Files
crewAI/tests/cassettes/test_agent_execute_task_with_tool.yaml
Brandon Hancock (bhancock_ai) 8f57753656 Brandon/eng 266 conversation crew v1 (#1843)
* worked on foundation for new conversational crews. Now going to work on chatting.

* core loop should be working and ready for testing.

* high level chat working

* its alive!!

* Added in Joaos feedback to steer crew chats back towards the purpose of the crew

* properly return tool call result

* accessing crew directly instead of through uv commands

* everything is working for conversation now

* Fix linting

* fix llm_utils.py and other type errors

* fix more type errors

* fixing type error

* More fixing of types

* fix failing tests

* Fix more failing tests

* adding tests. cleaing up pr.

* improve

* drop old functions

* improve type hintings
2025-01-06 16:12:43 -05:00

241 lines
9.5 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: dummy_tool\nTool
Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
Useful for when you need to get a dummy result for a query.\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [dummy_tool], 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"}, {"role": "user", "content": "\nCurrent Task: Use the dummy tool
to get a result for ''test query''\n\nThis is the expect criteria for your final
answer: The result from the dummy tool\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-3.5-turbo", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1363'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AmjTkjHtNtJfKGo6wS35grXEzfoqv\",\n \"object\":
\"chat.completion\",\n \"created\": 1736177928,\n \"model\": \"gpt-3.5-turbo-0125\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I should use the dummy tool to get a
result for the 'test query'.\\n\\nAction: dummy_tool\\nAction Input: {\\\"query\\\":
\\\"test query\\\"}\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
271,\n \"completion_tokens\": 31,\n \"total_tokens\": 302,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fdccc13af387bb2-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 06 Jan 2025 15:38:48 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=PdbRW9vzO7559czIqn0xmXQjbN8_vV_J7k1DlkB4d_Y-1736177928-1.0.1.1-7yNcyljwqHI.TVflr9ZnkS705G.K5hgPbHpxRzcO3ZMFi5lHCBPs_KB5pFE043wYzPmDIHpn6fu6jIY9mlNoLQ;
path=/; expires=Mon, 06-Jan-25 16:08:48 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=lOOz0FbrrPaRb4IFEeHNcj7QghHzxI1tTV2N0jD9icA-1736177928767-0.0.1.1-604800000;
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:
- '444'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '50000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '49999686'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5b3e93f5d4e6ab8feef83dc26b6eb623
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: dummy_tool\nTool
Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
Useful for when you need to get a dummy result for a query.\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [dummy_tool], 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"}, {"role": "user", "content": "\nCurrent Task: Use the dummy tool
to get a result for ''test query''\n\nThis is the expect criteria for your final
answer: The result from the dummy tool\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}, {"role": "assistant", "content": "I should use the dummy
tool to get a result for the ''test query''.\n\nAction: dummy_tool\nAction Input:
{\"query\": \"test query\"}\nObservation: Dummy result for: test query"}], "model":
"gpt-3.5-turbo", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1574'
content-type:
- application/json
cookie:
- __cf_bm=PdbRW9vzO7559czIqn0xmXQjbN8_vV_J7k1DlkB4d_Y-1736177928-1.0.1.1-7yNcyljwqHI.TVflr9ZnkS705G.K5hgPbHpxRzcO3ZMFi5lHCBPs_KB5pFE043wYzPmDIHpn6fu6jIY9mlNoLQ;
_cfuvid=lOOz0FbrrPaRb4IFEeHNcj7QghHzxI1tTV2N0jD9icA-1736177928767-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AmjTkjtDnt98YQ3k4y71C523EQM9p\",\n \"object\":
\"chat.completion\",\n \"created\": 1736177928,\n \"model\": \"gpt-3.5-turbo-0125\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Final Answer: Dummy result for: test
query\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 315,\n \"completion_tokens\":
9,\n \"total_tokens\": 324,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fdccc171b647bb2-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 06 Jan 2025 15:38:49 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:
- '249'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '50000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '49999643'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_cdc7b25a3877bb9a7cb7c6d2645ff447
http_version: HTTP/1.1
status_code: 200
version: 1