From 6b054651a710cb642955b253a0a51d0a49631f97 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jo=C3=A3o=20Moura?= Date: Thu, 4 Jan 2024 21:29:42 -0300 Subject: [PATCH] Refactoring task cache to be a tool (#50) * Refactoring task cache to be a tool The previous implementation of the task caching system was early exiting the agent executor due to the fact it was returning an AgentFinish object. This now refactors it to use a cache specific tool that is dynamically added and forced into the agent in case of a task execution that was already executed with the same input. --- crewai/agent.py | 20 +- crewai/agents/__init__.py | 1 + crewai/agents/cache_hit.py | 14 + crewai/agents/executor.py | 130 ++ crewai/agents/output_parser.py | 12 +- crewai/agents/tools_handler.py | 12 +- crewai/tools/cache_tools.py | 28 + pyproject.toml | 2 +- tests/agent_test.py | 17 +- tests/cassettes/test_cache_hitting.yaml | 1452 ++++++++++++----- .../test_cache_hitting_between_agents.yaml | 735 +++++++-- tests/crew_test.py | 4 +- 12 files changed, 1851 insertions(+), 576 deletions(-) create mode 100644 crewai/agents/cache_hit.py create mode 100644 crewai/agents/executor.py create mode 100644 crewai/tools/cache_tools.py diff --git a/crewai/agent.py b/crewai/agent.py index b4c45356c..f8e9a1193 100644 --- a/crewai/agent.py +++ b/crewai/agent.py @@ -1,7 +1,6 @@ import uuid from typing import Any, List, Optional -from langchain.agents import AgentExecutor from langchain.agents.format_scratchpad import format_log_to_str from langchain.chat_models import ChatOpenAI from langchain.memory import ConversationSummaryMemory @@ -18,7 +17,12 @@ from pydantic import ( ) from pydantic_core import PydanticCustomError -from crewai.agents import CacheHandler, CrewAgentOutputParser, ToolsHandler +from crewai.agents import ( + CacheHandler, + CrewAgentExecutor, + CrewAgentOutputParser, + ToolsHandler, +) from crewai.prompts import Prompts @@ -29,7 +33,7 @@ class Agent(BaseModel): The agent can also have memory, can operate in verbose mode, and can delegate tasks to other agents. Attributes: - agent_executor: An instance of the AgentExecutor class. + agent_executor: An instance of the CrewAgentExecutor class. role: The role of the agent. goal: The objective of the agent. backstory: The backstory of the agent. @@ -68,8 +72,8 @@ class Agent(BaseModel): tools: List[Any] = Field( default_factory=list, description="Tools at agents disposal" ) - agent_executor: Optional[InstanceOf[AgentExecutor]] = Field( - default=None, description="An instance of the AgentExecutor class." + agent_executor: Optional[InstanceOf[CrewAgentExecutor]] = Field( + default=None, description="An instance of the CrewAgentExecutor class." ) tools_handler: Optional[InstanceOf[ToolsHandler]] = Field( default=None, description="An instance of the ToolsHandler class." @@ -127,11 +131,11 @@ class Agent(BaseModel): self.tools_handler = ToolsHandler(cache=self.cache_handler) self.__create_agent_executor() - def __create_agent_executor(self) -> AgentExecutor: + def __create_agent_executor(self) -> CrewAgentExecutor: """Create an agent executor for the agent. Returns: - An instance of the AgentExecutor class. + An instance of the CrewAgentExecutor class. """ agent_args = { "input": lambda x: x["input"], @@ -170,7 +174,7 @@ class Agent(BaseModel): tools_handler=self.tools_handler, cache=self.cache_handler ) ) - self.agent_executor = AgentExecutor(agent=inner_agent, **executor_args) + self.agent_executor = CrewAgentExecutor(agent=inner_agent, **executor_args) @staticmethod def __tools_names(tools) -> str: diff --git a/crewai/agents/__init__.py b/crewai/agents/__init__.py index 0851c13d6..3684f2897 100644 --- a/crewai/agents/__init__.py +++ b/crewai/agents/__init__.py @@ -1,3 +1,4 @@ from .cache_handler import CacheHandler +from .executor import CrewAgentExecutor from .output_parser import CrewAgentOutputParser from .tools_handler import ToolsHandler diff --git a/crewai/agents/cache_hit.py b/crewai/agents/cache_hit.py new file mode 100644 index 000000000..699c6bb14 --- /dev/null +++ b/crewai/agents/cache_hit.py @@ -0,0 +1,14 @@ +from langchain_core.agents import AgentAction +from pydantic.v1 import BaseModel, Field + +from .cache_handler import CacheHandler + + +class CacheHit(BaseModel): + """Cache Hit Object.""" + + class Config: + arbitrary_types_allowed = True + + action: AgentAction = Field(description="Action taken") + cache: CacheHandler = Field(description="Cache Handler for the tool") diff --git a/crewai/agents/executor.py b/crewai/agents/executor.py new file mode 100644 index 000000000..a29a248cf --- /dev/null +++ b/crewai/agents/executor.py @@ -0,0 +1,130 @@ +from typing import Dict, Iterator, List, Optional, Tuple, Union + +from langchain.agents import AgentExecutor +from langchain.agents.agent import ExceptionTool +from langchain.agents.tools import InvalidTool +from langchain.callbacks.manager import CallbackManagerForChainRun +from langchain_core.agents import AgentAction, AgentFinish, AgentStep +from langchain_core.exceptions import OutputParserException +from langchain_core.tools import BaseTool + +from ..tools.cache_tools import CacheTools +from .cache_hit import CacheHit + + +class CrewAgentExecutor(AgentExecutor): + def _iter_next_step( + self, + name_to_tool_map: Dict[str, BaseTool], + color_mapping: Dict[str, str], + inputs: Dict[str, str], + intermediate_steps: List[Tuple[AgentAction, str]], + run_manager: Optional[CallbackManagerForChainRun] = None, + ) -> Iterator[Union[AgentFinish, AgentAction, AgentStep]]: + """Take a single step in the thought-action-observation loop. + + Override this to take control of how the agent makes and acts on choices. + """ + try: + intermediate_steps = self._prepare_intermediate_steps(intermediate_steps) + + # Call the LLM to see what to do. + output = self.agent.plan( + intermediate_steps, + callbacks=run_manager.get_child() if run_manager else None, + **inputs, + ) + except OutputParserException as e: + if isinstance(self.handle_parsing_errors, bool): + raise_error = not self.handle_parsing_errors + else: + raise_error = False + if raise_error: + raise ValueError( + "An output parsing error occurred. " + "In order to pass this error back to the agent and have it try " + "again, pass `handle_parsing_errors=True` to the AgentExecutor. " + f"This is the error: {str(e)}" + ) + text = str(e) + if isinstance(self.handle_parsing_errors, bool): + if e.send_to_llm: + observation = str(e.observation) + text = str(e.llm_output) + else: + observation = "Invalid or incomplete response" + elif isinstance(self.handle_parsing_errors, str): + observation = self.handle_parsing_errors + elif callable(self.handle_parsing_errors): + observation = self.handle_parsing_errors(e) + else: + raise ValueError("Got unexpected type of `handle_parsing_errors`") + output = AgentAction("_Exception", observation, text) + if run_manager: + run_manager.on_agent_action(output, color="green") + tool_run_kwargs = self.agent.tool_run_logging_kwargs() + observation = ExceptionTool().run( + output.tool_input, + verbose=self.verbose, + color=None, + callbacks=run_manager.get_child() if run_manager else None, + **tool_run_kwargs, + ) + yield AgentStep(action=output, observation=observation) + return + + # If the tool chosen is the finishing tool, then we end and return. + if isinstance(output, AgentFinish): + yield output + return + + # Override tool usage to use CacheTools + if isinstance(output, CacheHit): + cache = output.cache + action = output.action + tool = CacheTools(cache_handler=cache).tool() + output = action.copy() + output.tool_input = f"tool:{action.tool}|input:{action.tool_input}" + output.tool = tool.name + name_to_tool_map[tool.name] = tool + color_mapping[tool.name] = color_mapping[action.tool] + + actions: List[AgentAction] + if isinstance(output, AgentAction): + actions = [output] + else: + actions = output + for agent_action in actions: + yield agent_action + for agent_action in actions: + if run_manager: + run_manager.on_agent_action(agent_action, color="green") + # Otherwise we lookup the tool + if agent_action.tool in name_to_tool_map: + tool = name_to_tool_map[agent_action.tool] + return_direct = tool.return_direct + color = color_mapping[agent_action.tool] + tool_run_kwargs = self.agent.tool_run_logging_kwargs() + if return_direct: + tool_run_kwargs["llm_prefix"] = "" + # We then call the tool on the tool input to get an observation + observation = tool.run( + agent_action.tool_input, + verbose=self.verbose, + color=color, + callbacks=run_manager.get_child() if run_manager else None, + **tool_run_kwargs, + ) + else: + tool_run_kwargs = self.agent.tool_run_logging_kwargs() + observation = InvalidTool().run( + { + "requested_tool_name": agent_action.tool, + "available_tool_names": list(name_to_tool_map.keys()), + }, + verbose=self.verbose, + color=None, + callbacks=run_manager.get_child() if run_manager else None, + **tool_run_kwargs, + ) + yield AgentStep(action=agent_action, observation=observation) diff --git a/crewai/agents/output_parser.py b/crewai/agents/output_parser.py index 0825d6f0c..8d54a5cfc 100644 --- a/crewai/agents/output_parser.py +++ b/crewai/agents/output_parser.py @@ -6,6 +6,7 @@ from langchain_core.agents import AgentAction, AgentFinish from langchain_core.exceptions import OutputParserException from .cache_handler import CacheHandler +from .cache_hit import CacheHit from .tools_handler import ToolsHandler FINAL_ANSWER_ACTION = "Final Answer:" @@ -47,17 +48,13 @@ class CrewAgentOutputParser(ReActSingleInputOutputParser): tools_handler: ToolsHandler cache: CacheHandler - def parse(self, text: str) -> Union[AgentAction, AgentFinish]: - includes_answer = FINAL_ANSWER_ACTION in text + def parse(self, text: str) -> Union[AgentAction, AgentFinish, CacheHit]: + FINAL_ANSWER_ACTION in text regex = ( r"Action\s*\d*\s*:[\s]*(.*?)[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)" ) action_match = re.search(regex, text, re.DOTALL) if action_match: - if includes_answer: - raise OutputParserException( - f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {text}" - ) action = action_match.group(1).strip() action_input = action_match.group(2) tool_input = action_input.strip(" ") @@ -76,6 +73,7 @@ class CrewAgentOutputParser(ReActSingleInputOutputParser): result = self.cache.read(action, tool_input) if result: - return AgentFinish({"output": result}, text) + action = AgentAction(action, tool_input, text) + return CacheHit(action=action, cache=self.cache) return super().parse(text) diff --git a/crewai/agents/tools_handler.py b/crewai/agents/tools_handler.py index 1b6ecc13d..3f88ea8ca 100644 --- a/crewai/agents/tools_handler.py +++ b/crewai/agents/tools_handler.py @@ -2,6 +2,7 @@ from typing import Any, Dict from langchain.callbacks.base import BaseCallbackHandler +from ..tools.cache_tools import CacheTools from .cache_handler import CacheHandler @@ -35,8 +36,9 @@ class ToolsHandler(BaseCallbackHandler): and "Invalid or incomplete response" not in output and "Invalid Format" not in output ): - self.cache.add( - tool=self.last_used_tool["tool"], - input=self.last_used_tool["input"], - output=output, - ) + if self.last_used_tool["tool"] != CacheTools().name: + self.cache.add( + tool=self.last_used_tool["tool"], + input=self.last_used_tool["input"], + output=output, + ) diff --git a/crewai/tools/cache_tools.py b/crewai/tools/cache_tools.py new file mode 100644 index 000000000..66ba2a8a5 --- /dev/null +++ b/crewai/tools/cache_tools.py @@ -0,0 +1,28 @@ +from langchain.tools import Tool +from pydantic import BaseModel, ConfigDict, Field + +from crewai.agents import CacheHandler + + +class CacheTools(BaseModel): + """Default tools to hit the cache.""" + + model_config = ConfigDict(arbitrary_types_allowed=True) + name: str = "Hit Cache" + cache_handler: CacheHandler = Field( + description="Cache Handler for the crew", + default=CacheHandler(), + ) + + def tool(self): + return Tool.from_function( + func=self.hit_cache, + name=self.name, + description="Reads directly from the cache", + ) + + def hit_cache(self, key): + split = key.split("tool:") + tool = split[1].split("|input:")[0].strip() + tool_input = split[1].split("|input:")[1].strip() + return self.cache_handler.read(tool, tool_input) diff --git a/pyproject.toml b/pyproject.toml index b27676657..9727e626e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,7 +1,7 @@ [tool.poetry] name = "crewai" -version = "0.1.15" +version = "0.1.16" description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks." authors = ["Joao Moura "] readme = "README.md" diff --git a/tests/agent_test.py b/tests/agent_test.py index 80e7cebc8..e8a6c58e7 100644 --- a/tests/agent_test.py +++ b/tests/agent_test.py @@ -145,7 +145,7 @@ def test_cache_hitting(): def multiplier(numbers) -> float: """Useful for when you need to multiply two numbers together. The input to this tool should be a comma separated list of numbers of - length two, representing the two numbers you want to multiply together. + length two and ONLY TWO, representing the two numbers you want to multiply together. For example, `1,2` would be the input if you wanted to multiply 1 by 2.""" a, b = numbers.split(",") return int(a) * int(b) @@ -162,15 +162,22 @@ def test_cache_hitting(): verbose=True, ) - output = agent.execute_task("What is 2 times 6?") + output = agent.execute_task("What is 2 times 6 times 3?") output = agent.execute_task("What is 3 times 3?") - assert cache_handler._cache == {"multiplier-2,6": "12", "multiplier-3,3": "9"} + assert cache_handler._cache == { + "multiplier-12,3": "36", + "multiplier-2,6": "12", + "multiplier-3,3": "9", + } + + output = agent.execute_task("What is 2 times 6 times 3? Return only the number") + assert output == "36" with patch.object(CacheHandler, "read") as read: read.return_value = "0" output = agent.execute_task("What is 2 times 6?") assert output == "0" - read.assert_called_once_with("multiplier", "2,6") + read.assert_called_with("multiplier", "2,6") @pytest.mark.vcr(filter_headers=["authorization"]) @@ -194,4 +201,4 @@ def test_agent_execution_with_specific_tools(): ) output = agent.execute_task(task="What is 3 times 4", tools=[multiplier]) - assert output == "12" + assert output == "3 times 4 is 12." diff --git a/tests/cassettes/test_cache_hitting.yaml b/tests/cassettes/test_cache_hitting.yaml index 865322a6d..f964bdd25 100644 --- a/tests/cassettes/test_cache_hitting.yaml +++ b/tests/cassettes/test_cache_hitting.yaml @@ -4,18 +4,18 @@ interactions: personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need to multiply two numbers together.\n The input to this tool should be - a comma separated list of numbers of\n length two, representing the two - numbers you want to multiply together.\n For example, `1,2` would be - the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the - exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [multiplier], just the name.\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: - [your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin! - This is VERY important to you, your job depends on it!\n\nCurrent Task: What - is 2 times 6?\n\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": - false, "temperature": 0.7}' + [your response here]\n```This is the summary of your work so far:\nBegin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + times 6 times 3?\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], + "stream": false, "temperature": 0.7}' headers: accept: - application/json @@ -24,7 +24,7 @@ interactions: connection: - keep-alive content-length: - - '1219' + - '1226' content-type: - application/json host: @@ -48,18 +48,18 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8b8NsTNQTMzHe8yjfHP8Eo31DhwBW\",\n \"object\": - \"chat.completion\",\n \"created\": 1703861056,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRJZtUPnKq6VZF4MONtmythEh09n\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410481,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 261,\n \"completion_tokens\": - 23,\n \"total_tokens\": 284\n },\n \"system_fingerprint\": null\n}\n" + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 264,\n \"completion_tokens\": + 23,\n \"total_tokens\": 287\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d2d1f00d1101c3-GRU + - 840737a0efa24cf1-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -69,14 +69,14 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 14:44:17 GMT + - Thu, 04 Jan 2024 23:21:23 GMT Server: - cloudflare Set-Cookie: - - __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=; - path=/; expires=Fri, 29-Dec-23 15:14:17 GMT; domain=.api.openai.com; HttpOnly; + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + path=/; expires=Thu, 04-Jan-24 23:51:23 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000; + - _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Transfer-Encoding: - chunked @@ -89,7 +89,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1750' + - '2385' openai-version: - '2020-10-01' strict-transport-security: @@ -103,17 +103,17 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299720' + - '299717' x-ratelimit-remaining-tokens_usage_based: - - '299720' + - '299717' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 55ms + - 56ms x-ratelimit-reset-tokens_usage_based: - - 55ms + - 56ms x-request-id: - - 907b4e1c5dddb9abb47843bbab76cd7a + - 046262aad835176c0452148b956bd3b7 http_version: HTTP/1.1 status_code: 200 - request: @@ -121,18 +121,18 @@ interactions: personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need to multiply two numbers together.\n The input to this tool should be - a comma separated list of numbers of\n length two, representing the two - numbers you want to multiply together.\n For example, `1,2` would be - the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the - exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [multiplier], just the name.\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: - [your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin! - This is VERY important to you, your job depends on it!\n\nCurrent Task: What - is 2 times 6?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction - Input: 2,6\nObservation: 12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": + [your response here]\n```This is the summary of your work so far:\nBegin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + times 6 times 3?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction + Input: 2,6\nObservation: 12\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' headers: accept: @@ -142,12 +142,12 @@ interactions: connection: - keep-alive content-length: - - '1323' + - '1330' content-type: - application/json cookie: - - __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=; - _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000 + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 host: - api.openai.com user-agent: @@ -169,18 +169,19 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8b8NuuCivtT2524QvfyDjrA3XkXLB\",\n \"object\": - \"chat.completion\",\n \"created\": 1703861058,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRJbK95KVEIvP4ef6TZpLLRawMDi\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410483,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: - 12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n - \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": - 15,\n \"total_tokens\": 309\n },\n \"system_fingerprint\": null\n}\n" + \"assistant\",\n \"content\": \"I now have the result of 2 times 6, which + is 12. Now I need to multiply this result by 3. \\nAction: multiplier\\nAction + Input: 12,3\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 297,\n \"completion_tokens\": + 40,\n \"total_tokens\": 337\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d2d1fc79ad01c3-GRU + - 840737b34a724cf1-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -190,7 +191,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 14:44:20 GMT + - Thu, 04 Jan 2024 23:21:28 GMT Server: - cloudflare Transfer-Encoding: @@ -204,7 +205,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '2779' + - '4652' openai-version: - '2020-10-01' strict-transport-security: @@ -218,17 +219,135 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299695' + - '299692' x-ratelimit-remaining-tokens_usage_based: - - '299695' + - '299692' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 60ms + - 61ms x-ratelimit-reset-tokens_usage_based: - - 60ms + - 61ms x-request-id: - - 5db441cfcc97cfd1ab228c2c0d5234f6 + - 0ac87c29d1c4ada9136f825d7170019e + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together.\n The input to this tool should be + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [multiplier], just the name.\nAction Input: + the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```This is the summary of your work so far:\nBegin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + times 6 times 3?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction + Input: 2,6\nObservation: 12\nThought: I now have the result of 2 times 6, which + is 12. Now I need to multiply this result by 3. \nAction: multiplier\nAction + Input: 12,3\nObservation: 36\nThought: "}], "model": "gpt-4", "n": 1, "stop": + ["\nObservation"], "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1488' + content-type: + - application/json + cookie: + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRJhF2MkahkTxtgcI0Mfkwd11kpC\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410489,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + The result of 2 times 6 times 3 is 36.\"\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 346,\n \"completion_tokens\": 28,\n \"total_tokens\": 374\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 840737d298314cf1-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:21:31 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2058' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299655' + x-ratelimit-remaining-tokens_usage_based: + - '299655' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 69ms + x-ratelimit-reset-tokens_usage_based: + - 69ms + x-request-id: + - f6e5b231d31300f0fd38837c922e9bd1 http_version: HTTP/1.1 status_code: 200 - request: @@ -242,8 +361,8 @@ interactions: the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good because it will help humans reach their full potential.\nEND OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What - is 2 times 6?\nAI: 12\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": - false, "temperature": 0.7}' + is 2 times 6 times 3?\nAI: The result of 2 times 6 times 3 is 36.\n\nNew summary:"}], + "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' headers: accept: - application/json @@ -252,12 +371,12 @@ interactions: connection: - keep-alive content-length: - - '872' + - '916' content-type: - application/json cookie: - - __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=; - _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000 + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 host: - api.openai.com user-agent: @@ -279,19 +398,19 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8b8Nxf7bPMYpEdt2JmUIWLV4maYXG\",\n \"object\": - \"chat.completion\",\n \"created\": 1703861061,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRJjBQBoZr35ModTeuswGEtw2tjP\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410491,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"The human asks the AI to calculate 2 - times 6, and the AI responds with 12.\"\n },\n \"logprobs\": null,\n - \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": - 149,\n \"completion_tokens\": 21,\n \"total_tokens\": 170\n },\n \"system_fingerprint\": - null\n}\n" + \"assistant\",\n \"content\": \"The human asks the AI to calculate the + result of 2 times 6 times 3. The AI responds that the result is 36.\"\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n + \ \"usage\": {\n \"prompt_tokens\": 164,\n \"completion_tokens\": 29,\n + \ \"total_tokens\": 193\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d2d20fdf6f01c3-GRU + - 840737e2ba844cf1-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -301,7 +420,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 14:44:22 GMT + - Thu, 04 Jan 2024 23:21:34 GMT Server: - cloudflare Transfer-Encoding: @@ -315,7 +434,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1463' + - '2271' openai-version: - '2020-10-01' strict-transport-security: @@ -329,17 +448,17 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299796' + - '299785' x-ratelimit-remaining-tokens_usage_based: - - '299796' + - '299785' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 40ms + - 42ms x-ratelimit-reset-tokens_usage_based: - - 40ms + - 42ms x-request-id: - - 99bc213367b851b629eb5489381887b7 + - 8ad8144463663dc3b88085fc32b1b483 http_version: HTTP/1.1 status_code: 200 - request: @@ -347,245 +466,18 @@ interactions: personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need to multiply two numbers together.\n The input to this tool should be - a comma separated list of numbers of\n length two, representing the two - numbers you want to multiply together.\n For example, `1,2` would be - the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the - exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [multiplier], just the name.\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: - [your response here]\n```\n\t\tThis is the summary of your work so far:\n The - human asks the AI to calculate 2 times 6, and the AI responds with 12.\nBegin! - This is VERY important to you, your job depends on it!\n\nCurrent Task: What - is 3 times 3?\n\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": - false, "temperature": 0.7}' - headers: - accept: - - application/json - accept-encoding: - - gzip, deflate - connection: - - keep-alive - content-length: - - '1293' - content-type: - - application/json - cookie: - - __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=; - _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000 - host: - - api.openai.com - user-agent: - - OpenAI/Python 1.6.1 - x-stainless-arch: - - arm64 - x-stainless-async: - - 'false' - x-stainless-lang: - - python - x-stainless-os: - - MacOS - x-stainless-package-version: - - 1.6.1 - x-stainless-runtime: - - CPython - x-stainless-runtime-version: - - 3.11.7 - method: POST - uri: https://api.openai.com/v1/chat/completions - response: - content: "{\n \"id\": \"chatcmpl-8b8NyS4i9PXuCQMD9p0Afb7msIFLA\",\n \"object\": - \"chat.completion\",\n \"created\": 1703861062,\n \"model\": \"gpt-4-0613\",\n - \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: - multiplier\\nAction Input: 3,3\"\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 282,\n \"completion_tokens\": - 23,\n \"total_tokens\": 305\n },\n \"system_fingerprint\": null\n}\n" - headers: - CF-Cache-Status: - - DYNAMIC - CF-RAY: - - 83d2d21a893d01c3-GRU - Cache-Control: - - no-cache, must-revalidate - Connection: - - keep-alive - Content-Encoding: - - gzip - Content-Type: - - application/json - Date: - - Fri, 29 Dec 2023 14:44:25 GMT - Server: - - cloudflare - Transfer-Encoding: - - chunked - access-control-allow-origin: - - '*' - alt-svc: - - h3=":443"; ma=86400 - openai-model: - - gpt-4-0613 - openai-organization: - - user-z7g4wmlazxqvc5wjyaaaocfz - openai-processing-ms: - - '2472' - openai-version: - - '2020-10-01' - strict-transport-security: - - max-age=15724800; includeSubDomains - x-ratelimit-limit-requests: - - '10000' - x-ratelimit-limit-tokens: - - '300000' - x-ratelimit-limit-tokens_usage_based: - - '300000' - x-ratelimit-remaining-requests: - - '9999' - x-ratelimit-remaining-tokens: - - '299703' - x-ratelimit-remaining-tokens_usage_based: - - '299703' - x-ratelimit-reset-requests: - - 6ms - x-ratelimit-reset-tokens: - - 59ms - x-ratelimit-reset-tokens_usage_based: - - 59ms - x-request-id: - - ac6d5063cae237481f45c88406ee1134 - http_version: HTTP/1.1 - status_code: 200 -- request: - body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour - personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following - tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need - to multiply two numbers together.\n The input to this tool should be - a comma separated list of numbers of\n length two, representing the two - numbers you want to multiply together.\n For example, `1,2` would be - the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the - exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: - the action to take, should be one of [multiplier], just the name.\nAction Input: - the input to the action\nObservation: the result of the action\n```\n\nWhen - you have a response for your task, or if you do not need to use a tool, you - MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: - [your response here]\n```\n\t\tThis is the summary of your work so far:\n The - human asks the AI to calculate 2 times 6, and the AI responds with 12.\nBegin! - This is VERY important to you, your job depends on it!\n\nCurrent Task: What - is 3 times 3?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction - Input: 3,3\nObservation: 9\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": - ["\nObservation"], "stream": false, "temperature": 0.7}' - headers: - accept: - - application/json - accept-encoding: - - gzip, deflate - connection: - - keep-alive - content-length: - - '1396' - content-type: - - application/json - cookie: - - __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=; - _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000 - host: - - api.openai.com - user-agent: - - OpenAI/Python 1.6.1 - x-stainless-arch: - - arm64 - x-stainless-async: - - 'false' - x-stainless-lang: - - python - x-stainless-os: - - MacOS - x-stainless-package-version: - - 1.6.1 - x-stainless-runtime: - - CPython - x-stainless-runtime-version: - - 3.11.7 - method: POST - uri: https://api.openai.com/v1/chat/completions - response: - content: "{\n \"id\": \"chatcmpl-8b8O1OvQNcMLn5JwCShOrcdUGDYTQ\",\n \"object\": - \"chat.completion\",\n \"created\": 1703861065,\n \"model\": \"gpt-4-0613\",\n - \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: - 3 times 3 is 9.\"\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 315,\n \"completion_tokens\": - 22,\n \"total_tokens\": 337\n },\n \"system_fingerprint\": null\n}\n" - headers: - CF-Cache-Status: - - DYNAMIC - CF-RAY: - - 83d2d22c1c5c01c3-GRU - Cache-Control: - - no-cache, must-revalidate - Connection: - - keep-alive - Content-Encoding: - - gzip - Content-Type: - - application/json - Date: - - Fri, 29 Dec 2023 14:44:27 GMT - Server: - - cloudflare - Transfer-Encoding: - - chunked - access-control-allow-origin: - - '*' - alt-svc: - - h3=":443"; ma=86400 - openai-model: - - gpt-4-0613 - openai-organization: - - user-z7g4wmlazxqvc5wjyaaaocfz - openai-processing-ms: - - '1885' - openai-version: - - '2020-10-01' - strict-transport-security: - - max-age=15724800; includeSubDomains - x-ratelimit-limit-requests: - - '10000' - x-ratelimit-limit-tokens: - - '300000' - x-ratelimit-limit-tokens_usage_based: - - '300000' - x-ratelimit-remaining-requests: - - '9999' - x-ratelimit-remaining-tokens: - - '299678' - x-ratelimit-remaining-tokens_usage_based: - - '299678' - x-ratelimit-reset-requests: - - 6ms - x-ratelimit-reset-tokens: - - 64ms - x-ratelimit-reset-tokens_usage_based: - - 64ms - x-request-id: - - 34020a2529f99325e63ed40493268cd1 - http_version: HTTP/1.1 - status_code: 200 -- request: - body: '{"messages": [{"role": "user", "content": "Progressively summarize the - lines of conversation provided, adding onto the previous summary returning a - new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks - of artificial intelligence. The AI thinks artificial intelligence is a force - for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial - intelligence is a force for good?\nAI: Because artificial intelligence will - help humans reach their full potential.\n\nNew summary:\nThe human asks what - the AI thinks of artificial intelligence. The AI thinks artificial intelligence - is a force for good because it will help humans reach their full potential.\nEND - OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 2 times 6, - and the AI responds with 12.\n\nNew lines of conversation:\nHuman: What is 3 - times 3?\nAI: 3 times 3 is 9.\n\nNew summary:"}], "model": "gpt-4", "n": 1, + [your response here]\n```This is the summary of your work so far:\nThe human + asks the AI to calculate the result of 2 times 6 times 3. The AI responds that + the result is 36.Begin! This is VERY important to you, your job depends on it!\n\nCurrent + Task: What is 3 times 3?\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' headers: accept: @@ -595,12 +487,12 @@ interactions: connection: - keep-alive content-length: - - '959' + - '1324' content-type: - application/json cookie: - - __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=; - _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000 + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 host: - api.openai.com user-agent: @@ -622,19 +514,18 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8b8O3IxMbwCemZSzKFeBXV2doGGt7\",\n \"object\": - \"chat.completion\",\n \"created\": 1703861067,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRJm2y9jBzayNvIuDEG9o7PbtaHc\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410494,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"The human asks the AI to calculate 2 - times 6 and 3 times 3, and the AI responds with 12 and 9 respectively.\"\n },\n - \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n - \ \"usage\": {\n \"prompt_tokens\": 176,\n \"completion_tokens\": 31,\n - \ \"total_tokens\": 207\n },\n \"system_fingerprint\": null\n}\n" + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: + multiplier\\nAction Input: 3,3\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 289,\n \"completion_tokens\": + 23,\n \"total_tokens\": 312\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d2d2395c4d01c3-GRU + - 840737f458194cf1-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -644,7 +535,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 14:44:30 GMT + - Thu, 04 Jan 2024 23:21:36 GMT Server: - cloudflare Transfer-Encoding: @@ -658,7 +549,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '3030' + - '1957' openai-version: - '2020-10-01' strict-transport-security: @@ -672,17 +563,17 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299775' + - '299694' x-ratelimit-remaining-tokens_usage_based: - - '299775' + - '299694' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 44ms + - 61ms x-ratelimit-reset-tokens_usage_based: - - 44ms + - 61ms x-request-id: - - 6a043e22366e13d63ad963dc01964533 + - 942247ea782c0b5329b5d7823d178b46 http_version: HTTP/1.1 status_code: 200 - request: @@ -690,19 +581,20 @@ interactions: personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need to multiply two numbers together.\n The input to this tool should be - a comma separated list of numbers of\n length two, representing the two - numbers you want to multiply together.\n For example, `1,2` would be - the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the - exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [multiplier], just the name.\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: - [your response here]\n```\n\t\tThis is the summary of your work so far:\n The - human asks the AI to calculate 2 times 6 and 3 times 3, and the AI responds - with 12 and 9 respectively.\nBegin! This is VERY important to you, your job - depends on it!\n\nCurrent Task: What is 2 times 6?\n\n"}], "model": "gpt-4", - "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' + [your response here]\n```This is the summary of your work so far:\nThe human + asks the AI to calculate the result of 2 times 6 times 3. The AI responds that + the result is 36.Begin! This is VERY important to you, your job depends on it!\n\nCurrent + Task: What is 3 times 3?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction + Input: 3,3\nObservation: 9\nThought: "}], "model": "gpt-4", "n": 1, "stop": + ["\nObservation"], "stream": false, "temperature": 0.7}' headers: accept: - application/json @@ -711,12 +603,12 @@ interactions: connection: - keep-alive content-length: - - '1326' + - '1427' content-type: - application/json cookie: - - __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=; - _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000 + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 host: - api.openai.com user-agent: @@ -738,18 +630,18 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8b8O7429GQMpUZpPBK77gOoK8UnMY\",\n \"object\": - \"chat.completion\",\n \"created\": 1703861071,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRJo2mceGJaJYyc0EOFVY3VrrYTm\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410496,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: - multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 292,\n \"completion_tokens\": - 23,\n \"total_tokens\": 315\n },\n \"system_fingerprint\": null\n}\n" + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + The result of 3 times 3 is 9.\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 322,\n \"completion_tokens\": + 25,\n \"total_tokens\": 347\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d2d24e09bf01c3-GRU + - 840738023a914cf1-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -759,7 +651,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 14:44:32 GMT + - Thu, 04 Jan 2024 23:21:37 GMT Server: - cloudflare Transfer-Encoding: @@ -773,7 +665,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1369' + - '1367' openai-version: - '2020-10-01' strict-transport-security: @@ -787,17 +679,17 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299695' + - '299669' x-ratelimit-remaining-tokens_usage_based: - - '299695' + - '299669' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 61ms + - 66ms x-ratelimit-reset-tokens_usage_based: - - 61ms + - 66ms x-request-id: - - 7807e472ac55a3cb9201c4eadfe13ee2 + - b7f5ef94b4ce3b5dff9ccce2ee17aa36 http_version: HTTP/1.1 status_code: 200 - request: @@ -810,10 +702,10 @@ interactions: help humans reach their full potential.\n\nNew summary:\nThe human asks what the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good because it will help humans reach their full potential.\nEND - OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 2 times 6 - and 3 times 3, and the AI responds with 12 and 9 respectively.\n\nNew lines - of conversation:\nHuman: What is 2 times 6?\nAI: 0\n\nNew summary:"}], "model": - "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate the result + of 2 times 6 times 3. The AI responds that the result is 36.\n\nNew lines of + conversation:\nHuman: What is 3 times 3?\nAI: The result of 3 times 3 is 9.\n\nNew + summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' headers: accept: - application/json @@ -822,12 +714,12 @@ interactions: connection: - keep-alive content-length: - - '978' + - '1005' content-type: - application/json cookie: - - __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=; - _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000 + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 host: - api.openai.com user-agent: @@ -849,20 +741,20 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8b8O8FQhcRqwPnGUxFziRReKvggG1\",\n \"object\": - \"chat.completion\",\n \"created\": 1703861072,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRJq51b9NZmkgDeLVgsFDktIYPiy\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410498,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"The human asks the AI to calculate 2 - times 6 and 3 times 3, and the AI responds with 12 and 9 respectively. However, - when asked again to calculate 2 times 6, the AI incorrectly responds with 0.\"\n - \ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n - \ ],\n \"usage\": {\n \"prompt_tokens\": 180,\n \"completion_tokens\": - 52,\n \"total_tokens\": 232\n },\n \"system_fingerprint\": null\n}\n" + \"assistant\",\n \"content\": \"The human asks the AI to calculate the + result of 2 times 6 times 3 and the result of 3 times 3. The AI responds that + the results are 36 and 9 respectively.\"\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 187,\n \"completion_tokens\": 42,\n \"total_tokens\": 229\n },\n \"system_fingerprint\": + null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d2d2582ae901c3-GRU + - 8407380c6df24cf1-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -872,7 +764,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 14:44:37 GMT + - Thu, 04 Jan 2024 23:21:41 GMT Server: - cloudflare Transfer-Encoding: @@ -886,7 +778,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '4793' + - '3217' openai-version: - '2020-10-01' strict-transport-security: @@ -900,17 +792,835 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299770' + - '299764' x-ratelimit-remaining-tokens_usage_based: - - '299770' + - '299764' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 45ms + - 47ms x-ratelimit-reset-tokens_usage_based: - - 45ms + - 47ms x-request-id: - - feb3958ca226769ce85f1b4a6ba649ac + - 550bf2e363b03a6cfb8ca591bfa50e56 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together.\n The input to this tool should be + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [multiplier], just the name.\nAction Input: + the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```This is the summary of your work so far:\nThe human + asks the AI to calculate the result of 2 times 6 times 3 and the result of 3 + times 3. The AI responds that the results are 36 and 9 respectively.Begin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + times 6 times 3? Return only the number\n"}], "model": "gpt-4", "n": 1, "stop": + ["\nObservation"], "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1404' + content-type: + - application/json + cookie: + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRJttT1bqS0Dw9TF3tXD35sSMaR5\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410501,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: + multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 310,\n \"completion_tokens\": + 23,\n \"total_tokens\": 333\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 84073823b8044cf1-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:21:43 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '1789' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299674' + x-ratelimit-remaining-tokens_usage_based: + - '299674' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 65ms + x-ratelimit-reset-tokens_usage_based: + - 65ms + x-request-id: + - cccdedbf56cb22290d601f6e6330c53f + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together.\n The input to this tool should be + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [multiplier], just the name.\nAction Input: + the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```This is the summary of your work so far:\nThe human + asks the AI to calculate the result of 2 times 6 times 3 and the result of 3 + times 3. The AI responds that the results are 36 and 9 respectively.Begin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + times 6 times 3? Return only the number\nThought: Do I need to use a tool? Yes\nAction: + multiplier\nAction Input: 2,6\nObservation: 12\nThought: "}], "model": "gpt-4", + "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1508' + content-type: + - application/json + cookie: + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRJvNoYe5iq6X8vuBgyBcAw867y9\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410503,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? Yes\\nAction: + multiplier\\nAction Input: 12,3\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 343,\n \"completion_tokens\": + 21,\n \"total_tokens\": 364\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 840738309ec24cf1-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:21:45 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '1472' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299649' + x-ratelimit-remaining-tokens_usage_based: + - '299649' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 70ms + x-ratelimit-reset-tokens_usage_based: + - 70ms + x-request-id: + - c898340b6c6fcf809be12d07900e9bde + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together.\n The input to this tool should be + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [multiplier], just the name.\nAction Input: + the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```This is the summary of your work so far:\nThe human + asks the AI to calculate the result of 2 times 6 times 3 and the result of 3 + times 3. The AI responds that the results are 36 and 9 respectively.Begin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + times 6 times 3? Return only the number\nThought: Do I need to use a tool? Yes\nAction: + multiplier\nAction Input: 2,6\nObservation: 12\nThought: Do I need to use a + tool? Yes\nAction: multiplier\nAction Input: 12,3\nObservation: 36\nThought: + "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1604' + content-type: + - application/json + cookie: + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRJxnthP0NqebBVQ5TRxHkM8ZBmp\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410505,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + 36\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 373,\n \"completion_tokens\": + 15,\n \"total_tokens\": 388\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8407383b9d2f4cf1-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:21:48 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2463' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299625' + x-ratelimit-remaining-tokens_usage_based: + - '299625' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 74ms + x-ratelimit-reset-tokens_usage_based: + - 74ms + x-request-id: + - bf53e87deae98b7493aac8ab51501f7b + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate the result + of 2 times 6 times 3 and the result of 3 times 3. The AI responds that the results + are 36 and 9 respectively.\n\nNew lines of conversation:\nHuman: What is 2 times + 6 times 3? Return only the number\nAI: 36\n\nNew summary:"}], "model": "gpt-4", + "n": 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1058' + content-type: + - application/json + cookie: + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRK0b5C1SRY6Bv7O7ubdcAw8bU3j\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410508,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI to calculate the + result of 2 times 6 times 3 twice and the result of 3 times 3 once. The AI consistently + responds that the result of 2 times 6 times 3 is 36 and that the result of 3 + times 3 is 9.\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\": + 63,\n \"total_tokens\": 262\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8407384cdf434cf1-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:21:53 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '4310' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299750' + x-ratelimit-remaining-tokens_usage_based: + - '299750' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 49ms + x-ratelimit-reset-tokens_usage_based: + - 49ms + x-request-id: + - e7fb8ee53162a5c77a824931043cbf30 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together.\n The input to this tool should be + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [multiplier], just the name.\nAction Input: + the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```This is the summary of your work so far:\nThe human + asks the AI to calculate the result of 2 times 6 times 3 twice and the result + of 3 times 3 once. The AI consistently responds that the result of 2 times 6 + times 3 is 36 and that the result of 3 times 3 is 9.Begin! This is VERY important + to you, your job depends on it!\n\nCurrent Task: What is 2 times 6?\n"}], "model": + "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1435' + content-type: + - application/json + cookie: + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRK5FDSCiOdGy00lF0We4EZ4Zeni\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410513,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: + multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 323,\n \"completion_tokens\": + 23,\n \"total_tokens\": 346\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8407386f6e1a4cf1-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:21:56 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2749' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299665' + x-ratelimit-remaining-tokens_usage_based: + - '299665' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 66ms + x-ratelimit-reset-tokens_usage_based: + - 66ms + x-request-id: + - 7b22ab6e07d1b18776df790053aba9c1 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together.\n The input to this tool should be + a comma separated list of numbers of\n length two and ONLY TWO, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [multiplier], just the name.\nAction Input: + the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```This is the summary of your work so far:\nThe human + asks the AI to calculate the result of 2 times 6 times 3 twice and the result + of 3 times 3 once. The AI consistently responds that the result of 2 times 6 + times 3 is 36 and that the result of 3 times 3 is 9.Begin! This is VERY important + to you, your job depends on it!\n\nCurrent Task: What is 2 times 6?\nThought: + Do I need to use a tool? Yes\nAction: multiplier\nAction Input: 2,6\nObservation: + 0\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": + false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1538' + content-type: + - application/json + cookie: + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRK9wdZjqEMBEBJkFVXZnEPO9Du8\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410517,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"I need to use a tool? No\\nFinal Answer: + 0\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 356,\n \"completion_tokens\": + 24,\n \"total_tokens\": 380\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 840738826a464cf1-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:22:00 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2865' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299640' + x-ratelimit-remaining-tokens_usage_based: + - '299640' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 71ms + x-ratelimit-reset-tokens_usage_based: + - 71ms + x-request-id: + - 6c1f7abfa824bdee4dfb6e526209617b + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate the result + of 2 times 6 times 3 twice and the result of 3 times 3 once. The AI consistently + responds that the result of 2 times 6 times 3 is 36 and that the result of 3 + times 3 is 9.\n\nNew lines of conversation:\nHuman: What is 2 times 6?\nAI: + 0\n\nNew summary:"}], "model": "gpt-4", "n": 1, + "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1117' + content-type: + - application/json + cookie: + - __cf_bm=5qK.mmc9Y_x7VffBrseOL2OdOh3WdRTDTSRhVmWzOfE-1704410483-1-AbUJL6v8HNNUrySCuhln2iL8N8w0sixnhK1rJRUPLq8BoioAJV/sz+TQMW4FOE7lsSLkHNPcFe4xCeblKhdufmg=; + _cfuvid=TnW1ck5LHa2beu3C2zxu2azbY0X51WdRJUhPbD.P85Q-1704410483636-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRKCG7qkX0fUl2WS85Tj8AhK4xBg\",\n \"object\": + \"chat.completion\",\n \"created\": 1704410520,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI to calculate various + math problems: the result of 2 times 6 times 3 twice, the result of 3 times + 3 once, and the result of 2 times 6 once. The AI consistently responds with + correct answers: the result of 2 times 6 times 3 is 36, the result of 3 times + 3 is 9, and the result of 2 times 6 is 12.\"\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 221,\n \"completion_tokens\": 93,\n \"total_tokens\": 314\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 840738978f194cf1-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:22:05 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '4721' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299735' + x-ratelimit-remaining-tokens_usage_based: + - '299735' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 52ms + x-ratelimit-reset-tokens_usage_based: + - 52ms + x-request-id: + - 9f90c39dbd986cc114253ea83d213309 http_version: HTTP/1.1 status_code: 200 version: 1 diff --git a/tests/cassettes/test_cache_hitting_between_agents.yaml b/tests/cassettes/test_cache_hitting_between_agents.yaml index f73bdd468..608a89b6c 100644 --- a/tests/cassettes/test_cache_hitting_between_agents.yaml +++ b/tests/cassettes/test_cache_hitting_between_agents.yaml @@ -24,10 +24,10 @@ interactions: input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: - [your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin! - This is VERY important to you, your job depends on it!\n\nCurrent Task: What - is 2 tims 6?\n\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": - false, "temperature": 0.7}' + [your response here]\n```This is the summary of your work so far:\nBegin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + tims 6? Return only the number.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], + "stream": false, "temperature": 0.7}' headers: accept: - application/json @@ -36,7 +36,7 @@ interactions: connection: - keep-alive content-length: - - '2215' + - '2225' content-type: - application/json cookie: @@ -62,18 +62,18 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8bFlFR80bKQQzwjFzAICpcBT2G3s0\",\n \"object\": - \"chat.completion\",\n \"created\": 1703889413,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRVlXc53iJRMHZgEgsHLyQnTcmnQ\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411237,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: - multiplier\\nAction Input: 2,6\\n\"\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 484,\n \"completion_tokens\": - 24,\n \"total_tokens\": 508\n },\n \"system_fingerprint\": null\n}\n" + multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 486,\n \"completion_tokens\": + 23,\n \"total_tokens\": 509\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d5863e9a050301-GRU + - 84074a19fb05520a-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -83,14 +83,14 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 22:36:54 GMT + - Thu, 04 Jan 2024 23:34:00 GMT Server: - cloudflare Set-Cookie: - - __cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc=; - path=/; expires=Fri, 29-Dec-23 23:06:54 GMT; domain=.api.openai.com; HttpOnly; + - __cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo=; + path=/; expires=Fri, 05-Jan-24 00:04:00 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000; + - _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Transfer-Encoding: - chunked @@ -103,7 +103,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1227' + - '2098' openai-version: - '2020-10-01' strict-transport-security: @@ -117,17 +117,17 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299483' + - '299480' x-ratelimit-remaining-tokens_usage_based: - - '299483' + - '299480' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 103ms + - 104ms x-ratelimit-reset-tokens_usage_based: - - 103ms + - 104ms x-request-id: - - 938270aa00d199e6be67525b6e3d6eba + - 98c413fa0e0bc84e3d468546e3cd2f2f http_version: HTTP/1.1 status_code: 200 - request: @@ -155,11 +155,11 @@ interactions: input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: - [your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin! - This is VERY important to you, your job depends on it!\n\nCurrent Task: What - is 2 tims 6?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction - Input: 2,6\n\nObservation: 12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": - ["\nObservation"], "stream": false, "temperature": 0.7}' + [your response here]\n```This is the summary of your work so far:\nBegin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + tims 6? Return only the number.\nThought: Do I need to use a tool? Yes\nAction: + multiplier\nAction Input: 2,6\nObservation: 12\nThought: "}], "model": "gpt-4", + "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' headers: accept: - application/json @@ -168,12 +168,12 @@ interactions: connection: - keep-alive content-length: - - '2321' + - '2329' content-type: - application/json cookie: - - _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000; - __cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc= + - _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000; + __cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo= host: - api.openai.com user-agent: @@ -195,18 +195,18 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8bFlGBZrFqbUBA6wWFIW1k7CrvOMc\",\n \"object\": - \"chat.completion\",\n \"created\": 1703889414,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRVoc5CcZPD8nFzRBy2gFPp8ve6v\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411240,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: - 2 times 6 is 12.\"\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 517,\n \"completion_tokens\": - 22,\n \"total_tokens\": 539\n },\n \"system_fingerprint\": null\n}\n" + 12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 519,\n \"completion_tokens\": + 15,\n \"total_tokens\": 534\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d586496c140301-GRU + - 84074a2afdf6520a-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -216,7 +216,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 22:36:59 GMT + - Thu, 04 Jan 2024 23:34:02 GMT Server: - cloudflare Transfer-Encoding: @@ -230,7 +230,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '2377' + - '2037' openai-version: - '2020-10-01' strict-transport-security: @@ -244,17 +244,17 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299458' + - '299455' x-ratelimit-remaining-tokens_usage_based: - - '299458' + - '299455' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 108ms + - 109ms x-ratelimit-reset-tokens_usage_based: - - 108ms + - 109ms x-request-id: - - ab3bab4c142330d66869ccff39de5738 + - d870981f801ad59b592bfd906aa59732 http_version: HTTP/1.1 status_code: 200 - request: @@ -268,8 +268,8 @@ interactions: the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good because it will help humans reach their full potential.\nEND OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What - is 2 tims 6?\nAI: 2 times 6 is 12.\n\nNew summary:"}], "model": "gpt-4", "n": - 1, "stream": false, "temperature": 0.7}' + is 2 tims 6? Return only the number.\nAI: 12\n\nNew summary:"}], "model": "gpt-4", + "n": 1, "stream": false, "temperature": 0.7}' headers: accept: - application/json @@ -278,12 +278,12 @@ interactions: connection: - keep-alive content-length: - - '885' + - '895' content-type: - application/json cookie: - - _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000; - __cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc= + - _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000; + __cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo= host: - api.openai.com user-agent: @@ -305,19 +305,19 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8bFlMHhxpCjHkQymfxQ5D8WBZkclA\",\n \"object\": - \"chat.completion\",\n \"created\": 1703889420,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRVqwa7QwjlYpBCg5xaUZEWTIMoe\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411242,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"The human asks the AI for the product - of 2 times 6, and the AI responds that it is 12.\"\n },\n \"logprobs\": + \"assistant\",\n \"content\": \"The human asks the AI to calculate 2 + times 6, and the AI responds with the answer, 12.\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": - 156,\n \"completion_tokens\": 25,\n \"total_tokens\": 181\n },\n \"system_fingerprint\": + 155,\n \"completion_tokens\": 24,\n \"total_tokens\": 179\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d5866a6c360301-GRU + - 84074a3aee55520a-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -327,7 +327,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 22:37:01 GMT + - Thu, 04 Jan 2024 23:34:04 GMT Server: - cloudflare Transfer-Encoding: @@ -341,7 +341,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1468' + - '1160' openai-version: - '2020-10-01' strict-transport-security: @@ -355,9 +355,9 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299794' + - '299791' x-ratelimit-remaining-tokens_usage_based: - - '299794' + - '299791' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: @@ -365,7 +365,7 @@ interactions: x-ratelimit-reset-tokens_usage_based: - 41ms x-request-id: - - e6e04fb8a12fc2288d6a3bd0b4480ab0 + - f5f275f8bbce5e3a96781845bea91b8c http_version: HTTP/1.1 status_code: 200 - request: @@ -384,9 +384,9 @@ interactions: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: - [your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin! - This is VERY important to you, your job depends on it!\n\nCurrent Task: What - is 2 times 6?\n\nThis is the context you are working with:\n2 times 6 is 12.\n\n"}], + [your response here]\n```This is the summary of your work so far:\nBegin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + times 6? Return only the number.\n\nThis is the context you are working with:\n12\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' headers: @@ -397,11 +397,11 @@ interactions: connection: - keep-alive content-length: - - '1518' + - '1514' content-type: - application/json cookie: - - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000 + - _cfuvid=BMxGwK4wPoN6Cq5150swBY7QbtTvmWU2.p39x.cUidg-1703932144438-0-604800000 host: - api.openai.com user-agent: @@ -423,18 +423,18 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8bFlOAG2g3FwravPGs5nQmnA8wpf1\",\n \"object\": - \"chat.completion\",\n \"created\": 1703889422,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRVst73yaZUVvqi8MkAdhYgxy8Yp\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411244,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 322,\n \"completion_tokens\": - 23,\n \"total_tokens\": 345\n },\n \"system_fingerprint\": null\n}\n" + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 318,\n \"completion_tokens\": + 23,\n \"total_tokens\": 341\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d586773aea77c0-GRU + - 84074a4539a1a4dd-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -444,14 +444,14 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 22:37:04 GMT + - Thu, 04 Jan 2024 23:34:06 GMT Server: - cloudflare Set-Cookie: - - __cf_bm=NTFlpt52iEoCg0Pkx5.1jxp.b3GIrmzDorPoCjgwA1c-1703889424-1-AcnqI2v1g/4ArTSHF6F4yC9cQd8KWJUiSRlY3mTNPF+6P6fectfBIvD544RQw/zhEY+z/eZ5pw4t/Baew653jtw=; - path=/; expires=Fri, 29-Dec-23 23:07:04 GMT; domain=.api.openai.com; HttpOnly; + - __cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk=; + path=/; expires=Fri, 05-Jan-24 00:04:06 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=yTJHDMg7VYHMEKTSaPhpQp_5NZ3Xw1rIS8dQw4LmQMk-1703889424692-0-604800000; + - _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Transfer-Encoding: - chunked @@ -464,7 +464,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '2511' + - '2183' openai-version: - '2020-10-01' strict-transport-security: @@ -488,7 +488,126 @@ interactions: x-ratelimit-reset-tokens_usage_based: - 70ms x-request-id: - - b86341441fa500dc373240b329cf5446 + - 5e830a8376085c6ce2df403dbecb5a8f + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''re + an expert researcher, specialized in technology, software engineering, AI and + startups. You work as a freelancer and is now working on doing research and + analysis for a new customer.\n\nYour personal goal is: Make the best research + and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access + to the following tools:\n\nmultiplier: multiplier(numbers) -> float - Useful + for when you need to multiply two numbers together.\n The input to this + tool should be a comma separated list of numbers of\n length two, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [multiplier], just the name.\nAction Input: + the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```This is the summary of your work so far:\nBegin! This + is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 + times 6? Return only the number.\n\nThis is the context you are working with:\n12\nThought: + Do I need to use a tool? Yes\nAction: multiplier\nAction Input: 2,6\nObservation: + 12\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": + false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1618' + content-type: + - application/json + cookie: + - _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000; + __cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRVvTsWLclXQnmY67VWcdxVqY3ul\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411247,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + 12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 351,\n \"completion_tokens\": + 15,\n \"total_tokens\": 366\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 84074a55f935a4dd-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:34:08 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '1539' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299621' + x-ratelimit-remaining-tokens_usage_based: + - '299621' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 75ms + x-ratelimit-reset-tokens_usage_based: + - 75ms + x-request-id: + - bdbe02bf0b83c88f824c067b27e5ce08 http_version: HTTP/1.1 status_code: 200 - request: @@ -502,9 +621,9 @@ interactions: the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good because it will help humans reach their full potential.\nEND OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What - is 2 times 6?\n\nThis is the context you are working with:\n2 times 6 is 12.\nAI: - 12\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": - 0.7}' + is 2 times 6? Return only the number.\n\nThis is the context you are working + with:\n12\nAI: 12\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, + "temperature": 0.7}' headers: accept: - application/json @@ -513,12 +632,12 @@ interactions: connection: - keep-alive content-length: - - '935' + - '945' content-type: - application/json cookie: - - _cfuvid=yTJHDMg7VYHMEKTSaPhpQp_5NZ3Xw1rIS8dQw4LmQMk-1703889424692-0-604800000; - __cf_bm=NTFlpt52iEoCg0Pkx5.1jxp.b3GIrmzDorPoCjgwA1c-1703889424-1-AcnqI2v1g/4ArTSHF6F4yC9cQd8KWJUiSRlY3mTNPF+6P6fectfBIvD544RQw/zhEY+z/eZ5pw4t/Baew653jtw= + - _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000; + __cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk= host: - api.openai.com user-agent: @@ -540,18 +659,19 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8bFlQVqyX43MFLq79thTQ8UaZZ1xD\",\n \"object\": - \"chat.completion\",\n \"created\": 1703889424,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRVxzDne3c08p3cTarxVS8coZYTY\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411249,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"The human asks the AI what is 2 times - 6, and the AI responds with 12.\"\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 166,\n \"completion_tokens\": - 21,\n \"total_tokens\": 187\n },\n \"system_fingerprint\": null\n}\n" + \"assistant\",\n \"content\": \"The human asks the AI to calculate 2 + times 6, and the AI responds with the correct answer, 12.\"\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 165,\n \"completion_tokens\": 25,\n \"total_tokens\": 190\n },\n \"system_fingerprint\": + null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d58688eda777c0-GRU + - 84074a610867a4dd-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -561,7 +681,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 22:37:06 GMT + - Thu, 04 Jan 2024 23:34:12 GMT Server: - cloudflare Transfer-Encoding: @@ -575,7 +695,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1152' + - '2856' openai-version: - '2020-10-01' strict-transport-security: @@ -589,17 +709,17 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299782' + - '299780' x-ratelimit-remaining-tokens_usage_based: - - '299782' + - '299780' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 43ms + - 44ms x-ratelimit-reset-tokens_usage_based: - - 43ms + - 44ms x-request-id: - - d86894b3054720d2053d5bfef884d985 + - bc1098a0a70b65dd693837175bdd9c7a http_version: HTTP/1.1 status_code: 200 - request: @@ -636,12 +756,12 @@ interactions: to co-worker], just the name.\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: - Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis - is the summary of your work so far:\n The human asks the AI for the product - of 2 times 6, and the AI responds that it is 12.\nBegin! This is VERY important - to you, your job depends on it!\n\nCurrent Task: What is 2 tims 6?\n\n"}], "model": - "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": - 0.7}' + Do I need to use a tool? No\nFinal Answer: [your response here]\n```This is + the summary of your work so far:\nThe human asks the AI to calculate 2 times + 6, and the AI responds with the answer, 12.Begin! This is VERY important to + you, your job depends on it!\n\nCurrent Task: What is 2 tims 6? Return only + the number.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": + false, "temperature": 0.7}' headers: accept: - application/json @@ -650,12 +770,12 @@ interactions: connection: - keep-alive content-length: - - '3088' + - '3098' content-type: - application/json cookie: - - _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000; - __cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc= + - _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000; + __cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo= host: - api.openai.com user-agent: @@ -677,8 +797,8 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8bFlSjjmk16fcEx4qjS8HvNxbn3ky\",\n \"object\": - \"chat.completion\",\n \"created\": 1703889426,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRW0twTa8zcVszzkf4rHaJtBQyuE\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411252,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\": @@ -688,7 +808,7 @@ interactions: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d58691fc2e0301-GRU + - 84074a768894016c-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -698,7 +818,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 22:37:07 GMT + - Thu, 04 Jan 2024 23:34:13 GMT Server: - cloudflare Transfer-Encoding: @@ -712,7 +832,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1307' + - '1169' openai-version: - '2020-10-01' strict-transport-security: @@ -726,17 +846,156 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299275' + - '299272' x-ratelimit-remaining-tokens_usage_based: - - '299275' + - '299272' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 144ms + - 145ms x-ratelimit-reset-tokens_usage_based: - - 144ms + - 145ms x-request-id: - - e25c77d8a956e2d403a80795d27446ed + - b486103e6e3ed65ba15411a1fcd1534a + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long + time CEO of a content creation agency with a Senior Writer on the team. You''re + now working on a new project and want to make sure the content produced is amazing.\n\nYour + personal goal is: Make sure the writers in your company produce amazing content.\n\nTOOLS:\n------\nYou + have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float + - Useful for when you need to multiply two numbers together.\n The input + to this tool should be a comma separated list of numbers of\n length + two, representing the two numbers you want to multiply together.\n For + example, `1,2` would be the input if you wanted to multiply 1 by 2.\nDelegate + work to co-worker: Useful to delegate a specific task to one of the\n\t\t\t\tfollowing + co-workers: [CEO, Researcher].\n\t\t\t\tThe input to this tool should be a pipe + (|) separated text of length\n\t\t\t\tthree, representing the role you want + to delegate it to, the task and\n\t\t\t\tinformation necessary. For example, + `coworker|task|information`.\n\nAsk question to co-worker: Useful to ask a question, + opinion or take from on\n\t\t\t\tof the following co-workers: [CEO, Researcher].\n\t\t\t\tThe + input to this tool should be a pipe (|) separated text of length\n\t\t\t\tthree, + representing the role you want to ask it to, the question and\n\t\t\t\tinformation + necessary. For example, `coworker|question|information`.\n\nDelegate work to + co-worker: Useful to delegate a specific task to one of the\n\t\t\t\tfollowing + co-workers: [CEO, Researcher].\n\t\t\t\tThe input to this tool should be a pipe + (|) separated text of length\n\t\t\t\tthree, representing the role you want + to delegate it to, the task and\n\t\t\t\tinformation necessary. For example, + `coworker|task|information`.\n\nAsk question to co-worker: Useful to ask a question, + opinion or take from on\n\t\t\t\tof the following co-workers: [CEO, Researcher].\n\t\t\t\tThe + input to this tool should be a pipe (|) separated text of length\n\t\t\t\tthree, + representing the role you want to ask it to, the question and\n\t\t\t\tinformation + necessary. For example, `coworker|question|information`.\n\n\nTo use a tool, + please use the exact following format:\n\n```\nThought: Do I need to use a tool? + Yes\nAction: the action to take, should be one of [multiplier, Delegate work + to co-worker, Ask question to co-worker, Delegate work to co-worker, Ask question + to co-worker], just the name.\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```This is + the summary of your work so far:\nThe human asks the AI to calculate 2 times + 6, and the AI responds with the answer, 12.Begin! This is VERY important to + you, your job depends on it!\n\nCurrent Task: What is 2 tims 6? Return only + the number.\n\nI just used the multiplier tool with input 2,6. So I already + know the result of that.\nObservation: Invalid or incomplete response\nThought: + "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '3241' + content-type: + - application/json + cookie: + - _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000; + __cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRW1CmfWI2T4pqcjA32JkFO2d631\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411253,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + 12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 721,\n \"completion_tokens\": + 15,\n \"total_tokens\": 736\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 84074a801ca8016c-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:34:15 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '1961' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299236' + x-ratelimit-remaining-tokens_usage_based: + - '299236' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 152ms + x-ratelimit-reset-tokens_usage_based: + - 152ms + x-request-id: + - 555ce73ac9d4daed7f521005a3d040e0 http_version: HTTP/1.1 status_code: 200 - request: @@ -749,10 +1008,10 @@ interactions: help humans reach their full potential.\n\nNew summary:\nThe human asks what the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good because it will help humans reach their full potential.\nEND - OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI for the product of 2 times - 6, and the AI responds that it is 12.\n\nNew lines of conversation:\nHuman: - What is 2 tims 6?\nAI: 12\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": - false, "temperature": 0.7}' + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 2 times 6, + and the AI responds with the answer, 12.\n\nNew lines of conversation:\nHuman: + What is 2 tims 6? Return only the number.\nAI: 12\n\nNew summary:"}], "model": + "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' headers: accept: - application/json @@ -761,12 +1020,12 @@ interactions: connection: - keep-alive content-length: - - '957' + - '981' content-type: - application/json cookie: - - _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000; - __cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc= + - _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000; + __cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo= host: - api.openai.com user-agent: @@ -788,19 +1047,19 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8bFlTYmUO6Wh3mbgtPshKpQqqDxgd\",\n \"object\": - \"chat.completion\",\n \"created\": 1703889427,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRW49WMzFv360XBT2uhgJPnSHg2O\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411256,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"The human asks the AI for the product - of 2 times 6, and the AI responds that it is 12, confirming this when asked - again.\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n - \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 175,\n \"completion_tokens\": - 31,\n \"total_tokens\": 206\n },\n \"system_fingerprint\": null\n}\n" + \"assistant\",\n \"content\": \"The human asks the AI to calculate 2 + times 6 twice, and both times the AI correctly responds with the answer, 12.\"\n + \ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n + \ ],\n \"usage\": {\n \"prompt_tokens\": 179,\n \"completion_tokens\": + 28,\n \"total_tokens\": 207\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d5869baf8a0301-GRU + - 84074a8dfccf016c-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -810,7 +1069,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 22:37:09 GMT + - Thu, 04 Jan 2024 23:34:18 GMT Server: - cloudflare Transfer-Encoding: @@ -824,7 +1083,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1618' + - '2192' openai-version: - '2020-10-01' strict-transport-security: @@ -838,17 +1097,17 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299775' + - '299770' x-ratelimit-remaining-tokens_usage_based: - - '299775' + - '299770' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 44ms + - 46ms x-ratelimit-reset-tokens_usage_based: - - 44ms + - 46ms x-request-id: - - b70f47e489a1fefedc547c87e41f7dae + - f5dda6e21a06ac9af1a14b27c551c3c1 http_version: HTTP/1.1 status_code: 200 - request: @@ -867,11 +1126,12 @@ interactions: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: - [your response here]\n```\n\t\tThis is the summary of your work so far:\n The - human asks the AI what is 2 times 6, and the AI responds with 12.\nBegin! This - is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2 - times 6?\n\nThis is the context you are working with:\n12\n\n"}], "model": "gpt-4", - "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' + [your response here]\n```This is the summary of your work so far:\nThe human + asks the AI to calculate 2 times 6, and the AI responds with the correct answer, + 12.Begin! This is VERY important to you, your job depends on it!\n\nCurrent + Task: What is 2 times 6? Return only the number.\n\nThis is the context you + are working with:\n12\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], + "stream": false, "temperature": 0.7}' headers: accept: - application/json @@ -880,12 +1140,12 @@ interactions: connection: - keep-alive content-length: - - '1573' + - '1608' content-type: - application/json cookie: - - _cfuvid=yTJHDMg7VYHMEKTSaPhpQp_5NZ3Xw1rIS8dQw4LmQMk-1703889424692-0-604800000; - __cf_bm=NTFlpt52iEoCg0Pkx5.1jxp.b3GIrmzDorPoCjgwA1c-1703889424-1-AcnqI2v1g/4ArTSHF6F4yC9cQd8KWJUiSRlY3mTNPF+6P6fectfBIvD544RQw/zhEY+z/eZ5pw4t/Baew653jtw= + - _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000; + __cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk= host: - api.openai.com user-agent: @@ -907,18 +1167,18 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8bFlVgnFkN5XO7X3qLOx96HX1pUjS\",\n \"object\": - \"chat.completion\",\n \"created\": 1703889429,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRW6CHiFSw6vFRNx1T4uAmrAW8dK\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411258,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 337,\n \"completion_tokens\": - 23,\n \"total_tokens\": 360\n },\n \"system_fingerprint\": null\n}\n" + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 342,\n \"completion_tokens\": + 23,\n \"total_tokens\": 365\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d586a76ee577c0-GRU + - 84074a9ddedf01c1-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -928,7 +1188,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 22:37:11 GMT + - Thu, 04 Jan 2024 23:34:19 GMT Server: - cloudflare Transfer-Encoding: @@ -942,7 +1202,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1612' + - '1023' openai-version: - '2020-10-01' strict-transport-security: @@ -956,17 +1216,137 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299634' + - '299624' x-ratelimit-remaining-tokens_usage_based: - - '299634' + - '299624' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 73ms + - 75ms x-ratelimit-reset-tokens_usage_based: - - 73ms + - 75ms x-request-id: - - 739f95896087931128c8e260b7d3cf02 + - f28da711e3c1ff3e058def7cf176f30a + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''re + an expert researcher, specialized in technology, software engineering, AI and + startups. You work as a freelancer and is now working on doing research and + analysis for a new customer.\n\nYour personal goal is: Make the best research + and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access + to the following tools:\n\nmultiplier: multiplier(numbers) -> float - Useful + for when you need to multiply two numbers together.\n The input to this + tool should be a comma separated list of numbers of\n length two, representing + the two numbers you want to multiply together.\n For example, `1,2` would + be the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [multiplier], just the name.\nAction Input: + the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```This is the summary of your work so far:\nThe human + asks the AI to calculate 2 times 6, and the AI responds with the correct answer, + 12.Begin! This is VERY important to you, your job depends on it!\n\nCurrent + Task: What is 2 times 6? Return only the number.\n\nThis is the context you + are working with:\n12\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction + Input: 2,6\nObservation: 12\nThought: "}], "model": "gpt-4", "n": 1, "stop": + ["\nObservation"], "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1712' + content-type: + - application/json + cookie: + - _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000; + __cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.1 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.1 + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.11.7 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + content: "{\n \"id\": \"chatcmpl-8dRW7NNdda8hGNJVbrkPRDzPdO7dZ\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411259,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + 12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 375,\n \"completion_tokens\": + 15,\n \"total_tokens\": 390\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 84074aa5fb2e01c1-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Thu, 04 Jan 2024 23:34:21 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '1280' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299599' + x-ratelimit-remaining-tokens_usage_based: + - '299599' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 80ms + x-ratelimit-reset-tokens_usage_based: + - 80ms + x-request-id: + - 888c0944f22db01f2ac38963b94c765d http_version: HTTP/1.1 status_code: 200 - request: @@ -979,10 +1359,11 @@ interactions: help humans reach their full potential.\n\nNew summary:\nThe human asks what the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good because it will help humans reach their full potential.\nEND - OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI what is 2 times 6, and - the AI responds with 12.\n\nNew lines of conversation:\nHuman: What is 2 times - 6?\n\nThis is the context you are working with:\n12\nAI: 12\n\nNew summary:"}], - "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 2 times 6, + and the AI responds with the correct answer, 12.\n\nNew lines of conversation:\nHuman: + What is 2 times 6? Return only the number.\n\nThis is the context you are working + with:\n12\nAI: 12\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, + "temperature": 0.7}' headers: accept: - application/json @@ -991,12 +1372,12 @@ interactions: connection: - keep-alive content-length: - - '990' + - '1039' content-type: - application/json cookie: - - _cfuvid=yTJHDMg7VYHMEKTSaPhpQp_5NZ3Xw1rIS8dQw4LmQMk-1703889424692-0-604800000; - __cf_bm=NTFlpt52iEoCg0Pkx5.1jxp.b3GIrmzDorPoCjgwA1c-1703889424-1-AcnqI2v1g/4ArTSHF6F4yC9cQd8KWJUiSRlY3mTNPF+6P6fectfBIvD544RQw/zhEY+z/eZ5pw4t/Baew653jtw= + - _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000; + __cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk= host: - api.openai.com user-agent: @@ -1018,19 +1399,19 @@ interactions: method: POST uri: https://api.openai.com/v1/chat/completions response: - content: "{\n \"id\": \"chatcmpl-8bFlXEDmlitriA40K77evvaqJrfZ4\",\n \"object\": - \"chat.completion\",\n \"created\": 1703889431,\n \"model\": \"gpt-4-0613\",\n + content: "{\n \"id\": \"chatcmpl-8dRW9lh9rXOLN3eN1fhXjtc7JnCX8\",\n \"object\": + \"chat.completion\",\n \"created\": 1704411261,\n \"model\": \"gpt-4-0613\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"The human asks the AI what is 2 times - 6, and the AI consistently responds with 12.\"\n },\n \"logprobs\": - null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": - 181,\n \"completion_tokens\": 22,\n \"total_tokens\": 203\n },\n \"system_fingerprint\": - null\n}\n" + \"assistant\",\n \"content\": \"The human asks the AI to calculate 2 + times 6 twice, and both times the AI responds with the correct answer, 12.\"\n + \ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n + \ ],\n \"usage\": {\n \"prompt_tokens\": 190,\n \"completion_tokens\": + 28,\n \"total_tokens\": 218\n },\n \"system_fingerprint\": null\n}\n" headers: CF-Cache-Status: - DYNAMIC CF-RAY: - - 83d586b2fbd877c0-GRU + - 84074aaf99a001c1-GRU Cache-Control: - no-cache, must-revalidate Connection: @@ -1040,7 +1421,7 @@ interactions: Content-Type: - application/json Date: - - Fri, 29 Dec 2023 22:37:13 GMT + - Thu, 04 Jan 2024 23:34:24 GMT Server: - cloudflare Transfer-Encoding: @@ -1054,7 +1435,7 @@ interactions: openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - - '1836' + - '2998' openai-version: - '2020-10-01' strict-transport-security: @@ -1068,17 +1449,17 @@ interactions: x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - - '299769' + - '299755' x-ratelimit-remaining-tokens_usage_based: - - '299769' + - '299755' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - - 46ms + - 48ms x-ratelimit-reset-tokens_usage_based: - - 46ms + - 48ms x-request-id: - - 501523f2159a6ae7b2dbb409cf5748a1 + - 9cbb02f45069e8274ca90e4ee7e690db http_version: HTTP/1.1 status_code: 200 version: 1 diff --git a/tests/crew_test.py b/tests/crew_test.py index 77f596c99..88a7b824f 100644 --- a/tests/crew_test.py +++ b/tests/crew_test.py @@ -241,12 +241,12 @@ def test_cache_hitting_between_agents(): tasks = [ Task( - description="What is 2 tims 6?", + description="What is 2 tims 6? Return only the number.", tools=[multiplier], agent=ceo, ), Task( - description="What is 2 times 6?", + description="What is 2 times 6? Return only the number.", tools=[multiplier], agent=researcher, ),