From a394e0e0267984c31bd74479dec5c2214fbdb86a Mon Sep 17 00:00:00 2001 From: Merwane Hamadi Date: Mon, 22 May 2023 12:31:57 -0700 Subject: [PATCH 1/2] fix ci --- tests/integration/agent_factory.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py index b96953feb73f..e91f04e20a0e 100644 --- a/tests/integration/agent_factory.py +++ b/tests/integration/agent_factory.py @@ -88,7 +88,7 @@ def writer_agent(agent_test_config, memory_none: NoMemory, workspace: Workspace) ai_role="an AI designed to use the write_to_file command to write 'Hello World' into a file named \"hello_world.txt\" and then use the task_complete command to complete the task.", ai_goals=[ "Use the write_to_file command to write 'Hello World' into a file named \"hello_world.txt\".", - "Use the task_complete command to complete the task.", + "Uses the task_complete command to complete the task.", "Do not use any other commands.", ], ) From 86dd3c8661d0bd0b58f0d956b8dff1b9a58cf170 Mon Sep 17 00:00:00 2001 From: GitHub Actions Date: Mon, 22 May 2023 19:35:07 +0000 Subject: [PATCH 2/2] Add new cassettes --- .../test_write_file/test_write_file.yaml | 271 ++++++++++++++++++ 1 file changed, 271 insertions(+) diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml index d744b2efb045..6d1cee5b4f1b 100644 --- a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml +++ b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml @@ -943,4 +943,275 @@ interactions: status: code: 200 message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You + are write_to_file-GPT, an AI designed to use the write_to_file command to write + ''Hello World'' into a file named \"hello_world.txt\" and then 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 write_to_file + command to write ''Hello World'' into a file named \"hello_world.txt\".\n2. + Uses the task_complete command to complete the task.\n3. 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. + delete_agent: Delete GPT Agent, args: \"key\": \"\"\n7. get_hyperlinks: + Get text summary, args: \"url\": \"\"\n8. get_text_summary: Get text summary, + args: \"url\": \"\", \"question\": \"\"\n9. list_agents: List + GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\": + \"\", \"message\": \"\"\n11. start_agent: Start GPT Agent, args: + \"name\": \"\", \"task\": \"\", \"prompt\": \"\"\n12. + 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": + "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: + - '3394' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA7yTQY/TQAyF7/wKy5deplVKW1py47ZFHFlWgqJqOnGboTPjMOOwRVX+O0rSdneD + OCG4+jnvffY4Z7QF5mhKLcZXbrx8v/j8w6+m8m6++/ThLvxcFut4Xz/QkhczVMi7b2Tk8sXEsK8c + ieWACk0kLVRgPn2zmi9X82w2Vei5IIc5HioZzyaLsdRxx+Nslk1RYZ30gTA/YxXZV7IVPlJImC8X + K4VP3rf66yxTKCza3UpvF6tGoSnZGkqYfzmjp3S1jewIc9Qp2SQ6SAvJQSi0A5w3AQBgg1JyfSgl + bTCHS/Ei0Ena4gbXEIgKEIY6EUhJ8Bit0FZ4u7eOwLD3OnQNnQCjO3KO4YGjK0ZggzBo6FqD9lTA + qGz17WOrT+Qko8kG1fPsSDpxsOHQA3wsCUSnI0T6XttICTz9RZqCjvaPc9jUiZ6TgK6qyFW0Wgj2 + HEHKVtXpOESunA497Rju/9OaTLRijU1++E4UUh1bBi2wvr2a4RjJSBfRJvRroJM8IQl3nW3HMCxV + pI/XoEfr3L+8hj64UdcrvZj+dqStQ8/0AmKAruNheN+9cN1EbzHgeGEy/CeezXSl7Ygv4JvQYKNw + b4NN5bY/Z8wxCVeo0IaCTphnzdfm1S8AAAD//wMAVDw3P4MEAAA= + 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: + - 7cb77e45ed8f86a4-ORD + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Mon, 22 May 2023 19:34:10 GMT + Function-Execution-Id: + - nvj7l5p0k8fw + Openai-Model: + - gpt-3.5-turbo-0301 + Openai-Organization: + - significant-gravitas + Openai-Processing-Ms: + - '18808' + Openai-Version: + - '2020-10-01' + Server: + - Google Frontend + Strict-Transport-Security: + - max-age=15724800; includeSubDomains + Vary: + - Accept-Encoding + X-Cloud-Trace-Context: + - ae4f222d9ff0f503bb6853f647d7e09a;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: + - '86496' + X-Ratelimit-Reset-Requests: + - 17ms + X-Ratelimit-Reset-Tokens: + - 2.336s + X-Request-Id: + - 09be305e70886bf68f4d59bb71dfa8f1 + status: + code: 200 + message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You + are write_to_file-GPT, an AI designed to use the write_to_file command to write + ''Hello World'' into a file named \"hello_world.txt\" and then 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 write_to_file + command to write ''Hello World'' into a file named \"hello_world.txt\".\n2. + Uses the task_complete command to complete the task.\n3. 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. + delete_agent: Delete GPT Agent, args: \"key\": \"\"\n7. get_hyperlinks: + Get text summary, args: \"url\": \"\"\n8. get_text_summary: Get text summary, + args: \"url\": \"\", \"question\": \"\"\n9. list_agents: List + GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\": + \"\", \"message\": \"\"\n11. start_agent: Start GPT Agent, args: + \"name\": \"\", \"task\": \"\", \"prompt\": \"\"\n12. + 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 write_to_file command to write ''Hello World'' into a file + named ''hello_world.txt''.\",\n \"reasoning\": \"The task requires me + to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file + command is the most appropriate for this task.\",\n \"plan\": \"- Use + the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n \"criticism\": + \"I need to ensure that I use the correct filename and text to write to the + file.\",\n \"speak\": \"I will use the write_to_file command to write + ''Hello World'' into a file named ''hello_world.txt''.\"\n },\n \"command\": + {\n \"name\": \"write_to_file\",\n \"args\": {\n \"filename\": + \"hello_world.txt\",\n \"text\": \"Hello World\"\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: + - '4638' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA7RTS2/bMAy+71cQvOSiBE6atJ1vPQxotuMybMBcBIrM2FpkyZPoJGvg/z4ottuu + ewB73QTy4/eQqBPqHFNUpWRV1WZ89Xohlx/29qZ5s795eV++klxt7gtSt7vpCgW6zSdS3E9MlKtq + Q6ydRYHKk2TKMZ1eXs+vrufJYi6wcjkZTLGoeXwxWYy58Rs3Ti6SKQpsgiwI0xPW3lU1r9ntyAZM + p8lsIfCR/KExS6YC2bE0j9jZ7LIVqEqnFQVMP56wojAQe2cIU5Qh6MDScrTpLJONEU6ZBQDIkEvX + FCWHDFPoi32DjhyLGS6hlHuC0ChFIWwbY77AwWtmsjC6JWMcvHfe5CPQlh1I2GpDYGVFOYzK2F8f + Yn/CRx5NYFUSWDoyBKYadAB20AQCLglYht26D0+gXFVJm0fAQ21ATTIUT+16ksFZbYvO86qHgafP + jfYUoKLIE33T77uGs42S7A+MwFttFcGvbondGR4VxPn07/PXRtou+hje/TWb8pq10qEaNsASnSfJ + hsbHOcmwhNq7vc4JJOyl0Tl0jwBb5wcJbYufioSa5G4QOGhj/uwaOspWDBvdw79b6Pi0ndo39M9M + SV88/wtPF+x//IghwjlGnyazLbYCt9rqUK47bUwxsKtRoLY5HTFN2rv2xVcAAAD//wMAg1+hkcYE + AAA= + 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: + - 7cb77ed14d2c2334-ORD + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Mon, 22 May 2023 19:34:40 GMT + Function-Execution-Id: + - nvj7ms2odipo + Openai-Model: + - gpt-3.5-turbo-0301 + Openai-Organization: + - significant-gravitas + Openai-Processing-Ms: + - '26611' + Openai-Version: + - '2020-10-01' + Server: + - Google Frontend + Strict-Transport-Security: + - max-age=15724800; includeSubDomains + Vary: + - Accept-Encoding + X-Cloud-Trace-Context: + - 14ea58a412f3f54b69e23bbb65cbaa58;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: + - '86481' + X-Ratelimit-Reset-Requests: + - 17ms + X-Ratelimit-Reset-Tokens: + - 2.346s + X-Request-Id: + - 9d119e718856a7f227f26591176d1b7e + status: + code: 200 + message: OK version: 1