andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 23:58:34 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
78bf008c366aa95487819761e4b001c117cb0a25
crewAI/tests/cassettes/test_agent_repeated_tool_usage.yaml
João Moura 1c7f9826b4 adding new converter logic
2024-02-22 15:16:17 -03:00

489 lines
19 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalYou have access to ONLY the following tools, use
one at time:\n\nget_final_answer: get_final_answer(anything: str) -> float -
Get the final answer but don''t give it yet, just re-use this\n tool
non-stop.\n\nTo use a tool you MUST use the exact following format:\n\n```\nUse
Tool: the tool you wanna use, should be one of [get_final_answer] and absolute
all relevant input and context for using the tool, you must use only one tool
at once.\nResult: [result of the tool]\n```\n\nTo give your final answer use
the exact following format:\n\n```\nFinal Answer: [THE MOST COMPLETE ANSWE WITH
ALL CONTEXT, DO NOT LEAVE ANYTHING OUT]\n```\nI MUST use these formats, my jobs
depends on it!This is the summary of your work so far:\n\n\nCurrent Task: The
final answer is 42. But don''t give it until I tell you so, instead keep using
the `get_final_answer` tool.\n\n Begin! This is VERY important to you, your
job depends on it!\n\n\n"}], "model": "gpt-4-0125-preview", "n": 1, "stop":
["\nResult"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '1145'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-8umSlvb0E49ZRvWth5FKSw9Me8O4a","object":"chat.completion.chunk","created":1708543351,"model":"gpt-4-0125-preview","system_fingerprint":"fp_f084bcfc79","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSlvb0E49ZRvWth5FKSw9Me8O4a","object":"chat.completion.chunk","created":1708543351,"model":"gpt-4-0125-preview","system_fingerprint":"fp_f084bcfc79","choices":[{"index":0,"delta":{"content":"Use"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSlvb0E49ZRvWth5FKSw9Me8O4a","object":"chat.completion.chunk","created":1708543351,"model":"gpt-4-0125-preview","system_fingerprint":"fp_f084bcfc79","choices":[{"index":0,"delta":{"content":"
Tool"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSlvb0E49ZRvWth5FKSw9Me8O4a","object":"chat.completion.chunk","created":1708543351,"model":"gpt-4-0125-preview","system_fingerprint":"fp_f084bcfc79","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSlvb0E49ZRvWth5FKSw9Me8O4a","object":"chat.completion.chunk","created":1708543351,"model":"gpt-4-0125-preview","system_fingerprint":"fp_f084bcfc79","choices":[{"index":0,"delta":{"content":"
get"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSlvb0E49ZRvWth5FKSw9Me8O4a","object":"chat.completion.chunk","created":1708543351,"model":"gpt-4-0125-preview","system_fingerprint":"fp_f084bcfc79","choices":[{"index":0,"delta":{"content":"_final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSlvb0E49ZRvWth5FKSw9Me8O4a","object":"chat.completion.chunk","created":1708543351,"model":"gpt-4-0125-preview","system_fingerprint":"fp_f084bcfc79","choices":[{"index":0,"delta":{"content":"_answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSlvb0E49ZRvWth5FKSw9Me8O4a","object":"chat.completion.chunk","created":1708543351,"model":"gpt-4-0125-preview","system_fingerprint":"fp_f084bcfc79","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85915bc79a85a537-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Type:
- text/event-stream
Date:
- Wed, 21 Feb 2024 19:22:31 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=yNWN6xxJzIde4UgAgONRHE3BZJmmCPGu7Ch2r8cft9A-1708543351-1.0-ASCEMu/lL3CxJvBcFTc1tUBtRrna4KuvHkF7gIGXFGT7IzdbHGcbdzKpMclXH0YRkPX7kIeGPEhgHxYfptOxLlM=;
path=/; expires=Wed, 21-Feb-24 19:52:31 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=rc0f50rp.We1R7UrhqtjVUfOr0VA90lt_6hQ5eO2240-1708543351878-0.0-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0125-preview
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '595'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '800000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '799739'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 19ms
x-request-id:
- req_5811f8911568932229521026f504c92b
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Tools available:\n###\nTool
Name: get_final_answer\nTool Description: get_final_answer(anything: str) ->
float - Get the final answer but don''t give it yet, just re-use this\n tool
non-stop.\nTool Arguments: {''anything'': {''type'': ''string''}}\n\nReturn
a valid schema for the tool, the tool name must be equal one of the options,
use this text to inform a valid ouput schema:\nUse Tool: get_final_answer```"},
{"role": "system", "content": "The schema should have the following structure,
only two keys:\n- tool_name: str\n- arguments: dict (with all arguments being
passed)\n\nExample:\n{\"tool_name\": \"tool name\", \"arguments\": {\"arg_name1\":
\"value\", \"arg_name2\": 2}}"}], "model": "gpt-4-0125-preview", "tool_choice":
{"type": "function", "function": {"name": "InstructorToolCalling"}}, "tools":
[{"type": "function", "function": {"name": "InstructorToolCalling", "description":
"Correctly extracted `InstructorToolCalling` with all the required parameters
with correct types", "parameters": {"properties": {"tool_name": {"description":
"The name of the tool to be called.", "title": "Tool Name", "type": "string"},
"arguments": {"anyOf": [{"type": "object"}, {"type": "null"}], "description":
"A dictinary of arguments to be passed to the tool.", "title": "Arguments"}},
"required": ["arguments", "tool_name"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '1393'
content-type:
- application/json
cookie:
- __cf_bm=yNWN6xxJzIde4UgAgONRHE3BZJmmCPGu7Ch2r8cft9A-1708543351-1.0-ASCEMu/lL3CxJvBcFTc1tUBtRrna4KuvHkF7gIGXFGT7IzdbHGcbdzKpMclXH0YRkPX7kIeGPEhgHxYfptOxLlM=;
_cfuvid=rc0f50rp.We1R7UrhqtjVUfOr0VA90lt_6hQ5eO2240-1708543351878-0.0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
IZgMACD+N1V3LdO/N7tV1pTS8HEYIZmEpuae///mg0OL9qBoLVr3RK+AEgw7aZhNwQ/+P9DHdE4f
YzyNShGHvMC2zx4SIpgUjKBWslYu2vascS9u+7kt3ieft1fvT8OPLL74/ufNJj2t0EqIEJa/WtWc
TMfFwDLBQ8jI5Xs6BaP+tDcbj4bD8YD4yIVUWzBCHuv2qN3rD8btKOmy3nDvroJRugKjn4SI6DCa
EOH79yMw6rVWSW8MFQz4JyKUwWowgqwqU9XS12gBQPq6WUa+sZa4VIdghZLWCsd79DAHynpVWive
Vu7zPLvdngyfR0/bbzNW5evqu76SiW8v7uKhKE+MXgxFG2MCc0Tw0vGrVz6U++9C+RqCPZHWGp9v
5hLh0gtghAN/sne8dJqDceS6Fpnx0grpq40uOVqcrcLBDhwGhFXSq+dbaiqZa47/fygE/VcPmNOL
yvyrfh1syGMZllVhkAYPEa8cWwMjVHWIYvz/hGhhEsPmli8hlsHFWtThT/sKjAaTUUNghQAh98cF
/DQCQPMG03lyShaZCTZEZnyuy1gaCzmALIqsNxstVaamcyT/iQED
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85915bcfcd52a537-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- br
Content-Type:
- application/json
Date:
- Wed, 21 Feb 2024 19:22:34 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0125-preview
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1629'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '800000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '799825'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 13ms
x-request-id:
- req_fdf979d873b6bedc600dbe2d9a119f05
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalYou have access to ONLY the following tools, use
one at time:\n\nget_final_answer: get_final_answer(anything: str) -> float -
Get the final answer but don''t give it yet, just re-use this\n tool
non-stop.\n\nTo use a tool you MUST use the exact following format:\n\n```\nUse
Tool: the tool you wanna use, should be one of [get_final_answer] and absolute
all relevant input and context for using the tool, you must use only one tool
at once.\nResult: [result of the tool]\n```\n\nTo give your final answer use
the exact following format:\n\n```\nFinal Answer: [THE MOST COMPLETE ANSWE WITH
ALL CONTEXT, DO NOT LEAVE ANYTHING OUT]\n```\nI MUST use these formats, my jobs
depends on it!This is the summary of your work so far:\n\n\nCurrent Task: The
final answer is 42. But don''t give it until I tell you so, instead keep using
the `get_final_answer` tool.\n\n Begin! This is VERY important to you, your
job depends on it!\n\n\nUse Tool: get_final_answer\nResult: 42\n\nIf you don''t
need to use any more tools, make sure use the correct format to give your final
answer:\n\n```Final Answer: [entire content of your most complete final answer
goes here]```\n You MUST use these formats, your jobs depends on it!\n"}], "model":
"gpt-4-0125-preview", "n": 1, "stop": ["\nResult"], "stream": true, "temperature":
0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '1430'
content-type:
- application/json
cookie:
- __cf_bm=yNWN6xxJzIde4UgAgONRHE3BZJmmCPGu7Ch2r8cft9A-1708543351-1.0-ASCEMu/lL3CxJvBcFTc1tUBtRrna4KuvHkF7gIGXFGT7IzdbHGcbdzKpMclXH0YRkPX7kIeGPEhgHxYfptOxLlM=;
_cfuvid=rc0f50rp.We1R7UrhqtjVUfOr0VA90lt_6hQ5eO2240-1708543351878-0.0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-8umSotD3VfmGvWS89RCR98d94YN56","object":"chat.completion.chunk","created":1708543354,"model":"gpt-4-0125-preview","system_fingerprint":"fp_d0c0cfacb3","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSotD3VfmGvWS89RCR98d94YN56","object":"chat.completion.chunk","created":1708543354,"model":"gpt-4-0125-preview","system_fingerprint":"fp_d0c0cfacb3","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSotD3VfmGvWS89RCR98d94YN56","object":"chat.completion.chunk","created":1708543354,"model":"gpt-4-0125-preview","system_fingerprint":"fp_d0c0cfacb3","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSotD3VfmGvWS89RCR98d94YN56","object":"chat.completion.chunk","created":1708543354,"model":"gpt-4-0125-preview","system_fingerprint":"fp_d0c0cfacb3","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSotD3VfmGvWS89RCR98d94YN56","object":"chat.completion.chunk","created":1708543354,"model":"gpt-4-0125-preview","system_fingerprint":"fp_d0c0cfacb3","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSotD3VfmGvWS89RCR98d94YN56","object":"chat.completion.chunk","created":1708543354,"model":"gpt-4-0125-preview","system_fingerprint":"fp_d0c0cfacb3","choices":[{"index":0,"delta":{"content":"42"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8umSotD3VfmGvWS89RCR98d94YN56","object":"chat.completion.chunk","created":1708543354,"model":"gpt-4-0125-preview","system_fingerprint":"fp_d0c0cfacb3","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85915bdb9be6a537-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Type:
- text/event-stream
Date:
- Wed, 21 Feb 2024 19:22:34 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0125-preview
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '475'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '800000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '799670'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 24ms
x-request-id:
- req_d2c8ba56102d51a77a7088ed56eaf8c5
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
lines of conversation provided, adding onto the previous summary returning a
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
of artificial intelligence. The AI thinks artificial intelligence is a force
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
intelligence is a force for good?\nAI: Because artificial intelligence will
help humans reach their full potential.\n\nNew summary:\nThe human asks what
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
is a force for good because it will help humans reach their full potential.\nEND
OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final
answer is 42. But don''t give it until I tell you so, instead keep using the
`get_final_answer` tool.\nAI: 42\n\nNew summary:"}], "model": "gpt-4-0125-preview",
"n": 1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '977'
content-type:
- application/json
cookie:
- __cf_bm=yNWN6xxJzIde4UgAgONRHE3BZJmmCPGu7Ch2r8cft9A-1708543351-1.0-ASCEMu/lL3CxJvBcFTc1tUBtRrna4KuvHkF7gIGXFGT7IzdbHGcbdzKpMclXH0YRkPX7kIeGPEhgHxYfptOxLlM=;
_cfuvid=rc0f50rp.We1R7UrhqtjVUfOr0VA90lt_6hQ5eO2240-1708543351878-0.0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
IeAJACB+6vR3L9PTzSGteIsy/V6pBkw7C5ukH94CGShuhxt9PTrq+fS3C7MAp4FHvyUYeGC9TXz6
g3Bnt6t3TwIgnZAExXno4tpU3rKrX8xmf9xeH+5e3vT3k12v3PXzZM2zzSf1BEAcFSp2nLwfYhBq
bkggc/meSkhitBguZ9PJZDZDPqo5URVJUGacN/WGo/HMy5Iu1Y57N2cdK0sSPwIATqcZQPPvpyQx
7EEhGkOTJPwJoJYrRRIUWqutCxtHPYJe+bolCXrNFQZFHDRSiu3AjzvrKzjGTrs85yoBf0p1E1YI
G7tTbd+tjraYjnPqR4zOKgFRkCnnsxC/EsAxV2pcFSZ9FC9k6ia6ngAhdao6IOqFmgLbTsd9uoO4
XP6u4sy0HFmSaLqqwkFhOeQ38VojCbKOjYjoIoA/J487vx2Qabk2zndcqsa+GZWJ6F17FHI6Wr1v
GOjh7Hg0ElYKyvW/4qe6yVRrWu3z7dT46XA5jeI0XqxIXIQBAw==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85915be1aca3a537-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- br
Content-Type:
- application/json
Date:
- Wed, 21 Feb 2024 19:22:37 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0125-preview
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2510'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '800000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '799774'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 16ms
x-request-id:
- req_5850b110143112eb39fed9077edbe8f8
status:
code: 200
message: OK
version: 1
Reference in New Issue View Git Blame Copy Permalink