-
Notifications
You must be signed in to change notification settings - Fork 1.9k
Fix and test validate_tools_and_managed_agents #731
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
The failing CI tests is unrelated: and will be fixed by: |
tests/test_agents.py
Outdated
# Invalid case: tool name same as managed agent's tool name | ||
([MockTool("tool1")], [MockAgent("agent1", [MockTool("tool1")])], pytest.raises(ValueError)), | ||
# Invalid case: duplicate managed agent name and managed agent tool name | ||
([], [MockAgent("tool1", [MockTool("tool1")])], pytest.raises(ValueError)), |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Same as above, I'm not sure that this should raise an error.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done.
You are right, @aymeric-roucher: those test should not raise error. I have reverted: and include the agent.name to be compared wit agent.tools and agent.managed_agents names, so that we fix issue: This PR also fixes: |
Fix and test
_validate_tools_and_managed_agents
.Revert PR:
Fix #795.