Conversation
|
@filip-michalsky could you share a video showing this tool working? |
Hey @lucasgomide - absolutely! Here is a video of the Stagehand tool powering atomic browsing commands for CrewAI web research agent: https://screen.studio/share/1HTuXVvs please let me know if you have any other questions for this PR? |
lucasgomide
left a comment
There was a problem hiding this comment.
Good job! I liked that..
I drop a few comments, let me know what you think
|
@lucasgomide the feedback was addressed - is this good to merge? Thanks so much! |
|
@filip-michalsky Just double-checking it’s important that we support both ways of using StagehandTool: with a context manager and without one. # Using as a context manager
with StagehandTool() as tool:
Agent(tools=[tool])# Manual management
tool = StagehandTool()
try:
Agent(tools=[tool])
finally:
tool.close()Just update the documentation by adding we can use with context manager also |
|
@lucasgomide this was updated as well! |
|
@lucasgomide thanks for the approval! I see there are other tools not related to stagehand failing in the CI - how should we address so that this can be merged? I am happy to try to help but I am not familiar with the other tools that much |
|
@filip-michalsky Add it into your then run |
|
@filip-michalsky something weird is happing with your tests.. I gonna checkout later and fix it |
|
thank you @lucasgomide ! |
|
@lucasgomide i have been trying to fix the tests. in isolation the tests work, but the module mocking is when running the whole test suite is failing... |
* stagehand tool * update import paths * updates * improve example * add tests * revert init * imports * add context manager * update tests * update example to run again * update context manager docs * add to pyproject.toml and run uv sync * run uv sync * update lazy import * update test mock * fixing tests * attempt to fix tests
Integration of Stagehand Python SDK with CrewAI
https://pypi.org/project/stagehand-py/