Connect processing to shared PromptKit backend capacity

internal/framework/validators/llm_validators_test.go

@@ -3,12 +3,8 @@ package validators
 import (
 	"context"
 	"errors"
-	"runtime"
 	"strings"
-	"sync"
-	"sync/atomic"
 	"testing"
-	"time"
 
 	"gitea.maximumdirect.net/eric/audita/internal/core/chunking"
 	"gitea.maximumdirect.net/eric/audita/internal/core/config"
@@ -25,17 +21,6 @@ type fakeStructuredLLMClient struct {
 	calls     []StructuredCompletionRequest
 }
 
-type sleepingValidationClient struct {
-	inFlight    int32
-	maxInFlight int32
-	entered     chan struct{}
-	release     chan struct{}
-}
-
-type boundedScheduler struct {
-	permits chan struct{}
-}
-
 type captureValidationDiagnosticsWriter struct {
 	lastRequestMetadata any
 }
@@ -49,48 +34,6 @@ func (w *captureValidationDiagnosticsWriter) WriteInteraction(stage string, requ
 	return InteractionArtifacts{}, nil
 }
 
-func newBoundedScheduler(max int) *boundedScheduler {
-	return &boundedScheduler{permits: make(chan struct{}, max)}
-}
-
-func (s *boundedScheduler) Run(ctx context.Context, fn func(context.Context) error) error {
-	select {
-	case s.permits <- struct{}{}:
-	case <-ctx.Done():
-		return ctx.Err()
-	}
-	defer func() { <-s.permits }()
-	return fn(ctx)
-}
-
-func (c *sleepingValidationClient) CompleteStructured(ctx context.Context, req StructuredCompletionRequest, out any) (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
-		}
-	}
-	if c.entered != nil {
-		c.entered <- struct{}{}
-	}
-	select {
-	case <-c.release:
-	case <-ctx.Done():
-		atomic.AddInt32(&c.inFlight, -1)
-		return StructuredCompletionResponse{}, ctx.Err()
-	}
-	atomic.AddInt32(&c.inFlight, -1)
-	target := out.(*LLMValidationResponse)
-	*target = LLMValidationResponse{
-		Validations: []LLMValidationDecision{
-			{CorrectionIndex: 0, Approved: true, Confidence: 0.9, Reason: "ok"},
-		},
-	}
-	return StructuredCompletionResponse{}, nil
-}
-
 func (f *fakeStructuredLLMClient) CompleteStructured(ctx context.Context, req StructuredCompletionRequest, out any) (StructuredCompletionResponse, error) {
 	_ = ctx
 	f.calls = append(f.calls, req)
@@ -313,42 +256,6 @@ func TestLLMBackedValidatorOversizedSingleProposalRejectsOnlyThatProposal(t *tes
 	}
 }
 
-func TestLLMBackedValidatorRespectsSchedulerConcurrency(t *testing.T) {
-	scheduler := newBoundedScheduler(2)
-	client := &sleepingValidationClient{
-		entered: make(chan struct{}, 16),
-		release: make(chan struct{}),
-	}
-	v, err := NewLLMBackedValidator("spoken_form_plausibility_review", LLMValidatorTypeSpokenFormPlausibility)
-	if err != nil {
-		t.Fatalf("new validator error: %v", err)
-	}
-
-	var wg sync.WaitGroup
-	for i := 0; i < 8; i++ {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			req := makeReq([]proposals.EnrichedCorrectionProposal{mk(0, "gestures", "Jesters")})
-			req.LLMClient = client
-			req.Scheduler = scheduler
-			if _, runErr := v.Validate(context.Background(), req); runErr != nil {
-				t.Errorf("Validate error: %v", runErr)
-			}
-		}()
-	}
-	waitForValidationEntries(t, client.entered, 2)
-	close(client.release)
-	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)
-	}
-}
-
 func TestLLMBackedValidatorDiagnosticsIncludeSchemaMetadata(t *testing.T) {
 	client := &fakeStructuredLLMClient{responses: []LLMValidationResponse{{Validations: []LLMValidationDecision{
 		{CorrectionIndex: 0, Approved: true, Confidence: 0.9, Reason: "ok"},
@@ -379,24 +286,6 @@ func TestLLMBackedValidatorDiagnosticsIncludeSchemaMetadata(t *testing.T) {
 	}
 
 }
-
-func waitForValidationEntries(t *testing.T, entered <-chan struct{}, want int) {
-	t.Helper()
-	deadline := time.Now().Add(300 * time.Millisecond)
-	got := 0
-	for got < want && time.Now().Before(deadline) {
-		select {
-		case <-entered:
-			got++
-		default:
-			runtime.Gosched()
-		}
-	}
-	if got < want {
-		t.Fatalf("timed out waiting for %d validator calls to enter (got %d)", want, got)
-	}
-}
-
 func TestEveryValidationTypeSelectsEmbeddedPromptAndVariables(t *testing.T) {
 	cases := []struct {
 		kind   LLMValidatorType