notarius/internal/framework/pipeline/profile.go

package pipeline

import (
	"crypto/sha256"
	"encoding/hex"
	"encoding/json"
	"fmt"
	"reflect"
	"sort"
	"strings"

	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
)

const (
	DefaultChunkModule     = "generic"
	DefaultMergeModule     = "appendorder"
	DefaultNormalizeModule = "noop"
	DefaultOutputModule    = "json"
	DefaultLLMProfile      = "default"
)

type ModuleBinding struct {
	Module     string                     `json:"module"`
	LLMProfile string                     `json:"llm_profile,omitempty"`
	Retries    int                        `json:"retries,omitempty"`
	Options    map[string]any             `json:"options,omitempty"`
	References map[string]ReferenceSource `json:"references,omitempty"`
	Validators ValidatorOverride          `json:"validators,omitempty"`
}

// ArtifactReference identifies a normalized artifact produced by an earlier
// ordered step. It is a selector only; it does not contain artifact bytes.
type ArtifactReference struct {
	Step string `json:"step"`
	Lane string `json:"lane"`
}

// ReferenceSource is the discriminated source form used by configured
// reference maps. Exactly one of Path and Artifact is set after resolution.
type ReferenceSource struct {
	Path     string             `json:"path,omitempty"`
	Artifact *ArtifactReference `json:"artifact,omitempty"`
}

func ExternalReference(path string) ReferenceSource {
	return ReferenceSource{Path: strings.TrimSpace(path)}
}

func ExternalReferenceMap(values map[string]string) map[string]ReferenceSource {
	out := make(map[string]ReferenceSource, len(values))
	for key, value := range values {
		out[key] = ExternalReference(value)
	}
	return out
}

func GeneratedReference(step, lane string) ReferenceSource {
	return ReferenceSource{Artifact: &ArtifactReference{Step: strings.TrimSpace(step), Lane: strings.TrimSpace(lane)}}
}

func (source ReferenceSource) IsGenerated() bool { return source.Artifact != nil }

func (source ReferenceSource) MarshalJSON() ([]byte, error) {
	if source.Path != "" && source.Artifact != nil {
		return nil, fmt.Errorf("reference source must not contain both an external path and an artifact selector")
	}
	if source.Artifact != nil {
		return json.Marshal(struct {
			Artifact *ArtifactReference `json:"artifact"`
		}{Artifact: source.Artifact})
	}
	return json.Marshal(source.Path)
}

type ValidatorOverride struct {
	Set        bool            `json:"set,omitempty"`
	Validators []ModuleBinding `json:"validators,omitempty"`
}

func (binding ModuleBinding) MarshalJSON() ([]byte, error) {
	type moduleBindingJSON struct {
		Module     string                     `json:"module"`
		LLMProfile string                     `json:"llm_profile,omitempty"`
		Retries    int                        `json:"retries,omitempty"`
		Options    map[string]any             `json:"options,omitempty"`
		References map[string]ReferenceSource `json:"references,omitempty"`
		Validators *[]ModuleBinding           `json:"validators,omitempty"`
	}
	out := moduleBindingJSON{
		Module:     binding.Module,
		LLMProfile: binding.LLMProfile,
		Retries:    binding.Retries,
		Options:    binding.Options,
		References: binding.References,
	}
	if binding.Validators.Set {
		validators := cloneModuleBindings(binding.Validators.Validators)
		out.Validators = &validators
	}
	return json.Marshal(out)
}

type ArtifactLaneProfile struct {
	Extract    ModuleBinding              `json:"extract"`
	Merge      ModuleBinding              `json:"merge,omitempty"`
	Normalize  ModuleBinding              `json:"normalize,omitempty"`
	Validators []ModuleBinding            `json:"validators,omitempty"`
	References map[string]ReferenceSource `json:"references,omitempty"`
}

type PipelineStepProfile struct {
	ID         string                         `json:"id"`
	Artifacts  map[string]ArtifactLaneProfile `json:"artifacts"`
	References map[string]ReferenceSource     `json:"references,omitempty"`
}

type PipelineProfile struct {
	ID         string                         `json:"id"`
	LLMProfile string                         `json:"llm_profile,omitempty"`
	Input      ModuleBinding                  `json:"input"`
	Chunk      ModuleBinding                  `json:"chunk,omitempty"`
	Artifacts  map[string]ArtifactLaneProfile `json:"artifacts"`
	Steps      []PipelineStepProfile          `json:"steps,omitempty"`
	Output     ModuleBinding                  `json:"output,omitempty"`
	References map[string]ReferenceSource     `json:"references,omitempty"`
}

type ResolveOptions struct {
	Only               []string
	LLMProfileOverride string
	ReferenceOverrides []ReferenceBinding
	ReferenceUnbinds   []ReferenceUnbind
}

type ReferenceBinding struct {
	Stage         ModuleStage        `json:"stage,omitempty"`
	LaneID        string             `json:"lane_id,omitempty"`
	SlotName      string             `json:"slot_name"`
	Source        string             `json:"source,omitempty"`
	Artifact      *ArtifactReference `json:"artifact,omitempty"`
	BindingSource string             `json:"binding_source,omitempty"`
}

type ReferenceUnbind struct {
	Stage    ModuleStage `json:"stage,omitempty"`
	LaneID   string      `json:"lane_id,omitempty"`
	SlotName string      `json:"slot_name"`
}

type ResolvedReferenceTarget struct {
	Stage        ModuleStage            `json:"stage"`
	StepID       string                 `json:"step_id,omitempty"`
	LaneID       string                 `json:"lane_id,omitempty"`
	Module       string                 `json:"module"`
	Bindings     []ReferenceBinding     `json:"bindings,omitempty"`
	ReferenceSet contracts.ReferenceSet `json:"-"`
}

type ResolvedArtifactLane struct {
	StepID                  string
	ID                      string
	ArtifactKind            contracts.ArtifactKind `json:"artifact_kind,omitempty"`
	ArtifactSchemaID        string                 `json:"artifact_schema_id,omitempty"`
	ArtifactSchemaName      string                 `json:"artifact_schema_name,omitempty"`
	ArtifactSchemaVersion   string                 `json:"artifact_schema_version,omitempty"`
	ArtifactSchemaDigest    string                 `json:"artifact_schema_digest,omitempty"`
	Extract                 ModuleBinding
	ExtractExecutionClass   contracts.ExecutionClass `json:"extract_execution_class"`
	Merge                   ModuleBinding
	MergeExecutionClass     contracts.ExecutionClass `json:"merge_execution_class"`
	Normalize               ModuleBinding
	NormalizeExecutionClass contracts.ExecutionClass `json:"normalize_execution_class"`
	Validators              []ModuleBinding
	ExtractReferences       ResolvedReferenceTarget `json:"extract_references"`
	MergeReferences         ResolvedReferenceTarget `json:"merge_references"`
	NormalizeReferences     ResolvedReferenceTarget `json:"normalize_references"`
}

type ResolvedPipelineStep struct {
	ID            string                 `json:"id"`
	ArtifactLanes []ResolvedArtifactLane `json:"artifact_lanes"`
}

type ResolvedValidatorChain struct {
	Stage      ModuleStage         `json:"stage"`
	LaneID     string              `json:"lane_id,omitempty"`
	ModuleKey  string              `json:"module_key"`
	Validators []ResolvedValidator `json:"validators"`
}

type ResolvedValidator struct {
	Binding        ModuleBinding            `json:"binding"`
	ExecutionClass contracts.ExecutionClass `json:"execution_class"`
	Target         ValidatorTarget          `json:"target,omitempty"`
	ArtifactKind   contracts.ArtifactKind   `json:"artifact_kind,omitempty"`
}

type ResolvedPipeline struct {
	ID                   string
	Digest               string
	Input                ModuleBinding
	InputExecutionClass  contracts.ExecutionClass `json:"input_execution_class"`
	Chunk                ModuleBinding
	ChunkExecutionClass  contracts.ExecutionClass `json:"chunk_execution_class"`
	ChunkReferences      ResolvedReferenceTarget  `json:"chunk_references"`
	Steps                []ResolvedPipelineStep
	ValidatorChains      []ResolvedValidatorChain `json:"validator_chains"`
	Output               ModuleBinding
	OutputExecutionClass contracts.ExecutionClass `json:"output_execution_class"`
}

// AllArtifactLanes returns lanes in deterministic step order for read-only
// discovery and identity construction.
func (resolved ResolvedPipeline) AllArtifactLanes() []ResolvedArtifactLane {
	var lanes []ResolvedArtifactLane
	for _, step := range resolved.Steps {
		lanes = append(lanes, step.ArtifactLanes...)
	}
	return lanes
}

type ModuleCatalog struct {
	Inputs           *InputAdapterRegistry
	Chunkers         *ChunkerRegistry
	ArtifactCodecs   *ArtifactCodecRegistry
	ArtifactEvidence *ArtifactEvidenceRegistry
	Extractors       *ExtractorRegistry
	Mergers          *MergerRegistry
	Normalizers      *NormalizerRegistry
	Validators       *ValidatorRegistry
	ValidatorChains  *ValidatorChainRegistry
	Outputs          *OutputEncoderRegistry
}

// ExecutionClass returns the registered execution class for a module selected
// by stage and key without constructing the module.
func (catalog ModuleCatalog) ExecutionClass(stage ModuleStage, key string) (contracts.ExecutionClass, bool) {
	var executionClass contracts.ExecutionClass
	var ok bool

	switch stage {
	case StageInput:
		var spec ModuleSpec
		spec, ok = catalog.Inputs.Spec(key)
		executionClass = spec.ExecutionClass
	case StageChunk:
		var spec ModuleSpec
		spec, ok = catalog.Chunkers.Spec(key)
		executionClass = spec.ExecutionClass
	case StageExtract:
		var spec ModuleSpec
		spec, ok = catalog.Extractors.Spec(key)
		executionClass = spec.ExecutionClass
	case StageMerge:
		var spec ModuleSpec
		spec, ok = catalog.Mergers.Spec(key)
		executionClass = spec.ExecutionClass
	case StageNormalize:
		var spec ModuleSpec
		spec, ok = catalog.Normalizers.Spec(key)
		executionClass = spec.ExecutionClass
	case StageValidate:
		var spec ValidatorSpec
		spec, ok = catalog.Validators.Spec(key)
		executionClass = spec.ExecutionClass
	case StageOutput:
		var spec ModuleSpec
		spec, ok = catalog.Outputs.Spec(key)
		executionClass = spec.ExecutionClass
	}

	return executionClass, ok
}

func Binding(module string) ModuleBinding {
	return ModuleBinding{Module: strings.TrimSpace(module)}
}

func ResolvePipeline(profile PipelineProfile, options ResolveOptions, catalog ModuleCatalog) (ResolvedPipeline, error) {
	pipelineID := strings.TrimSpace(profile.ID)
	if pipelineID == "" {
		return ResolvedPipeline{}, fmt.Errorf("pipeline id must not be empty")
	}

	explicitSteps := profile.Steps != nil
	if len(profile.Artifacts) > 0 && explicitSteps {
		return ResolvedPipeline{}, fmt.Errorf("pipeline %q must not declare both artifacts and steps", pipelineID)
	}
	if explicitSteps && len(options.Only) > 0 {
		return ResolvedPipeline{}, fmt.Errorf("pipeline %q --only is not supported for explicit ordered steps", pipelineID)
	}
	steps := profile.Steps
	if !explicitSteps {
		steps = []PipelineStepProfile{{ID: "default", Artifacts: profile.Artifacts}}
	}
	if explicitSteps && len(steps) == 0 {
		return ResolvedPipeline{}, fmt.Errorf("pipeline %q must declare at least one ordered step", pipelineID)
	}
	if len(steps) == 0 {
		return ResolvedPipeline{}, fmt.Errorf("pipeline %q must declare at least one artifact lane", pipelineID)
	}
	configuredLaneIDs, err := configuredProfileLaneIDs(pipelineID, steps)
	if err != nil {
		return ResolvedPipeline{}, err
	}

	input := resolveBinding(profile.Input, "")
	if input.Module == "" {
		return ResolvedPipeline{}, fmt.Errorf("pipeline %q input module must not be empty", pipelineID)
	}
	inputModuleSpec, err := inputSpec(catalog, input.Module)
	if err != nil {
		return ResolvedPipeline{}, moduleLookupError(pipelineID, "", StageInput, input.Module, err)
	}

	capabilities := newCapabilitySet()
	if missing, ok := capabilities.missing(inputModuleSpec.Requires); ok {
		return ResolvedPipeline{}, capabilityError(pipelineID, "", StageInput, input.Module, missing)
	}
	capabilities.add(inputModuleSpec.Provides...)

	chunk := resolveBinding(profile.Chunk, DefaultChunkModule)
	chunkSpec, err := chunkerSpec(catalog, chunk.Module)
	if err != nil {
		return ResolvedPipeline{}, moduleLookupError(pipelineID, "", StageChunk, chunk.Module, err)
	}
	if missing, ok := capabilities.missing(chunkSpec.Requires); ok {
		return ResolvedPipeline{}, capabilityError(pipelineID, "", StageChunk, chunk.Module, missing)
	}
	capabilities.add(chunkSpec.Provides...)

	if !explicitSteps {
		if err := validatePipelineReferenceDefaults(pipelineID, profile.References, chunkSpec, profile.Artifacts, catalog); err != nil {
			return ResolvedPipeline{}, err
		}
	} else {
		allLanes := make(map[string]ArtifactLaneProfile)
		for _, step := range profile.Steps {
			for laneID, lane := range step.Artifacts {
				allLanes[strings.TrimSpace(laneID)] = lane
			}
		}
		if err := validatePipelineReferenceDefaults(pipelineID, profile.References, chunkSpec, allLanes, catalog); err != nil {
			return ResolvedPipeline{}, err
		}
	}
	for _, source := range profile.References {
		if source.Artifact != nil {
			return ResolvedPipeline{}, fmt.Errorf("pipeline %q pipeline-level references may not use generated artifact selectors", pipelineID)
		}
	}

	chunkReferences, err := resolveReferenceTargetBindings(referenceResolutionTarget{
		PipelineID:         pipelineID,
		Stage:              StageChunk,
		Module:             chunk.Module,
		Slots:              chunkSpec.ReferenceSlots,
		PipelineReferences: profile.References,
		LocalReferences:    chunk.References,
		Options:            options,
	})
	if err != nil {
		return ResolvedPipeline{}, err
	}
	resolved := ResolvedPipeline{
		ID:                  pipelineID,
		Input:               input,
		InputExecutionClass: inputModuleSpec.ExecutionClass,
		Chunk:               chunk,
		ChunkExecutionClass: chunkSpec.ExecutionClass,
		ChunkReferences:     referenceTarget(StageChunk, "", chunk.Module, chunkReferences),
		Output:              resolveBinding(profile.Output, DefaultOutputModule),
	}
	chunkValidatorChain, err := resolveValidatorChain(pipelineID, "", StageChunk, chunk.Module, chunk.Validators, "", nil, catalog)
	if err != nil {
		return ResolvedPipeline{}, err
	}
	resolved.ValidatorChains = append(resolved.ValidatorChains, chunkValidatorChain)
	outputCapabilities := capabilities.clone()
	seenResolvedLanes := make(map[string]string)
	seenResolvedSteps := make(map[string]struct{}, len(steps))

	for _, step := range steps {
		stepID := strings.TrimSpace(step.ID)
		if stepID == "" {
			return ResolvedPipeline{}, fmt.Errorf("pipeline %q step id must not be empty", pipelineID)
		}
		if _, exists := seenResolvedSteps[stepID]; exists {
			return ResolvedPipeline{}, fmt.Errorf("pipeline %q step id %q is duplicated after trimming", pipelineID, stepID)
		}
		seenResolvedSteps[stepID] = struct{}{}
		laneOptions := ResolveOptions{}
		if !explicitSteps {
			laneOptions = options
		}
		lanesByID, selectedLaneIDs, err := selectedArtifactLanes(pipelineID, step.Artifacts, laneOptions)
		if err != nil {
			return ResolvedPipeline{}, err
		}
		if len(selectedLaneIDs) == 0 {
			return ResolvedPipeline{}, fmt.Errorf("pipeline %q step %q must declare at least one artifact lane", pipelineID, stepID)
		}
		if referenceSourceMapsConflict(profile.References, step.References) {
			return ResolvedPipeline{}, fmt.Errorf("pipeline %q step %q has a generated and external reference collision", pipelineID, stepID)
		}
		if err := validatePipelineReferenceDefaults(pipelineID, step.References, chunkSpec, lanesByID, catalog); err != nil {
			return ResolvedPipeline{}, err
		}
		stepReferences := mergeReferenceMaps(profile.References, step.References)
		resolvedStep := ResolvedPipelineStep{ID: stepID}
		for _, laneID := range selectedLaneIDs {
			if previousStep, exists := seenResolvedLanes[laneID]; exists {
				return ResolvedPipeline{}, fmt.Errorf("pipeline %q artifact lane id %q is duplicated across steps %q and %q", pipelineID, laneID, previousStep, stepID)
			}
			seenResolvedLanes[laneID] = stepID
			laneProfile := lanesByID[laneID]
			lane, validatorChains, laneCapabilities, err := resolveArtifactLane(pipelineID, stepID, laneID, laneProfile, stepReferences, options, capabilities, catalog)
			if err != nil {
				return ResolvedPipeline{}, err
			}
			resolvedStep.ArtifactLanes = append(resolvedStep.ArtifactLanes, lane)
			resolved.ValidatorChains = append(resolved.ValidatorChains, validatorChains...)
			outputCapabilities.addSet(laneCapabilities)
		}
		resolved.Steps = append(resolved.Steps, resolvedStep)
	}
	if err := validateGeneratedBindings(pipelineID, resolved, catalog); err != nil {
		return ResolvedPipeline{}, err
	}

	outputSpec, err := outputSpec(catalog, resolved.Output.Module)
	if err != nil {
		return ResolvedPipeline{}, moduleLookupError(pipelineID, "", StageOutput, resolved.Output.Module, err)
	}
	if missing, ok := outputCapabilities.missing(outputSpec.Requires); ok {
		return ResolvedPipeline{}, capabilityError(pipelineID, "", StageOutput, resolved.Output.Module, missing)
	}
	resolved.OutputExecutionClass = outputSpec.ExecutionClass
	if err := applyEffectiveLLMProfiles(&resolved, profile.LLMProfile, options.LLMProfileOverride); err != nil {
		return ResolvedPipeline{}, err
	}
	if err := validateResolvedOptions(resolved, catalog, configuredLaneIDs); err != nil {
		return ResolvedPipeline{}, err
	}

	digest, err := resolvedPipelineDigest(resolved)
	if err != nil {
		return ResolvedPipeline{}, fmt.Errorf("pipeline %q digest: %w", pipelineID, err)
	}
	resolved.Digest = digest
	return resolved, nil
}

// configuredProfileLaneIDs validates the complete configured lane identity
// set before invocation-level selection removes legacy-profile lanes.
func configuredProfileLaneIDs(pipelineID string, steps []PipelineStepProfile) ([]string, error) {
	seen := make(map[string]string)
	var laneIDs []string
	for _, step := range steps {
		_, ids, err := selectedArtifactLanes(pipelineID, step.Artifacts, ResolveOptions{})
		if err != nil {
			return nil, err
		}
		stepID := strings.TrimSpace(step.ID)
		for _, laneID := range ids {
			if previous, ok := seen[laneID]; ok {
				return nil, fmt.Errorf("pipeline %q artifact lane id %q is duplicated across steps %q and %q", pipelineID, laneID, previous, stepID)
			}
			seen[laneID] = stepID
			laneIDs = append(laneIDs, laneID)
		}
	}
	sort.Strings(laneIDs)
	return laneIDs, nil
}

func resolveArtifactLane(
	pipelineID string,
	stepID string,
	laneID string,
	profile ArtifactLaneProfile,
	pipelineReferences map[string]ReferenceSource,
	options ResolveOptions,
	inherited capabilitySet,
	catalog ModuleCatalog,
) (ResolvedArtifactLane, []ResolvedValidatorChain, capabilitySet, error) {
	lane := ResolvedArtifactLane{
		StepID:     strings.TrimSpace(stepID),
		ID:         laneID,
		Extract:    resolveBinding(profile.Extract, ""),
		Merge:      resolveBinding(profile.Merge, DefaultMergeModule),
		Normalize:  resolveBinding(profile.Normalize, DefaultNormalizeModule),
		Validators: resolveBindings(profile.Validators, ""),
	}
	if lane.Extract.Module == "" {
		return ResolvedArtifactLane{}, nil, nil, fmt.Errorf("pipeline %q lane %q extract module must not be empty", pipelineID, laneID)
	}

	capabilities := inherited.clone()

	extractSpec, err := extractorSpec(catalog, lane.Extract.Module)
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, moduleLookupError(pipelineID, laneID, StageExtract, lane.Extract.Module, err)
	}
	if missing, ok := capabilities.missing(extractSpec.Requires); ok {
		return ResolvedArtifactLane{}, nil, nil, capabilityError(pipelineID, laneID, StageExtract, lane.Extract.Module, missing)
	}
	artifactType, err := resolveArtifactIdentity(pipelineID, laneID, &lane, extractSpec, catalog)
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, err
	}
	if referenceSourceMapsConflict(profile.References, lane.Extract.References) {
		return ResolvedArtifactLane{}, nil, nil, fmt.Errorf("pipeline %q step %q lane %q extract has a generated and external reference collision", pipelineID, stepID, laneID)
	}
	extractReferences := mergeReferenceMaps(profile.References, lane.Extract.References)
	references, err := resolveReferenceTargetBindings(referenceResolutionTarget{
		PipelineID:         pipelineID,
		LaneID:             laneID,
		Stage:              StageExtract,
		Module:             lane.Extract.Module,
		Slots:              extractSpec.ReferenceSlots,
		PipelineReferences: pipelineReferences,
		LocalReferences:    extractReferences,
		Options:            options,
	})
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, err
	}
	lane.ExtractReferences = referenceTarget(StageExtract, laneID, lane.Extract.Module, references)
	lane.ExtractReferences.StepID = strings.TrimSpace(stepID)
	lane.ExtractExecutionClass = extractSpec.ExecutionClass
	capabilities.add(extractSpec.Provides...)

	mergeSpec, err := mergerSpecForArtifact(catalog, lane.Merge.Module, lane.ArtifactKind, artifactType)
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, moduleLookupError(pipelineID, laneID, StageMerge, lane.Merge.Module, err)
	}
	if missing, ok := capabilities.missing(mergeSpec.Requires); ok {
		return ResolvedArtifactLane{}, nil, nil, capabilityError(pipelineID, laneID, StageMerge, lane.Merge.Module, missing)
	}
	mergeReferences, err := resolveReferenceTargetBindings(referenceResolutionTarget{
		PipelineID:         pipelineID,
		LaneID:             laneID,
		Stage:              StageMerge,
		Module:             lane.Merge.Module,
		Slots:              mergeSpec.ReferenceSlots,
		PipelineReferences: pipelineReferences,
		LocalReferences:    lane.Merge.References,
		Options:            options,
	})
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, err
	}
	lane.MergeReferences = referenceTarget(StageMerge, laneID, lane.Merge.Module, mergeReferences)
	lane.MergeReferences.StepID = strings.TrimSpace(stepID)
	lane.MergeExecutionClass = mergeSpec.ExecutionClass
	capabilities.add(mergeSpec.Provides...)

	normalizeSpec, err := normalizerSpecForArtifact(catalog, lane.Normalize.Module, lane.ArtifactKind, artifactType)
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, moduleLookupError(pipelineID, laneID, StageNormalize, lane.Normalize.Module, err)
	}
	if missing, ok := capabilities.missing(normalizeSpec.Requires); ok {
		return ResolvedArtifactLane{}, nil, nil, capabilityError(pipelineID, laneID, StageNormalize, lane.Normalize.Module, missing)
	}
	normalizeReferences, err := resolveReferenceTargetBindings(referenceResolutionTarget{
		PipelineID:         pipelineID,
		LaneID:             laneID,
		Stage:              StageNormalize,
		Module:             lane.Normalize.Module,
		Slots:              normalizeSpec.ReferenceSlots,
		PipelineReferences: pipelineReferences,
		LocalReferences:    lane.Normalize.References,
		Options:            options,
	})
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, err
	}
	lane.NormalizeReferences = referenceTarget(StageNormalize, laneID, lane.Normalize.Module, normalizeReferences)
	lane.NormalizeReferences.StepID = strings.TrimSpace(stepID)
	lane.NormalizeExecutionClass = normalizeSpec.ExecutionClass
	capabilities.add(normalizeSpec.Provides...)

	if len(lane.Validators) > 0 {
		return ResolvedArtifactLane{}, nil, nil, configuredValidatorsError(pipelineID, laneID)
	}

	extractValidatorChain, err := resolveValidatorChain(pipelineID, laneID, StageExtract, lane.Extract.Module, lane.Extract.Validators, lane.ArtifactKind, artifactType, catalog)
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, err
	}
	mergeValidatorChain, err := resolveValidatorChain(pipelineID, laneID, StageMerge, lane.Merge.Module, lane.Merge.Validators, lane.ArtifactKind, artifactType, catalog)
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, err
	}
	normalizeValidatorChain, err := resolveValidatorChain(pipelineID, laneID, StageNormalize, lane.Normalize.Module, lane.Normalize.Validators, lane.ArtifactKind, artifactType, catalog)
	if err != nil {
		return ResolvedArtifactLane{}, nil, nil, err
	}
	validatorChains := []ResolvedValidatorChain{extractValidatorChain, mergeValidatorChain, normalizeValidatorChain}

	return lane, validatorChains, capabilities, nil
}

func configuredValidatorsError(pipelineID string, laneID string) error {
	return fmt.Errorf("pipeline %q lane %q validators are not supported at artifact lane level; use extract.validators, merge.validators, or normalize.validators", pipelineID, laneID)
}

func validateGeneratedBindings(pipelineID string, resolved ResolvedPipeline, catalog ModuleCatalog) error {
	stepIndex := make(map[string]int, len(resolved.Steps))
	laneIndex := make(map[string]ResolvedArtifactLane)
	for index, step := range resolved.Steps {
		if _, exists := stepIndex[step.ID]; exists {
			return fmt.Errorf("pipeline %q step id %q is ambiguous", pipelineID, step.ID)
		}
		stepIndex[step.ID] = index
		for _, lane := range step.ArtifactLanes {
			laneIndex[step.ID+"\x00"+lane.ID] = lane
		}
	}
	for consumerIndex, step := range resolved.Steps {
		for _, lane := range step.ArtifactLanes {
			for _, target := range []ResolvedReferenceTarget{lane.ExtractReferences, lane.MergeReferences, lane.NormalizeReferences} {
				slots, err := resolvedReferenceSlots(target, lane.ArtifactKind, catalog)
				if err != nil {
					return fmt.Errorf("pipeline %q step %q lane %q: %w", pipelineID, step.ID, lane.ID, err)
				}
				slotByName := make(map[string]contracts.ReferenceSlot, len(slots))
				for _, slot := range slots {
					slotByName[slot.Name] = slot
				}
				for _, binding := range target.Bindings {
					if binding.Artifact == nil {
						continue
					}
					producerStep, ok := stepIndex[strings.TrimSpace(binding.Artifact.Step)]
					if !ok {
						return fmt.Errorf("pipeline %q step %q lane %q %s reference slot %q producer step %q is not declared", pipelineID, step.ID, lane.ID, target.Stage, binding.SlotName, binding.Artifact.Step)
					}
					if producerStep >= consumerIndex {
						return fmt.Errorf("pipeline %q step %q lane %q reference slot %q producer %q must be an earlier step", pipelineID, step.ID, lane.ID, binding.SlotName, binding.Artifact.Step)
					}
					producer, ok := laneIndex[strings.TrimSpace(binding.Artifact.Step)+"\x00"+strings.TrimSpace(binding.Artifact.Lane)]
					if !ok {
						return fmt.Errorf("pipeline %q step %q lane %q reference slot %q producer lane %q is not selected", pipelineID, step.ID, lane.ID, binding.SlotName, binding.Artifact.Lane)
					}
					slot, ok := slotByName[strings.TrimSpace(binding.SlotName)]
					if !ok {
						return fmt.Errorf("pipeline %q step %q lane %q %s reference slot %q is not declared", pipelineID, step.ID, lane.ID, target.Stage, binding.SlotName)
					}
					if len(slot.AcceptedArtifactKinds) == 0 {
						return fmt.Errorf("pipeline %q step %q lane %q reference slot %q does not accept generated artifacts", pipelineID, step.ID, lane.ID, binding.SlotName)
					}
					accepted := false
					for _, kind := range slot.AcceptedArtifactKinds {
						if kind == producer.ArtifactKind {
							accepted = true
							break
						}
					}
					if !accepted {
						return fmt.Errorf("pipeline %q step %q lane %q reference slot %q does not accept artifact kind %q", pipelineID, step.ID, lane.ID, binding.SlotName, producer.ArtifactKind)
					}
					codecSpec, ok := catalog.ArtifactCodecs.Spec(producer.ArtifactKind)
					if !ok {
						return fmt.Errorf("pipeline %q step %q lane %q producer %q artifact codec %q is not registered", pipelineID, step.ID, lane.ID, producer.ID, producer.ArtifactKind)
					}
					if !referenceMediaTypeAccepted(codecSpec.MediaType, slot.AcceptedMediaTypes) {
						return fmt.Errorf("pipeline %q step %q lane %q reference slot %q does not accept producer media type %q", pipelineID, step.ID, lane.ID, binding.SlotName, codecSpec.MediaType)
					}
				}
			}
		}
	}
	return nil
}

func resolvedReferenceSlots(target ResolvedReferenceTarget, artifactKind contracts.ArtifactKind, catalog ModuleCatalog) ([]contracts.ReferenceSlot, error) {
	spec, err := referenceTargetSpec(target, artifactKind, catalog)
	if err != nil {
		return nil, err
	}
	return contracts.CloneReferenceSlots(spec.ReferenceSlots), nil
}

func resolveArtifactIdentity(pipelineID, laneID string, lane *ResolvedArtifactLane, extractSpec ModuleSpec, catalog ModuleCatalog) (reflect.Type, error) {
	if extractSpec.ArtifactKind == "" {
		return nil, fmt.Errorf("pipeline %q lane %q extract module %q does not declare an artifact kind", pipelineID, laneID, lane.Extract.Module)
	}
	if catalog.Extractors == nil {
		return nil, fmt.Errorf("pipeline %q lane %q extractor registry must not be nil", pipelineID, laneID)
	}
	extractor, ok := catalog.Extractors.typedEntry(lane.Extract.Module)
	if !ok {
		return nil, fmt.Errorf("pipeline %q lane %q extract module %q declares artifact kind %q without a typed registration", pipelineID, laneID, lane.Extract.Module, extractSpec.ArtifactKind)
	}
	if catalog.ArtifactCodecs == nil {
		return nil, fmt.Errorf("pipeline %q lane %q artifact codec registry must not be nil for kind %q", pipelineID, laneID, extractSpec.ArtifactKind)
	}
	codecSpec, ok := catalog.ArtifactCodecs.Spec(extractSpec.ArtifactKind)
	if !ok {
		return nil, fmt.Errorf("pipeline %q lane %q artifact codec %q is not registered", pipelineID, laneID, extractSpec.ArtifactKind)
	}
	codecType, ok := catalog.ArtifactCodecs.valueType(extractSpec.ArtifactKind)
	if !ok {
		return nil, fmt.Errorf("pipeline %q lane %q artifact codec %q has no Go type", pipelineID, laneID, extractSpec.ArtifactKind)
	}
	if extractor.valueType != codecType {
		return nil, artifactTypeMismatchError(pipelineID, laneID, StageExtract, lane.Extract.Module, extractSpec.ArtifactKind, codecType, extractor.valueType)
	}
	lane.ArtifactKind = codecSpec.Kind
	lane.ArtifactSchemaID = codecSpec.Schema.ID
	lane.ArtifactSchemaName = codecSpec.Schema.Name
	lane.ArtifactSchemaVersion = codecSpec.Schema.Version
	lane.ArtifactSchemaDigest = codecSpec.SchemaDigest
	return codecType, nil
}

func mergerSpecForArtifact(catalog ModuleCatalog, key string, kind contracts.ArtifactKind, expectedType reflect.Type) (ModuleSpec, error) {
	if kind == "" {
		return ModuleSpec{}, fmt.Errorf("merger %q cannot be resolved without an artifact kind", key)
	}
	if catalog.Mergers == nil {
		return ModuleSpec{}, fmt.Errorf("module %q is not registered", key)
	}
	entry, ok := catalog.Mergers.typedEntry(key, kind)
	if !ok {
		return ModuleSpec{}, missingArtifactVariantError("merger", key, kind, catalog.Mergers.registeredKinds(key))
	}
	if entry.valueType != expectedType {
		return ModuleSpec{}, fmt.Errorf("artifact kind %q requires Go type %s, but merger %q variant uses %s", kind, typeName(expectedType), key, typeName(entry.valueType))
	}
	return cloneModuleSpec(entry.spec), nil
}

func normalizerSpecForArtifact(catalog ModuleCatalog, key string, kind contracts.ArtifactKind, expectedType reflect.Type) (ModuleSpec, error) {
	if kind == "" {
		return ModuleSpec{}, fmt.Errorf("normalizer %q cannot be resolved without an artifact kind", key)
	}
	if catalog.Normalizers == nil {
		return ModuleSpec{}, fmt.Errorf("module %q is not registered", key)
	}
	entry, ok := catalog.Normalizers.typedEntry(key, kind)
	if !ok {
		return ModuleSpec{}, missingArtifactVariantError("normalizer", key, kind, catalog.Normalizers.registeredKinds(key))
	}
	if entry.valueType != expectedType {
		return ModuleSpec{}, fmt.Errorf("artifact kind %q requires Go type %s, but normalizer %q variant uses %s", kind, typeName(expectedType), key, typeName(entry.valueType))
	}
	return cloneModuleSpec(entry.spec), nil
}

func validatorSpecForTarget(registry *ValidatorRegistry, stage ModuleStage, key string, kind contracts.ArtifactKind, expectedType reflect.Type) (ValidatorSpec, ValidatorTarget, error) {
	key = strings.TrimSpace(key)
	if stage == StageChunk {
		if entry, ok := registry.chunkEntry(key); ok {
			return entry.spec, ValidatorTargetChunk, nil
		}
		if entry, ok := registry.serializedEntry(key); ok && entry.spec.SupportsChunks {
			return entry.spec.ValidatorSpec, ValidatorTargetSerialized, nil
		}
		if spec, ok := registry.Spec(key); ok {
			return spec, "", nil
		}
		return ValidatorSpec{}, "", fmt.Errorf("references unknown validator %q for chunk target", key)
	}
	if kind == "" {
		if spec, ok := registry.Spec(key); ok {
			return spec, "", nil
		}
		return ValidatorSpec{}, "", fmt.Errorf("references unknown validator %q without an artifact kind", key)
	}
	if entry, ok := registry.typedEntry(key, kind); ok {
		if entry.valueType != expectedType {
			return ValidatorSpec{}, "", fmt.Errorf("artifact kind %q requires Go type %s, but validator %q variant uses %s", kind, typeName(expectedType), key, typeName(entry.valueType))
		}
		return entry.spec, ValidatorTargetTyped, nil
	}
	if entry, ok := registry.serializedEntry(key); ok && entry.spec.SupportsArtifacts {
		return entry.spec.ValidatorSpec, ValidatorTargetSerialized, nil
	}
	if _, ok := registry.Spec(key); !ok {
		return ValidatorSpec{}, "", fmt.Errorf("references unknown validator %q for artifact kind %q", key, kind)
	}
	return ValidatorSpec{}, "", missingArtifactVariantError("validator", key, kind, registry.registeredTypedKinds(key))
}

func missingArtifactVariantError(moduleType, key string, kind contracts.ArtifactKind, registered []contracts.ArtifactKind) error {
	if len(registered) == 0 {
		return fmt.Errorf("%s %q has no typed variant for artifact kind %q", moduleType, key, kind)
	}
	values := make([]string, len(registered))
	for i, value := range registered {
		values[i] = string(value)
	}
	return fmt.Errorf("%s %q has no typed variant for artifact kind %q; registered kinds: %s", moduleType, key, kind, strings.Join(values, ", "))
}

func artifactTypeMismatchError(pipelineID, laneID string, stage ModuleStage, module string, kind contracts.ArtifactKind, expected, actual reflect.Type) error {
	return fmt.Errorf("pipeline %q lane %q %s module %q artifact kind %q requires Go type %s, got %s", pipelineID, laneID, stage, module, kind, typeName(expected), typeName(actual))
}

func typeName(value reflect.Type) string {
	if value == nil {
		return "<nil>"
	}
	return value.String()
}

func resolveValidatorChain(pipelineID string, laneID string, stage ModuleStage, module string, override ValidatorOverride, artifactKind contracts.ArtifactKind, artifactType reflect.Type, catalog ModuleCatalog) (ResolvedValidatorChain, error) {
	chain := ResolvedValidatorChain{
		Stage:     stage,
		LaneID:    strings.TrimSpace(laneID),
		ModuleKey: strings.TrimSpace(module),
	}
	if chain.ModuleKey == "" {
		return ResolvedValidatorChain{}, fmt.Errorf("pipeline %q validator chain %q module key must not be empty", pipelineID, stage)
	}
	switch stage {
	case StageChunk, StageExtract, StageMerge, StageNormalize:
	default:
		return ResolvedValidatorChain{}, fmt.Errorf("pipeline %q validator chain stage %q is not supported", pipelineID, stage)
	}

	var bindings []ModuleBinding
	if override.Set {
		bindings = cloneModuleBindings(override.Validators)
	} else if catalog.ValidatorChains != nil {
		bindings = catalog.ValidatorChains.Validators(stage, chain.ModuleKey)
	}
	if len(bindings) == 0 {
		return chain, nil
	}
	if catalog.Validators == nil {
		return ResolvedValidatorChain{}, fmt.Errorf("pipeline %q validator registry must not be nil for %s validator chain on module %q", pipelineID, stage, chain.ModuleKey)
	}
	chain.Validators = make([]ResolvedValidator, 0, len(bindings))
	for _, validator := range bindings {
		spec, target, err := validatorSpecForTarget(catalog.Validators, stage, validator.Module, artifactKind, artifactType)
		if err != nil {
			return ResolvedValidatorChain{}, fmt.Errorf("pipeline %q %s validator chain for module %q: %w", pipelineID, stage, chain.ModuleKey, err)
		}
		chain.Validators = append(chain.Validators, ResolvedValidator{
			Binding:        cloneModuleBinding(validator),
			ExecutionClass: spec.ExecutionClass,
			Target:         target,
			ArtifactKind:   artifactKind,
		})
	}
	return chain, nil
}

func cloneResolvedValidatorChains(chains []ResolvedValidatorChain) []ResolvedValidatorChain {
	if len(chains) == 0 {
		return nil
	}
	out := make([]ResolvedValidatorChain, len(chains))
	for i, chain := range chains {
		out[i] = ResolvedValidatorChain{
			Stage:      chain.Stage,
			LaneID:     strings.TrimSpace(chain.LaneID),
			ModuleKey:  strings.TrimSpace(chain.ModuleKey),
			Validators: cloneResolvedValidators(chain.Validators),
		}
	}
	return out
}

func cloneResolvedValidators(validators []ResolvedValidator) []ResolvedValidator {
	if len(validators) == 0 {
		return nil
	}
	out := make([]ResolvedValidator, len(validators))
	for i, validator := range validators {
		out[i] = ResolvedValidator{
			Binding:        cloneModuleBinding(validator.Binding),
			ExecutionClass: validator.ExecutionClass,
			Target:         validator.Target,
			ArtifactKind:   validator.ArtifactKind,
		}
	}
	return out
}

func referenceTarget(stage ModuleStage, laneID string, module string, bindings []ReferenceBinding) ResolvedReferenceTarget {
	return ResolvedReferenceTarget{
		Stage:    stage,
		LaneID:   strings.TrimSpace(laneID),
		Module:   strings.TrimSpace(module),
		Bindings: append([]ReferenceBinding(nil), bindings...),
	}
}

func mergeReferenceMaps(base map[string]ReferenceSource, override map[string]ReferenceSource) map[string]ReferenceSource {
	if len(base) == 0 && len(override) == 0 {
		return nil
	}
	out := make(map[string]ReferenceSource, len(base)+len(override))
	for key, value := range base {
		out[key] = cloneReferenceSource(value)
	}
	for key, value := range override {
		out[key] = cloneReferenceSource(value)
	}
	return out
}

func referenceSourceMapsConflict(base, override map[string]ReferenceSource) bool {
	for rawKey, left := range base {
		key := strings.TrimSpace(rawKey)
		for rawOverrideKey, right := range override {
			if key == strings.TrimSpace(rawOverrideKey) && left.IsGenerated() != right.IsGenerated() {
				return true
			}
		}
	}
	return false
}

func validatePipelineReferenceDefaults(
	pipelineID string,
	pipelineReferences map[string]ReferenceSource,
	chunkSpec ModuleSpec,
	lanesByID map[string]ArtifactLaneProfile,
	catalog ModuleCatalog,
) error {
	normalizedPipelineReferences, err := normalizedReferenceMap(pipelineReferences, fmt.Sprintf("pipeline %q reference slot", pipelineID))
	if err != nil {
		return err
	}
	if len(normalizedPipelineReferences) == 0 {
		return nil
	}

	declaredByAnyTarget := make(map[string]struct{}, len(normalizedPipelineReferences))
	for _, slot := range chunkSpec.ReferenceSlots {
		declaredByAnyTarget[slot.Name] = struct{}{}
	}
	for _, laneID := range sortedArtifactLaneProfileKeys(lanesByID) {
		laneProfile := lanesByID[laneID]
		extract := resolveBinding(laneProfile.Extract, "")
		if extract.Module == "" {
			return fmt.Errorf("pipeline %q lane %q extract module must not be empty", pipelineID, laneID)
		}
		extractSpec, err := extractorSpec(catalog, extract.Module)
		if err != nil {
			return moduleLookupError(pipelineID, laneID, StageExtract, extract.Module, err)
		}
		for _, slot := range extractSpec.ReferenceSlots {
			declaredByAnyTarget[slot.Name] = struct{}{}
		}

		merge := resolveBinding(laneProfile.Merge, DefaultMergeModule)
		var artifactType reflect.Type
		artifactKind := extractSpec.ArtifactKind
		if artifactKind != "" && catalog.Extractors != nil {
			if entry, ok := catalog.Extractors.typedEntry(extract.Module); ok {
				artifactType = entry.valueType
			}
		}
		mergeSpec, err := mergerSpecForArtifact(catalog, merge.Module, artifactKind, artifactType)
		if err != nil {
			return moduleLookupError(pipelineID, laneID, StageMerge, merge.Module, err)
		}
		for _, slot := range mergeSpec.ReferenceSlots {
			declaredByAnyTarget[slot.Name] = struct{}{}
		}

		normalize := resolveBinding(laneProfile.Normalize, DefaultNormalizeModule)
		normalizeSpec, err := normalizerSpecForArtifact(catalog, normalize.Module, artifactKind, artifactType)
		if err != nil {
			return moduleLookupError(pipelineID, laneID, StageNormalize, normalize.Module, err)
		}
		for _, slot := range normalizeSpec.ReferenceSlots {
			declaredByAnyTarget[slot.Name] = struct{}{}
		}
	}

	for _, slotName := range sortedStringMapKeys(normalizedPipelineReferences) {
		if _, ok := declaredByAnyTarget[slotName]; !ok {
			return fmt.Errorf("pipeline %q reference slot %q is not declared by any eligible reference target", pipelineID, slotName)
		}
	}
	return nil
}

type referenceResolutionTarget struct {
	PipelineID         string
	LaneID             string
	Stage              ModuleStage
	Module             string
	Slots              []contracts.ReferenceSlot
	PipelineReferences map[string]ReferenceSource
	LocalReferences    map[string]ReferenceSource
	Options            ResolveOptions
}

func resolveReferenceTargetBindings(target referenceResolutionTarget) ([]ReferenceBinding, error) {
	slotByName := make(map[string]contracts.ReferenceSlot, len(target.Slots))
	for _, slot := range target.Slots {
		slotByName[slot.Name] = slot
	}

	bindings := make(map[string]ReferenceBinding)
	addBinding := func(slotName string, source ReferenceSource, bindingSource string) error {
		slotName = strings.TrimSpace(slotName)
		if slotName == "" {
			return fmt.Errorf("%s reference slot name must not be empty", referenceTargetErrorContext(target))
		}
		if source.Artifact == nil {
			source.Path = strings.TrimSpace(source.Path)
		}
		if source.Artifact == nil && source.Path == "" {
			return fmt.Errorf("%s reference slot %q source must not be empty", referenceTargetErrorContext(target), slotName)
		}
		if source.Artifact != nil {
			if strings.TrimSpace(source.Path) != "" {
				return fmt.Errorf("%s reference slot %q must contain exactly one source form", referenceTargetErrorContext(target), slotName)
			}
			artifact := *source.Artifact
			artifact.Step = strings.TrimSpace(artifact.Step)
			artifact.Lane = strings.TrimSpace(artifact.Lane)
			if artifact.Step == "" || artifact.Lane == "" {
				return fmt.Errorf("%s reference slot %q artifact selector step and lane must not be empty", referenceTargetErrorContext(target), slotName)
			}
			source.Artifact = &artifact
		}
		if _, ok := slotByName[slotName]; !ok {
			return fmt.Errorf("%s reference slot %q is not declared by %s module %q", referenceTargetErrorContext(target), slotName, target.Stage, target.Module)
		}
		if previous, exists := bindings[slotName]; exists && (previous.Artifact != nil || source.Artifact != nil) {
			return fmt.Errorf("%s reference slot %q has conflicting generated and external bindings", referenceTargetErrorContext(target), slotName)
		}
		binding := ReferenceBinding{
			LaneID:        target.LaneID,
			SlotName:      slotName,
			BindingSource: bindingSource,
		}
		if source.Artifact != nil {
			binding.Artifact = source.Artifact
		} else {
			binding.Source = source.Path
		}
		bindings[slotName] = binding
		return nil
	}

	normalizedPipelineReferences, err := normalizedReferenceMap(target.PipelineReferences, fmt.Sprintf("pipeline %q reference slot", target.PipelineID))
	if err != nil {
		return nil, err
	}
	for _, slotName := range sortedStringMapKeys(normalizedPipelineReferences) {
		if _, ok := slotByName[slotName]; !ok {
			continue
		}
		if err := addBinding(slotName, normalizedPipelineReferences[slotName], contracts.ReferenceBindingSourceConfig); err != nil {
			return nil, err
		}
	}

	normalizedLocalReferences, err := normalizedReferenceMap(target.LocalReferences, referenceTargetSlotLabel(target))
	if err != nil {
		return nil, err
	}
	for _, slotName := range sortedStringMapKeys(normalizedLocalReferences) {
		if err := addBinding(slotName, normalizedLocalReferences[slotName], contracts.ReferenceBindingSourceConfig); err != nil {
			return nil, err
		}
	}

	for _, override := range target.Options.ReferenceOverrides {
		match, err := referenceOverrideMatchesTarget(target, override)
		if err != nil {
			return nil, err
		}
		if !match {
			continue
		}
		source := override.BindingSource
		if strings.TrimSpace(source) == "" {
			source = contracts.ReferenceBindingSourceCLI
		}
		if err := addBinding(override.SlotName, ExternalReference(override.Source), strings.TrimSpace(source)); err != nil {
			return nil, err
		}
	}

	for _, unbind := range target.Options.ReferenceUnbinds {
		match, err := referenceUnbindMatchesTarget(target, unbind)
		if err != nil {
			return nil, err
		}
		if !match {
			continue
		}
		slotName := strings.TrimSpace(unbind.SlotName)
		if slotName == "" {
			return nil, fmt.Errorf("%s reference unbind slot name must not be empty", referenceTargetErrorContext(target))
		}
		if _, ok := slotByName[slotName]; !ok {
			return nil, fmt.Errorf("%s reference slot %q is not declared", referenceTargetErrorContext(target), slotName)
		}
		if binding, ok := bindings[slotName]; ok && binding.Artifact == nil {
			delete(bindings, slotName)
		}
	}

	for _, slot := range target.Slots {
		if slot.Required {
			if _, ok := bindings[slot.Name]; !ok {
				return nil, fmt.Errorf("%s required reference slot %q is not bound", referenceTargetErrorContext(target), slot.Name)
			}
		}
	}

	return sortedReferenceBindings(bindings), nil
}

func referenceOverrideMatchesTarget(target referenceResolutionTarget, override ReferenceBinding) (bool, error) {
	stage, laneID, err := normalizeReferenceOptionTarget(target.PipelineID, "override", override.Stage, override.LaneID)
	if err != nil {
		return false, err
	}
	return stage == target.Stage && laneID == target.LaneID, nil
}

func referenceUnbindMatchesTarget(target referenceResolutionTarget, unbind ReferenceUnbind) (bool, error) {
	stage, laneID, err := normalizeReferenceOptionTarget(target.PipelineID, "unbind", unbind.Stage, unbind.LaneID)
	if err != nil {
		return false, err
	}
	return stage == target.Stage && laneID == target.LaneID, nil
}

func normalizeReferenceOptionTarget(pipelineID string, operation string, stage ModuleStage, laneID string) (ModuleStage, string, error) {
	stage = ModuleStage(strings.TrimSpace(string(stage)))
	if stage == "" {
		stage = StageExtract
	}
	laneID = strings.TrimSpace(laneID)

	switch stage {
	case StageChunk:
		if laneID != "" {
			return "", "", fmt.Errorf("pipeline %q reference %s for chunk must not include a lane id", pipelineID, operation)
		}
	case StageExtract, StageMerge, StageNormalize:
		if laneID == "" {
			return "", "", fmt.Errorf("pipeline %q reference %s lane id must not be empty", pipelineID, operation)
		}
	default:
		return "", "", fmt.Errorf("pipeline %q reference %s stage %q is not supported", pipelineID, operation, stage)
	}
	return stage, laneID, nil
}

func sortedReferenceBindings(bindings map[string]ReferenceBinding) []ReferenceBinding {
	keys := sortedReferenceBindingKeys(bindings)
	resolved := make([]ReferenceBinding, 0, len(keys))
	for _, slotName := range keys {
		resolved = append(resolved, bindings[slotName])
	}
	return resolved
}

func referenceTargetErrorContext(target referenceResolutionTarget) string {
	if target.LaneID != "" {
		return fmt.Sprintf("pipeline %q lane %q %s module %q", target.PipelineID, target.LaneID, target.Stage, target.Module)
	}
	return fmt.Sprintf("pipeline %q %s module %q", target.PipelineID, target.Stage, target.Module)
}

func referenceTargetSlotLabel(target referenceResolutionTarget) string {
	if target.LaneID != "" {
		return fmt.Sprintf("pipeline %q lane %q %s reference slot", target.PipelineID, target.LaneID, target.Stage)
	}
	return fmt.Sprintf("pipeline %q %s reference slot", target.PipelineID, target.Stage)
}

func normalizedReferenceMap(values map[string]ReferenceSource, keyName string) (map[string]ReferenceSource, error) {
	if len(values) == 0 {
		return nil, nil
	}
	out := make(map[string]ReferenceSource, len(values))
	for rawSlotName, rawSource := range values {
		slotName := strings.TrimSpace(rawSlotName)
		if slotName == "" {
			return nil, fmt.Errorf("%s must not be empty", keyName)
		}
		if _, ok := out[slotName]; ok {
			return nil, fmt.Errorf("%s %q is duplicated after trimming", keyName, slotName)
		}
		source := cloneReferenceSource(rawSource)
		if source.Artifact == nil && strings.TrimSpace(source.Path) == "" {
			return nil, fmt.Errorf("%s %q source must not be empty", keyName, slotName)
		}
		out[slotName] = source
	}
	return out, nil
}

func sortedArtifactLaneProfileKeys(values map[string]ArtifactLaneProfile) []string {
	if len(values) == 0 {
		return nil
	}
	keys := make([]string, 0, len(values))
	for key := range values {
		keys = append(keys, key)
	}
	sort.Strings(keys)
	return keys
}

func sortedStringMapKeys(values map[string]ReferenceSource) []string {
	if len(values) == 0 {
		return nil
	}
	keys := make([]string, 0, len(values))
	for key := range values {
		keys = append(keys, key)
	}
	sort.Strings(keys)
	return keys
}

func sortedReferenceBindingKeys(values map[string]ReferenceBinding) []string {
	if len(values) == 0 {
		return nil
	}
	keys := make([]string, 0, len(values))
	for key := range values {
		keys = append(keys, key)
	}
	sort.Strings(keys)
	return keys
}

func resolveBinding(binding ModuleBinding, defaultModule string) ModuleBinding {
	module := strings.TrimSpace(binding.Module)
	if module == "" {
		module = defaultModule
	}
	llmProfile := strings.TrimSpace(binding.LLMProfile)
	return ModuleBinding{
		Module:     module,
		LLMProfile: llmProfile,
		Retries:    binding.Retries,
		Options:    cloneOptions(binding.Options),
		References: normalizeReferenceMap(binding.References),
		Validators: cloneValidatorOverride(binding.Validators),
	}
}

func applyEffectiveLLMProfiles(resolved *ResolvedPipeline, pipelineProfile, overrideProfile string) error {
	pipelineProfile = strings.TrimSpace(pipelineProfile)
	overrideProfile = strings.TrimSpace(overrideProfile)

	apply := func(stage ModuleStage, laneID, module string, binding *ModuleBinding, executionClass contracts.ExecutionClass, kind string) error {
		binding.LLMProfile = strings.TrimSpace(binding.LLMProfile)
		if executionClass != contracts.ExecutionClassLLMBacked {
			if binding.LLMProfile != "" {
				if laneID == "" {
					return fmt.Errorf("pipeline %q %s %q assigns llm_profile to deterministic %s %q", resolved.ID, stage, module, kind, binding.Module)
				}
				return fmt.Errorf("pipeline %q lane %q %s %q assigns llm_profile to deterministic %s %q", resolved.ID, laneID, stage, module, kind, binding.Module)
			}
			return nil
		}
		if overrideProfile != "" {
			binding.LLMProfile = overrideProfile
			return nil
		}
		if binding.LLMProfile == "" {
			binding.LLMProfile = pipelineProfile
		}
		return nil
	}

	if err := apply(StageInput, "", resolved.Input.Module, &resolved.Input, resolved.InputExecutionClass, "module"); err != nil {
		return err
	}
	if err := apply(StageChunk, "", resolved.Chunk.Module, &resolved.Chunk, resolved.ChunkExecutionClass, "module"); err != nil {
		return err
	}
	for stepIndex := range resolved.Steps {
		for laneIndex := range resolved.Steps[stepIndex].ArtifactLanes {
			lane := &resolved.Steps[stepIndex].ArtifactLanes[laneIndex]
			if err := apply(StageExtract, lane.ID, lane.Extract.Module, &lane.Extract, lane.ExtractExecutionClass, "module"); err != nil {
				return err
			}
			if err := apply(StageMerge, lane.ID, lane.Merge.Module, &lane.Merge, lane.MergeExecutionClass, "module"); err != nil {
				return err
			}
			if err := apply(StageNormalize, lane.ID, lane.Normalize.Module, &lane.Normalize, lane.NormalizeExecutionClass, "module"); err != nil {
				return err
			}
		}
	}
	if err := apply(StageOutput, "", resolved.Output.Module, &resolved.Output, resolved.OutputExecutionClass, "module"); err != nil {
		return err
	}
	for chainIndex := range resolved.ValidatorChains {
		chain := &resolved.ValidatorChains[chainIndex]
		for validatorIndex := range chain.Validators {
			validator := &chain.Validators[validatorIndex]
			if err := apply(chain.Stage, chain.LaneID, chain.ModuleKey, &validator.Binding, validator.ExecutionClass, "validator"); err != nil {
				return err
			}
		}
	}
	return nil
}

func resolveBindings(bindings []ModuleBinding, defaultModule string) []ModuleBinding {
	if len(bindings) == 0 {
		return nil
	}

	resolved := make([]ModuleBinding, 0, len(bindings))
	for _, binding := range bindings {
		resolvedBinding := resolveBinding(binding, defaultModule)
		resolved = append(resolved, resolvedBinding)
	}
	return resolved
}

func cloneOptions(options map[string]any) map[string]any {
	if len(options) == 0 {
		return nil
	}

	copied := make(map[string]any, len(options))
	for key, value := range options {
		copied[key] = cloneOptionValue(value)
	}
	return copied
}

func cloneOptionValue(value any) any {
	switch typed := value.(type) {
	case map[string]any:
		return cloneOptions(typed)
	case []any:
		out := make([]any, len(typed))
		for i := range typed {
			out[i] = cloneOptionValue(typed[i])
		}
		return out
	case []string:
		return append([]string(nil), typed...)
	case []byte:
		return append([]byte(nil), typed...)
	case json.RawMessage:
		return append(json.RawMessage(nil), typed...)
	default:
		return value
	}
}

func normalizeReferenceMap(values map[string]ReferenceSource) map[string]ReferenceSource {
	if len(values) == 0 {
		return nil
	}
	out := make(map[string]ReferenceSource, len(values))
	keys := make([]string, 0, len(values))
	rawByNormalized := make(map[string]string, len(values))
	for rawKey := range values {
		key := strings.TrimSpace(rawKey)
		rawByNormalized[key] = rawKey
		keys = append(keys, key)
	}
	sort.Strings(keys)
	for _, key := range keys {
		out[key] = cloneReferenceSource(values[rawByNormalized[key]])
	}
	return out
}

func selectedArtifactLanes(pipelineID string, artifacts map[string]ArtifactLaneProfile, options ResolveOptions) (map[string]ArtifactLaneProfile, []string, error) {
	lanesByID := make(map[string]ArtifactLaneProfile, len(artifacts))
	for rawLaneID, lane := range artifacts {
		laneID := strings.TrimSpace(rawLaneID)
		if laneID == "" {
			return nil, nil, fmt.Errorf("pipeline %q artifact lane id must not be empty", pipelineID)
		}
		if _, ok := lanesByID[laneID]; ok {
			return nil, nil, fmt.Errorf("pipeline %q artifact lane %q is duplicated after trimming", pipelineID, laneID)
		}
		lanesByID[laneID] = lane
	}

	if len(options.Only) == 0 {
		keys := make([]string, 0, len(lanesByID))
		for laneID := range lanesByID {
			keys = append(keys, laneID)
		}
		sort.Strings(keys)
		return lanesByID, keys, nil
	}

	selected := make(map[string]struct{}, len(options.Only))
	for _, rawLaneID := range options.Only {
		laneID := strings.TrimSpace(rawLaneID)
		if laneID == "" {
			return nil, nil, fmt.Errorf("pipeline %q selected artifact lane id must not be empty", pipelineID)
		}
		if _, ok := lanesByID[laneID]; !ok {
			return nil, nil, fmt.Errorf("pipeline %q selected artifact lane %q is not declared", pipelineID, laneID)
		}
		selected[laneID] = struct{}{}
	}

	keys := make([]string, 0, len(selected))
	for laneID := range selected {
		keys = append(keys, laneID)
	}
	sort.Strings(keys)
	return lanesByID, keys, nil
}

func resolvedPipelineDigest(resolved ResolvedPipeline) (string, error) {
	withoutDigest := struct {
		ID                   string
		Input                ModuleBinding
		InputExecutionClass  contracts.ExecutionClass
		Chunk                ModuleBinding
		ChunkExecutionClass  contracts.ExecutionClass
		ChunkReferences      ResolvedReferenceTarget
		Steps                []ResolvedPipelineStep
		ValidatorChains      []ResolvedValidatorChain
		Output               ModuleBinding
		OutputExecutionClass contracts.ExecutionClass
	}{
		ID:                   resolved.ID,
		Input:                resolved.Input,
		InputExecutionClass:  resolved.InputExecutionClass,
		Chunk:                resolved.Chunk,
		ChunkExecutionClass:  resolved.ChunkExecutionClass,
		ChunkReferences:      resolved.ChunkReferences,
		Steps:                resolved.Steps,
		ValidatorChains:      resolved.ValidatorChains,
		Output:               resolved.Output,
		OutputExecutionClass: resolved.OutputExecutionClass,
	}
	encoded, err := json.Marshal(withoutDigest)
	if err != nil {
		return "", err
	}

	sum := sha256.Sum256(encoded)
	return "sha256:" + hex.EncodeToString(sum[:]), nil
}

func inputSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
	return registrySpec(catalog.Inputs, key)
}

func chunkerSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
	return registrySpec(catalog.Chunkers, key)
}

func extractorSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
	return registrySpec(catalog.Extractors, key)
}

func outputSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
	return registrySpec(catalog.Outputs, key)
}

type specRegistry interface {
	Spec(key string) (ModuleSpec, bool)
}

func registrySpec(registry specRegistry, key string) (ModuleSpec, error) {
	if registry == nil {
		return ModuleSpec{}, fmt.Errorf("module %q is not registered", key)
	}
	spec, ok := registry.Spec(key)
	if !ok {
		return ModuleSpec{}, fmt.Errorf("module %q is not registered", key)
	}
	return spec, nil
}

func moduleLookupError(pipelineID, laneID string, stage ModuleStage, module string, err error) error {
	if laneID != "" {
		return fmt.Errorf("pipeline %q lane %q %s module %q: %w", pipelineID, laneID, stage, module, err)
	}
	return fmt.Errorf("pipeline %q %s module %q: %w", pipelineID, stage, module, err)
}

func capabilityError(pipelineID, laneID string, stage ModuleStage, module, capability string) error {
	if laneID != "" {
		return fmt.Errorf("pipeline %q lane %q %s module %q requires missing capability %q", pipelineID, laneID, stage, module, capability)
	}
	return fmt.Errorf("pipeline %q %s module %q requires missing capability %q", pipelineID, stage, module, capability)
}

type capabilitySet map[string]struct{}

func newCapabilitySet() capabilitySet {
	return make(capabilitySet)
}

func (set capabilitySet) clone() capabilitySet {
	copied := make(capabilitySet, len(set))
	for capability := range set {
		copied[capability] = struct{}{}
	}
	return copied
}

func (set capabilitySet) add(values ...string) {
	for _, value := range values {
		set[value] = struct{}{}
	}
}

func (set capabilitySet) addSet(other capabilitySet) {
	for value := range other {
		set[value] = struct{}{}
	}
}

func (set capabilitySet) missing(required []string) (string, bool) {
	for _, capability := range required {
		if _, ok := set[capability]; !ok {
			return capability, true
		}
	}
	return "", false
}