Implemented an --llm-concurrency flag in the Go application that enforces a global LLM concurrency cap

internal/cli/run.go

@@ -194,21 +194,28 @@ var processRunner = func(inv processInvocation, stdout io.Writer) (*normalizatio
 					validationLLMClient = client
 				}
 			}
-			if proposalScheduler == nil {
+			globalScheduler := proposalScheduler
+			if globalScheduler == nil {
 				primaryCfg := llm.ResolvePrimaryConfig(inv.Config)
 				s, sErr := llm.NewScheduler(primaryCfg.Concurrency)
 				if sErr != nil {
 					return fail("runner_setup", sErr, nil)
 				}
-				proposalScheduler = s
+				globalScheduler = s
+			}
+			if proposalScheduler == nil {
+				proposalScheduler = globalScheduler
 			}
 			if validationScheduler == nil {
-				validationCfg := llm.ResolveValidationConfig(inv.Config)
-				s, sErr := llm.NewScheduler(validationCfg.Concurrency)
-				if sErr != nil {
-					return fail("runner_setup", sErr, nil)
+				validationScheduler = globalScheduler
+				if inv.Config.ValidationLLM.Concurrency != nil && inv.Config.PrimaryLLM.Concurrency > inv.Config.EffectiveValidationLLMConfig().Concurrency {
+					validationCfg := llm.ResolveValidationConfig(inv.Config)
+					s, sErr := llm.NewScheduler(validationCfg.Concurrency)
+					if sErr != nil {
+						return fail("runner_setup", sErr, nil)
+					}
+					validationScheduler = composeSchedulers(globalScheduler, s)
 				}
-				validationScheduler = s
 			}
 		}
 
@@ -276,6 +283,42 @@ func sourceToCanonicalTranscript(source *schema.SourceTranscript) *schema.Transc
 	return &schema.Transcript{Segments: segments}
 }
 
+type chainedScheduler struct {
+	schedulers []runner.ValidationScheduler
+}
+
+func (s chainedScheduler) Run(ctx context.Context, fn func(context.Context) error) error {
+	if len(s.schedulers) == 0 {
+		return fn(ctx)
+	}
+	run := fn
+	for i := len(s.schedulers) - 1; i >= 0; i-- {
+		scheduler := s.schedulers[i]
+		next := run
+		run = func(callCtx context.Context) error {
+			return scheduler.Run(callCtx, next)
+		}
+	}
+	return run(ctx)
+}
+
+func composeSchedulers(schedulers ...runner.ValidationScheduler) runner.ValidationScheduler {
+	filtered := make([]runner.ValidationScheduler, 0, len(schedulers))
+	for _, scheduler := range schedulers {
+		if scheduler != nil {
+			filtered = append(filtered, scheduler)
+		}
+	}
+	switch len(filtered) {
+	case 0:
+		return nil
+	case 1:
+		return filtered[0]
+	default:
+		return chainedScheduler{schedulers: filtered}
+	}
+}
+
 // Run executes the Audita CLI with the provided arguments and streams.
 func Run(args []string, stdout, stderr io.Writer) int {
 	if len(args) == 0 {
@@ -349,6 +392,8 @@ func runProcess(args []string, stdout, stderr io.Writer) int {
 			overrides.ValidationBaseURL = pFlags.validationBaseURL
 		case "llm-timeout-seconds":
 			overrides.PrimaryLLMTimeoutSeconds = pFlags.llmTimeoutSeconds
+		case "llm-concurrency":
+			overrides.PrimaryLLMConcurrency = pFlags.llmConcurrency
 		case "validation-llm-timeout-seconds":
 			overrides.ValidationLLMTimeoutSeconds = pFlags.validationLLMTimeoutSeconds
 		case "max-retries":
@@ -637,6 +682,7 @@ type processFlags struct {
 	baseURL                       *string
 	validationBaseURL             *string
 	llmTimeoutSeconds             *int
+	llmConcurrency                *int
 	validationLLMTimeoutSeconds   *int
 	validationMaxPromptTokens     *int
 	targetSections                *int
@@ -693,6 +739,7 @@ func newProcessFlagSet(cfg config.Config, stderr io.Writer) (*flag.FlagSet, proc
 		baseURL:                       fs.String("base-url", cfg.PrimaryLLM.BaseURL, "Primary OpenAI-compatible base URL"),
 		validationBaseURL:             fs.String("validation-base-url", cfg.ValidationLLM.BaseURL, "Validation OpenAI-compatible base URL"),
 		llmTimeoutSeconds:             fs.Int("llm-timeout-seconds", cfg.PrimaryLLM.TimeoutSeconds, "Primary LLM timeout in seconds"),
+		llmConcurrency:                fs.Int("llm-concurrency", cfg.PrimaryLLM.Concurrency, "Primary LLM concurrency"),
 		validationLLMTimeoutSeconds:   fs.Int("validation-llm-timeout-seconds", validationTimeoutSecondsDefault, "Validation LLM timeout in seconds"),
 		validationMaxPromptTokens:     fs.Int("validation-max-prompt-tokens", cfg.ValidationMaxPromptTokens, "Validation max prompt tokens"),
 		targetSections:                fs.Int("target-sections", targetSectionsDefault, "Target number of transcript sections"),