narratio/internal/config/load_validate_test.go

package config

import (
	"io/fs"
	"os"
	"path/filepath"
	"reflect"
	"sort"
	"strings"
	"testing"
)

func TestRepresentativeLoadDefaultsAndValidation(t *testing.T) {
	pipelinePath, sessionPath := writeConfigFiles(t, `whisperx:
  transcribe_url: https://transcription.example.com/transcribe
`, `session_id: 2026-05-03
inputs:
  audio_dir: ./audio
`)

	cfg, err := Load(pipelinePath, sessionPath)
	if err != nil {
		t.Fatalf("Load() error = %v", err)
	}
	if cfg.Pipeline.Workspace.Root != DefaultWorkspaceRoot {
		t.Fatalf("workspace.root = %q, want %q", cfg.Pipeline.Workspace.Root, DefaultWorkspaceRoot)
	}
	if cfg.Pipeline.Storage.Backend != StorageBackendLocal || cfg.Pipeline.Storage.S3 != nil {
		t.Fatalf("storage = %#v, want local backend without S3 configuration", cfg.Pipeline.Storage)
	}
	if cfg.Pipeline.WhisperX.Timeout != DefaultWhisperXTimeout || cfg.Pipeline.WhisperX.RetryDelay != DefaultWhisperXRetryDelay {
		t.Fatalf("whisperx defaults = %#v, want timeout and retry-delay defaults", cfg.Pipeline.WhisperX)
	}
	if err := Validate(cfg); err != nil {
		t.Fatalf("Validate() error = %v", err)
	}
}

func TestMarshalEffectivePipelineRendersStablePublicConfiguration(t *testing.T) {
	dir := t.TempDir()
	path := filepath.Join(dir, "pipeline.yml")
	if err := os.WriteFile(path, []byte(`scriptorium:
  artifacts:
    zeta:
      enabled: false
      output_path: artifacts/zeta.md
    alpha:
      enabled: false
      output_path: artifacts/alpha.md
workspace:
  root: /srv/narratio
whisperx:
  transcribe_url: https://transcription.example.com/transcribe
`), 0o644); err != nil {
		t.Fatal(err)
	}

	first, err := LoadPipeline(path)
	if err != nil {
		t.Fatal(err)
	}
	second, err := LoadPipeline(path)
	if err != nil {
		t.Fatal(err)
	}
	firstYAML, err := MarshalEffectivePipeline(first)
	if err != nil {
		t.Fatal(err)
	}
	secondYAML, err := MarshalEffectivePipeline(second)
	if err != nil {
		t.Fatal(err)
	}
	if string(firstYAML) != string(secondYAML) || !strings.HasSuffix(string(firstYAML), "\n") {
		t.Fatalf("effective YAML is not stable: first=%q second=%q", firstYAML, secondYAML)
	}
	output := string(firstYAML)
	if strings.Contains(output, "artifact_families") || strings.Contains(output, "resolution") {
		t.Fatalf("effective YAML leaked runtime fields: %q", output)
	}
	if strings.Index(output, "alpha:") > strings.Index(output, "zeta:") {
		t.Fatalf("configured artifacts are not sorted: %q", output)
	}
}

func TestValidateMissingAudioSource(t *testing.T) {
	cfg := loadedValidConfig(t)
	cfg.Session.Inputs.AudioDir = ""
	cfg.Session.Inputs.AudioFiles = nil
	cfg.Session.Inputs.AudioS3 = nil

	err := Validate(cfg)
	if err == nil {
		t.Fatal("expected validation error, got nil")
	}
	if !strings.Contains(err.Error(), "audio_dir, at least one audio_files entry, or audio_s3") {
		t.Fatalf("error = %q, want audio source guidance", err.Error())
	}
	if !strings.Contains(err.Error(), "session config") {
		t.Fatalf("error = %q, want session config context", err.Error())
	}
}

func TestExamplesLoadAndValidate(t *testing.T) {
	examplesDir := filepath.Join("..", "..", "examples")
	if got, want := maintainedPipelineRoots(t, examplesDir), []string{
		"pipeline.extraction-subset.yml",
		"pipeline.full.annotated.yml",
		"pipeline.minimal.yml",
		"pipeline.production.yml",
		filepath.Join("production-testing", "pipeline.yml"),
	}; !reflect.DeepEqual(got, want) {
		t.Fatalf("maintained pipeline roots = %#v, want %#v", got, want)
	}
	tests := []struct {
		name         string
		pipelineFile string
		sessionFile  string
	}{
		{
			name:         "minimal pipeline with local audio session",
			pipelineFile: "pipeline.minimal.yml",
			sessionFile:  "session.local-audio.yml",
		},
		{
			name:         "production pipeline with s3 audio session",
			pipelineFile: "pipeline.production.yml",
			sessionFile:  "session.s3-audio.yml",
		},
		{
			name:         "full annotated pipeline with local audio session",
			pipelineFile: "pipeline.full.annotated.yml",
			sessionFile:  "session.local-audio.yml",
		},
		{
			name:         "extraction subset pipeline with local audio session",
			pipelineFile: "pipeline.extraction-subset.yml",
			sessionFile:  "session.local-audio.yml",
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			pipelinePath := filepath.Join(examplesDir, tt.pipelineFile)
			campaignPath := filepath.Join(examplesDir, "campaigns", "sample-campaign", "campaign.yml")
			sessionPath := filepath.Join(examplesDir, tt.sessionFile)

			cfg, err := Load(pipelinePath, campaignPath, sessionPath)
			if err != nil {
				t.Fatalf("load example config error = %v", err)
			}
			if err := Validate(cfg); err != nil {
				t.Fatalf("validate example config error = %v", err)
			}
		})
	}

	t.Run("split production and testing bundle", func(t *testing.T) {
		pipelinePath := filepath.Join(examplesDir, "production-testing", "pipeline.yml")
		campaignPath := filepath.Join(examplesDir, "campaigns", "sample-campaign", "campaign.yml")
		sessionPath := filepath.Join(examplesDir, "session.local-audio.yml")
		campaign, err := LoadCampaign(campaignPath)
		if err != nil {
			t.Fatalf("load split bundle campaign: %v", err)
		}
		for _, profile := range []struct {
			name  string
			model string
		}{
			{name: "production", model: "narratio-production-model-placeholder"},
			{name: "testing", model: "narratio-testing-model-placeholder"},
		} {
			t.Run(profile.name, func(t *testing.T) {
				selected := profile.name
				pipeline, err := LoadPipelineWithOptions(pipelinePath, PipelineLoadOptions{Profile: &selected})
				if err != nil {
					t.Fatalf("load split bundle pipeline: %v", err)
				}
				loaded, err := LoadPipelineCampaign(pipelinePath, pipeline, campaignPath, campaign)
				if err != nil {
					t.Fatalf("resolve split bundle campaign: %v", err)
				}
				cfg, err := LoadSessionWithPipelineCampaignOptions(loaded, sessionPath, SessionLoadOptions{})
				if err != nil {
					t.Fatalf("load split bundle session: %v", err)
				}
				if err := Validate(cfg); err != nil {
					t.Fatalf("validate split bundle: %v", err)
				}
				if cfg.Pipeline.Audita.Model != profile.model {
					t.Fatalf("audita model = %q, want %q", cfg.Pipeline.Audita.Model, profile.model)
				}
				if cfg.Pipeline.Secrets != nil || cfg.Pipeline.Audita.LLMAPIKeyEnv != "" || cfg.Pipeline.Storage.Backend != StorageBackendLocal || cfg.Pipeline.Storage.S3 != nil {
					t.Fatalf("split bundle must remain offline and secret-free: secrets=%#v audita=%#v storage=%#v", cfg.Pipeline.Secrets, cfg.Pipeline.Audita, cfg.Pipeline.Storage)
				}
				if selectedProfile, ok := SelectedPipelineProfile(cfg.Pipeline); !ok || selectedProfile.Name != profile.name {
					t.Fatalf("selected profile = %#v, want %q", selectedProfile, profile.name)
				}
				for _, key := range []string{
					"character_meta_arannis",
					"character_meta_brenna",
					"character_items_arannis",
					"character_items_brenna",
				} {
					if _, exists := cfg.Pipeline.Scriptorium.Artifacts[key]; !exists {
						t.Fatalf("expanded artifact %q is absent", key)
					}
				}
				if got := cfg.Pipeline.Scriptorium.Artifacts["character_items_arannis"].Inputs["character_meta"].Source; got != "narratio.artifact.character_meta_arannis" {
					t.Fatalf("same-member input source = %q", got)
				}
				if cfg.Party.Canonical == nil || len(cfg.Party.Canonical.Characters) != 2 {
					t.Fatalf("canonical party = %#v", cfg.Party)
				}
				characters := cfg.Party.Canonical.Characters
				if characters[0].Player.Name != characters[1].Player.Name || len(characters[0].Character.Aliases) != 2 || len(characters[1].Character.Classes) != 2 {
					t.Fatalf("canonical party does not preserve repeated player, aliases, and multiclass data: %#v", characters)
				}
				if len(cfg.Pipeline.Publish.Outputs) != 3 {
					t.Fatalf("publish outputs = %#v, want transcript plus two family outputs", cfg.Pipeline.Publish.Outputs)
				}
				if profile.name == "testing" {
					artifact, exists := cfg.Pipeline.Scriptorium.Artifacts["testing_notes"]
					if !exists || artifact.Enabled {
						t.Fatalf("testing-only disabled artifact = %#v", artifact)
					}
				}
			})
		}
	})
}

func maintainedPipelineRoots(t *testing.T, examplesDir string) []string {
	t.Helper()
	var roots []string
	err := filepath.WalkDir(examplesDir, func(path string, entry fs.DirEntry, walkErr error) error {
		if walkErr != nil {
			return walkErr
		}
		if entry.IsDir() {
			return nil
		}
		name := entry.Name()
		if name != "pipeline.yml" && !(strings.HasPrefix(name, "pipeline.") && (strings.HasSuffix(name, ".yml") || strings.HasSuffix(name, ".yaml"))) {
			return nil
		}
		relative, err := filepath.Rel(examplesDir, path)
		if err != nil {
			return err
		}
		roots = append(roots, relative)
		return nil
	})
	if err != nil {
		t.Fatalf("discover maintained pipeline roots: %v", err)
	}
	sort.Strings(roots)
	return roots
}

func TestMaintainedExtractionExamplesPreservePublishedContracts(t *testing.T) {
	examplesDir := filepath.Join("..", "..", "examples")
	full, err := LoadPipeline(filepath.Join(examplesDir, "pipeline.full.annotated.yml"))
	if err != nil {
		t.Fatalf("load full example error = %v", err)
	}
	want := map[string]NotariusOutputConfig{
		"item_registry":        {LaneID: "item-registry", MediaType: "application/json", SchemaID: "notarius.dnd.item_registry", SchemaVersion: "v1", ModuleKey: "dnd/item-registry"},
		"npc_registry":         {LaneID: "npc-registry", MediaType: "application/json", SchemaID: "notarius.dnd.npc_registry", SchemaVersion: "v1", ModuleKey: "dnd/npc-registry"},
		"location_registry":    {LaneID: "location-registry", MediaType: "application/json", SchemaID: "notarius.dnd.location_registry", SchemaVersion: "v1", ModuleKey: "dnd/location-registry"},
		"scene_descriptions":   {LaneID: "scene-descriptions", MediaType: "application/json", SchemaID: "notarius.dnd.scene_descriptions", SchemaVersion: "v1", ModuleKey: "dnd/scene-descriptions"},
		"item_occurrences":     {LaneID: "item-occurrences", MediaType: "application/json", SchemaID: "notarius.dnd.item_occurrences", SchemaVersion: "v1", ModuleKey: "dnd/item-occurrences"},
		"spells":               {LaneID: "spells", MediaType: "application/json", SchemaID: "notarius.dnd.spells", SchemaVersion: "v1", ModuleKey: "dnd/spells"},
		"combat_turns":         {LaneID: "combat-turns", MediaType: "application/json", SchemaID: "notarius.dnd.combat_turns", SchemaVersion: "v1", ModuleKey: "dnd/combat-turns"},
		"npc_occurrences":      {LaneID: "npc-occurrences", MediaType: "application/json", SchemaID: "notarius.dnd.npc_occurrences", SchemaVersion: "v1", ModuleKey: "dnd/npc-occurrences"},
		"location_occurrences": {LaneID: "location-occurrences", MediaType: "application/json", SchemaID: "notarius.dnd.location_occurrences", SchemaVersion: "v1", ModuleKey: "dnd/location-occurrences"},
		"enemy_events":         {LaneID: "enemy-events", MediaType: "application/json", SchemaID: "notarius.dnd.enemy_events", SchemaVersion: "v1", ModuleKey: "dnd/enemy-events"},
	}
	if full.Notarius == nil || !reflect.DeepEqual(full.Notarius.Outputs, want) {
		t.Fatalf("full example outputs = %#v, want %#v", full.Notarius, want)
	}

	subset, err := LoadPipeline(filepath.Join(examplesDir, "pipeline.extraction-subset.yml"))
	if err != nil {
		t.Fatalf("load subset example error = %v", err)
	}
	brief := subset.Scriptorium.Artifacts["session_brief"]
	wantSources := map[string]string{
		"npcs":      "narratio.extraction.npc_registry",
		"locations": "narratio.extraction.location_registry",
		"scenes":    "narratio.extraction.scene_descriptions",
	}
	gotSources := make(map[string]string, len(brief.Inputs))
	for name, input := range brief.Inputs {
		gotSources[name] = input.Source
	}
	if !reflect.DeepEqual(gotSources, wantSources) {
		t.Fatalf("subset example sources = %#v, want %#v", gotSources, wantSources)
	}
}

func writeConfigFiles(t *testing.T, pipelineYAML, sessionYAML string) (string, string) {
	t.Helper()
	if !strings.Contains(pipelineYAML, "\naudita:") && !strings.HasPrefix(pipelineYAML, "audita:") {
		if !strings.HasSuffix(pipelineYAML, "\n") {
			pipelineYAML += "\n"
		}
		pipelineYAML += "audita:\n  binary: audita\n"
	}
	if !strings.Contains(sessionYAML, "\ncampaign:") && !strings.HasPrefix(sessionYAML, "campaign:") {
		if !strings.HasSuffix(sessionYAML, "\n") {
			sessionYAML += "\n"
		}
		sessionYAML += "campaign: sample-campaign\n"
	}

	dir := t.TempDir()
	pipelinePath := filepath.Join(dir, "pipeline.yml")
	campaignPath := filepath.Join(dir, "campaign.yml")
	sessionPath := filepath.Join(dir, "session.yml")

	if err := os.WriteFile(pipelinePath, []byte(pipelineYAML), 0o644); err != nil {
		t.Fatalf("write pipeline.yml: %v", err)
	}
	campaignYAML := `campaign_id: ` + campaignNameFromSessionYAML(sessionYAML) + `
inputs:
  speakers_file: ./speakers.yml
  autocorrect_file: ./autocorrect.yml
  glossary_file: ./glossary.yml
  party_file: ./party.yml
`
	if err := os.WriteFile(campaignPath, []byte(campaignYAML), 0o644); err != nil {
		t.Fatalf("write campaign.yml: %v", err)
	}
	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
		t.Fatalf("write session.yml: %v", err)
	}
	if err := os.WriteFile(filepath.Join(dir, "party.yml"), []byte(canonicalPartyFixture), 0o644); err != nil {
		t.Fatalf("write party.yml: %v", err)
	}

	return pipelinePath, sessionPath
}

func campaignNameFromSessionYAML(sessionYAML string) string {
	for _, line := range strings.Split(sessionYAML, "\n") {
		trimmed := strings.TrimSpace(line)
		if strings.HasPrefix(trimmed, "campaign:") {
			return strings.Trim(strings.TrimSpace(strings.TrimPrefix(trimmed, "campaign:")), `"'`)
		}
	}
	return "sample-campaign"
}