Files
crewAI/tests/cassettes/test_task_tools_override_agent_tools.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

248 lines
10 KiB
YAML

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and is now working on doing research and
analysis for a new customer.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: Another Test Tool\nTool Arguments: {''query'': {''description'': ''Query
to process'', ''type'': ''str''}}\nTool Description: Another test tool\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Another Test 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: Write a test
task\n\nThis is the expect criteria for your final answer: Test output\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:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1525'
content-type:
- application/json
cookie:
- _cfuvid=eQzzWvIXDS8Me1OIBdCG5F1qFyVfAo3sumvYRE7J41E-1734965710778-0.0.1.1-604800000
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-AmjYyKbTn42DzaLVOjDvJpLubTjSq\",\n \"object\":
\"chat.completion\",\n \"created\": 1736178252,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Action: Another Test Tool\\nAction Input:
{\\\"query\\\": \\\"AI and AI agents\\\"}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 295,\n \"completion_tokens\": 18,\n
\ \"total_tokens\": 313,\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\":
\"fp_5f20662549\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fdcd3fc9a56bf66-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 06 Jan 2025 15:44:12 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=X1fuDKrQrN8tU.uxjB0murgJXWXcPtlNLnD7xUrAKTs-1736178252-1.0.1.1-AME9VZZVtEpqX9.BEN_Kj9pI9uK3sIJc2LdbuPsP3wULKxF4Il6r8ghX0to2wpcYsGWbJXSqWP.dQz4vGf_Gbw;
path=/; expires=Mon, 06-Jan-25 16:14:12 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=mv42xOepGYaNopc5ovT9Ajamw5rJrze8tlWTik8lfrk-1736178252935-0.0.1.1-604800000;
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:
- '632'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999644'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_9276753b2200fc95c74fc43c9d7d84a6
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and is now working on doing research and
analysis for a new customer.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: Another Test Tool\nTool Arguments: {''query'': {''description'': ''Query
to process'', ''type'': ''str''}}\nTool Description: Another test tool\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Another Test 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: Write a test
task\n\nThis is the expect criteria for your final answer: Test output\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":
"Action: Another Test Tool\nAction Input: {\"query\": \"AI and AI agents\"}\nObservation:
Another processed: AI and AI agents"}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1687'
content-type:
- application/json
cookie:
- _cfuvid=mv42xOepGYaNopc5ovT9Ajamw5rJrze8tlWTik8lfrk-1736178252935-0.0.1.1-604800000;
__cf_bm=X1fuDKrQrN8tU.uxjB0murgJXWXcPtlNLnD7xUrAKTs-1736178252-1.0.1.1-AME9VZZVtEpqX9.BEN_Kj9pI9uK3sIJc2LdbuPsP3wULKxF4Il6r8ghX0to2wpcYsGWbJXSqWP.dQz4vGf_Gbw
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-AmjYzChV9s4D4qOJJvTvBAt3kRh7n\",\n \"object\":
\"chat.completion\",\n \"created\": 1736178253,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: Another processed: AI and AI agents\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 326,\n \"completion_tokens\":
19,\n \"total_tokens\": 345,\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\":
\"fp_5f20662549\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fdcd4011938bf66-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 06 Jan 2025 15:44:15 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:
- '2488'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999613'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5e3a1a90ef91ff4f12d5b84e396beccc
http_version: HTTP/1.1
status_code: 200
version: 1