notarius/internal/modules/integration/dnd_spells_config_test.go

package integration_test

import (
	"context"
	"os"
	"strings"
	"testing"

	"gitea.maximumdirect.net/eric/notarius/internal/core/config"
	"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"
	spellcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/spells"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/spells"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/generic/merge/appendorder"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/generic/normalize/noop"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/seriatim/input/transcript"
)

func TestDNDSpellCapabilityFailures(t *testing.T) {
	tests := []struct {
		name       string
		mutate     func(pipeline.ModuleSpec, pipeline.ModuleSpec) (pipeline.ModuleSpec, pipeline.ModuleSpec)
		wantModule string
		wantCap    string
	}{
		{
			name: "spell extractor requires transcript source",
			mutate: func(input, extractor pipeline.ModuleSpec) (pipeline.ModuleSpec, pipeline.ModuleSpec) {
				input.Provides = withoutCapability(input.Provides, "source.transcript")
				return input, extractor
			},
			wantModule: spells.Key,
			wantCap:    "source.transcript",
		},
		{
			name: "append-order merger requires spell casts",
			mutate: func(input, extractor pipeline.ModuleSpec) (pipeline.ModuleSpec, pipeline.ModuleSpec) {
				extractor.Provides = withoutCapability(extractor.Provides, "dnd.spell_casts")
				return input, extractor
			},
			wantModule: pipeline.DefaultMergeModule,
			wantCap:    "dnd.spell_casts",
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			inputSpec, extractorSpec := tt.mutate(transcript.ModuleSpec(), spells.ModuleSpec())
			_, err := pipeline.ResolvePipeline(dndCapabilityProfile(), pipeline.ResolveOptions{}, dndCapabilityCatalog(t, inputSpec, extractorSpec))
			if err == nil || !strings.Contains(err.Error(), "missing capability") || !strings.Contains(err.Error(), tt.wantCap) || !strings.Contains(err.Error(), tt.wantModule) {
				t.Fatalf("ResolvePipeline() error = %v, want %s missing %s capability", err, tt.wantModule, tt.wantCap)
			}
		})
	}
}

func dndCapabilityProfile() pipeline.PipelineProfile {
	return pipeline.PipelineProfile{
		ID:    "dnd-capability",
		Input: pipeline.Binding(transcript.Key),
		Chunk: pipeline.Binding("fake/chunk"),
		Artifacts: map[string]pipeline.ArtifactLaneProfile{
			"spells": {Extract: pipeline.Binding(spells.Key)},
		},
	}
}

func dndCapabilityCatalog(t *testing.T, inputSpec, extractorSpec pipeline.ModuleSpec) pipeline.ModuleCatalog {
	t.Helper()
	inputs := pipeline.NewInputAdapterRegistry()
	if err := inputs.RegisterWithSpec(inputSpec, func() (contracts.InputAdapter, error) { return transcript.New(), nil }); err != nil {
		t.Fatalf("register capability input: %v", err)
	}

	chunkers := pipeline.NewChunkerRegistry()
	if err := chunkers.RegisterWithSpec(pipeline.ModuleSpec{Key: "fake/chunk", Stage: pipeline.StageChunk, ExecutionClass: contracts.ExecutionClassDeterministic, Provides: []string{"chunks"}}, func() (contracts.Chunker, error) { return dndSpellsChunker{}, nil }); err != nil {
		t.Fatalf("register capability chunker: %v", err)
	}

	extractors := pipeline.NewExtractorRegistry()
	extractorSpec.ArtifactKind = dnd.SpellListKind
	if err := pipeline.RegisterExtractor[dnd.SpellList](extractors, extractorSpec, func() (contracts.Extractor[dnd.SpellList], error) {
		return configExtractor{key: extractorSpec.Key}, nil
	}); err != nil {
		t.Fatalf("register capability extractor: %v", err)
	}

	codecs := pipeline.NewArtifactCodecRegistry()
	evidence := pipeline.NewArtifactEvidenceRegistry()
	if err := pipeline.RegisterArtifactCodec(codecs, spellcodec.New()); err != nil {
		t.Fatalf("register capability codec: %v", err)
	}

	mergers := pipeline.NewMergerRegistry()
	if err := pipeline.RegisterMerger[dnd.SpellList](mergers, pipeline.ModuleSpec{
		Key: pipeline.DefaultMergeModule, Stage: pipeline.StageMerge, ExecutionClass: contracts.ExecutionClassDeterministic, ArtifactKind: dnd.SpellListKind, Requires: []string{"dnd.spell_casts"},
	}, func() (contracts.Merger[dnd.SpellList], error) { return appendorder.NewTyped(appendSpellLists) }); err != nil {
		t.Fatalf("register capability merger: %v", err)
	}

	normalizers := pipeline.NewNormalizerRegistry()
	if err := pipeline.RegisterNormalizer[dnd.SpellList](normalizers, pipeline.ModuleSpec{Key: pipeline.DefaultNormalizeModule, Stage: pipeline.StageNormalize, ExecutionClass: contracts.ExecutionClassDeterministic, ArtifactKind: dnd.SpellListKind}, func() (contracts.Normalizer[dnd.SpellList], error) {
		return noop.NewTyped[dnd.SpellList](), nil
	}); err != nil {
		t.Fatalf("register capability normalizer: %v", err)
	}

	outputs := pipeline.NewOutputEncoderRegistry()
	if err := outputs.RegisterWithSpec(pipeline.ModuleSpec{Key: pipeline.DefaultOutputModule, Stage: pipeline.StageOutput, ExecutionClass: contracts.ExecutionClassDeterministic}, func() (contracts.OutputEncoder, error) { return dndSpellsOutput{}, nil }); err != nil {
		t.Fatalf("register capability output: %v", err)
	}

	return pipeline.ModuleCatalog{
		Inputs: inputs, Chunkers: chunkers, ArtifactCodecs: codecs, ArtifactEvidence: evidence, Extractors: extractors,
		Mergers: mergers, Normalizers: normalizers, ValidatorChains: pipeline.NewValidatorChainRegistry(), Outputs: outputs,
	}
}

func loadDNDSpellsPipelineConfig(t *testing.T) config.Config {
	t.Helper()

	data, err := os.ReadFile("testdata/pipeline.yml")
	if err != nil {
		t.Fatalf("ReadFile(pipeline.yml) error = %v, want nil", err)
	}
	fileCfg, err := config.ParseFileConfigYAML(data)
	if err != nil {
		t.Fatalf("ParseFileConfigYAML() error = %v, want nil", err)
	}
	cfg := config.Default()
	if err := cfg.ApplyFileConfig(fileCfg); err != nil {
		t.Fatalf("ApplyFileConfig() error = %v, want nil", err)
	}
	return cfg
}

type dndSpellsCatalogSpecs struct {
	input     pipeline.ModuleSpec
	chunk     pipeline.ModuleSpec
	extractor pipeline.ModuleSpec
}

func dndSpellsTestCatalog(t *testing.T, specs dndSpellsCatalogSpecs) pipeline.ModuleCatalog {
	t.Helper()

	inputs := pipeline.NewInputAdapterRegistry()
	chunkers := pipeline.NewChunkerRegistry()
	extractors := pipeline.NewExtractorRegistry()
	codecs := pipeline.NewArtifactCodecRegistry()
	evidence := pipeline.NewArtifactEvidenceRegistry()
	mergers := pipeline.NewMergerRegistry()
	normalizers := pipeline.NewNormalizerRegistry()
	outputs := pipeline.NewOutputEncoderRegistry()

	if specs.input.Key == "" {
		if err := transcript.Register(inputs); err != nil {
			t.Fatalf("register seriatim input: %v", err)
		}
	} else if err := inputs.RegisterWithSpec(specs.input, func() (contracts.InputAdapter, error) {
		return transcript.New(), nil
	}); err != nil {
		t.Fatalf("register seriatim input override: %v", err)
	}

	chunkSpec := specs.chunk
	if chunkSpec.Key == "" {
		chunkSpec = dndSpellsChunkerSpec()
	}
	if err := chunkers.RegisterWithSpec(chunkSpec, func() (contracts.Chunker, error) {
		return dndSpellsChunker{}, nil
	}); err != nil {
		t.Fatalf("register chunker: %v", err)
	}

	codec := spellcodec.New()
	if err := pipeline.RegisterArtifactCodec(codecs, codec); err != nil {
		t.Fatalf("register dnd spells codec: %v", err)
	}
	if specs.extractor.Key == "" {
		if err := spells.Register(extractors); err != nil {
			t.Fatalf("register dnd spells extractor: %v", err)
		}
	} else {
		specs.extractor.ArtifactKind = dnd.SpellListKind
		if err := pipeline.RegisterExtractor[dnd.SpellList](extractors, specs.extractor, func() (contracts.Extractor[dnd.SpellList], error) {
			return configExtractor{key: specs.extractor.Key}, nil
		}); err != nil {
			t.Fatalf("register dnd spells extractor override: %v", err)
		}
	}

	if err := pipeline.RegisterMerger[dnd.SpellList](mergers, pipeline.ModuleSpec{
		Key:            pipeline.DefaultMergeModule,
		Stage:          pipeline.StageMerge,
		ExecutionClass: contracts.ExecutionClassDeterministic,
		ArtifactKind:   dnd.SpellListKind,
		Requires:       []string{"dnd.spell_casts"},
	}, func() (contracts.Merger[dnd.SpellList], error) {
		return appendorder.NewTyped(appendSpellLists)
	}); err != nil {
		t.Fatalf("register merger: %v", err)
	}
	if err := pipeline.RegisterNormalizer[dnd.SpellList](normalizers, pipeline.ModuleSpec{
		Key:            pipeline.DefaultNormalizeModule,
		Stage:          pipeline.StageNormalize,
		ExecutionClass: contracts.ExecutionClassDeterministic,
		ArtifactKind:   dnd.SpellListKind,
	}, func() (contracts.Normalizer[dnd.SpellList], error) {
		return noop.NewTyped[dnd.SpellList](), nil
	}); err != nil {
		t.Fatalf("register normalizer: %v", err)
	}
	if err := outputs.RegisterWithSpec(pipeline.ModuleSpec{
		Key:            pipeline.DefaultOutputModule,
		Stage:          pipeline.StageOutput,
		ExecutionClass: contracts.ExecutionClassDeterministic,
	}, func() (contracts.OutputEncoder, error) {
		return dndSpellsOutput{}, nil
	}); err != nil {
		t.Fatalf("register output: %v", err)
	}

	return pipeline.ModuleCatalog{
		Inputs:           inputs,
		Chunkers:         chunkers,
		ArtifactCodecs:   codecs,
		ArtifactEvidence: evidence,
		Extractors:       extractors,
		Mergers:          mergers,
		Normalizers:      normalizers,
		ValidatorChains:  pipeline.NewValidatorChainRegistry(),
		Outputs:          outputs,
	}
}

type configExtractor struct{ key string }

func (extractor configExtractor) Key() string                     { return extractor.key }
func (configExtractor) ReferenceSlots() []contracts.ReferenceSlot { return nil }
func (configExtractor) Extract(context.Context, contracts.TypedExtractionRequest) (contracts.TypedExtractionResult[dnd.SpellList], error) {
	return contracts.TypedExtractionResult[dnd.SpellList]{}, nil
}

func appendSpellLists(values []dnd.SpellList) (dnd.SpellList, error) {
	combined := dnd.SpellList{SpellCasts: []dnd.SpellCast{}}
	for _, value := range values {
		combined.SpellCasts = append(combined.SpellCasts, value.SpellCasts...)
	}
	return combined, nil
}

func dndSpellsChunkerSpec() pipeline.ModuleSpec {
	return pipeline.ModuleSpec{
		Key:            "fake/chunk",
		Stage:          pipeline.StageChunk,
		ExecutionClass: contracts.ExecutionClassDeterministic,
		Requires:       []string{"source.transcript"},
		Provides:       []string{"chunks"},
	}
}

type dndSpellsChunker struct{}

func (dndSpellsChunker) Key() string {
	return "fake/chunk"
}

func (dndSpellsChunker) ReferenceSlots() []contracts.ReferenceSlot {
	return nil
}

func (dndSpellsChunker) Plan(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkPlanResult, error) {
	return contracts.ChunkPlanResult{
		Plan: source.ChunkPlan{SourceDigest: req.Source.Digest, Ranges: []source.ChunkRange{{StartUnitID: req.Source.Units[0].ID, EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID}}},
	}, nil
}

type dndSpellsOutput struct{}

func (dndSpellsOutput) Key() string {
	return pipeline.DefaultOutputModule
}

func (dndSpellsOutput) Encode(ctx context.Context, req contracts.OutputRequest) (contracts.OutputResult, error) {
	return contracts.OutputResult{
		Files: []contracts.OutputFile{
			{Name: "output.json", ContentType: "application/json", Bytes: []byte(`{"encoded":true}`)},
		},
	}, nil
}

func withoutCapability(capabilities []string, capability string) []string {
	filtered := make([]string, 0, len(capabilities))
	for _, candidate := range capabilities {
		if candidate != capability {
			filtered = append(filtered, candidate)
		}
	}
	return filtered
}

var (
	_ contracts.Chunker       = dndSpellsChunker{}
	_ contracts.OutputEncoder = dndSpellsOutput{}
)