Files
crewAI/tests/cassettes/test_increment_delegations_for_hierarchical_process.yaml
2024-09-23 17:45:20 -03:00

384 lines
17 KiB
YAML

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\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: Scorer\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: Scorer\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 [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: Give me an integer score between 1-5 for the following title:
''The impact of AI in the future of work''\n\nThis is the expect criteria for
your final answer: The score of the title.\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:
- '2986'
content-type:
- application/json
cookie:
- __cf_bm=iOyeV6o_mR0USNA.hPdpKPtAzYgMoprpObRHvn0tmcc-1727120402-1.0.1.1-yMOSz4qncmM1wdtrwFfBQNfITkLs2w_sxijeM44F7aSIrclbkQ2G_18su02eVMVPMW2O55B1rty8BiY_WAoayg;
_cfuvid=9K_ipT1uTVyDTneB1W5OZHPxCh36aOsDZCBnsQTONqQ-1727119501207-0.0.1.1-604800000
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-AAjLbRa4ANPkzMAywnkSGqg3M1bYb\",\n \"object\":
\"chat.completion\",\n \"created\": 1727120959,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to get an expert evaluation on
the title \\\"The impact of AI in the future of work\\\" using the scoring system
between 1-5. I'll ask Scorer to provide the score based on this title.\\n\\nAction:
Ask question to coworker\\nAction Input: {\\\"question\\\": \\\"Can you provide
an integer score between 1-5 for the title 'The impact of AI in the future of
work'?\\\", \\\"context\\\": \\\"We need to evaluate the given title and provide
a score. The score should be an integer between 1-5, where 1 is the lowest and
5 is the highest.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 664,\n \"completion_tokens\":
135,\n \"total_tokens\": 799,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7d0eac5f3fa4c7-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 19:49:21 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:
- '1786'
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:
- '29999269'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_0265b8f41e7486480fd725ec48821e74
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an
expert scorer, specialized in scoring titles.\nYour personal goal is: Score
the title\nTo give my best complete final answer to the task use the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Can you provide an integer score between 1-5 for
the title ''The impact of AI in the future of work''?\n\nThis is the expect
criteria for your final answer: Your best answer to your coworker asking you
this, accounting for the context shared.\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nThis is the context you''re working
with:\nWe need to evaluate the given title and provide a score. The score should
be an integer between 1-5, where 1 is the lowest and 5 is the highest.\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:
- '1165'
content-type:
- application/json
cookie:
- __cf_bm=iOyeV6o_mR0USNA.hPdpKPtAzYgMoprpObRHvn0tmcc-1727120402-1.0.1.1-yMOSz4qncmM1wdtrwFfBQNfITkLs2w_sxijeM44F7aSIrclbkQ2G_18su02eVMVPMW2O55B1rty8BiY_WAoayg;
_cfuvid=9K_ipT1uTVyDTneB1W5OZHPxCh36aOsDZCBnsQTONqQ-1727119501207-0.0.1.1-604800000
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-AAjLdEftLZCTFDyFtZIph1vtrC285\",\n \"object\":
\"chat.completion\",\n \"created\": 1727120961,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
242,\n \"completion_tokens\": 15,\n \"total_tokens\": 257,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7d0eba2cc6a4c7-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 19:49:22 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:
- '756'
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:
- '29999719'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_0bd539e146244f8cf0dd8c6f65298d42
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\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: Scorer\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: Scorer\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 [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: Give me an integer score between 1-5 for the following title:
''The impact of AI in the future of work''\n\nThis is the expect criteria for
your final answer: The score of the title.\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": "I need to get an expert evaluation
on the title \"The impact of AI in the future of work\" using the scoring system
between 1-5. I''ll ask Scorer to provide the score based on this title.\n\nAction:
Ask question to coworker\nAction Input: {\"question\": \"Can you provide an
integer score between 1-5 for the title ''The impact of AI in the future of
work''?\", \"context\": \"We need to evaluate the given title and provide a
score. The score should be an integer between 1-5, where 1 is the lowest and
5 is the highest.\", \"coworker\": \"Scorer\"}\nObservation: 4"}], "model":
"gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3582'
content-type:
- application/json
cookie:
- __cf_bm=iOyeV6o_mR0USNA.hPdpKPtAzYgMoprpObRHvn0tmcc-1727120402-1.0.1.1-yMOSz4qncmM1wdtrwFfBQNfITkLs2w_sxijeM44F7aSIrclbkQ2G_18su02eVMVPMW2O55B1rty8BiY_WAoayg;
_cfuvid=9K_ipT1uTVyDTneB1W5OZHPxCh36aOsDZCBnsQTONqQ-1727119501207-0.0.1.1-604800000
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-AAjLeWGhLOIThUrKXDXvnKLjYFk2z\",\n \"object\":
\"chat.completion\",\n \"created\": 1727120962,\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: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
807,\n \"completion_tokens\": 14,\n \"total_tokens\": 821,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7d0ec0feeba4c7-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 19:49:23 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:
- '759'
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:
- '29999131'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_e31c676ecd19137c2a4b0f51aa65ed5f
http_version: HTTP/1.1
status_code: 200
version: 1