag and stop there.
+    {%- endif %}
 
-    Now write your new plan below.
+    Now write your updated facts survey below, then your new plan.
 "managed_agent":
   "task": |-
     You're a helpful agent named '{{name}}'.
@@ -329,5 +321,5 @@
   "pre_messages": |-
     An agent tried to answer a user query but it got stuck and failed to do so. You are tasked with providing an answer instead. Here is the agent's memory:
   "post_messages": |-
-    Based on the above, please provide an answer to the following user request:
+    Based on the above, please provide an answer to the following user task:
     {{task}}

requirements.txt

@@ -1,4 +1,4 @@
-requests
 duckduckgo_search
-smolagents
 markdownify
+requests
+smolagents

tools/catering_service_tool.py

@@ -4,7 +4,7 @@ from typing import Any, Optional
 class SimpleTool(Tool):
     name = "catering_service_tool"
     description = "This tool returns the highest-rated catering service in Gotham City."
-    inputs = {"query":{"type":"string","description":"A search term for finding catering services."}}
+    inputs = {'query': {'type': 'string', 'description': 'A search term for finding catering services.'}}
     output_type = "string"
 
     def forward(self, query: str) -> str:

tools/suggest_menu.py

@@ -4,7 +4,7 @@ from typing import Any, Optional
 class SimpleTool(Tool):
     name = "suggest_menu"
     description = "Suggests a menu based on the occasion."
-    inputs = {"occasion":{"type":"string","description":"The type of occasion for the party."}}
+    inputs = {'occasion': {'type': 'string', 'description': 'The type of occasion for the party.'}}
     output_type = "string"
 
     def forward(self, occasion: str) -> str:

tools/superhero_party_theme_generator.py

@@ -6,17 +6,17 @@ class SuperheroPartyThemeTool(Tool):
     description = """
     This tool suggests creative superhero-themed party ideas based on a category.
     It returns a unique party theme idea."""
-    inputs = {'category': {'type': 'string', 'description': "The type of superhero party (e.g., 'classic heroes', 'villain masquerade', 'futuristic Gotham')."}}
+    inputs = {'category': {'type': 'string', 'description': "The type of superhero party (e.g., 'classic heroes', 'villain masquerade', 'futuristic gotham')."}}
     output_type = "string"
 
     def forward(self, category: str):
         themes = {
             "classic heroes": "Justice League Gala: Guests come dressed as their favorite DC heroes with themed cocktails like 'The Kryptonite Punch'.",
             "villain masquerade": "Gotham Rogues' Ball: A mysterious masquerade where guests dress as classic Batman villains.",
-            "futuristic Gotham": "Neo-Gotham Night: A cyberpunk-style party inspired by Batman Beyond, with neon decorations and futuristic gadgets."
+            "futuristic gotham": "Neo-Gotham Night: A cyberpunk-style party inspired by Batman Beyond, with neon decorations and futuristic gadgets."
         }
 
-        return themes.get(category.lower(), "Themed party idea not found. Try 'classic heroes', 'villain masquerade', or 'futuristic Gotham'.")
+        return themes.get(category.lower(), "Themed party idea not found. Try 'classic heroes', 'villain masquerade', or 'futuristic gotham'.")
 
     def __init__(self, *args, **kwargs):
         self.is_initialized = False

tools/visit_webpage.py

@@ -1,8 +1,9 @@
 from typing import Any, Optional
 from smolagents.tools import Tool
-import requests
-import smolagents
 import markdownify
+import smolagents
+import requests
+import re
 
 class VisitWebpageTool(Tool):
     name = "visit_webpage"
@@ -10,8 +11,14 @@ class VisitWebpageTool(Tool):
     inputs = {'url': {'type': 'string', 'description': 'The url of the webpage to visit.'}}
     output_type = "string"
 
+    def __init__(self, max_output_length: int = 40000):
+        super().__init__()
+        self.max_output_length = max_output_length
+
     def forward(self, url: str) -> str:
         try:
+            import re
+
             import requests
             from markdownify import markdownify
             from requests.exceptions import RequestException
@@ -32,7 +39,7 @@ class VisitWebpageTool(Tool):
             # Remove multiple line breaks
             markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)
 
-            return truncate_content(markdown_content, 10000)
+            return truncate_content(markdown_content, self.max_output_length)
 
         except requests.exceptions.Timeout:
             return "The request timed out. Please try again later or check the URL."
@@ -40,6 +47,3 @@ class VisitWebpageTool(Tool):
             return f"Error fetching the webpage: {str(e)}"
         except Exception as e:
             return f"An unexpected error occurred: {str(e)}"
-
-    def __init__(self, *args, **kwargs):
-        self.is_initialized = False