Add extract worker configuration controls

internal/core/config/validation.go

@@ -2,6 +2,7 @@ package config
 
 import (
 	"fmt"
+	"sort"
 	"strings"
 
 	"gitea.maximumdirect.net/eric/notarius/internal/core/diagnostics"
@@ -9,6 +10,7 @@ import (
 )
 
 func (c Config) Validate() error {
+	c.Concurrency.recomputeStageWorkerDefaults()
 	if err := validateScriptorium(c.Scriptorium); err != nil {
 		return err
 	}
@@ -21,9 +23,36 @@ func (c Config) Validate() error {
 	if c.Concurrency.TotalLLM <= 0 {
 		return fmt.Errorf("total LLM concurrency must be greater than zero")
 	}
+	if err := validateStageWorkers(c.Concurrency); err != nil {
+		return err
+	}
 	return validatePipelineProfiles(c.Pipelines)
 }
 
+func validateStageWorkers(cfg ConcurrencyConfig) error {
+	keys := make([]string, 0, len(cfg.StageWorkers))
+	for key := range cfg.StageWorkers {
+		keys = append(keys, key)
+	}
+	sort.Strings(keys)
+	for _, key := range keys {
+		if strings.TrimSpace(key) == "" {
+			return fmt.Errorf("concurrency.stage_workers key must not be empty")
+		}
+		if key != "extract" {
+			return fmt.Errorf("concurrency.stage_workers key %q is not supported", key)
+		}
+	}
+	extractWorkers, ok := cfg.StageWorkers["extract"]
+	if !ok {
+		extractWorkers = cfg.TotalLLM
+	}
+	if extractWorkers < 1 || extractWorkers > cfg.TotalLLM {
+		return fmt.Errorf("concurrency.stage_workers.extract must be between 1 and concurrency.total_llm (%d)", cfg.TotalLLM)
+	}
+	return nil
+}
+
 func validateScriptorium(cfg ScriptoriumConfig) error {
 	if strings.TrimSpace(cfg.ProfileDir) != "" && strings.TrimSpace(cfg.ProfileFile) != "" {
 		return fmt.Errorf("scriptorium profile_dir and profile_file are mutually exclusive")