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

Where `kube.cue` sets reasonable defaults (e.g. image is /). The "cluster" runs on a mini PC in my basement, and I have a small Digital Ocean VM with a static IP acting as an ingress (networking via Tailscale). Backups to cloud storage with restic, alerting/monitoring with Prometheus/Grafana, Caddy/Tailscale for local ingress.

[1] https://www.talos.dev/

[2] https://cuelang.org/

I've been somewhat surprised that CUE bills itself as "tooling friendly" and doesn't yet have a language server- the number one bit of tooling most devs use for a particular language.

I'm assuming it's becaus CUE is still unstable?

Anyway, if others are interested in CUE's LSP work, I think https://github.com/cue-lang/cue/issues/142 is the issue to subscribe to

This is where I usually pitch in with "Have your heard of CUELang, our lord and savior?": https://cuelang.org/

- Not turing complete

CUE: The core problem CUE solves is "type checking", which is mainly used in configuration constraint verification scenarios and simple cloud native configuration scenarios.

If you really want executable configurations please consider a newer language like https://dascript.org or https://cuelang.org which provide better type safety.

1- https://news.ycombinator.com/item?id=38030778

Markdown and XML are nice, but what about more advanced documentation formats like OpenAPI? For one recent project, I set up automatic generation of the OpenAPI docs from (much more compact and flexible) CUE definitions (https://cuelang.org/) - which has the bonus of also being able to test the API against the definitions. JetBrains has a CUE plugin, but it's really barebones (doesn't even support jumping from the usage of a schema to its definition). Of course the possibilities when generating docs are endless (just think of the various syntaxes for doc comments, embedding examples/tests in source code etc.)...

It doesn't include validators for TOML and INI, but if you're doing JSON and YAML, I would take a look at using or building upon CUE (https://cuelang.org/). It is a different take on schema definition (plus more), and is surprising terse and powerful model.