pythagora VS pythagora-demo-lodash

Product which you can try - https://github.com/Pythagora-io/pythagora, check also video - Open-Source AI Agent Can Build FULL STACK Apps (FREE “Devin” Alternative) (youtube.com)

P.S. If you found this post helpful, it would mean a lot to me if you starred the Pythagora Github repo and if you try Pythagora out, please let us know how it went on [email protected].

Thanks, yes, it can, we actually started off with integration tests. Take a look at the integration tests README. They work by recording server activity (db queries, 3rd party API requests, etc.) during the processing of an API request.

Recently, I open sourced Pythagora - a dev tool that tracks the server activity and creates integration tests from it. However, many people said that they wanted to analyze better what is inside the tests and to use tests as code documentation. So, I used GPT-4 to export Pythagora tests (which are basically JSON files that contain all captured data) to Jest code which can be reviewed and used for documentation.

I'm working on Pythagora, an open source tool that writes automated integration tests by itself (well, with a bit of help from GPT-4) without you, the dev, having to write a single line of code. Basically, you can get from 0 to 80% code code coverage within 30 minutes (video).

Hey! I'm working on Pythagora (https://github.com/Pythagora-io/pythagora) - it's an open source tool that creates automated integration tests by analyzing server activity without you having to write a single line of code.

Pythagora is an NPM package designed to create automated tests for your Node.js applications by analyzing server activity. It records all requests to your app's endpoints, along with responses and server actions, such as Mongo and Redis queries. Pythagora during testing simulates the server conditions from the time when the request was captured, allowing for consistent and accurate testing across different environments.

Finally, if you read this far and would like to support us, please consider starring the Pythagora Github repository here – it would mean the world to us.

Re types of bugs, I'm assuming you're talking about Lodash bugs. I've made a fork and added the bugs in the readme - https://github.com/Pythagora-io/pythagora-demo-lodash

Not sure if I understand - how do you mean? Btw, you can see all generated tests in the lodash demo repo - https://github.com/Pythagora-io/pythagora-demo-lodash. Also, tests in Pythagora itself are all generated by itself.

'Not sure about your other tests, but at least one of the failures in your pick() tests is a result of an incorrect call signature. https://github.com/Pythagora-io/pythagora-demo-lodash/pull/1

If you’re curious to check these out yourself, we’ve forked the Lodash repository and added the tests generated by Pythagora. Feel free to explore them here.

However, after testing on a couple of different repos, it seems that GPT is able to find edge cases which are quite hard to think of. This way, the generated tests actually found bugs right away. TBH, I was quite blown away by this. Here is a lodash demo repo that I forked and generated tests with Pythagora. It took 4 hours to finish but the results are quite amazing:

However, it seems that tests that GPT creates cover edge cases that are quite impressive (check out the tests in the demo lodash repo I linked). I think that generating tests with GPT might have a bigger value than we think.