andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-23 23:28:15 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity
Files
90ab4d25270969a2af32d40b6272cf4028bb4f3b
crewAI/lib/crewai/tests/cassettes/test_cache_hitting_between_agents.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

509 lines
22 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are CEO. You''re an long time
CEO of a content creation agency with a Senior Writer on the team. You''re now
working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content."},{"role":"user","content":"\nCurrent
Task: What is 2 tims 6? Return only the number.\n\nThis is the expected criteria
for your final answer: the result of multiplication\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nThis is VERY important
to you, your job depends on it!"}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"multiplier","description":"Useful
for when you need to multiply two numbers together.","parameters":{"properties":{"first_number":{"title":"First
Number","type":"integer"},"second_number":{"title":"Second Number","type":"integer"}},"required":["first_number","second_number"],"type":"object"}}},{"type":"function","function":{"name":"Delegate_work_to_coworker","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.","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: 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.","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:
- '2568'
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-D0uXGE7ziiDyterHaMd4uTV632jqj\",\n \"object\":
\"chat.completion\",\n \"created\": 1769109694,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_hBVgKS5hzSypSiDz9YNFa5cT\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"multiplier\",\n
\ \"arguments\": \"{\\\"first_number\\\":2,\\\"second_number\\\":6}\"\n
\ }\n }\n ],\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 433,\n \"completion_tokens\":
20,\n \"total_tokens\": 453,\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 19:21:35 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:
- '644'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '892'
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 CEO. You''re an long time
CEO of a content creation agency with a Senior Writer on the team. You''re now
working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content."},{"role":"user","content":"\nCurrent
Task: What is 2 tims 6? Return only the number.\n\nThis is the expected criteria
for your final answer: the result of multiplication\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nThis is VERY important
to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_hBVgKS5hzSypSiDz9YNFa5cT","type":"function","function":{"name":"multiplier","arguments":"{\"first_number\":2,\"second_number\":6}"}}]},{"role":"tool","tool_call_id":"call_hBVgKS5hzSypSiDz9YNFa5cT","content":"12"},{"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-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"multiplier","description":"Useful
for when you need to multiply two numbers together.","parameters":{"properties":{"first_number":{"title":"First
Number","type":"integer"},"second_number":{"title":"Second Number","type":"integer"}},"required":["first_number","second_number"],"type":"object"}}},{"type":"function","function":{"name":"Delegate_work_to_coworker","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.","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: 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.","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:
- '3026'
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-D0uXItTo7W2QeDcp2MqfCtsuQKWOJ\",\n \"object\":
\"chat.completion\",\n \"created\": 1769109696,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"12\",\n \"refusal\": null,\n
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 497,\n \"completion_tokens\":
2,\n \"total_tokens\": 499,\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 19:21:36 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:
- '296'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '919'
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 Researcher. You''re an
expert researcher, specialized in technology, software engineering, AI and startups.
You work as a freelancer and is now working on doing research and analysis for
a new customer.\nYour personal goal is: Make the best research and analysis
on content about AI and AI agents"},{"role":"user","content":"\nCurrent Task:
What is 2 times 6? Return only the number.\n\nThis is the expected criteria
for your final answer: the result of multiplication\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\n12\n\nThis is VERY important to you, your job depends
on it!"}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"multiplier","description":"Useful
for when you need to multiply two numbers together.","parameters":{"properties":{"first_number":{"title":"First
Number","type":"integer"},"second_number":{"title":"Second Number","type":"integer"}},"required":["first_number","second_number"],"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:
- '1095'
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-D0uXIwVfFzuDJbIGQDnqYeAuGwdJA\",\n \"object\":
\"chat.completion\",\n \"created\": 1769109696,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_50ioxO3eZjl4xCaZBJAhKaxP\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"multiplier\",\n
\ \"arguments\": \"{\\\"first_number\\\":2,\\\"second_number\\\":6}\"\n
\ }\n }\n ],\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 190,\n \"completion_tokens\":
20,\n \"total_tokens\": 210,\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 19:21:36 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:
- '510'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '532'
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 Researcher. You''re an
expert researcher, specialized in technology, software engineering, AI and startups.
You work as a freelancer and is now working on doing research and analysis for
a new customer.\nYour personal goal is: Make the best research and analysis
on content about AI and AI agents"},{"role":"user","content":"\nCurrent Task:
What is 2 times 6? Return only the number.\n\nThis is the expected criteria
for your final answer: the result of multiplication\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\n12\n\nThis is VERY important to you, your job depends
on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_50ioxO3eZjl4xCaZBJAhKaxP","type":"function","function":{"name":"multiplier","arguments":"{\"first_number\":2,\"second_number\":6}"}}]},{"role":"tool","tool_call_id":"call_50ioxO3eZjl4xCaZBJAhKaxP","content":"12"},{"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-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"multiplier","description":"Useful
for when you need to multiply two numbers together.","parameters":{"properties":{"first_number":{"title":"First
Number","type":"integer"},"second_number":{"title":"Second Number","type":"integer"}},"required":["first_number","second_number"],"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:
- '1553'
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-D0uXKU2XWaNtJOKC5UEhlkPlr1Th3\",\n \"object\":
\"chat.completion\",\n \"created\": 1769109698,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"12\",\n \"refusal\": null,\n
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 254,\n \"completion_tokens\":
2,\n \"total_tokens\": 256,\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 19:21:38 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:
- '315'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1703'
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
Reference in New Issue View Git Blame Copy Permalink