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
Files
0ab072a95ed08404260c841f97b706189ae161a7
crewAI/tests/cassettes/test_agent_moved_on_after_max_iterations.yaml
João Moura 5a3b888f43 Updating all cassetes
2024-09-18 04:17:41 -03:00

483 lines
20 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
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: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool over and over until you''re told you can give
your final answer.\n\nThis is the expect criteria for your final answer: The
final answer\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:
- '1480'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isBAhrMVV8F12lCkP28PFEThmte\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642479,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I should use the `get_final_answer` tool
repeatedly as instructed until told to give the final answer.\\n\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
303,\n \"completion_tokens\": 31,\n \"total_tokens\": 334,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6d046cbea67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:54:39 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:
- '631'
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:
- '29999651'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_74382ce706ce58ac88ce879b6d458023
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
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: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool over and over until you''re told you can give
your final answer.\n\nThis is the expect criteria for your final answer: The
final answer\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":
"user", "content": "I should use the `get_final_answer` tool repeatedly as instructed
until told to give the final answer.\n\nAction: get_final_answer\nAction Input:
{}\nObservation: 42"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1678'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isBfCGN11dTnwC1tWtsQY0K1cC8\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642479,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to continue using the
`get_final_answer` tool as instructed.\\n\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
342,\n \"completion_tokens\": 27,\n \"total_tokens\": 369,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6d0a3f37a67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:54:40 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:
- '419'
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:
- '29999609'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_00ae8f7f0df7ad9ec8135f229521ecdd
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
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: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool over and over until you''re told you can give
your final answer.\n\nThis is the expect criteria for your final answer: The
final answer\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":
"user", "content": "I should use the `get_final_answer` tool repeatedly as instructed
until told to give the final answer.\n\nAction: get_final_answer\nAction Input:
{}\nObservation: 42"}, {"role": "user", "content": "Thought: I need to continue
using the `get_final_answer` tool as instructed.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n"}], "model": "gpt-4o", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1953'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isCc67QkMOf4ybMWQZqRy24kVO4\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642480,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I should try using the `get_final_answer`
tool again as instructed.\\n\\nAction: get_final_answer\\nAction Input: {}\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 397,\n \"completion_tokens\":
27,\n \"total_tokens\": 424,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6d0eb9a8a67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:54:41 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:
- '520'
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:
- '29999550'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a6c7ca4262c6fcae0832c71c6401e334
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
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: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool over and over until you''re told you can give
your final answer.\n\nThis is the expect criteria for your final answer: The
final answer\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":
"user", "content": "I should use the `get_final_answer` tool repeatedly as instructed
until told to give the final answer.\n\nAction: get_final_answer\nAction Input:
{}\nObservation: 42"}, {"role": "user", "content": "Thought: I need to continue
using the `get_final_answer` tool as instructed.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n"}, {"role": "user", "content":
"Thought: I should try using the `get_final_answer` tool again as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: I tried reusing the same input,
I must stop using this action input. I''ll try something else instead.\n\n\n\n\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: get_final_answer(*args: Any, **kwargs: Any)
-> Any\nTool Description: get_final_answer() - Get the final answer but don''t
give it yet, just re-use this tool non-stop. \nTool Arguments: {}\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], 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\nNow it''s time you MUST give your absolute best final answer.
You''ll ignore all previous instructions, stop using any tools, and just return
your absolute BEST Final answer."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3231'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isDUt7sjbLN7oAssqM0SIvqBZLI\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642481,\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: The final answer is 42.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
661,\n \"completion_tokens\": 19,\n \"total_tokens\": 680,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6d143cb5a67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:54:41 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:
- '375'
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_8295fdf315dd20e243cadd737640169b
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink