audita/internal/cli/run_test.go

package cli

import (
	"bytes"
	"encoding/json"
	"io"
	"os"
	"path/filepath"
	"reflect"
	"strings"
	"testing"
)

func TestRunRootHelp(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"--help"}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d", exitCode)
	}
	if !strings.Contains(stdout.String(), "audita <command> [options]") {
		t.Fatalf("expected root usage in stdout, got %q", stdout.String())
	}
	if !strings.Contains(stdout.String(), "process") {
		t.Fatalf("expected process command in root help, got %q", stdout.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr, got %q", stderr.String())
	}
}

func TestRunProcessHelpListsExpectedFlags(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"process", "--help"}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d", exitCode)
	}

	for _, expectedFlag := range []string{
		"--glossary",
		"--output",
		"--report-json",
		"--modules",
		"--llm-api-key",
		"--validation-llm-api-key",
		"--model",
		"--validation-model",
		"--base-url",
		"--validation-base-url",
		"--llm-timeout-seconds",
		"--validation-llm-timeout-seconds",
		"--validation-max-prompt-tokens",
		"--target-sections",
		"--max-retries",
		"--validation-max-retries",
		"--validation-llm-concurrency",
		"--max-section-tokens",
		"--min-section-tokens",
		"--glossary-confidence-threshold",
		"--grammar-confidence-threshold",
		"--homophones-confidence-threshold",
		"--spoken-word-confidence-threshold",
		"--normalize-max-segment-gap",
		"--normalize-ellipsis-gap",
		"--normalize-max-segment-duration",
		"--normalize-max-segment-tokens",
		"--work-dir",
		"--work-dir-retention",
	} {
		if !strings.Contains(stdout.String(), expectedFlag) {
			t.Fatalf("expected process help to include %q, got %q", expectedFlag, stdout.String())
		}
	}

	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr, got %q", stderr.String())
	}
}

func TestRunUnknownCommand(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"unknown"}, &stdout, &stderr)
	if exitCode != 2 {
		t.Fatalf("expected exit code 2, got %d", exitCode)
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout, got %q", stdout.String())
	}
	if !strings.Contains(stderr.String(), "unknown command") {
		t.Fatalf("expected unknown command error in stderr, got %q", stderr.String())
	}
}

func TestRunProcessMissingTranscriptPath(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"process", "--glossary", fixturePath("tiny_glossary.yaml")}, &stdout, &stderr)
	if exitCode == 0 {
		t.Fatalf("expected nonzero exit code")
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout, got %q", stdout.String())
	}
	if !strings.Contains(stderr.String(), "expected exactly 1 transcript JSON path argument") {
		t.Fatalf("expected missing transcript error, got %q", stderr.String())
	}
}

func TestRunProcessMissingGlossary(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"process", fixturePath("tiny_transcript.json")}, &stdout, &stderr)
	if exitCode == 0 {
		t.Fatalf("expected nonzero exit code")
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout, got %q", stdout.String())
	}
	if !strings.Contains(stderr.String(), "--glossary is required") {
		t.Fatalf("expected missing glossary error, got %q", stderr.String())
	}
}

func TestRunProcessUnreadableTranscript(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	missingTranscript := filepath.Join(t.TempDir(), "missing.json")
	exitCode := Run([]string{"process", missingTranscript, "--glossary", fixturePath("tiny_glossary.yaml")}, &stdout, &stderr)
	if exitCode == 0 {
		t.Fatalf("expected nonzero exit code")
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout, got %q", stdout.String())
	}
	if !strings.Contains(stderr.String(), "failed to read transcript file") {
		t.Fatalf("expected unreadable transcript error, got %q", stderr.String())
	}
}

func TestRunProcessMalformedTranscriptJSON(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"process", fixturePath("malformed_transcript.json"), "--glossary", fixturePath("tiny_glossary.yaml")}, &stdout, &stderr)
	if exitCode == 0 {
		t.Fatalf("expected nonzero exit code")
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout, got %q", stdout.String())
	}
	if !strings.Contains(stderr.String(), "is not valid JSON") {
		t.Fatalf("expected malformed transcript error, got %q", stderr.String())
	}
}

func TestRunProcessOutputToFile(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	transcriptPath := fixturePath("tiny_transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")
	outputPath := filepath.Join(t.TempDir(), "corrected.json")

	exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath, "--output", outputPath}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout when --output is used, got %q", stdout.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
	}

	inputBytes := readFile(t, transcriptPath)
	outputBytes := readFile(t, outputPath)
	assertJSONSemanticallyEqual(t, inputBytes, outputBytes)
}

func TestRunProcessOutputToStdout(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	transcriptPath := fixturePath("tiny_transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")

	exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
	}

	inputBytes := readFile(t, transcriptPath)
	assertJSONSemanticallyEqual(t, inputBytes, stdout.Bytes())
}

func TestRunProcessReportJSONSuccess(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	transcriptPath := fixturePath("tiny_transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")
	outputPath := filepath.Join(t.TempDir(), "corrected.json")
	reportPath := filepath.Join(t.TempDir(), "report.json")

	exitCode := Run([]string{
		"process",
		transcriptPath,
		"--glossary",
		glossaryPath,
		"--output",
		outputPath,
		"--report-json",
		reportPath,
	}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout when --output is used, got %q", stdout.String())
	}

	report := readProcessReport(t, reportPath)
	if report.Status != "success" {
		t.Fatalf("expected success report status, got %q", report.Status)
	}
	if report.Operation != "process" {
		t.Fatalf("expected operation process, got %q", report.Operation)
	}
	if report.TranscriptPath != transcriptPath {
		t.Fatalf("unexpected transcript path in report: %q", report.TranscriptPath)
	}
	if report.GlossaryPath != glossaryPath {
		t.Fatalf("unexpected glossary path in report: %q", report.GlossaryPath)
	}
	if report.OutputPath != outputPath {
		t.Fatalf("unexpected output path in report: %q", report.OutputPath)
	}
	if len(report.Modules) == 0 {
		t.Fatalf("expected configured module sequence in report")
	}
	if report.StartedAt == "" || report.CompletedAt == "" {
		t.Fatalf("expected started_at and completed_at timestamps in report")
	}
	if report.ErrorMessage != "" {
		t.Fatalf("did not expect error message in success report, got %q", report.ErrorMessage)
	}
}

func TestRunProcessReportJSONNoStdoutPollution(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	transcriptPath := fixturePath("tiny_transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")
	reportPath := filepath.Join(t.TempDir(), "report.json")

	exitCode := Run([]string{
		"process",
		transcriptPath,
		"--glossary",
		glossaryPath,
		"--report-json",
		reportPath,
	}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	assertJSONSemanticallyEqual(t, readFile(t, transcriptPath), stdout.Bytes())

	reportBytes := readFile(t, reportPath)
	if bytes.Contains(stdout.Bytes(), reportBytes) {
		t.Fatalf("stdout was polluted with report JSON")
	}
}

func TestRunProcessReportJSONRedactsSecrets(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	secretPrimary := "top-secret-primary-key"
	secretValidation := "top-secret-validation-key"
	t.Setenv("AUDITA_LLM_API_KEY", secretPrimary)
	t.Setenv("AUDITA_VALIDATION_LLM_API_KEY", secretValidation)

	reportPath := filepath.Join(t.TempDir(), "report.json")
	exitCode := Run([]string{
		"process",
		fixturePath("tiny_transcript.json"),
		"--glossary",
		fixturePath("tiny_glossary.yaml"),
		"--report-json",
		reportPath,
	}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}

	reportBytes := readFile(t, reportPath)
	if strings.Contains(string(reportBytes), secretPrimary) || strings.Contains(string(reportBytes), secretValidation) {
		t.Fatalf("report JSON leaked API key material: %q", string(reportBytes))
	}
}

func TestRunProcessReportJSONBestEffortOnFailure(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	reportPath := filepath.Join(t.TempDir(), "report.json")
	exitCode := Run([]string{
		"process",
		fixturePath("malformed_transcript.json"),
		"--glossary",
		fixturePath("tiny_glossary.yaml"),
		"--report-json",
		reportPath,
	}, &stdout, &stderr)
	if exitCode == 0 {
		t.Fatalf("expected nonzero exit code for malformed transcript")
	}

	report := readProcessReport(t, reportPath)
	if report.Status != "failed" {
		t.Fatalf("expected failed report status, got %q", report.Status)
	}
	if report.ErrorMessage == "" {
		t.Fatalf("expected error message in failed report")
	}
	if !strings.Contains(report.ErrorMessage, "not valid JSON") {
		t.Fatalf("expected malformed JSON failure in report error, got %q", report.ErrorMessage)
	}
}

func TestRunProcessInvalidTranscriptSchema(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"process", fixturePath("transcript_empty_speaker.json"), "--glossary", fixturePath("tiny_glossary.yaml")}, &stdout, &stderr)
	if exitCode == 0 {
		t.Fatalf("expected nonzero exit code for invalid transcript schema")
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout, got %q", stdout.String())
	}
	if !strings.Contains(stderr.String(), "invalid transcript:") {
		t.Fatalf("expected invalid transcript error, got %q", stderr.String())
	}
	if !strings.Contains(stderr.String(), "speaker") {
		t.Fatalf("expected speaker validation error, got %q", stderr.String())
	}
}

func TestRunProcessValidBareArrayTranscript(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"process", "../core/schema/testdata/transcript_bare_array.json", "--glossary", fixturePath("tiny_glossary.yaml")}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
	}

	// Should produce valid JSON output
	if !json.Valid(stdout.Bytes()) {
		t.Fatalf("expected valid JSON output, got %q", stdout.String())
	}

	// Parse the output to verify it's a proper transcript
	var output any
	if err := json.Unmarshal(stdout.Bytes(), &output); err != nil {
		t.Fatalf("failed to unmarshal output JSON: %v", err)
	}

	// Should be an array at the top level (canonical object form would be {"segments": [...]})
	outputArray, ok := output.([]any)
	if !ok {
		t.Fatalf("expected output to be JSON array, got %T", output)
	}
	if len(outputArray) != 2 {
		t.Fatalf("expected 2 segments in output, got %d", len(outputArray))
	}
}

func TestRunProcessInvalidGlossarySchema(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"process", fixturePath("tiny_transcript.json"), "--glossary", "../core/schema/testdata/glossary_missing_fields.yaml"}, &stdout, &stderr)
	if exitCode == 0 {
		t.Fatalf("expected nonzero exit code for invalid glossary schema")
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout, got %q", stdout.String())
	}
	if !strings.Contains(stderr.String(), "invalid glossary:") {
		t.Fatalf("expected invalid glossary error, got %q", stderr.String())
	}
}

func fixturePath(name string) string {
	return filepath.Join("testdata", name)
}

func readFile(t *testing.T, path string) []byte {
	t.Helper()
	data, err := os.ReadFile(path)
	if err != nil {
		t.Fatalf("failed to read file %q: %v", path, err)
	}
	return data
}

func assertJSONSemanticallyEqual(t *testing.T, expected []byte, actual []byte) {
	t.Helper()
	if !json.Valid(actual) {
		t.Fatalf("actual output is not valid JSON: %q", string(actual))
	}

	var expectedValue any
	var actualValue any
	if err := json.Unmarshal(expected, &expectedValue); err != nil {
		t.Fatalf("failed to unmarshal expected JSON: %v", err)
	}
	if err := json.Unmarshal(actual, &actualValue); err != nil {
		t.Fatalf("failed to unmarshal actual JSON: %v", err)
	}
	if !reflect.DeepEqual(expectedValue, actualValue) {
		t.Fatalf("JSON content mismatch: expected %q got %q", string(expected), string(actual))
	}
}

type minimalProcessReport struct {
	Status         string   `json:"status"`
	Operation      string   `json:"operation"`
	TranscriptPath string   `json:"transcript_path"`
	GlossaryPath   string   `json:"glossary_path"`
	OutputPath     string   `json:"output_path"`
	Modules        []string `json:"modules"`
	StartedAt      string   `json:"started_at"`
	CompletedAt    string   `json:"completed_at"`
	ErrorMessage   string   `json:"error_message"`
}

func readProcessReport(t *testing.T, path string) minimalProcessReport {
	t.Helper()
	raw := readFile(t, path)
	var report minimalProcessReport
	if err := json.Unmarshal(raw, &report); err != nil {
		t.Fatalf("failed to unmarshal process report JSON: %v (raw: %q)", err, string(raw))
	}
func TestRunProcessStdoutBehaviorWithoutOutput(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	exitCode := Run([]string{"process", "../core/schema/testdata/transcript_bare_array.json", "--glossary", fixturePath("tiny_glossary.yaml")}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
	}

	// Should have transcript JSON in stdout
	if stdout.Len() == 0 {
		t.Fatalf("expected transcript JSON in stdout, got empty stdout")
	}
	if !json.Valid(stdout.Bytes()) {
		t.Fatalf("expected valid JSON in stdout, got %q", stdout.String())
	}
}

func TestRunProcessEmptyStdoutWithOutput(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	transcriptPath := "../core/schema/testdata/transcript_bare_array.json"
	glossaryPath := fixturePath("tiny_glossary.yaml")
	outputPath := filepath.Join(t.TempDir(), "corrected.json")

	exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath, "--output", outputPath}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout when --output is used, got %q", stdout.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
	}

	// Verify output file was created and contains valid JSON
	outputBytes := readFile(t, outputPath)
	if !json.Valid(outputBytes) {
		t.Fatalf("expected valid JSON in output file, got %q", string(outputBytes))
	}
}

func TestRunProcessNormalizationMergeInOutput(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	// Create a test transcript with segments that should be merged
	transcriptJSON := `[
		{"id": 1, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"},
		{"id": 2, "speaker": "Alice", "start": 1.5, "end": 2.5, "text": "world"}
	]`

	transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")
	outputPath := filepath.Join(t.TempDir(), "corrected.json")

	if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
		t.Fatalf("failed to create test transcript: %v", err)
	}

	exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath, "--output", outputPath}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout when --output is used, got %q", stdout.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
	}

	// Read and parse the output
	outputBytes := readFile(t, outputPath)
	var outputTranscript schema.Transcript
	if err := schema.ParseTranscriptJSON(outputBytes); err != nil {
		t.Fatalf("failed to parse output transcript: %v (output: %s)", err, string(outputBytes))
	}

	// Should have merged the two segments into one
	if len(outputTranscript.Segments) != 1 {
		t.Fatalf("expected 1 merged segment, got %d segments", len(outputTranscript.Segments))
	}

	// Should have sequential ID starting at 1
	if outputTranscript.Segments[0].ID != 1 {
		t.Fatalf("expected segment ID 1, got %d", outputTranscript.Segments[0].ID)
	}

	// Should contain merged text
	if !strings.Contains(outputTranscript.Segments[0].Text, "Hello") || !strings.Contains(outputTranscript.Segments[0].Text, "world") {
		t.Fatalf("expected merged text to contain both parts, got %q", outputTranscript.Segments[0].Text)
	}
}

func TestRunProcessNormalizedOutputToStdout(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	transcriptJSON := `[
		{"id": 1, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"},
		{"id": 2, "speaker": "Alice", "start": 1.5, "end": 2.5, "text": "world"}
	]`

	transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")

	if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
		t.Fatalf("failed to create test transcript: %v", err)
	}

	exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
	}

	// Should have normalized output in stdout
	if stdout.Len() == 0 {
		t.Fatalf("expected normalized transcript in stdout, got empty stdout")
	}

	// Should be valid JSON
	if !json.Valid(stdout.Bytes()) {
		t.Fatalf("expected valid JSON in stdout, got %q", stdout.String())
	}

	// Parse and verify it's normalized (merged)
	var outputTranscript schema.Transcript
	if err := schema.ParseTranscriptJSON(stdout.Bytes()); err != nil {
		t.Fatalf("failed to parse stdout transcript: %v", err)
	}

	if len(outputTranscript.Segments) != 1 {
		t.Fatalf("expected 1 merged segment in stdout, got %d", len(outputTranscript.Segments))
	}
}

func TestRunProcessSequentialIDsInOutput(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	transcriptJSON := `[
		{"id": 5, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"},
		{"id": 10, "speaker": "Bob", "start": 2.0, "end": 3.0, "text": "Hi"}
	]`

	transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")

	if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
		t.Fatalf("failed to create test transcript: %v", err)
	}

	exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}

	// Parse output and verify sequential IDs
	var outputTranscript schema.Transcript
	if err := schema.ParseTranscriptJSON(stdout.Bytes()); err != nil {
		t.Fatalf("failed to parse output transcript: %v", err)
	}

	// Should have sequential IDs starting at 1
	for i, segment := range outputTranscript.Segments {
		expectedID := i + 1
		if segment.ID != expectedID {
			t.Fatalf("expected segment %d to have ID %d, got %d", i, expectedID, segment.ID)
		}
	}
}

func TestRunProcessNoStdoutWithOutput(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	transcriptJSON := `[
		{"id": 1, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"}
	]`

	transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")
	outputPath := filepath.Join(t.TempDir(), "corrected.json")

	if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
		t.Fatalf("failed to create test transcript: %v", err)
	}

	exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath, "--output", outputPath}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout when --output is used, got %q", stdout.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
	}

	// Verify output file exists and is valid
	if _, err := os.Stat(outputPath); err != nil {
		t.Fatalf("expected output file to be created: %v", err)
	}
}

func TestRunProcessReportIncludesNormalizationSummary(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	// Create a test transcript with segments that will be merged
	transcriptJSON := `[
		{"id": 1, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"},
		{"id": 2, "speaker": "Alice", "start": 1.5, "end": 2.5, "text": "world"}
	]`

	transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")
	reportPath := filepath.Join(t.TempDir(), "report.json")

	if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
		t.Fatalf("failed to create test transcript: %v", err)
	}

	exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath, "--report-json", reportPath}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout when --output is not used but --report-json is provided, got %q", stdout.String())
	}
	if stderr.Len() != 0 {
		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
	}

	// Read and parse the report
	reportBytes := readFile(t, reportPath)
	var report reporting.ProcessReport
	if err := json.Unmarshal(reportBytes, &report); err != nil {
		t.Fatalf("failed to parse report JSON: %v (raw: %s)", err, string(reportBytes))
	}

	// Verify report includes normalization summary
	if report.Status != "success" {
		t.Fatalf("expected success status, got %q", report.Status)
	}
	if report.InputSegmentCount == nil || *report.InputSegmentCount != 2 {
		t.Fatalf("expected input segment count 2, got %v", report.InputSegmentCount)
	}
	if report.NormalizedSegmentCount == nil || *report.NormalizedSegmentCount != 1 {
		t.Fatalf("expected normalized segment count 1, got %v", report.NormalizedSegmentCount)
	}
	if report.NormalizationMerges == nil || *report.NormalizationMerges != 1 {
		t.Fatalf("expected 1 merge, got %v", report.NormalizationMerges)
	}
	if report.NormalizationIDReassignments == nil || *report.NormalizationIDReassignments != 0 {
		t.Fatalf("expected 0 ID reassignments (already sequential), got %v", report.NormalizationIDReassignments)
	}
}

func TestRunProcessReportFailedTranscriptSchema(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	reportPath := filepath.Join(t.TempDir(), "report.json")
	exitCode := Run([]string{
		"process",
		fixturePath("transcript_empty_speaker.json"),
		"--glossary",
		fixturePath("tiny_glossary.yaml"),
		"--report-json",
		reportPath,
	}, &stdout, &stderr)
	if exitCode == 0 {
		t.Fatalf("expected nonzero exit code for invalid transcript")
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout on failure, got %q", stdout.String())
	}

	// Read and parse the report
	reportBytes := readFile(t, reportPath)
	var report reporting.ProcessReport
	if err := json.Unmarshal(reportBytes, &report); err != nil {
		t.Fatalf("failed to parse report JSON: %v (raw: %s)", err, string(reportBytes))
	}

	// Verify failed report structure
	if report.Status != "failed" {
		t.Fatalf("expected failed status, got %q", report.Status)
	}
	if report.ErrorPhase != "transcript_schema" {
		t.Fatalf("expected error phase 'transcript_schema', got %q", report.ErrorPhase)
	}
	if report.ErrorMessage == "" {
		t.Fatalf("expected error message in failed report")
	}
	if !strings.Contains(report.ErrorMessage, "speaker") {
		t.Fatalf("expected speaker validation error, got %q", report.ErrorMessage)
	}
}

func TestRunProcessReportFailedGlossarySchema(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	reportPath := filepath.Join(t.TempDir(), "report.json")
	exitCode := Run([]string{
		"process",
		fixturePath("tiny_transcript.json"),
		"--glossary",
		"../core/schema/testdata/glossary_missing_fields.yaml",
		"--report-json",
		reportPath,
	}, &stdout, &stderr)
	if exitCode == 0 {
		t.Fatalf("expected nonzero exit code for invalid glossary")
	}
	if stdout.Len() != 0 {
		t.Fatalf("expected empty stdout on failure, got %q", stdout.String())
	}

	// Read and parse the report
	reportBytes := readFile(t, reportPath)
	var report reporting.ProcessReport
	if err := json.Unmarshal(reportBytes, &report); err != nil {
		t.Fatalf("failed to parse report JSON: %v (raw: %s)", err, string(reportBytes))
	}

	// Verify failed report structure
	if report.Status != "failed" {
		t.Fatalf("expected failed status, got %q", report.Status)
	}
	if report.ErrorPhase != "glossary_schema" {
		t.Fatalf("expected error phase 'glossary_schema', got %q", report.ErrorPhase)
	}
	if report.ErrorMessage == "" {
		t.Fatalf("expected error message in failed report")
	}
}

func TestRunProcessReportJSONNotInStdout(t *testing.T) {
	var stdout bytes.Buffer
	var stderr bytes.Buffer

	transcriptJSON := `[
		{"id": 1, "speaker": "Alice", "start": 0.0, "end": 1.0, "text": "Hello"}
	]`

	transcriptPath := filepath.Join(t.TempDir(), "transcript.json")
	glossaryPath := fixturePath("tiny_glossary.yaml")
	reportPath := filepath.Join(t.TempDir(), "report.json")

	if err := os.WriteFile(transcriptPath, []byte(transcriptJSON), 0644); err != nil {
		t.Fatalf("failed to create test transcript: %v", err)
	}

	exitCode := Run([]string{"process", transcriptPath, "--glossary", glossaryPath, "--report-json", reportPath}, &stdout, &stderr)
	if exitCode != 0 {
		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
	}

	// Read the report to get its content
	reportBytes := readFile(t, reportPath)

	// Verify report JSON is not in stdout
	if bytes.Contains(stdout.Bytes(), reportBytes) {
		t.Fatalf("stdout was polluted with report JSON")
	}

	// Verify stdout only contains transcript JSON
	if !json.Valid(stdout.Bytes()) {
		t.Fatalf("expected valid JSON in stdout, got %q", stdout.String())
	}

	// Parse stdout to verify it's a transcript, not a report
	var stdoutContent map[string]interface{}
	if err := json.Unmarshal(stdout.Bytes(), &stdoutContent); err != nil {
		t.Fatalf("failed to parse stdout as JSON: %v", err)
	}

	// Transcript should be an array at top level
	if _, isArray := stdoutContent["segments"]; !isArray && stdoutContent["segments"] != nil {
		t.Fatalf("expected transcript in stdout, got report structure")
	}
}