hey any plans to have the option to always allow to run command for the new composer agent on 0.43? that would be really amazing ! unless it’s too spicy for now…
1 Like
I’m thinking the same thing:
It would be great if we could have a whitelist of Run Commands that the Composer Agent could execute without waiting for approval. I often have the agent generate unit tests as it goes, run the tests, and iterate on the results. I don’t want to give the agent the ability to run everything without my approval, but I would like to be able to say that ‘pytest’ commands are ok to run without my approval.
Even if we needed to include the entire command in the whitelist for safety it would be helpful…