Added initial segment overlap resolution logic

internal/config/config.go

@@ -6,6 +6,7 @@ import (
 	"os"
 	"path/filepath"
 	"sort"
+	"strconv"
 	"strings"
 )
 
@@ -14,6 +15,8 @@ const (
 	DefaultOutputModules         = "json"
 	DefaultPreprocessingModules  = "validate-raw,normalize-speakers,trim-text"
 	DefaultPostprocessingModules = "detect-overlaps,resolve-overlaps,autocorrect,assign-ids,validate-output"
+	DefaultOverlapWordRunGap     = 0.75
+	OverlapWordRunGapEnv         = "SERIATIM_OVERLAP_WORD_RUN_GAP"
 )
 
 // MergeOptions captures raw CLI option values before validation.
@@ -40,6 +43,7 @@ type Config struct {
 	OutputModules         []string
 	PreprocessingModules  []string
 	PostprocessingModules []string
+	OverlapWordRunGap     float64
 }
 
 // NewMergeConfig validates raw merge options and returns normalized config.
@@ -49,6 +53,7 @@ func NewMergeConfig(opts MergeOptions) (Config, error) {
 		OutputModules:         nil,
 		PreprocessingModules:  nil,
 		PostprocessingModules: nil,
+		OverlapWordRunGap:     DefaultOverlapWordRunGap,
 	}
 
 	if cfg.InputReader == "" {
@@ -110,6 +115,11 @@ func NewMergeConfig(opts MergeOptions) (Config, error) {
 		}
 	}
 
+	cfg.OverlapWordRunGap, err = parseOverlapWordRunGap()
+	if err != nil {
+		return Config{}, err
+	}
+
 	return cfg, nil
 }
 
@@ -187,6 +197,22 @@ func requireFile(path string, flag string) error {
 	return nil
 }
 
+func parseOverlapWordRunGap() (float64, error) {
+	value := strings.TrimSpace(os.Getenv(OverlapWordRunGapEnv))
+	if value == "" {
+		return DefaultOverlapWordRunGap, nil
+	}
+
+	gap, err := strconv.ParseFloat(value, 64)
+	if err != nil {
+		return 0, fmt.Errorf("%s must be a positive number of seconds: %w", OverlapWordRunGapEnv, err)
+	}
+	if gap <= 0 {
+		return 0, fmt.Errorf("%s must be positive", OverlapWordRunGapEnv)
+	}
+	return gap, nil
+}
+
 func contains(values []string, target string) bool {
 	for _, value := range values {
 		if value == target {