Files
crewAI/tests/cassettes/test_cache_hitting_between_agents.yaml
2024-09-13 04:38:19 -05:00

576 lines
26 KiB
YAML

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.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) ->
Any\nTool Description: multiplier(first_number: ''integer'', second_number:
''integer'') - Useful for when you need to multiply two numbers together. \nTool
Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''},
''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\nTool
Name: Delegate work to coworker(task: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Delegate a specific task to one of the
following coworkers: 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 absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''task'': {''title'':
''Task'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool Name: Ask question
to coworker(question: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool
Description: Ask a specific question to one of the following coworkers: 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 absolute everything you know, don''t reference things
but instead explain them.\nTool Arguments: {''question'': {''title'': ''Question'',
''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''},
''coworker'': {''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'':
''Kwargs'', ''type'': ''object''}}\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [multiplier, Delegate work to coworker, Ask question to coworker], just
the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: What is 2 tims 6? Return only the number.\n\nThis is the expect
criteria for your final answer: the result of multiplication\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3109'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A6viypFjQCjtHUGu9CO7RqmElXDhG\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215224,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to find the result of
multiplying 2 by 6. To do this, I should use the multiplier tool.\\n\\nAction:
multiplier\\nAction Input: {\\\"first_number\\\": 2, \\\"second_number\\\":
6}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 691,\n \"completion_tokens\":
48,\n \"total_tokens\": 739,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26ae029ae52ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:13:45 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '596'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999244'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_33bb245000aa6a93e237ca7cf7310efe
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '2104'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Fri, 13 Sep 2024 08:13:46 GMT
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.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) ->
Any\nTool Description: multiplier(first_number: ''integer'', second_number:
''integer'') - Useful for when you need to multiply two numbers together. \nTool
Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''},
''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\nTool
Name: Delegate work to coworker(task: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Delegate a specific task to one of the
following coworkers: 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 absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''task'': {''title'':
''Task'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool Name: Ask question
to coworker(question: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool
Description: Ask a specific question to one of the following coworkers: 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 absolute everything you know, don''t reference things
but instead explain them.\nTool Arguments: {''question'': {''title'': ''Question'',
''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''},
''coworker'': {''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'':
''Kwargs'', ''type'': ''object''}}\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [multiplier, Delegate work to coworker, Ask question to coworker], just
the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: What is 2 tims 6? Return only the number.\n\nThis is the expect
criteria for your final answer: the result of multiplication\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 find the result of multiplying 2 by 6. To do this, I should use the
multiplier tool.\n\nAction: multiplier\nAction Input: {\"first_number\": 2,
\"second_number\": 6}\nObservation: 12"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3348'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A6vj0QcWiNAzGUI97VTWr1OvRXlbA\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215226,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\n\\nFinal
Answer: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
747,\n \"completion_tokens\": 14,\n \"total_tokens\": 761,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26ae0c7c3f2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:13:47 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '406'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999196'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_5cd7e9e14806611d0dc5cd89a03caa79
http_version: HTTP/1.1
status_code: 200
- 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\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number:
''integer'', second_number: ''integer'') - Useful for when you need to multiply
two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First
Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'',
''type'': ''integer''}}\n\nUse the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, only one name of
[multiplier], just the name, exactly as it''s written.\nAction Input: the input
to the action, just a simple python dictionary, enclosed in curly braces, using
\" to wrap keys and values.\nObservation: the result of the action\n\nOnce all
necessary information is gathered:\n\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n"}, {"role": "user",
"content": "\nCurrent Task: What is 2 times 6? Return only the number.\n\nThis
is the expect 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\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
connection:
- keep-alive
content-length:
- '1790'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A6vj2lQ3xsFO1qzEGNum8gXgHBqQT\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215228,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to calculate 2 times
6 using the given tool.\\n\\nAction: multiplier\\nAction Input: {\\\"first_number\\\":
2, \\\"second_number\\\": 6}\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
365,\n \"completion_tokens\": 37,\n \"total_tokens\": 402,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26ae15fcfd2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:13:48 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '528'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999573'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_539db84e703f219f66d30a92be2b2d02
http_version: HTTP/1.1
status_code: 200
- 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\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number:
''integer'', second_number: ''integer'') - Useful for when you need to multiply
two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First
Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'',
''type'': ''integer''}}\n\nUse the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, only one name of
[multiplier], just the name, exactly as it''s written.\nAction Input: the input
to the action, just a simple python dictionary, enclosed in curly braces, using
\" to wrap keys and values.\nObservation: the result of the action\n\nOnce all
necessary information is gathered:\n\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n"}, {"role": "user",
"content": "\nCurrent Task: What is 2 times 6? Return only the number.\n\nThis
is the expect 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\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 calculate
2 times 6 using the given tool.\n\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 6}\nObservation: 12"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1986'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A6vj3U5lV1MhN5XB2nsqVeKuQpmIT\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215229,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
410,\n \"completion_tokens\": 14,\n \"total_tokens\": 424,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26ae1f5e662ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:13:49 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '255'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999535'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_3254099a8e08fe25c521a6c7c3619957
http_version: HTTP/1.1
status_code: 200
version: 1