andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-28 01:28:14 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

removing langchain

Browse Source
This commit is contained in:
João Moura
2024-09-13 02:57:50 -05:00
parent 3cd464497b
commit 7120a9860b
40 changed files with 6295 additions and 2499 deletions
Download Patch File Download Diff File Expand all files Collapse all files

681
tests/cassettes/test_agent_respect_the_max_rpm_set_over_crew_rpm.yaml Normal file
View File

@@ -0,0 +1,681 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Use tool logic
for `get_final_answer` but fon''t give you final answer yet, instead keep using
it unless you''re told to give your final answer\n\nThis 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:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1428'
content-type:
- application/json
cookie:
- _cfuvid=iTR1OQH6LALCSFaeT0eFfOeYnI_fkFZDwyyndcJuH8E-1725908571214-0.0.1.1-604800000
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-A6odyF7CqdjrQvnC5uCb1bvBaenyJ\",\n \"object\":
\"chat.completion\",\n \"created\": 1726188006,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to gather the final answer
using the tool `get_final_answer`. \\n\\nAction: get_final_answer\\nAction Input:
{}\\n\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 293,\n \"completion_tokens\":
28,\n \"total_tokens\": 321,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c2415813879a4a4-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 00:40:07 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=AXZJ7J0cPjCfRcqHyeujSubu93QdP8nyUfDNGDdZ9sk-1726188007-1.0.1.1-Va48NGQp7m5s_49xk6pZFgWl42rmJvSd2pJWZgm8smJukvX6lsRktqdzUJSSVZfi.Sj6wIbs5LNZh6gLbbRzrA;
path=/; expires=Fri, 13-Sep-24 01:10:07 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=NqphhptgCYl51k8kIFxQ.T4x1aYVbhAz5evGBO5HX5E-1726188007226-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '373'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999656'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_55ff8e5d3188f7fd4d342f32f54562f8
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Use tool logic
for `get_final_answer` but fon''t give you final answer yet, instead keep using
it unless you''re told to give your final answer\n\nThis 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": "assistant", "content": "Thought: I need to gather
the final answer using the tool `get_final_answer`. \n\nAction: get_final_answer\nAction
Input: {}\n\nObservation: 42"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1609'
content-type:
- application/json
cookie:
- _cfuvid=NqphhptgCYl51k8kIFxQ.T4x1aYVbhAz5evGBO5HX5E-1726188007226-0.0.1.1-604800000;
__cf_bm=AXZJ7J0cPjCfRcqHyeujSubu93QdP8nyUfDNGDdZ9sk-1726188007-1.0.1.1-Va48NGQp7m5s_49xk6pZFgWl42rmJvSd2pJWZgm8smJukvX6lsRktqdzUJSSVZfi.Sj6wIbs5LNZh6gLbbRzrA
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-A6oe0ouqKJ3JA97oL6Q25oaVzYCMm\",\n \"object\":
\"chat.completion\",\n \"created\": 1726188008,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to keep using the `get_final_answer`
tool until I'm explicitly told to give the final answer.\\n\\nAction: get_final_answer\\nAction
Input: {}\\n\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
329,\n \"completion_tokens\": 34,\n \"total_tokens\": 363,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c24158a0bf3a4a4-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 00:40:08 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:
- '522'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999619'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_bb8f63a31f97df85a3d24aee679dd202
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Use tool logic
for `get_final_answer` but fon''t give you final answer yet, instead keep using
it unless you''re told to give your final answer\n\nThis 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": "assistant", "content": "Thought: I need to gather
the final answer using the tool `get_final_answer`. \n\nAction: get_final_answer\nAction
Input: {}\n\nObservation: 42"}, {"role": "assistant", "content": "Thought: I
need to keep using the `get_final_answer` tool until I''m explicitly told to
give the final answer.\n\nAction: get_final_answer\nAction Input: {}\n\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", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1924'
content-type:
- application/json
cookie:
- _cfuvid=NqphhptgCYl51k8kIFxQ.T4x1aYVbhAz5evGBO5HX5E-1726188007226-0.0.1.1-604800000;
__cf_bm=AXZJ7J0cPjCfRcqHyeujSubu93QdP8nyUfDNGDdZ9sk-1726188007-1.0.1.1-Va48NGQp7m5s_49xk6pZFgWl42rmJvSd2pJWZgm8smJukvX6lsRktqdzUJSSVZfi.Sj6wIbs5LNZh6gLbbRzrA
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-A6oe2sIpF1RHB39P1ezjwAcW4WC2D\",\n \"object\":
\"chat.completion\",\n \"created\": 1726188010,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I misunderstood how to use the
tool correctly. I should continue to reuse the `get_final_answer` tool without
changing the input until instructed otherwise.\\n\\nAction: get_final_answer\\nAction
Input: {}\\n\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
391,\n \"completion_tokens\": 41,\n \"total_tokens\": 432,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c2415923f1ca4a4-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 00:40:10 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:
- '563'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999552'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a36db34b9e07fe0dbd8ba02d59c2d641
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1430'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Fri, 13 Sep 2024 00:40:10 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Use tool logic
for `get_final_answer` but fon''t give you final answer yet, instead keep using
it unless you''re told to give your final answer\n\nThis 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": "assistant", "content": "Thought: I need to gather
the final answer using the tool `get_final_answer`. \n\nAction: get_final_answer\nAction
Input: {}\n\nObservation: 42"}, {"role": "assistant", "content": "Thought: I
need to keep using the `get_final_answer` tool until I''m explicitly told to
give the final answer.\n\nAction: get_final_answer\nAction Input: {}\n\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
misunderstood how to use the tool correctly. I should continue to reuse the
`get_final_answer` tool without changing the input until instructed otherwise.\n\nAction:
get_final_answer\nAction Input: {}\n\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", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3124'
content-type:
- application/json
cookie:
- _cfuvid=NqphhptgCYl51k8kIFxQ.T4x1aYVbhAz5evGBO5HX5E-1726188007226-0.0.1.1-604800000;
__cf_bm=AXZJ7J0cPjCfRcqHyeujSubu93QdP8nyUfDNGDdZ9sk-1726188007-1.0.1.1-Va48NGQp7m5s_49xk6pZFgWl42rmJvSd2pJWZgm8smJukvX6lsRktqdzUJSSVZfi.Sj6wIbs5LNZh6gLbbRzrA
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-A6oe3eXsyKUGU1mtnlpMYqhPkY9vk\",\n \"object\":
\"chat.completion\",\n \"created\": 1726188011,\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 re-using
the `get_final_answer` tool without changes to the action input until directed
otherwise.\\n\\nAction: get_final_answer\\nAction Input: {}\\n\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 637,\n \"completion_tokens\":
36,\n \"total_tokens\": 673,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c2415a049b2a4a4-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 00:40:12 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:
- '426'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999266'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_54b7d4fe860a410c3c255e740349e3a9
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "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\nCurrent Task: Use tool logic
for `get_final_answer` but fon''t give you final answer yet, instead keep using
it unless you''re told to give your final answer\n\nThis 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": "assistant", "content": "Thought: I need to gather
the final answer using the tool `get_final_answer`. \n\nAction: get_final_answer\nAction
Input: {}\n\nObservation: 42"}, {"role": "assistant", "content": "Thought: I
need to keep using the `get_final_answer` tool until I''m explicitly told to
give the final answer.\n\nAction: get_final_answer\nAction Input: {}\n\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
misunderstood how to use the tool correctly. I should continue to reuse the
`get_final_answer` tool without changing the input until instructed otherwise.\n\nAction:
get_final_answer\nAction Input: {}\n\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": "assistant", "content": "Thought: I need to continue
re-using the `get_final_answer` tool without changes to the action input until
directed otherwise.\n\nAction: get_final_answer\nAction Input: {}\n\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", "stop":
["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3630'
content-type:
- application/json
cookie:
- _cfuvid=NqphhptgCYl51k8kIFxQ.T4x1aYVbhAz5evGBO5HX5E-1726188007226-0.0.1.1-604800000;
__cf_bm=AXZJ7J0cPjCfRcqHyeujSubu93QdP8nyUfDNGDdZ9sk-1726188007-1.0.1.1-Va48NGQp7m5s_49xk6pZFgWl42rmJvSd2pJWZgm8smJukvX6lsRktqdzUJSSVZfi.Sj6wIbs5LNZh6gLbbRzrA
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-A6oe4i3SwBj8bAwY16R4LQ9dwbdC5\",\n \"object\":
\"chat.completion\",\n \"created\": 1726188012,\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\":
733,\n \"completion_tokens\": 14,\n \"total_tokens\": 747,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c2415a63a09a4a4-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 00:40:13 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:
- '294'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999151'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_92043ae9f639b2142c318b44155ba673
http_version: HTTP/1.1
status_code: 200
version: 1

795
tests/cassettes/test_agent_use_specific_tasks_output_as_context.yaml
View File

@@ -1,145 +1,15 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "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: Delegate
work to coworker(task: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool
Description: Delegate a specific task to one of the following coworkers: test
role2\nThe input to this tool should be the coworker, the task you want them
to do, and ALL necessary context to execute the task, they know nothing about
the task, so share absolute everything you know, don''t reference things but
instead explain them.\nTool Arguments: {''task'': {''title'': ''Task'', ''type'':
''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''}, ''coworker'':
{''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'',
''type'': ''object''}}\nTool Name: Ask question to coworker(question: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Ask a specific
question to one of the following coworkers: test role2\nThe input to this tool
should be the coworker, the question you have for them, and ALL necessary context
to ask the question properly, they know nothing about the question, so share
absolute everything you know, don''t reference things but instead explain them.\nTool
Arguments: {''question'': {''title'': ''Question'', ''type'': ''string''}, ''context'':
{''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Delegate work to coworker, Ask question
to coworker], 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\nCurrent Task: Just
say hi.\n\nThis is the expect criteria for your final answer: Your greeting.
\n you MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2467'
content-type:
- application/json
cookie:
- __cf_bm=iMsGonnXhDDCqOz9miNRwOGOr7OzXm1EqcxEiFk_nT4-1725908571-1.0.1.1-1P.quluT8iIibKOx0N4Mj8vflrRuSZk7gOWmptSyOKAFsTkvt3UultWM2b_B6I956Cvswux_SgpniB37rKO8Vw;
_cfuvid=iTR1OQH6LALCSFaeT0eFfOeYnI_fkFZDwyyndcJuH8E-1725908571214-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5dzeiqDrCjVKuTKGMamN5DDr97bc\",\n \"object\":
\"chat.completion\",\n \"created\": 1725908738,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to consider how to handle
the current task which is to just say hi. Given the tools available, I can either
delegate the task to test role2 or ask them a question. \\n\\nAction: Ask question
to coworker\\nAction Input: {\\\"question\\\": \\\"Can you help me by saying
hi?\\\", \\\"context\\\": \\\"My task is to simply say hi, and I need your help
to complete this task.\\\", \\\"coworker\\\": \\\"test role2\\\"}\\n\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 552,\n \"completion_tokens\":
96,\n \"total_tokens\": 648\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c09736d6a8f7ad6-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 09 Sep 2024 19:05:39 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:
- '879'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999396'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_b6f10c8c065bc60b511a0533325b5f7e
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role2. test backstory2\nYour
personal goal is: test goal2\nTo give my best complete final answer to the task
personal goal is: test goal\nTo give my best complete final answer to the task
use the exact following format:\n\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!\nCurrent Task: Can you help me by saying hi?\n\nThis is the expect criteria
for your final answer: Your best answer to your coworker asking you this, accounting
for the context shared. \n you MUST return the actual complete content as the
final answer, not a summary.\n\nThis is the context you''re working with:\nMy
task is to simply say hi, and I need your help to complete this task.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
it!\nCurrent Task: Just say hi.\n\nThis is the expect criteria for your final
answer: Your greeting.\nyou MUST return the actual complete content as the final
answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
@@ -148,16 +18,15 @@ interactions:
connection:
- keep-alive
content-length:
- '975'
- '764'
content-type:
- application/json
cookie:
- __cf_bm=iMsGonnXhDDCqOz9miNRwOGOr7OzXm1EqcxEiFk_nT4-1725908571-1.0.1.1-1P.quluT8iIibKOx0N4Mj8vflrRuSZk7gOWmptSyOKAFsTkvt3UultWM2b_B6I956Cvswux_SgpniB37rKO8Vw;
_cfuvid=iTR1OQH6LALCSFaeT0eFfOeYnI_fkFZDwyyndcJuH8E-1725908571214-0.0.1.1-604800000
- _cfuvid=NqphhptgCYl51k8kIFxQ.T4x1aYVbhAz5evGBO5HX5E-1726188007226-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -167,7 +36,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -177,19 +46,19 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A5dzfRUplszjSVhxWFMBsY9YmHxv6\",\n \"object\":
\"chat.completion\",\n \"created\": 1725908739,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A6tNJ1p3d1HLKrZtqVlgpFJ02EXoG\",\n \"object\":
\"chat.completion\",\n \"created\": 1726206193,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
\"assistant\",\n \"content\": \"I now can give a great answer\\nFinal
Answer: Hi!\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
197,\n \"completion_tokens\": 15,\n \"total_tokens\": 212\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
149,\n \"completion_tokens\": 13,\n \"total_tokens\": 162,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c097374e8c87ad6-SJC
- 8c25d18319117c44-LAX
Connection:
- keep-alive
Content-Encoding:
@@ -197,9 +66,15 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 09 Sep 2024 19:05:39 GMT
- Fri, 13 Sep 2024 05:43:13 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=ClnNKAuXgV.ion8pbtUaEfUtQSyni9o4VnBEhtjLcvY-1726206193-1.0.1.1-irjAKQKLFXoFHYMHg.GoJNcvu6A7u6ASFzz_Sr3U6wi_72IUfIRiLp7tOwWp0WXUbEKvKk3dJqoTqwblHvq7Wg;
path=/; expires=Fri, 13-Sep-24 06:13:13 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=7gNruCM_IOsMgDEA4EI0g9dg0NDN5T9HigjiRwrAKc0-1726206193576-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
@@ -211,7 +86,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '258'
- '278'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -223,497 +98,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999766'
- '29999818'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_01632d20b8601bc3f4acae684870c803
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "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: Delegate
work to coworker(task: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool
Description: Delegate a specific task to one of the following coworkers: test
role2\nThe input to this tool should be the coworker, the task you want them
to do, and ALL necessary context to execute the task, they know nothing about
the task, so share absolute everything you know, don''t reference things but
instead explain them.\nTool Arguments: {''task'': {''title'': ''Task'', ''type'':
''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''}, ''coworker'':
{''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'',
''type'': ''object''}}\nTool Name: Ask question to coworker(question: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Ask a specific
question to one of the following coworkers: test role2\nThe input to this tool
should be the coworker, the question you have for them, and ALL necessary context
to ask the question properly, they know nothing about the question, so share
absolute everything you know, don''t reference things but instead explain them.\nTool
Arguments: {''question'': {''title'': ''Question'', ''type'': ''string''}, ''context'':
{''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Delegate work to coworker, Ask question
to coworker], 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\nCurrent Task: Just
say hi.\n\nThis is the expect criteria for your final answer: Your greeting.
\n you 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":
"Thought: I need to consider how to handle the current task which is to just
say hi. Given the tools available, I can either delegate the task to test role2
or ask them a question. \n\nAction: Ask question to coworker\nAction Input:
{\"question\": \"Can you help me by saying hi?\", \"context\": \"My task is
to simply say hi, and I need your help to complete this task.\", \"coworker\":
\"test role2\"}\n\nObservation: Hi!"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2927'
content-type:
- application/json
cookie:
- __cf_bm=iMsGonnXhDDCqOz9miNRwOGOr7OzXm1EqcxEiFk_nT4-1725908571-1.0.1.1-1P.quluT8iIibKOx0N4Mj8vflrRuSZk7gOWmptSyOKAFsTkvt3UultWM2b_B6I956Cvswux_SgpniB37rKO8Vw;
_cfuvid=iTR1OQH6LALCSFaeT0eFfOeYnI_fkFZDwyyndcJuH8E-1725908571214-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5dzfumk7ZBIa57yk9p2brs7cJSkx\",\n \"object\":
\"chat.completion\",\n \"created\": 1725908739,\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: Hi!\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
656,\n \"completion_tokens\": 14,\n \"total_tokens\": 670\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c097377ab587ad6-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 09 Sep 2024 19:05:40 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:
- '199'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999295'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_3dde81dd8c0ec39c49c3eb8557d09526
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "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: Delegate
work to coworker(task: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool
Description: Delegate a specific task to one of the following coworkers: test
role2\nThe input to this tool should be the coworker, the task you want them
to do, and ALL necessary context to execute the task, they know nothing about
the task, so share absolute everything you know, don''t reference things but
instead explain them.\nTool Arguments: {''task'': {''title'': ''Task'', ''type'':
''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''}, ''coworker'':
{''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'',
''type'': ''object''}}\nTool Name: Ask question to coworker(question: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Ask a specific
question to one of the following coworkers: test role2\nThe input to this tool
should be the coworker, the question you have for them, and ALL necessary context
to ask the question properly, they know nothing about the question, so share
absolute everything you know, don''t reference things but instead explain them.\nTool
Arguments: {''question'': {''title'': ''Question'', ''type'': ''string''}, ''context'':
{''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Delegate work to coworker, Ask question
to coworker], 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\nCurrent Task: Just
say bye.\n\nThis is the expect criteria for your final answer: Your farewell.
\n you MUST return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\nHi!\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2517'
content-type:
- application/json
cookie:
- __cf_bm=iMsGonnXhDDCqOz9miNRwOGOr7OzXm1EqcxEiFk_nT4-1725908571-1.0.1.1-1P.quluT8iIibKOx0N4Mj8vflrRuSZk7gOWmptSyOKAFsTkvt3UultWM2b_B6I956Cvswux_SgpniB37rKO8Vw;
_cfuvid=iTR1OQH6LALCSFaeT0eFfOeYnI_fkFZDwyyndcJuH8E-1725908571214-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5dzgUnJ6aJi26kLV0OI3Wf4Ub7zD\",\n \"object\":
\"chat.completion\",\n \"created\": 1725908740,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: To successfully complete the
current task, which is to say \\\"bye,\\\" I need to ensure that my farewell
is complete and appropriate based on the given context \\\"Hi!\\\"\\n\\nFinal
Answer: Bye!\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
562,\n \"completion_tokens\": 40,\n \"total_tokens\": 602\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c09737b0e7c7ad6-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 09 Sep 2024 19:05:40 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:
- '420'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999385'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_a36a51c9e279c6f62c4f308c3dea9288
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '3731'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Mon, 09 Sep 2024 19:05:42 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are test role2. test backstory2\nYour
personal goal is: test goal2\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: Delegate
work to coworker(task: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool
Description: Delegate a specific task to one of the following coworkers: test
role\nThe input to this tool should be the coworker, the task you want them
to do, and ALL necessary context to execute the task, they know nothing about
the task, so share absolute everything you know, don''t reference things but
instead explain them.\nTool Arguments: {''task'': {''title'': ''Task'', ''type'':
''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''}, ''coworker'':
{''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'',
''type'': ''object''}}\nTool Name: Ask question to coworker(question: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Ask a specific
question to one of the following coworkers: test role\nThe input to this tool
should be the coworker, the question you have for them, and ALL necessary context
to ask the question properly, they know nothing about the question, so share
absolute everything you know, don''t reference things but instead explain them.\nTool
Arguments: {''question'': {''title'': ''Question'', ''type'': ''string''}, ''context'':
{''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Delegate work to coworker, Ask question
to coworker], 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\nCurrent Task: Answer
accordingly to the context you got.\n\nThis is the expect criteria for your
final answer: Your answer. \n you MUST return the actual complete content as
the final answer, not a summary.\n\nThis is the context you''re working with:\nHi!\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2545'
content-type:
- application/json
cookie:
- __cf_bm=iMsGonnXhDDCqOz9miNRwOGOr7OzXm1EqcxEiFk_nT4-1725908571-1.0.1.1-1P.quluT8iIibKOx0N4Mj8vflrRuSZk7gOWmptSyOKAFsTkvt3UultWM2b_B6I956Cvswux_SgpniB37rKO8Vw;
_cfuvid=iTR1OQH6LALCSFaeT0eFfOeYnI_fkFZDwyyndcJuH8E-1725908571214-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5dzh9UtjYFsx1FIyZNu4fcHCv4hd\",\n \"object\":
\"chat.completion\",\n \"created\": 1725908741,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: My job is to provide the best
possible answer based on the context \\\"Hi!\\\" and use the tools available
if necessary to gather more information. Since the provided context is minimal,
I need to clarify what the requester needs from me.\\n\\nAction: Ask question
to coworker\\nAction Input: {\\\"question\\\": \\\"What task do you need assistance
with?\\\", \\\"context\\\": \\\"The only information provided is 'Hi!'. Could
you please specify what task you need help with or any additional details?\\\",
\\\"coworker\\\": \\\"test role\\\"}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 567,\n \"completion_tokens\": 108,\n
\ \"total_tokens\": 675\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c09737fead97ad6-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 09 Sep 2024 19:05:42 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:
- '1522'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999379'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_2e4f43ec6df32cf8fad8e75705a9b1a8
- req_508393c5be3af0df1b77f458001603b6
http_version: HTTP/1.1
status_code: 200
- request:
@@ -722,14 +113,11 @@ interactions:
use the exact following format:\n\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!\nCurrent Task: What task do you need assistance with?\n\nThis is the expect
criteria for your final answer: Your best answer to your coworker asking you
this, accounting for the context shared. \n you MUST return the actual complete
content as the final answer, not a summary.\n\nThis is the context you''re working
with:\nThe only information provided is ''Hi!''. Could you please specify what
task you need help with or any additional details?\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
it!\nCurrent Task: Just say bye.\n\nThis is the expect criteria for your final
answer: Your farewell.\nyou MUST return the actual complete content as the final
answer, not a summary.\n\nThis is the context you''re working with:\nHi!\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
@@ -738,16 +126,16 @@ interactions:
connection:
- keep-alive
content-length:
- '1029'
- '814'
content-type:
- application/json
cookie:
- __cf_bm=iMsGonnXhDDCqOz9miNRwOGOr7OzXm1EqcxEiFk_nT4-1725908571-1.0.1.1-1P.quluT8iIibKOx0N4Mj8vflrRuSZk7gOWmptSyOKAFsTkvt3UultWM2b_B6I956Cvswux_SgpniB37rKO8Vw;
_cfuvid=iTR1OQH6LALCSFaeT0eFfOeYnI_fkFZDwyyndcJuH8E-1725908571214-0.0.1.1-604800000
- _cfuvid=7gNruCM_IOsMgDEA4EI0g9dg0NDN5T9HigjiRwrAKc0-1726206193576-0.0.1.1-604800000;
__cf_bm=ClnNKAuXgV.ion8pbtUaEfUtQSyni9o4VnBEhtjLcvY-1726206193-1.0.1.1-irjAKQKLFXoFHYMHg.GoJNcvu6A7u6ASFzz_Sr3U6wi_72IUfIRiLp7tOwWp0WXUbEKvKk3dJqoTqwblHvq7Wg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -757,7 +145,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -767,20 +155,19 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A5dzjBlbcYaqsY9FSUbOvbYhDni5X\",\n \"object\":
\"chat.completion\",\n \"created\": 1725908743,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A6tNKg5xx1h379SmfwvVe9T0qx8Qk\",\n \"object\":
\"chat.completion\",\n \"created\": 1726206194,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: Hi! Could you please specify what task you need help with or provide
any additional details? Thank you!\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\": 34,\n
\ \"total_tokens\": 234\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
Answer: Bye!\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
159,\n \"completion_tokens\": 15,\n \"total_tokens\": 174,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_157b3831f5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c09738b6dae7ad6-SJC
- 8c25d189de367c44-LAX
Connection:
- keep-alive
Content-Encoding:
@@ -788,7 +175,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 09 Sep 2024 19:05:43 GMT
- Fri, 13 Sep 2024 05:43:15 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -802,7 +189,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '413'
- '261'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -814,57 +201,27 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999753'
- '29999807'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_292b6d0fa818839ad01236355bf7e880
- req_5e4fa349168edad6c2eae435ee880756
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role2. test backstory2\nYour
personal goal is: test goal2\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: Delegate
work to coworker(task: str, context: str, coworker: Optional[str] = None, **kwargs)\nTool
Description: Delegate a specific task to one of the following coworkers: test
role\nThe input to this tool should be the coworker, the task you want them
to do, and ALL necessary context to execute the task, they know nothing about
the task, so share absolute everything you know, don''t reference things but
instead explain them.\nTool Arguments: {''task'': {''title'': ''Task'', ''type'':
''string''}, ''context'': {''title'': ''Context'', ''type'': ''string''}, ''coworker'':
{''title'': ''Coworker'', ''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'',
''type'': ''object''}}\nTool Name: Ask question to coworker(question: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Ask a specific
question to one of the following coworkers: test role\nThe input to this tool
should be the coworker, the question you have for them, and ALL necessary context
to ask the question properly, they know nothing about the question, so share
absolute everything you know, don''t reference things but instead explain them.\nTool
Arguments: {''question'': {''title'': ''Question'', ''type'': ''string''}, ''context'':
{''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Delegate work to coworker, Ask question
to coworker], 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\nCurrent Task: Answer
accordingly to the context you got.\n\nThis is the expect criteria for your
final answer: Your answer. \n you MUST return the actual complete content as
the final answer, not a summary.\n\nThis is the context you''re working with:\nHi!\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":
"Thought: My job is to provide the best possible answer based on the context
\"Hi!\" and use the tools available if necessary to gather more information.
Since the provided context is minimal, I need to clarify what the requester
needs from me.\n\nAction: Ask question to coworker\nAction Input: {\"question\":
\"What task do you need assistance with?\", \"context\": \"The only information
provided is ''Hi!''. Could you please specify what task you need help with or
any additional details?\", \"coworker\": \"test role\"}\nObservation: Hi! Could
you please specify what task you need help with or provide any additional details?
Thank you!"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
personal goal is: test goal2\nTo give my best complete final answer to the task
use the exact following format:\n\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!\nCurrent Task: Answer accordingly to the context you got.\n\nThis is the
expect criteria for your final answer: Your answer.\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nHi!\n\nBegin! This is VERY important to you, use the
tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
@@ -873,16 +230,16 @@ interactions:
connection:
- keep-alive
content-length:
- '3222'
- '844'
content-type:
- application/json
cookie:
- __cf_bm=iMsGonnXhDDCqOz9miNRwOGOr7OzXm1EqcxEiFk_nT4-1725908571-1.0.1.1-1P.quluT8iIibKOx0N4Mj8vflrRuSZk7gOWmptSyOKAFsTkvt3UultWM2b_B6I956Cvswux_SgpniB37rKO8Vw;
_cfuvid=iTR1OQH6LALCSFaeT0eFfOeYnI_fkFZDwyyndcJuH8E-1725908571214-0.0.1.1-604800000
- _cfuvid=7gNruCM_IOsMgDEA4EI0g9dg0NDN5T9HigjiRwrAKc0-1726206193576-0.0.1.1-604800000;
__cf_bm=ClnNKAuXgV.ion8pbtUaEfUtQSyni9o4VnBEhtjLcvY-1726206193-1.0.1.1-irjAKQKLFXoFHYMHg.GoJNcvu6A7u6ASFzz_Sr3U6wi_72IUfIRiLp7tOwWp0WXUbEKvKk3dJqoTqwblHvq7Wg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -892,7 +249,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -902,21 +259,19 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A5dzj9osiocPBXZN0MiQmLvGZ8ENt\",\n \"object\":
\"chat.completion\",\n \"created\": 1725908743,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A6tNLvrOTcvGiku88z0yUR1qGt3Og\",\n \"object\":
\"chat.completion\",\n \"created\": 1726206195,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Since there is no observation
provided, I will proceed with an answer based on the given context, \\\"Hi!\\\".\\n\\nFinal
Answer: Hello! How can I assist you today? Please let me know if there is anything
specific you need help with.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
702,\n \"completion_tokens\": 51,\n \"total_tokens\": 753\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: Hi!\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
166,\n \"completion_tokens\": 15,\n \"total_tokens\": 181,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c09738f49597ad6-SJC
- 8c25d1937dff7c44-LAX
Connection:
- keep-alive
Content-Encoding:
@@ -924,7 +279,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 09 Sep 2024 19:05:44 GMT
- Fri, 13 Sep 2024 05:43:16 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -938,7 +293,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '688'
- '667'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -950,13 +305,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999222'
- '29999799'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
- 0s
x-request-id:
- req_4cbd99d9fc8ae79dcf745375e1575dd2
- req_7220b5cf61789924adb498bf1b2db031
http_version: HTTP/1.1
status_code: 200
version: 1

1038
tests/cassettes/test_api_calls_throttling.yaml
View File

File diff suppressed because it is too large Load Diff

1756
tests/cassettes/test_crew_function_calling_llm.yaml
View File

File diff suppressed because it is too large Load Diff

106
tests/cassettes/test_custom_converter_cls.yaml Normal file
View File

@@ -0,0 +1,106 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Give me an integer score
between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
is the expect criteria for your final answer: The score of the title. \n you
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '909'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2wSIKV2MyRFQCpm4RB0sWWGOBu\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128050,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
182,\n \"completion_tokens\": 15,\n \"total_tokens\": 197\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5dbdaed76280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:51 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:
- '334'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999781'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_cce338fbc4502babd1e64ea1e7058bfc
http_version: HTTP/1.1
status_code: 200
version: 1

472
tests/cassettes/test_increment_delegations_for_hierarchical_process.yaml Normal file
View File

@@ -0,0 +1,472 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are Crew Manager. You are
a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
specific task to one of the following coworkers: Scorer\nThe input to this tool
should be the coworker, the task you want them to do, and ALL necessary context
to execute the task, they know nothing about the task, so share absolute everything
you know, don''t reference things but instead explain them.\nTool Arguments:
{''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'':
''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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\nCurrent Task: Give me an
integer score between 1-5 for the following title: ''The impact of AI in the
future of work''\n\nThis is the expect criteria for your final answer: The score
of the title. \n you MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2980'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2yke9Z49R9L16MG3XgIVtfSCwY\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128052,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to gather an evaluation
score for the title \\\"The impact of AI in the future of work\\\" based on
some criteria. The best way to accomplish this is to delegate this task to Scorer
and provide all the necessary context.\\n\\nAction: Delegate work to coworker\\nAction
Input: {\\\"task\\\": \\\"Give an integer score between 1-5 for the following
title: 'The impact of AI in the future of work'\\\", \\\"context\\\": \\\"Please
evaluate the title based on relevance, clarity, and significance. The title
should be rated with an integer score where 1 means very poor and 5 means excellent.\\\",
\\\"coworker\\\": \\\"Scorer\\\"}\\n\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 660,\n \"completion_tokens\": 136,\n
\ \"total_tokens\": 796\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5dc2e8ad6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:54 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:
- '1731'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999270'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_1efbe90172036fca00dc98b82e1d36b7
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Give an integer score between
1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
is the expect criteria for your final answer: Your best answer to your coworker
asking you this, accounting for the context shared. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nPlease evaluate the title based on relevance, clarity,
and significance. The title should be rated with an integer score where 1 means
very poor and 5 means excellent.\n\nBegin! This is VERY important to you, use
the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1181'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z3055c8eQwgrOGdho2OPHJJVpDm\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128054,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 5\\n\\nThe title \\\"The impact of AI in the future of work\\\" is highly
relevant, clear, and significant. It addresses a current and crucial topic in
the field of technology and employment, making it an excellent choice.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 234,\n \"completion_tokens\":
59,\n \"total_tokens\": 293\n },\n \"system_fingerprint\": \"fp_157b3831f5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5dd3beab6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:55 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:
- '880'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999714'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_dd6f1578546f53814be3082794dc14a4
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '2703'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Thu, 12 Sep 2024 08:00:56 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are Crew Manager. You are
a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
specific task to one of the following coworkers: Scorer\nThe input to this tool
should be the coworker, the task you want them to do, and ALL necessary context
to execute the task, they know nothing about the task, so share absolute everything
you know, don''t reference things but instead explain them.\nTool Arguments:
{''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'':
''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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\nCurrent Task: Give me an
integer score between 1-5 for the following title: ''The impact of AI in the
future of work''\n\nThis is the expect criteria for your final answer: The score
of the title. \n you 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": "Thought: I need to gather an evaluation score for the
title \"The impact of AI in the future of work\" based on some criteria. The
best way to accomplish this is to delegate this task to Scorer and provide all
the necessary context.\n\nAction: Delegate work to coworker\nAction Input: {\"task\":
\"Give an integer score between 1-5 for the following title: ''The impact of
AI in the future of work''\", \"context\": \"Please evaluate the title based
on relevance, clarity, and significance. The title should be rated with an integer
score where 1 means very poor and 5 means excellent.\", \"coworker\": \"Scorer\"}\n\nObservation:
5\n\nThe title \"The impact of AI in the future of work\" is highly relevant,
clear, and significant. It addresses a current and crucial topic in the field
of technology and employment, making it an excellent choice."}], "model": "gpt-4o",
"stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3863'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z32SMvj8xe2HIGWbtAU1NJiQQMu\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128056,\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\\n\\nFinal
Answer: 5\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
848,\n \"completion_tokens\": 14,\n \"total_tokens\": 862\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5ddebb106280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:57 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:
- '261'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999062'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_fcdfbf430a138e20427a734ee04d6609
http_version: HTTP/1.1
status_code: 200
version: 1

441
tests/cassettes/test_increment_delegations_for_sequential_process.yaml Normal file
View File

@@ -0,0 +1,441 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are Manager. You''re great
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
processes\nYou ONLY have access to the following tools, and should NEVER make
up tools that are not listed here:\n\nTool Name: Delegate work to coworker(task:
str, context: str, coworker: Optional[str] = None, **kwargs)\nTool Description:
Delegate a specific task to one of the following coworkers: Scorer\nThe input
to this tool should be the coworker, the task you want them to do, and ALL necessary
context to execute the task, they know nothing about the task, so share absolute
everything you know, don''t reference things but instead explain them.\nTool
Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'':
{''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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\nCurrent Task: Give me an
integer score between 1-5 for the following title: ''The impact of AI in the
future of work''\n\nThis is the expect criteria for your final answer: The score
of the title. \n you MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2607'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z33vxoIkYm0m4jSbwym7Wc3Vxm8\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128057,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to coordinate the scoring process
for the title \\\"The impact of AI in the future of work\\\". I will delegate
this task to the Scorer, providing them with all the necessary context and details
for scoring.\\n\\nAction: Delegate work to coworker\\nAction Input: {\\\"task\\\":
\\\"Give an integer score between 1-5 for the following title: 'The impact of
AI in the future of work'\\\", \\\"context\\\": \\\"Please score the title based
on its relevance, clarity, and potential impact in the context of the future
of work. Consider factors such as current trends in AI, its applications in
the workplace, and possible future advancements.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\\n\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 580,\n \"completion_tokens\":
139,\n \"total_tokens\": 719\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5de67e2e6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:00 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:
- '2637'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999361'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_f207cc3e7d94e0883825e3595ea8a96a
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Give an integer score between
1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
is the expect criteria for your final answer: Your best answer to your coworker
asking you this, accounting for the context shared. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nPlease score the title based on its relevance, clarity,
and potential impact in the context of the future of work. Consider factors
such as current trends in AI, its applications in the workplace, and possible
future advancements.\n\nBegin! This is VERY important to you, use the tools
available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1244'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z36jzKD4rmMvTw7b9GqEV6nUg2p\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128060,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer\\nFinal
Answer: 5\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
243,\n \"completion_tokens\": 13,\n \"total_tokens\": 256\n },\n \"system_fingerprint\":
\"fp_157b3831f5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5df9cea56280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:01 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:
- '362'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999698'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_af608b3b93f27393f27d907adb216e3e
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1730'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Thu, 12 Sep 2024 08:01:01 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are Manager. You''re great
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
processes\nYou ONLY have access to the following tools, and should NEVER make
up tools that are not listed here:\n\nTool Name: Delegate work to coworker(task:
str, context: str, coworker: Optional[str] = None, **kwargs)\nTool Description:
Delegate a specific task to one of the following coworkers: Scorer\nThe input
to this tool should be the coworker, the task you want them to do, and ALL necessary
context to execute the task, they know nothing about the task, so share absolute
everything you know, don''t reference things but instead explain them.\nTool
Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'':
{''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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\nCurrent Task: Give me an
integer score between 1-5 for the following title: ''The impact of AI in the
future of work''\n\nThis is the expect criteria for your final answer: The score
of the title. \n you MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role":
"assistant", "content": "I need to coordinate the scoring process for the title
\"The impact of AI in the future of work\". I will delegate this task to the
Scorer, providing them with all the necessary context and details for scoring.\n\nAction:
Delegate work to coworker\nAction Input: {\"task\": \"Give an integer score
between 1-5 for the following title: ''The impact of AI in the future of work''\",
\"context\": \"Please score the title based on its relevance, clarity, and potential
impact in the context of the future of work. Consider factors such as current
trends in AI, its applications in the workplace, and possible future advancements.\",
\"coworker\": \"Scorer\"}\n\nObservation: 5"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3316'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z37Cj4kDP8u0Z5wTOuzSyQ7cH5q\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128061,\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: The score of the title \\\"The impact of AI in the future of work\\\"
is 5.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 727,\n \"completion_tokens\":
32,\n \"total_tokens\": 759\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5dff78bb6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:02 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:
- '669'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999197'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_a1c97d3f0bdf96af5454b71ba6912703
http_version: HTTP/1.1
status_code: 200
version: 1

804
tests/cassettes/test_increment_tool_errors.yaml Normal file
View File

@@ -0,0 +1,804 @@
interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1408'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Thu, 12 Sep 2024 08:01:06 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are Crew Manager. You are
a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
specific task to one of the following coworkers: Scorer\nThe input to this tool
should be the coworker, the task you want them to do, and ALL necessary context
to execute the task, they know nothing about the task, so share absolute everything
you know, don''t reference things but instead explain them.\nTool Arguments:
{''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'':
''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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\nCurrent Task: Give me an
integer score between 1-5 for the following title: ''The impact of AI in the
future of work'', check examples to based your evaluation.\n\nThis is the expect
criteria for your final answer: The score of the title. \n you 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-4-0125-preview", "stop":
["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3034'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z38ir9Vhym04xT66OQrDky4EI34\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128062,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Before assigning a score, I
must understand the criteria that we use for evaluation. Since I cannot evaluate
the title myself, I need to delegate the task to my coworker, Scorer, providing
them with all the necessary context to assess the title appropriately.\\n\\nAction:
Delegate work to coworker\\nAction Input: {\\\"task\\\": \\\"Evaluate title\\\",
\\\"context\\\": \\\"We need to give an integer score between 1-5 for the title:
'The impact of AI in the future of work'. The score should be based on relevance,
insightfulness, and originality. Please consider these criteria when evaluating
the title.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 672,\n \"completion_tokens\":
135,\n \"total_tokens\": 807\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5e06bbdc6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:08 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:
- '5366'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1999259'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 22ms
x-request-id:
- req_0256635e5f90bc1005c9c2897c1899e4
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: scoring_examples(*args: Any, **kwargs: Any)
-> Any\nTool Description: scoring_examples() - Useful examples for scoring titles.
\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 [scoring_examples],
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\nCurrent Task: Evaluate title\n\nThis
is the expect criteria for your final answer: Your best answer to your coworker
asking you this, accounting for the context shared. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nWe need to give an integer score between 1-5 for the
title: ''The impact of AI in the future of work''. The score should be based
on relevance, insightfulness, and originality. Please consider these criteria
when evaluating the title.\n\nBegin! This is VERY important to you, use the
tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1646'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z3EMuWJ0zfPW7ZBkzpCDZA7UghH\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128068,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To accurately score the title 'The impact
of AI in the future of work' based on relevance, insightfulness, and originality,
I should first gather some useful examples for scoring titles.\\n\\nAction:
scoring_examples\\nAction Input: {}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 329,\n \"completion_tokens\": 46,\n
\ \"total_tokens\": 375\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5e2af9fc6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:09 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:
- '962'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999602'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_f5d3635348e20fcfa7f86ee64ec68072
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: scoring_examples(*args: Any, **kwargs: Any)
-> Any\nTool Description: scoring_examples() - Useful examples for scoring titles.
\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 [scoring_examples],
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\nCurrent Task: Evaluate title\n\nThis
is the expect criteria for your final answer: Your best answer to your coworker
asking you this, accounting for the context shared. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nWe need to give an integer score between 1-5 for the
title: ''The impact of AI in the future of work''. The score should be based
on relevance, insightfulness, and originality. Please consider these criteria
when evaluating the title.\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": "To accurately score the title ''The impact
of AI in the future of work'' based on relevance, insightfulness, and originality,
I should first gather some useful examples for scoring titles.\n\nAction: scoring_examples\nAction
Input: {}\nObservation: \nI encountered an error while trying to use the tool.
This was the error: Error.\n Tool scoring_examples accepts these inputs: scoring_examples()
- Useful examples for scoring titles. .\nMoving on then. I MUST either use a
tool (use one at time) OR give my best final answer. To Use the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, should
be one of [scoring_examples]\nAction Input: the input to the action, dictionary
enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
Input/Observation can repeat N times)\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described\n\n "}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2700'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z3FGyPXjQLqtQi1bP839f3sXJTR\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128069,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I will make another attempt to gather
useful examples for scoring titles to ensure my evaluation is accurate.\\n\\nAction:
scoring_examples\\nAction Input: {}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 547,\n \"completion_tokens\": 28,\n
\ \"total_tokens\": 575\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5e33be1c6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:10 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:
- '522'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999351'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_ca6ab2c18724eab9c3cf14e0420b62a6
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CqYBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSfgoSChBjcmV3YWkudGVs
ZW1ldHJ5EmgKELy5u7S9ciySMmk+s0SGxW4SCE4a9Lw+zbFYKhBUb29sIFVzYWdlIEVycm9yMAE5
+D9Fb1Vw9BdBcA5Kb1Vw9BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC41NS4yegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '169'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Thu, 12 Sep 2024 08:01:11 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: scoring_examples(*args: Any, **kwargs: Any)
-> Any\nTool Description: scoring_examples() - Useful examples for scoring titles.
\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 [scoring_examples],
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\nCurrent Task: Evaluate title\n\nThis
is the expect criteria for your final answer: Your best answer to your coworker
asking you this, accounting for the context shared. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nWe need to give an integer score between 1-5 for the
title: ''The impact of AI in the future of work''. The score should be based
on relevance, insightfulness, and originality. Please consider these criteria
when evaluating the title.\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": "To accurately score the title ''The impact
of AI in the future of work'' based on relevance, insightfulness, and originality,
I should first gather some useful examples for scoring titles.\n\nAction: scoring_examples\nAction
Input: {}\nObservation: \nI encountered an error while trying to use the tool.
This was the error: Error.\n Tool scoring_examples accepts these inputs: scoring_examples()
- Useful examples for scoring titles. .\nMoving on then. I MUST either use a
tool (use one at time) OR give my best final answer. To Use the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, should
be one of [scoring_examples]\nAction Input: the input to the action, dictionary
enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
Input/Observation can repeat N times)\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described\n\n "}, {"role": "assistant", "content": "I will
make another attempt to gather useful examples for scoring titles to ensure
my evaluation is accurate.\n\nAction: scoring_examples\nAction Input: {}\nObservation:
\nI encountered an error while trying to use the tool. This was the error: Error.\n
Tool scoring_examples accepts these inputs: scoring_examples() - Useful examples
for scoring titles. .\nMoving on then. I MUST either use a tool (use one at
time) OR give my best final answer. To Use the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, should
be one of [scoring_examples]\nAction Input: the input to the action, dictionary
enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
Input/Observation can repeat N times)\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described\n\n "}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3677'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z3GzC7QdzdIS35KeUPkd98Pok9p\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128070,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Given the persistent issue with retrieving
examples, I will leverage my expertise to evaluate the title based on the criteria
provided: relevance, insightfulness, and originality.\\n\\nThought: I will evaluate
the title 'The impact of AI in the future of work' using the three criteria
directly.\\n\\n1. **Relevance:** \\n - The title is highly relevant as AI
is a significant and timely topic in today's technological landscape.\\n -
The future of work is a pertinent issue affecting a broad audience, including
industries, employees, and policymakers.\\n\\n2. **Insightfulness:**\\n -
The title promises an examination of AI's impact, which suggests an exploration
of both potential benefits and challenges.\\n - It invites a discussion on
how AI could reshape the workforce, hinting at valuable insights for preparing
for future changes.\\n\\n3. **Originality:**\\n - The concept of AI influencing
the future of work is a common discussion point in many academic and industry
circles.\\n - However, the title doesn't hint at a unique angle or novel perspective
that sets it apart from other similar works.\\n\\nBased on these points, I will
score the title accordingly.\\n\\nFinal Answer: Based on relevance (5), insightfulness
(4), and originality (3):\\n\\n**Final Score: 4**\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 747,\n \"completion_tokens\":
252,\n \"total_tokens\": 999\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5e39d87d6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:14 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:
- '3391'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999119'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_198e30d47bf1cfd5979af826a36e4c58
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CsYCCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSnQIKEgoQY3Jld2FpLnRl
bGVtZXRyeRJoChCMo9WDZAlYK58kAM8/CEQsEgjOTYPwOZ0v6CoQVG9vbCBVc2FnZSBFcnJvcjAB
OSDEO6lVcPQXQRD8QKlVcPQXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNTUuMnoCGAGFAQABAAAS
nAEKECjsvAFKsK4VP6bGPZdG/RISCHc4LY7teq30KgpUb29sIFVzYWdlMAE5IBQMjVZw9BdBCIMP
jVZw9BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC41NS4ySigKCXRvb2xfbmFtZRIbChlEZWxlZ2F0
ZSB3b3JrIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAA=
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '329'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Thu, 12 Sep 2024 08:01:16 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are Crew Manager. You are
a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
specific task to one of the following coworkers: Scorer\nThe input to this tool
should be the coworker, the task you want them to do, and ALL necessary context
to execute the task, they know nothing about the task, so share absolute everything
you know, don''t reference things but instead explain them.\nTool Arguments:
{''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'':
''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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\nCurrent Task: Give me an
integer score between 1-5 for the following title: ''The impact of AI in the
future of work'', check examples to based your evaluation.\n\nThis is the expect
criteria for your final answer: The score of the title. \n you 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": "Thought:
Before assigning a score, I must understand the criteria that we use for evaluation.
Since I cannot evaluate the title myself, I need to delegate the task to my
coworker, Scorer, providing them with all the necessary context to assess the
title appropriately.\n\nAction: Delegate work to coworker\nAction Input: {\"task\":
\"Evaluate title\", \"context\": \"We need to give an integer score between
1-5 for the title: ''The impact of AI in the future of work''. The score should
be based on relevance, insightfulness, and originality. Please consider these
criteria when evaluating the title.\", \"coworker\": \"Scorer\"}\nObservation:
Based on relevance (5), insightfulness (4), and originality (3):\n\n**Final
Score: 4**"}], "model": "gpt-4-0125-preview", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3801'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z3KZMtHCI3KHSZ8UIt3DAfN3ONf\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128074,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\n\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
838,\n \"completion_tokens\": 14,\n \"total_tokens\": 852\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5e51b9be6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:18 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '3884'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1999080'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 27ms
x-request-id:
- req_4388c534a4e3cc95495ce98010ad7001
http_version: HTTP/1.1
status_code: 200
version: 1

426
tests/cassettes/test_output_json_to_another_task.yaml Normal file
View File

@@ -0,0 +1,426 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Give me an integer score
between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
is the expect criteria for your final answer: The score of the title. \n you
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '909'
content-type:
- application/json
cookie:
- _cfuvid=vAWf6_0Extt99cMI2V6jEXskpiREa5aqNqsAF6BIU3Y-1726009485721-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2eGCwRe7OfC5Gp77RZIVV5nQjL\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128032,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
182,\n \"completion_tokens\": 15,\n \"total_tokens\": 197\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5d47aacc1af2-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:32 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg;
path=/; expires=Thu, 12-Sep-24 08:30:32 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '352'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999781'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_3ce8d1ab53beacd087e70d43f2dd1fbf
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON.\n\nThe json should have the
following structure, with the following keys:\n{\n score: int\n}"}], "model":
"gpt-4o", "tool_choice": {"type": "function", "function": {"name": "ScoreOutput"}},
"tools": [{"type": "function", "function": {"name": "ScoreOutput", "description":
"Correctly extracted `ScoreOutput` with all the required parameters with correct
types", "parameters": {"properties": {"score": {"title": "Score", "type": "integer"}},
"required": ["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '615'
content-type:
- application/json
cookie:
- _cfuvid=uLAishvhwojpVQNsRgyhpZp9roGiBGh8LnHtWbwIqZc-1726009486440-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2fA6JnzoadQsDR6O756Ng1awQl\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128033,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_5ArLOcaht2ENTgacI1oaWFNg\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n
\ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
100,\n \"completion_tokens\": 5,\n \"total_tokens\": 105\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5d50da0301ad-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:34 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=HvJmZMMILh3L8ER1.CKQZK_SCiH.I_p.f.0Apd9J48w-1726128034-1.0.1.1-CCUvpxYqRyncCGONMzj0JABjEIfF9ZCXPucIlUYcFx5nhgjbtgEDHW0gkIaswYymxaf47tij7g4Y3etwuMaWWQ;
path=/; expires=Thu, 12-Sep-24 08:30:34 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=DJdNqfKDS.BcnhYjawtnaAt.yKPbCuXfgDNkS.B3BdI-1726128034247-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '160'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999947'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_306aa86f9d0663d6a2f38fa479b42fa0
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Given the score the title
''The impact of AI in the future of work'' got, give me an integer score between
1-5 for the following title: ''Return of the Jedi''\n\nThis is the expect criteria
for your final answer: The score of the title. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\n4\n\nBegin! This is VERY important to you, use the tools
available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1008'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2giNphqJXaySSn6gRhIwpGncyK\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128034,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
205,\n \"completion_tokens\": 15,\n \"total_tokens\": 220\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5d577fd91af2-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:35 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:
- '234'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999757'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_edc84a9a3462d816ad85c31928040590
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON.\n\nThe json should have the
following structure, with the following keys:\n{\n score: int\n}"}], "model":
"gpt-4o", "tool_choice": {"type": "function", "function": {"name": "ScoreOutput"}},
"tools": [{"type": "function", "function": {"name": "ScoreOutput", "description":
"Correctly extracted `ScoreOutput` with all the required parameters with correct
types", "parameters": {"properties": {"score": {"title": "Score", "type": "integer"}},
"required": ["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '615'
content-type:
- application/json
cookie:
- _cfuvid=DJdNqfKDS.BcnhYjawtnaAt.yKPbCuXfgDNkS.B3BdI-1726128034247-0.0.1.1-604800000;
__cf_bm=HvJmZMMILh3L8ER1.CKQZK_SCiH.I_p.f.0Apd9J48w-1726128034-1.0.1.1-CCUvpxYqRyncCGONMzj0JABjEIfF9ZCXPucIlUYcFx5nhgjbtgEDHW0gkIaswYymxaf47tij7g4Y3etwuMaWWQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2hOd373qgnC93kzewjR8fKrTW0\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128035,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_4i2tHv0f0hgbuKZGsLeyhDCj\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n
\ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
100,\n \"completion_tokens\": 5,\n \"total_tokens\": 105\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5d5c4dd801ad-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:35 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:
- '202'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999947'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_273ef8f01c69557565317a041b446de9
http_version: HTTP/1.1
status_code: 200
version: 1

210
tests/cassettes/test_save_task_json_output.yaml Normal file
View File

@@ -0,0 +1,210 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Give me an integer score
between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
is the expect criteria for your final answer: The score of the title. \n you
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '909'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2tsOmxegTTpYlo196QAIvorcKp\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128047,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
182,\n \"completion_tokens\": 15,\n \"total_tokens\": 197\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5da67ef86280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:47 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:
- '316'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999781'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_bead24fae4a8e2bf9439756b0e6a03cc
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON.\n\nThe json should have the
following structure, with the following keys:\n{\n score: int\n}"}], "model":
"gpt-4o", "tool_choice": {"type": "function", "function": {"name": "ScoreOutput"}},
"tools": [{"type": "function", "function": {"name": "ScoreOutput", "description":
"Correctly extracted `ScoreOutput` with all the required parameters with correct
types", "parameters": {"properties": {"score": {"title": "Score", "type": "integer"}},
"required": ["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '615'
content-type:
- application/json
cookie:
- _cfuvid=DJdNqfKDS.BcnhYjawtnaAt.yKPbCuXfgDNkS.B3BdI-1726128034247-0.0.1.1-604800000;
__cf_bm=HvJmZMMILh3L8ER1.CKQZK_SCiH.I_p.f.0Apd9J48w-1726128034-1.0.1.1-CCUvpxYqRyncCGONMzj0JABjEIfF9ZCXPucIlUYcFx5nhgjbtgEDHW0gkIaswYymxaf47tij7g4Y3etwuMaWWQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2u1dV64KHe8QVBv3oD89yp9tJW\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128048,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_EBHpz2Bkwsu2Ie4109O51Eoo\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n
\ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
100,\n \"completion_tokens\": 5,\n \"total_tokens\": 105\n },\n \"system_fingerprint\":
\"fp_992d1ea92d\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5dad9d540301-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:48 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:
- '196'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999947'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4e19d159a63421b2d0b0a7a7c11489af
http_version: HTTP/1.1
status_code: 200
version: 1

106
tests/cassettes/test_save_task_output.yaml Normal file
View File

@@ -0,0 +1,106 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Give me an integer score
between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
is the expect criteria for your final answer: The score of the title. \n you
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '909'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2sZAC3NtbvLSyhTumukly2REto\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128046,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
182,\n \"completion_tokens\": 15,\n \"total_tokens\": 197\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5da15d5a6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:46 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '364'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999781'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_1e108a5a00881be38068f863f86e2afe
http_version: HTTP/1.1
status_code: 200
version: 1

210
tests/cassettes/test_save_task_pydantic_output.yaml Normal file
View File

@@ -0,0 +1,210 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Give me an integer score
between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
is the expect criteria for your final answer: The score of the title. \n you
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '909'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2v3sFvrWI04jIQPBku2UsieKJH\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128049,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
182,\n \"completion_tokens\": 15,\n \"total_tokens\": 197\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5db2ab346280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:49 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:
- '473'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999781'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c8ebab919704c382e98ebaa37d38acbf
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON.\n\nThe json should have the
following structure, with the following keys:\n{\n score: int\n}"}], "model":
"gpt-4o", "tool_choice": {"type": "function", "function": {"name": "ScoreOutput"}},
"tools": [{"type": "function", "function": {"name": "ScoreOutput", "description":
"Correctly extracted `ScoreOutput` with all the required parameters with correct
types", "parameters": {"properties": {"score": {"title": "Score", "type": "integer"}},
"required": ["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '615'
content-type:
- application/json
cookie:
- _cfuvid=DJdNqfKDS.BcnhYjawtnaAt.yKPbCuXfgDNkS.B3BdI-1726128034247-0.0.1.1-604800000;
__cf_bm=HvJmZMMILh3L8ER1.CKQZK_SCiH.I_p.f.0Apd9J48w-1726128034-1.0.1.1-CCUvpxYqRyncCGONMzj0JABjEIfF9ZCXPucIlUYcFx5nhgjbtgEDHW0gkIaswYymxaf47tij7g4Y3etwuMaWWQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A6Z2wEFmgPol9lGW6nBEHYxyiVSBh\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128050,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_gdR0ZHNDoNnUor7loDVKvVq4\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n
\ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
100,\n \"completion_tokens\": 5,\n \"total_tokens\": 105\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5db8596d0301-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:00:50 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:
- '244'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999947'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_74a3f638e7ee61db84371dec8a32f4d5
http_version: HTTP/1.1
status_code: 200
version: 1