andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 08:38:30 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
91ddab207f5c3348333102f034856cca6f4bbbd4
crewAI/tests/cassettes/test_increment_delegations_for_sequential_process.yaml
João Moura 91ddab207f Making all tests good
2024-09-13 04:38:19 -05:00

394 lines
18 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Manager. You''re great
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
processes\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", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2640'
content-type:
- application/json
cookie:
- __cf_bm=pgsskMPipgeSB6HhnkjwcOEfengIvt0p9whKNmTJVLs-1726215280-1.0.1.1-Gtqb.nO1U.cHTnd9mR9sEA5tpVo1.pexRrxqXOkn.6Mzja8mLG1URJsOLTfjMAAYpWaUQe4Rjmnr6lqQk5hAxQ;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
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-A6vp8du27ZEb6qG03UeIgpJJYmjNk\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215606,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To provide an accurate integer score
between 1-5 for the title 'The impact of AI in the future of work', I need to
delegate this task to the Scorer.\\n\\nAction: Delegate work to coworker\\nAction
Input: {\\\"task\\\": \\\"Provide an integer score between 1-5 for the title
'The impact of AI in the future of work'\\\", \\\"context\\\": \\\"We need you
to rate the given title based on your expert judgment. The scoring range is
between 1 and 5. Please provide a brief rationale for your rating as well, if
possible.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 584,\n \"completion_tokens\":
126,\n \"total_tokens\": 710,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26b74ddb752ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:20:07 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:
- '1743'
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:
- '29999361'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_a4a571fc8e825316f692e01f2a3b41ba
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: 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 you to rate the given title based on your expert judgment. The scoring
range is between 1 and 5. Please provide a brief rationale for your rating as
well, if possible.\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:
- '1214'
content-type:
- application/json
cookie:
- __cf_bm=pgsskMPipgeSB6HhnkjwcOEfengIvt0p9whKNmTJVLs-1726215280-1.0.1.1-Gtqb.nO1U.cHTnd9mR9sEA5tpVo1.pexRrxqXOkn.6Mzja8mLG1URJsOLTfjMAAYpWaUQe4Rjmnr6lqQk5hAxQ;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
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-A6vpApQ8II2bUOvaJpMJ9CbqfY2Ex\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215608,\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: I would rate the title 'The impact of AI in the future of work' a 4
out of 5. The title is clear and directly addresses a relevant and timely topic.
It promises an exploration of the influence of artificial intelligence on the
future of employment, which is a subject of great interest and importance. However,
it could be slightly more specific to further enhance its appeal, such as specifying
which aspects of work (e.g., job displacement, skill evolution, industry-specific
impacts) it will focus on.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
241,\n \"completion_tokens\": 116,\n \"total_tokens\": 357,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_992d1ea92d\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26b7612dc92ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:20:10 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:
- '1387'
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:
- '29999714'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_b6ff0770d4481c72e3558cd83d76e615
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Manager. You''re great
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
processes\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": "assistant", "content": "To provide an accurate
integer score between 1-5 for the title ''The impact of AI in the future of
work'', I need to delegate this task to the Scorer.\n\nAction: Delegate work
to coworker\nAction Input: {\"task\": \"Provide an integer score between 1-5
for the title ''The impact of AI in the future of work''\", \"context\": \"We
need you to rate the given title based on your expert judgment. The scoring
range is between 1 and 5. Please provide a brief rationale for your rating as
well, if possible.\", \"coworker\": \"Scorer\"}\nObservation: I would rate the
title ''The impact of AI in the future of work'' a 4 out of 5. The title is
clear and directly addresses a relevant and timely topic. It promises an exploration
of the influence of artificial intelligence on the future of employment, which
is a subject of great interest and importance. However, it could be slightly
more specific to further enhance its appeal, such as specifying which aspects
of work (e.g., job displacement, skill evolution, industry-specific impacts)
it will focus on."}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3725'
content-type:
- application/json
cookie:
- __cf_bm=pgsskMPipgeSB6HhnkjwcOEfengIvt0p9whKNmTJVLs-1726215280-1.0.1.1-Gtqb.nO1U.cHTnd9mR9sEA5tpVo1.pexRrxqXOkn.6Mzja8mLG1URJsOLTfjMAAYpWaUQe4Rjmnr6lqQk5hAxQ;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
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-A6vpDvwJSM03OuDbYj6OWWMblLMwD\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215611,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now have the final answer
from the Scorer.\\n\\nFinal Answer: 4\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 819,\n \"completion_tokens\": 18,\n
\ \"total_tokens\": 837,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26b76fdbd62ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:20:11 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:
- '318'
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:
- '29999103'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_77d5c12bb1af1c29348b67843bba8d12
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink