andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-22 22:58:13 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

regen cassette

Browse Source
This commit is contained in:
lorenzejay
2026-01-22 09:17:21 -08:00
parent 0d62d8dc0c
commit 85096ca086
1 changed files with 229 additions and 96 deletions
Download Patch File Download Diff File Expand all files Collapse all files

325
lib/crewai/tests/cassettes/test_output_json_dict_hierarchical.yaml
View File

@@ -1,295 +1,428 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Crew Manager. You are a seasoned manager with a knack for getting the best out of your team.\nYou are also known for your ability to delegate work to the right people, and to ask the right questions to get the best out of your team.\nEven though you don''t perform tasks by yourself, you have a lot of experience in the field, which allows you to properly evaluate the work of your team members.\nYour personal goal is: Manage the team to complete the task in the best way possible.\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: Delegate work to coworker\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 strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\":
\"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure 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"}'
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."},{"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 strictly adheres
to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\":
\"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\":
\"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo
not include the OpenAPI schema in the final output. Ensure the final output
does not include any code block markers like ```json or ```python.\n\nThis is
VERY important to you, your job depends on it!"}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"Delegate_work_to_coworker","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.","parameters":{"properties":{"task":{"description":"The
task to delegate","title":"Task","type":"string"},"context":{"description":"The
context for the task","title":"Context","type":"string"},"coworker":{"description":"The
role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object"}}},{"type":"function","function":{"name":"Ask_question_to_coworker","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.","parameters":{"properties":{"question":{"description":"The question
to ask","title":"Question","type":"string"},"context":{"description":"The context
for the question","title":"Context","type":"string"},"coworker":{"description":"The
role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object"}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '3433'
- '2959'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.109.1
- 1.83.0
x-stainless-read-timeout:
- '600'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CYg0U9ZI1XDhqLHsWjVD8eW4wZKuX\",\n \"object\": \"chat.completion\",\n \"created\": 1762380662,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: To provide an integer score between 1-5 for the given title \\\"The impact of AI in the future of work\\\", I need to delegate this evaluation task to the Scorer, as they are equipped to handle scoring tasks based on specific criteria.\\n\\nAction: Delegate work to coworker\\nAction Input: {\\\"task\\\": \\\"Provide an integer score between 1-5 for the title 'The impact of AI in the future of work'.\\\", \\\"context\\\": \\\"Please evaluate the title based on clarity, relevance, and potential impact. The score should reflect how well the title conveys these elements.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\"\
: null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 744,\n \"completion_tokens\": 130,\n \"total_tokens\": 874,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_a788c5aef0\"\n}\n"
string: "{\n \"id\": \"chatcmpl-D0saVsERZNPf8ik1d3QKTrjSEJ6K0\",\n \"object\":
\"chat.completion\",\n \"created\": 1769102207,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_rxammSe41zSSAz3qdOTsSj7c\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"Ask_question_to_coworker\",\n
\ \"arguments\": \"{\\\"question\\\":\\\"Given the title 'The
impact of AI in the future of work', what integer score between 1-5 would
you assign to it?\\\",\\\"context\\\":\\\"We need to evaluate the title based
on its potential impact, engagement, relevance, and clarity. The scoring criteria
are as follows: 1 for poor, 2 for fair, 3 for good, 4 for very good, and 5
for excellent.\\\",\\\"coworker\\\":\\\"Scorer\\\"}\"\n }\n }\n
\ ],\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 562,\n \"completion_tokens\":
109,\n \"total_tokens\": 671,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n"
headers:
CF-RAY:
- REDACTED-RAY
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Wed, 05 Nov 2025 22:11:06 GMT
- Thu, 22 Jan 2026 17:16:49 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:41:06 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- SET-COOKIE-XXX
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- user-hortuttj2f3qtmxyik2zxf4q
- OPENAI-ORG-XXX
openai-processing-ms:
- '3867'
- '1943'
openai-project:
- proj_fL4UBWR1CMpAAdgzaSKqsVvA
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '3883'
- '1966'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '500'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '30000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '499'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '29181'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 120ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 1.638s
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_REDACTED
- X-REQUEST-ID-XXX
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: Provide an integer score between 1-5 for the title ''The impact of AI in the future of work''.\n\nThis is the expected criteria for your final answer: Your best answer to your coworker asking you this, accounting for the context shared.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nThis is the context you''re working with:\nPlease evaluate the title based on clarity, relevance, and potential impact. The score should reflect how well the title conveys
these elements.\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-4.1-mini"}'
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: Given the title ''The impact of AI in the future of work'', what integer
score between 1-5 would you assign to it?\n\nThis is the expected criteria for
your final answer: Your best answer to your coworker asking you this, accounting
for the context shared.\nyou MUST return the actual complete content as the
final answer, not a summary.\n\nThis is the context you''re working with:\nWe
need to evaluate the title based on its potential impact, engagement, relevance,
and clarity. The scoring criteria are as follows: 1 for poor, 2 for fair, 3
for good, 4 for very good, and 5 for 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:"}],"model":"gpt-4.1-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1165'
- '1248'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.109.1
- 1.83.0
x-stainless-read-timeout:
- '600'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CYg0Yw2AWueMcb9jag3LZhkgEmKJt\",\n \"object\": \"chat.completion\",\n \"created\": 1762380666,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: The title \\\"The impact of AI in the future of work\\\" is clear and directly addresses the topic. It is highly relevant given the current and ongoing discussions about AI transforming job markets and workplace dynamics. The phrase conveys potential impact effectively by highlighting \\\"impact\\\" and \\\"future of work,\\\" which are compelling and important themes. However, the title could be slightly more specific or engaging to enhance its impact, but overall it is strong and relevant.\\n\\nFinal Answer: 4\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\"\
: 229,\n \"completion_tokens\": 95,\n \"total_tokens\": 324,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n"
string: "{\n \"id\": \"chatcmpl-D0saXzeVQyzw1c18FM0Y8HkUYV6lF\",\n \"object\":
\"chat.completion\",\n \"created\": 1769102209,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: I would assign a score of 4 to the title \\\"The impact of AI in the
future of work.\\\" The title is very relevant and timely, as artificial intelligence
is a major transformative force affecting the labor market and employment
trends. It is clear and concise, effectively highlighting the focus on AI's
influence on the future of work. However, while it is engaging and implies
substantial potential impact, it could be slightly more specific or dynamic
to reach an excellent level. Overall, it meets very good standards for potential
impact, engagement, relevance, and clarity.\",\n \"refusal\": null,\n
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 261,\n \"completion_tokens\":
123,\n \"total_tokens\": 384,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
headers:
CF-RAY:
- REDACTED-RAY
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Wed, 05 Nov 2025 22:11:08 GMT
- Thu, 22 Jan 2026 17:16:52 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:41:08 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- SET-COOKIE-XXX
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- user-hortuttj2f3qtmxyik2zxf4q
- OPENAI-ORG-XXX
openai-processing-ms:
- '1531'
- '2175'
openai-project:
- proj_fL4UBWR1CMpAAdgzaSKqsVvA
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1543'
- '2193'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '500'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '200000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '499'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '199734'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 120ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 79ms
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_REDACTED
- X-REQUEST-ID-XXX
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 strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\":
\"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure 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: To provide an integer score between 1-5 for the given title \"The impact of AI in the future of work\", I need to delegate this evaluation task to the Scorer, as they are equipped to handle scoring tasks based on specific criteria.\n\nAction: Delegate work to coworker\nAction Input: {\"task\": \"Provide an integer score between 1-5 for the title ''The impact of AI in the future of work''.\", \"context\": \"Please evaluate the title based on clarity, relevance, and potential impact.
The score should reflect how well the title conveys these elements.\", \"coworker\": \"Scorer\"}\nObservation: 4"}],"model":"gpt-4o"}'
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."},{"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 strictly adheres
to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\":
\"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\":
\"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo
not include the OpenAPI schema in the final output. Ensure the final output
does not include any code block markers like ```json or ```python.\n\nThis is
VERY important to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_rxammSe41zSSAz3qdOTsSj7c","type":"function","function":{"name":"Ask_question_to_coworker","arguments":"{\"question\":\"Given
the title ''The impact of AI in the future of work'', what integer score between
1-5 would you assign to it?\",\"context\":\"We need to evaluate the title based
on its potential impact, engagement, relevance, and clarity. The scoring criteria
are as follows: 1 for poor, 2 for fair, 3 for good, 4 for very good, and 5 for
excellent.\",\"coworker\":\"Scorer\"}"}}]},{"role":"tool","tool_call_id":"call_rxammSe41zSSAz3qdOTsSj7c","content":"I
would assign a score of 4 to the title \"The impact of AI in the future of work.\"
The title is very relevant and timely, as artificial intelligence is a major
transformative force affecting the labor market and employment trends. It is
clear and concise, effectively highlighting the focus on AI''s influence on
the future of work. However, while it is engaging and implies substantial potential
impact, it could be slightly more specific or dynamic to reach an excellent
level. Overall, it meets very good standards for potential impact, engagement,
relevance, and clarity."},{"role":"user","content":"Analyze the tool result.
If requirements are met, provide the Final Answer. Otherwise, call the next
tool. Deliver only the answer without meta-commentary."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"Delegate_work_to_coworker","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.","parameters":{"properties":{"task":{"description":"The
task to delegate","title":"Task","type":"string"},"context":{"description":"The
context for the task","title":"Context","type":"string"},"coworker":{"description":"The
role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object"}}},{"type":"function","function":{"name":"Ask_question_to_coworker","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.","parameters":{"properties":{"question":{"description":"The question
to ask","title":"Question","type":"string"},"context":{"description":"The context
for the question","title":"Context","type":"string"},"coworker":{"description":"The
role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object"}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '4073'
- '4344'
content-type:
- application/json
cookie:
- __cf_bm=REDACTED; _cfuvid=REDACTED
- COOKIE-XXX
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.109.1
- 1.83.0
x-stainless-read-timeout:
- '600'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CYg0aZYVeemJxWLiwY2ctjMeSmzWs\",\n \"object\": \"chat.completion\",\n \"created\": 1762380668,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal Answer: {\\\"score\\\": 4}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 882,\n \"completion_tokens\": 18,\n \"total_tokens\": 900,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_a788c5aef0\"\n}\n"
string: "{\n \"id\": \"chatcmpl-D0saaXZpXh24rhAcDui3Tm13VCj4L\",\n \"object\":
\"chat.completion\",\n \"created\": 1769102212,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
829,\n \"completion_tokens\": 6,\n \"total_tokens\": 835,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n"
headers:
CF-RAY:
- REDACTED-RAY
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Wed, 05 Nov 2025 22:11:09 GMT
- Thu, 22 Jan 2026 17:16:52 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- user-hortuttj2f3qtmxyik2zxf4q
- OPENAI-ORG-XXX
openai-processing-ms:
- '503'
- '397'
openai-project:
- proj_fL4UBWR1CMpAAdgzaSKqsVvA
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '521'
- '674'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '500'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '30000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '499'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '29033'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 120ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 1.934s
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_REDACTED
- X-REQUEST-ID-XXX
status:
code: 200
message: OK