andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-19 12:58:14 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
f216b0a78c5138ed4e0b4fe6715b5d7ac888d872
crewAI/tests/cassettes/test_cache_hitting_between_agents.yaml
João Moura f216b0a78c fixing parser, tools and executor
2024-09-15 18:41:59 -03:00

587 lines
27 KiB
YAML
Raw Blame History

interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '2652'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sun, 15 Sep 2024 06:12:37 GMT
status:
code: 200
message: OK
- 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": ["\nResult"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3104'
content-type:
- application/json
cookie:
- __cf_bm=e.frhlfi1m.8j1hzfGzahuOh4rgR9gvx.2zCHQ2w_Vs-1726380612-1.0.1.1-T58wIEXn0GTV8AZMALaUyULORFkNEBuxpds8RSWAM0Ltrg2U7jLBEKs0nwIneMiBAiiOmyZaoaH2RyLtNcunLQ;
_cfuvid=Bz2zevKuFYZqnEFwqmqVHcRo5pT0fm0fTtc_6_VQs4g-1726379702153-0.0.1.1-604800000
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-A7cmq5pmlNwC0r75t38JnYsdw8IM2\",\n \"object\":
\"chat.completion\",\n \"created\": 1726380756,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: To find the product of 2 and
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\":
42,\n \"total_tokens\": 733,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c367750bfb0745a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 06:12:37 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:
- '524'
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_3b885ee527af307dd1f101a1d160e67b
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:
To find the product of 2 and 6, I need to use the multiplier tool.\n\nAction:
multiplier\nAction Input: {\"first_number\": 2, \"second_number\": 6}\nObservation:
12"}], "model": "gpt-4o", "stop": ["\nResult"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3315'
content-type:
- application/json
cookie:
- __cf_bm=e.frhlfi1m.8j1hzfGzahuOh4rgR9gvx.2zCHQ2w_Vs-1726380612-1.0.1.1-T58wIEXn0GTV8AZMALaUyULORFkNEBuxpds8RSWAM0Ltrg2U7jLBEKs0nwIneMiBAiiOmyZaoaH2RyLtNcunLQ;
_cfuvid=Bz2zevKuFYZqnEFwqmqVHcRo5pT0fm0fTtc_6_VQs4g-1726379702153-0.0.1.1-604800000
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-A7cmrI98PgyZZlYIkXQsSaPCb2vxB\",\n \"object\":
\"chat.completion\",\n \"created\": 1726380757,\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\":
741,\n \"completion_tokens\": 14,\n \"total_tokens\": 755,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c367755db4e745a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 06:12:37 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:
- '242'
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:
- '29999203'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_2da1eee07355196b666a542ff688355e
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": ["\nResult"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1785'
content-type:
- application/json
cookie:
- __cf_bm=e.frhlfi1m.8j1hzfGzahuOh4rgR9gvx.2zCHQ2w_Vs-1726380612-1.0.1.1-T58wIEXn0GTV8AZMALaUyULORFkNEBuxpds8RSWAM0Ltrg2U7jLBEKs0nwIneMiBAiiOmyZaoaH2RyLtNcunLQ;
_cfuvid=Bz2zevKuFYZqnEFwqmqVHcRo5pT0fm0fTtc_6_VQs4g-1726379702153-0.0.1.1-604800000
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-A7cms3RrQnoDAIb7AdiCJg4w4AJZO\",\n \"object\":
\"chat.completion\",\n \"created\": 1726380758,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to multiply the numbers
2 and 6 to get the final 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\":
365,\n \"completion_tokens\": 40,\n \"total_tokens\": 405,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3677592e00745a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 06:12:38 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:
- '511'
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_a17229f8cd4d0c131330568b02e5ce5a
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 multiply
the numbers 2 and 6 to get the final answer.\n\nAction: multiplier\nAction Input:
{\"first_number\": 2, \"second_number\": 6}\nObservation: 12"}], "model": "gpt-4o",
"stop": ["\nResult"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1993'
content-type:
- application/json
cookie:
- __cf_bm=e.frhlfi1m.8j1hzfGzahuOh4rgR9gvx.2zCHQ2w_Vs-1726380612-1.0.1.1-T58wIEXn0GTV8AZMALaUyULORFkNEBuxpds8RSWAM0Ltrg2U7jLBEKs0nwIneMiBAiiOmyZaoaH2RyLtNcunLQ;
_cfuvid=Bz2zevKuFYZqnEFwqmqVHcRo5pT0fm0fTtc_6_VQs4g-1726379702153-0.0.1.1-604800000
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-A7cmsW8lEMKb31TVdZDJQ3QhgSZGi\",\n \"object\":
\"chat.completion\",\n \"created\": 1726380758,\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\":
413,\n \"completion_tokens\": 14,\n \"total_tokens\": 427,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c36775e3983745a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 06:12:39 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:
- '288'
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:
- '29999531'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_1859a2f9fd2e6aedec804032a0dd7763
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink