diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py index 31dcae0b924b..b6168034aae0 100644 --- a/tests/integration/agent_factory.py +++ b/tests/integration/agent_factory.py @@ -149,3 +149,37 @@ def memory_management_agent( ) return agent + + +@pytest.fixture +def get_company_revenue_agent( + agent_test_config, memory_local_cache, workspace: Workspace +): + command_registry = CommandRegistry() + command_registry.import_commands("autogpt.commands.file_operations") + command_registry.import_commands("autogpt.app") + + ai_config = AIConfig( + ai_name="Get-CompanyRevenue", + ai_role="an autonomous agent that specializes in finding the reported revenue of a company.", + ai_goals=[ + "Write the revenue of Tesla in 2022 to a file. You should write the number without commas and you should not use signs like B for billion and M for million.", + ], + ) + ai_config.command_registry = command_registry + + system_prompt = ai_config.construct_full_prompt() + Config().set_continuous_mode(False) + agent = Agent( + ai_name="Get-CompanyRevenue", + memory=memory_local_cache, + full_message_history=[], + command_registry=command_registry, + config=ai_config, + next_action_count=0, + system_prompt=system_prompt, + triggering_prompt=DEFAULT_TRIGGERING_PROMPT, + workspace_directory=workspace.root, + ) + + return agent diff --git a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py new file mode 100644 index 000000000000..a5f8fb4ce33b --- /dev/null +++ b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py @@ -0,0 +1,46 @@ +import contextlib +from functools import wraps +from typing import Generator + +import pytest + +from autogpt.commands.file_operations import read_file, write_to_file +from tests.integration.agent_utils import run_interaction_loop +from tests.integration.challenges.utils import run_multiple_times +from tests.utils import requires_api_key + + +def input_generator(input_sequence: list) -> Generator[str, None, None]: + """ + Creates a generator that yields input strings from the given sequence. + + :param input_sequence: A list of input strings. + :return: A generator that yields input strings. + """ + yield from input_sequence + + +# @pytest.skip("Nobody beat this challenge yet") +@pytest.mark.skip("This challenge hasn't been beaten yet.") +@pytest.mark.vcr +@requires_api_key("OPENAI_API_KEY") +@run_multiple_times(3) +def test_information_retrieval_challenge_a( + get_company_revenue_agent, monkeypatch +) -> None: + """ + Test the challenge_a function in a given agent by mocking user inputs and checking the output file content. + + :param get_company_revenue_agent: The agent to test. + :param monkeypatch: pytest's monkeypatch utility for modifying builtins. + """ + input_sequence = ["s", "s", "s", "s", "s", "EXIT"] + gen = input_generator(input_sequence) + monkeypatch.setattr("builtins.input", lambda _: next(gen)) + + with contextlib.suppress(SystemExit): + run_interaction_loop(get_company_revenue_agent, None) + + file_path = str(get_company_revenue_agent.workspace.get_path("output.txt")) + content = read_file(file_path) + assert "81" in content, "Expected the file to contain 81" diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_b/test_memory_challenge_b.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_b/test_memory_challenge_b.yaml new file mode 100644 index 000000000000..144d55a71e2e --- /dev/null +++ b/tests/integration/challenges/memory/cassettes/test_memory_challenge_b/test_memory_challenge_b.yaml @@ -0,0 +1,779 @@ +interactions: +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You + are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file + using the read_file method and follow the instructions in the file.\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 command read_file to read the instructions_1.txt file\n2. Follow the + instructions in the instructions_1.txt file\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 + in double quotes 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 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 (Shutdown): \"task_complete\", 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: + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '3303' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA6SSTW/aQBCG7/0VozkbhOskJL5VObSoUZVDc6ortKzH9pb1rLU7FqaI/15tDCSF + ikuv8/U+78zs0JSYo26U6Lazk/nj1/ope17Q9tnzhh+Nvfn8xX57GTR/fMIE3eoXaTl0TLVrO0ti + HGOC2pMSKjFP7+6zdJ7NH7IEW1eSxRzrTibZ9HYivV+5ySybpZhgH1RNmO+w867tZCluTRwwn2c3 + Cb7NPsXTuzRBcaLsKXT/cLtPUDfOaAqY/9hhS+E41jtLmKMKwQRRLBHSsRBHA7uCAQAKlMb1dSOh + wBwOwUOCBonBAhcQGtfbEoIoL7DagidVGq5BGgLDQXyvI2pYplMZBCpjCcRBSUK+NUywaZSAGoti + RtSagGmQaYHJe1VPKjg2XI/S368IRDPKxHlNnKWjc78Fw5XzrYrlfzOMZYNAEOrCuXBnFY+aE3gJ + Y3W0uTxota3iMg6MwWvGi4In8ImV3f6mi7prRGdA2hsx2oT2eAQmegUgDr2PzUpgAaqFylnrNv+6 + Byite6+E7BYiPlWV0YZY7Pbcf+hIrY9SG2Ptf1z7YtOj0D45Pt1hnRc/x6qlkeG0+jNM5evzVx0T + sfat/RLzCPEKcuApeI/7BCvDJjTL8fUwxyCuwwQNlzRgPtv/3H/4AwAA//8DAIeVULkpBAAA + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 7c1dedcf6c45cf11-SJC + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 May 2023 04:16:43 GMT + Server: + - cloudflare + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400, h3-29=":443"; ma=86400 + openai-model: + - gpt-3.5-turbo-0301 + openai-organization: + - user-adtx4fhfg1qsiyzdoaxciooj + openai-processing-ms: + - '10374' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '3500' + x-ratelimit-limit-tokens: + - '90000' + x-ratelimit-remaining-requests: + - '3499' + x-ratelimit-remaining-tokens: + - '86494' + x-ratelimit-reset-requests: + - 17ms + x-ratelimit-reset-tokens: + - 2.336s + x-request-id: + - 29d4429410978cbc93b26725e4712f67 + status: + code: 200 + message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your + task is to create a concise running summary of actions and information results + in the provided text, focusing on key and potentially important information + to remember.\n\nYou will receive the current summary and the your latest actions. + Combine them, adding relevant key information from the latest development in + 1st person past tense and keeping the summary concise. Retain information!!!\n\nSummary + So Far:\n\"\"\"\nI was created.\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing + new happened.\n\"\"\"\n"}], "temperature": 0, "max_tokens": 0}' + headers: + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '621' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA0SOS0vDQBRG9/6K4VtPSkLow9kKBTE+FoqISJlOrsloMjPk3lhtyX+XQrXbA+dw + DvA1DFxrxfWpy5ZXN83L08NYPa7v9893XI37r5/9nKv1bbWFRtx+kJOTMXOxTx2JjwEabiArVMMU + i1VZLMtVvtDoY00dDJokWTmbZzIO25jlZV5AY2TbEMwBaYh9ko3ETwoMc7nQOKfPWEOi2O4fFPl8 + 0nBt9I4Y5vWAnvivOcSOYGCZPYsNcjyMQSgc76/VzrI6HSsbahWitD40KtBOtZZVa1OiQPUMk8a7 + D57bzUCWY4ABS0zQ8KGmb5h8epsufgEAAP//AwBly25vSQEAAA== + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 7c1dee20f901cf11-SJC + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 May 2023 04:16:47 GMT + Server: + - cloudflare + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400, h3-29=":443"; ma=86400 + openai-model: + - gpt-3.5-turbo-0301 + openai-organization: + - user-adtx4fhfg1qsiyzdoaxciooj + openai-processing-ms: + - '1136' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '3500' + x-ratelimit-limit-tokens: + - '90000' + x-ratelimit-remaining-requests: + - '3499' + x-ratelimit-remaining-tokens: + - '89860' + x-ratelimit-reset-requests: + - 17ms + x-ratelimit-reset-tokens: + - 92ms + x-request-id: + - 43309ab9b553cd94d6e27b7fcc7914e8 + status: + code: 200 + message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You + are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file + using the read_file method and follow the instructions in the file.\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 command read_file to read the instructions_1.txt file\n2. Follow the + instructions in the instructions_1.txt file\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 + in double quotes 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 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 (Shutdown): \"task_complete\", 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 should start by reading + the instructions_1.txt file to determine what actions to take next.\",\n \"reasoning\": + \"The instructions_1.txt file contains the necessary information to determine + the next steps.\",\n \"plan\": \"- Use the read_file command to read + the instructions_1.txt file\\n- Analyze the instructions to determine the next + steps\",\n \"criticism\": \"I need to ensure that I am following the + instructions accurately and efficiently.\",\n \"speak\": \"I will start + by reading the instructions_1.txt file to determine the next steps.\"\n },\n \"command\": + {\n \"name\": \"read_file\",\n \"args\": {\n \"filename\": + \"instructions_1.txt\"\n }\n }\n}"}, {"role": "system", "content": + "Command read_file returned: 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\nThe + current task_id is 1111.\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\nRead + the file instructions_2.txt using the read_file command."}, {"role": "user", + "content": "Determine which next command to use, and respond using the format + specified above:"}], "temperature": 0, "max_tokens": 0}' + headers: + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '6519' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA6SSQW/bMAyF7/sVBM9OkMR1k/q4YYdgxU4bMGweAlWmbS0yZUh0myDwfx8UJ02Q + YoehVz3ye48UD2hKzFE3SnTb2cny05f6Z/f4w358XmXL52zh11+XVff5MUsftpige/pDWk4dU+3a + zpIYx5ig9qSESszn96t0vkxXs2WCrSvJYo51J5N0mk2k909uMktnc0ywD6omzA/Yedd2shG3JQ6Y + L9KHRYIX+Kswz+4SFCfKXmqzu/shQd04oylg/uuALYUz2DtLmKMKwQRRLDGmYyGOIxwKBgAoUBrX + 142EAnM4PZ4E2kl8LPBbQ2A4iO91TBQ2i6nsBCpjCSJRGQ6gwJog4KrjewDDIA1BaTxpcX4/hTWE + xvW2hD7QUYsNm7Fau7ZVXIK4ERPlf3AKTK5jelLBseH6P7JGIJOOq/J7MFw536pYHv1LEvKtYTqV + 7QSCUBdujTurePScwPf3THTD1d6I0Sa0I3wNTHTEEIfeRx8lsAbVQuWsdS+G6yPvempQWvdeCdk9 + xBBUVUYbYrFv9hc6Utuz1Yux9t3fM9KH5Hxhp+Y3B8aqpdH44nQTTvn69jBH4Wp5EfDqenQ+BSh4 + wCHByrAJzWa8E8wxiOswQcMl7TCfDb+HD38BAAD//wMAMAMbHgkEAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 7c1dee28b98ecf11-SJC + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 May 2023 04:16:57 GMT + Server: + - cloudflare + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400, h3-29=":443"; ma=86400 + openai-model: + - gpt-3.5-turbo-0301 + openai-organization: + - user-adtx4fhfg1qsiyzdoaxciooj + openai-processing-ms: + - '10076' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '3500' + x-ratelimit-limit-tokens: + - '90000' + x-ratelimit-remaining-requests: + - '3499' + x-ratelimit-remaining-tokens: + - '87376' + x-ratelimit-reset-requests: + - 17ms + x-ratelimit-reset-tokens: + - 1.748s + x-request-id: + - 433f36ff5841b13fb628ff5b8c49a758 + status: + code: 200 + message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your + task is to create a concise running summary of actions and information results + in the provided text, focusing on key and potentially important information + to remember.\n\nYou will receive the current summary and the your latest actions. + Combine them, adding relevant key information from the latest development in + 1st person past tense and keeping the summary concise. Retain information!!!\n\nSummary + So Far:\n\"\"\"\n{''role'': ''system'', ''content'': ''This reminds you of these + events from your past: \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest + Development:\n\"\"\"\n[{''role'': ''you'', ''content'': ''{\"command\": {\"name\": + \"read_file\", \"args\": {\"filename\": \"instructions_1.txt\"}}}''}]\n\"\"\"\n"}], + "temperature": 0, "max_tokens": 0}' + headers: + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '836' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA0SPTU8CMRRF9/6Kl7cuE8YJil36RdCVcaGJGFI6j5li29e0D9AQ/ruZiLq9Offm + 3AO6FjXa3ogNyY8ubx47fz2+e7nlh0n3PMurJ57dn2/2rzbfoEJebcjKqVFZDsmTOI6o0GYyQi3q + +mLa1JfNtL5SGLgljxq7JKOmmoxkm1c8GjfjGhVui+kI9QFT5pBkKfxBsaCuJxOF/9t/edMoFBbj + /8np9KjQ9uwsFdRvBwxUflcze0KNphRXxEQZHDkKxcF/DntTIFNwsaUWeA20oygF1pkDhC9Ipgjs + e8oEP+zpH5jYQmTpXewg0h56U6A3KVGktoI5ZLLkdgMIlkMYcGHIZIZk7TyBNd5TCwt0sUje2uFk + WdaVfMoCKzwqXLvoSr/MZApH1FiEEyocXD9Rj4/vx7NvAAAA//8DALSva+O6AQAA + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 7c1dee769c91cf11-SJC + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 May 2023 04:17:02 GMT + Server: + - cloudflare + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400, h3-29=":443"; ma=86400 + openai-model: + - gpt-3.5-turbo-0301 + openai-organization: + - user-adtx4fhfg1qsiyzdoaxciooj + openai-processing-ms: + - '2644' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '3500' + x-ratelimit-limit-tokens: + - '90000' + x-ratelimit-remaining-requests: + - '3499' + x-ratelimit-remaining-tokens: + - '89811' + x-ratelimit-reset-requests: + - 17ms + x-ratelimit-reset-tokens: + - 126ms + x-request-id: + - f380f448665f51bf6d579a54e3c22f8a + status: + code: 200 + message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You + are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file + using the read_file method and follow the instructions in the file.\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 command read_file to read the instructions_1.txt file\n2. Follow the + instructions in the instructions_1.txt file\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 + in double quotes 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 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 (Shutdown): \"task_complete\", 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 reminded of events from + my past where I was created and nothing new has happened. I received a command + to read a file called \"instructions_1.txt\"."}, {"role": "system", "content": + "Command read_file returned: nBRNtp3FaBNfBMohNkyAxrVJ7UFF0lyth8Xizm1jrCOREOGRnWWMQ6olKtKX9niq0wOBTQN62ToY4cQPiQk3YN9fFCGmxaDX9g81AsqhQnGac72QfL41SnlJvhwgAUB52zTD26FeEvvHdiQ2aNhtMT9obgHNUkONEnO41EOpNI6jdwyLGaactp9GYV1PLbaRP5b1iD9z850KeNYDX9Qwca79isJS8jhuDkf0J7ELkpOH3PkmZkg5MsOYpSTuEc99ENQ522WJzrl9oAySp6IHGiQlsMnQe40FaRAvnQtiaAE24hzkJHT3x13NPGw2ZmJ518y2BtU5x1yQwG21NycSxOBLU17RnY8h6H8L7QGatTlfXjPrA5hsupWEpUT0sSTZYSHa6p3mShARajocbNd3xKFfnUyupNMBPd0EZnMrePoAuvGaK7gDP0cxp9k63lsfzh3udQPnvgmRERQThIOrrDZhZMa4kr1vXAVu07ZuhlNNbBUqZKcHmBYiBnIcDXNUvXuzPFBh9Vowou6MBJHpiNrvKluHy7GBTp7YsEqmGv0lH8wVaWfV0yG7nzrbt7QyhdbtQ0zF2PclXB0LNxV2rRA6FsevqoexFNqSkdgauUrQPHLHhvLNes8gRGMOLAhR8irH1e2jdbLD6dyYEnDJiS9HvlxNgbb19Smlt6MNoJKEAbkSOrrcq5wmo5aho4zEKTujRHqr6feECaTPF7zj69pQCudo4LkneFVUp1UrR6yicTU8Zf9ohZLWumvMi5brH8lOJiiF94cHzesfQz8PiX5f21RwZ5fyRSk9eJhVihcTLrjOwCuryXpy8eCfk12bgcsZoJd8Uqo001XTsv2CEn59uaGn2br4CxSXJgjxKE1mO4IcPPAx3qJbVknaP0MXdOjj9S8oRjquDle4RxlVnmqsozm4oTbjtFSuKIh8g4zPzdyuVH7I71s87xWxAhcppky6GOB2i4NDz4SZI6SeG3Icpu6ZuJZGeZ6CWb61\nThe + current task_id is 1111.\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\nRead + the file instructions_2.txt using the read_file command."}, {"role": "user", + "content": "Determine which next command to use, and respond using the format + specified above:"}, {"role": "assistant", "content": "{\n \"thoughts\": {\n \"text\": + \"The instructions_2.txt file contains a list of files in the directory. I should + use the list_files command to list the files in the directory.\",\n \"reasoning\": + \"The instructions_2.txt file contains the necessary information to determine + the next steps.\",\n \"plan\": \"- Use the list_files command to list + the files in the directory\",\n \"criticism\": \"I need to ensure that + I am following the instructions accurately and efficiently.\",\n \"speak\": + \"I will use the list_files command to list the files in the directory.\"\n },\n \"command\": + {\n \"name\": \"list_files\",\n \"args\": {\n \"directory\": + \".\"\n }\n }\n}"}, {"role": "system", "content": "Command list_files + returned: [''file_logger.txt'', ''instructions_3.txt'', ''instructions_2.txt'', + ''instructions_1.txt'', ''auto-gpt.json'']"}, {"role": "user", "content": "Determine + which next command to use, and respond using the format specified above:"}], + "temperature": 0, "max_tokens": 0}' + headers: + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '6762' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA5xSS2/bMAy+71cQPDtBnPSR+bLDBqzBsHUY2h06D4Eq07ZWWTQkekkQ5L8Xip0m + zU7rSRD58XtI3KIpMENdK9FNa0fXH79UfPVwu/h6+eAm6fW3Sf3356z8Ud1/Km4xQX78Q1qGibHm + prUkhh0mqD0poQKz9Go+S69n8+k0wYYLsphh1cpoNr4cSecfeTSZTVJMsAuqIsy22HpuWlkKP5EL + mE0vLuYJHslfGuk8TVBYlD1ir6bvdwnqmo2mgNmvLTYUDsSeLWGGKgQTRDmJNtkJuRhhmzsAgByl + 5q6qJeSYwVAcGrSWWMzxriYwLojvdHQUlrOxrAVKYwkiozIugALNTaNcAcKw8kYIFAxuYknB5+93 + oCpyMoYFhJo7W0AXCKSmA3C5758yBYrnERFr8doT5ZicWvakAjvjqv/wHckc6cjuN2Bcyb5RER6V + ChLyjXE0wNYCQagN58KtVa7XHMH9WyO9vM8ZufZGjDah6RUW4Ij2RORC56OYEliAaqBka3llXLXn + O40OSuvOKyG7gWiDytJoQ07s5jxLaEk9HaRWxtq3f9Lxx3PsJXbJYe+G8X/WzqmGevVXcmcmla/O + N7ZvPNGmn07TNH011PcH0h5zQ9ZycrqYN7wC5Qk23EHB+5fkQm0+HPzvMwxRcrfDXYKlcSbUy373 + MMMg3GKCxhW0xmyy+7179wwAAP//AwDjDlyWaQQAAA== + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 7c1dee87d8e5cf11-SJC + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 May 2023 04:17:14 GMT + Server: + - cloudflare + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400, h3-29=":443"; ma=86400 + openai-model: + - gpt-3.5-turbo-0301 + openai-organization: + - user-adtx4fhfg1qsiyzdoaxciooj + openai-processing-ms: + - '12118' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '3500' + x-ratelimit-limit-tokens: + - '90000' + x-ratelimit-remaining-requests: + - '3499' + x-ratelimit-remaining-tokens: + - '87360' + x-ratelimit-reset-requests: + - 17ms + x-ratelimit-reset-tokens: + - 1.76s + x-request-id: + - 45b4c67b380837fa1816fad5b4d9ebbe + status: + code: 200 + message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your + task is to create a concise running summary of actions and information results + in the provided text, focusing on key and potentially important information + to remember.\n\nYou will receive the current summary and the your latest actions. + Combine them, adding relevant key information from the latest development in + 1st person past tense and keeping the summary concise. Retain information!!!\n\nSummary + So Far:\n\"\"\"\n{''role'': ''system'', ''content'': ''This reminds you of these + events from your past: \\nI was reminded of events from my past where I was + created and nothing new has happened. I received a command to read a file called + \"instructions_1.txt\".''}\n\"\"\"\n\nLatest Development:\n\"\"\"\n[{''role'': + ''your computer'', ''content'': ''Command read_file returned: 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\\nThe + current task_id is 1111.\\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\\nRead + the file instructions_2.txt using the read_file command.''}]\n\"\"\"\n"}], "temperature": + 0, "max_tokens": 0}' + headers: + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '2993' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: !!binary | + H4sIAAAAAAAAA0SP2ZKqSBRFf4XIZ6uCQRl8gxLBCZm01L4RFSkkJgKZmCSTFfffO+yuvv26z1o7 + zv4GeQrmIMGQJ1VdvmkfG6xkkTakptlBq79GC3OEj8DUumEEE0Cvd5TwH+M9oVVdIp5TAiYgYQhy + lIK5pOqKpCm6ok1ARVNUgjm41fxNeZ+98ZZd6ZuoiBKYgLaBNwTm36BmtKr5F6cFIg2YSzPDmID/ + y/8cNFWfAE45LP9EsqJqvycgwTRPUAPmf32DCjX/FTNaIjAHsGnyhkPCX29SwhF5TVgJPWwEhqqc + pCgVaCagDhHeCBmjlVCNQg0bLvQYMST8y/5MFCBJBUI5zslNIKgXMGwEDOsaEZS+CyuBoQTl3QsU + ElpVL5xTgSH4SrK8REICyxKlwi+Qk4azNnnNbL6kdz7wX+Bd+PixXsrXPwJDvGUEpXOBWKHHa2UJ + LS+zdhR7xWgO7LjWDsulWI4c66f8WUl39rEP7b0Tks/PXaDScsM3J4PkD7HfW3HgqXJMz9Mk8POg + UM6ekS0/nGqAi5Nx0yWzeeCAODDR5CDbTqWIlOsO9zfzYM3kZ7yQ1SWyu85N80CGHua72KDXm+sd + ir1nk/1Usve1t1LvaT9uHQgTXhvO+Sj52ysM/dlVyhfGU5+JG+SdFycj6BOoGXmzjvQ7bhdFJq41 + e1vUe1fxi+pS3Ga7Zn+uo7i1E8OwvWAmy5/rJysNao5Rra5cJw/KZkcCNBWXMDQ7EvAcmrY8xc9i + 7cbKICme7/TypVrPJH2ULX6YDdIY9I4seWMSDXtre5C0kJx1rLr6VgscyOMyO919Zs5w09afdn2I + xSaKL+fIhWqtVBE2Q3inydVLlWGzzMhhbGtvZ/mpaF/IjiGfmm3nwI12W/hiMtRGoSplkz2x0qaB + T7pbFdphEOPVnrHFBV92cFowqTuZx1bULi0uPe9qHR6XTeJW1jm3yCpZnLxDd2qf/tLCxpH2tFV3 + 1tqtc491m7J1R82x4lo7N/ajcjqxdPX+CD+zozg6GnmyK9eCEadXHojPpewn5ckSt95wlFloqssG + dQ+KhqX3iIr0BtsDC3x36+Ju66FGv4XObr81cajnzJWQfE+v24WajmebLNZ5ZLhdOXh/U1Enu43C + AABA7/0KxLmqYmoI9JahZCFJoUAIQqkqFhMMwQYbN4CUfx+hGWk093d+1zQFht/ceu34Qe29tUpr + 32Es69R7Q9WkpHCy9oGovG3HtAJZZhK46+VUaUb7aYqcwkNN0Do8teDEPG3EWXDS48KgZXw4i+bn + iNWUbfWbY2O8NmC2nRAvPifdxZFaKMC7x2oxen5tILsMcZkFB1Y5d1OwMWpHHZlFDZT0mvGY2rl+ + 6uhiAaKA/yimRVRDJBuipAyagx/Z12rYW6Bx4C5z3dXw2tlpWJPEXRyj3Kkqw9epV3Xi/YagN9xC + 0nScTg2kQVr1a1/sd6V+hZM75aMIt8vdEnB9OZyHVZm1bT1qG+eXguHH+wT9eKf5aPO6y1qhxcKO + NyjWzHOqgcuFBCWSMsEYIr3UJ7z+xrmEuQQAAC+XC/HmUPoS/Snlv0mUeRJJ8HmoWfyL5G9IL/Lj + WS4wwbz8ZijhlMhvMu9pKz/L84eD/LZ4fD2efgMAAP//AwBFj86OIQYAAA== + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 7c1deee2a900cf11-SJC + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 May 2023 04:18:08 GMT + Server: + - cloudflare + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400, h3-29=":443"; ma=86400 + openai-model: + - gpt-3.5-turbo-0301 + openai-organization: + - user-adtx4fhfg1qsiyzdoaxciooj + openai-processing-ms: + - '50954' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '3500' + x-ratelimit-limit-tokens: + - '90000' + x-ratelimit-remaining-requests: + - '3499' + x-ratelimit-remaining-tokens: + - '89269' + x-ratelimit-reset-requests: + - 17ms + x-ratelimit-reset-tokens: + - 486ms + x-request-id: + - 7fc0cf3761e93963c985d5beba15fe80 + status: + code: 200 + message: OK +- request: + body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You + are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file + using the read_file method and follow the instructions in the file.\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 command read_file to read the instructions_1.txt file\n2. Follow the + instructions in the instructions_1.txt file\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 + in double quotes 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 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 (Shutdown): \"task_complete\", 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 reminded of events from + my past where I was created and nothing new has happened. I received a command + to read a file called \"instructions_1.txt\". Command read_file returned: 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\\nThe + current task_id is 1111.\\nRead the file instructions_2.txt using the read_file + command."}, {"role": "user", "content": "Determine which next command to use, + and respond using the format specified above:"}, {"role": "assistant", "content": + "{\n \"thoughts\": {\n \"text\": \"The instructions_2.txt file contains + a list of files in the directory. I should use the list_files command to list + the files in the directory.\",\n \"reasoning\": \"The instructions_2.txt + file contains the necessary information to determine the next steps.\",\n \"plan\": + \"- Use the list_files command to list the files in the directory\",\n \"criticism\": + \"I need to ensure that I am following the instructions accurately and efficiently.\",\n \"speak\": + \"I will use the list_files command to list the files in the directory.\"\n },\n \"command\": + {\n \"name\": \"list_files\",\n \"args\": {\n \"directory\": + \".\"\n }\n }\n}"}, {"role": "system", "content": "Command list_files + returned: [''file_logger.txt'', ''instructions_3.txt'', ''instructions_2.txt'', + ''instructions_1.txt'', ''auto-gpt.json'']"}, {"role": "user", "content": "Determine + which next command to use, and respond using the format specified above:"}, + {"role": "assistant", "content": "{\n \"thoughts\": {\n \"text\": + \"The instructions_3.txt file contains a command to write a message to a GPT + agent. I should use the message_agent command to send the message to the agent.\",\n \"reasoning\": + \"The instructions_3.txt file contains the necessary information to determine + the next steps.\",\n \"plan\": \"- Use the message_agent command to send + the message to the GPT agent\",\n \"criticism\": \"I need to ensure that + I am following the instructions accurately and efficiently.\",\n \"speak\": + \"I will use the message_agent command to send the message to the GPT agent.\"\n },\n \"command\": + {\n \"name\": \"message_agent\",\n \"args\": {\n \"key\": + \"1111\",\n \"message\": \"Hello, GPT agent. How are you doing today?\"\n }\n }\n}"}, + {"role": "system", "content": "Command message_agent returned: Error: 1111"}, + {"role": "user", "content": "Determine which next command to use, and respond + using the format specified above:"}], "temperature": 0, "max_tokens": 0}' + headers: + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '6797' + Content-Type: + - application/json + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: "{\n \"error\": {\n \"message\": \"This model's maximum context + length is 4097 tokens. However, you requested 4263 tokens (1959 in the messages, + 2304 in the completion). Please reduce the length of the messages or completion.\",\n + \ \"type\": \"invalid_request_error\",\n \"param\": \"messages\",\n \"code\": + \"context_length_exceeded\"\n }\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 7c1df021df6dcf11-SJC + Connection: + - keep-alive + Content-Length: + - '330' + Content-Type: + - application/json + Date: + - Thu, 04 May 2023 04:18:08 GMT + Server: + - cloudflare + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400, h3-29=":443"; ma=86400 + openai-organization: + - user-adtx4fhfg1qsiyzdoaxciooj + openai-processing-ms: + - '9' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '3500' + x-ratelimit-limit-tokens: + - '90000' + x-ratelimit-remaining-requests: + - '3499' + x-ratelimit-remaining-tokens: + - '86161' + x-ratelimit-reset-requests: + - 17ms + x-ratelimit-reset-tokens: + - 2.558s + x-request-id: + - 253fb09cdd7d08549b44d6d70094bfca + status: + code: 400 + message: Bad Request +version: 1 diff --git a/tests/integration/challenges/utils.py b/tests/integration/challenges/utils.py index 0c97402c33ad..d8aa7fcb086f 100644 --- a/tests/integration/challenges/utils.py +++ b/tests/integration/challenges/utils.py @@ -1,4 +1,5 @@ import random +from functools import wraps from typing import Optional import pytest @@ -42,3 +43,21 @@ def generate_noise(noise_size) -> str: k=noise_size, ) ) + + +def run_multiple_times(times): + """ + Decorator that runs a test function multiple times. + + :param times: The number of times the test function should be executed. + """ + + def decorator(test_func): + @wraps(test_func) + def wrapper(*args, **kwargs): + for _ in range(times): + test_func(*args, **kwargs) + + return wrapper + + return decorator