andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-11 09:08:31 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity
Files
8ca08217189345b0d28ce7174bee700faea5bdcf
crewAI/tests/cassettes/test_cache_hitting_between_agents.yaml
João Moura 8ca0821718 making sure all tests pass
2024-09-15 19:37:58 -03:00

511 lines
23 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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3110'
content-type:
- application/json
cookie:
- _cfuvid=XOthMhC8E2o0ojs9QD6edSEeqE1gLP2e0PTT.ls_Oqk-1726439597069-0.0.1.1-604800000;
__cf_bm=2d.Y9HMLckd.JrNHDFu0lE5Z_wd0IkygyCLN7XSOZJ4-1726439597-1.0.1.1-n4zhLu.njy3WBfj4ihCtUTMsQN0qib7wJEILVPhGd9SrR6rJ8JKyqoPgsGgi8Xv_ys0Bj4.EPQb0RKKx6md_bQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A7s6XZDkCwxTlXN8wzem1XLRD8QC1\",\n \"object\":
\"chat.completion\",\n \"created\": 1726439637,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: The current task is to find
the result of multiplying 2 by 6. I will use the multiplier tool to get the
answer.\\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\":
50,\n \"total_tokens\": 741,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3c14d28e30d9c1-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:33:57 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '475'
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_de08746db1758c27fdc2e77a2d75091c
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": "assistant", "content": "Thought:
The current task is to find the result of multiplying 2 by 6. I will use the
multiplier tool to get the answer.\n\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 6}\nObservation: 12"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3366'
content-type:
- application/json
cookie:
- _cfuvid=XOthMhC8E2o0ojs9QD6edSEeqE1gLP2e0PTT.ls_Oqk-1726439597069-0.0.1.1-604800000;
__cf_bm=2d.Y9HMLckd.JrNHDFu0lE5Z_wd0IkygyCLN7XSOZJ4-1726439597-1.0.1.1-n4zhLu.njy3WBfj4ihCtUTMsQN0qib7wJEILVPhGd9SrR6rJ8JKyqoPgsGgi8Xv_ys0Bj4.EPQb0RKKx6md_bQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A7s6XlWO4ZF4wHUyn8v0WAWF2LynB\",\n \"object\":
\"chat.completion\",\n \"created\": 1726439637,\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\":
749,\n \"completion_tokens\": 14,\n \"total_tokens\": 763,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3c14d75b13d9c1-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:33:58 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '251'
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:
- '29999192'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_969dda6fc213797c0bbe78642f42c553
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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1791'
content-type:
- application/json
cookie:
- _cfuvid=XOthMhC8E2o0ojs9QD6edSEeqE1gLP2e0PTT.ls_Oqk-1726439597069-0.0.1.1-604800000;
__cf_bm=2d.Y9HMLckd.JrNHDFu0lE5Z_wd0IkygyCLN7XSOZJ4-1726439597-1.0.1.1-n4zhLu.njy3WBfj4ihCtUTMsQN0qib7wJEILVPhGd9SrR6rJ8JKyqoPgsGgi8Xv_ys0Bj4.EPQb0RKKx6md_bQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A7s6YdQwL5beRYKa2zRDX99TZbQgN\",\n \"object\":
\"chat.completion\",\n \"created\": 1726439638,\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 find the result of multiplying 2 by 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\":
42,\n \"total_tokens\": 407,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3c14daaeb4d9c1-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:33:58 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '533'
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_b7a1ddc7b45b4ac0c81d31fd8f41c3c0
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": "assistant", "content": "Thought: I need to use
the multiplier tool to find the result of multiplying 2 by 6.\n\nAction: multiplier\nAction
Input: {\"first_number\": 2, \"second_number\": 6}\nObservation: 12"}], "model":
"gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2011'
content-type:
- application/json
cookie:
- _cfuvid=XOthMhC8E2o0ojs9QD6edSEeqE1gLP2e0PTT.ls_Oqk-1726439597069-0.0.1.1-604800000;
__cf_bm=2d.Y9HMLckd.JrNHDFu0lE5Z_wd0IkygyCLN7XSOZJ4-1726439597-1.0.1.1-n4zhLu.njy3WBfj4ihCtUTMsQN0qib7wJEILVPhGd9SrR6rJ8JKyqoPgsGgi8Xv_ys0Bj4.EPQb0RKKx6md_bQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A7s6ZUppI8WxIYmGmM9YNe7tLMsz8\",\n \"object\":
\"chat.completion\",\n \"created\": 1726439639,\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\":
415,\n \"completion_tokens\": 14,\n \"total_tokens\": 429,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3c14dfdb8ad9c1-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:33:59 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '282'
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:
- '29999529'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_30f99e96e91ce5df96f2ad2251758f93
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink