majordomo/meshgen/meshgen.go

// Package meshgen is majordomo's canonical image-to-3D surface. Like
// imagegen/audio/videogen, it is a deliberately separate leaf contract from
// the llm package: mesh generation shares none of the chat machinery, so it
// gets its own small Provider/Model interfaces (ADR-0020, following the
// ADR-0016→0019 lineage: functional options, zero values = backend default,
// bytes-only I/O, Raw escape hatch).
//
// The first implementation is provider/llamaswap, which targets a
// Hunyuan3D-2.1-style api_server reached through the /upstream passthrough.
// The surface is image-to-3D only: text-to-3D is the composition
// imagegen.Generate → meshgen.Generate, owned by the caller.
package meshgen

import (
	"context"

	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
)

// Image is the conditioning input (bytes + MIME), aliased to llm.ImagePart so
// chat- or imagegen-sourced images feed mesh generation without conversion.
type Image = llm.ImagePart

// Mesh is one generated 3D asset: raw encoded bytes plus its format.
type Mesh struct {
	// Data is the encoded mesh (binary GLB/STL/OBJ container).
	Data []byte

	// Format is the lowercase container name ("glb", "stl", "obj").
	Format string

	// MIME is the corresponding MIME type, e.g. "model/gltf-binary",
	// "model/stl".
	MIME string
}

// Request is an image-to-3D generation request. Zero values mean "backend
// default".
type Request struct {
	// Image is the source image the mesh is reconstructed from. Required.
	Image Image

	// Format is the requested output container ("glb", "stl", "obj");
	// "" = backend default (glb).
	Format string

	// Texture asks the backend to also synthesize surface textures. Much
	// slower and much more VRAM-hungry than shape-only on the reference
	// backend; leave false for print-pipeline geometry.
	Texture bool

	// RemoveBackground lets the backend cut the subject out first; nil =
	// backend default (true on Hunyuan3D). Set explicitly to false when the
	// input is already a clean cutout.
	RemoveBackground *bool

	// OctreeResolution is the shape-decoder grid resolution; 0 = backend
	// default.
	OctreeResolution int

	// Steps is the number of diffusion steps; nil = backend default.
	Steps *int

	// GuidanceScale is the guidance strength; nil = backend default.
	GuidanceScale *float64

	// Seed fixes the RNG seed for reproducible output; nil = backend default.
	Seed *int64

	// FaceCount caps the output mesh's face count; 0 = backend default.
	FaceCount int
}

// Result is the canonical mesh-generation result.
type Result struct {
	// Mesh is the generated asset.
	Mesh Mesh

	// Raw is the provider-native response object. May be nil.
	Raw any
}

// Option mutates a Request before it is sent. Options passed to Generate are
// applied to a copy of the request, so a Request value can be reused.
type Option func(*Request)

// WithFormat sets the output container ("glb", "stl", "obj").
func WithFormat(f string) Option { return func(r *Request) { r.Format = f } }

// WithTexture enables texture synthesis.
func WithTexture() Option { return func(r *Request) { r.Texture = true } }

// WithRemoveBackground sets the backend's background-removal preprocessing.
func WithRemoveBackground(v bool) Option {
	return func(r *Request) { r.RemoveBackground = &v }
}

// WithOctreeResolution sets the shape-decoder grid resolution.
func WithOctreeResolution(n int) Option { return func(r *Request) { r.OctreeResolution = n } }

// WithSteps overrides the number of diffusion steps.
func WithSteps(n int) Option { return func(r *Request) { r.Steps = &n } }

// WithGuidanceScale overrides the guidance strength.
func WithGuidanceScale(s float64) Option { return func(r *Request) { r.GuidanceScale = &s } }

// WithSeed fixes the RNG seed.
func WithSeed(seed int64) Option { return func(r *Request) { r.Seed = &seed } }

// WithFaceCount caps the output mesh's face count.
func WithFaceCount(n int) Option { return func(r *Request) { r.FaceCount = n } }

// Apply returns a copy of the request with all options applied. Providers
// call this once at the top of Generate.
func (r Request) Apply(opts ...Option) Request {
	for _, opt := range opts {
		opt(&r)
	}
	return r
}

// Model generates 3D meshes from images.
type Model interface {
	// Generate reconstructs a mesh from the request's image.
	Generate(ctx context.Context, req Request, opts ...Option) (*Result, error)
}

// ModelOption configures a Model at construction time. Reserved for future
// per-model settings.
type ModelOption func(*ModelConfig)

// ModelConfig carries per-model construction settings.
type ModelConfig struct{}

// ApplyModelOptions folds options into a config.
func ApplyModelOptions(opts []ModelOption) ModelConfig {
	var cfg ModelConfig
	for _, opt := range opts {
		opt(&cfg)
	}
	return cfg
}

// Provider mints mesh models bound to one backend.
type Provider interface {
	// Name is the registry identifier for the provider.
	Name() string

	// MeshModel returns a Model bound to the given id (passed through to the
	// backend verbatim; no catalog validation).
	MeshModel(id string, opts ...ModelOption) (Model, error)
}