Updating all cassetes

This commit is contained in:
João Moura
2024-09-18 04:17:41 -03:00
parent d7473edb41
commit 5a3b888f43
86 changed files with 14978 additions and 14587 deletions

View File

@@ -30,12 +30,12 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __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 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -45,7 +45,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -55,21 +55,21 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81cWlVtV5ekOB5c9azdzBW40yEFC\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476216,\n \"model\": \"gpt-4-0613\",\n
content: "{\n \"id\": \"chatcmpl-A8irmZ9KkpJ4HdoeUZSoiHbWEP57p\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642454,\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 generate the final answer but I should not give the final answer yet.
I will use the tool constantly until I am told to provide the final response.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 308,\n \"completion_tokens\":
42,\n \"total_tokens\": 350,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
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\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f91e2e8d62233-MIA
- 8c4f6c6a0862a67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -77,7 +77,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:39 GMT
- Wed, 18 Sep 2024 06:54:16 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -91,7 +91,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2141'
- '2304'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -109,7 +109,7 @@ interactions:
x-ratelimit-reset-tokens:
- 20ms
x-request-id:
- req_92057a976dd36d0b40261eb3603f4971
- req_59748a1e3e7476a9ba48617751eb1e07
http_version: HTTP/1.1
status_code: 200
- request:
@@ -130,13 +130,10 @@ 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:"}, {"role": "assistant", "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"}], "model": "gpt-4", "stop": ["\nObservation:"]}'
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:"]}'
headers:
accept:
- application/json
@@ -145,16 +142,16 @@ interactions:
connection:
- keep-alive
content-length:
- '1906'
- '1643'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __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 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -164,7 +161,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -174,21 +171,21 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81cZcHeshIeHD88EFdOWuwEQcQRE\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476219,\n \"model\": \"gpt-4-0613\",\n
content: "{\n \"id\": \"chatcmpl-A8iroAgwZEnnGloC9vZt7SB2uKaYz\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642456,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to keep using the `get_final_answer`
tool until told otherwise. However, I don't have any specific input for the
tool at the moment. \\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\":
43,\n \"total_tokens\": 448,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
\"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:
- 8c3f91f21cf02233-MIA
- 8c4f6c7a6f5ba67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -196,7 +193,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:41 GMT
- Wed, 18 Sep 2024 06:54:19 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -210,7 +207,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1965'
- '2666'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -222,13 +219,133 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999553'
- '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_7f85a269238f0bef62e175fc1c8fd9d3
- req_b55974af99b831ac211799c06d23d453
http_version: HTTP/1.1
status_code: 200
- request:
@@ -249,16 +366,18 @@ 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:"}, {"role": "assistant", "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": "assistant", "content": "I need to keep using the
`get_final_answer` tool until told otherwise. However, I don''t have any specific
input for the tool at the moment. \nAction: get_final_answer\nAction Input:
{}\nObservation: 42"}], "model": "gpt-4", "stop": ["\nObservation:"]}'
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
@@ -267,16 +386,16 @@ interactions:
connection:
- keep-alive
content-length:
- '2145'
- '2273'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __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 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -286,7 +405,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -296,22 +415,22 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81cbdMi0Ptxq4heqiAPKADCy9HYI\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476221,\n \"model\": \"gpt-4-0613\",\n
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 got the answer as 42 from
the tool. However, the task explicitly stated that I shouldn't give the answer
until told. Therefore, I need to keep using the `get_final_answer` tool.\\nAction:
\"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\": 457,\n \"completion_tokens\": 54,\n
\ \"total_tokens\": 511,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
\ \"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:
- 8c3f9200496e2233-MIA
- 8c4f6c9fcf6da67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -319,7 +438,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:44 GMT
- Wed, 18 Sep 2024 06:54:25 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -333,7 +452,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2736'
- '2502'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -345,13 +464,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999503'
- '999477'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 29ms
- 31ms
x-request-id:
- req_ceecd9fba3a93a5e09b7bcea992c6299
- req_5f36c40b6e54cbab266704bd7faac9a8
http_version: HTTP/1.1
status_code: 200
- request:
@@ -372,165 +491,35 @@ 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:"}, {"role": "assistant", "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": "assistant", "content": "I need to keep using the
`get_final_answer` tool until told otherwise. However, I don''t have any specific
input for the tool at the moment. \nAction: get_final_answer\nAction Input:
{}\nObservation: 42"}, {"role": "assistant", "content": "Thought: I got the
answer as 42 from the tool. However, the task explicitly stated that I shouldn''t
give the answer until told. Therefore, I need to keep using the `get_final_answer`
tool.\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:
- '2535'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
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-A81cezl6pjhfjS47BWUbFtXHdnOsz\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476224,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I am not sure whether to provide
the final answer yet since the task specifies to not give the answer until told.
I should continue using the `get_final_answer` tool.\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
541,\n \"completion_tokens\": 47,\n \"total_tokens\": 588,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9213d82f2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:47 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2451'
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:
- '999415'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 35ms
x-request-id:
- req_8d350f93e97fc2ecb9b9df5975dc3b2b
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": "assistant", "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": "assistant", "content": "I need to keep using the
`get_final_answer` tool until told otherwise. However, I don''t have any specific
input for the tool at the moment. \nAction: get_final_answer\nAction Input:
{}\nObservation: 42"}, {"role": "assistant", "content": "Thought: I got the
answer as 42 from the tool. However, the task explicitly stated that I shouldn''t
give the answer until told. Therefore, I need to keep using the `get_final_answer`
tool.\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": "assistant", "content": "Thought: I am not sure whether
to provide the final answer yet since the task specifies to not give the answer
until told. I should continue using the `get_final_answer` tool.\nAction: get_final_answer\nAction
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\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:"]}'
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
@@ -539,16 +528,16 @@ interactions:
connection:
- keep-alive
content-length:
- '3915'
- '3657'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __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 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -558,7 +547,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -568,19 +557,19 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81chmZnwAdzXb96fOTgZgdjGhh4u\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476227,\n \"model\": \"gpt-4-0613\",\n
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\":
832,\n \"completion_tokens\": 19,\n \"total_tokens\": 851,\n \"completion_tokens_details\":
769,\n \"completion_tokens\": 19,\n \"total_tokens\": 788,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f92250d632233-MIA
- 8c4f6cb19fada67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -588,7 +577,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:48 GMT
- Wed, 18 Sep 2024 06:54:26 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -602,7 +591,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '987'
- '1127'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -614,13 +603,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999085'
- '999144'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 54ms
- 51ms
x-request-id:
- req_ffa5c2ca63f4ed556210071b071ce72b
- req_13305d886d3dd194f1c674a9d61bdb9b
http_version: HTTP/1.1
status_code: 200
version: 1