Agents that run while I sleep
claudecodecamp.com
Agents that run while I sleep
1–10 of 532 posts
Re: Agents that run while I sleep
#2I wish there was a way to "freeze" the tests. I want to write the tests first (or have Claude do it with my review), and then I want to get Claude to change the code to get them to pass - but with confidence that it doesn't edit any of the test files!
Re: Agents that run while I sleep
#3I wish there was a way to "freeze" the tests. I want to write the tests first (or have Claude do it with my review), and then I want to get Claude to change the code to get them to pass - but with confidence that it doesn't edit any of the test files!
yeah i agree - this is somewhat the approach I have been using more of. Write the tests first based on specs and then write code to make the tests pass. This works well for cases where unit tests are sufficient.
Re: Agents that run while I sleep
#4It's... really the same problem when you hire people to just write tests. A lot of time it just confirms that the code does what the code does. Having clear specs of what the code should do make things better and clearer.
Re: Agents that run while I sleep
#5I wish there was a way to "freeze" the tests. I want to write the tests first (or have Claude do it with my review), and then I want to get Claude to change the code to get them to pass - but with confidence that it doesn't edit any of the test files!
I use devcontainers in all the projects I use claude code on. [1] With it you can have claude running inside a container with just the project's code in write access and also mount a test folder with just read permissions, or do the opposite. You can even have both devcontainers and run them at the same time.
[1] https://code.claude.com/docs/en/devcontainer
If you want to try it just ask Claude to set it up for your project and review it after.
Re: Agents that run while I sleep
#6I wish there was a way to "freeze" the tests. I want to write the tests first (or have Claude do it with my review), and then I want to get Claude to change the code to get them to pass - but with confidence that it doesn't edit any of the test files!
Why can't you do just that? You can configure file path permissions in Claude or via an external tool.
Re: Agents that run while I sleep
#7It's... really the same problem when you hire people to just write tests. A lot of time it just confirms that the code does what the code does. Having clear specs of what the code should do make things better and clearer.
yup agree - i think have specs and then do verifications against the spec. I have heard that this is how a lot of consulting firms work - you have acceptance criterias and thats how work is validated.
Re: Agents that run while I sleep
#8They're definitely inferior to proper tests, but even weak CC tests on top of CC code is an improvement over no tests. If CC does make a change that shifts something dramatically even a weak test may flag enough to get CC to investigate.
Even better though - external test suits. Recently made a S3 server of which the LLM made quick work for MVP. Then I found a Ceph S3 test suite that I could run against it and oh boy. Ended up working really good as TDD though.
Re: Agents that run while I sleep
#9I wish there was a way to "freeze" the tests. I want to write the tests first (or have Claude do it with my review), and then I want to get Claude to change the code to get them to pass - but with confidence that it doesn't edit any of the test files!
"Add a config option preventing you from modifying files matching src/*_test.py."
Re: Agents that run while I sleep
#10I wish there was a way to "freeze" the tests. I want to write the tests first (or have Claude do it with my review), and then I want to get Claude to change the code to get them to pass - but with confidence that it doesn't edit any of the test files!
Just tell it that the tests can't be changed. Honestly I'd be surprised if it tried to anyway. I've never had it do that through many projects where tests were provided to drive development.