andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-02 07:42:40 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Bringing support to o1 family back + any models that don't support stop words

Browse Source
This commit is contained in:
João Moura
2024-09-24 22:18:20 -03:00
parent b8aa46a767
commit e19bdcb97d
104 changed files with 56051 additions and 65319 deletions
Download Patch File Download Diff File Expand all files Collapse all files

336
tests/cassettes/test_agent_respect_the_max_rpm_set.yaml
View File

@@ -30,8 +30,8 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=4rzJDR3F8S3Dp4B_qwylZU0mdm_WUwmv8vNHHp3IplM-1727119501-1.0.1.1-qobO_Sf88yG1qtXFnLgykvyc9YXR_fm1J7ZpXIhvtynVnsz67Uwcf4122PgHs4GMrlvZMaL6z_UVcVYSYUJOKQ;
_cfuvid=9K_ipT1uTVyDTneB1W5OZHPxCh36aOsDZCBnsQTONqQ-1727119501207-0.0.1.1-604800000
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
@@ -55,20 +55,20 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AAj0Q1CmjSLQ7WYLhiIqJNThKF8AI\",\n \"object\":
\"chat.completion\",\n \"created\": 1727119646,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AB7NqbL5212OzckjAUiwsFYMK0vAz\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213354,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to use the `get_final_answer`
tool repeatedly as specified. \\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\": 298,\n \"completion_tokens\":
26,\n \"total_tokens\": 324,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
\"assistant\",\n \"content\": \"I need to use the tool `get_final_answer`
as instructed and keep using it repeatedly.\\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\":
298,\n \"completion_tokens\": 29,\n \"total_tokens\": 327,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7cee9a29a5228a-MIA
- 8c85de66cffe1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
@@ -76,7 +76,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 19:27:26 GMT
- Tue, 24 Sep 2024 21:29:15 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -88,11 +88,11 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '384'
- '413'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
@@ -106,7 +106,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2b8f087282d5891bccb641764e947a3c
- req_48fe3362ef1295d84323dc3a383f9fee
http_version: HTTP/1.1
status_code: 200
- request:
@@ -127,9 +127,9 @@ interactions:
is the expect criteria for your final answer: The final answer\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "user", "content": "I need to
use the `get_final_answer` tool repeatedly as specified. \n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}], "model": "gpt-4o"}'
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need
to use the tool `get_final_answer` as instructed and keep using it repeatedly.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
@@ -138,12 +138,12 @@ interactions:
connection:
- keep-alive
content-length:
- '1599'
- '1622'
content-type:
- application/json
cookie:
- __cf_bm=4rzJDR3F8S3Dp4B_qwylZU0mdm_WUwmv8vNHHp3IplM-1727119501-1.0.1.1-qobO_Sf88yG1qtXFnLgykvyc9YXR_fm1J7ZpXIhvtynVnsz67Uwcf4122PgHs4GMrlvZMaL6z_UVcVYSYUJOKQ;
_cfuvid=9K_ipT1uTVyDTneB1W5OZHPxCh36aOsDZCBnsQTONqQ-1727119501207-0.0.1.1-604800000
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
@@ -167,20 +167,20 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AAj0RYK4ZfXp0YZkFg3Ep6jlID6L3\",\n \"object\":
\"chat.completion\",\n \"created\": 1727119647,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AB7NroAwKV3FWwX0hG5iKpMggeiPW\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213355,\n \"model\": \"gpt-4o-2024-05-13\",\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 instructed.\\n\\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\":
332,\n \"completion_tokens\": 32,\n \"total_tokens\": 364,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
tool as instructed.\\n\\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\": 335,\n \"completion_tokens\":
26,\n \"total_tokens\": 361,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7ceea29c7a228a-MIA
- 8c85de6d78d81cf3-GRU
Connection:
- keep-alive
Content-Encoding:
@@ -188,7 +188,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 19:27:28 GMT
- Tue, 24 Sep 2024 21:29:16 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -200,11 +200,11 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '438'
- '401'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
@@ -212,13 +212,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999622'
- '29999618'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a1d19147e5a3fdbe7143d1d6706fba7e
- req_06c4d6bae443c6c294613e10b5bceb4e
http_version: HTTP/1.1
status_code: 200
- request:
@@ -239,11 +239,12 @@ interactions:
is the expect criteria for your final answer: The final answer\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "user", "content": "I need to
use the `get_final_answer` tool repeatedly as specified. \n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "user", "content": "Thought: I need to
continue using the `get_final_answer` tool, as instructed.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42\nObservation: 42"}], "model": "gpt-4o"}'
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need
to use the tool `get_final_answer` as instructed and keep using it repeatedly.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42"}, {"role": "assistant",
"content": "Thought: I need to continue using the tool as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42\nObservation: 42"}], "model":
"gpt-4o"}'
headers:
accept:
- application/json
@@ -252,12 +253,12 @@ interactions:
connection:
- keep-alive
content-length:
- '1789'
- '1797'
content-type:
- application/json
cookie:
- __cf_bm=4rzJDR3F8S3Dp4B_qwylZU0mdm_WUwmv8vNHHp3IplM-1727119501-1.0.1.1-qobO_Sf88yG1qtXFnLgykvyc9YXR_fm1J7ZpXIhvtynVnsz67Uwcf4122PgHs4GMrlvZMaL6z_UVcVYSYUJOKQ;
_cfuvid=9K_ipT1uTVyDTneB1W5OZHPxCh36aOsDZCBnsQTONqQ-1727119501207-0.0.1.1-604800000
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
@@ -281,21 +282,20 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AAj0S9ezJuIW1m7Wg1xinFCaD23EQ\",\n \"object\":
\"chat.completion\",\n \"created\": 1727119648,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AB7NsgjKb0w7N1KemjH6bXSBQ77CI\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213356,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to continue following
the instructions by repeatedly using the `get_final_answer` tool.\\n\\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\": 373,\n \"completion_tokens\":
34,\n \"total_tokens\": 407,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
the instructions and keep using the tool.\\n\\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\":
370,\n \"completion_tokens\": 29,\n \"total_tokens\": 399,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7ceea9ad38228a-MIA
- 8c85de7419161cf3-GRU
Connection:
- keep-alive
Content-Encoding:
@@ -303,7 +303,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 19:27:29 GMT
- Tue, 24 Sep 2024 21:29:16 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -315,11 +315,11 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '484'
- '446'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
@@ -333,7 +333,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2dea80621ae6682506fb311d99a74baa
- req_66d88cd50cb691cde93764fff19bec21
http_version: HTTP/1.1
status_code: 200
- request:
@@ -354,25 +354,26 @@ interactions:
is the expect criteria for your final answer: The final answer\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "user", "content": "I need to
use the `get_final_answer` tool repeatedly as specified. \n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "user", "content": "Thought: I need to
continue using the `get_final_answer` tool, as instructed.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42\nObservation: 42"}, {"role": "user", "content": "Thought:
I need to continue following the instructions by repeatedly using the `get_final_answer`
tool.\n\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"}], "model": "gpt-4o"}'
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need
to use the tool `get_final_answer` as instructed and keep using it repeatedly.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42"}, {"role": "assistant",
"content": "Thought: I need to continue using the tool as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42\nObservation: 42"}, {"role":
"assistant", "content": "Thought: I need to continue following the instructions
and keep using the tool.\n\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"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
@@ -381,12 +382,12 @@ interactions:
connection:
- keep-alive
content-length:
- '2937'
- '2926'
content-type:
- application/json
cookie:
- __cf_bm=4rzJDR3F8S3Dp4B_qwylZU0mdm_WUwmv8vNHHp3IplM-1727119501-1.0.1.1-qobO_Sf88yG1qtXFnLgykvyc9YXR_fm1J7ZpXIhvtynVnsz67Uwcf4122PgHs4GMrlvZMaL6z_UVcVYSYUJOKQ;
_cfuvid=9K_ipT1uTVyDTneB1W5OZHPxCh36aOsDZCBnsQTONqQ-1727119501207-0.0.1.1-604800000
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
@@ -410,20 +411,20 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AAj0TExB2AAoCYadk6uNFrcB0Qdth\",\n \"object\":
\"chat.completion\",\n \"created\": 1727119649,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AB7Nt75000jvCcyx5QWcIG6FiV9vZ\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213357,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to continue using the
`get_final_answer` tool without making up any new tools.\\n\\nAction: get_final_answer\\nAction
\"assistant\",\n \"content\": \"Thought: I should continue as the task
requires me to reuse the tool non-stop. \\n\\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\":
613,\n \"completion_tokens\": 35,\n \"total_tokens\": 648,\n \"completion_tokens_details\":
605,\n \"completion_tokens\": 32,\n \"total_tokens\": 637,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7ceeb14ea4228a-MIA
- 8c85de793ffa1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
@@ -431,7 +432,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 19:27:30 GMT
- Tue, 24 Sep 2024 21:29:18 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -443,11 +444,11 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '496'
- '522'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
@@ -455,13 +456,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999311'
- '29999317'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_a130d9ff32611670bf15d3cc216fde8c
- req_ed0a43177ad54ded634defcdd87d4149
http_version: HTTP/1.1
status_code: 200
- request:
@@ -482,29 +483,30 @@ interactions:
is the expect criteria for your final answer: The final answer\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "user", "content": "I need to
use the `get_final_answer` tool repeatedly as specified. \n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "user", "content": "Thought: I need to
continue using the `get_final_answer` tool, as instructed.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42\nObservation: 42"}, {"role": "user", "content": "Thought:
I need to continue following the instructions by repeatedly using the `get_final_answer`
tool.\n\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"}, {"role": "user", "content":
"Thought: I need to continue using the `get_final_answer` tool without making
up any new tools.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need
to use the tool `get_final_answer` as instructed and keep using it repeatedly.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42"}, {"role": "assistant",
"content": "Thought: I need to continue using the tool as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42\nObservation: 42"}, {"role":
"assistant", "content": "Thought: I need to continue following the instructions
and keep using the tool.\n\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"}], "model": "gpt-4o"}'
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"}, {"role": "assistant", "content": "Thought: I should continue as
the task requires me to reuse the tool non-stop. \n\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"}], "model":
"gpt-4o"}'
headers:
accept:
- application/json
@@ -513,12 +515,12 @@ interactions:
connection:
- keep-alive
content-length:
- '3247'
- '3226'
content-type:
- application/json
cookie:
- __cf_bm=4rzJDR3F8S3Dp4B_qwylZU0mdm_WUwmv8vNHHp3IplM-1727119501-1.0.1.1-qobO_Sf88yG1qtXFnLgykvyc9YXR_fm1J7ZpXIhvtynVnsz67Uwcf4122PgHs4GMrlvZMaL6z_UVcVYSYUJOKQ;
_cfuvid=9K_ipT1uTVyDTneB1W5OZHPxCh36aOsDZCBnsQTONqQ-1727119501207-0.0.1.1-604800000
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
@@ -542,21 +544,20 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AAj0UcIMY2Re9VHijcc4OanswMF0v\",\n \"object\":
\"chat.completion\",\n \"created\": 1727119650,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AB7NuCunlabpv4mHCdqZh2IqILmMj\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213358,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: According to the instructions,
I must continue using the `get_final_answer` tool. I should not create new tools
and should follow the format closely.\\n\\nAction: get_final_answer\\nAction
\"assistant\",\n \"content\": \"Thought: Continuously reusing the tool
is the key here, so I will keep doing it.\\n\\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\":
677,\n \"completion_tokens\": 46,\n \"total_tokens\": 723,\n \"completion_tokens_details\":
666,\n \"completion_tokens\": 34,\n \"total_tokens\": 700,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7ceeb6bdbe228a-MIA
- 8c85de816b041cf3-GRU
Connection:
- keep-alive
Content-Encoding:
@@ -564,7 +565,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 19:27:31 GMT
- Tue, 24 Sep 2024 21:29:19 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -576,11 +577,11 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '587'
- '497'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
@@ -588,13 +589,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999241'
- '29999251'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_45810d9103d53b59ee3490c43bcf95b0
- req_4dcd680e6ac1ca48ac20d2e6397847d2
http_version: HTTP/1.1
status_code: 200
- request:
@@ -615,36 +616,35 @@ interactions:
is the expect criteria for your final answer: The final answer\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "user", "content": "I need to
use the `get_final_answer` tool repeatedly as specified. \n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42"}, {"role": "user", "content": "Thought: I need to
continue using the `get_final_answer` tool, as instructed.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42\nObservation: 42"}, {"role": "user", "content": "Thought:
I need to continue following the instructions by repeatedly using the `get_final_answer`
tool.\n\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"}, {"role": "user", "content":
"Thought: I need to continue using the `get_final_answer` tool without making
up any new tools.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need
to use the tool `get_final_answer` as instructed and keep using it repeatedly.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42"}, {"role": "assistant",
"content": "Thought: I need to continue using the tool as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42\nObservation: 42"}, {"role":
"assistant", "content": "Thought: I need to continue following the instructions
and keep using the tool.\n\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"}, {"role": "user", "content":
"Thought: According to the instructions, I must continue using the `get_final_answer`
tool. I should not create new tools and should follow the format closely.\n\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\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"}'
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"}, {"role": "assistant", "content": "Thought: I should continue as
the task requires me to reuse the tool non-stop. \n\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"}, {"role":
"assistant", "content": "Thought: Continuously reusing the tool is the key here,
so I will keep doing it.\n\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\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"}'
headers:
accept:
- application/json
@@ -653,12 +653,12 @@ interactions:
connection:
- keep-alive
content-length:
- '3795'
- '3701'
content-type:
- application/json
cookie:
- __cf_bm=4rzJDR3F8S3Dp4B_qwylZU0mdm_WUwmv8vNHHp3IplM-1727119501-1.0.1.1-qobO_Sf88yG1qtXFnLgykvyc9YXR_fm1J7ZpXIhvtynVnsz67Uwcf4122PgHs4GMrlvZMaL6z_UVcVYSYUJOKQ;
_cfuvid=9K_ipT1uTVyDTneB1W5OZHPxCh36aOsDZCBnsQTONqQ-1727119501207-0.0.1.1-604800000
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
@@ -682,19 +682,19 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AAj0Vyy3vi6ebJ5x0H0NGtDcEIh9r\",\n \"object\":
\"chat.completion\",\n \"created\": 1727119651,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AB7Nwnc0ceyQDceN6OUQsj3k97yVq\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213360,\n \"model\": \"gpt-4o-2024-05-13\",\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\":
784,\n \"completion_tokens\": 14,\n \"total_tokens\": 798,\n \"completion_tokens_details\":
Answer: The final answer is 42.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
761,\n \"completion_tokens\": 19,\n \"total_tokens\": 780,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c7ceebcbd58228a-MIA
- 8c85de89ef191cf3-GRU
Connection:
- keep-alive
Content-Encoding:
@@ -702,7 +702,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 19:27:31 GMT
- Tue, 24 Sep 2024 21:29:20 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -714,11 +714,11 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '252'
- '340'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
@@ -726,13 +726,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999114'
- '29999144'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_bd411ea9640c0641ccf6e7880f8df442
- req_040cf33af36004cd6409d695444c2d2b
http_version: HTTP/1.1
status_code: 200
version: 1