andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-24 07:38:14 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity
Files
3cd464497b26ae499d46ddfda0eb92a294051cbe
crewAI/tests/cassettes/test_api_calls_throttling.yaml
João Moura 3cd464497b rebuilding executor
2024-09-13 04:38:19 -05:00

766 lines
33 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Don''t give
a Final Answer, instead keep using the `get_final_answer` tool.\n\nThis is the
expect criteria for your final answer: The final answer. \n you 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-4-0125-preview", "stop":
["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1376'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mMevw9MC3OvV2KhIGvPf231nfVR\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940916,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I'm unable to fulfill this request.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 283,\n \"completion_tokens\":
8,\n \"total_tokens\": 291\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c8509cb1e2ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:01:58 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:
- '1374'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1999671'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 9ms
x-request-id:
- req_8ac0c0ac01779e40e61de9dabdb1ce95
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Don''t give
a Final Answer, instead keep using the `get_final_answer` tool.\n\nThis is the
expect criteria for your final answer: The final answer. \n you 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-4-0125-preview", "stop":
["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1376'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mMgh25zdJk1FEdhNi8q1GiciXLI\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940918,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I am unable to complete this task as
it is described.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
283,\n \"completion_tokens\": 12,\n \"total_tokens\": 295\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c85138f552ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:01:59 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:
- '615'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1999671'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 9ms
x-request-id:
- req_c02c11bb62b2b54d9c3ce0a441d484d5
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:
- '2261'
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:
- Tue, 10 Sep 2024 04:01:59 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Don''t give
a Final Answer, instead keep using the `get_final_answer` tool.\n\nThis is the
expect criteria for your final answer: The final answer. \n you 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-4-0125-preview", "stop":
["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1376'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mMhrm2OmQ8jG597tMk0aGS24moJ\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940919,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Given the instructions not to provide
a Final Answer and to continually use the `get_final_answer` tool, I cannot
proceed with a normal format that leads to a conclusive end. \\n\\nThought:
Since the directions explicitly instruct to NOT give a Final Answer but to keep
using the `get_final_answer` tool non-stop, I'll align my actions accordingly.\\n\\nAction:
get_final_answer\\nAction Input: {}\\n\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 283,\n \"completion_tokens\": 80,\n
\ \"total_tokens\": 363\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c85188d552ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:02:01 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:
- '2727'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1999671'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 9ms
x-request-id:
- req_8ca3039e0453dae471c11865fe075c88
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CqYBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSfgoSChBjcmV3YWkudGVs
ZW1ldHJ5EmgKEHVg0AggN4lMlElyVTW85JcSCH/etMoeqiqYKhBUb29sIFVzYWdlIEVycm9yMAE5
sFSxwR/G8xdB2F+1wR/G8xdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC41NS4yegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '169'
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:
- Tue, 10 Sep 2024 04:02:04 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Don''t give
a Final Answer, instead keep using the `get_final_answer` tool.\n\nThis is the
expect criteria for your final answer: The final answer. \n you 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": "Given
the instructions not to provide a Final Answer and to continually use the `get_final_answer`
tool, I cannot proceed with a normal format that leads to a conclusive end.
\n\nThought: Since the directions explicitly instruct to NOT give a Final Answer
but to keep using the `get_final_answer` tool non-stop, I''ll align my actions
accordingly.\n\nAction: get_final_answer\nAction Input: {}\n\nObservation: \nI
encountered an error while trying to use the tool. This was the error: test_api_calls_throttling.<locals>.get_final_answer()
missing 1 required positional argument: ''anything''.\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-4-0125-preview", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2739'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mMkPdRi74tvh4yCAvVldlXFU7nX\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940922,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Given the instructions and the constraints
of this task, it seems I've reached a conceptual dead end. Since I'm instructed
to merely use the `get_final_answer` tool non-stop and explicitly advised against
providing a Final Answer, I must continue in this loop indefinitely.\\n\\n---\\n\\nThought:
Since further actions seem to loop back to using the only available tool without
providing a final answer as per instructions, I recognize the task's requirements
are to remain in an ongoing process of inquiry without conclusion.\\n\\nAction:
get_final_answer\\nAction Input: {}\\n\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 575,\n \"completion_tokens\": 106,\n
\ \"total_tokens\": 681\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c852abc392ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:02:06 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:
- '4499'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1999345'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 19ms
x-request-id:
- req_992c50a582a0b70ae140c9d52931e631
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CqYBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSfgoSChBjcmV3YWkudGVs
ZW1ldHJ5EmgKEGsv4wWcvM+VIcp9yrzI9MASCHOrcgr84Z7FKhBUb29sIFVzYWdlIEVycm9yMAE5
kNhX2SDG8xdBsJFb2SDG8xdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC41NS4yegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '169'
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:
- Tue, 10 Sep 2024 04:02:11 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Don''t give
a Final Answer, instead keep using the `get_final_answer` tool.\n\nThis is the
expect criteria for your final answer: The final answer. \n you 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": "Given
the instructions not to provide a Final Answer and to continually use the `get_final_answer`
tool, I cannot proceed with a normal format that leads to a conclusive end.
\n\nThought: Since the directions explicitly instruct to NOT give a Final Answer
but to keep using the `get_final_answer` tool non-stop, I''ll align my actions
accordingly.\n\nAction: get_final_answer\nAction Input: {}\n\nObservation: \nI
encountered an error while trying to use the tool. This was the error: test_api_calls_throttling.<locals>.get_final_answer()
missing 1 required positional argument: ''anything''.\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": "Given the instructions and the constraints of this
task, it seems I''ve reached a conceptual dead end. Since I''m instructed to
merely use the `get_final_answer` tool non-stop and explicitly advised against
providing a Final Answer, I must continue in this loop indefinitely.\n\n---\n\nThought:
Since further actions seem to loop back to using the only available tool without
providing a final answer as per instructions, I recognize the task''s requirements
are to remain in an ongoing process of inquiry without conclusion.\n\nAction:
get_final_answer\nAction Input: {}\n\nObservation: \nI encountered an error
while trying to use the tool. This was the error: test_api_calls_throttling.<locals>.get_final_answer()
missing 1 required positional argument: ''anything''.\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-4-0125-preview", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4278'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5mMo6EoWYukjo0rprrZtSBAX3Mkc\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940926,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Given the constructed parameters and
the feedback loop that's been established, I find myself in an endless cycle
as per the instructions. The task was to continually use the `get_final_answer`
tool without actually converging on a final answer. Thus, adhering to the guidelines,
I am executing the task as instructed but am unable to proceed to a conclusive
final answer due to the very nature of the task's design constraints.\\n\\n---
\\n\\nSince the instructions lead to a paradox where action is expected without
reaching a conclusion, and considering the tool's usage results in an error
message indicating misuse or misunderstanding of how to properly utilize it
within given constraints, I acknowledge the cyclical nature of this task and
the impossibility of breaking from it under current directions. \\n\\nIn following
the instructions to neither provide a final answer nor deviate from the specified
tool, my role is fulfilled by continuously engaging with the process as outlined,
without arriving at a distinct conclusion.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 893,\n \"completion_tokens\": 187,\n
\ \"total_tokens\": 1080\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c854808da2ae0-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 04:02:12 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:
- '6121'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1998973'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 30ms
x-request-id:
- req_7c65a15afe980e38160d1f149ecb1052
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink