notarius/internal/modules/dnd/extract/itemoccurrences/extractor.go

// Package itemoccurrences extracts source-grounded D&D item occurrences.
package itemoccurrences

import (
	"context"
	"fmt"
	"sort"

	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
	itemregistry "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/items/registry"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
)

const Key = "dnd/item-occurrences"

const (
	ItemRegistryReferenceSlot = itemregistry.ReferenceSlot
	ItemRegistryMaxBytes      = itemregistry.MaxBytes
)

const mappingPolicy = "dnd.item_occurrences.extract_mapping.v2"

var requiredCapabilities = []string{
	"chunks",
	"source.transcript",
}

var providedCapabilities = []string{
	"dnd.item_occurrences",
}

var referenceSlotDescriptions = shared.ReferenceSlotDescriptions{
	Glossary: "Optional campaign glossary reference material used only for item and holder disambiguation.",
	Party:    "Optional party roster reference material used only for item and holder disambiguation.",
	Players:  "Optional player list reference material used only for item and holder disambiguation.",
	Roster:   "Deprecated alias for party roster reference material used only for item and holder disambiguation.",
}

func referenceSlots() []contracts.ReferenceSlot {
	slots := shared.ReferenceSlots(referenceSlotDescriptions)
	slots = append(slots, contracts.ReferenceSlot{
		Name:                  ItemRegistryReferenceSlot,
		Description:           "Required normalized item registry used only for item identity grounding, never as occurrence evidence.",
		Required:              true,
		AcceptedMediaTypes:    []string{"application/json"},
		AcceptedArtifactKinds: []contracts.ArtifactKind{dnd.ItemRegistryKind},
		MaxBytes:              ItemRegistryMaxBytes,
	})
	sort.Slice(slots, func(left, right int) bool { return slots[left].Name < slots[right].Name })
	return slots
}

var _ contracts.Extractor[dnd.ItemOccurrenceList] = (*Extractor)(nil)
var _ contracts.ManifestMetadataProvider = (*Extractor)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Extractor)(nil)

type Options struct{}

type Extractor struct {
	llm               contracts.StructuredLLMClient
	itemResolver      *itemregistry.Resolver
	promptSHA         string
	responseSchemaSHA string
}

func New(llmClient contracts.StructuredLLMClient, _ Options, references ...contracts.ReferenceSet) (*Extractor, error) {
	if llmClient == nil {
		return nil, extractorErrorf("LLM client must not be nil")
	}
	if len(references) > 1 {
		return nil, extractorErrorf("at most one reference set may be supplied")
	}
	var referenceSet contracts.ReferenceSet
	if len(references) == 1 {
		referenceSet = references[0]
	}
	itemResolver, err := itemregistry.NewResolver(referenceSet)
	if err != nil {
		return nil, extractorErrorf("prepare item registry prompt input: %w", err)
	}
	promptSHA, err := promptAssetMetadata()
	if err != nil {
		return nil, extractorErrorf("load prompt metadata: %w", err)
	}
	responseSchema, err := loadResponseSchema()
	if err != nil {
		return nil, extractorErrorf("load response schema: %w", err)
	}
	return &Extractor{llm: llmClient, itemResolver: itemResolver, promptSHA: promptSHA, responseSchemaSHA: responseSchema.SHA256}, nil
}

func (e *Extractor) Key() string { return Key }

func (e *Extractor) ReferenceSlots() []contracts.ReferenceSlot { return referenceSlots() }

func (e *Extractor) ManifestMetadata() map[string]any {
	if e == nil {
		return nil
	}
	metadata := map[string]any{
		"prompt_id":               PromptID,
		"prompt_version":          SchemaVersion,
		"prompt_sha256":           e.promptSHA,
		"response_schema_key":     string(ResponseSchemaKey),
		"response_schema_id":      ResponseSchemaID,
		"response_schema_name":    ResponseSchemaName,
		"response_schema_version": SchemaVersion,
		"response_schema_sha256":  e.responseSchemaSHA,
		"mapping_policy":          mappingPolicy,
		"comparison_policy":       shared.TextComparisonPolicy,
	}
	seeded := e.itemResolver.Seeded()
	if seeded.Bound() {
		metadata["item_registry_digest"] = seeded.Digest()
		metadata["item_count"] = seeded.Count()
	}
	return metadata
}

func (e *Extractor) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
	if e == nil {
		return nil
	}
	return []pipeline.CheckpointFingerprint{
		{Name: "prompt", Value: e.promptSHA},
		{Name: "response_schema", Value: e.responseSchemaSHA},
		{Name: "mapping_policy", Value: mappingPolicy},
		{Name: "comparison_policy", Value: shared.TextComparisonPolicy},
		{Name: "item_registry", Value: e.itemResolver.Seeded().ProjectionDigest()},
	}
}

func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRequest) (contracts.TypedExtractionResult[dnd.ItemOccurrenceList], error) {
	if e == nil {
		return contracts.TypedExtractionResult[dnd.ItemOccurrenceList]{}, extractorErrorf("extractor must not be nil")
	}
	if e.llm == nil {
		return contracts.TypedExtractionResult[dnd.ItemOccurrenceList]{}, extractorErrorf("LLM client must not be nil")
	}
	sourceInput, err := shared.PrepareChunkExtraction(ctx, req)
	if err != nil {
		return contracts.TypedExtractionResult[dnd.ItemOccurrenceList]{}, extractorErrorf("%w", err)
	}
	order := shared.NewSourceRefOrder(req.Source)

	registry, err := e.itemResolver.Resolve(req.References)
	if err != nil {
		return contracts.TypedExtractionResult[dnd.ItemOccurrenceList]{}, extractorErrorf("resolve item registry: %w", err)
	}
	if !registry.Bound() {
		return contracts.TypedExtractionResult[dnd.ItemOccurrenceList]{}, extractorErrorf("item registry reference is required")
	}
	var response extractionResponse
	inputs := shared.PromptInputs(sourceInput, req.References)
	inputs[ItemRegistryReferenceSlot] = registry.PromptInput()
	if _, err := e.llm.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
		StageName: Key, PromptID: PromptID, PromptVersion: SchemaVersion,
		ProfileID: req.LLMProfile, SessionID: req.SessionID, Inputs: inputs,
	}, &response); err != nil {
		return contracts.TypedExtractionResult[dnd.ItemOccurrenceList]{}, extractorErrorf("complete structured output: %w", err)
	}
	value, err := canonicalItemOccurrenceList(response, order, req.Source.ID, registry)
	if err != nil {
		return contracts.TypedExtractionResult[dnd.ItemOccurrenceList]{}, extractorErrorf("map item occurrence response: %w", err)
	}
	return contracts.TypedExtractionResult[dnd.ItemOccurrenceList]{Value: value}, nil
}

func ModuleSpec() pipeline.ModuleSpec {
	return pipeline.ModuleSpec{
		Key:            Key,
		Stage:          pipeline.StageExtract,
		ExecutionClass: contracts.ExecutionClassLLMBacked,
		Requires:       append([]string(nil), requiredCapabilities...),
		Provides:       append([]string(nil), providedCapabilities...),
		ArtifactKind:   dnd.ItemOccurrenceListKind,
		ReferenceSlots: referenceSlots(),
	}
}

func Register(registry *pipeline.ExtractorRegistry) error {
	return pipeline.RegisterExtractorBuilder(registry, ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Extractor[dnd.ItemOccurrenceList], error) {
		options, err := DecodeOptions(request.Options)
		if err != nil {
			return nil, err
		}
		return New(request.Dependencies.LLM, options, request.References)
	})
}

func validateOptions(options map[string]any) error {
	_, err := DecodeOptions(options)
	return err
}

func DecodeOptions(options map[string]any) (Options, error) {
	if err := pipeline.RejectUnknownOptions(options); err != nil {
		return Options{}, extractorErrorf("%w", err)
	}
	return Options{}, nil
}

func extractorErrorf(format string, args ...any) error {
	return fmt.Errorf("dnd item occurrences extractor: "+format, args...)
}