andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 16:18:30 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge branch 'main' into feature/procedure_v2

Browse Source
This commit is contained in:
Brandon Hancock
2024-07-17 13:37:27 -04:00
parent f737b3b379 5b442e4350
commit c0c329b6e0
24 changed files with 32275 additions and 727 deletions
Download Patch File Download Diff File Expand all files Collapse all files

87
docs/how-to/Conditional-Tasks.md Normal file
View File

@@ -0,0 +1,87 @@
---
title: Conditional Tasks
description: Learn how to use conditional tasks in a crewAI kickoff
---
## Introduction
Conditional Tasks in crewAI allow for dynamic workflow adaptation based on the outcomes of previous tasks. This powerful feature enables crews to make decisions and execute tasks selectively, enhancing the flexibility and efficiency of your AI-driven processes.
```python
from typing import List
from pydantic import BaseModel
from crewai import Agent, Crew
from crewai.tasks.conditional_task import ConditionalTask
from crewai.tasks.task_output import TaskOutput
from crewai.task import Task
from crewai_tools import SerperDevTool
# Define a condition function for the conditional task
# if false task will be skipped, true, then execute task
def is_data_missing(output: TaskOutput) -> bool:
return len(output.pydantic.events) < 10: # this will skip this task
# Define the agents
data_fetcher_agent = Agent(
role="Data Fetcher",
goal="Fetch data online using Serper tool",
backstory="Backstory 1",
verbose=True,
tools=[SerperDevTool()],
)
data_processor_agent = Agent(
role="Data Processor",
goal="Process fetched data",
backstory="Backstory 2",
verbose=True,
)
summary_generator_agent = Agent(
role="Summary Generator",
goal="Generate summary from fetched data",
backstory="Backstory 3",
verbose=True,
)
class EventOutput(BaseModel):
events: List[str]
task1 = Task(
description="Fetch data about events in San Francisco using Serper tool",
expected_output="List of 10 things to do in SF this week",
agent=data_fetcher_agent,
output_pydantic=EventOutput,
)
conditional_task = ConditionalTask(
description="""
Check if data is missing. If we have less than 10 events,
fetch more events using Serper tool so that
we have a total of 10 events in SF this week..
""",
expected_output="List of 10 Things to do in SF this week ",
condition=is_data_missing,
agent=data_processor_agent,
)
task3 = Task(
description="Generate summary of events in San Francisco from fetched data",
expected_output="summary_generated",
agent=summary_generator_agent,
)
# Create a crew with the tasks
crew = Crew(
agents=[data_fetcher_agent, data_processor_agent, summary_generator_agent],
tasks=[task1, conditional_task, task3],
verbose=2,
)
result = crew.kickoff()
print("results", result)
```

5
docs/index.md
View File

@@ -118,6 +118,11 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
Replay from a Task
</a>
</li>
<li>
<a href="./how-to/Conditional-Tasks">
Conditional Tasks
</a>
</li>
<li>
<a href="./how-to/AgentOps-Observability">
Agent Monitoring with AgentOps

1
mkdocs.yml
View File

@@ -146,6 +146,7 @@ nav:
- Kickoff a Crew Asynchronously: 'how-to/Kickoff-async.md'
- Kickoff a Crew for a List: 'how-to/Kickoff-for-each.md'
- Replay from a specific task from a kickoff: 'how-to/Replay-tasks-from-latest-Crew-Kickoff.md'
- Conditional Tasks: 'how-to/Conditional-Tasks.md'
- Agent Monitoring with AgentOps: 'how-to/AgentOps-Observability.md'
- Agent Monitoring with LangTrace: 'how-to/Langtrace-Observability.md'
- Tools Docs:

145
poetry.lock generated
View File

@@ -417,13 +417,13 @@ virtualenv = ["virtualenv (>=20.0.35)"]
[[package]]
name = "cachetools"
version = "5.3.3"
version = "5.4.0"
description = "Extensible memoizing collections and decorators"
optional = false
python-versions = ">=3.7"
files = [
{file = "cachetools-5.3.3-py3-none-any.whl", hash = "sha256:0abad1021d3f8325b2fc1d2e9c8b9c9d57b04c3932657a72465447332c24d945"},
{file = "cachetools-5.3.3.tar.gz", hash = "sha256:ba29e2dfa0b8b556606f097407ed1aa62080ee108ab0dc5ec9d6a723a007d105"},
{file = "cachetools-5.4.0-py3-none-any.whl", hash = "sha256:3ae3b49a3d5e28a77a0be2b37dbcb89005058959cb2323858c2657c4a8cab474"},
{file = "cachetools-5.4.0.tar.gz", hash = "sha256:b8adc2e7c07f105ced7bc56dbb6dfbe7c4a00acce20e2227b3f355be89bc6827"},
]
[[package]]
@@ -758,13 +758,13 @@ all = ["pycocotools (==2.0.6)"]
[[package]]
name = "clarifai-grpc"
version = "10.6.3"
version = "10.6.4"
description = "Clarifai gRPC API Client"
optional = false
python-versions = ">=3.8"
files = [
{file = "clarifai_grpc-10.6.3-py3-none-any.whl", hash = "sha256:304a8123dfe6fb41953026e0e4b800bffc3998a75408f51f3ab2a6eacfb1781e"},
{file = "clarifai_grpc-10.6.3.tar.gz", hash = "sha256:6be24d21f124678384902e693eb9b5d2e5c57aeef57c098e3a2b94e40a79c198"},
{file = "clarifai_grpc-10.6.4-py3-none-any.whl", hash = "sha256:9fb8c94e6ede5e1005010643f516aa7c1dd3c59ab9282e03ba4932fd929d7584"},
{file = "clarifai_grpc-10.6.4.tar.gz", hash = "sha256:84d92b10fc32c17ecf0c0fc30ec4c9960a6a9ee701f2829f0c372892ae761d14"},
]
[package.dependencies]
@@ -789,13 +789,13 @@ colorama = {version = "*", markers = "platform_system == \"Windows\""}
[[package]]
name = "cohere"
version = "5.5.8"
version = "5.6.1"
description = ""
optional = false
python-versions = "<4.0,>=3.8"
files = [
{file = "cohere-5.5.8-py3-none-any.whl", hash = "sha256:e1ed84b90eadd13c6a68ee28e378a0bb955f8945eadc6eb7ee126b3399cafd54"},
{file = "cohere-5.5.8.tar.gz", hash = "sha256:84ce7666ff8fbdf4f41fb5f6ca452ab2639a514bc88967a2854a9b1b820d6ea0"},
{file = "cohere-5.6.1-py3-none-any.whl", hash = "sha256:1c8bcd39a54622d64b83cafb865f102cd2565ce091b0856fd5ce11bf7169109a"},
{file = "cohere-5.6.1.tar.gz", hash = "sha256:5d7efda64f0e512d4cc35aa04b17a6f74b3d8c175a99f2797991a7f31dfac349"},
]
[package.dependencies]
@@ -2014,13 +2014,13 @@ files = [
[[package]]
name = "huggingface-hub"
version = "0.23.4"
version = "0.23.5"
description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
optional = false
python-versions = ">=3.8.0"
files = [
{file = "huggingface_hub-0.23.4-py3-none-any.whl", hash = "sha256:3a0b957aa87150addf0cc7bd71b4d954b78e749850e1e7fb29ebbd2db64ca037"},
{file = "huggingface_hub-0.23.4.tar.gz", hash = "sha256:35d99016433900e44ae7efe1c209164a5a81dbbcd53a52f99c281dcd7ce22431"},
{file = "huggingface_hub-0.23.5-py3-none-any.whl", hash = "sha256:d7a7d337615e11a45cc14a0ce5a605db6b038dc24af42866f731684825226e90"},
{file = "huggingface_hub-0.23.5.tar.gz", hash = "sha256:67a9caba79b71235be3752852ca27da86bd54311d2424ca8afdb8dda056edf98"},
]
[package.dependencies]
@@ -2400,24 +2400,24 @@ tests = ["aiohttp", "duckdb", "pandas (>=1.4)", "polars (>=0.19)", "pytest", "py
[[package]]
name = "langchain"
version = "0.2.7"
version = "0.2.9"
description = "Building applications with LLMs through composability"
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "langchain-0.2.7-py3-none-any.whl", hash = "sha256:98e79e0b9a60a9c740b44d5b0135c85f649219308f30d373cf5f10d0efe18b87"},
{file = "langchain-0.2.7.tar.gz", hash = "sha256:8742f363d2890854501e0075af04fcb470600f201dec251c9bd5841e1990e73d"},
{file = "langchain-0.2.9-py3-none-any.whl", hash = "sha256:be23fcb29adbd5059944f1fed08fa575f0739d420b1c4127531e0fbf5663fcca"},
{file = "langchain-0.2.9.tar.gz", hash = "sha256:cc326a7f6347787a19882928c324433b1a79df629bba45604b2d26495ee5d69c"},
]
[package.dependencies]
aiohttp = ">=3.8.3,<4.0.0"
async-timeout = {version = ">=4.0.0,<5.0.0", markers = "python_version < \"3.11\""}
langchain-core = ">=0.2.12,<0.3.0"
langchain-core = ">=0.2.20,<0.3.0"
langchain-text-splitters = ">=0.2.0,<0.3.0"
langsmith = ">=0.1.17,<0.2.0"
numpy = [
{version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""},
{version = ">=1,<2", markers = "python_version < \"3.12\""},
{version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""},
]
pydantic = ">=1,<3"
PyYAML = ">=5.3"
@@ -2464,8 +2464,8 @@ langchain = ">=0.2.7,<0.3.0"
langchain-core = ">=0.2.12,<0.3.0"
langsmith = ">=0.1.0,<0.2.0"
numpy = [
{version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""},
{version = ">=1,<2", markers = "python_version < \"3.12\""},
{version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""},
]
PyYAML = ">=5.3"
requests = ">=2,<3"
@@ -2474,13 +2474,13 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
[[package]]
name = "langchain-core"
version = "0.2.18"
version = "0.2.20"
description = "Building applications with LLMs through composability"
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "langchain_core-0.2.18-py3-none-any.whl", hash = "sha256:c9dbb197508e76337ed810ec977d40ae0c896397d191b420ef126c3818a1be96"},
{file = "langchain_core-0.2.18.tar.gz", hash = "sha256:ca5c5f1a783449dae8686e366ff3c5b775f8b5cef0de4ef346b8820d3d1c46ff"},
{file = "langchain_core-0.2.20-py3-none-any.whl", hash = "sha256:16cc4da6f7ebf33accea7af45a70480733dc852ab291030fb6924865bd7caf76"},
{file = "langchain_core-0.2.20.tar.gz", hash = "sha256:a66c439e085d8c75f822f7650a5551d17bada4003521173c763d875d949e4ed5"},
]
[package.dependencies]
@@ -2488,8 +2488,8 @@ jsonpatch = ">=1.33,<2.0"
langsmith = ">=0.1.75,<0.2.0"
packaging = ">=23.2,<25"
pydantic = [
{version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
{version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
{version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
]
PyYAML = ">=5.3"
tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
@@ -2541,20 +2541,20 @@ langchain-core = ">=0.2.10,<0.3.0"
[[package]]
name = "langsmith"
version = "0.1.85"
version = "0.1.88"
description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "langsmith-0.1.85-py3-none-any.whl", hash = "sha256:c1f94384f10cea96f7b4d33fd3db7ec180c03c7468877d50846f881d2017ff94"},
{file = "langsmith-0.1.85.tar.gz", hash = "sha256:acff31f9e53efa48586cf8e32f65625a335c74d7c4fa306d1655ac18452296f6"},
{file = "langsmith-0.1.88-py3-none-any.whl", hash = "sha256:460ebb7de440afd150fcea8f54ca8779821f2228cd59e149e5845c9dbe06db16"},
{file = "langsmith-0.1.88.tar.gz", hash = "sha256:28a07dec19197f4808aa2628d5a3ccafcbe14cc137aef0e607bbd128e7907821"},
]
[package.dependencies]
orjson = ">=3.9.14,<4.0.0"
pydantic = [
{version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
{version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
{version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
]
requests = ">=2,<3"
@@ -3278,13 +3278,13 @@ sympy = "*"
[[package]]
name = "openai"
version = "1.35.13"
version = "1.35.14"
description = "The official Python library for the openai API"
optional = false
python-versions = ">=3.7.1"
files = [
{file = "openai-1.35.13-py3-none-any.whl", hash = "sha256:36ec3e93e0d1f243f69be85c89b9221a471c3e450dfd9df16c9829e3cdf63e60"},
{file = "openai-1.35.13.tar.gz", hash = "sha256:c684f3945608baf7d2dcc0ef3ee6f3e27e4c66f21076df0b47be45d57e6ae6e4"},
{file = "openai-1.35.14-py3-none-any.whl", hash = "sha256:adadf8c176e0b8c47ad782ed45dc20ef46438ee1f02c7103c4155cff79c8f68b"},
{file = "openai-1.35.14.tar.gz", hash = "sha256:394ba1dfd12ecec1d634c50e512d24ff1858bbc2674ffcce309b822785a058de"},
]
[package.dependencies]
@@ -3627,9 +3627,9 @@ files = [
[package.dependencies]
numpy = [
{version = ">=1.26.0", markers = "python_version >= \"3.12\""},
{version = ">=1.23.2", markers = "python_version == \"3.11\""},
{version = ">=1.22.4", markers = "python_version < \"3.11\""},
{version = ">=1.26.0", markers = "python_version >= \"3.12\""},
]
python-dateutil = ">=2.8.2"
pytz = ">=2020.1"
@@ -4007,52 +4007,55 @@ files = [
[[package]]
name = "pyarrow"
version = "16.1.0"
version = "17.0.0"
description = "Python library for Apache Arrow"
optional = false
python-versions = ">=3.8"
files = [
{file = "pyarrow-16.1.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:17e23b9a65a70cc733d8b738baa6ad3722298fa0c81d88f63ff94bf25eaa77b9"},
{file = "pyarrow-16.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4740cc41e2ba5d641071d0ab5e9ef9b5e6e8c7611351a5cb7c1d175eaf43674a"},
{file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:98100e0268d04e0eec47b73f20b39c45b4006f3c4233719c3848aa27a03c1aef"},
{file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f68f409e7b283c085f2da014f9ef81e885d90dcd733bd648cfba3ef265961848"},
{file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:a8914cd176f448e09746037b0c6b3a9d7688cef451ec5735094055116857580c"},
{file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:48be160782c0556156d91adbdd5a4a7e719f8d407cb46ae3bb4eaee09b3111bd"},
{file = "pyarrow-16.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:9cf389d444b0f41d9fe1444b70650fea31e9d52cfcb5f818b7888b91b586efff"},
{file = "pyarrow-16.1.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:d0ebea336b535b37eee9eee31761813086d33ed06de9ab6fc6aaa0bace7b250c"},
{file = "pyarrow-16.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2e73cfc4a99e796727919c5541c65bb88b973377501e39b9842ea71401ca6c1c"},
{file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bf9251264247ecfe93e5f5a0cd43b8ae834f1e61d1abca22da55b20c788417f6"},
{file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ddf5aace92d520d3d2a20031d8b0ec27b4395cab9f74e07cc95edf42a5cc0147"},
{file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:25233642583bf658f629eb230b9bb79d9af4d9f9229890b3c878699c82f7d11e"},
{file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a33a64576fddfbec0a44112eaf844c20853647ca833e9a647bfae0582b2ff94b"},
{file = "pyarrow-16.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:185d121b50836379fe012753cf15c4ba9638bda9645183ab36246923875f8d1b"},
{file = "pyarrow-16.1.0-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:2e51ca1d6ed7f2e9d5c3c83decf27b0d17bb207a7dea986e8dc3e24f80ff7d6f"},
{file = "pyarrow-16.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:06ebccb6f8cb7357de85f60d5da50e83507954af617d7b05f48af1621d331c9a"},
{file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b04707f1979815f5e49824ce52d1dceb46e2f12909a48a6a753fe7cafbc44a0c"},
{file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0d32000693deff8dc5df444b032b5985a48592c0697cb6e3071a5d59888714e2"},
{file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:8785bb10d5d6fd5e15d718ee1d1f914fe768bf8b4d1e5e9bf253de8a26cb1628"},
{file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:e1369af39587b794873b8a307cc6623a3b1194e69399af0efd05bb202195a5a7"},
{file = "pyarrow-16.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:febde33305f1498f6df85e8020bca496d0e9ebf2093bab9e0f65e2b4ae2b3444"},
{file = "pyarrow-16.1.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:b5f5705ab977947a43ac83b52ade3b881eb6e95fcc02d76f501d549a210ba77f"},
{file = "pyarrow-16.1.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:0d27bf89dfc2576f6206e9cd6cf7a107c9c06dc13d53bbc25b0bd4556f19cf5f"},
{file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d07de3ee730647a600037bc1d7b7994067ed64d0eba797ac74b2bc77384f4c2"},
{file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fbef391b63f708e103df99fbaa3acf9f671d77a183a07546ba2f2c297b361e83"},
{file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:19741c4dbbbc986d38856ee7ddfdd6a00fc3b0fc2d928795b95410d38bb97d15"},
{file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:f2c5fb249caa17b94e2b9278b36a05ce03d3180e6da0c4c3b3ce5b2788f30eed"},
{file = "pyarrow-16.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:e6b6d3cd35fbb93b70ade1336022cc1147b95ec6af7d36906ca7fe432eb09710"},
{file = "pyarrow-16.1.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:18da9b76a36a954665ccca8aa6bd9f46c1145f79c0bb8f4f244f5f8e799bca55"},
{file = "pyarrow-16.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:99f7549779b6e434467d2aa43ab2b7224dd9e41bdde486020bae198978c9e05e"},
{file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f07fdffe4fd5b15f5ec15c8b64584868d063bc22b86b46c9695624ca3505b7b4"},
{file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ddfe389a08ea374972bd4065d5f25d14e36b43ebc22fc75f7b951f24378bf0b5"},
{file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:3b20bd67c94b3a2ea0a749d2a5712fc845a69cb5d52e78e6449bbd295611f3aa"},
{file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:ba8ac20693c0bb0bf4b238751d4409e62852004a8cf031c73b0e0962b03e45e3"},
{file = "pyarrow-16.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:31a1851751433d89a986616015841977e0a188662fcffd1a5677453f1df2de0a"},
{file = "pyarrow-16.1.0.tar.gz", hash = "sha256:15fbb22ea96d11f0b5768504a3f961edab25eaf4197c341720c4a387f6c60315"},
{file = "pyarrow-17.0.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:a5c8b238d47e48812ee577ee20c9a2779e6a5904f1708ae240f53ecbee7c9f07"},
{file = "pyarrow-17.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:db023dc4c6cae1015de9e198d41250688383c3f9af8f565370ab2b4cb5f62655"},
{file = "pyarrow-17.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:da1e060b3876faa11cee287839f9cc7cdc00649f475714b8680a05fd9071d545"},
{file = "pyarrow-17.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75c06d4624c0ad6674364bb46ef38c3132768139ddec1c56582dbac54f2663e2"},
{file = "pyarrow-17.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:fa3c246cc58cb5a4a5cb407a18f193354ea47dd0648194e6265bd24177982fe8"},
{file = "pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:f7ae2de664e0b158d1607699a16a488de3d008ba99b3a7aa5de1cbc13574d047"},
{file = "pyarrow-17.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:5984f416552eea15fd9cee03da53542bf4cddaef5afecefb9aa8d1010c335087"},
{file = "pyarrow-17.0.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:1c8856e2ef09eb87ecf937104aacfa0708f22dfeb039c363ec99735190ffb977"},
{file = "pyarrow-17.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2e19f569567efcbbd42084e87f948778eb371d308e137a0f97afe19bb860ccb3"},
{file = "pyarrow-17.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6b244dc8e08a23b3e352899a006a26ae7b4d0da7bb636872fa8f5884e70acf15"},
{file = "pyarrow-17.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b72e87fe3e1db343995562f7fff8aee354b55ee83d13afba65400c178ab2597"},
{file = "pyarrow-17.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:dc5c31c37409dfbc5d014047817cb4ccd8c1ea25d19576acf1a001fe07f5b420"},
{file = "pyarrow-17.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:e3343cb1e88bc2ea605986d4b94948716edc7a8d14afd4e2c097232f729758b4"},
{file = "pyarrow-17.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:a27532c38f3de9eb3e90ecab63dfda948a8ca859a66e3a47f5f42d1e403c4d03"},
{file = "pyarrow-17.0.0-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:9b8a823cea605221e61f34859dcc03207e52e409ccf6354634143e23af7c8d22"},
{file = "pyarrow-17.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:f1e70de6cb5790a50b01d2b686d54aaf73da01266850b05e3af2a1bc89e16053"},
{file = "pyarrow-17.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0071ce35788c6f9077ff9ecba4858108eebe2ea5a3f7cf2cf55ebc1dbc6ee24a"},
{file = "pyarrow-17.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:757074882f844411fcca735e39aae74248a1531367a7c80799b4266390ae51cc"},
{file = "pyarrow-17.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:9ba11c4f16976e89146781a83833df7f82077cdab7dc6232c897789343f7891a"},
{file = "pyarrow-17.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:b0c6ac301093b42d34410b187bba560b17c0330f64907bfa4f7f7f2444b0cf9b"},
{file = "pyarrow-17.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:392bc9feabc647338e6c89267635e111d71edad5fcffba204425a7c8d13610d7"},
{file = "pyarrow-17.0.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:af5ff82a04b2171415f1410cff7ebb79861afc5dae50be73ce06d6e870615204"},
{file = "pyarrow-17.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:edca18eaca89cd6382dfbcff3dd2d87633433043650c07375d095cd3517561d8"},
{file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7c7916bff914ac5d4a8fe25b7a25e432ff921e72f6f2b7547d1e325c1ad9d155"},
{file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f553ca691b9e94b202ff741bdd40f6ccb70cdd5fbf65c187af132f1317de6145"},
{file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:0cdb0e627c86c373205a2f94a510ac4376fdc523f8bb36beab2e7f204416163c"},
{file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:d7d192305d9d8bc9082d10f361fc70a73590a4c65cf31c3e6926cd72b76bc35c"},
{file = "pyarrow-17.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:02dae06ce212d8b3244dd3e7d12d9c4d3046945a5933d28026598e9dbbda1fca"},
{file = "pyarrow-17.0.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:13d7a460b412f31e4c0efa1148e1d29bdf18ad1411eb6757d38f8fbdcc8645fb"},
{file = "pyarrow-17.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9b564a51fbccfab5a04a80453e5ac6c9954a9c5ef2890d1bcf63741909c3f8df"},
{file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:32503827abbc5aadedfa235f5ece8c4f8f8b0a3cf01066bc8d29de7539532687"},
{file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a155acc7f154b9ffcc85497509bcd0d43efb80d6f733b0dc3bb14e281f131c8b"},
{file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:dec8d129254d0188a49f8a1fc99e0560dc1b85f60af729f47de4046015f9b0a5"},
{file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:a48ddf5c3c6a6c505904545c25a4ae13646ae1f8ba703c4df4a1bfe4f4006bda"},
{file = "pyarrow-17.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:42bf93249a083aca230ba7e2786c5f673507fa97bbd9725a1e2754715151a204"},
{file = "pyarrow-17.0.0.tar.gz", hash = "sha256:4beca9521ed2c0921c1023e68d097d0299b62c362639ea315572a58f3f50fd28"},
]
[package.dependencies]
numpy = ">=1.16.6"
[package.extras]
test = ["cffi", "hypothesis", "pandas", "pytest", "pytz"]
[[package]]
name = "pyasn1"
version = "0.6.0"
@@ -4104,8 +4107,8 @@ files = [
annotated-types = ">=0.4.0"
pydantic-core = "2.20.1"
typing-extensions = [
{version = ">=4.12.2", markers = "python_version >= \"3.13\""},
{version = ">=4.6.1", markers = "python_version < \"3.13\""},
{version = ">=4.12.2", markers = "python_version >= \"3.13\""},
]
[package.extras]
@@ -4334,13 +4337,13 @@ files = [
[[package]]
name = "pyright"
version = "1.1.371"
version = "1.1.372"
description = "Command line wrapper for pyright"
optional = false
python-versions = ">=3.7"
files = [
{file = "pyright-1.1.371-py3-none-any.whl", hash = "sha256:cce52e42ff73943243e7e5e24f2a59dee81b97d99f4e3cf97370b27e8a1858cd"},
{file = "pyright-1.1.371.tar.gz", hash = "sha256:777b508b92dda2db476214c400ce043aad8d8f3dd0e10d284c96e79f298308b5"},
{file = "pyright-1.1.372-py3-none-any.whl", hash = "sha256:25b15fb8967740f0949fd35b963777187f0a0404c0bd753cc966ec139f3eaa0b"},
{file = "pyright-1.1.372.tar.gz", hash = "sha256:a9f5e0daa955daaa17e3d1ef76d3623e75f8afd5e37b437d3ff84d5b38c15420"},
]
[package.dependencies]

2
src/crewai/agent.py
View File

@@ -205,7 +205,7 @@ class Agent(BaseAgent):
self._times_executed += 1
if self._times_executed > self.max_retry_limit:
raise e
return self.execute_task(task, context, tools)
result = self.execute_task(task, context, tools)
if self.max_rpm:
self._rpm_controller.stop_rpm_counter()

2
src/crewai/agents/executor.py
View File

@@ -242,6 +242,8 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
else:
if tool_calling.tool_name.casefold().strip() in [
name.casefold().strip() for name in name_to_tool_map
] or tool_calling.tool_name.casefold().replace("_", " ") in [
name.casefold().strip() for name in name_to_tool_map
]:
observation = tool_usage.use(tool_calling, agent_action.log)
else:

98
src/crewai/crew.py
View File

@@ -28,6 +28,7 @@ from crewai.memory.long_term.long_term_memory import LongTermMemory
from crewai.memory.short_term.short_term_memory import ShortTermMemory
from crewai.process import Process
from crewai.task import Task
from crewai.tasks.conditional_task import ConditionalTask
from crewai.tasks.task_output import TaskOutput
from crewai.telemetry import Telemetry
from crewai.tools.agent_tools import AgentTools
@@ -294,6 +295,29 @@ class Crew(BaseModel):
return self
@model_validator(mode="after")
def validate_first_task(self) -> "Crew":
"""Ensure the first task is not a ConditionalTask."""
if self.tasks and isinstance(self.tasks[0], ConditionalTask):
raise PydanticCustomError(
"invalid_first_task",
"The first task cannot be a ConditionalTask.",
{},
)
return self
@model_validator(mode="after")
def validate_async_tasks_not_async(self) -> "Crew":
"""Ensure that ConditionalTask is not async."""
for task in self.tasks:
if task.async_execution and isinstance(task, ConditionalTask):
raise PydanticCustomError(
"invalid_async_conditional_task",
f"Conditional Task: {task.description} , cannot be executed asynchronously.", # type: ignore # Argument of type "str" cannot be assigned to parameter "message_template" of type "LiteralString"
{},
)
return self
@model_validator(mode="after")
def validate_async_task_cannot_include_sequential_async_tasks_in_context(self):
"""
@@ -611,21 +635,27 @@ class Crew(BaseModel):
last_sync_output = task.output
continue
self._prepare_task(task, manager)
if self.process == Process.hierarchical:
agent_to_use = manager
else:
agent_to_use = task.agent
agent_to_use = self._get_agent_to_use(task, manager)
if agent_to_use is None:
raise ValueError(
f"No agent available for task: {task.description}. Ensure that either the task has an assigned agent or a manager agent is provided."
)
self._log_task_start(task, agent_to_use)
self._prepare_agent_tools(task, manager)
self._log_task_start(task, agent_to_use.role)
if isinstance(task, ConditionalTask):
skipped_task_output = self._handle_conditional_task(
task, task_outputs, futures, task_index, was_replayed
)
if skipped_task_output:
continue
if task.async_execution:
context = self._get_context(
task, [last_sync_output] if last_sync_output else []
)
self._log_task_start(task, agent_to_use.role)
future = task.execute_async(
agent=agent_to_use,
context=context,
@@ -634,12 +664,11 @@ class Crew(BaseModel):
futures.append((task, future, task_index))
else:
if futures:
task_outputs.extend(
self._process_async_tasks(futures, was_replayed)
)
task_outputs = self._process_async_tasks(futures, was_replayed)
futures.clear()
context = self._get_context(task, task_outputs)
self._log_task_start(task, agent_to_use.role)
task_output = task.execute_sync(
agent=agent_to_use,
context=context,
@@ -654,12 +683,48 @@ class Crew(BaseModel):
return self._create_crew_output(task_outputs)
def _prepare_task(self, task: Task, manager: Optional[BaseAgent]):
def _handle_conditional_task(
self,
task: ConditionalTask,
task_outputs: List[TaskOutput],
futures: List[Tuple[Task, Future[TaskOutput], int]],
task_index: int,
was_replayed: bool,
) -> Optional[TaskOutput]:
if futures:
task_outputs = self._process_async_tasks(futures, was_replayed)
futures.clear()
previous_output = task_outputs[task_index - 1] if task_outputs else None
if previous_output is not None and not task.should_execute(previous_output):
self._logger.log(
"debug",
f"Skipping conditional task: {task.description}",
color="yellow",
)
skipped_task_output = task.get_skipped_task_output()
if not was_replayed:
self._store_execution_log(task, skipped_task_output, task_index)
return skipped_task_output
return None
def _prepare_agent_tools(self, task: Task, manager: Optional[BaseAgent]):
if self.process == Process.hierarchical:
self._update_manager_tools(task, manager)
if manager:
self._update_manager_tools(task, manager)
else:
raise ValueError("Manager agent is required for hierarchical process.")
elif task.agent and task.agent.allow_delegation:
self._add_delegation_tools(task)
def _get_agent_to_use(
self, task: Task, manager: Optional[BaseAgent]
) -> Optional[BaseAgent]:
if self.process == Process.hierarchical:
return manager
return task.agent
def _add_delegation_tools(self, task: Task):
agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent:
@@ -686,18 +751,17 @@ class Crew(BaseModel):
# Add the new tool
task.tools.append(new_tool)
def _log_task_start(self, task: Task, agent: Optional[BaseAgent]):
def _log_task_start(self, task: Task, role: str = "None"):
color = self._logging_color
role = agent.role if agent else "None"
self._logger.log("debug", f"== Working Agent: {role}", color=color)
self._logger.log("info", f"== Starting Task: {task.description}", color=color)
if self.output_log_file:
self._file_handler.log(agent=role, task=task.description, status="started")
def _update_manager_tools(self, task: Task, manager: Optional[BaseAgent]):
if task.agent and manager:
def _update_manager_tools(self, task: Task, manager: BaseAgent):
if task.agent:
manager.tools = task.agent.get_delegation_tools([task.agent])
if manager:
else:
manager.tools = manager.get_delegation_tools(self.agents)
def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
@@ -737,7 +801,7 @@ class Crew(BaseModel):
futures: List[Tuple[Task, Future[TaskOutput], int]],
was_replayed: bool = False,
) -> List[TaskOutput]:
task_outputs = []
task_outputs: List[TaskOutput] = []
for future_task, future, task_index in futures:
task_output = future.result()
task_outputs.append(task_output)

5
src/crewai/task.py
View File

@@ -8,7 +8,6 @@ from copy import copy
from hashlib import md5
from typing import Any, Dict, List, Optional, Tuple, Type, Union
from langchain_openai import ChatOpenAI
from opentelemetry.trace import Span
from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
@@ -255,9 +254,7 @@ class Task(BaseModel):
content = (
json_output
if json_output
else pydantic_output.model_dump_json()
if pydantic_output
else result
else pydantic_output.model_dump_json() if pydantic_output else result
)
self._save_file(content)

47
src/crewai/tasks/conditional_task.py Normal file
View File

@@ -0,0 +1,47 @@
from typing import Any, Callable
from pydantic import Field
from crewai.task import Task
from crewai.tasks.output_format import OutputFormat
from crewai.tasks.task_output import TaskOutput
class ConditionalTask(Task):
"""
A task that can be conditionally executed based on the output of another task.
Note: This cannot be the only task you have in your crew and cannot be the first since its needs context from the previous task.
"""
condition: Callable[[TaskOutput], bool] = Field(
default=None,
description="Maximum number of retries for an agent to execute a task when an error occurs.",
)
def __init__(
self,
condition: Callable[[Any], bool],
**kwargs,
):
super().__init__(**kwargs)
self.condition = condition
def should_execute(self, context: TaskOutput) -> bool:
"""
Determines whether the conditional task should be executed based on the provided context.
Args:
context (Any): The context or output from the previous task that will be evaluated by the condition.
Returns:
bool: True if the task should be executed, False otherwise.
"""
return self.condition(context)
def get_skipped_task_output(self):
return TaskOutput(
description=self.description,
raw="",
agent=self.agent.role if self.agent else "",
output_format=OutputFormat.RAW,
)

4
src/crewai/utilities/converter.py
View File

@@ -38,10 +38,10 @@ class Converter(OutputConverter):
return self._create_instructor().to_json()
else:
return json.dumps(self._create_chain().invoke({}).model_dump())
except Exception:
except Exception as e:
if current_attempt < self.max_attempts:
return self.to_json(current_attempt + 1)
return ConverterError("Failed to convert text into JSON.")
return ConverterError(f"Failed to convert text into JSON, error: {e}.")
def _create_instructor(self):
"""Create an instructor."""

10
src/crewai/utilities/crew_pydantic_output_parser.py
View File

@@ -17,6 +17,16 @@ class CrewPydanticOutputParser(PydanticOutputParser):
def parse_result(self, result: List[Generation], *, partial: bool = False) -> Any:
result[0].text = self._transform_in_valid_json(result[0].text)
# Treating edge case of function calling llm returning the name instead of tool_name
json_object = json.loads(result[0].text)
json_object["tool_name"] = (
json_object["name"]
if "tool_name" not in json_object
else json_object["tool_name"]
)
result[0].text = json.dumps(json_object)
json_object = super().parse_result(result)
try:
return self.pydantic_object.parse_obj(json_object)

5
src/crewai/utilities/printer.py
View File

@@ -10,6 +10,8 @@ class Printer:
self._print_bold_purple(content)
elif color == "bold_blue":
self._print_bold_blue(content)
elif color == "yellow":
self._print_yellow(content)
else:
print(content)
@@ -27,3 +29,6 @@ class Printer:
def _print_bold_blue(self, content):
print("\033[1m\033[94m {}\033[00m".format(content))
def _print_yellow(self, content):
print("\033[93m {}\033[00m".format(content))

3098
tests/cassettes/test_conditional_task_last_task.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

151
tests/cassettes/test_conditional_task_last_task_when_conditional_is_false.yaml Normal file
View File

@@ -0,0 +1,151 @@
interactions:
- request:
body: '{"messages": [{"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 agentsTo 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: my best complete
final answer to the task.\nYour 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: Say Hi\n\nThis is the expect criteria for
your final answer: Hi \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:\n",
"role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"], "stream":
true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1072'
content-type:
- application/json
cookie:
- _cfuvid=Nxp5RE8CN2EyHxMIvB_SaTizIH5w0eWt9SPilMuIjMk-1721227661802-0.0.1.1-604800000;
__cf_bm=jadAYV2gh7qPDzgKO9A4JzJTaI9c2fnnjxloIQZeOIw-1721227661-1.0.1.1-apaA8kQyGiEV3kOuXHe8z1zeyvxd_jBHCQpdqWirUlylrUo.uRZjRDueI.sSXS4hXoWkyIW6kIMt7lamQM2mdw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a4b087e7d024593-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Wed, 17 Jul 2024 14:48:29 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '142'
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:
- '29999753'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_75100793afc289eaf8b56127e1cc0532
status:
code: 200
message: OK
version: 1

3467
tests/cassettes/test_conditional_task_last_task_when_conditional_is_true.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

2189
tests/cassettes/test_crew_does_not_interpolate_without_inputs.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

262
tests/cassettes/test_json_property_without_output_json.yaml Normal file
View File

@@ -0,0 +1,262 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
in scoring titles.\nYour personal goal is: Score the titleTo 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: my best complete final answer to the task.\nYour
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:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '997'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.14
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.14
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-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a488e81aa7f0c7e-EWR
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Wed, 17 Jul 2024 07:35:41 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=Ypr9N3lq.OD8hpimnkpN61rAsWyk216I8Tq7RA8.uwQ-1721201741-1.0.1.1-6Cj4aX9I96QHMmPwJBpO1iCFOJsvzq_agUIrl3XS.YhlPuGyA4K9sDONExvLn.cDe3W_p_1ET7Pt_hxjtHPAXQ;
path=/; expires=Wed, 17-Jul-24 08:05:41 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=NLa1BaUsRvD7shojIzUH9YSRXQIEzaoJVcq2_gNwqm0-1721201741646-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '106'
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:
- '29999771'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_e52461a1ab2702e360f6303fbcb4cc3c
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "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:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=Ypr9N3lq.OD8hpimnkpN61rAsWyk216I8Tq7RA8.uwQ-1721201741-1.0.1.1-6Cj4aX9I96QHMmPwJBpO1iCFOJsvzq_agUIrl3XS.YhlPuGyA4K9sDONExvLn.cDe3W_p_1ET7Pt_hxjtHPAXQ;
_cfuvid=NLa1BaUsRvD7shojIzUH9YSRXQIEzaoJVcq2_gNwqm0-1721201741646-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.14
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.14
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 |
H4sIAAAAAAAAA2xS22rjMBB991eIeY6LHTubrR9LKYUttKWUvbUYRRnb6sqSVhqTJiH/vshxYzes
H8QwZ86FGe8jxkCuoWAgGk6itSq+VPR8d8O/vXXZbiOzx13S5D9/PNwSv8nvYBYYZvWGgj5YF8K0
ViFJo4+wcMgJg2q6nKfzJF3maQ+0Zo0q0GpLcW7ieTLP42QRp9lAbIwU6KFgvyPGGNv3b4io1/gO
BUtmH50Wvec1QnEaYgycUaED3HvpiWuC2QgKowl1SK07pSYAGaNKwZUajY/fflKPe+JKlVe/nqvV
98vNtslul3/Xj7vrzaZ6StOJ31F6a/tAVafFaT8T/NQvzswYA83bnvskjMP7jmxHZ3TGgLu6a1FT
iA77F/Bh+AWK/ACfRg/R/+rXoTqc1qpMbZ1Z+bMtQSW19E3pkPs+LXgy9mgR5F7783WfLgLWmdZS
SeYP6iD4dbgejP/LCC4GjAxxNeEsoiEe+K0nbMtK6hqddbI/JVS2FDkuVl8qnqUQHaJ/AAAA//8D
ACb4o2zTAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a488e858ca50c7e-EWR
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 17 Jul 2024 07:35:42 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '241'
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:
- '29999968'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_01c2f40fe9c73f883b7ed5b60c8067e5
status:
code: 200
message: OK
version: 1

9599
tests/cassettes/test_manager_agent_delegating_to_all_agents.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

9619
tests/cassettes/test_manager_agent_delegating_to_assigned_task_agent.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

3326
tests/cassettes/test_output_json_dict_hierarchical.yaml
View File

File diff suppressed because it is too large Load Diff

159
tests/cassettes/test_replay_from_task_with_context.yaml Normal file
View File

@@ -0,0 +1,159 @@
interactions:
- request:
body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
goal is: Test GoalTo 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:
my best complete final answer to the task.\nYour 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: Test Task\n\nThis is the
expect criteria for your final answer: Say Hi \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\ncontext raw output\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:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop":
["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '910'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.14
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.14
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-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a488e7859304288-EWR
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Wed, 17 Jul 2024 07:35:40 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=tBullt04HIYduv1QEpAn86_ghx9PQ4DMe9LwLp7.bu4-1721201740-1.0.1.1-sGn3OYi9ntPGIzwuC4RH0UTUQFVy.BUFIvy9v9IrjorYeAsecsuuuREs7b19i4dXygWnZZEkH6cxvnQeJ62g7g;
path=/; expires=Wed, 17-Jul-24 08:05:40 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=uSSEccAecytxcWKGJoaQXLVBAwHLrZ.QckpcK..rN48-1721201740355-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '83'
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:
- '29999793'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_89b4947eaf51788bd7a69d6cc0da6c08
status:
code: 200
message: OK
version: 1

449
tests/cassettes/test_replay_task_with_context.yaml Normal file
View File

@@ -0,0 +1,449 @@
interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate, br
Connection:
- keep-alive
Content-Length:
- '23733'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.25.0
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:
- Tue, 16 Jul 2024 18:43:12 GMT
status:
code: 200
message: OK
version: 1

253
tests/crew_test.py
View File

@@ -4,11 +4,10 @@ import hashlib
import json
from concurrent.futures import Future
from unittest import mock
from unittest.mock import patch
from unittest.mock import MagicMock, patch
import pydantic_core
import pytest
from crewai.agent import Agent
from crewai.agents.cache import CacheHandler
from crewai.crew import Crew
@@ -16,6 +15,7 @@ from crewai.crews.crew_output import CrewOutput
from crewai.memory.contextual.contextual_memory import ContextualMemory
from crewai.process import Process
from crewai.task import Task
from crewai.tasks.conditional_task import ConditionalTask
from crewai.tasks.output_format import OutputFormat
from crewai.tasks.task_output import TaskOutput
from crewai.utilities import Logger, RPMController
@@ -286,7 +286,7 @@ def test_hierarchical_process():
crew = Crew(
agents=[researcher, writer],
process=Process.hierarchical,
manager_llm=ChatOpenAI(temperature=0, model="gpt-4"),
manager_llm=ChatOpenAI(temperature=0, model="gpt-4o"),
tasks=[task],
)
@@ -312,6 +312,82 @@ def test_manager_llm_requirement_for_hierarchical_process():
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_manager_agent_delegating_to_assigned_task_agent():
"""
Test that the manager agent delegates to the assigned task agent.
"""
from langchain_openai import ChatOpenAI
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
agent=researcher,
)
crew = Crew(
agents=[researcher, writer],
process=Process.hierarchical,
manager_llm=ChatOpenAI(temperature=0, model="gpt-4o"),
tasks=[task],
)
crew.kickoff()
# Check if the manager agent has the correct tools
assert crew.manager_agent is not None
assert crew.manager_agent.tools is not None
assert len(crew.manager_agent.tools) == 2
assert (
"Delegate a specific task to one of the following coworkers: Researcher\n"
in crew.manager_agent.tools[0].description
)
assert (
"Ask a specific question to one of the following coworkers: Researcher\n"
in crew.manager_agent.tools[1].description
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_manager_agent_delegating_to_all_agents():
"""
Test that the manager agent delegates to all agents when none are specified.
"""
from langchain_openai import ChatOpenAI
task = Task(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
)
crew = Crew(
agents=[researcher, writer],
process=Process.hierarchical,
manager_llm=ChatOpenAI(temperature=0, model="gpt-4o"),
tasks=[task],
)
crew.kickoff()
assert crew.manager_agent is not None
assert crew.manager_agent.tools is not None
assert len(crew.manager_agent.tools) == 2
print(
"crew.manager_agent.tools[0].description",
crew.manager_agent.tools[0].description,
)
assert (
"Delegate a specific task to one of the following coworkers: Researcher, Senior Writer\n"
in crew.manager_agent.tools[0].description
)
assert (
"Ask a specific question to one of the following coworkers: Researcher, Senior Writer\n"
in crew.manager_agent.tools[1].description
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_delegating_agents():
tasks = [
@@ -917,9 +993,7 @@ async def test_kickoff_async_basic_functionality_and_output():
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.asyncio
async def test_async_kickoff_for_each_async_basic_functionality_and_output():
"""Tests the basic functionality and output of akickoff_for_each_async."""
from unittest.mock import patch
"""Tests the basic functionality and output of kickoff_for_each_async."""
inputs = [
{"topic": "dog"},
{"topic": "cat"},
@@ -945,8 +1019,13 @@ async def test_async_kickoff_for_each_async_basic_functionality_and_output():
agent=agent,
)
async def mock_kickoff_async(**kwargs):
input_data = kwargs.get("inputs")
index = [input_["topic"] for input_ in inputs].index(input_data["topic"])
return expected_outputs[index]
with patch.object(
Crew, "kickoff_async", side_effect=expected_outputs
Crew, "kickoff_async", side_effect=mock_kickoff_async
) as mock_kickoff_async:
crew = Crew(agents=[agent], tasks=[task])
@@ -1355,6 +1434,7 @@ def test_crew_inputs_interpolate_both_agents_and_tasks_diff():
interpolate_task_inputs.assert_called()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_does_not_interpolate_without_inputs():
from unittest.mock import patch
@@ -1997,6 +2077,7 @@ def test_replay_task_with_context():
db_handler.reset()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_replay_from_task_with_context():
agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
task1 = Task(
@@ -2114,6 +2195,7 @@ def test_replay_with_invalid_task_id():
crew.replay_from_task("bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d")
@pytest.mark.vcr(filter_headers=["authorization"])
@patch.object(Crew, "_interpolate_inputs")
def test_replay_interpolates_inputs_properly(mock_interpolate_inputs):
agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
@@ -2260,3 +2342,160 @@ def test_key():
).hexdigest()
assert crew.key == hash
def test_conditional_task_requirement_breaks_when_singular_conditional_task():
def condition_fn(output) -> bool:
return output.raw.startswith("Andrew Ng has!!")
task = ConditionalTask(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
condition=condition_fn,
)
with pytest.raises(pydantic_core._pydantic_core.ValidationError):
Crew(
agents=[researcher, writer],
tasks=[task],
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_task_last_task_when_conditional_is_true():
def condition_fn(output) -> bool:
return True
task1 = Task(
description="Say Hi",
expected_output="Hi",
agent=researcher,
)
task2 = ConditionalTask(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
condition=condition_fn,
agent=writer,
)
crew = Crew(
agents=[researcher, writer],
tasks=[task1, task2],
)
result = crew.kickoff()
assert result.raw.startswith(
"1. **The Rise of AI Agents in Customer Service: Revolutionizing Customer Interactions**"
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_task_last_task_when_conditional_is_false():
def condition_fn(output) -> bool:
return False
task1 = Task(
description="Say Hi",
expected_output="Hi",
agent=researcher,
)
task2 = ConditionalTask(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
condition=condition_fn,
agent=writer,
)
crew = Crew(
agents=[researcher, writer],
tasks=[task1, task2],
)
result = crew.kickoff()
print(result.raw)
assert result.raw == "Hi"
def test_conditional_task_requirement_breaks_when_task_async():
def my_condition(context):
return context.get("some_value") > 10
task = ConditionalTask(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
execute_async=True,
condition=my_condition,
agent=researcher,
)
task2 = Task(
description="Say Hi",
expected_output="Hi",
agent=writer,
)
with pytest.raises(pydantic_core._pydantic_core.ValidationError):
Crew(
agents=[researcher, writer],
tasks=[task, task2],
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_should_skip():
task1 = Task(description="Return hello", expected_output="say hi", agent=researcher)
condition_mock = MagicMock(return_value=False)
task2 = ConditionalTask(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
condition=condition_mock,
agent=writer,
)
crew_met = Crew(
agents=[researcher, writer],
tasks=[task1, task2],
)
with patch.object(Task, "execute_sync") as mock_execute_sync:
mock_execute_sync.return_value = TaskOutput(
description="Task 1 description",
raw="Task 1 output",
agent="Researcher",
)
result = crew_met.kickoff()
assert mock_execute_sync.call_count == 1
assert condition_mock.call_count == 1
assert condition_mock() is False
assert task2.output is None
assert result.raw.startswith("Task 1 output")
@pytest.mark.vcr(filter_headers=["authorization"])
def test_conditional_should_execute():
task1 = Task(description="Return hello", expected_output="say hi", agent=researcher)
condition_mock = MagicMock(
return_value=True
) # should execute this conditional task
task2 = ConditionalTask(
description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
expected_output="5 bullet points with a paragraph for each idea.",
condition=condition_mock,
agent=writer,
)
crew_met = Crew(
agents=[researcher, writer],
tasks=[task1, task2],
)
with patch.object(Task, "execute_sync") as mock_execute_sync:
mock_execute_sync.return_value = TaskOutput(
description="Task 1 description",
raw="Task 1 output",
agent="Researcher",
)
crew_met.kickoff()
assert condition_mock.call_count == 1
assert condition_mock() is True
assert mock_execute_sync.call_count == 2

19
tests/task_test.py
View File

@@ -6,6 +6,7 @@ from unittest.mock import MagicMock, patch
import pytest
from crewai import Agent, Crew, Process, Task
from crewai.tasks.conditional_task import ConditionalTask
from crewai.tasks.task_output import TaskOutput
from crewai.utilities.converter import Converter
from pydantic import BaseModel
@@ -317,6 +318,7 @@ def test_output_json_hierarchical():
assert result.to_dict() == {"score": 4}
@pytest.mark.vcr(filter_headers=["authorization"])
def test_json_property_without_output_json():
class ScoreOutput(BaseModel):
score: int
@@ -397,8 +399,8 @@ def test_output_json_dict_hierarchical():
manager_llm=ChatOpenAI(model="gpt-4o"),
)
result = crew.kickoff()
assert {"score": 4} == result.json_dict
assert result.to_dict() == {"score": 4}
assert {"score": 5} == result.json_dict
assert result.to_dict() == {"score": 5}
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -695,6 +697,19 @@ def test_task_definition_based_on_dict():
assert task.agent is None
def test_conditional_task_definition_based_on_dict():
config = {
"description": "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.",
"expected_output": "The score of the title.",
}
task = ConditionalTask(config=config, condition=lambda x: True)
assert task.description == config["description"]
assert task.expected_output == config["expected_output"]
assert task.agent is None
def test_interpolate_inputs():
task = Task(
description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.",