andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 08:38:30 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
91ddab207f5c3348333102f034856cca6f4bbbd4
crewAI/tests/cassettes/test_agent_error_on_parsing_tool.yaml
João Moura 91ddab207f Making all tests good
2024-09-13 04:38:19 -05:00

928 lines
44 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: Use the get_final_answer tool.\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:
- '1352'
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-A6vcovkSD8jMIsWHYyXYFgj1plLQi\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214842,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to use the get_final_answer
tool to obtain 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\": 274,\n \"completion_tokens\":
27,\n \"total_tokens\": 301,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a4ae3fba2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:07:23 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:
- '410'
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:
- '29999682'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_26973f1ba0bdd1839bc98b90f3538459
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: Use the get_final_answer tool.\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": "Thought: I need to use
the get_final_answer tool to obtain the final answer.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\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:
- '2156'
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-A6vcqTuKLG365JTeJXy9SQ64D8F7v\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214844,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I will use the get_final_answer
tool again to achieve the final outcome.\\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\":
446,\n \"completion_tokens\": 27,\n \"total_tokens\": 473,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a4b6ff6c2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:07:24 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:
- '628'
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:
- '29999494'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_813045a0ae8b24c3917a177698f27b6b
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CqMOCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS+g0KEgoQY3Jld2FpLnRl
bGVtZXRyeRKTAQoQrJU32al7o+QA9LQ5q+I6pRIIzb+NPrtaVkcqClRvb2wgVXNhZ2UwATnguVUT
QL/0F0H49l8TQL/0F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjU2LjBKHwoJdG9vbF9uYW1lEhIK
EGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABKQAgoQoQnVnsAPqBVj
YUqZAlO8rRIIPUsbbzDTvnoqDlRhc2sgRXhlY3V0aW9uMAE58L9usj+/9BdBYG6vcEC/9BdKLgoI
Y3Jld19rZXkSIgogOTgzYzJhMDcyNmI1NmQwZDkyN2M5ZGYxMGJmZTI1YzhKMQoHY3Jld19pZBIm
CiQyYzAwNTk4Ny01MjQ2LTQyMTItYTYzOC0zMzk2OTcwYmJlNDNKLgoIdGFza19rZXkSIgogZmI0
YzI2MDg3YmI4NzNmNjRmNGRmNTU4MDJjNmVkMDlKMQoHdGFza19pZBImCiQyZTI4YzU2Ny0yOTli
LTQzMjItYjg0Yi01NTU1NTJkNTdmZGR6AhgBhQEAAQAAEq8HChDK4V1/VVQb4CwYKBCbsSpQEgjd
YiCdn+ERlioMQ3JldyBDcmVhdGVkMAE5oC02ckC/9BdBQBk8ckC/9BdKGgoOY3Jld2FpX3ZlcnNp
b24SCAoGMC41Ni4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiA3
M2FhYzI4NWU2NzQ2NjY3Zjc1MTQ3NjcwMDAzNDExMEoxCgdjcmV3X2lkEiYKJGI0NGRkMWVmLTBl
MjktNDhjOC1hM2MyLTYyYmE2ZmYzNzM2OEocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoR
CgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVt
YmVyX29mX2FnZW50cxICGAFKzAIKC2NyZXdfYWdlbnRzErwCCrkCW3sia2V5IjogImUxNDhlNTMy
MDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJiIiwgImlkIjogImE0MjA5NjI1LWEzMjgtNDk4Yi1iYTE5
LTQwMTkzYTI1ZmU2ZCIsICJyb2xlIjogInRlc3Qgcm9sZSIsICJ2ZXJib3NlPyI6IHRydWUsICJt
YXhfaXRlciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6IG51
bGwsICJsbG0iOiAiZ3B0LTRvIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93
X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25h
bWVzIjogW119XUqQAgoKY3Jld190YXNrcxKBAgr+AVt7ImtleSI6ICJmN2E5ZjdiYjFhZWU0YjZl
ZjJjNTI2ZDBhOGMyZjJhYyIsICJpZCI6ICI4YmU3MDE5Zi1jOTgyLTQyYWEtYmNmMC1mNDQxMjlk
Yzg4N2YiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2Us
ICJhZ2VudF9yb2xlIjogInRlc3Qgcm9sZSIsICJhZ2VudF9rZXkiOiAiZTE0OGU1MzIwMjkzNDk5
ZjhjZWJlYTgyNmU3MjU4MmIiLCAidG9vbHNfbmFtZXMiOiBbImdldF9maW5hbF9hbnN3ZXIiXX1d
egIYAYUBAAEAABKOAgoQN0J5i5ZgImoqc0cleBalphIIcUZhudQwDk8qDFRhc2sgQ3JlYXRlZDAB
OeAOanJAv/QXQYAYa3JAv/QXSi4KCGNyZXdfa2V5EiIKIDczYWFjMjg1ZTY3NDY2NjdmNzUxNDc2
NzAwMDM0MTEwSjEKB2NyZXdfaWQSJgokYjQ0ZGQxZWYtMGUyOS00OGM4LWEzYzItNjJiYTZmZjM3
MzY4Si4KCHRhc2tfa2V5EiIKIGY3YTlmN2JiMWFlZTRiNmVmMmM1MjZkMGE4YzJmMmFjSjEKB3Rh
c2tfaWQSJgokOGJlNzAxOWYtYzk4Mi00MmFhLWJjZjAtZjQ0MTI5ZGM4ODdmegIYAYUBAAEAABJ4
ChB6/qjzg+4s285bnp/7qE+HEghoZoLbzEODRyoQVG9vbCBVc2FnZSBFcnJvcjABOZDExcRAv/QX
QagZzMRAv/QXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNTYuMEoOCgNsbG0SBwoFZ3B0LTR6AhgB
hQEAAQAA
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1830'
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 08:07:26 GMT
status:
code: 200
message: OK
- 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: Use the get_final_answer tool.\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": "Thought: I need to use
the get_final_answer tool to obtain the final answer.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\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 will
use the get_final_answer tool again to achieve the final outcome.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: I encountered an error: Error
on parsing tool.\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:
- '2965'
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-A6vcr0Zy99KPnLgb2vwKAfQNCkcdD\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214845,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I will use the get_final_answer
tool to achieve the final outcome once more, following the correct format.\\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\": 618,\n \"completion_tokens\": 33,\n
\ \"total_tokens\": 651,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a4c158582ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:07:26 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:
- '559'
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:
- '29999304'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_da8379fa2e8b41a60b5eead39d650ab7
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: Use the get_final_answer tool.\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": "Thought: I need to use
the get_final_answer tool to obtain the final answer.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\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 will
use the get_final_answer tool again to achieve the final outcome.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: I encountered an error: Error
on parsing tool.\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 will use the get_final_answer tool to achieve the final outcome once more,
following the correct format.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
I encountered an error: Error on parsing tool.\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:
- '3808'
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-A6vctYjaBNZbtRnSyNQS6labgtMh3\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214847,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I will attempt to use the tool
again in the correct format to achieve the desired result.\\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\":
796,\n \"completion_tokens\": 30,\n \"total_tokens\": 826,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a4cc4a2f2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:07:28 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:
- '512'
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:
- '29999104'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_90c222d02ab84ab5420a0bf57253a7d2
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: Use the get_final_answer tool.\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": "Thought: I need to use
the get_final_answer tool to obtain the final answer.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\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 will
use the get_final_answer tool again to achieve the final outcome.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: I encountered an error: Error
on parsing tool.\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 will use the get_final_answer tool to achieve the final outcome once more,
following the correct format.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
I encountered an error: Error on parsing tool.\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 will attempt to use the tool again in the
correct format to achieve the desired result.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\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:
- '4634'
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-A6vcvS4WkpzJRLmsFK3ZwCA1lQQQE\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214849,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to ensure I use the tool
properly to obtain 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\":
971,\n \"completion_tokens\": 28,\n \"total_tokens\": 999,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a4d6baf82ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:07:29 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:
- '467'
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:
- '29998911'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_360bb0097c3ffa14f7a6975ee791d1a3
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CqsDCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSggMKEgoQY3Jld2FpLnRl
bGVtZXRyeRJ4ChDWU6Tm0J82nkUO4Atk2v0EEghcUVG8/OjtHSoQVG9vbCBVc2FnZSBFcnJvcjAB
ObgqvyhBv/QXQTBwxShBv/QXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNTYuMEoOCgNsbG0SBwoF
Z3B0LTR6AhgBhQEAAQAAEngKEMLVUYuBTzAJAsQgt7CPZ+4SCJSbTWuVYjHyKhBUb29sIFVzYWdl
IEVycm9yMAE5mKtZkUG/9BdBmARgkUG/9BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC41Ni4wSg4K
A2xsbRIHCgVncHQtNHoCGAGFAQABAAASeAoQApInrWTQcCG2RoWBJINhKhII/g6UtipyPz8qEFRv
b2wgVXNhZ2UgRXJyb3IwATkYKzbsQb/0F0EIXTzsQb/0F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYw
LjU2LjBKDgoDbGxtEgcKBWdwdC00egIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '430'
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 08:07:30 GMT
status:
code: 200
message: OK
- 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: Use the get_final_answer tool.\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": "Thought: I need to use
the get_final_answer tool to obtain the final answer.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\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 will
use the get_final_answer tool again to achieve the final outcome.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: I encountered an error: Error
on parsing tool.\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 will use the get_final_answer tool to achieve the final outcome once more,
following the correct format.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
I encountered an error: Error on parsing tool.\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 will attempt to use the tool again in the
correct format to achieve the desired result.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\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 need
to ensure I use the tool properly to obtain the final answer. \n\nAction: get_final_answer\nAction
Input: {}\nObservation: I encountered an error: Error on parsing tool.\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:
- '5440'
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-A6vcw78PlOg9wjkxMQmShkf37qua3\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214850,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Despite multiple attempts, I
continue to receive an error when using the tool. Since the instructions indicate
that I should use the tool non-stop but also either use a tool or give my best
final answer, I must now decide on the next appropriate step. Given that repetition
of the same steps hasn't resolved the issue, it's logical to conclude that the
only step left is to provide the final answer directly.\\n\\nFinal Answer: The
final answer\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
1144,\n \"completion_tokens\": 87,\n \"total_tokens\": 1231,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a4e09b982ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:07:32 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:
- '1372'
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:
- '29998722'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_4cd7cf794d3f33c2c35029719b05f0b3
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink