mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-10 08:38:30 +00:00
6f2e39c0dd
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Update Test Durations / update-durations (3.10) (push) Has been cancelled
Update Test Durations / update-durations (3.11) (push) Has been cancelled
Update Test Durations / update-durations (3.12) (push) Has been cancelled
Update Test Durations / update-durations (3.13) (push) Has been cancelled
* feat: enhance knowledge event handling in Agent class - Updated the Agent class to include task context in knowledge retrieval events. - Emitted new events for knowledge retrieval and query processes, capturing task and agent details. - Refactored knowledge event classes to inherit from a base class for better structure and maintainability. - Added tracing for knowledge events in the TraceCollectionListener to improve observability. This change improves the tracking and management of knowledge queries and retrievals, facilitating better debugging and performance monitoring. * refactor: remove task_id from knowledge event emissions in Agent class - Removed the task_id parameter from various knowledge event emissions in the Agent class to streamline event handling. - This change simplifies the event structure and focuses on the essential context of knowledge retrieval and query processes. This refactor enhances the clarity of knowledge events and aligns with the recent improvements in event handling. * surface association for guardrail events * fix: improve LLM selection logic in converter - Updated the logic for selecting the LLM in the convert_with_instructions function to handle cases where the agent may not have a function_calling_llm attribute. - This change ensures that the converter can still function correctly by falling back to the standard LLM if necessary, enhancing robustness and preventing potential errors. This fix improves the reliability of the conversion process when working with different agent configurations. * fix test * fix: enforce valid LLM instance requirement in converter - Updated the convert_with_instructions function to ensure that a valid LLM instance is provided by the agent. - If neither function_calling_llm nor the standard llm is available, a ValueError is raised, enhancing error handling and robustness. - Improved error messaging for conversion failures to provide clearer feedback on issues encountered during the conversion process. This change strengthens the reliability of the conversion process by ensuring that agents are properly configured with a valid LLM.
3561 lines
242 KiB
YAML
3561 lines
242 KiB
YAML
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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
|
|
in your response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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-mini", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1374'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.68.2
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.68.2
|
|
x-stainless-raw-response:
|
|
- 'true'
|
|
x-stainless-read-timeout:
|
|
- '600.0'
|
|
x-stainless-retry-count:
|
|
- '0'
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.12.8
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-BHIrzTIGOht7LtyCu63s9y6al9Wt0\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1743463811,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"I need to determine what action to take
|
|
next to retrieve the final answer. \\nAction: get_final_answer \\nAction Input:
|
|
{} \",\n \"refusal\": null,\n \"annotations\": []\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 \"prompt_tokens_details\": {\n \"cached_tokens\":
|
|
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
|
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
|
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
|
\"default\",\n \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
|
|
headers:
|
|
CF-RAY:
|
|
- 9293a2159f4c67b9-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 31 Mar 2025 23:30:13 GMT
|
|
Server:
|
|
- cloudflare
|
|
Set-Cookie:
|
|
- __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
|
|
path=/; expires=Tue, 01-Apr-25 00:00:13 GMT; domain=.api.openai.com; HttpOnly;
|
|
Secure; SameSite=None
|
|
- _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000;
|
|
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
|
Transfer-Encoding:
|
|
- chunked
|
|
X-Content-Type-Options:
|
|
- nosniff
|
|
access-control-expose-headers:
|
|
- X-Request-ID
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
cf-cache-status:
|
|
- DYNAMIC
|
|
openai-organization:
|
|
- crewai-iuxna1
|
|
openai-processing-ms:
|
|
- '2066'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=31536000; includeSubDomains; preload
|
|
x-ratelimit-limit-requests:
|
|
- '30000'
|
|
x-ratelimit-limit-tokens:
|
|
- '150000000'
|
|
x-ratelimit-remaining-requests:
|
|
- '29999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '149999694'
|
|
x-ratelimit-reset-requests:
|
|
- 2ms
|
|
x-ratelimit-reset-tokens:
|
|
- 0s
|
|
x-request-id:
|
|
- req_1311568b96e7fc639ff8dc1e0a43aa79
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: !!binary |
|
|
CuoNCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSwQ0KEgoQY3Jld2FpLnRl
|
|
bGVtZXRyeRKrCAoQqJ0LX3K2ujggGW8chWkxnhIIOKFYgK1mwk4qDENyZXcgQ3JlYXRlZDABOcih
|
|
DV8ZBzIYQQhnHF8ZBzIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKGgoOcHl0aG9uX3Zl
|
|
cnNpb24SCAoGMy4xMi44Si4KCGNyZXdfa2V5EiIKIDczYWFjMjg1ZTY3NDY2NjdmNzUxNDc2NzAw
|
|
MDM0MTEwSjEKB2NyZXdfaWQSJgokNGRkNDQyYjItNjE2My00YWY2LTg1NjMtNzM1ZWJmNjIxOTNh
|
|
ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
|
|
X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
|
|
X2ZpbmdlcnByaW50EiYKJGVlYWUyOTM3LWI0YzgtNGE5ZS04YWI4LWVjM2Y3ZGMxNDFmYko7Chtj
|
|
cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wMy0zMVQxNjozMDoxMS4yOTA0MjdK
|
|
zgIKC2NyZXdfYWdlbnRzEr4CCrsCW3sia2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZl
|
|
NzI1ODJiIiwgImlkIjogIjMzNDNjZjgzLWFiNmEtNDk5OS04Mjc2LTA1ZGM0MTE0N2E1YiIsICJy
|
|
b2xlIjogInRlc3Qgcm9sZSIsICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDEsICJtYXhf
|
|
cnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1p
|
|
bmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/
|
|
IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSpACCgpj
|
|
cmV3X3Rhc2tzEoECCv4BW3sia2V5IjogImY3YTlmN2JiMWFlZTRiNmVmMmM1MjZkMGE4YzJmMmFj
|
|
IiwgImlkIjogImIxZjRhMGFhLTYwMmQtNGFjMy05ODllLTY0NDdmNDlmZjZjMSIsICJhc3luY19l
|
|
eGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAi
|
|
dGVzdCByb2xlIiwgImFnZW50X2tleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgy
|
|
YiIsICJ0b29sc19uYW1lcyI6IFsiZ2V0X2ZpbmFsX2Fuc3dlciJdfV16AhgBhQEAAQAAEoAEChCN
|
|
K3bIxbl53On4qoM0P7BDEghZs7x1P32BHioMVGFzayBDcmVhdGVkMAE58PIvXxkHMhhBiKowXxkH
|
|
MhhKLgoIY3Jld19rZXkSIgogNzNhYWMyODVlNjc0NjY2N2Y3NTE0NzY3MDAwMzQxMTBKMQoHY3Jl
|
|
d19pZBImCiQ0ZGQ0NDJiMi02MTYzLTRhZjYtODU2My03MzVlYmY2MjE5M2FKLgoIdGFza19rZXkS
|
|
IgogZjdhOWY3YmIxYWVlNGI2ZWYyYzUyNmQwYThjMmYyYWNKMQoHdGFza19pZBImCiRiMWY0YTBh
|
|
YS02MDJkLTRhYzMtOTg5ZS02NDQ3ZjQ5ZmY2YzFKOgoQY3Jld19maW5nZXJwcmludBImCiRlZWFl
|
|
MjkzNy1iNGM4LTRhOWUtOGFiOC1lYzNmN2RjMTQxZmJKOgoQdGFza19maW5nZXJwcmludBImCiRl
|
|
MzJiYTMwZS00MDZmLTQ0ZmItOGM2Mi0wMmRkZTczZDIyNTJKOwobdGFza19maW5nZXJwcmludF9j
|
|
cmVhdGVkX2F0EhwKGjIwMjUtMDMtMzFUMTY6MzA6MTEuMjkwMzc4SjsKEWFnZW50X2ZpbmdlcnBy
|
|
aW50EiYKJDZiYjU4M2YxLWRkZTAtNDgwYy05YzZkLWRmNzQ0NTI1YTI3ZXoCGAGFAQABAAASegoQ
|
|
2qsKnI/iz5YZxt5B55H/3BIITw7exxOBPXIqEFRvb2wgVXNhZ2UgRXJyb3IwATmI7cjnGQcyGEFA
|
|
q9XnGQcyGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwOC4wSg8KA2xsbRIICgZncHQtNG96AhgB
|
|
hQEAAQAA
|
|
headers:
|
|
Accept:
|
|
- '*/*'
|
|
Accept-Encoding:
|
|
- gzip, deflate, zstd
|
|
Connection:
|
|
- keep-alive
|
|
Content-Length:
|
|
- '1773'
|
|
Content-Type:
|
|
- application/x-protobuf
|
|
User-Agent:
|
|
- OTel-OTLP-Exporter-Python/1.31.1
|
|
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:
|
|
- Mon, 31 Mar 2025 23:30:14 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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
|
|
in your response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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-mini", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '4193'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
|
|
_cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.68.2
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.68.2
|
|
x-stainless-raw-response:
|
|
- 'true'
|
|
x-stainless-read-timeout:
|
|
- '600.0'
|
|
x-stainless-retry-count:
|
|
- '0'
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.12.8
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-BHIs3RZWE0pDm4saOP5a2j2pUORUD\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1743463815,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"```\\nThought: I now know the final answer\\nFinal
|
|
Answer: I must follow the predefined structure and utilize the get_final_answer
|
|
tool to extract the necessary information.\\n```\",\n \"refusal\": null,\n
|
|
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
|
|
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 878,\n \"completion_tokens\":
|
|
35,\n \"total_tokens\": 913,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
|
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
|
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
|
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
|
\"default\",\n \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
|
|
headers:
|
|
CF-RAY:
|
|
- 9293a2235a2467b9-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 31 Mar 2025 23:30:16 GMT
|
|
Server:
|
|
- cloudflare
|
|
Transfer-Encoding:
|
|
- chunked
|
|
X-Content-Type-Options:
|
|
- nosniff
|
|
access-control-expose-headers:
|
|
- X-Request-ID
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
cf-cache-status:
|
|
- DYNAMIC
|
|
openai-organization:
|
|
- crewai-iuxna1
|
|
openai-processing-ms:
|
|
- '1050'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=31536000; includeSubDomains; preload
|
|
x-ratelimit-limit-requests:
|
|
- '30000'
|
|
x-ratelimit-limit-tokens:
|
|
- '150000000'
|
|
x-ratelimit-remaining-requests:
|
|
- '29999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '149999028'
|
|
x-ratelimit-reset-requests:
|
|
- 2ms
|
|
x-ratelimit-reset-tokens:
|
|
- 0s
|
|
x-request-id:
|
|
- req_a945851daba59247e89436242f50c663
|
|
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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
|
|
in your response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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-mini", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '4193'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
|
|
_cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.68.2
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.68.2
|
|
x-stainless-raw-response:
|
|
- 'true'
|
|
x-stainless-read-timeout:
|
|
- '600.0'
|
|
x-stainless-retry-count:
|
|
- '0'
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.12.8
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-BHIs5hXcx2fn8tJmCAJHoKpvbM9C5\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1743463817,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"```\\nThought: you should always think
|
|
about what to do\\nAction: get_final_answer\\nAction Input: {}\",\n \"refusal\":
|
|
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
|
|
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 878,\n \"completion_tokens\":
|
|
23,\n \"total_tokens\": 901,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
|
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
|
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
|
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
|
\"default\",\n \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
|
|
headers:
|
|
CF-RAY:
|
|
- 9293a237ced067b9-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 31 Mar 2025 23:30:17 GMT
|
|
Server:
|
|
- cloudflare
|
|
Transfer-Encoding:
|
|
- chunked
|
|
X-Content-Type-Options:
|
|
- nosniff
|
|
access-control-expose-headers:
|
|
- X-Request-ID
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
cf-cache-status:
|
|
- DYNAMIC
|
|
openai-organization:
|
|
- crewai-iuxna1
|
|
openai-processing-ms:
|
|
- '760'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=31536000; includeSubDomains; preload
|
|
x-ratelimit-limit-requests:
|
|
- '30000'
|
|
x-ratelimit-limit-tokens:
|
|
- '150000000'
|
|
x-ratelimit-remaining-requests:
|
|
- '29999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '149999027'
|
|
x-ratelimit-reset-requests:
|
|
- 2ms
|
|
x-ratelimit-reset-tokens:
|
|
- 0s
|
|
x-request-id:
|
|
- req_47c73df64cb410e71c6558fb111669b9
|
|
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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
|
|
in your response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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-mini", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '6960'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
|
|
_cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.68.2
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.68.2
|
|
x-stainless-raw-response:
|
|
- 'true'
|
|
x-stainless-read-timeout:
|
|
- '600.0'
|
|
x-stainless-retry-count:
|
|
- '0'
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.12.8
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-BHIs6Z7FbkaaEHZCks2aPg5RpB7p9\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1743463818,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"```\\nThought: I need to determine how
|
|
to proceed in order to get the final answer.\\nAction: get_final_answer\\nAction
|
|
Input: {}\",\n \"refusal\": null,\n \"annotations\": []\n },\n
|
|
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
|
\ \"usage\": {\n \"prompt_tokens\": 1474,\n \"completion_tokens\": 29,\n
|
|
\ \"total_tokens\": 1503,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
|
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
|
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
|
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
|
\"default\",\n \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
|
|
headers:
|
|
CF-RAY:
|
|
- 9293a23dadf367b9-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 31 Mar 2025 23:30:18 GMT
|
|
Server:
|
|
- cloudflare
|
|
Transfer-Encoding:
|
|
- chunked
|
|
X-Content-Type-Options:
|
|
- nosniff
|
|
access-control-expose-headers:
|
|
- X-Request-ID
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
cf-cache-status:
|
|
- DYNAMIC
|
|
openai-organization:
|
|
- crewai-iuxna1
|
|
openai-processing-ms:
|
|
- '807'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=31536000; includeSubDomains; preload
|
|
x-ratelimit-limit-requests:
|
|
- '30000'
|
|
x-ratelimit-limit-tokens:
|
|
- '150000000'
|
|
x-ratelimit-remaining-requests:
|
|
- '29999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '149998375'
|
|
x-ratelimit-reset-requests:
|
|
- 2ms
|
|
x-ratelimit-reset-tokens:
|
|
- 0s
|
|
x-request-id:
|
|
- req_116bd0a42b72845da93d150d06b3d074
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: !!binary |
|
|
CrkBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSkAEKEgoQY3Jld2FpLnRl
|
|
bGVtZXRyeRJ6ChBg77N3Xk6AOGtF6qHpgY/TEgjLb9iGJfRibCoQVG9vbCBVc2FnZSBFcnJvcjAB
|
|
ObCyK+IaBzIYQSCCN+IaBzIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKDwoDbGxtEggK
|
|
BmdwdC00b3oCGAGFAQABAAA=
|
|
headers:
|
|
Accept:
|
|
- '*/*'
|
|
Accept-Encoding:
|
|
- gzip, deflate, zstd
|
|
Connection:
|
|
- keep-alive
|
|
Content-Length:
|
|
- '188'
|
|
Content-Type:
|
|
- application/x-protobuf
|
|
User-Agent:
|
|
- OTel-OTLP-Exporter-Python/1.31.1
|
|
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:
|
|
- Mon, 31 Mar 2025 23:30:19 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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
|
|
in your response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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-mini", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '6960'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
|
|
_cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.68.2
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.68.2
|
|
x-stainless-raw-response:
|
|
- 'true'
|
|
x-stainless-read-timeout:
|
|
- '600.0'
|
|
x-stainless-retry-count:
|
|
- '0'
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.12.8
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-BHIs6TS0cl8Nktzxi2GavpYUOOcVV\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1743463818,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"```\\nThought: I need to pursue the action
|
|
to get the final answer.\\nAction: get_final_answer\\nAction Input: {}\",\n
|
|
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
|
|
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
|
1474,\n \"completion_tokens\": 26,\n \"total_tokens\": 1500,\n \"prompt_tokens_details\":
|
|
{\n \"cached_tokens\": 1408,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
|
|
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
|
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
|
\"default\",\n \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
|
|
headers:
|
|
CF-RAY:
|
|
- 9293a2433d5567b9-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 31 Mar 2025 23:30:19 GMT
|
|
Server:
|
|
- cloudflare
|
|
Transfer-Encoding:
|
|
- chunked
|
|
X-Content-Type-Options:
|
|
- nosniff
|
|
access-control-expose-headers:
|
|
- X-Request-ID
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
cf-cache-status:
|
|
- DYNAMIC
|
|
openai-organization:
|
|
- crewai-iuxna1
|
|
openai-processing-ms:
|
|
- '1031'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=31536000; includeSubDomains; preload
|
|
x-ratelimit-limit-requests:
|
|
- '30000'
|
|
x-ratelimit-limit-tokens:
|
|
- '150000000'
|
|
x-ratelimit-remaining-requests:
|
|
- '29999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '149998375'
|
|
x-ratelimit-reset-requests:
|
|
- 2ms
|
|
x-ratelimit-reset-tokens:
|
|
- 0s
|
|
x-request-id:
|
|
- req_772114061f86f1e4fc4d6af78e369c9c
|
|
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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
|
|
in your response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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-mini", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '9751'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
|
|
_cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.68.2
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.68.2
|
|
x-stainless-raw-response:
|
|
- 'true'
|
|
x-stainless-read-timeout:
|
|
- '600.0'
|
|
x-stainless-retry-count:
|
|
- '0'
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.12.8
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-BHIs88CTLDSND5eByFBW2ge57fKNW\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1743463820,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"```\\nThought: I need to pursue the action
|
|
to get the final answer.\\nAction: get_final_answer\\nAction Input: {}\",\n
|
|
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
|
|
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
|
2076,\n \"completion_tokens\": 26,\n \"total_tokens\": 2102,\n \"prompt_tokens_details\":
|
|
{\n \"cached_tokens\": 1408,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
|
|
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
|
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
|
\"default\",\n \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 9293a24a5d9b67b9-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 31 Mar 2025 23:30:20 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:
|
|
- '724'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=31536000; includeSubDomains; preload
|
|
x-ratelimit-limit-requests:
|
|
- '30000'
|
|
x-ratelimit-limit-tokens:
|
|
- '150000000'
|
|
x-ratelimit-remaining-requests:
|
|
- '29999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '149997717'
|
|
x-ratelimit-reset-requests:
|
|
- 2ms
|
|
x-ratelimit-reset-tokens:
|
|
- 0s
|
|
x-request-id:
|
|
- req_53b688c965fd8ea9aec538e23dc14d5f
|
|
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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
|
|
in your response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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-mini", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '9751'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
|
|
_cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.68.2
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.68.2
|
|
x-stainless-raw-response:
|
|
- 'true'
|
|
x-stainless-read-timeout:
|
|
- '600.0'
|
|
x-stainless-retry-count:
|
|
- '0'
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.12.8
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-BHIs8PPr1kQwag3x7EeShzJwgKBHQ\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1743463820,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"```\\nThought: I need to pursue the action
|
|
to get the final answer.\\nAction: get_final_answer\\nAction Input: {}\",\n
|
|
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
|
|
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
|
2076,\n \"completion_tokens\": 26,\n \"total_tokens\": 2102,\n \"prompt_tokens_details\":
|
|
{\n \"cached_tokens\": 2048,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
|
|
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
|
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
|
\"default\",\n \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
|
|
headers:
|
|
CF-RAY:
|
|
- 9293a24f5b6e67b9-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 31 Mar 2025 23:30:21 GMT
|
|
Server:
|
|
- cloudflare
|
|
Transfer-Encoding:
|
|
- chunked
|
|
X-Content-Type-Options:
|
|
- nosniff
|
|
access-control-expose-headers:
|
|
- X-Request-ID
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
cf-cache-status:
|
|
- DYNAMIC
|
|
openai-organization:
|
|
- crewai-iuxna1
|
|
openai-processing-ms:
|
|
- '970'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=31536000; includeSubDomains; preload
|
|
x-ratelimit-limit-requests:
|
|
- '30000'
|
|
x-ratelimit-limit-tokens:
|
|
- '150000000'
|
|
x-ratelimit-remaining-requests:
|
|
- '29999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '149997716'
|
|
x-ratelimit-reset-requests:
|
|
- 2ms
|
|
x-ratelimit-reset-tokens:
|
|
- 0s
|
|
x-request-id:
|
|
- req_003929761b6c31033aa046068854bb4d
|
|
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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
|
|
in your response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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-mini", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '12542'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
|
|
_cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.68.2
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.68.2
|
|
x-stainless-raw-response:
|
|
- 'true'
|
|
x-stainless-read-timeout:
|
|
- '600.0'
|
|
x-stainless-retry-count:
|
|
- '0'
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.12.8
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-BHIs9EQi1thZCKE6iowM7PKovOwHL\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1743463821,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"```\\nThought: I need to take action
|
|
to get the final answer.\\nAction: get_final_answer\\nAction Input: {}\",\n
|
|
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
|
|
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
|
2678,\n \"completion_tokens\": 25,\n \"total_tokens\": 2703,\n \"prompt_tokens_details\":
|
|
{\n \"cached_tokens\": 2048,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
|
|
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
|
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
|
\"default\",\n \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 9293a2560b2367b9-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 31 Mar 2025 23:30:22 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:
|
|
- '954'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=31536000; includeSubDomains; preload
|
|
x-ratelimit-limit-requests:
|
|
- '30000'
|
|
x-ratelimit-limit-tokens:
|
|
- '150000000'
|
|
x-ratelimit-remaining-requests:
|
|
- '29999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '149997058'
|
|
x-ratelimit-reset-requests:
|
|
- 2ms
|
|
x-ratelimit-reset-tokens:
|
|
- 1ms
|
|
x-request-id:
|
|
- req_58701a68086507409e813a7fe23fa4a3
|
|
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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
|
|
in your response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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-mini", "stop": ["\nObservation:"]}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate, zstd
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '12542'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
|
|
_cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.68.2
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.68.2
|
|
x-stainless-raw-response:
|
|
- 'true'
|
|
x-stainless-read-timeout:
|
|
- '600.0'
|
|
x-stainless-retry-count:
|
|
- '0'
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.12.8
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-BHIsBMTtfSuUn9wxvCtunG64V1bHD\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1743463823,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"```\\nThought: I now know the final answer\\nFinal
|
|
Answer: I am unable to provide a final answer due to a continuous error when
|
|
trying to retrieve it using the get_final_answer tool.\\n```\",\n \"refusal\":
|
|
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
|
|
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 2678,\n \"completion_tokens\":
|
|
41,\n \"total_tokens\": 2719,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
|
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
|
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
|
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
|
\"default\",\n \"system_fingerprint\": \"fp_b376dfbbd5\"\n}\n"
|
|
headers:
|
|
CF-RAY:
|
|
- 9293a25ceb3867b9-SJC
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Mon, 31 Mar 2025 23:30:24 GMT
|
|
Server:
|
|
- cloudflare
|
|
Transfer-Encoding:
|
|
- chunked
|
|
X-Content-Type-Options:
|
|
- nosniff
|
|
access-control-expose-headers:
|
|
- X-Request-ID
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
cf-cache-status:
|
|
- DYNAMIC
|
|
openai-organization:
|
|
- crewai-iuxna1
|
|
openai-processing-ms:
|
|
- '1095'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=31536000; includeSubDomains; preload
|
|
x-ratelimit-limit-requests:
|
|
- '30000'
|
|
x-ratelimit-limit-tokens:
|
|
- '150000000'
|
|
x-ratelimit-remaining-requests:
|
|
- '29999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '149997058'
|
|
x-ratelimit-reset-requests:
|
|
- 2ms
|
|
x-ratelimit-reset-tokens:
|
|
- 1ms
|
|
x-request-id:
|
|
- req_f3e522c8e419cab62842ddcee0e80b7b
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"trace_id": "f547ec24-65a2-4e61-af1f-56a272147fff", "execution_type":
|
|
"crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
|
|
"crew_name": "crew", "flow_name": null, "crewai_version": "0.201.1", "privacy_level":
|
|
"standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
|
|
0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-10-08T18:16:43.606547+00:00"}}'
|
|
headers:
|
|
Accept:
|
|
- '*/*'
|
|
Accept-Encoding:
|
|
- gzip, deflate, zstd
|
|
Connection:
|
|
- keep-alive
|
|
Content-Length:
|
|
- '428'
|
|
Content-Type:
|
|
- application/json
|
|
User-Agent:
|
|
- CrewAI-CLI/0.201.1
|
|
X-Crewai-Organization-Id:
|
|
- d3a3d10c-35db-423f-a7a4-c026030ba64d
|
|
X-Crewai-Version:
|
|
- 0.201.1
|
|
method: POST
|
|
uri: http://localhost:3000/crewai_plus/api/v1/tracing/batches
|
|
response:
|
|
body:
|
|
string: '{"id":"b8e9c37f-0704-4e28-bd7d-def0ecc17a38","trace_id":"f547ec24-65a2-4e61-af1f-56a272147fff","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"0.201.1","privacy_level":"standard","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"0.201.1","privacy_level":"standard"},"created_at":"2025-10-08T18:16:44.029Z","updated_at":"2025-10-08T18:16:44.029Z"}'
|
|
headers:
|
|
Content-Length:
|
|
- '480'
|
|
cache-control:
|
|
- no-store
|
|
content-security-policy:
|
|
- 'default-src ''self'' *.crewai.com crewai.com; script-src ''self'' ''unsafe-inline''
|
|
*.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com
|
|
https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
|
|
https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
|
|
https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
|
|
https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
|
|
https://js-na1.hs-scripts.com https://share.descript.com/; style-src ''self''
|
|
''unsafe-inline'' *.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts;
|
|
img-src ''self'' data: *.crewai.com crewai.com https://zeus.tools.crewai.com
|
|
https://dashboard.tools.crewai.com https://cdn.jsdelivr.net; font-src ''self''
|
|
data: *.crewai.com crewai.com; connect-src ''self'' *.crewai.com crewai.com
|
|
https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/*
|
|
https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/
|
|
https://*.sentry.io https://www.google-analytics.com ws://localhost:3036 wss://localhost:3036;
|
|
frame-src ''self'' *.crewai.com crewai.com https://connect.useparagon.com/
|
|
https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/
|
|
https://docs.google.com https://drive.google.com https://slides.google.com
|
|
https://accounts.google.com https://*.google.com https://www.youtube.com https://share.descript.com'
|
|
content-type:
|
|
- application/json; charset=utf-8
|
|
etag:
|
|
- W/"f7ef4a09307b1f22afe599e654f4b364"
|
|
expires:
|
|
- '0'
|
|
permissions-policy:
|
|
- camera=(), microphone=(self), geolocation=()
|
|
pragma:
|
|
- no-cache
|
|
referrer-policy:
|
|
- strict-origin-when-cross-origin
|
|
server-timing:
|
|
- cache_read.active_support;dur=0.21, sql.active_record;dur=32.18, cache_generate.active_support;dur=12.04,
|
|
cache_write.active_support;dur=0.23, cache_read_multi.active_support;dur=0.34,
|
|
start_processing.action_controller;dur=0.00, instantiation.active_record;dur=1.17,
|
|
feature_operation.flipper;dur=0.11, start_transaction.active_record;dur=0.01,
|
|
transaction.active_record;dur=16.34, process_action.action_controller;dur=345.81
|
|
vary:
|
|
- Accept
|
|
x-content-type-options:
|
|
- nosniff
|
|
x-frame-options:
|
|
- SAMEORIGIN
|
|
x-permitted-cross-domain-policies:
|
|
- none
|
|
x-request-id:
|
|
- 805c96e3-5b48-4958-a7b4-5b4269eb624f
|
|
x-runtime:
|
|
- '0.414250'
|
|
x-xss-protection:
|
|
- 1; mode=block
|
|
status:
|
|
code: 201
|
|
message: Created
|
|
- request:
|
|
body: '{"events": [{"event_id": "16a8f4da-5401-4181-a47d-e04135331203", "timestamp":
|
|
"2025-10-08T18:16:44.057758+00:00", "type": "crew_kickoff_started", "event_data":
|
|
{"timestamp": "2025-10-08T18:16:43.605145+00:00", "type": "crew_kickoff_started",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"crew_name": "crew", "crew": null, "inputs": null}}, {"event_id": "f91353c4-d5ea-43d0-b227-533b62ee85e5",
|
|
"timestamp": "2025-10-08T18:16:44.064866+00:00", "type": "task_started", "event_data":
|
|
{"task_description": "Use the get_final_answer tool.", "expected_output": "The
|
|
final answer", "task_name": "Use the get_final_answer tool.", "context": "",
|
|
"agent_role": "test role", "task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3"}},
|
|
{"event_id": "5a640158-996c-4f85-87ff-21ad7ea2fe20", "timestamp": "2025-10-08T18:16:44.065943+00:00",
|
|
"type": "agent_execution_started", "event_data": {"agent_role": "test role",
|
|
"agent_goal": "test goal", "agent_backstory": "test backstory"}}, {"event_id":
|
|
"a1160342-bb58-4eb7-85ad-c996b7096c93", "timestamp": "2025-10-08T18:16:44.067807+00:00",
|
|
"type": "llm_call_started", "event_data": {"timestamp": "2025-10-08T18:16:44.067549+00:00",
|
|
"type": "llm_call_started", "source_fingerprint": null, "source_type": null,
|
|
"fingerprint_metadata": null, "task_name": "Use the get_final_answer tool.",
|
|
"task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3", "agent_id": "163c48fa-466e-4470-b238-acbbfe263776",
|
|
"agent_role": "test role", "from_task": null, "from_agent": null, "model": "gpt-4o-mini",
|
|
"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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\ntool non-stop.\n\nIMPORTANT: Use the following format in your
|
|
response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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:"}], "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler
|
|
object at 0x1402345f0>"], "available_functions": null}}, {"event_id": "a14ce9ee-7832-4ccc-b78c-0d48da271f1e",
|
|
"timestamp": "2025-10-08T18:16:44.072905+00:00", "type": "llm_call_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.072815+00:00", "type": "llm_call_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": "Use the get_final_answer tool.", "task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3",
|
|
"agent_id": "163c48fa-466e-4470-b238-acbbfe263776", "agent_role": "test role",
|
|
"from_task": null, "from_agent": null, "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\nTool Arguments: {}\nTool Description:
|
|
Get the final answer but don''t give it yet, just re-use this\ntool non-stop.\n\nIMPORTANT:
|
|
Use the following format in your response:\n\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 JSON object, enclosed in curly braces, using \" to wrap keys and
|
|
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
|
is gathered, return the following format:\n\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 expected 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:"}], "response": "I need to determine what
|
|
action to take next to retrieve the final answer. \nAction: get_final_answer \nAction
|
|
Input: {} ", "call_type": "<LLMCallType.LLM_CALL: ''llm_call''>", "model":
|
|
"gpt-4o-mini"}}, {"event_id": "03ff68fd-169c-42ed-a466-546b50aa24bf", "timestamp":
|
|
"2025-10-08T18:16:44.078248+00:00", "type": "llm_call_started", "event_data":
|
|
{"timestamp": "2025-10-08T18:16:44.078102+00:00", "type": "llm_call_started",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": null, "task_id": null, "agent_id": null, "agent_role": null, "from_task":
|
|
null, "from_agent": null, "model": "gpt-4o-mini", "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\nTool Arguments: {}\nTool
|
|
Description: Get the final answer but don''t give it yet, just re-use this\ntool
|
|
non-stop.\n\nIMPORTANT: Use the following format in your response:\n\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 JSON object, enclosed in curly
|
|
braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
|
|
all necessary information is gathered, return the following format:\n\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 expected 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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}], "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler
|
|
object at 0x1402345f0>"], "available_functions": null}}, {"event_id": "9bc61f86-cf57-4971-aa11-5344a7015e23",
|
|
"timestamp": "2025-10-08T18:16:44.081687+00:00", "type": "llm_call_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.081634+00:00", "type": "llm_call_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": null, "task_id": null, "agent_id": null, "agent_role": null, "from_task":
|
|
null, "from_agent": null, "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\nTool Arguments: {}\nTool Description: Get the final
|
|
answer but don''t give it yet, just re-use this\ntool non-stop.\n\nIMPORTANT:
|
|
Use the following format in your response:\n\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 JSON object, enclosed in curly braces, using \" to wrap keys and
|
|
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
|
is gathered, return the following format:\n\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 expected 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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}], "response": "```\nThought:
|
|
I now know the final answer\nFinal Answer: I must follow the predefined structure
|
|
and utilize the get_final_answer tool to extract the necessary information.\n```",
|
|
"call_type": "<LLMCallType.LLM_CALL: ''llm_call''>", "model": "gpt-4o-mini"}},
|
|
{"event_id": "781c93ff-cf05-4a5e-81b8-0170f889ee5b", "timestamp": "2025-10-08T18:16:44.081795+00:00",
|
|
"type": "llm_call_started", "event_data": {"timestamp": "2025-10-08T18:16:44.081746+00:00",
|
|
"type": "llm_call_started", "source_fingerprint": null, "source_type": null,
|
|
"fingerprint_metadata": null, "task_name": "Use the get_final_answer tool.",
|
|
"task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3", "agent_id": "163c48fa-466e-4470-b238-acbbfe263776",
|
|
"agent_role": "test role", "from_task": null, "from_agent": null, "model": "gpt-4o-mini",
|
|
"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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\ntool non-stop.\n\nIMPORTANT: Use the following format in your
|
|
response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "I need to
|
|
determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}], "tools": null, "callbacks":
|
|
["<crewai.utilities.token_counter_callback.TokenCalcHandler object at 0x1402345f0>"],
|
|
"available_functions": null}}, {"event_id": "91dbc997-a5bb-4a55-91e2-31f601fff95a",
|
|
"timestamp": "2025-10-08T18:16:44.085678+00:00", "type": "llm_call_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.085617+00:00", "type": "llm_call_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": "Use the get_final_answer tool.", "task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3",
|
|
"agent_id": "163c48fa-466e-4470-b238-acbbfe263776", "agent_role": "test role",
|
|
"from_task": null, "from_agent": null, "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\nTool Arguments: {}\nTool Description:
|
|
Get the final answer but don''t give it yet, just re-use this\ntool non-stop.\n\nIMPORTANT:
|
|
Use the following format in your response:\n\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 JSON object, enclosed in curly braces, using \" to wrap keys and
|
|
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
|
is gathered, return the following format:\n\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 expected 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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}], "response": "```\nThought:
|
|
you should always think about what to do\nAction: get_final_answer\nAction Input:
|
|
{}", "call_type": "<LLMCallType.LLM_CALL: ''llm_call''>", "model": "gpt-4o-mini"}},
|
|
{"event_id": "5472e69e-83de-41f7-9406-69823552ff2f", "timestamp": "2025-10-08T18:16:44.087638+00:00",
|
|
"type": "llm_call_started", "event_data": {"timestamp": "2025-10-08T18:16:44.087510+00:00",
|
|
"type": "llm_call_started", "source_fingerprint": null, "source_type": null,
|
|
"fingerprint_metadata": null, "task_name": null, "task_id": null, "agent_id":
|
|
null, "agent_role": null, "from_task": null, "from_agent": null, "model": "gpt-4o-mini",
|
|
"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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\ntool non-stop.\n\nIMPORTANT: Use the following format in your
|
|
response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "I need to
|
|
determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}], "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler
|
|
object at 0x1402345f0>"], "available_functions": null}}, {"event_id": "b72092ce-ceda-4f82-9393-a80f9dcf0c09",
|
|
"timestamp": "2025-10-08T18:16:44.090720+00:00", "type": "llm_call_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.090679+00:00", "type": "llm_call_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": null, "task_id": null, "agent_id": null, "agent_role": null, "from_task":
|
|
null, "from_agent": null, "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\nTool Arguments: {}\nTool Description: Get the final
|
|
answer but don''t give it yet, just re-use this\ntool non-stop.\n\nIMPORTANT:
|
|
Use the following format in your response:\n\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 JSON object, enclosed in curly braces, using \" to wrap keys and
|
|
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
|
is gathered, return the following format:\n\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 expected 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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}], "response": "```\nThought: I need to determine how to proceed
|
|
in order to get the final answer.\nAction: get_final_answer\nAction Input: {}",
|
|
"call_type": "<LLMCallType.LLM_CALL: ''llm_call''>", "model": "gpt-4o-mini"}},
|
|
{"event_id": "a4709344-ef62-4836-ac7e-29e66fe56e9b", "timestamp": "2025-10-08T18:16:44.090828+00:00",
|
|
"type": "llm_call_started", "event_data": {"timestamp": "2025-10-08T18:16:44.090787+00:00",
|
|
"type": "llm_call_started", "source_fingerprint": null, "source_type": null,
|
|
"fingerprint_metadata": null, "task_name": "Use the get_final_answer tool.",
|
|
"task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3", "agent_id": "163c48fa-466e-4470-b238-acbbfe263776",
|
|
"agent_role": "test role", "from_task": null, "from_agent": null, "model": "gpt-4o-mini",
|
|
"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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\ntool non-stop.\n\nIMPORTANT: Use the following format in your
|
|
response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "I need to
|
|
determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}], "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler
|
|
object at 0x1402345f0>"], "available_functions": null}}, {"event_id": "01a16383-a9d3-4257-8fe6-cf644c9bfcdb",
|
|
"timestamp": "2025-10-08T18:16:44.093691+00:00", "type": "llm_call_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.093657+00:00", "type": "llm_call_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": "Use the get_final_answer tool.", "task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3",
|
|
"agent_id": "163c48fa-466e-4470-b238-acbbfe263776", "agent_role": "test role",
|
|
"from_task": null, "from_agent": null, "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\nTool Arguments: {}\nTool Description:
|
|
Get the final answer but don''t give it yet, just re-use this\ntool non-stop.\n\nIMPORTANT:
|
|
Use the following format in your response:\n\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 JSON object, enclosed in curly braces, using \" to wrap keys and
|
|
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
|
is gathered, return the following format:\n\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 expected 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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}], "response": "```\nThought: I need to pursue the action to
|
|
get the final answer.\nAction: get_final_answer\nAction Input: {}", "call_type":
|
|
"<LLMCallType.LLM_CALL: ''llm_call''>", "model": "gpt-4o-mini"}}, {"event_id":
|
|
"9290fb66-22c5-49fe-bc4c-0edef3213baf", "timestamp": "2025-10-08T18:16:44.095930+00:00",
|
|
"type": "llm_call_started", "event_data": {"timestamp": "2025-10-08T18:16:44.095245+00:00",
|
|
"type": "llm_call_started", "source_fingerprint": null, "source_type": null,
|
|
"fingerprint_metadata": null, "task_name": null, "task_id": null, "agent_id":
|
|
null, "agent_role": null, "from_task": null, "from_agent": null, "model": "gpt-4o-mini",
|
|
"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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\ntool non-stop.\n\nIMPORTANT: Use the following format in your
|
|
response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "I need to
|
|
determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "```\nThought: I need to pursue
|
|
the action to get the final answer.\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 not
|
|
both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "```\nThought:
|
|
I need to pursue the action to get the final answer.\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
|
|
not both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}], "tools": null, "callbacks":
|
|
["<crewai.utilities.token_counter_callback.TokenCalcHandler object at 0x1402345f0>"],
|
|
"available_functions": null}}, {"event_id": "e3c09cf8-7e54-4b7c-a941-48e40d11d482",
|
|
"timestamp": "2025-10-08T18:16:44.098722+00:00", "type": "llm_call_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.098680+00:00", "type": "llm_call_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": null, "task_id": null, "agent_id": null, "agent_role": null, "from_task":
|
|
null, "from_agent": null, "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\nTool Arguments: {}\nTool Description: Get the final
|
|
answer but don''t give it yet, just re-use this\ntool non-stop.\n\nIMPORTANT:
|
|
Use the following format in your response:\n\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 JSON object, enclosed in curly braces, using \" to wrap keys and
|
|
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
|
is gathered, return the following format:\n\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 expected 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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "```\nThought: I need to pursue
|
|
the action to get the final answer.\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 not
|
|
both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "```\nThought:
|
|
I need to pursue the action to get the final answer.\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
|
|
not both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}], "response": "```\nThought:
|
|
I need to pursue the action to get the final answer.\nAction: get_final_answer\nAction
|
|
Input: {}", "call_type": "<LLMCallType.LLM_CALL: ''llm_call''>", "model": "gpt-4o-mini"}},
|
|
{"event_id": "ec342da7-248c-4fb5-b7a9-c7fb90ec4e3a", "timestamp": "2025-10-08T18:16:44.098808+00:00",
|
|
"type": "llm_call_started", "event_data": {"timestamp": "2025-10-08T18:16:44.098774+00:00",
|
|
"type": "llm_call_started", "source_fingerprint": null, "source_type": null,
|
|
"fingerprint_metadata": null, "task_name": "Use the get_final_answer tool.",
|
|
"task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3", "agent_id": "163c48fa-466e-4470-b238-acbbfe263776",
|
|
"agent_role": "test role", "from_task": null, "from_agent": null, "model": "gpt-4o-mini",
|
|
"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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\ntool non-stop.\n\nIMPORTANT: Use the following format in your
|
|
response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "I need to
|
|
determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "```\nThought: I need to pursue
|
|
the action to get the final answer.\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 not
|
|
both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "```\nThought:
|
|
I need to pursue the action to get the final answer.\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
|
|
not both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}], "tools": null, "callbacks":
|
|
["<crewai.utilities.token_counter_callback.TokenCalcHandler object at 0x1402345f0>"],
|
|
"available_functions": null}}, {"event_id": "fcfab733-e239-4781-81e8-bbee191c3cce",
|
|
"timestamp": "2025-10-08T18:16:44.101471+00:00", "type": "llm_call_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.101441+00:00", "type": "llm_call_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": "Use the get_final_answer tool.", "task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3",
|
|
"agent_id": "163c48fa-466e-4470-b238-acbbfe263776", "agent_role": "test role",
|
|
"from_task": null, "from_agent": null, "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\nTool Arguments: {}\nTool Description:
|
|
Get the final answer but don''t give it yet, just re-use this\ntool non-stop.\n\nIMPORTANT:
|
|
Use the following format in your response:\n\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 JSON object, enclosed in curly braces, using \" to wrap keys and
|
|
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
|
is gathered, return the following format:\n\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 expected 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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "```\nThought: I need to pursue
|
|
the action to get the final answer.\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 not
|
|
both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "```\nThought:
|
|
I need to pursue the action to get the final answer.\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
|
|
not both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}], "response": "```\nThought:
|
|
I need to pursue the action to get the final answer.\nAction: get_final_answer\nAction
|
|
Input: {}", "call_type": "<LLMCallType.LLM_CALL: ''llm_call''>", "model": "gpt-4o-mini"}},
|
|
{"event_id": "a3b55181-2cc1-4c0c-8ef6-dd91b7da3cea", "timestamp": "2025-10-08T18:16:44.103430+00:00",
|
|
"type": "llm_call_started", "event_data": {"timestamp": "2025-10-08T18:16:44.102860+00:00",
|
|
"type": "llm_call_started", "source_fingerprint": null, "source_type": null,
|
|
"fingerprint_metadata": null, "task_name": null, "task_id": null, "agent_id":
|
|
null, "agent_role": null, "from_task": null, "from_agent": null, "model": "gpt-4o-mini",
|
|
"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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\ntool non-stop.\n\nIMPORTANT: Use the following format in your
|
|
response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "I need to
|
|
determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "```\nThought: I need to pursue
|
|
the action to get the final answer.\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 not
|
|
both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "```\nThought:
|
|
I need to pursue the action to get the final answer.\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
|
|
not both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: I need to pursue the action to get the final answer.\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}], "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler
|
|
object at 0x1402345f0>"], "available_functions": null}}, {"event_id": "7ce3a4d9-329c-4e03-97ee-1e7ff09b9e8a",
|
|
"timestamp": "2025-10-08T18:16:44.106320+00:00", "type": "llm_call_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.106287+00:00", "type": "llm_call_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": null, "task_id": null, "agent_id": null, "agent_role": null, "from_task":
|
|
null, "from_agent": null, "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\nTool Arguments: {}\nTool Description: Get the final
|
|
answer but don''t give it yet, just re-use this\ntool non-stop.\n\nIMPORTANT:
|
|
Use the following format in your response:\n\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 JSON object, enclosed in curly braces, using \" to wrap keys and
|
|
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
|
is gathered, return the following format:\n\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 expected 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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "```\nThought: I need to pursue
|
|
the action to get the final answer.\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 not
|
|
both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "```\nThought:
|
|
I need to pursue the action to get the final answer.\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
|
|
not both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: I need to pursue the action to get the final answer.\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}], "response": "```\nThought: I need to take action to get the
|
|
final answer.\nAction: get_final_answer\nAction Input: {}", "call_type": "<LLMCallType.LLM_CALL:
|
|
''llm_call''>", "model": "gpt-4o-mini"}}, {"event_id": "6973d64a-9c0e-451d-aa6b-a460364d290e",
|
|
"timestamp": "2025-10-08T18:16:44.106404+00:00", "type": "llm_call_started",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.106372+00:00", "type": "llm_call_started",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": "Use the get_final_answer tool.", "task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3",
|
|
"agent_id": "163c48fa-466e-4470-b238-acbbfe263776", "agent_role": "test role",
|
|
"from_task": null, "from_agent": null, "model": "gpt-4o-mini", "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\nTool
|
|
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
|
|
just re-use this\ntool non-stop.\n\nIMPORTANT: Use the following format in your
|
|
response:\n\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 JSON
|
|
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
|
the result of the action\n```\n\nOnce all necessary information is gathered,
|
|
return the following format:\n\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 expected
|
|
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": "I need to
|
|
determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "```\nThought: I need to pursue
|
|
the action to get the final answer.\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 not
|
|
both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "```\nThought:
|
|
I need to pursue the action to get the final answer.\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
|
|
not both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: I need to pursue the action to get the final answer.\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}], "tools": null, "callbacks": ["<crewai.utilities.token_counter_callback.TokenCalcHandler
|
|
object at 0x1402345f0>"], "available_functions": null}}, {"event_id": "79ebf739-db33-4fc4-ad3b-f3f1be07b3b6",
|
|
"timestamp": "2025-10-08T18:16:44.109198+00:00", "type": "llm_call_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.109164+00:00", "type": "llm_call_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"task_name": "Use the get_final_answer tool.", "task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3",
|
|
"agent_id": "163c48fa-466e-4470-b238-acbbfe263776", "agent_role": "test role",
|
|
"from_task": null, "from_agent": null, "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\nTool Arguments: {}\nTool Description:
|
|
Get the final answer but don''t give it yet, just re-use this\ntool non-stop.\n\nIMPORTANT:
|
|
Use the following format in your response:\n\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 JSON object, enclosed in curly braces, using \" to wrap keys and
|
|
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
|
is gathered, return the following format:\n\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 expected 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": "I need
|
|
to determine what action to take next to retrieve the final answer. \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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "I need to determine what action to take next to retrieve
|
|
the final answer. \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 not both at the same
|
|
time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: you should always think about what to do\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: you should always think about what to
|
|
do\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}, {"role": "assistant", "content": "```\nThought: I need to pursue
|
|
the action to get the final answer.\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 not
|
|
both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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": "```\nThought:
|
|
I need to pursue the action to get the final answer.\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
|
|
not both at the same time. When responding, I must use the following format:\n\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```\nThis Thought/Action/Action
|
|
Input/Result can repeat N times. Once I know the final answer, I must return
|
|
the following format:\n\n```\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."}, {"role": "assistant",
|
|
"content": "```\nThought: I need to pursue the action to get the final answer.\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 not both at the same time. When responding, I must
|
|
use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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": "```\nThought: I need to pursue the action to get the
|
|
final answer.\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 not both at the same time. When responding,
|
|
I must use the following format:\n\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```\nThis Thought/Action/Action Input/Result can repeat
|
|
N times. Once I know the final answer, I must return the following format:\n\n```\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."}], "response": "```\nThought: I now know the final answer\nFinal
|
|
Answer: I am unable to provide a final answer due to a continuous error when
|
|
trying to retrieve it using the get_final_answer tool.\n```", "call_type": "<LLMCallType.LLM_CALL:
|
|
''llm_call''>", "model": "gpt-4o-mini"}}, {"event_id": "3001082e-221b-47a0-9c15-4ac1f31e3b98",
|
|
"timestamp": "2025-10-08T18:16:44.109826+00:00", "type": "agent_execution_completed",
|
|
"event_data": {"agent_role": "test role", "agent_goal": "test goal", "agent_backstory":
|
|
"test backstory"}}, {"event_id": "6f921a6b-e3c2-45d2-a266-3658800dda49", "timestamp":
|
|
"2025-10-08T18:16:44.111015+00:00", "type": "task_completed", "event_data":
|
|
{"task_description": "Use the get_final_answer tool.", "task_name": "Use the
|
|
get_final_answer tool.", "task_id": "3515212f-6267-4b3d-a775-2cc602a9e8c3",
|
|
"output_raw": "I am unable to provide a final answer due to a continuous error
|
|
when trying to retrieve it using the get_final_answer tool.", "output_format":
|
|
"OutputFormat.RAW", "agent_role": "test role"}}, {"event_id": "ca83f844-3173-41eb-85b2-18ce4f3f2abd",
|
|
"timestamp": "2025-10-08T18:16:44.112376+00:00", "type": "crew_kickoff_completed",
|
|
"event_data": {"timestamp": "2025-10-08T18:16:44.111998+00:00", "type": "crew_kickoff_completed",
|
|
"source_fingerprint": null, "source_type": null, "fingerprint_metadata": null,
|
|
"crew_name": "crew", "crew": null, "output": {"description": "Use the get_final_answer
|
|
tool.", "name": "Use the get_final_answer tool.", "expected_output": "The final
|
|
answer", "summary": "Use the get_final_answer tool....", "raw": "I am unable
|
|
to provide a final answer due to a continuous error when trying to retrieve
|
|
it using the get_final_answer tool.", "pydantic": null, "json_dict": null, "agent":
|
|
"test role", "output_format": "raw"}, "total_tokens": 14744}}], "batch_metadata":
|
|
{"events_count": 24, "batch_sequence": 1, "is_final_batch": false}}'
|
|
headers:
|
|
Accept:
|
|
- '*/*'
|
|
Accept-Encoding:
|
|
- gzip, deflate, zstd
|
|
Connection:
|
|
- keep-alive
|
|
Content-Length:
|
|
- '118521'
|
|
Content-Type:
|
|
- application/json
|
|
User-Agent:
|
|
- CrewAI-CLI/0.201.1
|
|
X-Crewai-Organization-Id:
|
|
- d3a3d10c-35db-423f-a7a4-c026030ba64d
|
|
X-Crewai-Version:
|
|
- 0.201.1
|
|
method: POST
|
|
uri: http://localhost:3000/crewai_plus/api/v1/tracing/batches/f547ec24-65a2-4e61-af1f-56a272147fff/events
|
|
response:
|
|
body:
|
|
string: '{"events_created":24,"trace_batch_id":"b8e9c37f-0704-4e28-bd7d-def0ecc17a38"}'
|
|
headers:
|
|
Content-Length:
|
|
- '77'
|
|
cache-control:
|
|
- no-store
|
|
content-security-policy:
|
|
- 'default-src ''self'' *.crewai.com crewai.com; script-src ''self'' ''unsafe-inline''
|
|
*.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com
|
|
https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
|
|
https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
|
|
https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
|
|
https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
|
|
https://js-na1.hs-scripts.com https://share.descript.com/; style-src ''self''
|
|
''unsafe-inline'' *.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts;
|
|
img-src ''self'' data: *.crewai.com crewai.com https://zeus.tools.crewai.com
|
|
https://dashboard.tools.crewai.com https://cdn.jsdelivr.net; font-src ''self''
|
|
data: *.crewai.com crewai.com; connect-src ''self'' *.crewai.com crewai.com
|
|
https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/*
|
|
https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/
|
|
https://*.sentry.io https://www.google-analytics.com ws://localhost:3036 wss://localhost:3036;
|
|
frame-src ''self'' *.crewai.com crewai.com https://connect.useparagon.com/
|
|
https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/
|
|
https://docs.google.com https://drive.google.com https://slides.google.com
|
|
https://accounts.google.com https://*.google.com https://www.youtube.com https://share.descript.com'
|
|
content-type:
|
|
- application/json; charset=utf-8
|
|
etag:
|
|
- W/"8e091a3dffc34d9e84715a532d84af27"
|
|
expires:
|
|
- '0'
|
|
permissions-policy:
|
|
- camera=(), microphone=(self), geolocation=()
|
|
pragma:
|
|
- no-cache
|
|
referrer-policy:
|
|
- strict-origin-when-cross-origin
|
|
server-timing:
|
|
- cache_read.active_support;dur=0.09, sql.active_record;dur=154.27, cache_generate.active_support;dur=1.90,
|
|
cache_write.active_support;dur=0.16, cache_read_multi.active_support;dur=0.12,
|
|
start_processing.action_controller;dur=0.00, instantiation.active_record;dur=0.96,
|
|
start_transaction.active_record;dur=0.03, transaction.active_record;dur=339.87,
|
|
process_action.action_controller;dur=949.34
|
|
vary:
|
|
- Accept
|
|
x-content-type-options:
|
|
- nosniff
|
|
x-frame-options:
|
|
- SAMEORIGIN
|
|
x-permitted-cross-domain-policies:
|
|
- none
|
|
x-request-id:
|
|
- 0df136af-5a98-4324-9881-acb0dc2cf793
|
|
x-runtime:
|
|
- '1.011949'
|
|
x-xss-protection:
|
|
- 1; mode=block
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
- request:
|
|
body: '{"status": "completed", "duration_ms": 1536, "final_event_count": 24}'
|
|
headers:
|
|
Accept:
|
|
- '*/*'
|
|
Accept-Encoding:
|
|
- gzip, deflate, zstd
|
|
Connection:
|
|
- keep-alive
|
|
Content-Length:
|
|
- '69'
|
|
Content-Type:
|
|
- application/json
|
|
User-Agent:
|
|
- CrewAI-CLI/0.201.1
|
|
X-Crewai-Organization-Id:
|
|
- d3a3d10c-35db-423f-a7a4-c026030ba64d
|
|
X-Crewai-Version:
|
|
- 0.201.1
|
|
method: PATCH
|
|
uri: http://localhost:3000/crewai_plus/api/v1/tracing/batches/f547ec24-65a2-4e61-af1f-56a272147fff/finalize
|
|
response:
|
|
body:
|
|
string: '{"id":"b8e9c37f-0704-4e28-bd7d-def0ecc17a38","trace_id":"f547ec24-65a2-4e61-af1f-56a272147fff","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"completed","duration_ms":1536,"crewai_version":"0.201.1","privacy_level":"standard","total_events":24,"execution_context":{"crew_name":"crew","flow_name":null,"privacy_level":"standard","crewai_version":"0.201.1","crew_fingerprint":null},"created_at":"2025-10-08T18:16:44.029Z","updated_at":"2025-10-08T18:16:45.517Z"}'
|
|
headers:
|
|
Content-Length:
|
|
- '483'
|
|
cache-control:
|
|
- no-store
|
|
content-security-policy:
|
|
- 'default-src ''self'' *.crewai.com crewai.com; script-src ''self'' ''unsafe-inline''
|
|
*.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com
|
|
https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
|
|
https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
|
|
https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
|
|
https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
|
|
https://js-na1.hs-scripts.com https://share.descript.com/; style-src ''self''
|
|
''unsafe-inline'' *.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts;
|
|
img-src ''self'' data: *.crewai.com crewai.com https://zeus.tools.crewai.com
|
|
https://dashboard.tools.crewai.com https://cdn.jsdelivr.net; font-src ''self''
|
|
data: *.crewai.com crewai.com; connect-src ''self'' *.crewai.com crewai.com
|
|
https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/*
|
|
https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/
|
|
https://*.sentry.io https://www.google-analytics.com ws://localhost:3036 wss://localhost:3036;
|
|
frame-src ''self'' *.crewai.com crewai.com https://connect.useparagon.com/
|
|
https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/
|
|
https://docs.google.com https://drive.google.com https://slides.google.com
|
|
https://accounts.google.com https://*.google.com https://www.youtube.com https://share.descript.com'
|
|
content-type:
|
|
- application/json; charset=utf-8
|
|
etag:
|
|
- W/"d6a1d638049d3f206886a9e77884c925"
|
|
expires:
|
|
- '0'
|
|
permissions-policy:
|
|
- camera=(), microphone=(self), geolocation=()
|
|
pragma:
|
|
- no-cache
|
|
referrer-policy:
|
|
- strict-origin-when-cross-origin
|
|
server-timing:
|
|
- cache_read.active_support;dur=0.05, sql.active_record;dur=25.66, cache_generate.active_support;dur=4.16,
|
|
cache_write.active_support;dur=0.16, cache_read_multi.active_support;dur=0.11,
|
|
start_processing.action_controller;dur=0.00, instantiation.active_record;dur=1.95,
|
|
unpermitted_parameters.action_controller;dur=0.01, start_transaction.active_record;dur=0.01,
|
|
transaction.active_record;dur=6.63, process_action.action_controller;dur=309.37
|
|
vary:
|
|
- Accept
|
|
x-content-type-options:
|
|
- nosniff
|
|
x-frame-options:
|
|
- SAMEORIGIN
|
|
x-permitted-cross-domain-policies:
|
|
- none
|
|
x-request-id:
|
|
- 4ebe01f5-9359-4ce1-be3a-e67d91130a7c
|
|
x-runtime:
|
|
- '0.371201'
|
|
x-xss-protection:
|
|
- 1; mode=block
|
|
status:
|
|
code: 200
|
|
message: OK
|
|
version: 1
|