Files
crewAI/lib/crewai/tests/cassettes/test_output_json_hierarchical.yaml
lorenzejay 458f6867f0 Enhance tool handling and delegation tracking in agent executors
- Implemented immediate return for tools with result_as_answer=True in crew_agent_executor.py.
- Added delegation tracking functionality in agent_utils.py to increment delegations when specific tools are used.
- Updated tool usage logic to handle caching more effectively in tool_usage.py.
- Enhanced test cases to validate new delegation features and tool caching behavior.

This update improves the efficiency of tool execution and enhances the delegation capabilities of agents.
2026-01-22 11:35:27 -08:00

437 lines
20 KiB
YAML

interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Crew Manager. You are
a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible."},{"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:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '2959'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D0u2J708JSX4aBYHEikqtv7XEjBos\",\n \"object\":
\"chat.completion\",\n \"created\": 1769107775,\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_dUarFmWyTQ5irZgEICBGmkij\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"Ask_question_to_coworker\",\n
\ \"arguments\": \"{\\\"question\\\":\\\"Given your expertise,
what score would you give the title 'The impact of AI in the future of work'
on a scale of 1-5, and why?\\\",\\\"context\\\":\\\"We need a score for the
title 'The impact of AI in the future of work'. The score must be a single
integer between 1-5. Your expertise is required to ensure the score reflects
an accurate assessment of how impactful, relevant or engaging this title is
considered to be.\\\",\\\"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\":
119,\n \"total_tokens\": 681,\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:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 22 Jan 2026 18:49:37 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '2109'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '2364'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- 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: Given your expertise, what score would you give the title ''The impact
of AI in the future of work'' on a scale of 1-5, and why?\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 a score for the title ''The impact of AI in the future of work''.
The score must be a single integer between 1-5. Your expertise is required to
ensure the score reflects an accurate assessment of how impactful, relevant
or engaging this title is considered to be.\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:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1324'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D0u2LWZsnQRm51AYt5tlQhA0d3Qap\",\n \"object\":
\"chat.completion\",\n \"created\": 1769107777,\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 give the title 'The impact of AI in the future
of work' a score of 4. This title is highly relevant and timely given the
ongoing advancements in artificial intelligence and its widespread implications
for jobs and employment across many sectors. It effectively captures a significant,
forward-looking topic that is likely to engage a broad audience interested
in technology, business, and societal changes. The wording is clear and straightforward,
which helps in accessibility, though it could be made slightly more specific
or dynamic to reach a perfect score, for instance by highlighting a particular
aspect of AI or the workforce. Overall, it is impactful and relevant, meriting
a strong score of 4 on the 1-5 scale.\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 271,\n \"completion_tokens\":
153,\n \"total_tokens\": 424,\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:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 22 Jan 2026 18:49:40 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '2658'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '2696'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- 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."},{"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_dUarFmWyTQ5irZgEICBGmkij","type":"function","function":{"name":"Ask_question_to_coworker","arguments":"{\"question\":\"Given
your expertise, what score would you give the title ''The impact of AI in the
future of work'' on a scale of 1-5, and why?\",\"context\":\"We need a score
for the title ''The impact of AI in the future of work''. The score must be
a single integer between 1-5. Your expertise is required to ensure the score
reflects an accurate assessment of how impactful, relevant or engaging this
title is considered to be.\",\"coworker\":\"Scorer\"}"}}]},{"role":"tool","tool_call_id":"call_dUarFmWyTQ5irZgEICBGmkij","content":"I
would give the title ''The impact of AI in the future of work'' a score of 4.
This title is highly relevant and timely given the ongoing advancements in artificial
intelligence and its widespread implications for jobs and employment across
many sectors. It effectively captures a significant, forward-looking topic that
is likely to engage a broad audience interested in technology, business, and
societal changes. The wording is clear and straightforward, which helps in accessibility,
though it could be made slightly more specific or dynamic to reach a perfect
score, for instance by highlighting a particular aspect of AI or the workforce.
Overall, it is impactful and relevant, meriting a strong score of 4 on the 1-5
scale."},{"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:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '4573'
content-type:
- application/json
cookie:
- COOKIE-XXX
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D0u2ObPvCTvReLhW6Fizg8haajVst\",\n \"object\":
\"chat.completion\",\n \"created\": 1769107780,\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\":
869,\n \"completion_tokens\": 6,\n \"total_tokens\": 875,\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:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 22 Jan 2026 18:49:40 GMT
Server:
- cloudflare
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '288'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '527'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
version: 1