dagger-pulumi VS cue

This is one of the few definitions that we have in this package, I will not show you directly all of them since it's really specific to our implementation and it's not very relevant to explain how it's working. However, you can retrieve all of our source code here: https://github.com/camptocamp/dagger-pulumi

Have you considered using a different language for templating? this could be a BIG selling point. Some good ones are cue-lang (though I haven't seen support for rust), kcl or nickel-lang.

Among types and other useful properties, CUE supports everything you asked for.

https://cuelang.org

Shameless plug for cuelang, which, among many other things, avoid this problem:

https://cuelang.org

It's not a new issue, the Python community had exactly the same surprise with 3.10: https://github.com/actions/runner/issues/1989

I asked ChatGPT (GPT-4) about the idea of integrating GPT-JSON with CUE language (https://cuelang.org/) for improvement and the answers are quite impressive:

"Yes, integrating the CUE language with GPT-JSON can potentially lead to improvements in its capability. CUE, short for Configuration, Unification, and Environment, is an open-source data constraint language designed to simplify the definition, generation, and validation of data in structured formats, like JSON, YAML, and others.

Integrating CUE with GPT-JSON can bring several benefits:

1) Validation: By using CUE, you can define schemas for the input and output JSON, which helps in validating the data structure and ensuring it adheres to the expected format. This can help reduce errors and improve the quality of the interaction with the GPT model.

2) Simplification: CUE can help simplify the process of defining and generating JSON inputs and outputs for GPT-JSON. By providing a more concise and expressive syntax, CUE can make it easier to craft structured inputs and outputs, which can be especially helpful when working with complex data structures.

3) Interoperability: Integrating CUE can improve the interoperability between GPT-JSON and other systems or applications. With CUE's ability to work with multiple data formats (such as JSON, YAML, or HCL), it becomes easier to integrate GPT-JSON with various tools and platforms.

To integrate CUE with GPT-JSON, you would need to follow these general steps:

1) Define CUE schemas for the input and output JSON structures used by GPT-JSON.

We've been using Jsonnet to generate Pods for our complex DAGs at Opsgenie, wrote a similar one using Tekton: https://mustafaakin.dev/posts/2020-04-26-using-jsonnet-to-ge...

But if I was doing it again now, I would just use https://cuelang.org/ or https://dagger.io Jsonnet is really hard to debug.

We use CUE + ArgoCD, CUE is awesome