feat(adr): add architecture decision record for interactive project setup #6
Reference in New Issue
Block a user
No description provided.
Delete Branch "adr/005-interactive-project"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Add an Architecture Decision Record (ADR) outlining the approach to integrate LAMP projects into Harmony's automated delivery pipeline using either Score Spec or a custom Rust DSL. A decision will have to be made between the two in the short term to decide which we will implement first. The ADR details the benefits and consequences of each option, focusing on providing a seamless transition for developers while leveraging Harmony's enterprise-grade features.
I've had a little chat with Claude 3.7 trying to figure out what each option would look like for three different scenarios :
Claude 3.7 example of what it could look like with score vs rust
I'll create concrete sample configurations for each of the three project types in both Rust DSL and Score Spec formats.
1. Basic LAMP Stack
Score Spec Version
Rust DSL Version
2. Regular Svelte App
Score Spec Version
Rust DSL Version
3. Enterprise Grade Java Monolith
Score Spec Version
Rust DSL Version
These examples showcase how both approaches can describe the same infrastructure needs, with the Score Spec version being more declarative and YAML-based, while the Rust DSL provides type safety and a more programmatic approach. The Rust DSL would enable better IDE integration, compile-time validation, and extensibility, while Score Spec leverages existing CNCF standards and may be more approachable for developers already familiar with YAML-based configurations.
@@ -0,0 +188,4 @@fn name(&self) -> &str {&self.name}}@@ -0,0 +328,4 @@1. **From Runtime to Compile-Time**: Move capability checking from runtime to compile-time.2. **From Objects to Functions**: Think of scores less as objects and more as functions that transform topologies.Un score, c'est pas "un objet qui contient son environnement, ...", c'est plutôt une entité standalone, qui se fait "pitcher" dans un contexte. Une fois dans ce contexte, si tous les requis du score sont disponibles, il est en mesure de s'exécuter dans ce contexte
Pull request closed