Files
crewAI/tests/cassettes/test_agent_custom_max_iterations.yaml
João Moura e77442cf34 Removing LangChain and Rebuilding Executor (#1322)
* rebuilding executor

* removing langchain

* Making all tests good

* fixing types and adding ability for nor using system prompts

* improving types

* pleasing the types gods

* pleasing the types gods

* fixing parser, tools and executor

* making sure all tests pass

* final pass

* fixing type

* Updating Docs

* preparing to cut new version
2024-09-16 14:14:04 -03:00

231 lines
9.2 KiB
YAML

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool.\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:
- '1417'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81cVetqkmlZCzSUuY0W4Z75GIL2n\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476215,\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 as directed to arrive at the final answer, which is 42.\\n\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
291,\n \"completion_tokens\": 38,\n \"total_tokens\": 329,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f91d9be7a2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:35 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:
- '533'
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:
- '29999666'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a5354f860340d65be9701bb6bb47a4e6
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool.\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 keep using the `get_final_answer`
tool as directed to arrive at the final answer, which is 42.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: 42\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:
- '1805'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81cWdzWH4HTYCF2naQrvIP2OM8V3\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476216,\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\":
370,\n \"completion_tokens\": 14,\n \"total_tokens\": 384,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f91defffe2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:36 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:
- '227'
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:
- '29999578'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d5bbf13119e2065e9702b1455b8b7e49
http_version: HTTP/1.1
status_code: 200
version: 1