mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-09 08:08:32 +00:00
7addda9398
Some checks failed
Notify Downstream / notify-downstream (push) Has been cancelled
* feat: implement tool usage limit exception handling - Introduced `ToolUsageLimitExceeded` exception to manage maximum usage limits for tools. - Enhanced `CrewStructuredTool` to check and raise this exception when the usage limit is reached. - Updated `_run` and `_execute` methods to include usage limit checks and handle exceptions appropriately, improving reliability and user feedback. * feat: enhance PlusAPI and ToolUsage with task metadata - Removed the `send_trace_batch` method from PlusAPI to streamline the API. - Added timeout parameters to trace event methods in PlusAPI for improved reliability. - Updated ToolUsage to include task metadata (task name and ID) in event emissions, enhancing traceability and context during tool usage. - Refactored event handling in LLM and ToolUsage events to ensure task information is consistently captured. * feat: enhance memory and event handling with task and agent metadata - Added task and agent metadata to various memory and event classes, improving traceability and context during memory operations. - Updated the `ContextualMemory` and `Memory` classes to associate tasks and agents, allowing for better context management. - Enhanced event emissions in `LLM`, `ToolUsage`, and memory events to include task and agent information, facilitating improved debugging and monitoring. - Refactored event handling to ensure consistent capture of task and agent details across the system. * drop * refactor: clean up unused imports in memory and event modules - Removed unused TYPE_CHECKING imports from long_term_memory.py to streamline the code. - Eliminated unnecessary import from memory_events.py, enhancing clarity and maintainability. * fix memory tests * fix task_completed payload * fix: remove unused test agent variable in external memory tests * refactor: remove unused agent parameter from Memory class save method - Eliminated the agent parameter from the save method in the Memory class to streamline the code and improve clarity. - Updated the TraceBatchManager class by moving initialization of attributes into the constructor for better organization and readability. * refactor: enhance ExecutionState and ReasoningEvent classes with optional task and agent identifiers - Added optional `current_agent_id` and `current_task_id` attributes to the `ExecutionState` class for better tracking of agent and task states. - Updated the `from_task` attribute in the `ReasoningEvent` class to use `Optional[Any]` instead of a specific type, improving flexibility in event handling. * refactor: update ExecutionState class by removing unused agent and task identifiers - Removed the `current_agent_id` and `current_task_id` attributes from the `ExecutionState` class to simplify the code and enhance clarity. - Adjusted the import statements to include `Optional` for better type handling. * refactor: streamline LLM event handling in LiteAgent - Removed unused LLM event emissions (LLMCallStartedEvent, LLMCallCompletedEvent, LLMCallFailedEvent) from the LiteAgent class to simplify the code and improve performance. - Adjusted the flow of LLM response handling by eliminating unnecessary event bus interactions, enhancing clarity and maintainability. * flow ownership and not emitting events when a crew is done * refactor: remove unused agent parameter from ShortTermMemory save method - Eliminated the agent parameter from the save method in the ShortTermMemory class to streamline the code and improve clarity. - This change enhances the maintainability of the memory management system by reducing unnecessary complexity. * runtype check fix * fixing tests * fix lints * fix: update event assertions in test_llm_emits_event_with_lite_agent - Adjusted the expected counts for completed and started events in the test to reflect the correct behavior of the LiteAgent. - Updated assertions for agent roles and IDs to match the expected values after recent changes in event handling. * fix: update task name assertions in event tests - Modified assertions in `test_stream_llm_emits_event_with_task_and_agent_info` and `test_llm_emits_event_with_task_and_agent_info` to use `task.description` as a fallback for `task.name`. This ensures that the tests correctly validate the task name even when it is not explicitly set. * fix: update test assertions for output values and improve readability - Updated assertions in `test_output_json_dict_hierarchical` to reflect the correct expected score value. - Enhanced readability of assertions in `test_output_pydantic_to_another_task` and `test_key` by formatting the error messages for clarity. - These changes ensure that the tests accurately validate the expected outputs and improve overall code quality. * test fixes * fix crew_test * added another fixture * fix: ensure agent and task assignments in contextual memory are conditional - Updated the ContextualMemory class to check for the existence of short-term, long-term, external, and extended memory before assigning agent and task attributes. This prevents potential attribute errors when memory types are not initialized.
1194 lines
54 KiB
YAML
1194 lines
54 KiB
YAML
interactions:
|
|
- request:
|
|
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
|
|
are a seasoned manager with a knack for getting the best out of your team.\nYou
|
|
are also known for your ability to delegate work to the right people, and to
|
|
ask the right questions to get the best out of your team.\nEven though you don''t
|
|
perform tasks by yourself, you have a lot of experience in the field, which
|
|
allows you to properly evaluate the work of your team members.\nYour personal
|
|
goal is: Manage the team to complete the task in the best way possible.\nYou
|
|
ONLY have access to the following tools, and should NEVER make up tools that
|
|
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
|
|
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
|
|
specific task to one of the following coworkers: Scorer\nThe input to this tool
|
|
should be the coworker, the task you want them to do, and ALL necessary context
|
|
to execute the task, they know nothing about the task, so share absolute everything
|
|
you know, don''t reference things but instead explain them.\nTool Arguments:
|
|
{''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'':
|
|
''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
|
|
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
|
|
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
|
|
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
|
|
coworkers: Scorer\nThe input to this tool should be the coworker, the question
|
|
you have for them, and ALL necessary context to ask the question properly, they
|
|
know nothing about the question, so share absolute everything you know, don''t
|
|
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
|
|
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
|
|
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
|
|
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
|
|
format:\n\nThought: you should always think about what to do\nAction: the action
|
|
to take, only one name of [Delegate work to coworker, Ask question to coworker],
|
|
just the name, exactly as it''s written.\nAction Input: the input to the action,
|
|
just a simple python dictionary, enclosed in curly braces, using \" to wrap
|
|
keys and values.\nObservation: the result of the action\n\nOnce all necessary
|
|
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
|
|
the final answer to the original input question\n"}, {"role": "user", "content":
|
|
"\nCurrent Task: Give me an integer score between 1-5 for the following title:
|
|
''The impact of AI in the future of work''\n\nThis is the expect criteria for
|
|
your final answer: The score of the title.\nyou MUST return the actual complete
|
|
content as the final answer, not a summary.\n\nBegin! This is VERY important
|
|
to you, use the tools available and give your best Final Answer, your job depends
|
|
on it!\n\nThought:"}], "model": "gpt-4o"}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '2986'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=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-AB7g8URGcdob5DuebCrqcqCaXJczj\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1727214488,\n \"model\": \"gpt-4o-2024-05-13\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"To give an accurate score between 1-5
|
|
for the title \\\"The impact of AI in the future of work,\\\" I need to engage
|
|
Scorer to evaluate it based on the criteria they have.\\n\\nAction: Ask question
|
|
to coworker\\nAction Input: {\\\"question\\\": \\\"Can you provide an integer
|
|
score between 1-5 for the title 'The impact of AI in the future of work'?\\\",
|
|
\\\"context\\\": \\\"We need to evaluate the title 'The impact of AI in the
|
|
future of work' according to its quality, relevance, and appeal. Please provide
|
|
a score between 1-5, where 1 is the lowest and 5 is the highest.\\\", \\\"coworker\\\":
|
|
\\\"Scorer\\\"}\\n\\nObservation:\",\n \"refusal\": null\n },\n
|
|
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
|
\ \"usage\": {\n \"prompt_tokens\": 664,\n \"completion_tokens\": 146,\n
|
|
\ \"total_tokens\": 810,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
|
|
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 8c85fa1909cf1cf3-GRU
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Tue, 24 Sep 2024 21:48:10 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:
|
|
- '2091'
|
|
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_9aa3183c20ac41471d1d107854e4e502
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: !!binary |
|
|
CvwLCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS0wsKEgoQY3Jld2FpLnRl
|
|
bGVtZXRyeRKQAgoQaiW7ExV7PFmNK7y6QbFQCBIImZxnjiAjQxAqDlRhc2sgRXhlY3V0aW9uMAE5
|
|
SAbHe2xM+BdBsAAxE21M+BdKLgoIY3Jld19rZXkSIgogNWU2ZWZmZTY4MGE1ZDk3ZGMzODczYjE0
|
|
ODI1Y2NmYTNKMQoHY3Jld19pZBImCiQ5MGEwOTY1Ny0xNDY3LTQzMmMtYjQwZS02M2QzYTRhNzNl
|
|
ZmJKLgoIdGFza19rZXkSIgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFz
|
|
a19pZBImCiRkOTdlMDUyOS02NTY0LTQ4YmUtYjllZC0xOGJjNjdhMmE2OTJ6AhgBhQEAAQAAEpgH
|
|
ChD2aXxrYF5W85yKqjVQe0rTEgiizow4hqpQaSoMQ3JldyBDcmVhdGVkMAE5kM3nE21M+BdBgAvs
|
|
E21M+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMu
|
|
MTEuN0ouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4MjVjY2ZhM0oxCgdj
|
|
cmV3X2lkEiYKJDFjZWJhZTk5LWYwNmQtNDEzYS05N2ExLWRlZWU1NjU3ZWFjNkoeCgxjcmV3X3By
|
|
b2Nlc3MSDgoMaGllcmFyY2hpY2FsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9v
|
|
Zl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrIAgoLY3Jld19hZ2VudHMS
|
|
uAIKtQJbeyJrZXkiOiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQiOiAi
|
|
NjU5N2NhNWMtYzIyMS00ZDM4LTg1MTItMjMwNTFjYjMxZThlIiwgInJvbGUiOiAiU2NvcmVyIiwg
|
|
InZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDE1LCAibWF4X3JwbSI6IG51bGwsICJmdW5j
|
|
dGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJs
|
|
ZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9s
|
|
aW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K+wEKCmNyZXdfdGFza3MS7AEK6QFbeyJrZXki
|
|
OiAiMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODYiLCAiaWQiOiAiNTUyNDkzYjAtYWY0
|
|
Ny00ZWYwLTgzY2MtYjBiZGMzNTFlZjY3IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1
|
|
bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTY29yZXIiLCAiYWdlbnRfa2V5Ijog
|
|
IjkyZTdlYjE5MTY2NGM5MzU3ODVlZDdkNDI0MGEyOTRkIiwgInRvb2xzX25hbWVzIjogW119XXoC
|
|
GAGFAQABAAASjgIKEBqy7yzvVJE6v2HuRtisU48SCIGXqca8/TSDKgxUYXNrIENyZWF0ZWQwATkA
|
|
hAYVbUz4F0EQKAcVbUz4F0ouCghjcmV3X2tleRIiCiA1ZTZlZmZlNjgwYTVkOTdkYzM4NzNiMTQ4
|
|
MjVjY2ZhM0oxCgdjcmV3X2lkEiYKJDFjZWJhZTk5LWYwNmQtNDEzYS05N2ExLWRlZWU1NjU3ZWFj
|
|
NkouCgh0YXNrX2tleRIiCiAyN2VmMzhjYzk5ZGE0YThkZWQ3MGVkNDA2ZTQ0YWI4NkoxCgd0YXNr
|
|
X2lkEiYKJDU1MjQ5M2IwLWFmNDctNGVmMC04M2NjLWIwYmRjMzUxZWY2N3oCGAGFAQABAAA=
|
|
headers:
|
|
Accept:
|
|
- '*/*'
|
|
Accept-Encoding:
|
|
- gzip, deflate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Length:
|
|
- '1535'
|
|
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 21:48:12 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 the title ''The impact of AI in the future of work''
|
|
according to its quality, relevance, and appeal. Please provide a score between
|
|
1-5, where 1 is the lowest and 5 is the highest.\n\nBegin! This is VERY important
|
|
to you, use the tools available and give your best Final Answer, your job depends
|
|
on it!\n\nThought:"}], "model": "gpt-4o"}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1220'
|
|
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-AB7gBKY8RwpfJc5mSVrH1WmeT5L5z\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1727214491,\n \"model\": \"gpt-4o-2024-05-13\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
|
|
Answer: I would score the title 'The impact of AI in the future of work' a 4
|
|
out of 5. The title is clear, relevant, and appealing as it addresses a highly
|
|
topical subject with significant interest in both the academic and professional
|
|
communities. It implies a forward-looking analysis which can attract various
|
|
stakeholders interested in the future trends of employment, technology, and
|
|
society. The only improvement could be to make it slightly more specific or
|
|
engaging to ensure maximum impact.\",\n \"refusal\": null\n },\n
|
|
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
|
\ \"usage\": {\n \"prompt_tokens\": 255,\n \"completion_tokens\": 106,\n
|
|
\ \"total_tokens\": 361,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
|
|
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 8c85fa2878d21cf3-GRU
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Tue, 24 Sep 2024 21:48:12 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:
|
|
- '1460'
|
|
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:
|
|
- '29999705'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 0s
|
|
x-request-id:
|
|
- req_5d6460275a26c2b5a187d8e8cec85215
|
|
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 give an accurate
|
|
score between 1-5 for the title \"The impact of AI in the future of work,\"
|
|
I need to engage Scorer to evaluate it based on the criteria they have.\n\nAction:
|
|
Ask question to coworker\nAction Input: {\"question\": \"Can you provide an
|
|
integer score between 1-5 for the title ''The impact of AI in the future of
|
|
work''?\", \"context\": \"We need to evaluate the title ''The impact of AI in
|
|
the future of work'' according to its quality, relevance, and appeal. Please
|
|
provide a score between 1-5, where 1 is the lowest and 5 is the highest.\",
|
|
\"coworker\": \"Scorer\"}\n\nObservation:\nObservation: I would score the title
|
|
''The impact of AI in the future of work'' a 4 out of 5. The title is clear,
|
|
relevant, and appealing as it addresses a highly topical subject with significant
|
|
interest in both the academic and professional communities. It implies a forward-looking
|
|
analysis which can attract various stakeholders interested in the future trends
|
|
of employment, technology, and society. The only improvement could be to make
|
|
it slightly more specific or engaging to ensure maximum impact."}], "model":
|
|
"gpt-4o"}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '4129'
|
|
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-AB7gClsVUQLww5J3bHB40NunZxQTa\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1727214492,\n \"model\": \"gpt-4o-2024-05-13\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"Thought: I now know the final answer.\\n\\nFinal
|
|
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
|
|
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
|
909,\n \"completion_tokens\": 14,\n \"total_tokens\": 923,\n \"completion_tokens_details\":
|
|
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 8c85fa3348301cf3-GRU
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Tue, 24 Sep 2024 21:48:13 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:
|
|
- '298'
|
|
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:
|
|
- '29998996'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 2ms
|
|
x-request-id:
|
|
- req_78324a4c53dc4f87327b0e1060b0b445
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "4"}, {"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:
|
|
- '615'
|
|
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-AB7gDkv4V1cMJ6IVFldUfx5aJ54mS\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1727214493,\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_E79eAVdZeKx6iitt2tQLfiT6\",\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\":
|
|
100,\n \"completion_tokens\": 5,\n \"total_tokens\": 105,\n \"completion_tokens_details\":
|
|
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 8c85fa377e391cf3-GRU
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Tue, 24 Sep 2024 21:48:13 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:
|
|
- '220'
|
|
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:
|
|
- '29999947'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 0s
|
|
x-request-id:
|
|
- req_d13285e05176425b72094c7e74370ab6
|
|
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
|
|
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 |
|
|
H4sIAAAAAAAAAwAAAP//jFRNb9swDL3nVxC69JIESZukrW9Dt0MxbNi6HQbMRaBItM1WkTSRTjYU
|
|
/e+D7KTOvoBdDFmPpN57IvU0AlBkVQHKNFrMNrrJzdVm9vZuER8u7lbz9zfvPlzSbvXmo919ebg7
|
|
V+OcETYPaOSYNTVhGx0KBd/DJqEWzFXnl8vVfLW4ni06YBssupxWR5kswuR8dr6YzK4ms9UhsQlk
|
|
kFUBX0cAAE/dN1P0Fr+rAmbj484WmXWNqngJAlApuLyjNDOxaC9qPIAmeEHfsf7chLZupIDPDYJo
|
|
foSE31pKyKCBTUgIEmCDkAvVHm3+lRxL4hBKlfNoG7URCBW8ugXyHV610ibMe/uQHksFG81oIXjg
|
|
iIYqMmASCSbSU7gFbkLrLFh0WGtBkIa453M471PmksawbwIQQ0KOwTNtHEIVEuBOu1YL+Rq0tx3z
|
|
vO5Y8rT0pX9l8rUU8Pp4ROaVq5uQV5iOIXDrYysFPJUqEyhVAaX61FtxFF7A2f8JPyvVGMre8e/S
|
|
1/qQwo4sgvZAXrDGdHB6g7JH9DCfLAe7SBiwqtAI7dAjcycwocOd9gancJN9sJigCXvYo3NAAkbH
|
|
TINBS77qLCunxf5oBvJMdSOZwOE+QyTTKzljyO2TBXGjY/bxIKqzDP2OUvBb9MLTo7yDhYNXqVTP
|
|
pz2XsGpZ55b3rXMngPY+iM4Mu26/PyDPL/3tQh1T2PBvqaoiT9ysE2oOPvcyS4iqQ59HAPfdHLW/
|
|
jIaKKWyjrCU8Ynfc6nLV11PD5A7o/Pz6gEoQ7QbgarYc/6Xg2qJocnwyispo06AdUoe51a2lcAKM
|
|
TmT/SedvtXvp5Ov/KT8AxmAUtOuY0JL5VfIQljC/bP8Ke7G5I6wY044MroUw5auwWOnW9Y+O4h8s
|
|
uF1X5GtMMVH/8lRxfTW7Xq6WFxdmo0bPo58AAAD//wMA5uaSKYIFAAA=
|
|
headers:
|
|
CF-RAY:
|
|
- 974ee75a69b9fa49-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 25 Aug 2025 23:35:08 GMT
|
|
Server:
|
|
- cloudflare
|
|
Set-Cookie:
|
|
- __cf_bm=YpzdHjazbzCs_jFT50s5M0hX1JuSBHogZUhvJPwKBxo-1756164908-1.0.1.1-0_bgL0r_yqn68W2fJN2xF5CCACGY7K50iAbPVUOmryv.tRDq7ol7sxSwg426hLg0zfDxbndIK7kH_GroqzjZPEDEvz1epE4gpDLuWX.pkao;
|
|
path=/; expires=Tue, 26-Aug-25 00:05:08 GMT; domain=.api.openai.com; HttpOnly;
|
|
Secure; SameSite=None
|
|
- _cfuvid=tx8GIgZ811onK882sIkQbg1SC1WHXyFyvZ_UvhApcYI-1756164908485-0.0.1.1-604800000;
|
|
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:
|
|
- '4262'
|
|
openai-project:
|
|
- proj_xitITlrFeen7zjNSzML82h9x
|
|
openai-version:
|
|
- '2020-10-01'
|
|
x-envoy-upstream-service-time:
|
|
- '4328'
|
|
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_45f89eb33cb2484197c2a2510b2e4416
|
|
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''\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:\nProvide an integer
|
|
score between 1-5 based on its effectiveness and relevance. Consider how well
|
|
it captures attention and provides insight into the topic of AI''s role in shaping
|
|
future work environments.\n\nBegin! This is VERY important to you, use the tools
|
|
available and give your best Final Answer, your job depends on it!\n\nThought:"},
|
|
{"role": "assistant", "content": "Thought: The task requires a score to be assigned
|
|
to the title \"The impact of AI in the future of work\" based on specific criteria.
|
|
I should delegate this task to the Scorer, who is responsible for evaluating
|
|
and scoring titles.\n\nAction: Delegate work to coworker\nAction Input: {\"task\":
|
|
\"Score the title: ''The impact of AI in the future of work''\", \"context\":
|
|
\"Provide an integer score between 1-5 based on its effectiveness and relevance.
|
|
Consider how well it captures attention and provides insight into the topic
|
|
of AI''s role in shaping future work environments.\", \"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:
|
|
- '2680'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=YpzdHjazbzCs_jFT50s5M0hX1JuSBHogZUhvJPwKBxo-1756164908-1.0.1.1-0_bgL0r_yqn68W2fJN2xF5CCACGY7K50iAbPVUOmryv.tRDq7ol7sxSwg426hLg0zfDxbndIK7kH_GroqzjZPEDEvz1epE4gpDLuWX.pkao;
|
|
_cfuvid=tx8GIgZ811onK882sIkQbg1SC1WHXyFyvZ_UvhApcYI-1756164908485-0.0.1.1-604800000
|
|
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 |
|
|
H4sIAAAAAAAAAwAAAP//lFVLi+NGEL77VxS65GIbj/G8nNMQ8hhyCAkT2BAvpt1dkmqnVS26SnbM
|
|
Mv996ZZlazKzsHsxuOv9fV+VPk8ACnLFGgpbG7VN62c/3e0Wfxj9+/ahWdarp+Xv+pvx/zRPH/68
|
|
/1AV0xQRdp/Q6hA1t6FpPSoF7s02olFMWa9ur2+ublb3i7tsaIJDn8KqVmerMFsulqvZ4m62uDkF
|
|
1oEsSrGGfycAAJ/zb2qRHf5XrGExHV4aFDEVFuuzE0ARg08vhREhUcNaTC9GG1iRc9dPdeiqWtfw
|
|
CIzoQAMYERQBrRGU1CNsiqcagZrWWIVQwsMjEGd72WkXMb0dQnzeFLAzgg4CA6mA2ZEnPaac1rTZ
|
|
02gqTIHBsIM2hj05BGKhqlYg1pDzpu4vlaQ2LXE1VEulAHlPMXCDrDKHRziQ94B74zujOOo9VQKx
|
|
xiOUMTRwlbq5noINLOQwprypVyxLtEp75DR7ai6ix71hi/MNb/hqDj+PXdbwdK5hPZroj0DsyBrF
|
|
hJ3R3MQJ6b49R2I7EajDIU1mcj55B8gpHGqyNZCAAQ0t2WTZxWBcwggjis5zA20djSSGxuxsCpCu
|
|
qlBUQKhiKskaVrC14QoFQgSHe/ShzfAN1azhzBPtE4SGwXSOkC2C7SKFLhEaOgVFW3PwoSJrPBiX
|
|
QeqJSEgt5/DXAN0YJRKoqar9cUBWszC6GBNAJ2wosGRxDTWOmQtsWh+OqQYIWg1R5vAgWR7JPW2Z
|
|
EFeZg9J3yDbx+insoDHxGbVn9I1wpqA1yam/M2QtRiVOtVKQUoP+eCbSOBdRUrHEm+AAah791ySO
|
|
0/tJi2mg6aBPDoe0XVT1ogyx19Z4B8Mh81DRHsFAlc4HGJYDxg3/Qmw8POR/a7iG2Qjd79hRGql9
|
|
rHT9EUiHTZX3V1V6sb/d2LNKHx5/kDMLef++urbjkxSx7MSki8id9yODYQ7a45iO4ceT5eV8/nyo
|
|
2hh28r/QoiQmqbdJGoHTqRMNbZGtLxOAj/nMdq8uZ9HG0LS61fCMudz1atXnKy6H/WJdLk9HuNCg
|
|
xl8MtzdD2KuEW4dqyMvoUhfW2BrdJfRy1tP2hZFhMhr7bTvv5e5HJ66+Jf3FYC22im7bRnRkX498
|
|
cYuYPnxfczvDnBsuBOOeLG6VMCYqHJam8/03qZCjKDbbkrjC2EbqP0xlu3Xlorzd3V/f2GLyMvkC
|
|
AAD//wMAlpQiYaEHAAA=
|
|
headers:
|
|
CF-RAY:
|
|
- 974ee7768809fa49-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 25 Aug 2025 23:35:12 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:
|
|
- '4274'
|
|
openai-project:
|
|
- proj_xitITlrFeen7zjNSzML82h9x
|
|
openai-version:
|
|
- '2020-10-01'
|
|
x-envoy-upstream-service-time:
|
|
- '4339'
|
|
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:
|
|
- '29999380'
|
|
x-ratelimit-reset-project-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 1ms
|
|
x-request-id:
|
|
- req_9ad5330b210c40cab7dbaa4822ab4144
|
|
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:
|
|
The task requires a score to be assigned to the title \"The impact of AI in
|
|
the future of work\" based on specific criteria. I should delegate this task
|
|
to the Scorer, who is responsible for evaluating and scoring titles.\n\nAction:
|
|
Delegate work to coworker\nAction Input: {\"task\": \"Score the title: ''The
|
|
impact of AI in the future of work''\", \"context\": \"Provide an integer score
|
|
between 1-5 based on its effectiveness and relevance. Consider how well it captures
|
|
attention and provides insight into the topic of AI''s role in shaping future
|
|
work environments.\", \"coworker\": \"Scorer\"}\nObservation: 5 - The title
|
|
\"The impact of AI in the future of work\" is effective and relevant; it captures
|
|
attention and provides clear insight into the topic of AI''s influence on future
|
|
work environments."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '4046'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=YpzdHjazbzCs_jFT50s5M0hX1JuSBHogZUhvJPwKBxo-1756164908-1.0.1.1-0_bgL0r_yqn68W2fJN2xF5CCACGY7K50iAbPVUOmryv.tRDq7ol7sxSwg426hLg0zfDxbndIK7kH_GroqzjZPEDEvz1epE4gpDLuWX.pkao;
|
|
_cfuvid=tx8GIgZ811onK882sIkQbg1SC1WHXyFyvZ_UvhApcYI-1756164908485-0.0.1.1-604800000
|
|
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 |
|
|
H4sIAAAAAAAAAwAAAP//jFLLbtswELzrKxY8W4FkW37oFhQomhbopUEPrQKBplYSG4pkyVXSwPC/
|
|
F5RiS0lTIBcC5OwMZ3b3GAEwWbEcmGg5ic6q+MPukNx+eyJt09/f/fbHzUNF6svXZLX//Klji8Aw
|
|
h18o6My6EqazCkkaPcLCIScMquk226Sb9T5dDUBnKlSB1liK1yZeJst1nOziZPNMbI0U6FkOPyMA
|
|
gONwBou6wj8sh2RxfunQe94gyy9FAMwZFV4Y91564prYYgKF0YR6cH3bmr5pKYcb0OYR7sNBLUIt
|
|
NVfAtX9Ed1Xoj8P1erjmcCw0QMG8MA4LlkNW6NNc32Hdex7i6V6pGcC1NsRDe4Zkd8/I6ZJFmcY6
|
|
c/CvqKyWWvq2dMi90cG3J2PZgJ4igLuhZ/2LNjDrTGepJHOPw3e7LB312DSlCV2eQTLE1Yy1XS7e
|
|
0CsrJC6Vn3WdCS5arCbqNCLeV9LMgGiW+l83b2mPyaVu3iM/AUKgJaxK67CS4mXiqcxhWOL/lV26
|
|
PBhmHt2DFFiSRBcmUWHNezXuF/NPnrAra6kbdNbJcclqW+6SfbbJVitxYNEp+gsAAP//AwDpVFDZ
|
|
bQMAAA==
|
|
headers:
|
|
CF-RAY:
|
|
- 974ee792a8c6fa49-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 25 Aug 2025 23:35:13 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:
|
|
- '570'
|
|
openai-project:
|
|
- proj_xitITlrFeen7zjNSzML82h9x
|
|
openai-version:
|
|
- '2020-10-01'
|
|
x-envoy-upstream-service-time:
|
|
- '598'
|
|
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:
|
|
- '29999042'
|
|
x-ratelimit-reset-project-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 1ms
|
|
x-request-id:
|
|
- req_457bdb91af6147b39002e1b4804064fa
|
|
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:
|
|
The task requires a score to be assigned to the title \"The impact of AI in
|
|
the future of work\" based on specific criteria. I should delegate this task
|
|
to the Scorer, who is responsible for evaluating and scoring titles.\n\nAction:
|
|
Delegate work to coworker\nAction Input: {\"task\": \"Score the title: ''The
|
|
impact of AI in the future of work''\", \"context\": \"Provide an integer score
|
|
between 1-5 based on its effectiveness and relevance. Consider how well it captures
|
|
attention and provides insight into the topic of AI''s role in shaping future
|
|
work environments.\", \"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:
|
|
- '3872'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=YpzdHjazbzCs_jFT50s5M0hX1JuSBHogZUhvJPwKBxo-1756164908-1.0.1.1-0_bgL0r_yqn68W2fJN2xF5CCACGY7K50iAbPVUOmryv.tRDq7ol7sxSwg426hLg0zfDxbndIK7kH_GroqzjZPEDEvz1epE4gpDLuWX.pkao;
|
|
_cfuvid=tx8GIgZ811onK882sIkQbg1SC1WHXyFyvZ_UvhApcYI-1756164908485-0.0.1.1-604800000
|
|
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 |
|
|
H4sIAAAAAAAAA4xSXYvbMBB8969Y9BwXx03c4LfjoKVwlGsphbY+jCKvbfVkSZXWTY+Q/16kfNhp
|
|
e3AvAml2VjOzu08AmGxYCUz0nMRgVXq72eab/tOXdx/vOudvv+4+PHU/+3vxend3/40tAsNsf6Cg
|
|
M+uVMINVSNLoIywccsLQdflmXSyLdbYsIjCYBlWgdZbSlUnzLF+l2SbNihOxN1KgZyV8TwAA9vEM
|
|
EnWDv1kJ2eL8MqD3vENWXooAmDMqvDDuvfTENbHFBAqjCXVU/bk3Y9dTCe9Bmx08hoN6hFZqroBr
|
|
v0NX6bfxdhNvJewrDVAxL4zDipWwrvRh3t5hO3oe3OlRqRnAtTbEQzrR2MMJOVysKNNZZ7b+Lypr
|
|
pZa+rx1yb3SQ7clYFtFDAvAQIxuvUmDWmcFSTeYR43eb/BQZm4Y0ofnyBJIhrmas1Rm46lc3SFwq
|
|
PwudCS56bCbqNCE+NtLMgGTm+l81/+t9dC5195L2EyAEWsKmtg4bKa4dT2UOww4/V3ZJOQpmHt0v
|
|
KbAmiS5MosGWj+q4Xsw/ecKhbqXu0FknjzvW2npVbNs2w0xsWHJI/gAAAP//AwCoHa0pbAMAAA==
|
|
headers:
|
|
CF-RAY:
|
|
- 974eea15dfd2fa56-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 25 Aug 2025 23:36:57 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:
|
|
- '867'
|
|
openai-project:
|
|
- proj_xitITlrFeen7zjNSzML82h9x
|
|
openai-version:
|
|
- '2020-10-01'
|
|
x-envoy-upstream-service-time:
|
|
- '949'
|
|
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:
|
|
- '29999086'
|
|
x-ratelimit-reset-project-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 1ms
|
|
x-request-id:
|
|
- req_78fb283974264a01982de445532cac51
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
version: 1
|