andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 00:28:31 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Lorenze/better tracing events (#3382)
Some checks failed
Notify Downstream / notify-downstream (push) Has been cancelled
Details

Browse Source 
* 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.
This commit is contained in:
Lorenze Jay
2025-08-26 09:09:46 -07:00
committed by GitHub
parent 4b4a119a9f
commit 7addda9398
43 changed files with 5151 additions and 295 deletions
Download Patch File Download Diff File Expand all files Collapse all files

158
tests/cassettes/test_agent_usage_metrics_are_captured_for_hierarchical_process.yaml
View File

@@ -508,4 +508,162 @@ interactions:
- req_80eed127ea0361c637657470cf9b647e
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: Researcher\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: Researcher\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: Ask the researched to say hi!\n\nThis is the expected criteria
for your final answer: Howdy!\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": "Thought: To complete the task, I need to ask
the researcher to say \"Howdy!\" I will use the \"Ask question to coworker\"
tool to instruct the researcher accordingly.\n\nAction: Ask question to coworker\nAction
Input: {\"question\": \"Can you please say hi?\", \"context\": \"The expected
greeting is: Howdy!\", \"coworker\": \"Researcher\"}\nObservation: Howdy!"}],
"model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3318'
content-type:
- application/json
cookie:
- _cfuvid=g371YzJ.yOdjD9dcZxJ8VI4huWlRJL2j8lbKDhE0qV8-1743463280779-0.0.1.1-604800000
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:
- 974f08878cb7239e-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:57:43 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=veVLwO9uj9FvIBC_v55vfVlSdU8NHY.wdBapmpmtHn4-1756166263-1.0.1.1-LJ9bNXe6v06jg_mjVZp8vfvLT.9Hf8xUHOf2FempuntDnL5ogQXRuJvIJipz1trGr96_3WUCWlsexhQlkdtveEH6NbFMrm__Y61khA_IyPM;
path=/; expires=Tue, 26-Aug-25 00:27:43 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=miqmxIsNDZtXvrtcyhpeSI3TjT_zcUas9Enn6gGtIsI-1756166263603-0.0.1.1-604800000;
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:
- '472'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '550'
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:
- '29999222'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_4f627ee303b9429db117e9699b00656a
status:
code: 200
message: OK
version: 1

200
tests/cassettes/test_do_not_allow_crewai_trigger_context_for_first_task_hierarchical.yaml
View File

@@ -498,4 +498,204 @@ interactions:
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: First Agent\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: First Agent\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: Process initial data\n\nThis is the expected criteria for your
final answer: Initial analysis\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": "Thought: I need to delegate
the task of processing the initial data to the First Agent to ensure we have
a thorough and accurate analysis. I will provide them with all the necessary
details to complete this task effectively.\n\nAction: Delegate work to coworker\nAction
Input: {\"task\": \"Process initial data\", \"context\": \"The task involves
analyzing the initial data set we have received. This includes cleaning the
data, categorizing it for analysis, identifying any trends or patterns, and
summarizing the findings. The goal is to have a clear understanding of what
the data indicates and any initial insights that can be drawn from it.\", \"coworker\":
\"First Agent\"}\nObservation: To process the initial data set effectively,
we will follow several key steps to ensure we clean, categorize, analyze, and
summarize our findings comprehensively.\n\n1. **Data Cleaning**: \n - First,
we will review the dataset for missing, inconsistent, or erroneous entries.
\n - We will handle missing values by either imputing them based on surrounding
data or removing records where necessary.\n - Additionally, we will standardize
categorical variables to ensure consistency (e.g., ensuring all location names
are spelled the same way).\n\n2. **Data Categorization**: \n - Next, we will
categorize the data into relevant segments that will aid our analysis. \n -
This involves grouping data points based on common characteristics, such as
demographics, time periods, or any key performance indicators (KPIs) we are
focusing on.\n\n3. **Trend and Pattern Identification**: \n - With the cleaned
and categorized data, we will perform a detailed analysis to identify trends
and patterns.\n - This will involve using statistical tools and visualizations
to uncover relationships within the data. We will look at time series analysis,
correlation coefficients, and significant outliers that may require further
investigation.\n\n4. **Summarizing Findings**: \n - Finally, we will compile
a summary of our findings, including both qualitative insights and quantitative
metrics.\n - This summary should encapsulate the key trends identified, any
notable patterns, and implications of these findings.\n - We will also document
any limitations of the data and suggest areas for further research if necessary.\n\nBy
completing these steps, we will not only have a clear understanding of what
the data indicates but also provide actionable insights that can guide our next
steps. This comprehensive analysis will serve as a solid foundation for any
additional exploration or decision-making initiatives related to our project."}],
"model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '5593'
content-type:
- application/json
cookie:
- _cfuvid=YeODa6MF5ug3OZUV6ob1dSrBKCM8BXbKkS77TIihYoE-1755550362828-0.0.1.1-604800000
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:
- 97544b3fd9c66894-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 26 Aug 2025 15:17:10 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=AK6x7s00CdjvAhZqoKc.oyU2huXbBJAB_qi1o9cIHkk-1756221430-1.0.1.1-s9cWi1kLPHCBoqRe8BhCYWgaKEG.LQvm0b0NNJkJrpuMMIAUz9sSqijPatK.t2wknR3Qo65.PTew2trnDH5_.mL1l4JewiW1VndksvCWngY;
path=/; expires=Tue, 26-Aug-25 15:47:10 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=3NkIk1Ua5GwknkJHax_bb1dBUHU9Yobu11sjZ9yu7Rg-1756221430892-0.0.1.1-604800000;
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:
- '5563'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '5651'
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:
- '29998658'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_8ee5ddbc01374cf487da8763d7dee507
status:
code: 200
message: OK
version: 1

197
tests/cassettes/test_hierarchical_crew_creation_tasks_with_sync_last.yaml
View File

@@ -1158,4 +1158,201 @@ interactions:
- req_04364e8bad0fc80241f59550b9320360
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: Senior Writer, Researcher, CEO\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: Senior Writer, Researcher, CEO\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: Write one amazing paragraph about AI.\n\nThis is
the expected criteria for your final answer: A single paragraph with 4 sentences.\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n\"Artificial Intelligence (AI) stands
at the forefront of technological advancement, utilizing machine learning, neural
networks, and natural language processing to replicate human cognitive functions.
The transformative power of AI spans across industries, driving revolutionary
changes from predictive diagnostics in healthcare to algorithmic trading in
finance. By rapidly analyzing large datasets, AI reveals hidden patterns, enhances
efficiency, and sparks unprecedented innovation. As we embrace this technology,
it is crucial to prioritize ethical considerations and responsible development
to fully leverage its potential while addressing associated risks.\"\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: To craft an amazing paragraph about AI as described in the context,
I should delegate this task to the Senior Writer and include all the detailed
context provided.\n\nAction: Delegate work to coworker\nAction Input: {\"task\":
\"Write one amazing paragraph about AI\", \"context\": \"Artificial Intelligence
(AI) is a transformative technology that leverages machine learning, neural
networks, and natural language processing to perform tasks that traditionally
require human intelligence, such as visual perception, speech recognition, and
decision-making. Its potential to revolutionize industries\u2014from healthcare
with predictive diagnostics to finance with algorithmic trading\u2014underscores
its profound impact on our daily lives and the global economy. With the ability
to analyze vast amounts of data quickly and accurately, AI can unveil hidden
patterns, drive efficiencies, and foster innovation at an unprecedented scale.
As we move forward, the ethical and responsible development of AI will be paramount
to harness its benefits while mitigating risks.\", \"coworker\": \"Senior Writer\"}\n\nObservation:
The Senior Writer has received the task and context.\nObservation: Artificial
Intelligence (AI) is a transformative technology that leverages machine learning,
neural networks, and natural language processing to perform tasks that traditionally
require human intelligence, such as visual perception, speech recognition, and
decision-making. Its potential to revolutionize industries\u2014from healthcare
with predictive diagnostics to finance with algorithmic trading\u2014underscores
its profound impact on our daily lives and the global economy. With the ability
to analyze vast amounts of data quickly and accurately, AI can unveil hidden
patterns, drive efficiencies, and foster innovation at an unprecedented scale.
As we move forward, the ethical and responsible development of AI will be paramount
to harness its benefits while mitigating risks."}], "model": "gpt-4o", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '5729'
content-type:
- application/json
cookie:
- _cfuvid=Q23zZGhbuNaTNh.RPoM_1O4jWXLFM.KtSgSytn2NO.Q-1744492727869-0.0.1.1-604800000
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:
- 974f089aacfe239e-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:57:47 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=x3Z22TL7MiNrhhoqoBAkoerRf2slLEFNFLerhsr8uWg-1756166267-1.0.1.1-YsxFr.4IpdTvhEkob8OJGHggHZj5mRzRdK0Ta9PllabKVSUEp9sdbUxQpYatb5wW12dk9nglKUcebewHsL7RgYB0Y0BPnFRoyX0r5kn14HI;
path=/; expires=Tue, 26-Aug-25 00:27:47 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=H4uvKyyXorF4TlJkoLerJYI2PABtQ6M4T.XxqO7FHCQ-1756166267474-0.0.1.1-604800000;
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:
- '1314'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1380'
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:
- '29998623'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_47e6588839144756828145be5a5a3b63
status:
code: 200
message: OK
version: 1

245
tests/cassettes/test_hierarchical_process.yaml
View File

@@ -716,4 +716,249 @@ interactions:
- req_04659f093830c14dbc5342c119533861
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: Researcher, Senior Writer\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: Researcher, Senior Writer\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: Come up with a list of 5 interesting ideas to explore
for an article, then write one amazing paragraph highlight for each idea that
showcases how good an article about this topic could be. Return the list of
ideas with their paragraph and your notes.\n\nThis is the expected criteria
for your final answer: 5 bullet points with a paragraph for each idea.\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":
"```\nThought: To come up with interesting article ideas and write compelling
highlights, I should first generate a list of potential topics. The Researcher
can help with gathering current trends or interesting topics that might be engaging.
Then, I can delegate writing the paragraph highlights to the Senior Writer.\n\nAction:
Ask question to coworker\nAction Input: {\"question\": \"What are some current
trending topics or subjects that are interesting to explore for an article?\",
\"context\": \"I need to generate a list of 5 interesting ideas to explore for
an article, each paired with an amazing paragraph highlight. Current trends
or unusual insights could be a good source of inspiration for these ideas.\",
\"coworker\": \"Researcher\"}\nObservation: **1. The Rise of Autonomous AI Agents
in Daily Life** \nAs artificial intelligence technology progresses, the integration
of autonomous AI agents into everyday life becomes increasingly prominent. These
agents, capable of making decisions without human intervention, are reshaping
industries from healthcare to finance. Exploring case studies where autonomous
AI has successfully decreased operational costs or improved efficiency can reveal
not only the benefits but also the ethical implications of delegating decision-making
to machines. This topic offers an exciting opportunity to dive into the AI landscape,
showcasing current developments such as AI assistants and autonomous vehicles.\n\n**2.
Ethical Implications of Generative AI in Creative Industries** \nThe surge
of generative AI tools in creative fields, such as art, music, and writing,
has sparked a heated debate about authorship and originality. This article could
investigate how these tools are being used by artists and creators, examining
both the potential for innovation and the risk of devaluing traditional art
forms. Highlighting perspectives from creators, legal experts, and ethicists
could provide a comprehensive overview of the challenges faced, including copyright
concerns and the emotional impact on human artists. This discussion is vital
as the creative landscape evolves alongside technological advancements, making
it ripe for exploration.\n\n**3. AI in Climate Change Mitigation: Current Solutions
and Future Potential** \nAs the world grapples with climate change, AI technology
is increasingly being harnessed to develop innovative solutions for sustainability.
From predictive analytics that optimize energy consumption to machine learning
algorithms that improve carbon capture methods, AI''s potential in environmental
science is vast. This topic invites an exploration of existing AI applications
in climate initiatives, with a focus on groundbreaking research and initiatives
aimed at reducing humanity''s carbon footprint. Highlighting successful projects
and technology partnerships can illustrate the positive impact AI can have on
global climate efforts, inspiring further exploration and investment in this
area.\n\n**4. The Future of Work: How AI is Reshaping Employment Landscapes** \nThe
discussions around AI''s impact on the workforce are both urgent and complex,
as advances in automation and machine learning continue to transform the job
market. This article could delve into the current trends of AI-driven job displacement
alongside opportunities for upskilling and the creation of new job roles. By
examining case studies of companies that integrate AI effectively and the resulting
workforce adaptations, readers can gain valuable insights into preparing for
a future where humans and AI collaborate. This exploration highlights the importance
of policies that promote workforce resilience in the face of change.\n\n**5.
Decentralized AI: Exploring the Role of Blockchain in AI Development** \nAs
blockchain technology sweeps through various sectors, its application in AI
development presents a fascinating topic worth examining. Decentralized AI could
address issues of data privacy, security, and democratization in AI models by
allowing users to retain ownership of data while benefiting from AI''s capabilities.
This article could analyze how decentralized networks are disrupting traditional
AI development models, featuring innovative projects that harness the synergy
between blockchain and AI. Highlighting potential pitfalls and the future landscape
of decentralized AI could stimulate discussion among technologists, entrepreneurs,
and policymakers alike.\n\nThese topics not only reflect current trends but
also probe deeper into ethical and practical considerations, making them timely
and relevant for contemporary audiences."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '7865'
content-type:
- application/json
cookie:
- _cfuvid=icM8L9.yRk22iqPJZhDQeVHgfWZOnl1YiBFMJmVO8_8-1743465529821-0.0.1.1-604800000
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:
- 974efac6faf5cf15-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:48:25 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=yJXo3QqFAYYxljNSZBr47v.aphUMHM_ulx8v95ohSS4-1756165705-1.0.1.1-hhSjgTF5yD4vPuetC1LZGfC4KDF6RXEOSk8B4k4kOCq0XyfGNZkzt8kMn.F..aqu9T7UeYwKJprb.ZhscrKkokkqPou4V3aYXTAqIb2GZvE;
path=/; expires=Tue, 26-Aug-25 00:18:25 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=yh2RjFXBfB0RrOxRjxqkpRIka8SH8Bv0F2PRUGTNLkY-1756165705944-0.0.1.1-604800000;
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:
- '6170'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '6192'
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:
- '29998089'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 3ms
x-request-id:
- req_f470345c656b4bb7abb0ab09372eabef
status:
code: 200
message: OK
version: 1

347
tests/cassettes/test_hierarchical_verbose_false_manager_agent.yaml
View File

@@ -1384,4 +1384,351 @@ interactions:
- req_7fdc097dc5895a4d2d953e8b1a2479d1
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: Researcher, Senior Writer\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: Researcher, Senior Writer\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: Come up with a list of 5 interesting ideas to explore
for an article, then write one amazing paragraph highlight for each idea that
showcases how good an article about this topic could be. Return the list of
ideas with their paragraph and your notes.\n\nThis is the expected criteria
for your final answer: 5 bullet points with a paragraph for each idea.\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":
"Thought: The first step is to brainstorm and research interesting ideas for
the article. Since the task involves both research and writing, I will need
to delegate the brainstorming of ideas to the Researcher and the writing of
the paragraphs to the Senior Writer. \n\nAction: Delegate work to coworker\nAction
Input: {\"task\": \"Come up with a list of 5 interesting ideas to explore for
an article.\", \"context\": \"We need a list of 5 interesting ideas that would
make compelling articles. The topics should be relevant, timely, and engaging
for a broad audience.\", \"coworker\": \"Researcher\"}\nObservation: 1. **The
Rise of AI in Healthcare: Transforming Patient Care and Diagnostics**\n \"Imagine
a world where routine check-ups and complex diagnostics are seamlessly conducted
by intelligent systems. AI in healthcare is rapidly transforming this vision
into reality, enhancing patient care through early and accurate disease detection,
personalized treatment plans, and continuous health monitoring. This revolution
is not just a futuristic concept; it''s already happening with AI-driven technologies
enabling doctors to make more informed decisions and offering patients a more
proactive approach to their health. The ethical and privacy concerns, however,
pose new challenges that the industry must navigate to ensure responsible advancement.\"\n\n2.
**AI Agents in the Workplace: Boosting Productivity and Shaping the Future of
Jobs**\n \"The modern workplace is being redefined by the integration of AI
agents, intelligent systems designed to handle repetitive tasks, analyze vast
amounts of data, and assist in complex decision-making processes. These innovations
are boosting productivity, allowing employees to focus on creativity and strategic
thinking. The rise of AI in the workspace heralds a future where human and machine
collaboration leads to unparalleled efficiencies and novel job opportunities.
However, this shift also brings with it challenges related to job displacement
and the urgent need for reskilling the workforce to thrive in an AI-augmented
environment.\"\n\n3. **Ethical AI: Ensuring Fairness, Accountability, and Transparency**\n \"As
AI technology becomes more pervasive, the quest for ethical AI has become critical.
Ensuring fairness, accountability, and transparency in AI systems is essential
to prevent biases and promote trust. This involves creating robust frameworks
and guidelines that govern AI development and deployment. Real-world case studies
highlight both the triumphs and the tribulations of tech companies as they navigate
the complex moral landscape that AI presents. As society grapples with these
challenges, the push for ethical AI continues to drive innovation and policy-making
in the tech industry.\"\n\n4. **AI-Powered Startups: Innovators Changing the
Tech Landscape**\n \"In the bustling world of tech startups, AI-powered companies
are emerging as the vanguards of innovation, disrupting traditional business
models and reshaping entire industries. From revolutionizing financial services
to pioneering advances in healthcare and beyond, these startups are at the forefront
of technological progress. By leveraging machine learning and AI, they are solving
complex problems and bringing novel solutions to market at an unprecedented
pace. Investors are taking notice, pouring capital into these ventures, and
fueling a new wave of growth and competition in the AI ecosystem.\"\n\n5. **The
Future of AI in Entertainment: From Movies to Video Games**\n \"The entertainment
industry is undergoing a seismic shift driven by AI technology. In movies, AI
is revolutionizing special effects, enabling filmmakers to create stunning,
hyper-realistic worlds. In video games, AI is enhancing player experiences by
creating adaptive, intelligent characters and dynamic storylines that respond
to player choices. This transformative power of AI promises to push the boundaries
of creativity, offering audiences more immersive and interactive entertainment
experiences. As the technology continues to evolve, the future of entertainment
looks set to be more exciting and unpredictable than ever before.\""}, {"role":
"assistant", "content": "Thought: I''ll proceed to delegate the writing of one
amazing paragraph highlight for each of the identified ideas to the Senior Writer,
ensuring each topic is adequately detailed to showcase its potential.\n\nAction:
Delegate work to coworker\nAction Input: {\"task\": \"Write one amazing paragraph
highlight for each of these 5 ideas that showcases how good an article about
these topics could be.\", \"context\": \"Here are the 5 ideas:\\n1. The Rise
of AI in Healthcare: Transforming Patient Care and Diagnostics - Explore how
AI is revolutionizing healthcare through enhanced diagnostic tools, personalized
treatment plans, and post-operative care. Discuss current achievements, potential
future applications, and ethical considerations.\\n2. AI Agents in the Workplace:
Boosting Productivity and Shaping the Future of Jobs - Examine the integration
of AI agents in various industries. Highlight how these intelligent agents are
improving efficiency, automating mundane tasks, and assisting in decision-making
processes. Address potential job displacement and the need for upskilling the
workforce.\\n3. Ethical AI: Ensuring Fairness, Accountability, and Transparency
- Delve into the ethical implications of AI deployment. Analyze the frameworks
and guidelines being proposed to ensure AI systems are fair, transparent, and
accountable. Include case studies of ethical dilemmas faced by companies using
AI.\\n4. AI-Powered Startups: Innovators Changing the Tech Landscape - Provide
an overview of how AI-driven startups are disrupting traditional business models
and industries. Profile some of the most innovative startups, their business
models, and the unique challenges they face. Discuss the role of venture capital
in fostering AI innovation.\\n5. The Future of AI in Entertainment: From Movies
to Video Games - Investigate how AI is transforming the entertainment industry,
from scriptwriting and special effects in movies to creating more immersive
and intelligent experiences in video games. Offer predictions about future trends
and possible impacts on content creation and consumption.\", \"coworker\": \"Senior
Writer\"}\nObservation:\nObservation: 1. **The Rise of AI in Healthcare: Transforming
Patient Care and Diagnostics**\n AI is undeniably revolutionizing the healthcare
sector, introducing transformative changes in patient care and diagnostics.
With the advent of advanced diagnostic tools powered by AI, healthcare professionals
can now detect and monitor diseases with unprecedented accuracy and speed. Personalized
treatment plans, which were once a distant dream, are becoming a reality as
AI algorithms analyze vast amounts of patient data, tailoring treatments that
are specific to individual needs. Post-operative care has also seen significant
improvements, with AI-driven monitoring systems ensuring that patients receive
timely and effective care. Current achievements like IBM Watson''s oncology
platform or Google''s DeepMind in eye care are just the beginning, with future
applications promising to further enhance surgical robotics, predictive analytics,
and remote patient monitoring. However, alongside these advancements, ethical
considerations such as patient privacy, data security, and decision-making transparency
must be rigorously addressed to fully harness AI\u2019s potential in healthcare.\n\n2.
**AI Agents in the Workplace: Boosting Productivity and Shaping the Future of
Jobs**\n The integration of AI agents in the workplace marks a pivotal shift
in how businesses operate and compete. These intelligent agents are revolutionizing
various industries by automating mundane tasks, optimizing workflows, and providing
actionable insights from data analysis. For instance, AI chatbots in customer
service can handle routine inquiries, freeing human agents to tackle more complex
issues. In manufacturing, AI systems predict equipment failures, reducing downtime
and maintaining peak productivity. By enhancing operational efficiency, AI agents
not only boost productivity but also reshape the future of jobs. While the risk
of job displacement is a valid concern, it concurrently heralds opportunities
for upskilling and creating new roles that harness human creativity and strategic
thinking. Preparing the workforce for these changes is crucial, fostering a
symbiotic relationship between AI and human labor to drive innovation and economic
growth.\n\n3. **Ethical AI: Ensuring Fairness, Accountability, and Transparency**\n As
AI technologies become increasingly pervasive, ensuring their ethical deployment
is paramount. Ethical AI demands the formulation and implementation of robust
frameworks that enshrine fairness, accountability, and transparency. Such frameworks
are essential in mitigating biases embedded within AI systems, which can perpetuate
and even exacerbate inequality. Case studies, such as the controversy surrounding
facial recognition systems and their racial biases, highlight the pressing need
for ethical oversight. Transparency in how AI models make decisions, coupled
with accountability measures for their outcomes, establishes trust and integrity
in AI applications. Legislative frameworks from the EU\u2019s GDPR to the IEEE\u2019s
global initiatives for ethical AI provide the scaffolding for these principles.
Companies are now faced with the challenge of integrating these ethical considerations
into their development processes, ensuring that AI advancements benefit all
of society equitably.\n\n4. **AI-Powered Startups: Innovators Changing the Tech
Landscape**\n AI-powered startups are at the forefront of a technological
renaissance, disrupting traditional business models and reshaping industries.
These startups leverage AI to offer innovative solutions, whether it''s automating
financial trading with precision algorithms or enhancing cybersecurity through
predictive analytics. High-profile examples like OpenAI and UiPath illustrate
the transformative potential of AI-driven innovation. These companies face unique
challenges, from securing sufficient funding to navigating the complexities
of large-scale implementation. Venture capital plays a critical role in this
ecosystem, providing the necessary resources and support to turn bold ideas
into impactful realities. The synergy between AI innovation and entrepreneurial
spirit is fostering a dynamic landscape where the boundaries of technology and
commerce are continually expanding.\n\n5. **The Future of AI in Entertainment:
From Movies to Video Games**\n The entertainment industry is undergoing a
metamorphic change with the integration of AI technologies, paving the way for
more immersive and engaging experiences. In movies, AI streamlines the scriptwriting
process, enhances special effects, and even predicts box office success. Machine
learning models analyze vast datasets to create compelling narratives and optimize
marketing strategies. Video games have also been revolutionized by AI, with
non-player characters (NPCs) displaying more lifelike behaviors and adaptive
learning algorithms personalizing gaming experiences. Future trends indicate
a seamless blend of AI with augmented reality (AR) and virtual reality (VR),
creating interactive environments where the line between virtual and real worlds
blur. These advancements are not only transforming content creation but also
revolutionizing how audiences consume and interact with entertainment, predicting
a future where AI is an indispensable tool in the creative arsenal."}], "model":
"gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '14961'
content-type:
- application/json
cookie:
- _cfuvid=Dmt0PIbI1kDJNEjEUHh50Vv4Y9ZcWX6w2Uku_CIohuk-1751391377646-0.0.1.1-604800000
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:
- 974f08a7bda1239e-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:58:18 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=ivMv06nBtEBQA0RDYIILchv9UWNGtVY5W5EPjY_N5kM-1756166298-1.0.1.1-2Qisdm01V_T5uiCTx3ArSE5G4lPmSJXAC_FziI_DwOsWC_nN5OI4nlAAcT5w8A.DGB6SVkyNXoYzPqHQgSR2pUc8YECmxkJF6LXkXDhzC0A;
path=/; expires=Tue, 26-Aug-25 00:28:18 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=xP6HSAlowr0MDcDirVgpB.BcvTTqAlUD_fl6h1bu7io-1756166298177-0.0.1.1-604800000;
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:
- '29910'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '29994'
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:
- '29996336'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 7ms
x-request-id:
- req_ae1d0ce3d5584bbba38ba76c69a0e541
status:
code: 200
message: OK
version: 1

358
tests/cassettes/test_hierarchical_verbose_manager_agent.yaml
View File

@@ -1524,4 +1524,362 @@ interactions:
- req_55957b9cd106057878eea339ef651998
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: Researcher, Senior Writer\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: Researcher, Senior Writer\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: Come up with a list of 5 interesting ideas to explore
for an article, then write one amazing paragraph highlight for each idea that
showcases how good an article about this topic could be. Return the list of
ideas with their paragraph and your notes.\n\nThis is the expected criteria
for your final answer: 5 bullet points with a paragraph for each idea.\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":
"Thought: To come up with a list of 5 interesting article ideas and write a
compelling paragraph for each one, I should first generate the ideas. For this,
I will delegate the task to the Researcher and then use the Senior Writer to
create the paragraphs.\n\nAction: Delegate work to coworker\nAction Input: {\"task\":
\"Generate a list of 5 interesting ideas to explore for an article.\", \"context\":
\"We need to come up with 5 interesting and unique article ideas that will captivate
readers.\", \"coworker\": \"Researcher\"}\nObservation: 1. **The Rise of AI
in Healthcare: Revolutionizing Diagnosis and Treatment**\n - Artificial intelligence
is transforming the healthcare industry in unprecedented ways. From enhancing
diagnostic accuracy with AI-driven tools to creating personalized treatment
plans, AI is bridging gaps in medical care and bringing about a revolution.
Imagine a world where diseases are diagnosed at lightning speed, and treatments
are tailored to individual genetic makeups. This article will explore these
groundbreaking advancements, featuring real-world applications and expert insights,
revealing the future of healthcare driven by AI.\n\n2. **AI and Ethics: Navigating
the Moral Complexity of Machine Intelligence**\n - As AI technology advances,
ethical dilemmas emerge, challenging our understanding of morality and responsibility.
This article delves into the complex world of AI ethics, examining pressing
issues like algorithmic bias, privacy concerns, and the ethical responsibilities
of developers. With input from ethicists, technologists, and policymakers, it
offers a comprehensive look at the moral landscape of AI, guiding readers through
the critical questions that shape the future of machine intelligence and its
impact on society.\n\n3. **AI Agents in the Workplace: Enhancing Productivity
or Eroding Jobs?**\n - The introduction of AI agents in the workplace presents
a double-edged sword; while these technologies can vastly enhance productivity
by automating routine tasks, they also raise concerns about job displacement.
This article paints a balanced picture, drawing on data and expert forecasts
to explore both sides of the argument. Are we heading towards a future where
AI aids human creativity and efficiency, or are we on the brink of a job crisis?
The answer may be a nuanced blend of both.\n\n4. **From Science Fiction to Reality:
The Evolution of AI Agents in Popular Culture**\n - AI has long been a staple
of science fiction, captivating audiences with visions of intelligent machines.
This article traces the portrayal of AI agents in movies, books, and video games,
juxtaposing these fictional narratives against today\u2019s technological realities.
Interviews with creators from the entertainment industry and AI experts illuminate
how close\u2014or far\u2014we are from making these sci-fi dreams a reality,
providing a fascinating journey through the evolution of AI in popular culture.\n\n5.
**The Future of AI in Personalization: Creating Tailored Experiences in Everyday
Life**\n - Imagine a world where every experience, from shopping to entertainment,
is uniquely tailored to your preferences by intelligent systems. This article
explores the cutting-edge of AI-driven personalization, discussing current technologies
and future potentials. Featuring insights from industry leaders and technologists,
readers will discover how AI is revolutionizing the way we live, offering bespoke
experiences that were once the realm of fantasy but are swiftly becoming a part
of our daily lives."}, {"role": "assistant", "content": "Thought: Now that I
have the list of 5 interesting article ideas from the Researcher, the next step
is to ask the Senior Writer to create a compelling paragraph for each idea.
This will ensure that each topic is highlighted effectively.\n\nAction: Delegate
work to coworker\nAction Input: {\"task\": \"Write one amazing paragraph highlight
for each of these 5 article ideas: \\n\\n1. **The Rise of AI in Healthcare:
Revolutionizing Diagnosis and Treatment**\\n- This article could explore how
AI is making strides in the healthcare industry. From AI-driven diagnostic tools
to personalized treatment plans, the piece could highlight real-world applications
and the potential future impact. Interviews with healthcare professionals and
case studies could add depth and credibility.\\n\\n2. **AI and Ethics: Navigating
the Moral Complexity of Machine Intelligence**\\n- Delve into the ethical considerations
surrounding AI development and deployment. The article could examine issues
such as bias in AI algorithms, privacy concerns, and the ethical responsibility
of AI developers. Expert opinions from ethicists, technologists, and policymakers
can provide a well-rounded perspective.\\n\\n3. **AI Agents in the Workplace:
Enhancing Productivity or Eroding Jobs?**\\n- This piece can analyze the dual
impact of AI agents in the professional environment. While some argue that AI
can significantly boost productivity by automating mundane tasks, others fear
job displacement. The article can present both sides, backed by data and forecasts
about labor market trends.\\n\\n4. **From Science Fiction to Reality: The Evolution
of AI Agents in Popular Culture**\\n- An engaging piece that traces the depiction
of AI agents in movies, books, and video games, and compares these fictional
portrayals to the current state of AI technology. This can include interviews
with creators from the entertainment industry and AI experts to discuss how
close we are to realizing these sci-fi visions.\\n\\n5. **The Future of AI in
Personalization: Creating Tailored Experiences in Everyday Life**\\n- Discuss
how AI is enhancing personalization in various domains such as shopping, entertainment,
education, and personal finance. The focus can be on current technologies and
future possibilities, featuring insights from industry leaders and technologists
who are driving these innovations.\", \"context\": \"Create compelling paragraphs
that highlight the potential and intrigue of each article idea. These should
be engaging and showcase how fascinating each article could be.\", \"coworker\":
\"Senior Writer\"}\n\nObservation: The Senior Writer provided the following
compelling paragraphs for each article idea:\n\n1. **The Rise of AI in Healthcare:
Revolutionizing Diagnosis and Treatment**\n - Imagine a world where a doctor
can diagnose a condition with pinpoint accuracy, thanks to the help of artificial
intelligence. AI is already transforming healthcare with advanced diagnostic
tools and personalized treatment plans. This article would delve into real-world
cases where AI has made a significant impact, providing insights from healthcare
professionals who witness these technological advancements firsthand. The future
of medicine is not only in the hands of doctors and nurses but also in the code
and algorithms of AI systems.\n\n2. **AI and Ethics: Navigating the Moral Complexity
of Machine Intelligence**\n - The rapid development of artificial intelligence
brings with it not just technological advancements but also a slew of ethical
dilemmas. This article will explore the complex moral landscape AI inhabits,
questioning the bias that may be programmed into algorithms, the privacy concerns
surrounding data usage, and the ethical responsibilities of those who develop
AI technologies. Insightful perspectives from ethicists, technologists, and
policymakers will highlight how society can navigate these challenges to ensure
that AI benefits humanity as a whole.\n\n3. **AI Agents in the Workplace: Enhancing
Productivity or Eroding Jobs?**\n - As AI agents become more integrated into
the workforce, the debate over their impact intensifies. This article will examine
how AI can boost productivity by automating routine tasks, thereby freeing up
human workers for more creative and strategic roles. However, it will also address
the fear of job displacement and present data and forecasts about the future
labor market. Balanced viewpoints from industry analysts and workers affected
by AI implementation will offer a comprehensive understanding of the pros and
cons of AI in the workplace.\n\n4. **From Science Fiction to Reality: The Evolution
of AI Agents in Popular Culture**\n - From HAL 9000 to Jarvis, AI agents have
long captivated our imaginations in books, movies, and video games. This article
will take readers on a journey through time, highlighting how AI has been portrayed
in popular culture and comparing these fictional depictions to the current state
of AI technology. Conversations with creators from the entertainment industry
and AI experts will reveal whether these sci-fi visions are becoming our reality
and what the future holds for AI in culture.\n\n5. **The Future of AI in Personalization:
Creating Tailored Experiences in Everyday Life**\n - In an increasingly digital
world, AI is enhancing personalization across various domains, crafting tailored
experiences that cater to individual needs. This article will explore how AI
is revolutionizing everything from shopping and entertainment to education and
personal finance. Featuring insights from industry leaders and technologists,
the piece will showcase the current state of personalization technologies and
speculate on future advancements, painting a vivid picture of a world where
AI knows us better than we know ourselves.\nObservation: 1. **The Rise of AI
in Healthcare: Revolutionizing Diagnosis and Treatment**\n - Artificial Intelligence
is spearheading a transformative era in healthcare, fundamentally altering how
diseases are diagnosed and treated. AI-driven diagnostic tools are already outperforming
human experts in identifying ailments from medical images, while personalized
treatment plans are becoming a reality through predictive analytics that cater
to individual patient needs. This article will dive into real-world applications,
such as AI algorithms detecting early-stage cancers or predicting patient outcomes
with unprecedented accuracy. Featuring interviews with healthcare professionals
and insightful case studies, it will paint a vivid picture of how AI is not
only enhancing medical outcomes but also reshaping the entire healthcare landscape
for the future.\n\n2. **AI and Ethics: Navigating the Moral Complexity of Machine
Intelligence**\n - As Artificial Intelligence continues to evolve, it brings
with it a host of ethical dilemmas that society must grapple with. This article
will delve into the moral intricacies of AI, focusing on pressing issues such
as algorithmic bias, the preservation of privacy, and the ethical duties of
AI developers. By examining high-profile cases of biased AI and exploring the
perspectives of ethicists, technologists, and policymakers, the piece will offer
a comprehensive look at the ethical landscape of machine intelligence. It aims
to provoke thought and spark dialogue on how we can responsibly harness AI''s
power while safeguarding human values and rights.\n\n3. **AI Agents in the Workplace:
Enhancing Productivity or Eroding Jobs?**\n - The integration of AI agents
in the workplace presents a paradox of progress and peril. On one hand, AI can
drastically enhance productivity by automating repetitive tasks and offering
intelligent insights that drive innovation. On the other, there is a growing
concern about job displacement and the socioeconomic implications of a heavily
automated workforce. This article will explore this dual impact, presenting
data and forecasts on labor market trends and featuring opinions from industry
experts, economists, and affected workers. By striking a balance between optimism
and caution, it will provide a nuanced view of AI''s role in reshaping the future
of work.\n\n4. **From Science Fiction to Reality: The Evolution of AI Agents
in Popular Culture**\n - The portrayal of AI agents in popular culture has
long fascinated and terrified us, from the benevolent, human-like robots of
movies and books to the dystopian scenarios of video games. This article will
take readers on a journey through the evolution of AI in fiction, contrasting
these imaginative narratives with the current capabilities and limitations of
real-world AI. Interviews with filmmakers, authors, and game developers, alongside
insights from AI researchers, will shed light on how closely today''s technology
mirrors these sci-fi visions. The piece aims to captivate readers by exploring
the interplay between creativity and technological advancement, revealing the
thin line between fantasy and reality.\n\n5. **The Future of AI in Personalization:
Creating Tailored Experiences in Everyday Life**\n - AI is revolutionizing
the concept of personalization, offering users tailored experiences in areas
as diverse as shopping, entertainment, education, and personal finance. This
article will explore how AI algorithms are learning from user behaviors and
preferences to deliver highly customized content and recommendations, enhancing
user satisfaction and engagement. By highlighting current technologies and featuring
interviews with industry leaders and technologists, it will forecast future
possibilities and innovations. The piece will demonstrate how AI personalization
is not just a trend, but a paradigm shift in how we interact with technology
in our daily lives, promising a future where every experience can be uniquely
tailored to individual needs. \n\nThese paragraphs showcase the potential and
intrigue of each topic, demonstrating how engaging and insightful the articles
could be."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '16854'
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:
- 974ede154cc51701-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:29:03 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=5JVBbOOy3Z42TimGf_AeViTUOxCEjozvdxUWf6hbQmU-1756164543-1.0.1.1-ygsmJWfEEPPXLcyJJ.RM_4EU3eUrQ5umh1p5NnpVok3tJoYTzI_qdTIg85sL3QuSmGfOIM9i8qLgCV4etmoxJoh_wAlBljpVEi27.U3_dz0;
path=/; expires=Mon, 25-Aug-25 23:59:03 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=zAJ0jqazHLpztPpOyEi_EdNt5yCl9A2Gzu_U4E02x2E-1756164543702-0.0.1.1-604800000;
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:
- '19204'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '19224'
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:
- '29995866'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 8ms
x-request-id:
- req_946a3113146e463cb4c0bc9cb8cb9a22
status:
code: 200
message: OK
version: 1

159
tests/cassettes/test_increment_delegations_for_hierarchical_process.yaml
View File

@@ -607,4 +607,163 @@ interactions:
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.\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 get an integer score between
1-5 for the given title. To do this, I''ll ask the Scorer to evaluate the title
based on specific criteria.\n\nAction: Ask question to coworker\nAction Input:
{\"question\": \"Can you provide an integer score between 1-5 for the following
title: ''The impact of AI in the future of work''?\", \"context\": \"We need
a score for the title to assess its impact and relevance. Please evaluate based
on factors such as clarity, relevance, and potential interest to readers.\",
\"coworker\": \"Scorer\"}\nObservation: The score for the title ''The impact
of AI in the future of work'' is 4 out of 5."}], "model": "gpt-4o", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3675'
content-type:
- application/json
cookie:
- _cfuvid=lnKPmS3pW0Tw6qE4ZI8cf4lyVDuLg7ZNxmzxi7CqlME-1756165116673-0.0.1.1-604800000;
__cf_bm=r95s2Hh1kHgI6PI08wwTySLyufxeDnmixIX5GVDEyoA-1756165116-1.0.1.1-X5dML3NG4uvFgDnjqJ4pQWbB9MyxJisxAZJlRivMc7T1f83cCNBH_cy5fJjn4XjKks_UKUUj5PvBGifu2gLkaiqYYWvbSjrhjKseuPN8.Q4
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:
- 974eec8be8b98486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:37 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:
- '383'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '488'
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:
- '29999132'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_58742f78663b48c2be01fcc6497a46da
status:
code: 200
message: OK
version: 1

158
tests/cassettes/test_increment_delegations_for_sequential_process.yaml
View File

@@ -449,4 +449,162 @@ interactions:
- req_32907c02e96c6932e9424220bb24bb7a
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Manager. You''re great
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
processes\nYou ONLY have access to the following tools, and should NEVER make
up tools that are not listed here:\n\nTool Name: Delegate work to coworker\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.\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: To provide
an accurate score for the title \"The impact of AI in the future of work,\"
I need to delegate the task of scoring it to the Scorer, who is specialized
in this activity.\n\nAction: Delegate work to coworker\nAction Input: {\"coworker\":
\"Scorer\", \"task\": \"Give me an integer score between 1-5 for the following
title: ''The impact of AI in the future of work''\", \"context\": \"Your task
is to evaluate the provided title on a scale from 1 to 5 based on criteria such
as relevance, clarity, and intrigue.\"}\n\nObservation: The scorer has received
the task to score the title ''The impact of AI in the future of work''.\nObservation:
4"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3322'
content-type:
- application/json
cookie:
- _cfuvid=CW_cKQGYWY3cL.S6Xo5z0cmkmWHy5Q50OA_KjPEijNk-1735926034530-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA4xSTWvcMBC9+1cMOq+Dvd/1LTQt5NJLP6C0wWjlsa1G1ghpnLSE/e9F2uzaaVPo
RSC9eU/vzcxTBiB0IyoQqpesBmfyt/vDSpvbDx+97L+gftjhzVdX3rzT1/3nrVhEBh1+oOIz60rR
4AyyJnuClUfJGFXL3WZbbjdluU7AQA2aSOsc52vKl8VynRf7vHjWVT1phUFU8C0DAHhKZ7RoG/wp
KigW55cBQ5AdiupSBCA8mfgiZAg6sLQsFhOoyDLa5PpTT2PXcwW3YOkR7uPBPUKrrTQgbXhEf/Xd
vk/X63StYD0X89iOQcYsdjRmBkhriWXsRYpx94wcL8YNdc7TIfxBFa22OvS1RxnIRpOByYmEHjOA
u9Sg8UVm4TwNjmume0zf7U59TmHPI5nQC8jE0sxYy/3iFb26QZbahFmLhZKqx2aiTvOQY6NpBmSz
1H+7eU37lFzb7n/kJ0ApdIxN7Tw2Wr1MPJV5jBv7r7JLl5NhEdA/aIU1a/RxEg22cjSnZRLhV2Ac
6lbbDr3z+rRRrav3xZvNdrNaqYPIjtlvAAAA//8DAAsTiaNaAwAA
headers:
CF-RAY:
- 974eec7c4d438486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:35 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=ULOCzvd5MabFyMl9eSNQ3Sk_hNbVH25aTAfkSaYM6Cw-1756165115-1.0.1.1-jeyMlIwg.jml3h9XQDOYQXVxEFP44CSbUCENlr4W6RpdsZg08M.fWUD5kBWDNcupp2skTxNh5gCYFNop3HIrWq5pzgrydiA3FuSe7U15X1Y;
path=/; expires=Tue, 26-Aug-25 00:08:35 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=e_81pnlfj.JohLmFm8gTRISqkPCT6GwCVpOdPsECI.s-1756165115098-0.0.1.1-604800000;
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:
- '680'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '715'
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:
- '29999221'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_4006f3362c434ea2a39b9901f3f2e5cb
status:
code: 200
message: OK
version: 1

169
tests/cassettes/test_increment_tool_errors.yaml
View File

@@ -728,4 +728,173 @@ interactions:
- req_c065668c78262d2781db5b3b04f70dba
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'', check examples to based your evaluation.\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.\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:
To give an accurate score for the title \"The impact of AI in the future of
work\" based on the specified criteria, I''ll need the expertise of the Scorer.
They specialize in evaluating content, so I must delegate this task to them.
I need to provide them with all the necessary context, including the title and
the importance of giving a well-considered, integer score between 1-5. Since
the request stresses the importance of this task and its implications for my
job, I will make sure to communicate the urgency and the criteria very clearly
to the Scorer.\n\nAction: Delegate work to coworker\n\nAction Input: {\"task\":
\"Evaluate the title ''The impact of AI in the future of work'' and give it
an integer score between 1-5, based on your expert assessment.\", \"context\":
\"The task is to assign a score to the given title based on its significance,
relevance, and impactfulness regarding the future of work influenced by artificial
intelligence. This score needs to reflect a thorough evaluation within the range
of 1 (being the least impactful or relevant) to 5 (being the most impactful
or relevant). The assessment is highly important and could significantly affect
our future work, so it''s crucial to consider the current discourse on AI, its
potential transformative power on industries and job markets, and general expectations
of its future role.\", \"coworker\": \"Scorer\"}\nObservation: The score of
the title \"The impact of AI in the future of work\" is 5."}], "model": "gpt-4-0125-preview",
"stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '4575'
content-type:
- application/json
cookie:
- _cfuvid=FasG_74jjKfEtA2Mjn2iKdu62tv3zosBxYNYTk1E12M-1734025911900-0.0.1.1-604800000
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//jJJNaxsxEIbv/hWDznaIE9t19uYWUkLTQiG3OiyydnZXtlajSLN2m+D/
XqSNvZs2hV4E0jPvq/l6GQEIXYgMhKolq8aZyafl5nq7emqWz9+/bO8/Pu9n3+4VL+nz01e8FeOo
oM0WFZ9UF4oaZ5A12Q4rj5Ixuk4/zBfTxXw6nSfQUIEmyirHk9nkcno1nziPe42HV2VNWmEQGfwY
AQC8pDPmaAv8KTK4HJ9eGgxBViiycxCA8GTii5Ah6MDSshj3UJFltCnth5raquYM7sDSAXbx4Bqh
1FYakDYc0K/t2t6m+yrdM3ioEYIij0BlCmfNBmEtItCNk4ojWd2Btp1dy20XfSC/WwvQAeYXw5w8
lm2QsSe2NWYApLXEMvY0dePxlRzP9RuqnKdN+EMqSm11qHOPMpCNtQYmJxI9jgAeU5/bN60TzlPj
OGfaYfruZnHV+Yl+tD29PkEmlmagupmN3/HLC2SpTRhMSiipaix6aT9W2RaaBmA0qPrvbN7z7irX
tvof+x4ohY6xyJ3HQqu3FfdhHuPm/yvs3OWUsAjo91phzhp9nESBpWxNt5Mi/AqMTV5qW6F3XqfF
jJMcHUe/AQAA//8DAErhO7yXAwAA
headers:
CF-RAY:
- 974eec827a978486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:36 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=r95s2Hh1kHgI6PI08wwTySLyufxeDnmixIX5GVDEyoA-1756165116-1.0.1.1-X5dML3NG4uvFgDnjqJ4pQWbB9MyxJisxAZJlRivMc7T1f83cCNBH_cy5fJjn4XjKks_UKUUj5PvBGifu2gLkaiqYYWvbSjrhjKseuPN8.Q4;
path=/; expires=Tue, 26-Aug-25 00:08:36 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=lnKPmS3pW0Tw6qE4ZI8cf4lyVDuLg7ZNxmzxi7CqlME-1756165116673-0.0.1.1-604800000;
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:
- '1211'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1305'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1998911'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 32ms
x-request-id:
- req_3ee53a55bafb9d8ab8855cf07987362b
status:
code: 200
message: OK
version: 1

635
tests/cassettes/test_output_json_dict_hierarchical.yaml
View File

@@ -555,4 +555,639 @@ interactions:
- 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 |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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 |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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 |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==
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

653
tests/cassettes/test_output_json_hierarchical.yaml
View File

@@ -579,4 +579,657 @@ interactions:
- req_dd38f9b6e9e6ac64ebbb827111e31414
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the task you
want them to do, and ALL necessary context to execute the task, they know nothing
about the task, so share absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolutely everything you know, don''t
reference things but instead explain them.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Delegate work to coworker, Ask question
to coworker], just the name, exactly as it''s written.\nAction Input: the input
to the action, just a simple JSON object, enclosed in curly braces, using \"
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\n```\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n```"}, {"role": "user", "content": "\nCurrent Task: Give me
an integer score between 1-5 for the following title: ''The impact of AI in
the future of work''\n\nThis is the expected criteria for your final answer:
The score of the title.\nyou MUST return the actual complete content as the
final answer, not a summary.\nEnsure your final answer contains only the content
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
not include any code block markers like ```json or ```python.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3194'
content-type:
- application/json
cookie:
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
_cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 974eec36591c8486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:27 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '3819'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '3856'
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999242'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_e91c7ccb367243348f19a41989b6992d
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an
expert scorer, specialized in scoring titles.\nYour personal goal is: Score
the title\nTo give my best complete final answer to the task respond using the
exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
Your final answer must be the great and the most complete as possible, it must
be outcome described.\n\nI MUST use these formats, my job depends on it!"},
{"role": "user", "content": "\nCurrent Task: Score the title ''The impact of
AI in the future of work'' on a scale from 1 to 5.\n\nThis is the expected criteria
for your final answer: Your best answer to your coworker asking you this, accounting
for the context shared.\nyou MUST return the actual complete content as the
final answer, not a summary.\n\nThis is the context you''re working with:\nThe
task requires evaluating the title based on factors such as relevance, impact,
and clarity. The score should be an integer between 1 to 5, where 1 is poor
and 5 is excellent.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role":
"assistant", "content": "Thought: I need to delegate the task of scoring the
title \"The impact of AI in the future of work\" to the Scorer. I will provide
them with all necessary context to execute the task.\n\nAction: Delegate work
to coworker\nAction Input: {\"task\": \"Score the title ''The impact of AI in
the future of work'' on a scale from 1 to 5.\", \"context\": \"The task requires
evaluating the title based on factors such as relevance, impact, and clarity.
The score should be an integer between 1 to 5, where 1 is poor and 5 is excellent.\",
\"coworker\": \"Scorer\"}\nObservation: I encountered an error: Action ''Delegate
work to coworker'' don''t exist, these are the only available Actions:\n\nMoving
on then. I MUST either use a tool (use one at time) OR give my best final answer
not both at the same time. When responding, I must use the following format:\n\n```\nThought:
you should always think about what to do\nAction: the action to take, should
be one of []\nAction Input: the input to the action, dictionary enclosed in
curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action
Input/Result can repeat N times. Once I know the final answer, I must return
the following format:\n\n```\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described\n\n```"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '2627'
content-type:
- application/json
cookie:
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
_cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 974eec4fbebf8486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:31 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '4218'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '4238'
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999394'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_28f00852660542e88719133a722fce84
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the task you
want them to do, and ALL necessary context to execute the task, they know nothing
about the task, so share absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolutely everything you know, don''t
reference things but instead explain them.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Delegate work to coworker, Ask question
to coworker], just the name, exactly as it''s written.\nAction Input: the input
to the action, just a simple JSON object, enclosed in curly braces, using \"
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\n```\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n```"}, {"role": "user", "content": "\nCurrent Task: Give me
an integer score between 1-5 for the following title: ''The impact of AI in
the future of work''\n\nThis is the expected criteria for your final answer:
The score of the title.\nyou MUST return the actual complete content as the
final answer, not a summary.\nEnsure your final answer contains only the content
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
not include any code block markers like ```json or ```python.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "Thought:
I need to delegate the task of scoring the title \"The impact of AI in the future
of work\" to the Scorer. I will provide them with all necessary context to execute
the task.\n\nAction: Delegate work to coworker\nAction Input: {\"task\": \"Score
the title ''The impact of AI in the future of work'' on a scale from 1 to 5.\",
\"context\": \"The task requires evaluating the title based on factors such
as relevance, impact, and clarity. The score should be an integer between 1
to 5, where 1 is poor and 5 is excellent.\", \"coworker\": \"Scorer\"}\nObservation:
To evaluate the title ''The impact of AI in the future of work'', we need to
consider relevancy, impact, and clarity. Here''s the assessment:\n\n- **Relevance
(5/5):** The title is highly relevant, as Artificial Intelligence (AI) is a
major topic of interest in today''s fast-evolving technological landscape. The
future of work is a crucial subject that affects diverse industries and professions
worldwide, which makes it a timely and meaningful subject to explore.\n \n-
**Impact (5/5):** The title suggests a profound impact since AI is anticipated
to significantly transform the workspace by automating jobs, creating new job
categories, and altering how traditional jobs are performed. Analyzing these
potential changes can greatly inform and influence policymakers, businesses,
and the workforce.\n \n- **Clarity (5/5):** The title is clear and concise.
It directly points out the subject (AI) and the specific context (the future
of work) it impacts. There''s no ambiguity, making it accessible to a broad
audience, including professionals, students, and general readers interested
in technology''s influence on employment trends.\n\nOverall, the title ''The
impact of AI in the future of work'' scores an excellent 5 out of 5. It adequately
captures a complex, forward-thinking issue with clarity, relevance, and significant
impact potential."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '5147'
content-type:
- application/json
cookie:
- __cf_bm=N_ULh2gJbt2dWumbG8h6_rw_QD0TBQ3f1NYS.FsG3w0-1756165097-1.0.1.1-fGULs7H8u7wOLv7QAwRQdlWcZr2zj6dkLXQk5xPa.7SBOn9qj1nh6.VDONMzgxqO2telES4KZZPzeC2G4YFJXV5Q4hemTm4jcMsXA10XFYM;
_cfuvid=_3IyqhyxR3x9q67TqmIC1eWhmeXZIMbk_6ChUHMngHM-1756165097262-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAAwAAAP//jFJda9wwEHz3r1j0fA72fcXxW1oIlPahlFAKdTA6eW2rkSVFWt+1Pe6/
F9mXs9Ok0BeBNDujmd09RgBMViwHJlpOorMqfp/tVvXTzVP7ZU2Zv91/fWc/Hu7Ft893+0+/2SIw
zO4HCnpmXQnTWYUkjR5h4ZATBtX0erNNt5s0TQegMxWqQGssxWsTL5PlOk6yONmeia2RAj3L4XsE
AHAczmBRV/iT5ZAsnl869J43yPJLEQBzRoUXxr2XnrgmtphAYTShHlzft6ZvWsrhA2hzgMdwUItQ
S80VcO0P6K4KfTdcb4drDsdCAxTMC+OwYDlsCn2a6zuse89DPN0rNQO41oZ4aM+Q7OGMnC5ZlGms
Mzv/F5XVUkvflg65Nzr49mQsG9BTBPAw9Kx/0QZmnekslWQecfguTbLtKMimMU3wMj2DZIirGS1N
rhdvKJYVEpfKz/rOBBctVhN3GhLvK2lmQDTL/drOW9pjdqmb/5GfACHQElaldVhJ8TLyVOYwrPG/
yi59Hgwzj24vBZYk0YVZVFjzXo0bxvwvT9iVtdQNOuvkuGa1LbPkZrPdrFZix6JT9AcAAP//AwBy
ib1VbwMAAA==
headers:
CF-RAY:
- 974eec6aa9b18486-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:38:32 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '556'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '614'
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29998767'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_92650754cfb84bb9bff203c3b554da6e
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the task you
want them to do, and ALL necessary context to execute the task, they know nothing
about the task, so share absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolutely everything you know, don''t
reference things but instead explain them.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Delegate work to coworker, Ask question
to coworker], just the name, exactly as it''s written.\nAction Input: the input
to the action, just a simple JSON object, enclosed in curly braces, using \"
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\n```\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n```"}, {"role": "user", "content": "\nCurrent Task: Give me
an integer score between 1-5 for the following title: ''The impact of AI in
the future of work''\n\nThis is the expected criteria for your final answer:
The score of the title.\nyou MUST return the actual complete content as the
final answer, not a summary.\nEnsure your final answer contains only the content
in the following format: {\n \"score\": int\n}\n\nEnsure the final output does
not include any code block markers like ```json or ```python.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "Thought:
I need to delegate the task of scoring the title \"The impact of AI in the future
of work\" to the Scorer. I will provide them with all necessary context to execute
the task.\n\nAction: Delegate work to coworker\nAction Input: {\"task\": \"Score
the title ''The impact of AI in the future of work'' on a scale from 1 to 5.\",
\"context\": \"The task requires evaluating the title based on factors such
as relevance, impact, and clarity. The score should be an integer between 1
to 5, where 1 is poor and 5 is excellent.\", \"coworker\": \"Scorer\"}\nObservation:
{\n \"score\": 5\n}"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3822'
content-type:
- application/json
cookie:
- _cfuvid=CW_cKQGYWY3cL.S6Xo5z0cmkmWHy5Q50OA_KjPEijNk-1735926034530-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 974eef2f6d51dc0d-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:40:25 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=OccMxrmCRox_7bIJtedFlhoPOuuUvZzIFuNich2H1JY-1756165225-1.0.1.1-GZu0FYiwF3GrVFp6V5lDMCNsqJ3lPFJoATnPc50dACgSXHbkzGM7.MHv7GvUoDKXSyRy2Rxf5hGsRH_FPp.tBEzcki6qQDXIBhWde1NEJkE;
path=/; expires=Tue, 26-Aug-25 00:10:25 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=aj4gjWj2skMQt34sZXxfiLoWjDQdxXvxh0I9isfN5II-1756165225584-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '510'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '623'
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999099'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_18884789d50842b7bcfffb3752d3fd0f
status:
code: 200
message: OK
version: 1

630
tests/cassettes/test_output_pydantic_hierarchical.yaml
View File

@@ -561,4 +561,634 @@ interactions:
- 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

639
tests/cassettes/test_using_contextual_memory.yaml
View File

@@ -1028,4 +1028,643 @@ interactions:
status:
code: 200
message: OK
- request:
body: '{"input": ["Example: Toy Cars(Math Example): An example used to illustrate
addition by counting toy cars."], "model": "text-embedding-3-small", "encoding_format":
"base64"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '172'
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-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/embeddings
response:
body:
string: !!binary |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headers:
CF-RAY:
- 974f08951aa4251c-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:57:45 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=L28ZVHkSMOSpzu9MoQzdDgOYGHI9uQZnBcGj5Txg9e8-1756166265-1.0.1.1-9494dtPfVD9FwZG8RVJ6EnsQqAuzb2nnmeyRQLpPrX5IK2bR3KadJFV3K8HTAJa0lU9lIhCtu4fezMScnlMYOGAO0zGsIWMyozgrpePziWg;
path=/; expires=Tue, 26-Aug-25 00:27:45 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=NaNzk_g04ozIFjR4zD0Joz9IJWntjKPTzifJUuegmAo-1756166265356-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-allow-origin:
- '*'
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-model:
- text-embedding-3-small
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '69'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
via:
- envoy-router-74b9c68cd4-sld2z
x-envoy-upstream-service-time:
- '183'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '10000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '9999977'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_f779ba78781c452aa13e52ea0ca6a682
status:
code: 200
message: OK
- request:
body: '{"input": ["Example: Using Fingers(Math Example): An interactive way to
teach addition using fingers as counting tools."], "model": "text-embedding-3-small",
"encoding_format": "base64"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '186'
content-type:
- application/json
cookie:
- __cf_bm=L28ZVHkSMOSpzu9MoQzdDgOYGHI9uQZnBcGj5Txg9e8-1756166265-1.0.1.1-9494dtPfVD9FwZG8RVJ6EnsQqAuzb2nnmeyRQLpPrX5IK2bR3KadJFV3K8HTAJa0lU9lIhCtu4fezMScnlMYOGAO0zGsIWMyozgrpePziWg;
_cfuvid=NaNzk_g04ozIFjR4zD0Joz9IJWntjKPTzifJUuegmAo-1756166265356-0.0.1.1-604800000
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-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/embeddings
response:
body:
string: !!binary |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headers:
CF-RAY:
- 974f0896accb251c-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 25 Aug 2025 23:57:45 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-allow-origin:
- '*'
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-model:
- text-embedding-3-small
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '86'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
via:
- envoy-router-74b9c68cd4-l7mvz
x-envoy-upstream-service-time:
- '120'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '10000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '9999974'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_3118ad98ecf3443a93df58599e50e305
status:
code: 200
message: OK
- request:
body: '{"input": ["Example: Using Fingers(Math Example): An interactive way to
teach addition using fingers as counting tools."], "model": "text-embedding-3-small",
"encoding_format": "base64"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '186'
content-type:
- application/json
cookie:
- __cf_bm=L28ZVHkSMOSpzu9MoQzdDgOYGHI9uQZnBcGj5Txg9e8-1756166265-1.0.1.1-9494dtPfVD9FwZG8RVJ6EnsQqAuzb2nnmeyRQLpPrX5IK2bR3KadJFV3K8HTAJa0lU9lIhCtu4fezMScnlMYOGAO0zGsIWMyozgrpePziWg;
_cfuvid=NaNzk_g04ozIFjR4zD0Joz9IJWntjKPTzifJUuegmAo-1756166265356-0.0.1.1-604800000
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-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/embeddings
response:
body:
string: !!binary |
H4sIAAAAAAAAA1R6SROySrPm/vsVJ86WviGTVHJ2CIjIVCiD2NHRASoIDghIQdWN+9878P3idvfG
BZZaVmXmM2T+57/++uvvtmhul+/f//z197Mevn//j+XZNf/mf//z1//8119//fXXf/5e/7+Vt1dx
u17rd/Vb/nuzfl9v89///MX/95P/u+ifv/4+7q12rFMtdNkoCLF6MLQjPr2iJ6Mxv4lhdz6V440L
2oZt+SpE3fqj4XQ4Dw2TQT+qqlXkwaHICpdOl3elDvaT4O0W6mhqonMNt7N3widmYTZrrpIDn14I
Nl/tjvFW+M3AfT4fOLqah0KUXHGA+Lb7EizNpsGCioTIGXcpdvcacafkIteArnZBLg/njMj2eMxU
E102eHPaqBEbvEeGsnaNiEMUpR+K88qEM6oK4im9485pWg5yn1g+PivjhdFMxzVszTQfBbGMDD4V
LQob4e0HpZCqxcgSFEAhfWzsNaxA3zQ9jfB6SFesV3Bg8yF/TGgVqdy4mpSDyztM19SNnj1xJndW
T56rxlQz4bIl4U3XItHjVzdwpU2B4xntitl/3I8Aj/YzynzUMkH00QCllSd4u2NOL3yuuq2Ij01E
gmK4ugMeeVBtGj3IfjCdhueVoIbQFTlscPLdZSjSLDUuvY7gZtq70naURZXbPYzxHdOqmDxla0K6
X1d4f0oYo8/yGECNhxU53PBYsMu9qEA+8wXeSVe/kTykWDDsXBlbe83oJa5IJ3XzGh18vEhGQe3L
y0L1fkzIYUt3xmSbm04V/E4nW5qbPR/yjxxOh/OIz/t65XbAOxM6cDQj4eP9KAZSfWqV1ttbsOLM
DPHokwzq4ZyIBDe7i9EqrW6pI+/E5PYsqfs9gNLC9BB47GaZatBKsiw4lzQeucxAxtQEwgAPs3BH
4dwHxvy8oEzFZjyTrC620dTMxkMlTikTbMvIYCziPFjf088Igjr2k8zNJtKzWcDO+xZEwkZwU+Ao
9oP1jCiiTJUrWPKDxPprZtS/8Dzyg3s7ytfvnomB8+ngvsq3IyGG3dPY83TALjt+q5d3LRjE0QgH
0VNwGZHA5bvqSCH9ym6g1NMRUZtDHHDh7UK0c2wysRE3gborlIgYp5WEWL+9p8g+cN2oRFcWtSWy
TXDSTiD4yeGIr42bCPtaT/E1bC/GLPZPCs6lL7GxT7Y9f7GyUN1bISa26MzuSOm5RdvLTsDuuPYj
4UDfOfqEmU7Cct02gjQngUrm3gvmzT53pQRzF7TEH/bCYjTmQz5MMNhvMnJfxBVEyiqqbqdzQWw1
q10qhscKGDLqQAYiGNParF7woTYjucFSly/iXau6D/cbrJppbwxKMx5hXcozTi71vaBzG2TKqjRD
nDhRZYzqWgmgczcuDp7l0RAcoRL/3JfPd9Sd8iOvoejsxCMHpyoaz4QPVb9US5zwrcOE8RoqarHa
fYLX00X9tHUEUNF82eAChrqg+6GlQLYPlyTyd11MnZxk6rNYZyQS2Bu1yhY8sNm3IC7kzKDmcNRV
PrxsyfF2gWK2dbOD9kB9Epw4L5ptq7qoPvDNL18i4cFzOkhF8CKRPxiFpJ+QhQzgPXL4rt2GiR2C
Xz3BeIkP0a+HEIRLs8Wm27uGFILGq1l/I8Sfnk0zb/tAhHy9ibD92osGXV+3Ovh8tCX67XKJunbm
HeAgqDGelNkgkc1yUG0uGHmQ9gabPWbDyu/O40poh36OXm4HuLJkstv7h4Z/6gcO4hPdE7+TrsaS
/xRiKz6SdK8ZjXD+Xi/wScmLaNvog4gKB12VOCseH46r9QKXA4eqq1KTKw+biGcylUGhvBdw1vXF
BnPfxbCaBB2XvvxkLA5qXv3Vb7x3nIhJ4pFHJxAV7KbMQKxvigxkjTOIdbe+xszpSox09Gkw7hLf
YGru2tDJeI8Dp06KaXplnPqr/6dCexVTMpUxWs+fBh9uOCikoFMq5Deci/HhJfZULtY58vtswKZ3
ttB8+w4B1IXtkYNGL8VQaK0ITtW5AfWQiGg7mIMa4OEQrMqzW4zX54oCq/cO1o15ZPOkW+YvnvAp
P62LobdDR71qx4gcTXtgkzaH8i9fyfZ23jdzWZx1lHWajDdq07JJ5fmHOjthSmJGcc/TkXTwHToL
m1V+R/N8tCd1imslUISDUVCdBSma1VkOVD7iIwpkBHTnIjsQHcll3534HSVXzwAfsk0bMX015epL
yg74HKzf/ZRqR1NVtl0QcP1qV4jPTeuAmudbrK97O6Kf81zDYa9DwBDhmtmKvAAJfqvjY81yg1/w
VoGvtyM362qxmZ1dHnjqiSRTs9ro27GpVPl0eC/73zC+FIcQttyqwZuZyw12xVqMTlw4E89/5Mv/
hxeIfcnjjZhI6Mvf2BEeiaRj414QYx6n1QjVNB1I2rmvaAreawVIKefklI+S218HJVPzW7YnJy1/
N1/AN/MPHmEhvRbEOz881VoZmHiPy97gj5oRQzf6jBzfzGTCb//JlS9x9qoiNPuVf0OC3kzB9PLU
aKr92oKy3VukNJ1VTzfJ5ajan7NLEg9LLsND4KDGTp3l+x5oer+xBRxPN/ioH8yCXd46QCoHBb5W
D7sX/DzV1KG/XonV6iPqNrMyQJ9WJinXKyeaPK5VlHL9UHHqjXHx42Nqb3QpDlnLR6/L4+EgYZ3v
sRtvymhOEtNUf/np1c+q//E5NOihS8pr3RiTxI6e+vs+9632/fB1Vjnit5qMj/096SUaWBOIq0sZ
UNsvClasbzYc8fZInOmQ9QLajx2oaLPGtslFBbUO2AMze0XYfnzcRsKv24jaercbif58Fe1NCFtV
PyUc2SRMdyUQ7w/VTY4dcTjTj6hDM09lzXEXyHJ2KsRVS1vVfb4f2Cn12uV5xaqBs0oL+52kGiRV
+0DZZxstUCOjRq/7gyrK9M5bsl+Nu559u/Si+ofiFDw9fDLo9FImSO3rhyQvIUG0OPtH9FgbHbHr
4lnQck5btKoqGzvgP40x6zwe8lNYE2s4e7149l85eGe0x87bK13aV/xLFdKqwJc60JkU2EMH6R5V
I2ztsZ/OhypTfSHXsU7Jq2eqpAZQpZcNtvXp6xLF2Obq997wRAtjxSDP+6zBwvewv5JrNm0kO4aO
BmXAxmeKhJNdpepVCyMSJzu9mNtDE0J54j3sGCw1GKfbFXrMz/04zfNg0Lm1MpimaBM0dzogGj2C
FrlefiCmRj5LPqQmtGodYeNZXfu+ofJLtenhgf1bWhdztkeAkucTEe2sC81QZjRQ4bgTgs1pc42m
+HBo1T/1odu4rui/NQu4Mrkt+XpCfSkfQtU03HlkkLls8i6Rrj6VIAqYvAmML47uo+quXuugzzpv
iZ+dB+trohLv4ZwZ1ZkVw+lY9SQ3ndidVVXnock+JvaR8y7oTq1itTn5Pt58ah/RIfjkAGqzIdYl
mxumYkkG+uiOxNsYlTF3WjOCJRhKIKz8sRmbwFBgt0MtNpqH1Qjc0/aQfDiqGJvOqhmWfIN6596J
Ufotm9y0f4Bm0GmEXWsgiStuFNm7Nif2tch76rKGR+R6egV0o1jNjAL9guRSWPB4e+sJj1AF9Oxv
8WEvCQ1DNohKernEJAxf+4LhwbJBUHgNx0jTGjEhzxo+1Qhjde7rXqoddlSPPaRYH7MWMR3FL7V7
zUds5fePOwTbhw6Hb3wn+cIn521v8dB/4YmNLli7805ba+C4uB2RlJz7Hx6rzrhNxxW/WjU/fFWU
d7bCVvCE5inN1wAN0agT7aZXxUTHdwvnujXG9b4u3c9FwYCyg13hWPnUjJzju64khuDgzfcNUaMY
fg42HNfYUps4orf+7anHb+Zjs8xTRLhSeSHirglOWLtCI061Wr1+rk9ysDW/GLeO6YCoH2viRjD1
TPT3Cmxke0PSvp8Qq06lBgt+j3yZi2w6ZD4HH0OQyd7ATsGW85afTnkn+1rR+0FYqRyyO0HHG/H9
dmknSwF8rHwgpqd/3MlK9h4yqdIE0oABPXWFUvAbcEfxHTNj2joqKOtTEhFj3noF/cYZ//s83lc2
59Jc6Af0vN087IeKW8wyqi6qJWwU4q/uW1c6GfkIVbT2sVkkdjR1VU6RxBfrgE92dSTJtyyAPOH7
5by1gg89Yq5Xk6QTL9nvmz98bSjsBv/w7bN9lhnErr8it3Xlu7xhKMoffXxiFmGsv60eSFpVLgnQ
SSj6MnUzZJeFMPILn6RzIDsQfcogGBhpI/a8XgO08GtibSht7k0ix2BDuMaxGrwQC8VDDm3XPQNe
PG5dCmk4woI/ZOHj7veM+xx98az/6psxxR1REPpeE5x+6nM0+49PCMt9k5NmZwUjV2WEpb4TfK0N
V7hSTVdXL2kgrj92zbzobbV/nndYi9SLMdehraCFDxMj+7LmU7duDcg8Gjg6zAc2G9Z5hPuXC8hm
s8+NaYvPFCWSQbGtrR+MorFIgStPNxycklUxtFF7/O0HB1nSRXM8d7WiXactudJLj2gixJwq2akc
0Kx69rR7ZhnkL/cZrF+r2fhm75eGGqGyifV+1ZHg7PEAKUl1bNE37VkioQkcUzaxdo4fjFWG7IHE
mTFO6l0eMf2ETPjpYf0ZkX4uWdHC4+XCuMQfY0w0TVXjzmvsIPFtTG1UHVHc7gxsx23YDLuqssCN
eIYLNEjRdP3Mk9pU21eAIpiaSbmKPJB7fCTn0dfdKXCLG4Quz2HHuMjFJKeIoqpIxkBJ1Jb9+DY8
iWIEa2W8IGYDxylO6UX4+jyaBo9HngMfd0/sXNZdQ3vDqaEGWQ2krW248/d0v6mLvhn75f6WfOGQ
4O6CgDbbT8GmnTugBR+Cx8Z6R9Q3FQ+W+kMMLRyiMVnLEyDp1mNrQ4/9kl8i7HeDhf3tu2ck8LWL
+tp0wsjze7+RHmnuoJ/eWfKp+PEv8J5pGnBbfo3mg3zjkWLscuIv99nrKzmDyP/uyK4ZN2zKs/4G
RqnauLyvKzS/6o5H/Ce+ksOgGxHRozKE26c5EM9N+Z424sZD3WUGshVnvRCP2tNBivRdY4yzKZqm
QcvQKq0oPgmqYQjWJIbAe+X5Fw/N3Pq7CyreabDEMxikMuQAvpqsBcSWkfu5rFY5VK7OY4df8S7b
6+MNRbxSkC1p5mhUnJlXl3wdqyUfaLKeKOzDV4nd9GIZglAFCoxn3sTZ49M3cyIdONSevZHciuFq
PE4Ne6ji8+qQAH0ezcQrQQUvKT8Qd0Nv7qANgoWM+1kjftJajC54rqqi7eFk9fAiAeYefvWcWN+1
ZEzGmjxQvjYiYjwrtZkPlOSQ2uVn5JWPzr4uCo9qq1YRcW7nxBC67JXCOruFo4wVHk25MsdAz3hL
jNfeaaaYGIPqyZ4Z3HLv2LMv/xlAG80Vxpwps4lctgPsNg+TFFiqXTYc7AAWPkH8934o6JkPLZU6
sY639U12F3+CgjWOCXbBEKJx4RPK/nOT8O7hBBHbjpOoRmc7xnHKOc2iF0ERIvUdgPulBam/G0fN
QHmNQuY2DblvDR4EOfKI++RjV6ykwIKqOI0Lnq6b1rsUOlx5heINSvR+qQcjWHFm4TzXpYL8/J8G
VXS5z0NEvXvYqrCZEL6qFlewRV+rK0U84fN636CpOK8sZdEv2HC9L5uOW4WCFecWdi9EQZPg7EOY
49cLe4y0xR/9/vMTsH9v3Vkts0l1j0Qke3oMm3kYswvKR2IQfH8fGpZQM1X6SYzxj3/O4bACyHau
g03tmkfTe5/ocM1fNTHDyexZtnccILdbE0xyOrlUcWZRVXyTjMitzIhRXr4oaZGciPPhGrbEQ4Z+
69VTSdw//obHeSPeHLZWLx5vpQdX6ylhZ8wnl9r3Bd8fbhpglluFlFAvBiuK9tgRDk30q4/K9upR
Yv/02I/fMLBLcrN736Wb702BZ6KMWHu8H9FcHnyKlvqN9cuTd2c4f1K4R7DG2s45usw5fhzkb8zr
SFfroJizu/iATwAO3hsv25iGft3Cgvd4x51JQYRPFavPAmUjNcqyF5+5mK3D+Hsi+L7WmPDT78PG
DX5+QCQQ8e0AGdmV2EXZ9A/HNUdYkcIhdiluIl5pHROtFP5E3L2GXakqqKjaPJ/9m7+kyVeBfuJj
7MluzHrn+LHRoif+6NWpklYyLHo+ENeC0dCu8O0/+thK2LcfwrUdoAsnFti8GA+DP16FHIjidfhg
PDQmLnoAalGJsD7FJRqficWB8DzfiNM3FzQC71D0YY8uGC+D7U6d3g5QnkSP6LzqMTH+iBbU2TsL
vqHSR3RMhssf/PPPqdTTZxIA7Lf7I8bEaJt5hzY1SMePjY+r9RhNB6Xgf35/MIWvTzEy9g3RpzyY
OIzVnUF95aUARpWJfTX79oP29jv49Re8cvSLQcOGroYJHxM3DCqD/vRZc8I+2RRdF3U/PaF3eCC+
sROj6Qn1DURjOJOdEleM2q85hofivMmep5ZB449oqgvfJtY0OZHkHO823Eq8+fnN7oC+6woWPzng
BwTNIB3MGJWvLybO5jm5TAtlHVpWc9iviwmx1d59waY4qiNq409P/KdrKuH1KGAnurKip7x8Q1pr
JmRbvTFil32oIGuyfRwq5bsfZ+cSo2IK3gTfplsxfOgX/uj3bZCNDfNzSQSnNQeys1ZuwZ+FvYLo
YDFsFsba/SrcboRP617JZvF72uku2NAbbYq3QRb0P/2BzgfPW/oFH2MqwOOUuLbOeOc/cDSYW6sG
3LYp2e3LirFFn6rpiz7++MXz8SHr4NdCgF0pOTfDmFMTyISTxW/QGmGtNw9IZIeMwrZjxhcZkgeS
ppwC4ZP0Eetv0gt9YaVh2/Me0eyiMPzDb9Os09B3nFYDjOgh4JOiz80Qd28FKb5FyM5NP8b4wGUN
OuobYi/9k7aSJPl3PjgKjLsx9+1H/6P3tUU/0Vf15eH1zRE29OneE9LUjnqIb3usqWbfz4/1gYdo
635wsPQTvtxT8wDl7zc2v76Lhmx3tSGPv+NPH0fvtLimyuJ3Evy+nRlTExIrh0LuRnJ1txE79aEG
rZamI1riZwZ8sxQGTjku/lnfZWPVqevrSR1Xb+HUz5ZwtFR+3q2X/tLMehmco7rgB3G1h45+eIKy
hx5gnzzlhd9xIjyd6504J352p6Pmporex5+Fj+oRswQkw2s6dqMar9ZoDA+PEQTPc8nuGngN88uo
/eNvlMt+pewFHuwe0zCSe8jQdNeNQI3SZ0Ws1awU3eXGj/A0Nhp2X5ZRDGkWj6gbMfudZzPdej9T
tIkbR7r43ZKwyy/o53d5Qr+KxiZiKZye2XkEd3Vv6F1/6qCfFUr09fn868cEsOaDEzH71CiEYLJt
uDY39Ef/fY96bYPd5PdxteDbuH5nRxgtSHHS32r0VcuQ/voDBJtsaDo48DIs/tCoFuKAmLK7e3/8
9E1FDDYv/B0WfCBWxats8UtysMOKkUjeBC59T20N7lW0MT7ipp87BTxkPb7aj582NDl1MmxlWAer
H38sD9sJ+E96Jdvp8DXmNfAWWvg5KcBICkq/Ko9ajDOyX+8NxK82bxv49Ebw1r6/CurQ0APWhLuR
2/JnxBw7kUE9iO9x1SVfYzpZ+xrCdtSJmSZqP2d7BioUU0hK834tmA0iB58yMrFdiveIt5JNoG5l
bj32541jzIl0BoXu5iAgGf9u2P0aXEBI64IEFO0N0nrXFr3h1BHr1CVIoEIXgrSfyNL/a/oXTrVK
XfhBgBRvYMt+A/Trn0RRm7uMK+lDvTzBGF8L/vQ//clZVwtvVVNyqV8/QnCoqZPjWkfF5Ia8A+db
fxq5fvWOhtpIeTDKlR2sF//u55+hBY8wfux2rvRcNZY6cIlL9J14Lfj3/qqD2oQ3bLz2XTOI7kVG
NAoKbIqagGZLyM0/fjX9+SU/f27hR3jvnenPz+gAwg9HNPy6FfNHMCmMpThi4zDPjH4YnoDf6nLA
L/g5k8aOf3yUWEdQosk3s/zXfw0YZD0i5eIdLf1AnLnCq1j06/DD44WP2S5/9s0H5DEZ8a/e0sHZ
PpTjptthN+uGgn6po8BPb3nHY1qIx63GrV3ZyZZ+xIv1F+N+g+GhAbnMrxBNi58B3NbAAZclTjQ/
le8NFvwgGzJFSDpIXw1kGPakmM81++P/bd93nfifz4bR9TsL4e/fVMB//euvv/7Xb8Lg1V5vz2Uw
4Hubv//x36MC/yH9x/DKn88/YwjjkFe3v//59wTC35++fX2+//vbPm7v4e9//hL/PWvw97f95s//
9/m/lp/6r3/9HwAAAP//AwDb9NaU4CAAAA==
headers:
CF-RAY:
- 974f1417bd93ed39-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 26 Aug 2025 00:05:36 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-allow-origin:
- '*'
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-model:
- text-embedding-3-small
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '67'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
via:
- envoy-router-6855f85975-l2j69
x-envoy-upstream-service-time:
- '85'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '10000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '9999974'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_415fc597e216418bba813b4bb2f0e130
status:
code: 200
message: OK
version: 1