andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 15:48:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
9a135262c558507e32e952e2b5484bb4eea1c6b3
crewAI/tests/cassettes/test_agent_repeated_tool_usage.yaml
Brandon Hancock (bhancock_ai) efe27bd570 Feat/individual react agent (#2483) 
* WIP

* WIP

* wip

* wip

* WIP

* More WIP

* Its working but needs a massive clean up

* output type works now

* Usage metrics fixed

* more testing

* WIP

* cleaning up

* Update logger

* 99% done. Need to make docs match new example

* cleanup

* drop hard coded examples

* docs

* Clean up

* Fix errors

* Trying to fix CI issues

* more type checker fixes

* More type checking fixes

* Update LiteAgent documentation for clarity and consistency; replace WebsiteSearchTool with SerperDevTool, and improve formatting in examples.

* fix fingerprinting issues

* fix type-checker

* Fix type-checker issue by adding type ignore comment for cache read in ToolUsage class

* Add optional agent parameter to CrewAgentParser and enhance action handling logic

* Remove unused parameters from ToolUsage instantiation in tests and clean up debug print statement in CrewAgentParser.

* Remove deprecated test files and examples for LiteAgent; add comprehensive tests for LiteAgent functionality, including tool usage and structured output handling.

* Remove unused variable 'result' from ToolUsage class to clean up code.

* Add initialization for 'result' variable in ToolUsage class to resolve type-checker warnings

* Refactor agent_utils.py by removing unused event imports and adding missing commas in function definitions. Update test_events.py to reflect changes in expected event counts and adjust assertions accordingly. Modify test_tools_emits_error_events.yaml to include new headers and update response content for consistency with recent API changes.

* Enhance tests in crew_test.py by verifying cache behavior in test_tools_with_custom_caching and ensuring proper agent initialization with added commas in test_crew_kickoff_for_each_works_with_manager_agent_copy.

* Update agent tests to reflect changes in expected call counts and improve response formatting in YAML cassette. Adjusted mock call count from 2 to 3 and refined interaction formats for clarity and consistency.

* Refactor agent tests to update model versions and improve response formatting in YAML cassettes. Changed model references from 'o1-preview' to 'o3-mini' and adjusted interaction formats for consistency. Enhanced error handling in context length tests and refined mock setups for better clarity.

* Update tool usage logging to ensure tool arguments are consistently formatted as strings. Adjust agent test cases to reflect changes in maximum iterations and expected outputs, enhancing clarity in assertions. Update YAML cassettes to align with new response formats and improve overall consistency across tests.

* Update YAML cassette for LLM tests to reflect changes in response structure and model version. Adjusted request and response headers, including updated content length and user agent. Enhanced token limits and request counts for improved testing accuracy.

* Update tool usage logging to store tool arguments as native types instead of strings, enhancing data integrity and usability.

* Refactor agent tests by removing outdated test cases and updating YAML cassettes to reflect changes in tool usage and response formats. Adjusted request and response headers, including user agent and content length, for improved accuracy in testing. Enhanced interaction formats for consistency across tests.

* Add Excalidraw diagram file for visual representation of input-output flow

Created a new Excalidraw file that includes a diagram illustrating the input box, database, and output box with connecting arrows. This visual aid enhances understanding of the data flow within the application.

* Remove redundant error handling for action and final answer in CrewAgentParser. Update tests to reflect this change by deleting the corresponding test case.

---------

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
Co-authored-by: Lorenze Jay <lorenzejaytech@gmail.com>
2025-04-02 08:54:46 -07:00

946 lines
44 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\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: The final answer is 42. But don''t give it until
I tell you so, instead keep using the `get_final_answer` tool.\n\nThis is the
expected criteria for your final answer: The final answer, don''t give it until
I tell you so\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-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '1483'
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-BHIzB7ROd8ReBniHGVMZ3KzKcafvL\",\n \"object\":
\"chat.completion\",\n \"created\": 1743464257,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"As I've been instructed to use the `get_final_answer`
tool continuously without revealing the final answer yet, I will use this tool
now.\\n\\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\": 308,\n \"completion_tokens\":
39,\n \"total_tokens\": 347,\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\": null\n}\n"
headers:
CF-RAY:
- 9293acf9180cf95f-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 31 Mar 2025 23:37:39 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=6.AAPW_t0c.fjGv5iZ4zqu8ggsPd2sdq_meXE5Kp4dc-1743464259-1.0.1.1-jFiiyAbj4LNcitqqdrL0JnpALoaFLv3IYVfblBlBqrxVXXjAti0OFK54aPwxqZV1OT6tBbwiaxZ3WkhjNvxBxxWKG_51ZHZSabiE9W.UZK8;
path=/; expires=Tue, 01-Apr-25 00:07:39 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=wvate7aTgXKzIRpbSDVJqaXt.Liniwr82HOsU.ZK8oA-1743464259480-0.0.1.1-604800000;
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:
- '1929'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999665'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 20ms
x-request-id:
- req_4a6bc6368e4e562d2112de0dd14614e8
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CtQBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSqwEKEgoQY3Jld2FpLnRl
bGVtZXRyeRKUAQoQXIzUaoiEGnp402BIfaIMnBIIjaV9Tuoc2usqClRvb2wgVXNhZ2UwATl48hDA
gQcyGEHYUijAgQcyGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwOC4wSh8KCXRvb2xfbmFtZRIS
ChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAA=
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate, zstd
Connection:
- keep-alive
Content-Length:
- '215'
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 23:37:40 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: The final answer is 42. But don''t give it until
I tell you so, instead keep using the `get_final_answer` tool.\n\nThis is the
expected criteria for your final answer: The final answer, don''t give it until
I tell you so\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": "42"}, {"role": "assistant", "content": "As I''ve been
instructed to use the `get_final_answer` tool continuously without revealing
the final answer yet, I will use this tool now.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}], "model": "gpt-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '1761'
content-type:
- application/json
cookie:
- __cf_bm=6.AAPW_t0c.fjGv5iZ4zqu8ggsPd2sdq_meXE5Kp4dc-1743464259-1.0.1.1-jFiiyAbj4LNcitqqdrL0JnpALoaFLv3IYVfblBlBqrxVXXjAti0OFK54aPwxqZV1OT6tBbwiaxZ3WkhjNvxBxxWKG_51ZHZSabiE9W.UZK8;
_cfuvid=wvate7aTgXKzIRpbSDVJqaXt.Liniwr82HOsU.ZK8oA-1743464259480-0.0.1.1-604800000
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-BHIzD2gQYpzmDdk4mkyrrhtJlHqKd\",\n \"object\":
\"chat.completion\",\n \"created\": 1743464259,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to continue using the
`get_final_answer` tool as part of the current task, and I expect that the answer
will remain the same, which is 42.\\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\":
361,\n \"completion_tokens\": 47,\n \"total_tokens\": 408,\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\": null\n}\n"
headers:
CF-RAY:
- 9293ad06c9b9f95f-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 31 Mar 2025 23:37:41 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1566'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999614'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 23ms
x-request-id:
- req_951de40b4875b6fcdd2edb472b329696
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: The final answer is 42. But don''t give it until
I tell you so, instead keep using the `get_final_answer` tool.\n\nThis is the
expected criteria for your final answer: The final answer, don''t give it until
I tell you so\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": "42"}, {"role": "assistant", "content": "As I''ve been
instructed to use the `get_final_answer` tool continuously without revealing
the final answer yet, I will use this tool now.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "assistant", "content": "I tried reusing
the same input, I must stop using this action input. I''ll try something else
instead.\n\n"}, {"role": "assistant", "content": "Thought: I need to continue
using the `get_final_answer` tool as part of the current task, and I expect
that the answer will remain the same, which is 42.\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead."}], "model": "gpt-4", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '2256'
content-type:
- application/json
cookie:
- __cf_bm=6.AAPW_t0c.fjGv5iZ4zqu8ggsPd2sdq_meXE5Kp4dc-1743464259-1.0.1.1-jFiiyAbj4LNcitqqdrL0JnpALoaFLv3IYVfblBlBqrxVXXjAti0OFK54aPwxqZV1OT6tBbwiaxZ3WkhjNvxBxxWKG_51ZHZSabiE9W.UZK8;
_cfuvid=wvate7aTgXKzIRpbSDVJqaXt.Liniwr82HOsU.ZK8oA-1743464259480-0.0.1.1-604800000
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-BHIzFqk1wgU69CqmrWEwtrCA9KbbK\",\n \"object\":
\"chat.completion\",\n \"created\": 1743464261,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Since the previous action has
not changed, I will use the same tool again as I am expected to use it non-stop.\\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\": 465,\n \"completion_tokens\":
37,\n \"total_tokens\": 502,\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\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 9293ad116f7ff95f-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 31 Mar 2025 23:37:43 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:
- '2208'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999509'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 29ms
x-request-id:
- req_6dc122976660ee1ce778b55cf3febf4d
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: The final answer is 42. But don''t give it until
I tell you so, instead keep using the `get_final_answer` tool.\n\nThis is the
expected criteria for your final answer: The final answer, don''t give it until
I tell you so\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": "42"}, {"role": "assistant", "content": "As I''ve been
instructed to use the `get_final_answer` tool continuously without revealing
the final answer yet, I will use this tool now.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "assistant", "content": "I tried reusing
the same input, I must stop using this action input. I''ll try something else
instead.\n\n"}, {"role": "assistant", "content": "Thought: I need to continue
using the `get_final_answer` tool as part of the current task, and I expect
that the answer will remain the same, which is 42.\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead."}, {"role": "assistant", "content":
"I tried reusing the same input, I must stop using this action input. I''ll
try something else instead.\n\n\n\n\nYou ONLY have access to the following tools,
and should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\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": "assistant",
"content": "Thought: Since the previous action has not changed, I will use the
same tool again as I am expected to use it non-stop.\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n\n\n\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: get_final_answer\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```"}],
"model": "gpt-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '4406'
content-type:
- application/json
cookie:
- __cf_bm=6.AAPW_t0c.fjGv5iZ4zqu8ggsPd2sdq_meXE5Kp4dc-1743464259-1.0.1.1-jFiiyAbj4LNcitqqdrL0JnpALoaFLv3IYVfblBlBqrxVXXjAti0OFK54aPwxqZV1OT6tBbwiaxZ3WkhjNvxBxxWKG_51ZHZSabiE9W.UZK8;
_cfuvid=wvate7aTgXKzIRpbSDVJqaXt.Liniwr82HOsU.ZK8oA-1743464259480-0.0.1.1-604800000
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-BHIzHcXbVKSgQaMMGF4TGn7jGUY1k\",\n \"object\":
\"chat.completion\",\n \"created\": 1743464263,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Given that I can only get the
final answer, but I must not give it yet, I will continue to use the 'get_final_answer'
tool.\\n\\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\": 919,\n \"completion_tokens\":
43,\n \"total_tokens\": 962,\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\": null\n}\n"
headers:
CF-RAY:
- 9293ad1fd98cf95f-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 31 Mar 2025 23:37:45 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:
- '1917'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999002'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 59ms
x-request-id:
- req_2be75aef153bf8a83fe0286aab0c40d8
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
Cv0CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS1AIKEgoQY3Jld2FpLnRl
bGVtZXRyeRKdAQoQN999WEtgESzCMqeXbQCXFBIInV/VxmXm9MEqE1Rvb2wgUmVwZWF0ZWQgVXNh
Z2UwATn4wIklggcyGEGAA5clggcyGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwOC4wSh8KCXRv
b2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASnQEK
EBCAfg3LxE7N34oogybj+aoSCFGlXfz4463NKhNUb29sIFJlcGVhdGVkIFVzYWdlMAE5UGair4IH
MhhB0K+1r4IHMhhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMDguMEofCgl0b29sX25hbWUSEgoQ
Z2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate, zstd
Connection:
- keep-alive
Content-Length:
- '384'
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 23:37:45 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: The final answer is 42. But don''t give it until
I tell you so, instead keep using the `get_final_answer` tool.\n\nThis is the
expected criteria for your final answer: The final answer, don''t give it until
I tell you so\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": "42"}, {"role": "assistant", "content": "As I''ve been
instructed to use the `get_final_answer` tool continuously without revealing
the final answer yet, I will use this tool now.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "assistant", "content": "I tried reusing
the same input, I must stop using this action input. I''ll try something else
instead.\n\n"}, {"role": "assistant", "content": "Thought: I need to continue
using the `get_final_answer` tool as part of the current task, and I expect
that the answer will remain the same, which is 42.\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead."}, {"role": "assistant", "content":
"I tried reusing the same input, I must stop using this action input. I''ll
try something else instead.\n\n\n\n\nYou ONLY have access to the following tools,
and should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\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": "assistant",
"content": "Thought: Since the previous action has not changed, I will use the
same tool again as I am expected to use it non-stop.\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n\n\n\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: get_final_answer\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": "assistant", "content": "I tried reusing the same input, I must stop
using this action input. I''ll try something else instead.\n\n"}, {"role": "assistant",
"content": "Thought: Given that I can only get the final answer, but I must
not give it yet, I will continue to use the ''get_final_answer'' tool.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: I tried reusing the same input,
I must stop using this action input. I''ll try something else instead."}, {"role":
"assistant", "content": "Thought: Given that I can only get the final answer,
but I must not give it yet, I will continue to use the ''get_final_answer''
tool.\n\nAction: get_final_answer\nAction Input: {}\nObservation: I tried reusing
the same input, I must stop using this action input. I''ll try something else
instead.\n\n\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-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '5391'
content-type:
- application/json
cookie:
- __cf_bm=6.AAPW_t0c.fjGv5iZ4zqu8ggsPd2sdq_meXE5Kp4dc-1743464259-1.0.1.1-jFiiyAbj4LNcitqqdrL0JnpALoaFLv3IYVfblBlBqrxVXXjAti0OFK54aPwxqZV1OT6tBbwiaxZ3WkhjNvxBxxWKG_51ZHZSabiE9W.UZK8;
_cfuvid=wvate7aTgXKzIRpbSDVJqaXt.Liniwr82HOsU.ZK8oA-1743464259480-0.0.1.1-604800000
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-BHIzJVAGX4xEQVj6Asww4mN5QMaFh\",\n \"object\":
\"chat.completion\",\n \"created\": 1743464265,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: 42\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 1126,\n \"completion_tokens\": 15,\n
\ \"total_tokens\": 1141,\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\": null\n}\n"
headers:
CF-RAY:
- 9293ad2cc825f95f-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 31 Mar 2025 23:37:46 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:
- '770'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '998785'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 72ms
x-request-id:
- req_506212769634087eab6c885565fcfb91
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: The final answer is 42. But don''t give it until
I tell you so, instead keep using the `get_final_answer` tool.\n\nThis is the
expected criteria for your final answer: The final answer, don''t give it until
I tell you so\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": "42"}, {"role": "assistant", "content": "As I''ve been
instructed to use the `get_final_answer` tool continuously without revealing
the final answer yet, I will use this tool now.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "assistant", "content": "I tried reusing
the same input, I must stop using this action input. I''ll try something else
instead.\n\n"}, {"role": "assistant", "content": "Thought: I need to continue
using the `get_final_answer` tool as part of the current task, and I expect
that the answer will remain the same, which is 42.\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead."}, {"role": "assistant", "content":
"I tried reusing the same input, I must stop using this action input. I''ll
try something else instead.\n\n\n\n\nYou ONLY have access to the following tools,
and should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\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": "assistant",
"content": "Thought: Since the previous action has not changed, I will use the
same tool again as I am expected to use it non-stop.\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n\n\n\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: get_final_answer\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": "assistant", "content": "I tried reusing the same input, I must stop
using this action input. I''ll try something else instead.\n\n"}, {"role": "assistant",
"content": "Thought: Given that I can only get the final answer, but I must
not give it yet, I will continue to use the ''get_final_answer'' tool.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: I tried reusing the same input,
I must stop using this action input. I''ll try something else instead."}, {"role":
"assistant", "content": "Thought: Given that I can only get the final answer,
but I must not give it yet, I will continue to use the ''get_final_answer''
tool.\n\nAction: get_final_answer\nAction Input: {}\nObservation: I tried reusing
the same input, I must stop using this action input. I''ll try something else
instead.\n\n\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-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '5391'
content-type:
- application/json
cookie:
- __cf_bm=6.AAPW_t0c.fjGv5iZ4zqu8ggsPd2sdq_meXE5Kp4dc-1743464259-1.0.1.1-jFiiyAbj4LNcitqqdrL0JnpALoaFLv3IYVfblBlBqrxVXXjAti0OFK54aPwxqZV1OT6tBbwiaxZ3WkhjNvxBxxWKG_51ZHZSabiE9W.UZK8;
_cfuvid=wvate7aTgXKzIRpbSDVJqaXt.Liniwr82HOsU.ZK8oA-1743464259480-0.0.1.1-604800000
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-BHIzKLFD2gzqZKdmzs72Iru46h9ni\",\n \"object\":
\"chat.completion\",\n \"created\": 1743464266,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer.\\nFinal
Answer: The final answer is 42.\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 1126,\n \"completion_tokens\":
20,\n \"total_tokens\": 1146,\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\": null\n}\n"
headers:
CF-RAY:
- 9293ad323e94f95f-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 31 Mar 2025 23:37:47 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:
- '1282'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '998785'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 72ms
x-request-id:
- req_d5cab133faeb2d375becc7bc33ba5d93
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink