mesh-controller/internal/builder/toolchain.go

package builder

import (
	"fmt"
	"sort"
	"strings"
)

// What a language implies, so a module does not have to say it.
//
// **A module says what it is written in; this says what that means.** The alternative is what the
// mesh had: every module carrying a Dockerfile that repeated the same incantation, and most of the
// catalogue never converted because the incantation is easy to get wrong in ways that fail
// somewhere else (novox/hq 03-DESIGN/01-to-be/18-building-a-module.md).
//
// A toolchain is deliberately not configurable by the module. Anything a module could override
// here it would be writing a Dockerfile to override, and then this bought nothing.

// Toolchain is how one language is compiled into a bundle.
type Toolchain struct {
	// Language is what a module declares to select this.
	Language string
	// Base is the module whose artifact provides the compiler, named rather than pinned: the mesh
	// answers with the copy it holds, so a recipe never names one particular build of it
	// (novox/hq 04-ISSUES/044).
	Base string
	// Artifact is which of that module's artifacts is the compiling one.
	Artifact string
	// Compile is what runs inside it, relative to the module's own directory.
	//
	// The output directory is appended by the builder, per artifact, because one module may
	// declare several bundles — a daemon in one language, tools in another, a package in a third —
	// and a toolchain with one fixed output would have them overwrite each other and then be
	// packed together.
	Compile []string
	// OutputFlag is how this compiler is told where to put its output.
	OutputFlag string
	// Unit is what this compiler is pointed at: UnitSources, the entrypoint files the module named,
	// or UnitPackage, the one directory the artifact is built `from`.
	//
	// **The difference is the language and not the module.** A TypeScript bundle is a set of files
	// compiled into a set of files, so what to compile is the module's entrypoints with their source
	// extension. A Go bundle is a package compiled into one binary, and there is no per-file
	// compilation to name — pointing `go build` at a file list builds a program out of exactly those
	// files and ignores the rest of the package, which fails as a missing symbol rather than as a
	// wrong instruction.
	Unit string
	// SourceExt is the extension an entrypoint has in the repository, for UnitSources. An entrypoint
	// is named as it will be FOUND, inside the unpacked bundle, so the source is the same path with
	// the output directory taken off the front and this on the end.
	SourceExt string
	// SystemStamp is the variable this language's linker fills with the artifact's declared system,
	// for a language whose binaries are pinned to one at link time (novox/hq ADR 0005).
	//
	// **The one thing a toolchain takes from the artifact, and 0142 says why**: the target is a
	// property of the artifact rather than of the recipe, because a compiled binary is per system
	// and a toolchain that accepted it from the module would be accepting a build instruction. This
	// is the narrow exception, named here rather than inferred.
	//
	// Empty for a language that compiles to nothing pinned. A host built without it refuses every
	// declaration before applying anything — safely, totally, and with nothing reporting it
	// (novox/hq 04-ISSUES/161).
	SystemStamp string
}

// What a toolchain is pointed at.
const (
	// UnitSources is a list of files, derived from the module's entrypoints.
	UnitSources = "sources"
	// UnitPackage is the single directory the artifact is built `from`, compiled whole.
	UnitPackage = "package"
)

// Out is where one artifact's compiled output lands, inside the module's own directory.
//
// **Per artifact, never per toolchain.** A module is one piece of software and may still be
// written in several languages — a daemon in one, a tool in another, a package in a third (ADR
// 0040). Each bundle is compiled and packed alone, so what a machine unpacks is that artifact and
// nothing else.
//
// Under a directory named for the build rather than beside the source, so a pack never sweeps up
// the module's own working files, and two builds of one commit see the same tree.
func Out(artifact string) string { return ".mesh-build/" + artifact }

// toolchains is every language the mesh can build.
//
// **A closed list, and adding to it is a decision rather than a configuration.** Every language is
// permanent: it needs an SDK carrying the broker client, sealed-credential reading, the event
// envelope and tool serving, and the contracts every module shares change rarely and cascade when
// they do (novox/hq ADR 0039). A mesh whose languages disagree about the envelope fails by ignoring
// messages rather than by failing to compile, so a new entry here is a commitment to keeping N
// implementations of one contract in step.
var toolchains = []Toolchain{
	{
		Language: "typescript",
		Base:     "mesh-tools",
		Artifact: "build",
		// Invoked by its real path rather than through node_modules/.bin, whose entries are
		// symlinks to a launcher that requires its library relatively — and the base image's own
		// assembly resolves them away, leaving a launcher whose relative require points nowhere.
		// Every module's hand-written Dockerfile had to know this. Now none of them does.
		Compile: []string{
			"node", "/app/node_modules/typescript/bin/tsc",
			"--module", "NodeNext", "--moduleResolution", "NodeNext",
			"--target", "ES2022",
		},
		OutputFlag: "--outDir",
		Unit:       UnitSources,
		SourceExt:  ".ts",
	},
	{
		Language: "go",
		Base:     "mesh-tools-go",
		Artifact: "build",
		// **The mesh's own components, and not modules.** The warning above this list — that every
		// language is another implementation of the contracts modules share, so adding one commits
		// to keeping N implementations in step — does not attach here. Go is how the host, the
		// control plane and the builder are written, and none of them is a module in that sense:
		// the host is what APPLIES modules. So there is no SDK obligation, and the reason this
		// entry did not exist was that nothing needed to compile the mesh itself
		// (novox/hq ADR 0142, and 04-ISSUES/142 where that is why nothing delivers the host).
		//
		// Static, because what a machine ends up holding is a file rather than a container, and a
		// binary that needs a libc it did not bring is a delivery that works until a machine
		// differs. Trimmed of its own paths for the same reason a version comes from where it sits
		// rather than from the linker: two builds of one commit produce the same bytes.
		Compile: []string{
			"env", "CGO_ENABLED=0", "GOFLAGS=-trimpath",
			"go", "build", "-ldflags", "-s -w",
		},
		OutputFlag: "-o",
		// Pointed at the package the artifact is built `from`, compiled whole. Go writes the binary
		// into the output directory, named after the package — so the bundle a machine unpacks is a
		// directory holding one executable, which is what the delivery mechanism expects
		// (novox/hq ADR 0141).
		Unit: UnitPackage,
		// The mesh's own Go components read the system they were built for from this variable, and
		// refuse to touch a machine without one.
		SystemStamp: "main.builtFor",
	},
	{
		Language: "python",
		Base:     "mesh-tools-python",
		Artifact: "build",
		// Nothing to compile: what a bundle needs is the module's own code and its dependencies
		// resolved, so the "compile" is an install into the output directory. Named here rather
		// than left implicit because a reader comparing two toolchains should be able to see what
		// each actually does.
		Compile:    []string{"python", "-m", "pip", "install", "--no-compile", "--target"},
		OutputFlag: "",
		Unit:       UnitSources,
		SourceExt:  ".py",
	},
}

// ToolchainFor is what builds this language, or says what it can build.
func ToolchainFor(language string) (Toolchain, error) {
	want := strings.ToLower(strings.TrimSpace(language))
	if want == "" {
		return Toolchain{}, fmt.Errorf(
			"a bundle must say what language it is written in: the mesh chooses the compiler, and "+
				"it cannot choose one for a module that has not said. It can build %s", spoken())
	}
	for _, t := range toolchains {
		if t.Language == want {
			return t, nil
		}
	}
	return Toolchain{}, fmt.Errorf(
		"%q is not a language this mesh builds. It can build %s — and adding one is a decision "+
			"rather than a setting, because every language is another implementation of the "+
			"contracts every module shares", language, spoken())
}

// spoken lists the languages, so a refusal says what would have worked.
func spoken() string {
	names := make([]string, 0, len(toolchains))
	for _, t := range toolchains {
		names = append(names, t.Language)
	}
	sort.Strings(names)
	return strings.Join(names, ", ")
}

// Languages is every language the mesh can build, for anything that wants to say so.
func Languages() []string {
	names := make([]string, 0, len(toolchains))
	for _, t := range toolchains {
		names = append(names, t.Language)
	}
	sort.Strings(names)
	return names
}