andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 16:18:30 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
91ddab207f5c3348333102f034856cca6f4bbbd4
crewAI/tests/cassettes/test_agent_moved_on_after_max_iterations.yaml
João Moura 91ddab207f Making all tests good
2024-09-13 04:38:19 -05:00

535 lines
25 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:
- '1479'
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-A6vcMZivRLpfY9AJCvwMBTsUTSeWe\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214814,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Action: 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\":
10,\n \"total_tokens\": 313,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a3fb98f72ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:06:54 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:
- '237'
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_e2de7a8ec034d2524f17a4ef74c5c326
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":
"assistant", "content": "Action: get_final_answer\nAction Input: {}\nObservation:
\nI encountered an error while trying to use the tool. This was the error: test_agent_moved_on_after_max_iterations.<locals>.get_final_answer()
missing 1 required positional argument: ''numbers''.\n Tool get_final_answer
accepts these inputs: get_final_answer() - Get the final answer but don''t give
it yet, just re-use this tool non-stop. .\nMoving on then. I MUST either
use a tool (use one at time) OR give my best final answer. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [get_final_answer]\nAction Input: the input to the
action, dictionary enclosed in curly braces\nObservation: the result of the
action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\n "}], "model":
"gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2504'
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-A6vcNVpvHDezSnSN9D9k0Ajk60i3j\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214815,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: For every course of action,
I must keep using the `get_final_answer` tool repeatedly. \\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\":
523,\n \"completion_tokens\": 32,\n \"total_tokens\": 555,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a4035fd12ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:06:55 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:
- '447'
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:
- '29999406'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_ec48d336189661edc0c5c0b6b8c6238a
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":
"assistant", "content": "Action: get_final_answer\nAction Input: {}\nObservation:
\nI encountered an error while trying to use the tool. This was the error: test_agent_moved_on_after_max_iterations.<locals>.get_final_answer()
missing 1 required positional argument: ''numbers''.\n Tool get_final_answer
accepts these inputs: get_final_answer() - Get the final answer but don''t give
it yet, just re-use this tool non-stop. .\nMoving on then. I MUST either
use a tool (use one at time) OR give my best final answer. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [get_final_answer]\nAction Input: the input to the
action, dictionary enclosed in curly braces\nObservation: the result of the
action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\n "}, {"role":
"assistant", "content": "Thought: For every course of action, I must keep using
the `get_final_answer` tool repeatedly. \n\nAction: get_final_answer\nAction
Input: {}\nObservation: \nI encountered an error while trying to use the tool.
This was the error: test_agent_moved_on_after_max_iterations.<locals>.get_final_answer()
missing 1 required positional argument: ''numbers''.\n Tool get_final_answer
accepts these inputs: get_final_answer() - Get the final answer but don''t give
it yet, just re-use this tool non-stop. .\nMoving on then. I MUST either
use a tool (use one at time) OR give my best final answer. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [get_final_answer]\nAction Input: the input to the
action, dictionary enclosed in curly braces\nObservation: the result of the
action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\n "}], "model":
"gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3628'
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-A6vcPxEXTkyvRGgBH4tquNFgI1Mpo\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214817,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I should continue following
the instructions and use the `get_final_answer` tool repeatedly.\\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\": 765,\n \"completion_tokens\": 29,\n
\ \"total_tokens\": 794,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a40c3f372ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:06:57 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:
- '460'
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:
- '29999139'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_2ff80ac8a67459757d78605731dbef57
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":
"assistant", "content": "Action: get_final_answer\nAction Input: {}\nObservation:
\nI encountered an error while trying to use the tool. This was the error: test_agent_moved_on_after_max_iterations.<locals>.get_final_answer()
missing 1 required positional argument: ''numbers''.\n Tool get_final_answer
accepts these inputs: get_final_answer() - Get the final answer but don''t give
it yet, just re-use this tool non-stop. .\nMoving on then. I MUST either
use a tool (use one at time) OR give my best final answer. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [get_final_answer]\nAction Input: the input to the
action, dictionary enclosed in curly braces\nObservation: the result of the
action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\n "}, {"role":
"assistant", "content": "Thought: For every course of action, I must keep using
the `get_final_answer` tool repeatedly. \n\nAction: get_final_answer\nAction
Input: {}\nObservation: \nI encountered an error while trying to use the tool.
This was the error: test_agent_moved_on_after_max_iterations.<locals>.get_final_answer()
missing 1 required positional argument: ''numbers''.\n Tool get_final_answer
accepts these inputs: get_final_answer() - Get the final answer but don''t give
it yet, just re-use this tool non-stop. .\nMoving on then. I MUST either
use a tool (use one at time) OR give my best final answer. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [get_final_answer]\nAction Input: the input to the
action, dictionary enclosed in curly braces\nObservation: the result of the
action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\n "}, {"role":
"assistant", "content": "Thought: I should continue following the instructions
and use the `get_final_answer` tool repeatedly.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: \nI encountered an error while trying to use the tool.
This was the error: test_agent_moved_on_after_max_iterations.<locals>.get_final_answer()
missing 1 required positional argument: ''numbers''.\n Tool get_final_answer
accepts these inputs: get_final_answer() - Get the final answer but don''t give
it yet, just re-use this tool non-stop. .\nMoving on then. I MUST either
use a tool (use one at time) OR give my best final answer. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [get_final_answer]\nAction Input: the input to the
action, dictionary enclosed in curly braces\nObservation: the result of the
action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\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:
- '4932'
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-A6vcQ4LL5ICPF0TJlalJMw4MJmYUw\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214818,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I have followed the instruction
to repeatedly use the `get_final_answer` tool. 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\":
1035,\n \"completion_tokens\": 35,\n \"total_tokens\": 1070,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a415b8222ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:06:59 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:
- '686'
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:
- '29998826'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_d423b3877f1735f7f88e197a4e8b74c8
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink