andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 16:48:30 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
498a9e6e6865568f136b1afad78e19dbd17ae8e9
crewAI/tests/cassettes/test_cache_hitting_between_agents.yaml
João Moura 59e51f18fd updating tests
2024-09-23 03:58:41 -03:00

500 lines
22 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''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.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) ->
Any\nTool Description: multiplier(first_number: ''integer'', second_number:
''integer'') - Useful for when you need to multiply two numbers together. \nTool
Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''},
''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\nTool
Name: Delegate work to coworker(task: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Delegate a specific task to one of the
following coworkers: Researcher\nThe input to this tool should be the coworker,
the task you want them to do, and ALL necessary context to execute the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''task'': {''title'':
''Task'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool Name: Ask question
to coworker(question: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool
Description: Ask a specific question to one of the following coworkers: Researcher\nThe
input to this tool should be the coworker, the question you have for them, and
ALL necessary context to ask the question properly, they know nothing about
the question, so share absolute everything you know, don''t reference things
but instead explain them.\nTool Arguments: {''question'': {''title'': ''Question'',
''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''},
''coworker'': {''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'':
''Kwargs'', ''type'': ''object''}}\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [multiplier, Delegate work to coworker, Ask question to coworker], just
the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: What is 2 tims 6? Return only the number.\n\nThis is the expect
criteria for your final answer: the result of multiplication\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3082'
content-type:
- application/json
cookie:
- __cf_bm=hYfEMfBWpIoRPjx9ZBZg6DVeMOMr1IZt9ioup8yWZs0-1727072673-1.0.1.1-Ro7GCLuWS0K5ob0mSTYSmovONKNyxsK6oSA5io_Vwqhe6P0G7Ow4CuZUaWAaCdFGQUd7XZiFH0mI_sQC3uqe0g;
_cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
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-AAWoSkhll1ukgv03urvKaaxiLPcjU\",\n \"object\":
\"chat.completion\",\n \"created\": 1727072776,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To find the result of 2 times 6, I need
to use the multiplier tool.\\n\\nAction: multiplier\\nAction Input: {\\\"first_number\\\":
2, \\\"second_number\\\": 6}\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
691,\n \"completion_tokens\": 40,\n \"total_tokens\": 731,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c787653ca4ea4ee-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:26:16 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '573'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999244'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_63fe38519b729d7297cac4c45506cd8d
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''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.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) ->
Any\nTool Description: multiplier(first_number: ''integer'', second_number:
''integer'') - Useful for when you need to multiply two numbers together. \nTool
Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''},
''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\nTool
Name: Delegate work to coworker(task: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Delegate a specific task to one of the
following coworkers: Researcher\nThe input to this tool should be the coworker,
the task you want them to do, and ALL necessary context to execute the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''task'': {''title'':
''Task'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool Name: Ask question
to coworker(question: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool
Description: Ask a specific question to one of the following coworkers: Researcher\nThe
input to this tool should be the coworker, the question you have for them, and
ALL necessary context to ask the question properly, they know nothing about
the question, so share absolute everything you know, don''t reference things
but instead explain them.\nTool Arguments: {''question'': {''title'': ''Question'',
''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''},
''coworker'': {''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'':
''Kwargs'', ''type'': ''object''}}\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [multiplier, Delegate work to coworker, Ask question to coworker], just
the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: What is 2 tims 6? Return only the number.\n\nThis is the expect
criteria for your final answer: the result of multiplication\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "user", "content": "To find
the result of 2 times 6, I need to use the multiplier tool.\n\nAction: multiplier\nAction
Input: {\"first_number\": 2, \"second_number\": 6}\nObservation: 12"}], "model":
"gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3280'
content-type:
- application/json
cookie:
- __cf_bm=hYfEMfBWpIoRPjx9ZBZg6DVeMOMr1IZt9ioup8yWZs0-1727072673-1.0.1.1-Ro7GCLuWS0K5ob0mSTYSmovONKNyxsK6oSA5io_Vwqhe6P0G7Ow4CuZUaWAaCdFGQUd7XZiFH0mI_sQC3uqe0g;
_cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
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-AAWoTPb04kSFlAeip2nigfFMvxkhz\",\n \"object\":
\"chat.completion\",\n \"created\": 1727072777,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
739,\n \"completion_tokens\": 14,\n \"total_tokens\": 753,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7876590cfaa4ee-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:26:17 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '252'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999204'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_2d7cb3fea4d1b1153220639498f8af63
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''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.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number:
''integer'', second_number: ''integer'') - Useful for when you need to multiply
two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First
Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'',
''type'': ''integer''}}\n\nUse the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, only one name of
[multiplier], just the name, exactly as it''s written.\nAction Input: the input
to the action, just a simple python dictionary, enclosed in curly braces, using
\" to wrap keys and values.\nObservation: the result of the action\n\nOnce all
necessary information is gathered:\n\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n"}, {"role": "user",
"content": "\nCurrent Task: What is 2 times 6? Return only the number.\n\nThis
is the expect criteria for your final answer: the result of multiplication\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n12\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1763'
content-type:
- application/json
cookie:
- __cf_bm=hYfEMfBWpIoRPjx9ZBZg6DVeMOMr1IZt9ioup8yWZs0-1727072673-1.0.1.1-Ro7GCLuWS0K5ob0mSTYSmovONKNyxsK6oSA5io_Vwqhe6P0G7Ow4CuZUaWAaCdFGQUd7XZiFH0mI_sQC3uqe0g;
_cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
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-AAWoT8kckVxJt9fgHB0THxkfbI3uD\",\n \"object\":
\"chat.completion\",\n \"created\": 1727072777,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to use the multiplier
tool to calculate 2 times 6.\\n\\nAction: multiplier\\nAction Input: {\\\"first_number\\\":
2, \\\"second_number\\\": 6}\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
365,\n \"completion_tokens\": 38,\n \"total_tokens\": 403,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c78765daf29a4ee-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:26:18 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '554'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999573'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_8470b8b5bbb92d681113593a54e2e796
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''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.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number:
''integer'', second_number: ''integer'') - Useful for when you need to multiply
two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First
Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'',
''type'': ''integer''}}\n\nUse the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, only one name of
[multiplier], just the name, exactly as it''s written.\nAction Input: the input
to the action, just a simple python dictionary, enclosed in curly braces, using
\" to wrap keys and values.\nObservation: the result of the action\n\nOnce all
necessary information is gathered:\n\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n"}, {"role": "user",
"content": "\nCurrent Task: What is 2 times 6? Return only the number.\n\nThis
is the expect criteria for your final answer: the result of multiplication\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n12\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}, {"role": "user", "content": "Thought: I need to use the
multiplier tool to calculate 2 times 6.\n\nAction: multiplier\nAction Input:
{\"first_number\": 2, \"second_number\": 6}\nObservation: 12"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1960'
content-type:
- application/json
cookie:
- __cf_bm=hYfEMfBWpIoRPjx9ZBZg6DVeMOMr1IZt9ioup8yWZs0-1727072673-1.0.1.1-Ro7GCLuWS0K5ob0mSTYSmovONKNyxsK6oSA5io_Vwqhe6P0G7Ow4CuZUaWAaCdFGQUd7XZiFH0mI_sQC3uqe0g;
_cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
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-AAWoUllvSchIe4UjMDiHuMkr0HQYi\",\n \"object\":
\"chat.completion\",\n \"created\": 1727072778,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer.\\n\\nFinal
Answer: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
411,\n \"completion_tokens\": 14,\n \"total_tokens\": 425,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c787662b9a9a4ee-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:26:19 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '300'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999534'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2be2bcb79761b70e608117b5486af633
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink