notarius/internal/modules/dnd/validate/combatturns/source_refs/validator.go

package sourcerefs

import (
	"context"
	"fmt"

	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
	combatshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/combatturns/shape"
)

const (
	Key        = "extract/dnd/combat-turns/source_refs"
	ReasonCode = "invalid_combat_turn_source_refs"
	policy     = "dnd.combat_turns.validator.source_refs.v3"
)

type Options struct{}
type Validator struct{}

var _ contracts.TypedValidator[dnd.CombatTurnList] = (*Validator)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Validator)(nil)

func New(Options) *Validator      { return &Validator{} }
func (v *Validator) Name() string { return Key }
func (v *Validator) ExecutionClass() contracts.ExecutionClass {
	return contracts.ExecutionClassDeterministic
}
func (v *Validator) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
	return []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}
}

func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.CombatTurnList]) (contracts.ValidationResult, error) {
	if req.Stage == string(pipeline.StageExtract) && req.Chunk == nil {
		return contracts.ValidationResult{}, fmt.Errorf("combat-turn source-reference validator requires the current extraction chunk")
	}
	if err := combatshape.Validate(req.Value); err != nil {
		return contracts.ValidationResult{Approved: true}, nil
	}
	var coverage shared.ChunkCoverage
	if req.Stage == string(pipeline.StageExtract) {
		coverage = shared.NewChunkCoverage(req.Chunk)
	}
	issues, corrections := sourceRefIssues(source.NewDocumentIndex(req.Source), req.Source, coverage, req.Stage == string(pipeline.StageExtract), req.Value)
	if len(issues) == 0 {
		return contracts.ValidationResult{Approved: true}, nil
	}
	return contracts.ValidationResult{
		Approved:           false,
		ReasonCode:         ReasonCode,
		Message:            diagnostics.Aggregate("invalid combat turn source references", issues),
		CorrectionGuidance: corrections.Guidance("Correct every rejected combat-turn citation and return the complete replacement combat-turn list"),
	}, nil
}

func sourceRefIssues(index source.DocumentIndex, doc *source.SourceDocument, coverage shared.ChunkCoverage, checkCoverage bool, value dnd.CombatTurnList) ([]string, diagnostics.Corrections) {
	issues := make([]string, 0)
	var corrections diagnostics.Corrections
	for turnIndex, turn := range value.CombatTurns {
		for refIndex, ref := range turn.SourceRefs {
			record := fmt.Sprintf("Affected %s for actor %s, citing %s.", diagnostics.Quote(string(turn.TurnKind)), diagnostics.Quote(turn.Actor), diagnostics.SourceRefRange(ref))
			if err := index.ValidateRef(ref); err != nil {
				issues = append(issues, fmt.Sprintf("combat_turns[%d].source_refs[%d]: %s", turnIndex, refIndex, diagnostics.Truncate(err.Error())))
				corrections.Add("valid-range", "Use positive source range endpoints that occur in the supplied transcript, with the earlier unit first.", record)
				continue
			}
			if checkCoverage && !coverage.Contains(index, doc, ref) {
				issues = append(issues, fmt.Sprintf("combat_turns[%d].source_refs[%d]: source reference is outside the current extraction chunk", turnIndex, refIndex))
				corrections.Add("chunk-range", "Use only source ranges wholly contained in the supplied extraction chunk.", record)
			}
		}
	}
	return issues, corrections
}

func Spec() pipeline.ValidatorSpec {
	return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}

func Register(registry *pipeline.ValidatorRegistry) error {
	return pipeline.RegisterTypedValidatorBuilder(registry, dnd.CombatTurnListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.CombatTurnList], error) {
		options, err := DecodeOptions(request.Options)
		if err != nil {
			return nil, err
		}
		return New(options), nil
	})
}

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

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