notarius/internal/modules/dnd/npcs/registry/registry.go

// Package registry resolves normalized NPC artifacts into immutable grounding
// data for D&D extraction modules.
package registry

import (
	"crypto/sha256"
	"encoding/hex"
	"encoding/json"
	"fmt"
	"mime"
	"strings"
	"sync"

	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
	npccodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcs"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
)

const (
	ReferenceSlot = "npcs"
	MaxBytes      = 1048576
	emptyPrompt   = `{"npcs":[]}`
)

// Registry is an immutable, validated NPC registry prepared for prompt
// grounding. All accessors return defensive copies.
type Registry struct {
	bound            bool
	list             dnd.NPCList
	canonical        []byte
	digest           string
	projectionDigest string
	promptInput      contracts.LLMInputMaterial
	lookupByKey      map[string]int
}

// Resolver retains only the validated construction-time registry and immutable
// canonical registries keyed by their semantic digest. Operation references
// are resolved on demand; caller-owned reference bytes are never retained.
type Resolver struct {
	seeded *Registry

	mu       sync.Mutex
	cache    map[string]*Registry
	rawCache map[string]*Registry
}

// NewResolver validates the optional construction-time NPC reference and
// prepares the operation-time registry cache. A malformed static reference
// therefore fails before any operation starts.
func NewResolver(references contracts.ReferenceSet) (*Resolver, error) {
	seeded, err := Resolve(constructionReferences(references))
	if err != nil {
		return nil, err
	}
	return &Resolver{seeded: seeded, cache: make(map[string]*Registry), rawCache: make(map[string]*Registry)}, nil
}

func constructionReferences(references contracts.ReferenceSet) contracts.ReferenceSet {
	slot, ok := references.Slots[ReferenceSlot]
	if !ok || len(slot.Items) > 0 {
		return references
	}
	cloned := contracts.ReferenceSet{Slots: make(map[string]contracts.ResolvedReferenceSlot, len(references.Slots))}
	for name, value := range references.Slots {
		cloned.Slots[name] = value
	}
	delete(cloned.Slots, ReferenceSlot)
	return cloned
}

// Seeded returns the immutable construction-time registry. Its accessors are
// defensive, so callers may safely use the returned view for static metadata.
func (r *Resolver) Seeded() *Registry {
	if r == nil {
		return nil
	}
	return r.seeded
}

// Resolve returns the effective registry for one operation. An operation
// without an NPC item uses the construction-time registry. A canonical item
// matching that registry reuses it; other canonical registries are cached by
// digest for concurrent chunk operations.
func (r *Resolver) Resolve(references contracts.ReferenceSet) (*Registry, error) {
	if r == nil {
		return Resolve(references)
	}
	if _, ok := references.Slots[ReferenceSlot]; !ok {
		return r.seeded, nil
	}

	slot := references.Slots[ReferenceSlot]
	rawKey := ""
	if len(slot.Items) == 1 {
		rawKey = strings.ToLower(strings.TrimSpace(slot.Items[0].MediaType)) + "\x00" + semanticDigest(slot.Items[0].Content)
	}

	r.mu.Lock()
	defer r.mu.Unlock()
	if rawKey != "" {
		if cached, ok := r.rawCache[rawKey]; ok {
			return cached, nil
		}
	}
	resolved, err := Resolve(references)
	if err != nil {
		return nil, err
	}
	if sameRegistryIdentity(r.seeded, resolved) {
		if rawKey != "" {
			r.rawCache[rawKey] = r.seeded
		}
		return r.seeded, nil
	}

	if cached, ok := r.cache[resolved.Digest()]; ok {
		if rawKey != "" {
			r.rawCache[rawKey] = cached
		}
		return cached, nil
	}
	r.cache[resolved.Digest()] = resolved
	if rawKey != "" {
		r.rawCache[rawKey] = resolved
	}
	return resolved, nil
}

func sameRegistryIdentity(first, second *Registry) bool {
	if first == nil || second == nil {
		return first == second
	}
	return first.bound == second.bound && first.digest == second.digest
}

// Resolve prepares the optional NPC registry reference. An absent slot
// produces the exact empty prompt input and no semantic registry identity.
func Resolve(references contracts.ReferenceSet) (*Registry, error) {
	slot, ok := references.Slots[ReferenceSlot]
	if !ok {
		content := []byte(emptyPrompt)
		projectionDigest := semanticDigest(content)
		return &Registry{
			list:             dnd.NPCList{NPCs: []dnd.NPC{}},
			canonical:        append([]byte(nil), content...),
			projectionDigest: projectionDigest,
			promptInput:      contracts.NewLLMInputMaterial(ReferenceSlot, npccodec.MediaType, content, projectionDigest, ""),
			lookupByKey:      map[string]int{},
		}, nil
	}
	if len(slot.Items) != 1 {
		return nil, fmt.Errorf("reference slot %q must contain exactly one item", ReferenceSlot)
	}

	item := slot.Items[0]
	mediaType, _, err := mime.ParseMediaType(item.MediaType)
	if err != nil {
		return nil, fmt.Errorf("reference slot %q item media type is invalid", ReferenceSlot)
	}
	if !strings.EqualFold(mediaType, npccodec.MediaType) {
		return nil, fmt.Errorf("reference slot %q item media type must be %s", ReferenceSlot, npccodec.MediaType)
	}
	if len(item.Content) > MaxBytes {
		return nil, fmt.Errorf("reference slot %q item is %d bytes, limit %d", ReferenceSlot, len(item.Content), MaxBytes)
	}

	codec := npccodec.New()
	value, err := codec.Decode(item.Content)
	if err != nil {
		return nil, fmt.Errorf("decode NPC registry: invalid approved NPC 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 NPC registry: approved NPC value could not be encoded")
	}

	list := cloneNPCList(value)
	lookupByKey := make(map[string]int, len(list.NPCs))
	for index, npc := range list.NPCs {
		lookupByKey[identity.ComparisonKey(npc.Name)] = index
	}
	digest := semanticDigest(content)
	projection, err := nameProjection(list)
	if err != nil {
		return nil, fmt.Errorf("encode NPC name projection: %w", err)
	}
	projectionDigest := semanticDigest(projection)
	return &Registry{
		bound:            true,
		list:             list,
		canonical:        append([]byte(nil), content...),
		digest:           digest,
		projectionDigest: projectionDigest,
		promptInput:      contracts.NewLLMInputMaterial(ReferenceSlot, npccodec.MediaType, projection, projectionDigest, ""),
		lookupByKey:      lookupByKey,
	}, nil
}

// Bound reports whether an NPC reference was supplied and validated.
func (r *Registry) Bound() bool { return r != nil && r.bound }

// NPCs returns a defensive copy of the validated NPC records.
func (r *Registry) NPCs() []dnd.NPC {
	if r == nil {
		return nil
	}
	return cloneNPCs(r.list.NPCs)
}

// List returns a defensive copy of the validated NPC list.
func (r *Registry) List() dnd.NPCList {
	if r == nil {
		return dnd.NPCList{}
	}
	return cloneNPCList(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 NPC records.
func (r *Registry) Count() int {
	if r == nil {
		return 0
	}
	return len(r.list.NPCs)
}

// PromptInput returns the names-only registry projection as a content-safe
// prompt input. Durable IDs, evidence, and reference provenance are omitted.
func (r *Registry) PromptInput() contracts.LLMInputMaterial {
	if r == nil {
		return contracts.LLMInputMaterial{}
	}
	return r.promptInput.Clone()
}

// Lookup returns the canonical NPC for an exact canonical-name match under the
// NPC identity comparison policy.
func (r *Registry) Lookup(value string) (dnd.NPC, bool) {
	if r == nil {
		return dnd.NPC{}, false
	}
	index, ok := r.lookupByKey[identity.ComparisonKey(value)]
	if !ok {
		return dnd.NPC{}, false
	}
	return cloneNPC(r.list.NPCs[index]), true
}

func semanticDigest(content []byte) string {
	sum := sha256.Sum256(content)
	return "sha256:" + hex.EncodeToString(sum[:])
}

type projectedNPC struct {
	Name string `json:"name"`
}

type projectedNPCList struct {
	NPCs []projectedNPC `json:"npcs"`
}

func nameProjection(list dnd.NPCList) ([]byte, error) {
	projection := projectedNPCList{NPCs: make([]projectedNPC, len(list.NPCs))}
	for index, npc := range list.NPCs {
		projection.NPCs[index] = projectedNPC{Name: npc.Name}
	}
	return json.Marshal(projection)
}

func formatIdentityIssues(issues []identity.Issue) string {
	parts := make([]string, len(issues))
	for index, issue := range issues {
		location := fmt.Sprintf("record %d", issue.RecordIndex)
		parts[index] = fmt.Sprintf("%s at %s", issue.Code, location)
	}
	return diagnostics.Aggregate("validate NPC registry identity", parts)
}

func cloneNPCList(value dnd.NPCList) dnd.NPCList {
	return dnd.NPCList{NPCs: cloneNPCs(value.NPCs)}
}

func cloneNPCs(values []dnd.NPC) []dnd.NPC {
	if values == nil {
		return nil
	}
	cloned := make([]dnd.NPC, len(values))
	for index, value := range values {
		cloned[index] = cloneNPC(value)
	}
	return cloned
}

func cloneNPC(value dnd.NPC) dnd.NPC {
	value.SourceRefs = append([]source.SourceRef(nil), value.SourceRefs...)
	return value
}