Wire schema validation into process command

2026-05-11 00:01:42 +00:00
parent 950edc01f2
commit 3cfa4b6e8a
2 changed files with 178 additions and 42 deletions
--- a/internal/cli/run.go
+++ b/internal/cli/run.go
@@ -9,8 +9,9 @@ import (
 	"time"

 	"gitea.maximumdirect.net/eric/audita/internal/core/config"
-	coreio "gitea.maximumdirect.net/eric/audita/internal/core/io"
+	"gitea.maximumdirect.net/eric/audita/internal/core/io"
 	"gitea.maximumdirect.net/eric/audita/internal/core/reporting"
+	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
 )

 type processInvocation struct {
@@ -22,25 +23,61 @@ type processInvocation struct {
 }

 var processRunner = func(inv processInvocation, stdout io.Writer) error {
-	transcriptBytes, err := coreio.ReadRequiredFile(inv.TranscriptPath, "transcript")
+	transcriptBytes, err := io.ReadRequiredFile(inv.TranscriptPath, "transcript")
 	if err != nil {
 		return err
 	}
-	if err := coreio.ValidateWellFormedJSON(inv.TranscriptPath, transcriptBytes); err != nil {
-		return err
-	}
-	if _, err := coreio.ReadRequiredFile(inv.GlossaryPath, "glossary"); err != nil {
+
+	glossaryBytes, err := io.ReadRequiredFile(inv.GlossaryPath, "glossary")
+	if err != nil {
 		return err
 	}

+	// Parse and validate transcript using typed schema
+	transcript, err := schema.ParseSourceTranscriptJSON(transcriptBytes)
+	if err != nil {
+		return fmt.Errorf("invalid transcript: %w", err)
+	}
+
+	// Parse and validate glossary using typed schema
+	glossary, err := schema.ParseGlossaryYAML(glossaryBytes)
+	if err != nil {
+		return fmt.Errorf("invalid glossary: %w", err)
+	}
+
+	// Convert to canonical transcript format for output
+	outputTranscript := &schema.Transcript{
+		Segments: make([]schema.Segment, len(transcript.Segments)),
+	}
+	for i, s := range transcript.Segments {
+		id := i + 1
+		if s.ID != nil {
+			id = *s.ID
+		}
+		outputTranscript.Segments[i] = schema.Segment{
+			ID:         id,
+			Speaker:    s.Speaker,
+			Start:      s.Start,
+			End:        s.End,
+			Text:       s.Text,
+			Categories: s.Categories,
+		}
+	}
+
+	// Serialize output transcript to JSON
+	outputBytes, err := schema.TranscriptToJSON(outputTranscript)
+	if err != nil {
+		return fmt.Errorf("failed to serialize transcript: %w", err)
+	}
+
 	if strings.TrimSpace(inv.OutputPath) != "" {
-		if err := coreio.WriteFile(inv.OutputPath, transcriptBytes); err != nil {
+		if err := io.WriteFile(inv.OutputPath, outputBytes); err != nil {
 			return err
 		}
 		return nil
 	}

-	if _, err := stdout.Write(transcriptBytes); err != nil {
+	if _, err := stdout.Write(outputBytes); err != nil {
 		return fmt.Errorf("failed to write transcript to stdout: %w", err)
 	}
 	return nil
--- a/internal/cli/run_test.go
+++ b/internal/cli/run_test.go
@@ -341,49 +341,71 @@ func TestRunProcessReportJSONBestEffortOnFailure(t *testing.T) {
 	}
 }

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

-	t.Setenv("AUDITA_MODEL", "env-model")
-	t.Setenv("AUDITA_VALIDATION_LLM_CONCURRENCY", "2")
-
-	transcriptPath := fixturePath("tiny_transcript.json")
-	glossaryPath := fixturePath("tiny_glossary.yaml")
-
-	var captured processInvocation
-	originalRunner := processRunner
-	processRunner = func(inv processInvocation, output io.Writer) error {
-		_ = output
-		captured = inv
-		return nil
+	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")
 	}
-	t.Cleanup(func() {
-		processRunner = originalRunner
-	})
+	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())
+	}
+}

-	exitCode := Run([]string{
-		"process",
-		transcriptPath,
-		"--glossary",
-		glossaryPath,
-		"--model",
-		"cli-model",
-		"--validation-llm-concurrency",
-		"5",
-	}, &stdout, &stderr)
+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", exitCode)
+		t.Fatalf("expected exit code 0, got %d with stderr %q", exitCode, stderr.String())
 	}
-	if captured.Config.PrimaryLLM.Model != "cli-model" {
-		t.Fatalf("expected CLI model override, got %q", captured.Config.PrimaryLLM.Model)
+	if stderr.Len() != 0 {
+		t.Fatalf("expected empty stderr on success, got %q", stderr.String())
 	}
-	if captured.Config.ValidationLLM.Concurrency == nil || *captured.Config.ValidationLLM.Concurrency != 5 {
-		t.Fatalf("expected CLI validation concurrency override, got %#v", captured.Config.ValidationLLM.Concurrency)
+
+	// Should produce valid JSON output
+	if !json.Valid(stdout.Bytes()) {
+		t.Fatalf("expected valid JSON output, got %q", stdout.String())
 	}
-	if captured.GlossaryPath != glossaryPath {
-		t.Fatalf("unexpected glossary path: %q", captured.GlossaryPath)
+
+	// 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())
 	}
 }

@@ -438,5 +460,82 @@ func readProcessReport(t *testing.T, path string) minimalProcessReport {
 	if err := json.Unmarshal(raw, &report); err != nil {
 		t.Fatalf("failed to unmarshal process report JSON: %v (raw: %q)", err, string(raw))
 	}
-	return report
+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 TestRunProcessReportJSONOnParseFailure(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 parse failure")
+	}
+	if stdout.Len() != 0 {
+		t.Fatalf("expected empty stdout on failure, got %q", stdout.String())
+	}
+
+	// Report should still be written on parse failure
+	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, "invalid transcript:") {
+		t.Fatalf("expected invalid transcript error in report, got %q", report.ErrorMessage)
+	}
 }