andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 08:08:32 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
42f2b4d551dc23353f917f3f78b93f97d564e834
crewAI/tests/cassettes/test_output_json_hierarchical.yaml
Lorenze Jay 6f2e39c0dd
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
Details
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Details
Notify Downstream / notify-downstream (push) Has been cancelled
Details
Update Test Durations / update-durations (3.10) (push) Has been cancelled
Details
Update Test Durations / update-durations (3.11) (push) Has been cancelled
Details
Update Test Durations / update-durations (3.12) (push) Has been cancelled
Details
Update Test Durations / update-durations (3.13) (push) Has been cancelled
Details
feat: enhance knowledge and guardrail event handling in Agent class (#3672) 
* feat: enhance knowledge event handling in Agent class

- Updated the Agent class to include task context in knowledge retrieval events.
- Emitted new events for knowledge retrieval and query processes, capturing task and agent details.
- Refactored knowledge event classes to inherit from a base class for better structure and maintainability.
- Added tracing for knowledge events in the TraceCollectionListener to improve observability.

This change improves the tracking and management of knowledge queries and retrievals, facilitating better debugging and performance monitoring.

* refactor: remove task_id from knowledge event emissions in Agent class

- Removed the task_id parameter from various knowledge event emissions in the Agent class to streamline event handling.
- This change simplifies the event structure and focuses on the essential context of knowledge retrieval and query processes.

This refactor enhances the clarity of knowledge events and aligns with the recent improvements in event handling.

* surface association for guardrail events

* fix: improve LLM selection logic in converter

- Updated the logic for selecting the LLM in the convert_with_instructions function to handle cases where the agent may not have a function_calling_llm attribute.
- This change ensures that the converter can still function correctly by falling back to the standard LLM if necessary, enhancing robustness and preventing potential errors.

This fix improves the reliability of the conversion process when working with different agent configurations.

* fix test

* fix: enforce valid LLM instance requirement in converter

- Updated the convert_with_instructions function to ensure that a valid LLM instance is provided by the agent.
- If neither function_calling_llm nor the standard llm is available, a ValueError is raised, enhancing error handling and robustness.
- Improved error messaging for conversion failures to provide clearer feedback on issues encountered during the conversion process.

This change strengthens the reliability of the conversion process by ensuring that agents are properly configured with a valid LLM.
2025-10-08 11:53:13 -07:00

2017 lines
114 KiB
YAML
Raw Blame History

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=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
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-AB7fzflt7Fhs1oZsbsvf8UH2540zr\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214479,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To provide the score for the title \\\"The
impact of AI in the future of work,\\\" I need to ask Scorer to evaluate this
based on the criteria they use. \\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 this title based on your criteria for scoring titles. The context
for the scoring revolves entirely around the perceived impact of AI on the future
of work.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 664,\n \"completion_tokens\":
122,\n \"total_tokens\": 786,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f9de4b8c1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:48:01 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:
- '1846'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; 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_11f38fee4ec6e3f51a3324984c025e8a
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CrkXCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSkBcKEgoQY3Jld2FpLnRl
bGVtZXRyeRKQAgoQ1tibm5O29ydlYfnOavm8RBII2SJ7HUWzRw0qDlRhc2sgRXhlY3V0aW9uMAE5
MJ81e2lM+BdB2DorkWpM+BdKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0
ODI1Y2NmYTNKMQoHY3Jld19pZBImCiQwODczNWFkNy1iZTFhLTQ0ZDMtOTU3Ny1hMzM0ZjI2NTNm
NjFKLgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFz
a19pZBImCiQ5YjE2YjE3YS0wZTg5LTRmMGItODc3NC1mZjkxODU3NGYzNjZ6AhgBhQEAAQAAEpYH
ChBxyWIltrFtco3B5ZvJkfAeEgh/kPnzKKzEGioMQ3JldyBDcmVhdGVkMAE5SKsrkmpM+BdBqIMv
kmpM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMu
MTEuN0ouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdj
cmV3X2lkEiYKJDU3OWM3OGE3LTg2MjEtNGQ2Ni04NDQyLWRjY2NkNjY2YTk3ZkocCgxjcmV3X3By
b2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2Zf
dGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKyAIKC2NyZXdfYWdlbnRzErgC
CrUCW3sia2V5IjogIjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgImlkIjogIjVm
ODRlMTRiLWMzOTEtNDM4Mi1iNzM2LWNiYzlhZjE1M2I0OSIsICJyb2xlIjogIlNjb3JlciIsICJ2
ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rp
b25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVk
PyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGlt
aXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSvsBCgpjcmV3X3Rhc2tzEuwBCukBW3sia2V5Ijog
IjI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2IiwgImlkIjogImJlODc3NWQyLTU1OTQt
NGIyMy1hZDIwLTcxMTdlZTcyMDcyYiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1h
bl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiU2NvcmVyIiwgImFnZW50X2tleSI6ICI5
MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgB
hQEAAQAAEo4CChADNfQkyWpTxYTb4wV4Xi1zEgjhZIssXkYhYyoMVGFzayBDcmVhdGVkMAE54LRI
kmpM+BdBkGhJkmpM+BdKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0ODI1
Y2NmYTNKMQoHY3Jld19pZBImCiQ1NzljNzhhNy04NjIxLTRkNjYtODQ0Mi1kY2NjZDY2NmE5N2ZK
LgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19p
ZBImCiRiZTg3NzVkMi01NTk0LTRiMjMtYWQyMC03MTE3ZWU3MjA3MmJ6AhgBhQEAAQAAEpACChDW
xf6NEFlSgigrF1Uyj4hIEgiPFfsrt0iWwyoOVGFzayBFeGVjdXRpb24wATmYukmSakz4F0FgOfji
akz4F0ouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdj
cmV3X2lkEiYKJDU3OWM3OGE3LTg2MjEtNGQ2Ni04NDQyLWRjY2NkNjY2YTk3ZkouCgh0YXNrX2tl
eRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNrX2lkEiYKJGJlODc3
NWQyLTU1OTQtNGIyMy1hZDIwLTcxMTdlZTcyMDcyYnoCGAGFAQABAAASmAcKEPcwxZwxkQKMAj/Q
Ue+krp4SCK8Ly14L/2MwKgxDcmV3IENyZWF0ZWQwATkwT8bjakz4F0FIsMrjakz4F0oaCg5jcmV3
YWlfdmVyc2lvbhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdf
a2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2NyZXdfaWQSJgokN2Q5
ODViMTAtZjJlYy00NTI0LTg4ZGItMWI0Yzk4MDViZGYzSh4KDGNyZXdfcHJvY2VzcxIOCgxoaWVy
YXJjaGljYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUob
ChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSsgCCgtjcmV3X2FnZW50cxK4Agq1Alt7ImtleSI6
ICI5MmU3ZWIxOTE2NjRjOTM1Nzg1ZWQ3ZDQyNDBhMjk0ZCIsICJpZCI6ICI1YjA5Y2YyNC0xYjg4
LTQ4YzUtYjNhZi1jMDRjMTUyZDRmM2MiLCAicm9sZSI6ICJTY29yZXIiLCAidmVyYm9zZT8iOiBm
YWxzZSwgIm1heF9pdGVyIjogMTUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdf
bGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwg
ImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRv
b2xzX25hbWVzIjogW119XUr7AQoKY3Jld190YXNrcxLsAQrpAVt7ImtleSI6ICIyN2VmMzhjYzk5
ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NiIsICJpZCI6ICJiNmE2ZDhiNS1iMWRkLTQxYTctOTJlOS1j
YzIxNzAwODJmMTciLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/Ijog
ZmFsc2UsICJhZ2VudF9yb2xlIjogIlNjb3JlciIsICJhZ2VudF9rZXkiOiAiOTJlN2ViMTkxNjY0
YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQ
XyhkBtLg+uYDB+G/D3snoBII1hx0numRabUqDFRhc2sgQ3JlYXRlZDABObCgJeVqTPgXQXB7JuVq
TPgXSi4KCGNyZXdfa2V5EiIKIDVlNmVmZmU2ODBhNWQ5N2RjMzg3M2IxNDgyNWNjZmEzSjEKB2Ny
ZXdfaWQSJgokN2Q5ODViMTAtZjJlYy00NTI0LTg4ZGItMWI0Yzk4MDViZGYzSi4KCHRhc2tfa2V5
EiIKIDI3ZWYzOGNjOTlkYTRhOGRlZDcwZWQ0MDZlNDRhYjg2SjEKB3Rhc2tfaWQSJgokYjZhNmQ4
YjUtYjFkZC00MWE3LTkyZTktY2MyMTcwMDgyZjE3egIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '3004'
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:
- Tue, 24 Sep 2024 21:48:02 GMT
status:
code: 200
message: OK
- 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 this title based on your criteria for scoring titles.
The context for the scoring revolves entirely around the perceived impact of
AI on the future of work.\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:
- '1197'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
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-AB7g1mAHJE9QnUWqbrKUvROBJKSYb\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214481,\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 - The title 'The impact of AI in the future of work' is clear and
directly addresses a timely and significant topic that is highly relevant in
today's context. However, it could be made even more specific to immediately
hook the reader or audience.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
238,\n \"completion_tokens\": 64,\n \"total_tokens\": 302,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f9ec685c1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:48:02 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:
- '802'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999712'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a7c8c6c2bd1951dd5d067148bc6ceba8
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": "assistant", "content": "To provide the score
for the title \"The impact of AI in the future of work,\" I need to ask Scorer
to evaluate this based on the criteria they use. \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 this title based on your criteria for scoring titles.
The context for the scoring revolves entirely around the perceived impact of
AI on the future of work.\", \"coworker\": \"Scorer\"}\nObservation: 4 - The
title ''The impact of AI in the future of work'' is clear and directly addresses
a timely and significant topic that is highly relevant in today''s context.
However, it could be made even more specific to immediately hook the reader
or audience."}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3831'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
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-AB7g2oKgp7qGfodgXRIUm5FpBtpNp\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214482,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I have received the score from
Scorer.\\n\\nFinal Answer: 4 - The title 'The impact of AI in the future of
work' is clear and directly addresses a timely and significant topic that is
highly relevant in today's context. However, it could be made even more specific
to immediately hook the reader or audience.\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 843,\n \"completion_tokens\":
65,\n \"total_tokens\": 908,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f9f338e01cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:48:03 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:
- '1078'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999071'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_4bee152d111ba79c2f73025a64db943f
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "4 - The title ''The impact of
AI in the future of work'' is clear and directly addresses a timely and significant
topic that is highly relevant in today''s context. However, it could be made
even more specific to immediately hook the reader or audience."}, {"role": "system",
"content": "I''m gonna convert this raw text into valid JSON.\n\nThe json should
have the following structure, with the following keys:\n{\n score: int\n}"}],
"model": "gpt-4o", "tool_choice": {"type": "function", "function": {"name":
"ScoreOutput"}}, "tools": [{"type": "function", "function": {"name": "ScoreOutput",
"description": "Correctly extracted `ScoreOutput` with all the required parameters
with correct types", "parameters": {"properties": {"score": {"title": "Score",
"type": "integer"}}, "required": ["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '864'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
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-AB7g4iZixQjuGxE0RxbSIixLAsEGf\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214484,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_iIgRFzMLI0NHZwyJM2CwzJPL\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n
\ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
149,\n \"completion_tokens\": 5,\n \"total_tokens\": 154,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_9f2bfdaa89\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f9fc5e991cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:48:04 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:
- '141'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999884'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_dd38f9b6e9e6ac64ebbb827111e31414
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\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\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 absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\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 absolutely everything you know, don''t
reference things but instead explain them.\n\nIMPORTANT: Use the following format
in your response:\n\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 JSON object, enclosed in curly braces, using \"
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\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 expected criteria for your final answer:
The score of the title.\nyou MUST return the actual complete content as the
final answer, not a summary.\nEnsure your final answer contains only the content
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
not include any code block markers like ```json or ```python.\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, zstd
connection:
- keep-alive
content-length:
- '3194'
content-type:
- application/json
cookie:
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
_cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 974eec36591c8486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:27 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '3819'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '3856'
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999242'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_e91c7ccb367243348f19a41989b6992d
status:
code: 200
message: OK
- 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 respond using 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: Score the title ''The impact of
AI in the future of work'' on a scale from 1 to 5.\n\nThis is the expected 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:\nThe
task requires evaluating the title based on factors such as relevance, impact,
and clarity. The score should be an integer between 1 to 5, where 1 is poor
and 5 is excellent.\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 delegate the task of scoring the
title \"The impact of AI in the future of work\" to the Scorer. I will provide
them with all necessary context to execute the task.\n\nAction: Delegate work
to coworker\nAction Input: {\"task\": \"Score the title ''The impact of AI in
the future of work'' on a scale from 1 to 5.\", \"context\": \"The task requires
evaluating the title based on factors such as relevance, impact, and clarity.
The score should be an integer between 1 to 5, where 1 is poor and 5 is excellent.\",
\"coworker\": \"Scorer\"}\nObservation: I encountered an error: Action ''Delegate
work to coworker'' don''t exist, these are the only available Actions:\n\nMoving
on then. I MUST either use a tool (use one at time) OR give my best final answer
not both at the same time. When responding, I must use the following format:\n\n```\nThought:
you should always think about what to do\nAction: the action to take, should
be one of []\nAction Input: the input to the action, dictionary enclosed in
curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action
Input/Result can repeat N times. Once I know the final answer, I must return
the following format:\n\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\n```"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '2627'
content-type:
- application/json
cookie:
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
_cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 974eec4fbebf8486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:31 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '4218'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '4238'
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999394'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_28f00852660542e88719133a722fce84
status:
code: 200
message: OK
- 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\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\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 absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\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 absolutely everything you know, don''t
reference things but instead explain them.\n\nIMPORTANT: Use the following format
in your response:\n\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 JSON object, enclosed in curly braces, using \"
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\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 expected criteria for your final answer:
The score of the title.\nyou MUST return the actual complete content as the
final answer, not a summary.\nEnsure your final answer contains only the content
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
not include any code block markers like ```json or ```python.\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 delegate the task of scoring the title \"The impact of AI in the future
of work\" to the Scorer. I will provide them with all necessary context to execute
the task.\n\nAction: Delegate work to coworker\nAction Input: {\"task\": \"Score
the title ''The impact of AI in the future of work'' on a scale from 1 to 5.\",
\"context\": \"The task requires evaluating the title based on factors such
as relevance, impact, and clarity. The score should be an integer between 1
to 5, where 1 is poor and 5 is excellent.\", \"coworker\": \"Scorer\"}\nObservation:
To evaluate the title ''The impact of AI in the future of work'', we need to
consider relevancy, impact, and clarity. Here''s the assessment:\n\n- **Relevance
(5/5):** The title is highly relevant, as Artificial Intelligence (AI) is a
major topic of interest in today''s fast-evolving technological landscape. The
future of work is a crucial subject that affects diverse industries and professions
worldwide, which makes it a timely and meaningful subject to explore.\n \n-
**Impact (5/5):** The title suggests a profound impact since AI is anticipated
to significantly transform the workspace by automating jobs, creating new job
categories, and altering how traditional jobs are performed. Analyzing these
potential changes can greatly inform and influence policymakers, businesses,
and the workforce.\n \n- **Clarity (5/5):** The title is clear and concise.
It directly points out the subject (AI) and the specific context (the future
of work) it impacts. There''s no ambiguity, making it accessible to a broad
audience, including professionals, students, and general readers interested
in technology''s influence on employment trends.\n\nOverall, the title ''The
impact of AI in the future of work'' scores an excellent 5 out of 5. It adequately
captures a complex, forward-thinking issue with clarity, relevance, and significant
impact potential."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '5147'
content-type:
- application/json
cookie:
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
_cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 974eec6aa9b18486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:32 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '556'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '614'
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29998767'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_92650754cfb84bb9bff203c3b554da6e
status:
code: 200
message: OK
- 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\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\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 absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\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 absolutely everything you know, don''t
reference things but instead explain them.\n\nIMPORTANT: Use the following format
in your response:\n\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 JSON object, enclosed in curly braces, using \"
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\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 expected criteria for your final answer:
The score of the title.\nyou MUST return the actual complete content as the
final answer, not a summary.\nEnsure your final answer contains only the content
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
not include any code block markers like ```json or ```python.\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 delegate the task of scoring the title \"The impact of AI in the future
of work\" to the Scorer. I will provide them with all necessary context to execute
the task.\n\nAction: Delegate work to coworker\nAction Input: {\"task\": \"Score
the title ''The impact of AI in the future of work'' on a scale from 1 to 5.\",
\"context\": \"The task requires evaluating the title based on factors such
as relevance, impact, and clarity. The score should be an integer between 1
to 5, where 1 is poor and 5 is excellent.\", \"coworker\": \"Scorer\"}\nObservation:
{\n \"score\": 5\n}"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3822'
content-type:
- application/json
cookie:
- _cfuvid=CW_cKQGYWY3cL.S6Xo5z0cmkmWHy5Q50OA_KjPEijNk-1735926034530-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 974eef2f6d51dc0d-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:40:25 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=OccMxrmCRox_7bIJtedFlhoPOuuUvZzIFuNich2H1JY-1756165225-1.0.1.1-GZu0FYiwF3GrVFp6V5lDMCNsqJ3lPFJoATnPc50dACgSXHbkzGM7.MHv7GvUoDKXSyRy2Rxf5hGsRH_FPp.tBEzcki6qQDXIBhWde1NEJkE;
path=/; expires=Tue, 26-Aug-25 00:10:25 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=aj4gjWj2skMQt34sZXxfiLoWjDQdxXvxh0I9isfN5II-1756165225584-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '510'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '623'
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999099'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_18884789d50842b7bcfffb3752d3fd0f
status:
code: 200
message: OK
- request:
body: '{"trace_id": "1a5c71d1-4e28-4432-aa20-c7ef93a2657b", "execution_type":
"crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
"crew_name": "crew", "flow_name": null, "crewai_version": "0.201.1", "privacy_level":
"standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-10-08T18:18:08.160521+00:00"}}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate, zstd
Connection:
- keep-alive
Content-Length:
- '428'
Content-Type:
- application/json
User-Agent:
- CrewAI-CLI/0.201.1
X-Crewai-Organization-Id:
- d3a3d10c-35db-423f-a7a4-c026030ba64d
X-Crewai-Version:
- 0.201.1
method: POST
uri: http://localhost:3000/crewai_plus/api/v1/tracing/batches
response:
body:
string: '{"id":"6ce9315e-6cf2-47fc-8bbe-38f1ecfde6e0","trace_id":"1a5c71d1-4e28-4432-aa20-c7ef93a2657b","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"0.201.1","privacy_level":"standard","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"0.201.1","privacy_level":"standard"},"created_at":"2025-10-08T18:18:08.537Z","updated_at":"2025-10-08T18:18:08.537Z"}'
headers:
Content-Length:
- '480'
cache-control:
- no-store
content-security-policy:
- 'default-src ''self'' *.crewai.com crewai.com; script-src ''self'' ''unsafe-inline''
*.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com
https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
https://js-na1.hs-scripts.com https://share.descript.com/; style-src ''self''
''unsafe-inline'' *.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts;
img-src ''self'' data: *.crewai.com crewai.com https://zeus.tools.crewai.com
https://dashboard.tools.crewai.com https://cdn.jsdelivr.net; font-src ''self''
data: *.crewai.com crewai.com; connect-src ''self'' *.crewai.com crewai.com
https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/*
https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/
https://*.sentry.io https://www.google-analytics.com ws://localhost:3036 wss://localhost:3036;
frame-src ''self'' *.crewai.com crewai.com https://connect.useparagon.com/
https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/
https://docs.google.com https://drive.google.com https://slides.google.com
https://accounts.google.com https://*.google.com https://www.youtube.com https://share.descript.com'
content-type:
- application/json; charset=utf-8
etag:
- W/"2d7cdd2b5dfd9348b00b41c8d1949533"
expires:
- '0'
permissions-policy:
- camera=(), microphone=(self), geolocation=()
pragma:
- no-cache
referrer-policy:
- strict-origin-when-cross-origin
server-timing:
- cache_read.active_support;dur=0.05, cache_fetch_hit.active_support;dur=0.00,
cache_read_multi.active_support;dur=0.08, start_processing.action_controller;dur=0.00,
sql.active_record;dur=17.75, instantiation.active_record;dur=0.31, feature_operation.flipper;dur=0.03,
start_transaction.active_record;dur=0.00, transaction.active_record;dur=12.95,
process_action.action_controller;dur=339.15
vary:
- Accept
x-content-type-options:
- nosniff
x-frame-options:
- SAMEORIGIN
x-permitted-cross-domain-policies:
- none
x-request-id:
- c1055b9b-558b-454c-ad68-4a015818cb88
x-runtime:
- '0.386365'
x-xss-protection:
- 1; mode=block
status:
code: 201
message: Created
- request:
body: '{"events": [{"event_id": "0cc4e68a-6616-43f7-a52b-7850cbb49f5b", "timestamp":
"2025-10-08T18:18:08.551107+00:00", "type": "crew_kickoff_started", "event_data":
{"timestamp": "2025-10-08T18:18:08.159311+00:00", "type": "crew_kickoff_started",
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
"crew_name": "crew", "crew": null, "inputs": null}}, {"event_id": "4328757a-7427-4068-a5f8-8361d2e7a42e",
"timestamp": "2025-10-08T18:18:08.554388+00:00", "type": "task_started", "event_data":
{"task_description": "Give me an integer score between 1-5 for the following
title: ''The impact of AI in the future of work''", "expected_output": "The
score of the title.", "task_name": "Give me an integer score between 1-5 for
the following title: ''The impact of AI in the future of work''", "context":
"", "agent_role": "Crew Manager", "task_id": "5c23750c-affd-43fc-ad97-920bd15342e3"}},
{"event_id": "9c6a75ec-0aa2-400b-95c5-7eb9812726f5", "timestamp": "2025-10-08T18:18:08.554839+00:00",
"type": "agent_execution_started", "event_data": {"agent_role": "Crew Manager",
"agent_goal": "Manage the team to complete the task in the best way possible.",
"agent_backstory": "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."}},
{"event_id": "dfd6bc3a-7abd-4e12-ad0b-fa8589657dee", "timestamp": "2025-10-08T18:18:08.554930+00:00",
"type": "llm_call_started", "event_data": {"timestamp": "2025-10-08T18:18:08.554900+00:00",
"type": "llm_call_started", "source_fingerprint": null, "source_type": null,
"fingerprint_metadata": null, "task_name": "Give me an integer score between
1-5 for the following title: ''The impact of AI in the future of work''", "task_id":
"5c23750c-affd-43fc-ad97-920bd15342e3", "agent_id": "2fee0a63-ccf0-408a-9368-1b95eb6d628e",
"agent_role": "Crew Manager", "from_task": null, "from_agent": null, "model":
"gpt-4o", "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\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\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 absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\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 absolutely everything you know, don''t
reference things but instead explain them.\n\nIMPORTANT: Use the following format
in your response:\n\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 JSON object, enclosed in curly braces, using \"
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\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 expected criteria for your final answer:
The score of the title.\nyou MUST return the actual complete content as the
final answer, not a summary.\nEnsure your final answer contains only the content
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
not include any code block markers like ```json or ```python.\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:"}], "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler
object at 0x136aefd80>"], "available_functions": null}}, {"event_id": "58f2ed18-74e9-4e55-a925-41a6186c4e03",
"timestamp": "2025-10-08T18:18:08.558164+00:00", "type": "llm_call_completed",
"event_data": {"timestamp": "2025-10-08T18:18:08.558128+00:00", "type": "llm_call_completed",
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
"task_name": "Give me an integer score between 1-5 for the following title:
''The impact of AI in the future of work''", "task_id": "5c23750c-affd-43fc-ad97-920bd15342e3",
"agent_id": "2fee0a63-ccf0-408a-9368-1b95eb6d628e", "agent_role": "Crew Manager",
"from_task": null, "from_agent": null, "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\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\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 absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\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 absolutely everything you know, don''t
reference things but instead explain them.\n\nIMPORTANT: Use the following format
in your response:\n\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 JSON object, enclosed in curly braces, using \"
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\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 expected criteria for your final answer:
The score of the title.\nyou MUST return the actual complete content as the
final answer, not a summary.\nEnsure your final answer contains only the content
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
not include any code block markers like ```json or ```python.\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:"}], "response": "To provide the score for
the title \"The impact of AI in the future of work,\" I need to ask Scorer to
evaluate this based on the criteria they use. \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 this title based on your criteria for scoring titles. The context
for the scoring revolves entirely around the perceived impact of AI on the future
of work.\", \"coworker\": \"Scorer\"}", "call_type": "<LLMCallType.LLM_CALL:
''llm_call''>", "model": "gpt-4o"}}, {"event_id": "ad826003-5d03-4bcc-bdd9-6db229b0a419",
"timestamp": "2025-10-08T18:18:08.558720+00:00", "type": "tool_usage_started",
"event_data": {"timestamp": "2025-10-08T18:18:08.558636+00:00", "type": "tool_usage_started",
"source_fingerprint": "7ef5b626-3760-4b79-900f-65432b536f7c", "source_type":
"agent", "fingerprint_metadata": null, "agent_key": "6b5becc64d7e3c705a7d3784a5fab1d3",
"agent_role": "Crew Manager", "agent_id": null, "tool_name": "Ask question to
coworker", "tool_args": "{\"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 this title based on your criteria for scoring titles.
The context for the scoring revolves entirely around the perceived impact of
AI on the future of work.\", \"coworker\": \"Scorer\"}", "tool_class": "Ask
question to coworker", "run_attempts": null, "delegations": null, "agent": {"id":
"2fee0a63-ccf0-408a-9368-1b95eb6d628e", "role": "Crew Manager", "goal": "Manage
the team to complete the task in the best way possible.", "backstory": "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.", "cache": true,
"verbose": false, "max_rpm": null, "allow_delegation": true, "tools": [{"name":
"''Delegate work to coworker''", "description": "\"Tool Name: Delegate work
to coworker\\nTool Arguments: {''task'': {''description'': ''The task to delegate'',
''type'': ''str''}, ''context'': {''description'': ''The context for the task'',
''type'': ''str''}, ''coworker'': {''description'': ''The role/name of the coworker
to delegate to'', ''type'': ''str''}}\\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 absolutely everything
you know, don''t reference things but instead explain them.\"", "env_vars":
"[]", "args_schema": "<class ''crewai.tools.agent_tools.delegate_work_tool.DelegateWorkToolSchema''>",
"description_updated": "False", "cache_function": "<function BaseTool.<lambda>
at 0x1127be8e0>", "result_as_answer": "False", "max_usage_count": "None", "current_usage_count":
"0"}, {"name": "''Ask question to coworker''", "description": "\"Tool Name:
Ask question to coworker\\nTool Arguments: {''question'': {''description'':
''The question to ask'', ''type'': ''str''}, ''context'': {''description'':
''The context for the question'', ''type'': ''str''}, ''coworker'': {''description'':
''The role/name of the coworker to ask'', ''type'': ''str''}}\\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 absolutely everything you know, don''t reference things but
instead explain them.\"", "env_vars": "[]", "args_schema": "<class ''crewai.tools.agent_tools.ask_question_tool.AskQuestionToolSchema''>",
"description_updated": "False", "cache_function": "<function BaseTool.<lambda>
at 0x1127be8e0>", "result_as_answer": "False", "max_usage_count": "None", "current_usage_count":
"0"}], "max_iter": 25, "agent_executor": "<crewai.agents.crew_agent_executor.CrewAgentExecutor
object at 0x136ce03b0>", "llm": "<crewai.llm.LLM object at 0x136d04050>", "crew":
{"parent_flow": null, "name": "crew", "cache": true, "tasks": ["{''used_tools'':
0, ''tools_errors'': 0, ''delegations'': 0, ''i18n'': {''prompt_file'': None},
''name'': None, ''prompt_context'': '''', ''description'': \"Give me an integer
score between 1-5 for the following title: ''The impact of AI in the future
of work''\", ''expected_output'': ''The score of the title.'', ''config'': None,
''callback'': None, ''agent'': {''id'': UUID(''2fee0a63-ccf0-408a-9368-1b95eb6d628e''),
''role'': ''Crew Manager'', ''goal'': ''Manage the team to complete the task
in the best way possible.'', ''backstory'': \"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.\", ''cache'': True, ''verbose'': False,
''max_rpm'': None, ''allow_delegation'': True, ''tools'': [{''name'': ''Delegate
work to coworker'', ''description'': \"Tool Name: Delegate work to coworker\\nTool
Arguments: {''task'': {''description'': ''The task to delegate'', ''type'':
''str''}, ''context'': {''description'': ''The context for the task'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
delegate to'', ''type'': ''str''}}\\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 absolutely everything you
know, don''t reference things but instead explain them.\", ''env_vars'': [],
''args_schema'': <class ''crewai.tools.agent_tools.delegate_work_tool.DelegateWorkToolSchema''>,
''description_updated'': False, ''cache_function'': <function BaseTool.<lambda>
at 0x1127be8e0>, ''result_as_answer'': False, ''max_usage_count'': None, ''current_usage_count'':
0}, {''name'': ''Ask question to coworker'', ''description'': \"Tool Name: Ask
question to coworker\\nTool Arguments: {''question'': {''description'': ''The
question to ask'', ''type'': ''str''}, ''context'': {''description'': ''The
context for the question'', ''type'': ''str''}, ''coworker'': {''description'':
''The role/name of the coworker to ask'', ''type'': ''str''}}\\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 absolutely everything you know, don''t reference things but
instead explain them.\", ''env_vars'': [], ''args_schema'': <class ''crewai.tools.agent_tools.ask_question_tool.AskQuestionToolSchema''>,
''description_updated'': False, ''cache_function'': <function BaseTool.<lambda>
at 0x1127be8e0>, ''result_as_answer'': False, ''max_usage_count'': None, ''current_usage_count'':
0}], ''max_iter'': 25, ''agent_executor'': <crewai.agents.crew_agent_executor.CrewAgentExecutor
object at 0x136ce03b0>, ''llm'': <crewai.llm.LLM object at 0x136d04050>, ''crew'':
Crew(id=7237e268-30a9-4eca-b754-a6dea72b2dfc, process=Process.hierarchical,
number_of_agents=1, number_of_tasks=1), ''i18n'': {''prompt_file'': None}, ''cache_handler'':
{}, ''tools_handler'': <crewai.agents.tools_handler.ToolsHandler object at 0x136aef8b0>,
''tools_results'': [], ''max_tokens'': None, ''knowledge'': None, ''knowledge_sources'':
None, ''knowledge_storage'': None, ''security_config'': {''fingerprint'': {''metadata'':
{}}}, ''callbacks'': [], ''adapted_agent'': False, ''knowledge_config'': None},
''context'': NOT_SPECIFIED, ''async_execution'': False, ''output_json'': <class
''tests.test_task.test_output_json_hierarchical.<locals>.ScoreOutput''>, ''output_pydantic'':
None, ''output_file'': None, ''create_directory'': True, ''output'': None, ''tools'':
[], ''security_config'': {''fingerprint'': {''metadata'': {}}}, ''id'': UUID(''5c23750c-affd-43fc-ad97-920bd15342e3''),
''human_input'': False, ''markdown'': False, ''converter_cls'': None, ''processed_by_agents'':
{''Crew Manager''}, ''guardrail'': None, ''max_retries'': None, ''guardrail_max_retries'':
3, ''retry_count'': 0, ''start_time'': datetime.datetime(2025, 10, 8, 11, 18,
8, 554345), ''end_time'': None, ''allow_crewai_trigger_context'': None}"], "agents":
["{''id'': UUID(''16778b49-13e6-4cfc-bc0c-c95ebc698cb5''), ''role'': ''Scorer'',
''goal'': ''Score the title'', ''backstory'': \"You''re an expert scorer, specialized
in scoring titles.\", ''cache'': True, ''verbose'': False, ''max_rpm'': None,
''allow_delegation'': False, ''tools'': [], ''max_iter'': 25, ''agent_executor'':
<crewai.agents.crew_agent_executor.CrewAgentExecutor object at 0x136ce0290>,
''llm'': <crewai.llm.LLM object at 0x136a97950>, ''crew'': Crew(id=7237e268-30a9-4eca-b754-a6dea72b2dfc,
process=Process.hierarchical, number_of_agents=1, number_of_tasks=1), ''i18n'':
{''prompt_file'': None}, ''cache_handler'': {}, ''tools_handler'': <crewai.agents.tools_handler.ToolsHandler
object at 0x133fd0710>, ''tools_results'': [], ''max_tokens'': None, ''knowledge'':
None, ''knowledge_sources'': None, ''knowledge_storage'': None, ''security_config'':
{''fingerprint'': {''metadata'': {}}}, ''callbacks'': [], ''adapted_agent'':
False, ''knowledge_config'': None}"], "process": "hierarchical", "verbose":
false, "memory": false, "short_term_memory": null, "long_term_memory": null,
"entity_memory": null, "external_memory": null, "embedder": null, "usage_metrics":
null, "manager_llm": "<crewai.llm.LLM object at 0x136d04050>", "manager_agent":
{"id": "UUID(''2fee0a63-ccf0-408a-9368-1b95eb6d628e'')", "role": "''Crew Manager''",
"goal": "''Manage the team to complete the task in the best way possible.''",
"backstory": "\"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.\"", "cache": "True", "verbose": "False", "max_rpm": "None", "allow_delegation":
"True", "tools": "[{''name'': ''Delegate work to coworker'', ''description'':
\"Tool Name: Delegate work to coworker\\nTool Arguments: {''task'': {''description'':
''The task to delegate'', ''type'': ''str''}, ''context'': {''description'':
''The context for the task'', ''type'': ''str''}, ''coworker'': {''description'':
''The role/name of the coworker to delegate to'', ''type'': ''str''}}\\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 absolutely everything you know, don''t reference things but instead
explain them.\", ''env_vars'': [], ''args_schema'': <class ''crewai.tools.agent_tools.delegate_work_tool.DelegateWorkToolSchema''>,
''description_updated'': False, ''cache_function'': <function BaseTool.<lambda>
at 0x1127be8e0>, ''result_as_answer'': False, ''max_usage_count'': None, ''current_usage_count'':
0}, {''name'': ''Ask question to coworker'', ''description'': \"Tool Name: Ask
question to coworker\\nTool Arguments: {''question'': {''description'': ''The
question to ask'', ''type'': ''str''}, ''context'': {''description'': ''The
context for the question'', ''type'': ''str''}, ''coworker'': {''description'':
''The role/name of the coworker to ask'', ''type'': ''str''}}\\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 absolutely everything you know, don''t reference things but
instead explain them.\", ''env_vars'': [], ''args_schema'': <class ''crewai.tools.agent_tools.ask_question_tool.AskQuestionToolSchema''>,
''description_updated'': False, ''cache_function'': <function BaseTool.<lambda>
at 0x1127be8e0>, ''result_as_answer'': False, ''max_usage_count'': None, ''current_usage_count'':
0}]", "max_iter": "25", "agent_executor": "<crewai.agents.crew_agent_executor.CrewAgentExecutor
object at 0x136ce03b0>", "llm": "<crewai.llm.LLM object at 0x136d04050>", "crew":
"Crew(id=7237e268-30a9-4eca-b754-a6dea72b2dfc, process=Process.hierarchical,
number_of_agents=1, number_of_tasks=1)", "i18n": "{''prompt_file'': None}",
"cache_handler": "{}", "tools_handler": "<crewai.agents.tools_handler.ToolsHandler
object at 0x136aef8b0>", "tools_results": "[]", "max_tokens": "None", "knowledge":
"None", "knowledge_sources": "None", "knowledge_storage": "None", "security_config":
"{''fingerprint'': {''metadata'': {}}}", "callbacks": "[]", "adapted_agent":
"False", "knowledge_config": "None"}, "function_calling_llm": null, "config":
null, "id": "7237e268-30a9-4eca-b754-a6dea72b2dfc", "share_crew": false, "step_callback":
null, "task_callback": null, "before_kickoff_callbacks": [], "after_kickoff_callbacks":
[], "max_rpm": null, "prompt_file": null, "output_log_file": null, "planning":
false, "planning_llm": null, "task_execution_output_json_files": null, "execution_logs":
[], "knowledge_sources": null, "chat_llm": null, "knowledge": null, "security_config":
{"fingerprint": "{''metadata'': {}}"}, "token_usage": null, "tracing": false},
"i18n": {"prompt_file": null}, "cache_handler": {}, "tools_handler": "<crewai.agents.tools_handler.ToolsHandler
object at 0x136aef8b0>", "tools_results": [], "max_tokens": null, "knowledge":
null, "knowledge_sources": null, "knowledge_storage": null, "security_config":
{"fingerprint": {"metadata": "{}"}}, "callbacks": [], "adapted_agent": false,
"knowledge_config": null, "max_execution_time": null, "agent_ops_agent_name":
"Crew Manager", "agent_ops_agent_id": null, "step_callback": null, "use_system_prompt":
true, "function_calling_llm": null, "system_template": null, "prompt_template":
null, "response_template": null, "allow_code_execution": false, "respect_context_window":
true, "max_retry_limit": 2, "multimodal": false, "inject_date": false, "date_format":
"%Y-%m-%d", "code_execution_mode": "safe", "reasoning": false, "max_reasoning_attempts":
null, "embedder": null, "agent_knowledge_context": null, "crew_knowledge_context":
null, "knowledge_search_query": null, "from_repository": null, "guardrail":
null, "guardrail_max_retries": 3}, "task_name": "Give me an integer score between
1-5 for the following title: ''The impact of AI in the future of work''", "task_id":
"5c23750c-affd-43fc-ad97-920bd15342e3", "from_task": null, "from_agent": null}},
{"event_id": "b666ec5d-63b6-4d97-86f9-7ce85babdadd", "timestamp": "2025-10-08T18:18:08.560511+00:00",
"type": "agent_execution_started", "event_data": {"agent_role": "Scorer", "agent_goal":
"Score the title", "agent_backstory": "You''re an expert scorer, specialized
in scoring titles."}}, {"event_id": "ab280ea3-e649-4ed5-87f1-00363f28a5c9",
"timestamp": "2025-10-08T18:18:08.560588+00:00", "type": "llm_call_started",
"event_data": {"timestamp": "2025-10-08T18:18:08.560564+00:00", "type": "llm_call_started",
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
"task_name": "Can you provide an integer score between 1-5 for the title ''The
impact of AI in the future of work''?", "task_id": "d249cc86-962d-45ff-848d-46ebf36fb14f",
"agent_id": "16778b49-13e6-4cfc-bc0c-c95ebc698cb5", "agent_role": "Scorer",
"from_task": null, "from_agent": null, "model": "gpt-4o-mini", "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 respond using 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 expected 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
this title based on your criteria for scoring titles. The context for the scoring
revolves entirely around the perceived impact of AI on the future of work.\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:"}], "tools": null, "callbacks":
["<crewai.utilities.token_counter_callback.TokenCalcHandler object at 0x136cad8b0>"],
"available_functions": null}}, {"event_id": "4c9b120f-bed5-4398-8a53-7e581b552a04",
"timestamp": "2025-10-08T18:18:08.564442+00:00", "type": "llm_call_completed",
"event_data": {"timestamp": "2025-10-08T18:18:08.564412+00:00", "type": "llm_call_completed",
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
"task_name": "Can you provide an integer score between 1-5 for the title ''The
impact of AI in the future of work''?", "task_id": "d249cc86-962d-45ff-848d-46ebf36fb14f",
"agent_id": "16778b49-13e6-4cfc-bc0c-c95ebc698cb5", "agent_role": "Scorer",
"from_task": null, "from_agent": null, "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 respond using 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 expected 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 this title based on
your criteria for scoring titles. The context for the scoring revolves entirely
around the perceived impact of AI on the future of work.\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:"}], "response": "Thought: I now can give a great
answer\nFinal Answer: 4 - The title ''The impact of AI in the future of work''
is clear and directly addresses a timely and significant topic that is highly
relevant in today''s context. However, it could be made even more specific to
immediately hook the reader or audience.", "call_type": "<LLMCallType.LLM_CALL:
''llm_call''>", "model": "gpt-4o-mini"}}, {"event_id": "c3ab05fd-538f-43af-b3cf-459efac2e3f9",
"timestamp": "2025-10-08T18:18:08.564558+00:00", "type": "agent_execution_completed",
"event_data": {"agent_role": "Scorer", "agent_goal": "Score the title", "agent_backstory":
"You''re an expert scorer, specialized in scoring titles."}}, {"event_id": "ac4cb494-7cea-4335-8975-27afbe134b6f",
"timestamp": "2025-10-08T18:18:08.564704+00:00", "type": "tool_usage_finished",
"event_data": {"timestamp": "2025-10-08T18:18:08.564655+00:00", "type": "tool_usage_finished",
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
"agent_key": "6b5becc64d7e3c705a7d3784a5fab1d3", "agent_role": "Crew Manager",
"agent_id": null, "tool_name": "Ask question to coworker", "tool_args": {"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 this title based
on your criteria for scoring titles. The context for the scoring revolves entirely
around the perceived impact of AI on the future of work.", "coworker": "Scorer"},
"tool_class": "CrewStructuredTool", "run_attempts": 1, "delegations": 1, "agent":
null, "task_name": "Give me an integer score between 1-5 for the following title:
''The impact of AI in the future of work''", "task_id": "5c23750c-affd-43fc-ad97-920bd15342e3",
"from_task": null, "from_agent": null, "started_at": "2025-10-08T11:18:08.559118",
"finished_at": "2025-10-08T11:18:08.564633", "from_cache": false, "output":
"4 - The title ''The impact of AI in the future of work'' is clear and directly
addresses a timely and significant topic that is highly relevant in today''s
context. However, it could be made even more specific to immediately hook the
reader or audience."}}, {"event_id": "96c713d7-689d-430b-afbc-aa38998c1988",
"timestamp": "2025-10-08T18:18:08.564815+00:00", "type": "llm_call_started",
"event_data": {"timestamp": "2025-10-08T18:18:08.564794+00:00", "type": "llm_call_started",
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
"task_name": "Give me an integer score between 1-5 for the following title:
''The impact of AI in the future of work''", "task_id": "5c23750c-affd-43fc-ad97-920bd15342e3",
"agent_id": "2fee0a63-ccf0-408a-9368-1b95eb6d628e", "agent_role": "Crew Manager",
"from_task": null, "from_agent": null, "model": "gpt-4o", "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\nTool Arguments: {''task'': {''description'': ''The task to
delegate'', ''type'': ''str''}, ''context'': {''description'': ''The context
for the task'', ''type'': ''str''}, ''coworker'': {''description'': ''The role/name
of the coworker to delegate to'', ''type'': ''str''}}\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 absolutely
everything you know, don''t reference things but instead explain them.\nTool
Name: Ask question to coworker\nTool Arguments: {''question'': {''description'':
''The question to ask'', ''type'': ''str''}, ''context'': {''description'':
''The context for the question'', ''type'': ''str''}, ''coworker'': {''description'':
''The role/name of the coworker to ask'', ''type'': ''str''}}\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 absolutely everything you know, don''t reference things but
instead explain them.\n\nIMPORTANT: Use the following format in your response:\n\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
JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\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 expected criteria
for your final answer: The score of the title.\nyou MUST return the actual complete
content as the final answer, not a summary.\nEnsure your final answer contains
only the content in the following format: {\n \"score\": int\n}\n\nEnsure the
final output does not include any code block markers like ```json or ```python.\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 the score for the title \"The impact of AI in the future of work,\"
I need to ask Scorer to evaluate this based on the criteria they use. \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 this title based on your criteria
for scoring titles. The context for the scoring revolves entirely around the
perceived impact of AI on the future of work.\", \"coworker\": \"Scorer\"}\nObservation:
4 - The title ''The impact of AI in the future of work'' is clear and directly
addresses a timely and significant topic that is highly relevant in today''s
context. However, it could be made even more specific to immediately hook the
reader or audience."}], "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler
object at 0x136aefd80>"], "available_functions": null}}, {"event_id": "d51c432f-8ae5-4c42-8b24-317a494ec4bd",
"timestamp": "2025-10-08T18:18:08.567836+00:00", "type": "llm_call_completed",
"event_data": {"timestamp": "2025-10-08T18:18:08.567811+00:00", "type": "llm_call_completed",
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
"task_name": "Give me an integer score between 1-5 for the following title:
''The impact of AI in the future of work''", "task_id": "5c23750c-affd-43fc-ad97-920bd15342e3",
"agent_id": "2fee0a63-ccf0-408a-9368-1b95eb6d628e", "agent_role": "Crew Manager",
"from_task": null, "from_agent": null, "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\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\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 absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\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 absolutely everything you know, don''t
reference things but instead explain them.\n\nIMPORTANT: Use the following format
in your response:\n\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 JSON object, enclosed in curly braces, using \"
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\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 expected criteria for your final answer:
The score of the title.\nyou MUST return the actual complete content as the
final answer, not a summary.\nEnsure your final answer contains only the content
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
not include any code block markers like ```json or ```python.\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 the score for the title \"The impact of AI in the future of work,\"
I need to ask Scorer to evaluate this based on the criteria they use. \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 this title based on your criteria
for scoring titles. The context for the scoring revolves entirely around the
perceived impact of AI on the future of work.\", \"coworker\": \"Scorer\"}\nObservation:
4 - The title ''The impact of AI in the future of work'' is clear and directly
addresses a timely and significant topic that is highly relevant in today''s
context. However, it could be made even more specific to immediately hook the
reader or audience."}], "response": "Thought: I have received the score from
Scorer.\n\nFinal Answer: 4 - The title ''The impact of AI in the future of work''
is clear and directly addresses a timely and significant topic that is highly
relevant in today''s context. However, it could be made even more specific to
immediately hook the reader or audience.", "call_type": "<LLMCallType.LLM_CALL:
''llm_call''>", "model": "gpt-4o"}}, {"event_id": "6edb30ea-b452-4983-8442-d0fd34aadc6f",
"timestamp": "2025-10-08T18:18:08.567937+00:00", "type": "agent_execution_completed",
"event_data": {"agent_role": "Crew Manager", "agent_goal": "Manage the team
to complete the task in the best way possible.", "agent_backstory": "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."}}, {"event_id":
"f365ca78-ddbf-43bd-ac3e-ce31457800b9", "timestamp": "2025-10-08T18:18:08.571375+00:00",
"type": "task_completed", "event_data": {"task_description": "Give me an integer
score between 1-5 for the following title: ''The impact of AI in the future
of work''", "task_name": "Give me an integer score between 1-5 for the following
title: ''The impact of AI in the future of work''", "task_id": "5c23750c-affd-43fc-ad97-920bd15342e3",
"output_raw": "4 - The title ''The impact of AI in the future of work'' is clear
and directly addresses a timely and significant topic that is highly relevant
in today''s context. However, it could be made even more specific to immediately
hook the reader or audience.", "output_format": "OutputFormat.JSON", "agent_role":
"Crew Manager"}}, {"event_id": "5e2ac85b-d76c-4b38-b2b6-fd0e06f0ad41", "timestamp":
"2025-10-08T18:18:08.572521+00:00", "type": "crew_kickoff_completed", "event_data":
{"timestamp": "2025-10-08T18:18:08.572500+00:00", "type": "crew_kickoff_completed",
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
"crew_name": "crew", "crew": null, "output": {"description": "Give me an integer
score between 1-5 for the following title: ''The impact of AI in the future
of work''", "name": "Give me an integer score between 1-5 for the following
title: ''The impact of AI in the future of work''", "expected_output": "The
score of the title.", "summary": "Give me an integer score between 1-5 for the
following...", "raw": "4 - The title ''The impact of AI in the future of work''
is clear and directly addresses a timely and significant topic that is highly
relevant in today''s context. However, it could be made even more specific to
immediately hook the reader or audience.", "pydantic": null, "json_dict": {"score":
4}, "agent": "Crew Manager", "output_format": "json"}, "total_tokens": 1996}}],
"batch_metadata": {"events_count": 16, "batch_sequence": 1, "is_final_batch":
false}}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate, zstd
Connection:
- keep-alive
Content-Length:
- '42639'
Content-Type:
- application/json
User-Agent:
- CrewAI-CLI/0.201.1
X-Crewai-Organization-Id:
- d3a3d10c-35db-423f-a7a4-c026030ba64d
X-Crewai-Version:
- 0.201.1
method: POST
uri: http://localhost:3000/crewai_plus/api/v1/tracing/batches/1a5c71d1-4e28-4432-aa20-c7ef93a2657b/events
response:
body:
string: '{"events_created":16,"trace_batch_id":"6ce9315e-6cf2-47fc-8bbe-38f1ecfde6e0"}'
headers:
Content-Length:
- '77'
cache-control:
- no-store
content-security-policy:
- 'default-src ''self'' *.crewai.com crewai.com; script-src ''self'' ''unsafe-inline''
*.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com
https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
https://js-na1.hs-scripts.com https://share.descript.com/; style-src ''self''
''unsafe-inline'' *.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts;
img-src ''self'' data: *.crewai.com crewai.com https://zeus.tools.crewai.com
https://dashboard.tools.crewai.com https://cdn.jsdelivr.net; font-src ''self''
data: *.crewai.com crewai.com; connect-src ''self'' *.crewai.com crewai.com
https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/*
https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/
https://*.sentry.io https://www.google-analytics.com ws://localhost:3036 wss://localhost:3036;
frame-src ''self'' *.crewai.com crewai.com https://connect.useparagon.com/
https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/
https://docs.google.com https://drive.google.com https://slides.google.com
https://accounts.google.com https://*.google.com https://www.youtube.com https://share.descript.com'
content-type:
- application/json; charset=utf-8
etag:
- W/"3acf767046d524a3f23c35c4eea8012e"
expires:
- '0'
permissions-policy:
- camera=(), microphone=(self), geolocation=()
pragma:
- no-cache
referrer-policy:
- strict-origin-when-cross-origin
server-timing:
- cache_read.active_support;dur=0.06, cache_fetch_hit.active_support;dur=0.00,
cache_read_multi.active_support;dur=0.11, start_processing.action_controller;dur=0.00,
sql.active_record;dur=74.18, instantiation.active_record;dur=0.41, start_transaction.active_record;dur=0.00,
transaction.active_record;dur=173.74, process_action.action_controller;dur=538.57
vary:
- Accept
x-content-type-options:
- nosniff
x-frame-options:
- SAMEORIGIN
x-permitted-cross-domain-policies:
- none
x-request-id:
- 5617642e-2f52-47be-8b68-5ed5ae18d869
x-runtime:
- '0.589363'
x-xss-protection:
- 1; mode=block
status:
code: 200
message: OK
- request:
body: '{"status": "completed", "duration_ms": 1014, "final_event_count": 16}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate, zstd
Connection:
- keep-alive
Content-Length:
- '69'
Content-Type:
- application/json
User-Agent:
- CrewAI-CLI/0.201.1
X-Crewai-Organization-Id:
- d3a3d10c-35db-423f-a7a4-c026030ba64d
X-Crewai-Version:
- 0.201.1
method: PATCH
uri: http://localhost:3000/crewai_plus/api/v1/tracing/batches/1a5c71d1-4e28-4432-aa20-c7ef93a2657b/finalize
response:
body:
string: '{"id":"6ce9315e-6cf2-47fc-8bbe-38f1ecfde6e0","trace_id":"1a5c71d1-4e28-4432-aa20-c7ef93a2657b","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"completed","duration_ms":1014,"crewai_version":"0.201.1","privacy_level":"standard","total_events":16,"execution_context":{"crew_name":"crew","flow_name":null,"privacy_level":"standard","crewai_version":"0.201.1","crew_fingerprint":null},"created_at":"2025-10-08T18:18:08.537Z","updated_at":"2025-10-08T18:18:09.514Z"}'
headers:
Content-Length:
- '483'
cache-control:
- no-store
content-security-policy:
- 'default-src ''self'' *.crewai.com crewai.com; script-src ''self'' ''unsafe-inline''
*.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com
https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
https://js-na1.hs-scripts.com https://share.descript.com/; style-src ''self''
''unsafe-inline'' *.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts;
img-src ''self'' data: *.crewai.com crewai.com https://zeus.tools.crewai.com
https://dashboard.tools.crewai.com https://cdn.jsdelivr.net; font-src ''self''
data: *.crewai.com crewai.com; connect-src ''self'' *.crewai.com crewai.com
https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/*
https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/
https://*.sentry.io https://www.google-analytics.com ws://localhost:3036 wss://localhost:3036;
frame-src ''self'' *.crewai.com crewai.com https://connect.useparagon.com/
https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/
https://docs.google.com https://drive.google.com https://slides.google.com
https://accounts.google.com https://*.google.com https://www.youtube.com https://share.descript.com'
content-type:
- application/json; charset=utf-8
etag:
- W/"b84badb75e9dd6b55f201454666620d6"
expires:
- '0'
permissions-policy:
- camera=(), microphone=(self), geolocation=()
pragma:
- no-cache
referrer-policy:
- strict-origin-when-cross-origin
server-timing:
- cache_read.active_support;dur=0.04, cache_fetch_hit.active_support;dur=0.00,
cache_read_multi.active_support;dur=0.07, start_processing.action_controller;dur=0.00,
sql.active_record;dur=10.32, instantiation.active_record;dur=0.40, unpermitted_parameters.action_controller;dur=0.01,
start_transaction.active_record;dur=0.01, transaction.active_record;dur=2.89,
process_action.action_controller;dur=302.38
vary:
- Accept
x-content-type-options:
- nosniff
x-frame-options:
- SAMEORIGIN
x-permitted-cross-domain-policies:
- none
x-request-id:
- d01f9af8-6a51-4e9a-bd04-30396c5323bf
x-runtime:
- '0.337087'
x-xss-protection:
- 1; mode=block
status:
code: 200
message: OK
version: 1
Reference in New Issue View Git Blame Copy Permalink