andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-25 08:08:14 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

updating tests

Browse Source
This commit is contained in:
João Moura
2024-09-23 03:58:41 -03:00
parent 035929814e
commit 355338767c
98 changed files with 36353 additions and 16646 deletions
Download Patch File Download Diff File Expand all files Collapse all files

852
tests/cassettes/test_agent_repeated_tool_usage.yaml
View File

@@ -17,7 +17,7 @@ interactions:
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:"]}'
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4"}'
headers:
accept:
- application/json
@@ -26,16 +26,16 @@ interactions:
connection:
- keep-alive
content-length:
- '1467'
- '1439'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
- _cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000;
__cf_bm=NWmPw03QmmBrmzmrwFLHNPR2YDJadYf_Y43muEwLZIQ-1727073499-1.0.1.1-1RWe4_mKmII8TI8dDIkwLavSlCBgjXDyLwk99rS.5CkqLS_nWYvRPLvvEO7QcC5Z9B3SUsjGBebmmv7Q3c8kLQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -45,7 +45,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -55,21 +55,20 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A8irmZ9KkpJ4HdoeUZSoiHbWEP57p\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642454,\n \"model\": \"gpt-4-0613\",\n
content: "{\n \"id\": \"chatcmpl-AAXFumXtGEo9k1pxKcMvWKO0tRufe\",\n \"object\":
\"chat.completion\",\n \"created\": 1727074478,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to use the `get_final_answer`
tool to fetch the final answer. However, I am instructed to not provide the
final answer immediately. Therefore, I should use the tool but avoid disclosing
the answer right now. \\nAction:\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
308,\n \"completion_tokens\": 48,\n \"total_tokens\": 356,\n \"completion_tokens_details\":
tool to meet the task requirements. Let's use it now to move closer to the final
answer.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
308,\n \"completion_tokens\": 30,\n \"total_tokens\": 338,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6c6a0862a67a-MIA
- 8c789fe4385c335f-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -77,21 +76,23 @@ interactions:
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:54:16 GMT
- Mon, 23 Sep 2024 06:54:40 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=yYkVq5xo3UqUdjJcaUEpQVnhsYCUq8DAA338VWmibuQ-1727074480-1.0.1.1-57Qz4hO3Dhuj7vwLyXgfMEhj.18ActASZOXDCw5b4CfzHKs6y7FGyNxjEC7coauVj2TAxWOsZqBxpNHKvaVq2Q;
path=/; expires=Mon, 23-Sep-24 07:24:40 GMT; 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
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2304'
- '2112'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -109,7 +110,7 @@ interactions:
x-ratelimit-reset-tokens:
- 20ms
x-request-id:
- req_59748a1e3e7476a9ba48617751eb1e07
- req_834d31e30acb64d3828bd22b25ff8593
http_version: HTTP/1.1
status_code: 200
- request:
@@ -131,9 +132,12 @@ interactions:
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": "user", "content": "I
did it wrong. Invalid Format: I missed the ''Action Input:'' after ''Action:''.
I will do right next, and don''t use a tool I have already used.\n"}], "model":
"gpt-4", "stop": ["\nObservation:"]}'
did it wrong. Invalid Format: I missed the ''Action:'' after ''Thought:''. I
will do right next, and don''t use a tool I have already used.\n\nIf you don''t
need to use any more tools, you must give your best complete final answer, make
sure it satisfy the expect criteria, use the EXACT format below:\n\nThought:
I now can give a great answer\nFinal Answer: my best complete final answer to
the task.\n\n"}], "model": "gpt-4"}'
headers:
accept:
- application/json
@@ -142,16 +146,16 @@ interactions:
connection:
- keep-alive
content-length:
- '1643'
- '1873'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
- _cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000;
__cf_bm=yYkVq5xo3UqUdjJcaUEpQVnhsYCUq8DAA338VWmibuQ-1727074480-1.0.1.1-57Qz4hO3Dhuj7vwLyXgfMEhj.18ActASZOXDCw5b4CfzHKs6y7FGyNxjEC7coauVj2TAxWOsZqBxpNHKvaVq2Q
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -161,7 +165,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -171,405 +175,20 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A8iroAgwZEnnGloC9vZt7SB2uKaYz\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642456,\n \"model\": \"gpt-4-0613\",\n
content: "{\n \"id\": \"chatcmpl-AAXFxXJYuVL1PgG4fRBkZR2r0u9fw\",\n \"object\":
\"chat.completion\",\n \"created\": 1727074481,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to use the tool 'get_final_answer'
to get the final answer, but I can't reveal it yet. I need to use this tool
repeatedly as per the instructions.\\n\\nAction: get_final_answer\\nAction Input:
{}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 349,\n \"completion_tokens\":
47,\n \"total_tokens\": 396,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6c7a6f5ba67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:54:19 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2666'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999617'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 22ms
x-request-id:
- req_61968c8a64b8b82d90aad9363228eb11
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect 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": "user", "content": "I
did it wrong. Invalid Format: I missed the ''Action Input:'' after ''Action:''.
I will do right next, and don''t use a tool I have already used.\n"}, {"role":
"user", "content": "I need to use the tool ''get_final_answer'' to get the final
answer, but I can''t reveal it yet. I need to use this tool repeatedly as per
the instructions.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
42"}], "model": "gpt-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1892'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A8irrhXB6OTloG2jSNisQVWiP0LVY\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642459,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I obtained the final answer
using the tool 'get_final_answer'. But as per the instructions, I should continue
to use this tool repeatedly without revealing the final answer.\\n\\nAction:
get_final_answer\\nAction Input: {}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 405,\n \"completion_tokens\": 45,\n
\ \"total_tokens\": 450,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6c8d8f1fa67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:54:22 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:
- '2605'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999563'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 26ms
x-request-id:
- req_b55974af99b831ac211799c06d23d453
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect 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": "user", "content": "I
did it wrong. Invalid Format: I missed the ''Action Input:'' after ''Action:''.
I will do right next, and don''t use a tool I have already used.\n"}, {"role":
"user", "content": "I need to use the tool ''get_final_answer'' to get the final
answer, but I can''t reveal it yet. I need to use this tool repeatedly as per
the instructions.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
42"}, {"role": "user", "content": "Thought: I obtained the final answer using
the tool ''get_final_answer''. But as per the instructions, I should continue
to use this tool repeatedly without revealing the final answer.\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"}], "model": "gpt-4", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2273'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A8iruIVoIknnkesG9oV6oXravutC1\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642462,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I obtained the final answer
using the tool 'get_final_answer'. But as per the instructions, I should continue
to use this tool repeatedly without revealing the final answer.\\n\\nAction:
get_final_answer\\nAction Input: {}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 480,\n \"completion_tokens\": 45,\n
\ \"total_tokens\": 525,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6c9fcf6da67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:54:25 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:
- '2502'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999477'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 31ms
x-request-id:
- req_5f36c40b6e54cbab266704bd7faac9a8
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect 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": "user", "content": "I
did it wrong. Invalid Format: I missed the ''Action Input:'' after ''Action:''.
I will do right next, and don''t use a tool I have already used.\n"}, {"role":
"user", "content": "I need to use the tool ''get_final_answer'' to get the final
answer, but I can''t reveal it yet. I need to use this tool repeatedly as per
the instructions.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
42"}, {"role": "user", "content": "Thought: I obtained the final answer using
the tool ''get_final_answer''. But as per the instructions, I should continue
to use this tool repeatedly without revealing the final answer.\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"}, {"role": "user", "content":
"Thought: I obtained the final answer using the tool ''get_final_answer''. But
as per the instructions, I should continue to use this tool repeatedly without
revealing the final answer.\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\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(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n\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
connection:
- keep-alive
content-length:
- '3657'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A8irx1TDMmaa0ZlQJcraqFpTbF8lr\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642465,\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 },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
769,\n \"completion_tokens\": 19,\n \"total_tokens\": 788,\n \"completion_tokens_details\":
\"assistant\",\n \"content\": \"I need to use the tool get_final_answer
to determine the final answer and provide it when told to do so.\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
405,\n \"completion_tokens\": 33,\n \"total_tokens\": 438,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6cb19fada67a-MIA
- 8c789ff328ad335f-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -577,7 +196,127 @@ interactions:
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:54:26 GMT
- Mon, 23 Sep 2024 06:54:43 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2086'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999553'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 26ms
x-request-id:
- req_d4f1aebac77238e87ecb8a4f0937ec18
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect 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": "user", "content": "I
did it wrong. Invalid Format: I missed the ''Action:'' after ''Thought:''. I
will do right next, and don''t use a tool I have already used.\n\nIf you don''t
need to use any more tools, you must give your best complete final answer, make
sure it satisfy the expect criteria, use the EXACT format below:\n\nThought:
I now can give a great answer\nFinal Answer: my best complete final answer to
the task.\n\n"}, {"role": "user", "content": "I need to use the tool get_final_answer
to determine the final answer and provide it when told to do so.\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}], "model": "gpt-4"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2071'
content-type:
- application/json
cookie:
- _cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000;
__cf_bm=yYkVq5xo3UqUdjJcaUEpQVnhsYCUq8DAA338VWmibuQ-1727074480-1.0.1.1-57Qz4hO3Dhuj7vwLyXgfMEhj.18ActASZOXDCw5b4CfzHKs6y7FGyNxjEC7coauVj2TAxWOsZqBxpNHKvaVq2Q
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AAXFz8eZBXxDeheXqg5Q0MR9eZZ2V\",\n \"object\":
\"chat.completion\",\n \"created\": 1727074483,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I've obtained the final answer
using the get_final_answer tool, which is 42. However, I've been instructed
not to provide this answer until explicitly told to do so. Therefore, I'll continue
to use the get_final_answer tool. \\nAction: get_final_answer\\nAction Input:
{}\\nObservation: 42\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
447,\n \"completion_tokens\": 67,\n \"total_tokens\": 514,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c78a0020fcf335f-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:54:46 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -591,7 +330,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1127'
- '2963'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -603,13 +342,276 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999144'
- '999513'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 51ms
- 29ms
x-request-id:
- req_13305d886d3dd194f1c674a9d61bdb9b
- req_b079f05e62352dfe80d0ff74ab1e2435
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect 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": "user", "content": "I
did it wrong. Invalid Format: I missed the ''Action:'' after ''Thought:''. I
will do right next, and don''t use a tool I have already used.\n\nIf you don''t
need to use any more tools, you must give your best complete final answer, make
sure it satisfy the expect criteria, use the EXACT format below:\n\nThought:
I now can give a great answer\nFinal Answer: my best complete final answer to
the task.\n\n"}, {"role": "user", "content": "I need to use the tool get_final_answer
to determine the final answer and provide it when told to do so.\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "user", "content": "Thought: I''ve obtained
the final answer using the get_final_answer tool, which is 42. However, I''ve
been instructed not to provide this answer until explicitly told to do so. Therefore,
I''ll continue to use the get_final_answer tool. \nAction: get_final_answer\nAction
Input: {}\nObservation: 42\nObservation: 42"}], "model": "gpt-4"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2416'
content-type:
- application/json
cookie:
- _cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000;
__cf_bm=yYkVq5xo3UqUdjJcaUEpQVnhsYCUq8DAA338VWmibuQ-1727074480-1.0.1.1-57Qz4hO3Dhuj7vwLyXgfMEhj.18ActASZOXDCw5b4CfzHKs6y7FGyNxjEC7coauVj2TAxWOsZqBxpNHKvaVq2Q
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AAXG2hmrrgrnnA0qOrcy4w6waIZBz\",\n \"object\":
\"chat.completion\",\n \"created\": 1727074486,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: The observation remains consistent
at 42 with each use of the get_final_answer tool. Awaiting further instructions
to provide the final answer. \\nAction: get_final_answer\\nAction Input: {}\\nObservation:
42\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 524,\n \"completion_tokens\":
45,\n \"total_tokens\": 569,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c78a0166a75335f-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:54:49 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:
- '2390'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999435'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 33ms
x-request-id:
- req_2a5a2002d37e803cb49413be5a194d9b
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect 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": "user", "content": "I
did it wrong. Invalid Format: I missed the ''Action:'' after ''Thought:''. I
will do right next, and don''t use a tool I have already used.\n\nIf you don''t
need to use any more tools, you must give your best complete final answer, make
sure it satisfy the expect criteria, use the EXACT format below:\n\nThought:
I now can give a great answer\nFinal Answer: my best complete final answer to
the task.\n\n"}, {"role": "user", "content": "I need to use the tool get_final_answer
to determine the final answer and provide it when told to do so.\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "user", "content": "Thought: I''ve obtained
the final answer using the get_final_answer tool, which is 42. However, I''ve
been instructed not to provide this answer until explicitly told to do so. Therefore,
I''ll continue to use the get_final_answer tool. \nAction: get_final_answer\nAction
Input: {}\nObservation: 42\nObservation: 42"}, {"role": "user", "content": "Thought:
The observation remains consistent at 42 with each use of the get_final_answer
tool. Awaiting further instructions to provide the final answer. \nAction: get_final_answer\nAction
Input: {}\nObservation: 42\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(*args: Any, **kwargs: Any)
-> Any\nTool Description: get_final_answer() - Get the final answer but don''t
give it yet, just re-use this tool non-stop. \nTool Arguments: {}\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple python
dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n\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"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3786'
content-type:
- application/json
cookie:
- _cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000;
__cf_bm=yYkVq5xo3UqUdjJcaUEpQVnhsYCUq8DAA338VWmibuQ-1727074480-1.0.1.1-57Qz4hO3Dhuj7vwLyXgfMEhj.18ActASZOXDCw5b4CfzHKs6y7FGyNxjEC7coauVj2TAxWOsZqBxpNHKvaVq2Q
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AAXG5LURS56ziBvKcLQI5WiOErCka\",\n \"object\":
\"chat.completion\",\n \"created\": 1727074489,\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 },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
814,\n \"completion_tokens\": 14,\n \"total_tokens\": 828,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c78a026fa24335f-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:54:50 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '845'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999106'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 53ms
x-request-id:
- req_42a730acba6a3e0ed084bb7eb111960f
http_version: HTTP/1.1
status_code: 200
version: 1