Implement real Seriatim merge stage

internal/app/commands_test.go

@@ -3,6 +3,7 @@ package app
 import (
 	"bytes"
 	"context"
+	"fmt"
 	"net/http"
 	"net/http/httptest"
 	"os"
@@ -195,6 +196,8 @@ func writeValidConfigFiles(t *testing.T, workspaceRoot string, transcribeURL ...
 	if len(transcribeURL) > 0 && strings.TrimSpace(transcribeURL[0]) != "" {
 		url = transcribeURL[0]
 	}
+	seriatimBinary := writeSeriatimAppTestWrapper(t)
+	t.Setenv("GO_WANT_APP_SERIATIM_HELPER", "1")
 
 	pipelineYAML := `workspace:
   root: ` + workspaceRoot + `
@@ -207,7 +210,7 @@ whisperx:
   retry_delay: 1ms
   concurrency: 1
 seriatim:
-  binary: seriatim
+  binary: ` + seriatimBinary + `
   timeout: 10m
   output_schema: seriatim-intermediate
   coalesce_gap: 3.0
@@ -237,7 +240,7 @@ inputs:
 		t.Fatalf("write session config: %v", err)
 	}
 
-	mustWriteTestFile(t, filepath.Join(dir, "speakers.yml"), "alice: alice.flac\n")
+	mustWriteTestFile(t, filepath.Join(dir, "speakers.yml"), "match:\n  - speaker: Alice\n    match: [\"alice\"]\n")
 	mustWriteTestFile(t, filepath.Join(dir, "autocorrect.yml"), "[]\n")
 	mustWriteTestFile(t, filepath.Join(dir, "glossary.yml"), "[]\n")
 	mustWriteTestFile(t, filepath.Join(dir, "audio", "alice.flac"), "audio-bytes")
@@ -269,3 +272,74 @@ func mustWriteTestFile(t *testing.T, path, contents string) {
 		t.Fatalf("write %q: %v", path, err)
 	}
 }
+
+func writeSeriatimAppTestWrapper(t *testing.T) string {
+	t.Helper()
+	exe, err := os.Executable()
+	if err != nil {
+		t.Fatalf("os.Executable() error = %v", err)
+	}
+	path := filepath.Join(t.TempDir(), "seriatim-helper-wrapper.sh")
+	content := "#!/bin/sh\nexec \"" + exe + "\" -test.run=TestSeriatimAppHelper -- \"$@\"\n"
+	if err := os.WriteFile(path, []byte(content), 0o755); err != nil {
+		t.Fatalf("WriteFile(%q): %v", path, err)
+	}
+	return path
+}
+
+func TestSeriatimAppHelper(t *testing.T) {
+	if os.Getenv("GO_WANT_APP_SERIATIM_HELPER") != "1" {
+		return
+	}
+
+	args := os.Args
+	start := -1
+	for i := range args {
+		if args[i] == "--" {
+			start = i + 1
+			break
+		}
+	}
+	if start < 0 || start >= len(args) {
+		_, _ = os.Stderr.WriteString("missing -- args separator\n")
+		os.Exit(2)
+	}
+	mergeArgs := args[start:]
+
+	outputPath := appSeriatimFlagValue(mergeArgs, "--output-file")
+	reportPath := appSeriatimFlagValue(mergeArgs, "--report-file")
+	if strings.TrimSpace(outputPath) == "" {
+		_, _ = os.Stderr.WriteString("missing --output-file\n")
+		os.Exit(2)
+	}
+	if err := os.MkdirAll(filepath.Dir(outputPath), 0o755); err != nil {
+		_, _ = os.Stderr.WriteString(fmt.Sprintf("mkdir output dir: %v\n", err))
+		os.Exit(2)
+	}
+	if err := os.WriteFile(outputPath, []byte(`{"schema":"seriatim-intermediate","segments":[]}`), 0o644); err != nil {
+		_, _ = os.Stderr.WriteString(fmt.Sprintf("write output: %v\n", err))
+		os.Exit(2)
+	}
+	if strings.TrimSpace(reportPath) != "" {
+		if err := os.MkdirAll(filepath.Dir(reportPath), 0o755); err != nil {
+			_, _ = os.Stderr.WriteString(fmt.Sprintf("mkdir report dir: %v\n", err))
+			os.Exit(2)
+		}
+		if err := os.WriteFile(reportPath, []byte(`{"report":true}`), 0o644); err != nil {
+			_, _ = os.Stderr.WriteString(fmt.Sprintf("write report: %v\n", err))
+			os.Exit(2)
+		}
+	}
+	_, _ = os.Stdout.WriteString("seriatim helper stdout\n")
+	_, _ = os.Stderr.WriteString("seriatim helper stderr\n")
+	os.Exit(0)
+}
+
+func appSeriatimFlagValue(args []string, name string) string {
+	for i := 0; i < len(args)-1; i++ {
+		if args[i] == name {
+			return args[i+1]
+		}
+	}
+	return ""
+}