v1 proxy test: order arrivals by limiter state; note the 499-on-served-200 defect for v2.1

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

docs/plans/v1/_files/internal/proxy/proxy_test.go

@@ -85,6 +85,19 @@ func TestDifferentConversationsSpreadByFreeSlots(t *testing.T) {
 	}
 }
 
+// waitUntil polls cond every 5 ms for up to two seconds and fails the test if it never holds.
+func waitUntil(t *testing.T, cond func() bool) {
+	t.Helper()
+	deadline := time.Now().Add(2 * time.Second)
+	for time.Now().Before(deadline) {
+		if cond() {
+			return
+		}
+		time.Sleep(5 * time.Millisecond)
+	}
+	t.Fatal("condition not reached within two seconds")
+}
+
 func TestQueueFullIs503(t *testing.T) {
 	alpha := newUpstream(t, "alpha")
 	alpha.delay = 400 * time.Millisecond
@@ -99,14 +112,20 @@ hosts = ["alpha"]
 default_model = "shared"
 `, alpha)
 	codes := make(chan int, 3)
-	for i := 1; i <= 3; i++ {
-		go func(i int) {
+	fire := func(i int) {
+		go func() {
 			resp := r.post("/r/v1/chat/completions", conversation(i, 1))
 			drain(resp)
 			codes <- resp.StatusCode
-		}(i)
-		time.Sleep(30 * time.Millisecond) // arrival order: 1 runs, 2 queues, 3 finds the queue full
+		}()
 	}
+	// Arrival order is enforced by watching the limiter, not by sleeping: 1 runs, 2 queues,
+	// 3 finds the queue full.
+	fire(1)
+	waitUntil(t, func() bool { return r.lim.InFlight("alpha", "shared") == 1 })
+	fire(2)
+	waitUntil(t, func() bool { return r.lim.Queued("alpha", "shared") == 1 })
+	fire(3)
 	got := map[int]int{}
 	for i := 0; i < 3; i++ {
 		got[<-codes]++