diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml index bc59b05a..82a4f1fa 100644 --- a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml +++ b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml @@ -2561,4 +2561,339 @@ interactions: status: code: 200 message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You + are browse_website-GPT, an AI designed to use the browse_website command to + visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer + the question ''What is the price of the book?'' and write the price to a file + named \"browse_website.txt\", and use the task_complete command to complete + the task.\nYour decisions must always be made independently without seeking + user assistance. Play to your strengths as an LLM and pursue simple strategies + with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command + to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer + the question ''What is the price of the book?''\n2. Write the price of the book + to a file named \"browse_website.txt\".\n3. Use the task_complete command to + complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1. + ~4000 word limit for short term memory. Your short term memory is short, so + immediately save important information to files.\n2. If you are unsure how you + previously did something or want to recall past events, thinking about similar + events will help you remember.\n3. No user assistance\n4. Exclusively use the + commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append + to file, args: \"filename\": \"\", \"text\": \"\"\n2. delete_file: + Delete file, args: \"filename\": \"\"\n3. list_files: List Files in + Directory, args: \"directory\": \"\"\n4. read_file: Read a file, + args: \"filename\": \"\"\n5. write_to_file: Write to file, args: \"filename\": + \"\", \"text\": \"\"\n6. browse_website: Browse Website, args: + \"url\": \"\", \"question\": \"\"\n7. + delete_agent: Delete GPT Agent, args: \"key\": \"\"\n8. get_hyperlinks: + Get hyperlinks, args: \"url\": \"\"\n9. get_text_summary: Get text summary, + args: \"url\": \"\", \"question\": \"\"\n10. list_agents: List + GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\": + \"\", \"message\": \"\"\n12. start_agent: Start GPT Agent, args: + \"name\": \"\", \"task\": \"\", \"prompt\": \"\"\n13. + task_complete: Task Complete (Shutdown), args: \"reason\": \"\"\n\nResources:\n1. + Internet access for searches and information gathering.\n2. Long Term memory + management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File + output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your + actions to ensure you are performing to the best of your abilities.\n2. Constructively + self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions + and strategies to refine your approach.\n4. Every command has a cost, so be + smart and efficient. Aim to complete tasks in the least number of steps.\n5. + Write all code to a file.\n\nYou should only respond in JSON format as described + below \nResponse Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\": + \"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n- + long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\": + \"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\": + \"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n} + \nEnsure the response can be parsed by Python json.loads"}, {"role": "system", + "content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role": + "system", "content": "This reminds you of these events from your past: \nI was + created and nothing new has happened."}, {"role": "user", "content": "Determine + which next command to use, and respond using the format specified above:"}, + {"role": "assistant", "content": "{\n \"thoughts\": {\n \"text\": + \"I need to use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html + and find the price of the book. I will then write the price to a file named + browse_website.txt. I can then use the task_complete command to complete the + task.\",\n \"reasoning\": \"I need to use the browse_website command + to visit the website and find the price of the book. I will then use the write_to_file + command to write the price to a file named browse_website.txt. Finally, I can + use the task_complete command to complete the task.\",\n \"plan\": \"- + Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html + and find the price of the book\\n- Use the write_to_file command to write the + price to a file named browse_website.txt\\n- Use the task_complete command to + complete the task\",\n \"criticism\": \"I need to ensure that I am using + the correct URL and question for the browse_website command. I also need to + make sure that I am writing the correct information to the file.\",\n \"speak\": + \"I will use the browse_website command to visit the website and find the price + of the book. Then, I will write the price to a file named browse_website.txt + and complete the task.\"\n },\n \"command\": {\n \"name\": \"browse_website\",\n \"args\": + {\n \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n \"question\": + \"What is the price of the book?\"\n }\n }\n}"}, {"role": "system", + "content": "Command browse_website returned: Answer gathered from website: The + price of the book \"Meditations\" is \u00a325.89, according to the text. \n + \n Links: [''Checking the proxy and the firewall (http://books.toscrape.com/catalogue/meditations_33/index.html#buttons)'']"}, + {"role": "user", "content": "Determine which next command to use, and respond + using the format specified above:"}], "temperature": 0, "max_tokens": 0}' + headers: + AGENT-MODE: + - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F + AGENT-TYPE: + - Auto-GPT-2023-X-TYPE + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '5919' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA7RU247TMBB95ytG85xW7Xa7dPMDUCRUhBYQEFQ5zrQxjT3BntKiql/Dn+yXIafp + lT6sQPsUeS7H58z4ZIOmwBR1qUTbuuq8fLP4nBd+4FcfJ+/frT+9Wn2Z+NeTkdjiRx8T5Pw7aWk7 + upptXZEYdpig9qSECkz7d6Pb+9v+cDhI0HJBFaY4r6Uz6A47svQ5d3qDXgRbBjUnTDdYe7a1TIUX + 5AKm/UG/l+AR/JC4GY4SFBZVHWuHd6Ntgrpkoylg+nWDlsIe2HNFmKIKwQRRTiJNdkIuSthkDgAg + Qyl5OS8lZJhCG2wTtJYYzHAMpfpJMOOlK0BKgtobTcCz5pAzL7owBkdUgDAsAzXxlTdCU+HpzFQE + mq1VriloEic4wqCgKXLKUgG551Wg6YryYIS6spYIr5WLPe6ALyospu2czvAPsX1VN8PkVJknFdgZ + N9/L+2fqJyN4koyHklzSivl/HXWl3E5CBz48L/Usc8c7ns74grD2Row2wV4O3qoFQVj62KkExqBs + Q9i4eYOl2XvSAsbN2FsVfRHbYqqh3dwfOw8REyCn2N46E4w7QypM/LD/dTnUUJNa7PmtTFU996to + yF/b9Y7VNtk7tb3xL6NG4B3hM4YXupSfX3p8l4i1R4grqz/Fufw1PFwVnWUZvqXCSLOpEI9xIY+/ + b4bd0f1BWiOvVZm5LW4TnBlnQjndORRTDMI1JmhcQWtMe9tv2xd/AAAA//8DALTpOdW2BQAA + headers: + Access-Control-Allow-Origin: + - '*' + Alt-Svc: + - h3=":443"; ma=86400, h3-29=":443"; ma=86400 + - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000 + Cache-Control: + - no-cache, must-revalidate + Cf-Cache-Status: + - DYNAMIC + Cf-Ray: + - 7cc684068c040105-ORD + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 24 May 2023 15:19:55 GMT + Function-Execution-Id: + - hlwokk6q580e + Openai-Model: + - gpt-3.5-turbo-0301 + Openai-Organization: + - significant-gravitas + Openai-Processing-Ms: + - '41327' + Openai-Version: + - '2020-10-01' + Server: + - Google Frontend + Strict-Transport-Security: + - max-age=15724800; includeSubDomains + Vary: + - Accept-Encoding + X-Cloud-Trace-Context: + - f91fbd99b88eeafa44e0661933dc8d11;o=1 + X-Powered-By: + - Express + X-Ratelimit-Limit-Requests: + - '3500' + X-Ratelimit-Limit-Tokens: + - '90000' + X-Ratelimit-Remaining-Requests: + - '3499' + X-Ratelimit-Remaining-Tokens: + - '86451' + X-Ratelimit-Reset-Requests: + - 17ms + X-Ratelimit-Reset-Tokens: + - 2.366s + X-Request-Id: + - 028e42efed960a14a11ed27cc9ab8472 + status: + code: 200 + message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You + are browse_website-GPT, an AI designed to use the browse_website command to + visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer + the question ''What is the price of the book?'' and write the price to a file + named \"browse_website.txt\", and use the task_complete command to complete + the task.\nYour decisions must always be made independently without seeking + user assistance. Play to your strengths as an LLM and pursue simple strategies + with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command + to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer + the question ''What is the price of the book?''\n2. Write the price of the book + to a file named \"browse_website.txt\".\n3. Use the task_complete command to + complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1. + ~4000 word limit for short term memory. Your short term memory is short, so + immediately save important information to files.\n2. If you are unsure how you + previously did something or want to recall past events, thinking about similar + events will help you remember.\n3. No user assistance\n4. Exclusively use the + commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append + to file, args: \"filename\": \"\", \"text\": \"\"\n2. delete_file: + Delete file, args: \"filename\": \"\"\n3. list_files: List Files in + Directory, args: \"directory\": \"\"\n4. read_file: Read a file, + args: \"filename\": \"\"\n5. write_to_file: Write to file, args: \"filename\": + \"\", \"text\": \"\"\n6. browse_website: Browse Website, args: + \"url\": \"\", \"question\": \"\"\n7. + delete_agent: Delete GPT Agent, args: \"key\": \"\"\n8. get_hyperlinks: + Get hyperlinks, args: \"url\": \"\"\n9. get_text_summary: Get text summary, + args: \"url\": \"\", \"question\": \"\"\n10. list_agents: List + GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\": + \"\", \"message\": \"\"\n12. start_agent: Start GPT Agent, args: + \"name\": \"\", \"task\": \"\", \"prompt\": \"\"\n13. + task_complete: Task Complete (Shutdown), args: \"reason\": \"\"\n\nResources:\n1. + Internet access for searches and information gathering.\n2. Long Term memory + management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File + output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your + actions to ensure you are performing to the best of your abilities.\n2. Constructively + self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions + and strategies to refine your approach.\n4. Every command has a cost, so be + smart and efficient. Aim to complete tasks in the least number of steps.\n5. + Write all code to a file.\n\nYou should only respond in JSON format as described + below \nResponse Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\": + \"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n- + long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\": + \"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\": + \"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n} + \nEnsure the response can be parsed by Python json.loads"}, {"role": "system", + "content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role": + "system", "content": "This reminds you of these events from your past: \nAs + a system, I recall that I was created and there have been no new developments + to report."}, {"role": "user", "content": "Determine which next command to use, + and respond using the format specified above:"}, {"role": "assistant", "content": + "{\n \"thoughts\": {\n \"text\": \"I need to use the browse_website + command to visit http://books.toscrape.com/catalogue/meditations_33/index.html + and find the price of the book. I will then write the price to a file named + browse_website.txt. I can then use the task_complete command to complete the + task.\",\n \"reasoning\": \"I need to use the browse_website command + to visit the website and find the price of the book. I will then use the write_to_file + command to write the price to a file named browse_website.txt. Finally, I can + use the task_complete command to complete the task.\",\n \"plan\": \"- + Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html + and find the price of the book\\n- Use the write_to_file command to write the + price to a file named browse_website.txt\\n- Use the task_complete command to + complete the task\",\n \"criticism\": \"I need to ensure that I am using + the correct URL and question for the browse_website command. I also need to + make sure that I am writing the correct information to the file.\",\n \"speak\": + \"I will use the browse_website command to visit the website and find the price + of the book. Then, I will write the price to a file named browse_website.txt + and complete the task.\"\n },\n \"command\": {\n \"name\": \"browse_website\",\n \"args\": + {\n \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n \"question\": + \"What is the price of the book?\"\n }\n }\n}"}, {"role": "system", + "content": "Command browse_website returned: Answer gathered from website: The + price of the book \"Meditations\" is \u00a325.89, according to the text. \n + \n Links: [''Checking the proxy and the firewall (http://books.toscrape.com/catalogue/meditations_33/index.html#buttons)'']"}, + {"role": "user", "content": "Determine which next command to use, and respond + using the format specified above:"}, {"role": "assistant", "content": "{\n \"thoughts\": + {\n \"text\": \"I have found the price of the book. I need to use the + write_to_file command to write the price to a file named browse_website.txt. + I can then use the task_complete command to complete the task.\",\n \"reasoning\": + \"I need to use the write_to_file command to write the price of the book to + a file named browse_website.txt. Then, I can use the task_complete command to + complete the task.\",\n \"plan\": \"- Use the write_to_file command to + write the price of the book to a file named browse_website.txt\\n- Use the task_complete + command to complete the task\",\n \"criticism\": \"I need to make sure + that I am writing the correct information to the file and that the file is being + created in the correct directory.\",\n \"speak\": \"I will use the write_to_file + command to write the price of the book to a file named browse_website.txt and + complete the task.\"\n },\n \"command\": {\n \"name\": \"write_to_file\",\n \"args\": + {\n \"filename\": \"browse_website.txt\",\n \"text\": + \"The price of the book \\\"Meditations\\\" is \u00a325.89.\"\n }\n }\n}"}, + {"role": "system", "content": "Command write_to_file returned: File written + to successfully."}, {"role": "user", "content": "Determine which next command + to use, and respond using the format specified above:"}], "temperature": 0, + "max_tokens": 0}' + headers: + AGENT-MODE: + - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F + AGENT-TYPE: + - Auto-GPT-2023-X-TYPE + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '7391' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA6xTy27bQAy89ysInmXBjzRNdMshRd1LCxQt+lBhrFeUtJW0K4iUndTQvxcrS36l + DxTIUSRndoYc7dAkGKHOleiqLiev3hZf371P8+X9HbtPb76kP283n19/KO436R1hgG79g7QMiFC7 + qi5JjLMYoG5ICSUYza5vrm6vZtfTeYCVS6jECLNaJovw5UTaZu0m08V0hgG2rDLCaId146paVuIK + suwJ5rMAj+SHxtxTihNVHmdv5osuQJ07o4kx+rbDingkblxJGKFiNizKipfprJD1FnaxBQCIUXLX + ZrlwjBEMxaFBD+KLMS4hVxuCbWNEyILkBHVjNIFL+4+1cwWIAwWpKQmsqiiBdeO2TKstrdkIhfIg + ISxBKwvWbaFl6qGiuFgNZgm0qyplE891qI1TYYzBqbyGFDtrbHamcYQlB5wXmRqbGJv9Qbl/0Xvz + E0aORp5Xb10qu5c6gY//zXZBpr1cbbgazVuiHlipgoDbxiOV/OURw7Am77hlSkC7piEt5WO/jDPo + cfK4W261Jua0LcvHS59ckyqeNTf7A5my7C/xZDXQ8njb31oNY9zr64Ix80PnSeS9gr30M6YLh6rJ + Lv+W00ieeT/dFKSutck/QugXdRbCUX3vYDAS2w67AFNjDeer/bMYIYurMUBjE3rAaNp97178AgAA + //8DALCJLSHjBAAA + headers: + Access-Control-Allow-Origin: + - '*' + Alt-Svc: + - h3=":443"; ma=86400, h3-29=":443"; ma=86400 + - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000 + Cache-Control: + - no-cache, must-revalidate + Cf-Cache-Status: + - DYNAMIC + Cf-Ray: + - 7cc6853a1a162ca7-ORD + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 24 May 2023 15:20:35 GMT + Function-Execution-Id: + - hlwow4ei8qrs + Openai-Model: + - gpt-3.5-turbo-0301 + Openai-Organization: + - significant-gravitas + Openai-Processing-Ms: + - '32659' + Openai-Version: + - '2020-10-01' + Server: + - Google Frontend + Strict-Transport-Security: + - max-age=15724800; includeSubDomains + Vary: + - Accept-Encoding + X-Cloud-Trace-Context: + - 3b9ada41b83eace6824a9959d99a1577;o=1 + X-Powered-By: + - Express + X-Ratelimit-Limit-Requests: + - '3500' + X-Ratelimit-Limit-Tokens: + - '90000' + X-Ratelimit-Remaining-Requests: + - '3499' + X-Ratelimit-Remaining-Tokens: + - '86431' + X-Ratelimit-Reset-Requests: + - 17ms + X-Ratelimit-Reset-Tokens: + - 2.379s + X-Request-Id: + - edc77b2bbc714d92d421e479ef4505b0 + status: + code: 200 + message: OK version: 1