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
release/0.203.x
crewAI/tests/cassettes/test_output_pydantic_hierarchical.yaml
Lorenze Jay 7addda9398
Some checks failed
Notify Downstream / notify-downstream (push) Has been cancelled
Details
Lorenze/better tracing events (#3382) 
* 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.
2025-08-26 09:09:46 -07:00

1195 lines
54 KiB
YAML
Raw Permalink 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-AB7ftPrKueGANoTk2jisJQy28SMQZ\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214473,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to get an integer score between
1-5 for the given title \\\"The impact of AI in the future of work.\\\" I will
delegate this task to Scorer, providing them with all necessary context.\\n\\nAction:
Delegate work to coworker\\nAction Input: {\\\"coworker\\\": \\\"Scorer\\\",
\\\"task\\\": \\\"Provide an integer score between 1-5 for the following title:
'The impact of AI in the future of work'\\\", \\\"context\\\": \\\"This is for
evaluating the impact of AI on the future of work. The score must be an integer
between 1-5.\\\"}\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
664,\n \"completion_tokens\": 123,\n \"total_tokens\": 787,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f9b85bf71cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:47:55 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:
- '1941'
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_9ed13e6054d3e4d6b7b600e20891fb25
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an
expert scorer, specialized in scoring titles.\nYour personal goal is: Score
the title\nTo give my best complete final answer to the task use the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Provide an integer score between 1-5 for the following
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:\nThis
is for evaluating the impact of AI on the future of work. The score must be
an integer between 1-5.\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:
- '1127'
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-AB7fvCyQD7z7StdDBs7M1mDlMsW6l\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214475,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
230,\n \"completion_tokens\": 15,\n \"total_tokens\": 245,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f9c6df9b1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:47:56 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:
- '350'
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:
- '29999729'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a88c60d514500d2b940c40ad4d553e73
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": "I need to get an integer
score between 1-5 for the given title \"The impact of AI in the future of work.\"
I will delegate this task to Scorer, providing them with all necessary context.\n\nAction:
Delegate work to coworker\nAction Input: {\"coworker\": \"Scorer\", \"task\":
\"Provide an integer score between 1-5 for the following title: ''The impact
of AI in the future of work''\", \"context\": \"This is for evaluating the impact
of AI on the future of work. The score must be an integer between 1-5.\"}\nObservation:
4"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3546'
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-AB7fwZ4WSniWh4YMRrip2x1Bx03b7\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214476,\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\":
795,\n \"completion_tokens\": 14,\n \"total_tokens\": 809,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f9cd08fb1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:47:56 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:
- '285'
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:
- '29999141'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_7afa4cb902ce1bca02dcd7dbf2e36970
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '2888'
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 21:47:57 GMT
status:
code: 200
message: OK
- 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-AB7fxFJVaaPLV8eezP1LWgZes9p8t\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214477,\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_TuUA4HNG1rH6GOq9nrx94Fp7\",\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:
- 8c85f9d13ee71cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:47:57 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:
- '267'
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_c8bb2af8f4a63658c3c9316045a413e1
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 |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headers:
CF-RAY:
- 974eec034af08486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:17 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
path=/; expires=Tue, 26-Aug-25 00:08:17 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000;
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:
- '2201'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '2275'
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_8253241bc24547018d1600b0ec310060
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 involves evaluating the given title and providing an integer score between
1 and 5 based on the title''s potential impact, relevance, and interest level.\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 to our Scorer, providing
them with context about the title and the task at hand.\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
involves evaluating the given title and providing an integer score between 1
and 5 based on the title''s potential impact, relevance, and interest level.\",
\"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:
- '2548'
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:
- 974eec121c168486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:21 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:
- '3958'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '4032'
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:
- '29999412'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_bd8ada32c9474dad85877e84f73b632b
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 to our Scorer, providing them
with context about the title and the task at hand.\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 involves
evaluating the given title and providing an integer score between 1 and 5 based
on the title''s potential impact, relevance, and interest level.\", \"coworker\":
\"Scorer\"}\nObservation: 5 - The title \"The impact of AI in the future of
work\" is highly impactful, relevant, and interesting due to the transformative
potential of AI technologies in various job sectors and its relevance to ongoing
discussions about the future of employment."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3994'
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:
- 974eec2bee738486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:22 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:
- '879'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '923'
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:
- '29999055'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_5699dd0d905247f6b4b41d76411079e0
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 to our Scorer, providing them
with context about the title and the task at hand.\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 involves
evaluating the given title and providing an integer score between 1 and 5 based
on the title''s potential impact, relevance, and interest level.\", \"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:
- '3760'
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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:
CF-RAY:
- 974eed9bdf8aeb2a-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:39:21 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:
- '1085'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1107'
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:
- '29999114'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_1b900c7238124d04835cb54adf6d7aeb
status:
code: 200
message: OK
version: 1
Reference in New Issue View Git Blame Copy Permalink