Add explicit LLM concurrency controls

internal/framework/proposal_generation/generate_test.go

@@ -7,10 +7,14 @@ import (
 	"path/filepath"
 	"reflect"
 	"strings"
+	"sync"
+	"sync/atomic"
 	"testing"
+	"time"
 
 	"gitea.maximumdirect.net/eric/audita/internal/core/config"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/audita/internal/framework/llm"
 	"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
 )
 
@@ -47,6 +51,40 @@ func (s *countingScheduler) Run(ctx context.Context, fn func(context.Context) er
 	return fn(ctx)
 }
 
+type sleepingStructuredClient struct {
+	inFlight    int32
+	maxInFlight int32
+}
+
+func (c *sleepingStructuredClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
+	_ = req
+	current := atomic.AddInt32(&c.inFlight, 1)
+	for {
+		prior := atomic.LoadInt32(&c.maxInFlight)
+		if current <= prior || atomic.CompareAndSwapInt32(&c.maxInFlight, prior, current) {
+			break
+		}
+	}
+	select {
+	case <-time.After(20 * time.Millisecond):
+	case <-ctx.Done():
+		atomic.AddInt32(&c.inFlight, -1)
+		return contracts.StructuredCompletionResponse{}, ctx.Err()
+	}
+	atomic.AddInt32(&c.inFlight, -1)
+
+	target, ok := out.(*StructuredCorrectionSet)
+	if !ok {
+		return contracts.StructuredCompletionResponse{}, errors.New("unexpected output type")
+	}
+	*target = StructuredCorrectionSet{
+		Corrections: []StructuredCorrectionProposal{
+			{TargetSegmentID: 1, OriginalText: "x", CorrectedText: "y", Confidence: 0.9},
+		},
+	}
+	return contracts.StructuredCompletionResponse{}, nil
+}
+
 func defaultRequest(t *testing.T) Request {
 	t.Helper()
 	cfg := config.Default()
@@ -265,3 +303,35 @@ func TestGenerateCandidatesClientError(t *testing.T) {
 		t.Fatalf("expected error diagnostics artifact under %s", req.DiagnosticsDir)
 	}
 }
+
+func TestGenerateCandidatesRespectsSchedulerConcurrency(t *testing.T) {
+	scheduler, err := llm.NewScheduler(2)
+	if err != nil {
+		t.Fatalf("NewScheduler: %v", err)
+	}
+	client := &sleepingStructuredClient{}
+	baseReq := defaultRequest(t)
+	baseReq.LLMClient = client
+	baseReq.Scheduler = scheduler
+
+	var wg sync.WaitGroup
+	for i := 0; i < 8; i++ {
+		wg.Add(1)
+		go func(idx int) {
+			defer wg.Done()
+			req := baseReq
+			req.StartIndex = idx
+			if _, runErr := GenerateCandidates(context.Background(), req); runErr != nil {
+				t.Errorf("GenerateCandidates[%d] error: %v", idx, runErr)
+			}
+		}(i)
+	}
+	wg.Wait()
+
+	if got := atomic.LoadInt32(&client.maxInFlight); got > 2 {
+		t.Fatalf("expected scheduler cap <= 2, got %d", got)
+	}
+	if got := atomic.LoadInt32(&client.maxInFlight); got < 2 {
+		t.Fatalf("expected observed concurrency of at least 2, got %d", got)
+	}
+}