Files
notarius/internal/modules/dnd/items/registry/registry.go

287 lines
8.4 KiB
Go

// Package registry resolves normalized item artifacts into immutable grounding
// data for future D&D consumers.
package registry
import (
"crypto/sha256"
"encoding/hex"
"encoding/json"
"fmt"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
itemcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/itemregistry"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/items/identity"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/registryresolver"
)
const (
ReferenceSlot = "item_registry"
MaxBytes = 1048576
emptyPrompt = `{"items":[]}`
)
// Registry is an immutable, validated item registry prepared for grounding.
// All accessors return defensive copies.
type Registry struct {
bound bool
list dnd.ItemRegistry
canonical []byte
digest string
projectionDigest string
promptInput contracts.LLMInputMaterial
lookupByKey map[string]int
lookupByID map[string]int
}
// Resolver selects and memoizes immutable item registry views.
type Resolver struct {
resolver *registryresolver.Resolver[*Registry]
}
// NewResolver validates the optional construction-time item reference and
// prepares the operation-time registry cache.
func NewResolver(references contracts.ReferenceSet) (*Resolver, error) {
resolver, err := registryresolver.New(registryResolverConfig(), references)
if err != nil {
return nil, err
}
return &Resolver{resolver: resolver}, nil
}
// Seeded returns the immutable construction-time registry.
func (r *Resolver) Seeded() *Registry {
if r == nil {
return nil
}
return r.resolver.Seeded()
}
// Resolve returns the generated operation-time registry when supplied,
// otherwise it returns the construction-time registry.
func (r *Resolver) Resolve(references contracts.ReferenceSet) (*Registry, error) {
if r == nil || r.resolver == nil {
return Resolve(references)
}
return r.resolver.Resolve(references)
}
// Resolve prepares the optional item registry reference. An absent slot uses
// the exact empty prompt input and has no durable registry identity.
func Resolve(references contracts.ReferenceSet) (*Registry, error) {
item, present, err := registryresolver.ResolveOptionalSingleItem(references, itemReferenceSpec())
if err != nil {
return nil, err
}
if !present {
return emptyRegistry(), nil
}
return loadRegistry(item.Content)
}
func registryResolverConfig() registryresolver.Config[*Registry] {
return registryresolver.Config[*Registry]{
Reference: itemReferenceSpec(),
Absent: func() (*Registry, error) {
return emptyRegistry(), nil
},
Load: loadRegistry,
SemanticIdentity: func(registry *Registry) string {
return registry.Digest()
},
}
}
func itemReferenceSpec() registryresolver.ReferenceSpec {
return registryresolver.ReferenceSpec{SlotName: ReferenceSlot, AcceptedMediaType: itemcodec.MediaType, MaxBytes: MaxBytes}
}
func emptyRegistry() *Registry {
content := []byte(emptyPrompt)
projectionDigest := semanticDigest(content)
return &Registry{
list: dnd.ItemRegistry{Items: []dnd.Item{}},
canonical: append([]byte(nil), content...),
projectionDigest: projectionDigest,
promptInput: contracts.NewLLMInputMaterial(ReferenceSlot, itemcodec.MediaType, content, projectionDigest, ""),
lookupByKey: map[string]int{},
lookupByID: map[string]int{},
}
}
func loadRegistry(referenceContent []byte) (*Registry, error) {
codec := itemcodec.New()
value, err := codec.Decode(referenceContent)
if err != nil {
return nil, fmt.Errorf("decode item registry: invalid approved item JSON")
}
if issues := identity.ValidateList(value); len(issues) > 0 {
return nil, fmt.Errorf("%s", formatIdentityIssues(issues))
}
content, err := codec.Encode(value)
if err != nil {
return nil, fmt.Errorf("encode canonical item registry: approved item value could not be encoded")
}
list := cloneItemRegistry(value)
lookupByKey := make(map[string]int, len(list.Items))
lookupByID := make(map[string]int, len(list.Items))
for index, item := range list.Items {
lookupByKey[identity.ComparisonKey(item.Name)] = index
lookupByID[item.ID] = index
}
projection, err := promptProjection(list)
if err != nil {
return nil, fmt.Errorf("encode item registry projection: %w", err)
}
projectionDigest := semanticDigest(projection)
return &Registry{
bound: true,
list: list,
canonical: append([]byte(nil), content...),
digest: semanticDigest(content),
projectionDigest: projectionDigest,
promptInput: contracts.NewLLMInputMaterial(ReferenceSlot, itemcodec.MediaType, projection, projectionDigest, ""),
lookupByKey: lookupByKey,
lookupByID: lookupByID,
}, nil
}
// Bound reports whether an item reference was supplied and validated.
func (r *Registry) Bound() bool { return r != nil && r.bound }
// Items returns a defensive copy of the validated item records.
func (r *Registry) Items() []dnd.Item {
if r == nil {
return nil
}
return cloneItems(r.list.Items)
}
// List returns a defensive copy of the validated item registry.
func (r *Registry) List() dnd.ItemRegistry {
if r == nil {
return dnd.ItemRegistry{}
}
return cloneItemRegistry(r.list)
}
// CanonicalBytes returns a defensive copy of the canonical durable JSON.
func (r *Registry) CanonicalBytes() []byte {
if r == nil {
return nil
}
return append([]byte(nil), r.canonical...)
}
// Digest returns the semantic SHA-256 digest of the canonical JSON, or an
// empty string when the registry is unbound.
func (r *Registry) Digest() string {
if r == nil {
return ""
}
return r.digest
}
// ProjectionDigest returns the SHA-256 digest of the exact names-only prompt
// projection, including for an unbound or empty registry.
func (r *Registry) ProjectionDigest() string {
if r == nil {
return ""
}
return r.projectionDigest
}
// Count returns the number of validated item records.
func (r *Registry) Count() int {
if r == nil {
return 0
}
return len(r.list.Items)
}
// PromptInput returns the ordered names-only registry projection as a
// content-safe prompt input. Durable IDs, evidence, and provenance are omitted.
func (r *Registry) PromptInput() contracts.LLMInputMaterial {
if r == nil {
return contracts.LLMInputMaterial{}
}
return r.promptInput.Clone()
}
// Lookup returns the canonical item for an exact canonical-name match under
// the item identity comparison policy.
func (r *Registry) Lookup(value string) (dnd.Item, bool) {
if r == nil {
return dnd.Item{}, false
}
index, ok := r.lookupByKey[identity.ComparisonKey(value)]
if !ok {
return dnd.Item{}, false
}
return cloneItem(r.list.Items[index]), true
}
// LookupID returns the canonical item for an exact durable ID.
func (r *Registry) LookupID(value string) (dnd.Item, bool) {
if r == nil {
return dnd.Item{}, false
}
index, ok := r.lookupByID[value]
if !ok {
return dnd.Item{}, false
}
return cloneItem(r.list.Items[index]), true
}
func semanticDigest(content []byte) string {
sum := sha256.Sum256(content)
return "sha256:" + hex.EncodeToString(sum[:])
}
type projectedItem struct {
Name string `json:"name"`
}
type projectedItemRegistry struct {
Items []projectedItem `json:"items"`
}
func promptProjection(list dnd.ItemRegistry) ([]byte, error) {
projection := projectedItemRegistry{Items: make([]projectedItem, len(list.Items))}
for index, item := range list.Items {
projection.Items[index] = projectedItem{Name: item.Name}
}
return json.Marshal(projection)
}
func formatIdentityIssues(issues []identity.Issue) string {
parts := make([]string, len(issues))
for index, issue := range issues {
parts[index] = fmt.Sprintf("%s at record %d", issue.Code, issue.RecordIndex)
}
return diagnostics.Aggregate("validate item registry identity", parts)
}
func cloneItemRegistry(value dnd.ItemRegistry) dnd.ItemRegistry {
return dnd.ItemRegistry{Items: cloneItems(value.Items)}
}
func cloneItems(values []dnd.Item) []dnd.Item {
if values == nil {
return nil
}
cloned := make([]dnd.Item, len(values))
for index, value := range values {
cloned[index] = cloneItem(value)
}
return cloned
}
func cloneItem(value dnd.Item) dnd.Item {
value.SourceRefs = append([]source.SourceRef(nil), value.SourceRefs...)
return value
}