Register D&D scene description pipeline

internal/cli/dnd_scene_descriptions_contract_test.go

@@ -0,0 +1,111 @@
+package cli
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"reflect"
+	"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"
+	scenecodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/scenedescriptions"
+	sceneextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/scenedescriptions"
+	scenenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/scenedescriptions"
+)
+
+func TestProductionSceneDescriptionWorkflow(t *testing.T) {
+	components := productionTestComponents(t)
+	cfg := config.Default()
+	cfg.Pipelines["scene-descriptions"] = pipeline.PipelineProfile{
+		ID:     "scene-descriptions",
+		Input:  pipeline.Binding("seriatim"),
+		Chunk:  pipeline.ModuleBinding{Module: "generic", Options: map[string]any{"max_units": 1}},
+		Output: pipeline.Binding("json"),
+		Artifacts: map[string]pipeline.ArtifactLaneProfile{
+			"scene-descriptions": {
+				Extract:   pipeline.Binding(sceneextract.Key),
+				Normalize: pipeline.Binding(scenenormalize.Key),
+			},
+		},
+	}
+	effective, err := cfg.Resolve(config.ResolveInput{PipelineID: "scene-descriptions", Catalog: catalogFromRegistries(components.registries)})
+	if err != nil {
+		t.Fatalf("Resolve() error = %v", err)
+	}
+	lane := effective.ResolvedPipeline.Steps[0].ArtifactLanes[0]
+	if lane.ArtifactKind != dnd.SceneDescriptionListKind || lane.Extract.Module != sceneextract.Key || lane.Merge.Module != pipeline.DefaultMergeModule || lane.Normalize.Module != scenenormalize.Key {
+		t.Fatalf("resolved lane = %#v, want production scene-description composition", lane)
+	}
+	if len(lane.ExtractReferences.Bindings) != 0 || len(lane.NormalizeReferences.Bindings) != 0 {
+		t.Fatalf("resolved references = %#v / %#v, want no generated or required references", lane.ExtractReferences, lane.NormalizeReferences)
+	}
+
+	prepared, err := pipeline.Prepare(effective.ResolvedPipeline, components.registries, pipeline.ModuleDependencies{LLM: sceneDescriptionLLM{}})
+	if err != nil {
+		t.Fatalf("Prepare() error = %v", err)
+	}
+	output, err := pipeline.New().Run(context.Background(), pipeline.RunInput{
+		Prepared:       prepared,
+		RawInput:       readRepositoryFile(t, "examples", "seriatim-minimal-transcript.json"),
+		ChunkCacheMode: pipeline.ChunkCacheBypass,
+	})
+	if err != nil {
+		t.Fatalf("Run() error = %v", err)
+	}
+	if output.Manifest.ValidationStatus != "approved" || len(output.Rejected) != 0 || len(output.NormalizeOutputs) != 1 {
+		t.Fatalf("run output = %#v, want one approved normalized artifact", output)
+	}
+	normalizedOutput := output.NormalizeOutputs[0]
+	if normalizedOutput.NormalizerKey != scenenormalize.Key || normalizedOutput.Artifact.Kind != dnd.SceneDescriptionListKind || normalizedOutput.Artifact.Schema.ID != scenecodec.SchemaID || normalizedOutput.Artifact.Schema.Name != scenecodec.SchemaName || normalizedOutput.Artifact.Schema.Version != scenecodec.SchemaVersion {
+		t.Fatalf("normalized output = %#v, want registered durable scene-description schema", normalizedOutput)
+	}
+
+	var value dnd.SceneDescriptionList
+	if err := json.Unmarshal(normalizedOutput.Artifact.Content, &value); err != nil {
+		t.Fatalf("decode normalized artifact: %v", err)
+	}
+	want := dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{
+		{ID: "chunk-000001", SourceRef: source.SourceRef{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 1}, Kind: dnd.SceneKindNarrative, Title: "Aria casts Cure Wounds", Summary: "Aria casts Cure Wounds."},
+		{ID: "chunk-000002", SourceRef: source.SourceRef{SourceID: "session-alpha", StartUnitID: 2, EndUnitID: 2}, Kind: dnd.SceneKindCombat, Title: "Bandit mage casts Shield", Summary: "The bandit mage casts Shield."},
+	}}
+	if !reflect.DeepEqual(value, want) {
+		t.Fatalf("normalized scene descriptions = %#v, want %#v", value, want)
+	}
+	durable := decodeAssembledOutput[dnd.SceneDescriptionList](t, output.OutputFiles, "lanes/scene-descriptions.json")
+	if !reflect.DeepEqual(durable, want) {
+		t.Fatalf("durable output payload = %#v, want %#v", durable, want)
+	}
+	if len(output.Warnings) != 0 {
+		t.Fatalf("warnings = %#v, want grounded descriptions without warnings", output.Warnings)
+	}
+}
+
+type sceneDescriptionLLM struct{}
+
+func (sceneDescriptionLLM) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
+	if err := ctx.Err(); err != nil {
+		return contracts.StructuredCompletionResponse{}, err
+	}
+	if req.PromptID != sceneextract.PromptID {
+		return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected prompt %q", req.PromptID)
+	}
+	transcript := string(req.Inputs["transcript"].Content)
+	var content string
+	switch {
+	case strings.Contains(transcript, "Cure Wounds"):
+		content = `{"kind":"narrative","title":"  Aria casts Cure Wounds  ","summary":"  Aria casts Cure Wounds.  "}`
+	case strings.Contains(transcript, "Shield"):
+		content = `{"kind":"combat","title":"Bandit mage casts Shield","summary":"The bandit mage casts Shield."}`
+	default:
+		return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected transcript material %q", transcript)
+	}
+	if err := json.Unmarshal([]byte(content), out); err != nil {
+		return contracts.StructuredCompletionResponse{}, fmt.Errorf("populate structured response: %w", err)
+	}
+	return contracts.StructuredCompletionResponse{Content: []byte(content), Provider: "test", Model: "deterministic", ProfileID: req.ProfileID}, nil
+}