test(acceptance): 验证厂商三类额度与优先路由

为 provider-burst 固定三平台并发、RPM、TPM 和优先级组合，使用稳定 token 用量的本地视频负载验证同级按容量分流及低优先级溢出。\n\n报告升级为 v2，强制校验三类额度峰值精确命中上限、不越界、队列回收、三 Worker 分发以及重复提交和回调安全。\n\n验证：\n- env -u AI_GATEWAY_TEST_DATABASE_URL go test ./... -count=1\n- go vet ./...\n- bash -n scripts/acceptance/provider-burst.sh scripts/acceptance/run-local-acceptance.sh\n- shellcheck -x scripts/acceptance/provider-burst.sh scripts/acceptance/run-local-acceptance.sh

apps/api/internal/runner/limits_test.go

@@ -134,3 +134,15 @@ func TestReservationsFromPolicySkipsNonPositiveLimits(t *testing.T) {
 		t.Fatalf("expected concurrent reservation with limit 2, got %+v", reservations[0])
 	}
 }
+
+func TestProviderQuotaPromptReservesSevenTokens(t *testing.T) {
+	body := map[string]any{
+		"content": []any{map[string]any{
+			"type": "text",
+			"text": "acceptance-provider-quota",
+		}},
+	}
+	if got := estimateRequestTokens(body); got != 7 {
+		t.Fatalf("provider quota prompt tokens=%d, want 7", got)
+	}
+}