diff --git a/Dockerfile.intel b/Dockerfile.intel
index bda0458d2f3..ee0d0171ed9 100644
--- a/Dockerfile.intel
+++ b/Dockerfile.intel
@@ -146,7 +146,7 @@ RUN wget --no-check-certificate --quiet --tries=3 --timeout=30 \
     -DCMAKE_C_FLAGS="-O3 -fopenmp" \
     -DCMAKE_CXX_FLAGS="-O3 -fopenmp" \
     -DXSDK_ENABLE_Fortran=ON \
-    -DCMAKE_Fortran_COMPILER=mpiifx && \
+    -DCMAKE_Fortran_COMPILER=mpiifx && \                             
     make -j$(nproc) && \
     make install && \
     cd / && rm -rf superlu_dist-${SUPERLU_DIST_VERSION} v${SUPERLU_DIST_VERSION}.tar.gz
diff --git a/source/source_base/complexmatrix.h b/source/source_base/complexmatrix.h
index ac09c3ddb0b..df1585e4c18 100644
--- a/source/source_base/complexmatrix.h
+++ b/source/source_base/complexmatrix.h
@@ -6,7 +6,6 @@
 #include "matrix.h"
 
 #ifdef _MCD_CHECK
-#include "mcd.h"
 #endif
 namespace ModuleBase
 {
diff --git a/source/source_base/inverse_matrix.h b/source/source_base/inverse_matrix.h
index d49e109e157..bac2e5b979a 100644
--- a/source/source_base/inverse_matrix.h
+++ b/source/source_base/inverse_matrix.h
@@ -2,7 +2,6 @@
 #define INVERSE_MATRIX_H
 
 #include "global_function.h"
-#include "global_variable.h"
 #include "complexmatrix.h"
 namespace ModuleBase
 {
diff --git a/source/source_base/kernels/cuda/math_kernel_op_vec.cu b/source/source_base/kernels/cuda/math_kernel_op_vec.cu
index 4cf756c5794..f0edc47d101 100644
--- a/source/source_base/kernels/cuda/math_kernel_op_vec.cu
+++ b/source/source_base/kernels/cuda/math_kernel_op_vec.cu
@@ -1,6 +1,7 @@
 #include "source_base/kernels/math_kernel_op.h"
 
 #include <base/macros/macros.h>
+#include "source_base/parallel_reduce.h"
 #include <thrust/complex.h>
 
 template <>
diff --git a/source/source_base/kernels/dsp/dsp_connector.h b/source/source_base/kernels/dsp/dsp_connector.h
index 3dcc3d125df..2b21eb70357 100644
--- a/source/source_base/kernels/dsp/dsp_connector.h
+++ b/source/source_base/kernels/dsp/dsp_connector.h
@@ -4,7 +4,6 @@
 
 #include "source_base/module_device/device.h"
 #include "source_base/module_device/memory_op.h"
-#include "source_hsolver/diag_comm_info.h"
 
 namespace mtfunc
 {
diff --git a/source/source_base/kernels/math_kernel_op.h b/source/source_base/kernels/math_kernel_op.h
index 120844f3f9a..3bff00f9e9f 100644
--- a/source/source_base/kernels/math_kernel_op.h
+++ b/source/source_base/kernels/math_kernel_op.h
@@ -5,7 +5,6 @@
 
 #include "source_base/macros.h"
 
-#include "source_base/parallel_reduce.h"
 
 #include "source_base/module_device/memory_op.h"
 #include "source_base/module_device/types.h"
diff --git a/source/source_base/kernels/math_kernel_op_vec.cpp b/source/source_base/kernels/math_kernel_op_vec.cpp
index da3fdb8f06e..8957a96ba11 100644
--- a/source/source_base/kernels/math_kernel_op_vec.cpp
+++ b/source/source_base/kernels/math_kernel_op_vec.cpp
@@ -1,5 +1,6 @@
 #include "source_base/kernels/math_kernel_op.h"
 #include "source_base/module_external/blas_connector.h"
+#include "source_base/parallel_reduce.h"
 
 
 namespace ModuleBase
diff --git a/source/source_base/matrix.h b/source/source_base/matrix.h
index 0a117b4ca1a..62196113b29 100644
--- a/source/source_base/matrix.h
+++ b/source/source_base/matrix.h
@@ -4,7 +4,6 @@
 // Peize Lin update 2018-07-29
 
 #ifdef _MCD_CHECK
-#include "mcd.h"
 #endif
 
 #include <ostream>
diff --git a/source/source_base/parallel_2d.cpp b/source/source_base/parallel_2d.cpp
index 43a6c321064..b5bab96694b 100644
--- a/source/source_base/parallel_2d.cpp
+++ b/source/source_base/parallel_2d.cpp
@@ -1,5 +1,6 @@
 #include "parallel_2d.h"
 
+#include "source_base/module_external/blacs_connector.h"
 #include "source_base/module_external/scalapack_connector.h"
 
 #include <cassert>
diff --git a/source/source_base/parallel_2d.h b/source/source_base/parallel_2d.h
index ea027e58d04..c179dd18e79 100644
--- a/source/source_base/parallel_2d.h
+++ b/source/source_base/parallel_2d.h
@@ -4,7 +4,7 @@
 #include <cstdint>
 #include <vector>
 
-#include "source_base/module_external/blacs_connector.h"
+#include "source_base/parallel_comm.h"
 
 /// @brief  This class packs the basic information of
 /// 2D-block-cyclic parallel distribution of an arbitrary matrix.
diff --git a/source/source_base/parallel_device.cpp b/source/source_base/parallel_device.cpp
index 933064e2486..97bf68f13b6 100644
--- a/source/source_base/parallel_device.cpp
+++ b/source/source_base/parallel_device.cpp
@@ -1,4 +1,6 @@
 #include "parallel_device.h"
+#include "source_base/module_device/memory_op.h"
+#include "source_base/module_device/types.h"
 #ifdef __MPI
 namespace Parallel_Common
 {
diff --git a/source/source_base/parallel_device.h b/source/source_base/parallel_device.h
index 7293b375d74..9e9f755edf7 100644
--- a/source/source_base/parallel_device.h
+++ b/source/source_base/parallel_device.h
@@ -2,8 +2,6 @@
 #define __PARALLEL_DEVICE_H__
 #ifdef __MPI
 #include "mpi.h"
-#include "source_base/module_device/device.h"
-#include "source_base/module_device/memory_op.h"
 #include <complex>
 namespace Parallel_Common
 {
diff --git a/source/source_base/vector3.h b/source/source_base/vector3.h
index 5e28357496d..5fb2bf3f7e1 100644
--- a/source/source_base/vector3.h
+++ b/source/source_base/vector3.h
@@ -8,7 +8,6 @@
 #include <array>
 
 #ifdef _MCD_CHECK
-#include "mcd.h"
 #endif
 
 namespace ModuleBase
diff --git a/source/source_basis/module_ao/ORB_atomic_lm.h b/source/source_basis/module_ao/ORB_atomic_lm.h
index 9b2be4f01a3..4d013d04453 100644
--- a/source/source_basis/module_ao/ORB_atomic_lm.h
+++ b/source/source_basis/module_ao/ORB_atomic_lm.h
@@ -9,7 +9,6 @@
 #include <vector>
 using std::vector;
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 
 /**
  * CLASS Num_orbital_lm
diff --git a/source/source_basis/module_ao/ORB_nonlocal.h b/source/source_basis/module_ao/ORB_nonlocal.h
index 4c4007a796c..1204dd86912 100644
--- a/source/source_basis/module_ao/ORB_nonlocal.h
+++ b/source/source_basis/module_ao/ORB_nonlocal.h
@@ -1,7 +1,6 @@
 #ifndef NUMERICAL_NONLOCAL_H
 #define NUMERICAL_NONLOCAL_H
 
-#include "source_base/complexarray.h"
 #include "source_base/complexmatrix.h"
 #include "ORB_nonlocal_lm.h"
 /**
diff --git a/source/source_basis/module_ao/ORB_read.h b/source/source_basis/module_ao/ORB_read.h
index efb4d532b16..6ee794c080a 100644
--- a/source/source_basis/module_ao/ORB_read.h
+++ b/source/source_basis/module_ao/ORB_read.h
@@ -3,7 +3,6 @@
 
 #include "ORB_atomic.h"
 #include "ORB_atomic_lm.h"
-#include "ORB_nonlocal.h"
 
 ////////////////////////////////////////////////////////////
 /// advices for reconstructions:
diff --git a/source/source_basis/module_nao/two_center_table.h b/source/source_basis/module_nao/two_center_table.h
index 6240ce84292..dc977872194 100644
--- a/source/source_basis/module_nao/two_center_table.h
+++ b/source/source_basis/module_nao/two_center_table.h
@@ -2,7 +2,6 @@
 #define TWO_CENTER_TABLE_H
 
 #include <ATen/tensor.h>
-#include "source_base/spherical_bessel_transformer.h"
 #include "source_basis/module_nao/radial_collection.h"
 
 class TwoCenterTable
diff --git a/source/source_basis/module_pw/pw_basis_sup.h b/source/source_basis/module_pw/pw_basis_sup.h
index 9e6ada0054a..b77dfa6bec0 100644
--- a/source/source_basis/module_pw/pw_basis_sup.h
+++ b/source/source_basis/module_pw/pw_basis_sup.h
@@ -1,7 +1,6 @@
 #ifndef PWBASIS_SUP_H
 #define PWBASIS_SUP_H
 
-#include "source_base/complexmatrix.h"
 
 namespace ModulePW
 {
diff --git a/source/source_basis/module_pw/test/test-other.cpp b/source/source_basis/module_pw/test/test-other.cpp
index b81787f16d8..e6efa90654a 100644
--- a/source/source_basis/module_pw/test/test-other.cpp
+++ b/source/source_basis/module_pw/test/test-other.cpp
@@ -140,7 +140,6 @@ TEST_F(PWTEST,test_other)
     fftwf_cleanup();
 #endif
 }
-
 TEST_F(PWTEST, test_no_plane_wave_message_global_empty_k)
 {
     ModulePW::PW_Basis_K pwktest(device_flag, precision_flag);
@@ -201,4 +200,4 @@ TEST_F(PWTEST, test_no_plane_wave_message_parallel_local_empty)
                     testing::HasSubstr("Current core has no plane waves! Please reduce the cores."));
     }
 #endif
-}
\ No newline at end of file
+}
diff --git a/source/source_cell/atom_pseudo.h b/source/source_cell/atom_pseudo.h
index 9f04e0861a3..8f78a64dff2 100644
--- a/source/source_cell/atom_pseudo.h
+++ b/source/source_cell/atom_pseudo.h
@@ -1,9 +1,7 @@
 #ifndef ATOM_PSEUDO_H
 #define ATOM_PSEUDO_H
 
-#include "source_base/global_variable.h"
 #include "source_base/vector3.h"
-#include "source_io/module_output/output.h"
 #include "source_base/complexarray.h"
 #include "source_base/complexmatrix.h"
 #include "pseudo.h"
diff --git a/source/source_cell/atom_spec.cpp b/source/source_cell/atom_spec.cpp
index 82645d079e0..5c989191620 100644
--- a/source/source_cell/atom_spec.cpp
+++ b/source/source_cell/atom_spec.cpp
@@ -1,5 +1,6 @@
 #include "atom_spec.h"
 #include "source_io/module_parameter/parameter.h"
+#include "source_io/module_output/output.h"
 #include <cstdlib>
 
 Atom::Atom()
diff --git a/source/source_cell/atom_spec.h b/source/source_cell/atom_spec.h
index 3ee18d39716..96730b00de1 100644
--- a/source/source_cell/atom_spec.h
+++ b/source/source_cell/atom_spec.h
@@ -1,7 +1,6 @@
 #ifndef ATOM_H
 #define ATOM_H
 
-#include "../source_io/module_output/output.h"
 #include "atom_pseudo.h"
 class Atom
 {
diff --git a/source/source_cell/k_vector_utils.h b/source/source_cell/k_vector_utils.h
index 188a621523f..624012b7d31 100644
--- a/source/source_cell/k_vector_utils.h
+++ b/source/source_cell/k_vector_utils.h
@@ -5,7 +5,6 @@
 #ifndef K_VECTOR_UTILS_H
 #define K_VECTOR_UTILS_H
 
-#include "source_base/global_variable.h"
 #include "source_base/matrix3.h"
 #include "source_cell/unitcell.h"
 
diff --git a/source/source_cell/klist.h b/source/source_cell/klist.h
index 46fa51be499..4960ac68463 100644
--- a/source/source_cell/klist.h
+++ b/source/source_cell/klist.h
@@ -2,7 +2,6 @@
 #define K_VECTORS_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix3.h"
 #include "source_cell/unitcell.h"
 #include "parallel_kpoints.h"
diff --git a/source/source_cell/module_neighbor/sltk_atom.h b/source/source_cell/module_neighbor/sltk_atom.h
index 94406417ae2..a21055f3f5c 100644
--- a/source/source_cell/module_neighbor/sltk_atom.h
+++ b/source/source_cell/module_neighbor/sltk_atom.h
@@ -2,8 +2,6 @@
 #define INCLUDE_FATOM
 
 #include <memory>
-#include "sltk_util.h"
-#include "source_base/timer.h"
 #include <vector>
 
 // a class contains the atom position, 
diff --git a/source/source_cell/module_neighbor/sltk_atom_arrange.h b/source/source_cell/module_neighbor/sltk_atom_arrange.h
index 5dd1c94f98c..2fdd5fc469e 100644
--- a/source/source_cell/module_neighbor/sltk_atom_arrange.h
+++ b/source/source_cell/module_neighbor/sltk_atom_arrange.h
@@ -1,7 +1,6 @@
 #ifndef ATOM_ARRANGE_H
 #define ATOM_ARRANGE_H
 
-#include "sltk_grid.h"
 #include "sltk_grid_driver.h"
 
 
diff --git a/source/source_cell/module_neighbor/sltk_grid.h b/source/source_cell/module_neighbor/sltk_grid.h
index b5c3e836295..4b2da582800 100644
--- a/source/source_cell/module_neighbor/sltk_grid.h
+++ b/source/source_cell/module_neighbor/sltk_grid.h
@@ -3,7 +3,6 @@
 
 #include "source_cell/unitcell.h"
 #include "sltk_atom.h"
-#include "sltk_util.h"
 
 #include <functional>
 #include <stdexcept>
diff --git a/source/source_cell/module_neighbor/sltk_grid_driver.h b/source/source_cell/module_neighbor/sltk_grid_driver.h
index 9576617f59d..95db2d85c29 100644
--- a/source/source_cell/module_neighbor/sltk_grid_driver.h
+++ b/source/source_cell/module_neighbor/sltk_grid_driver.h
@@ -2,11 +2,8 @@
 #define GRID_DRIVER_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/vector3.h"
 #include "source_cell/unitcell.h"
-#include "source_pw/module_pwdft/structure_factor.h"
-#include "sltk_atom.h"
 #include "sltk_grid.h"
 
 #include <memory>
diff --git a/source/source_cell/module_symmetry/symm_analysis.cpp b/source/source_cell/module_symmetry/symm_analysis.cpp
index 208efa53084..16bd470ff33 100644
--- a/source/source_cell/module_symmetry/symm_analysis.cpp
+++ b/source/source_cell/module_symmetry/symm_analysis.cpp
@@ -1,5 +1,6 @@
 #include "symmetry.h"
 #include "source_io/module_parameter/parameter.h"
+#include "source_io/module_output/output.h"
 
 using namespace ModuleSymmetry;
 
diff --git a/source/source_cell/module_symmetry/symmetry.h b/source/source_cell/module_symmetry/symmetry.h
index 7fe03cb5390..cd95d3ce011 100644
--- a/source/source_cell/module_symmetry/symmetry.h
+++ b/source/source_cell/module_symmetry/symmetry.h
@@ -6,7 +6,6 @@
 #include "source_base/timer.h"
 #include "source_base/mathzone.h"
 #include "source_base/constants.h"
-#include "source_io/module_output/output.h"
 #include "symmetry_basic.h"
 
 namespace ModuleSymmetry
diff --git a/source/source_cell/module_symmetry/test/symmetry_test_analysis.cpp b/source/source_cell/module_symmetry/test/symmetry_test_analysis.cpp
index c2947eb3bee..1ca197c032d 100644
--- a/source/source_cell/module_symmetry/test/symmetry_test_analysis.cpp
+++ b/source/source_cell/module_symmetry/test/symmetry_test_analysis.cpp
@@ -1,4 +1,5 @@
 #include "symmetry_test_cases.h"
+#include "source_io/module_output/output.h"
 #include "mpi.h"
 /************************************************
  *  unit test of class Symmetry
diff --git a/source/source_cell/module_symmetry/test/symmetry_test_symtrz.cpp b/source/source_cell/module_symmetry/test/symmetry_test_symtrz.cpp
index 08ee783972d..45ea873e3f7 100644
--- a/source/source_cell/module_symmetry/test/symmetry_test_symtrz.cpp
+++ b/source/source_cell/module_symmetry/test/symmetry_test_symtrz.cpp
@@ -1,4 +1,5 @@
 #include "symmetry_test_cases.h"
+#include "source_io/module_output/output.h"
 #include "mpi.h"
 
 /************************************************
diff --git a/source/source_cell/pseudo.cpp b/source/source_cell/pseudo.cpp
index d2025768212..70785839f2d 100644
--- a/source/source_cell/pseudo.cpp
+++ b/source/source_cell/pseudo.cpp
@@ -1,5 +1,6 @@
 #include "pseudo.h"
 #include "source_base/tool_title.h"
+#include "source_io/module_output/output.h"
 #include <cstdint>
 
 pseudo::pseudo()
diff --git a/source/source_cell/pseudo.h b/source/source_cell/pseudo.h
index abd5be8475b..11dee21af36 100644
--- a/source/source_cell/pseudo.h
+++ b/source/source_cell/pseudo.h
@@ -3,7 +3,8 @@
 
 #include <cstdint>
 #include "source_base/global_function.h"
-#include "source_io/module_output/output.h"
+#include "source_base/matrix.h"
+#include "source_base/realarray.h"
 
 //-----------------------------------------
 // read in pseudopotentials
diff --git a/source/source_cell/setup_nonlocal.h b/source/source_cell/setup_nonlocal.h
index 4ac214c97e2..b9a3ad9ea4b 100644
--- a/source/source_cell/setup_nonlocal.h
+++ b/source/source_cell/setup_nonlocal.h
@@ -2,8 +2,6 @@
 #define INFONONLOCAL_H
 
 #include "atom_spec.h"
-#include "../source_base/global_function.h"
-#include "../source_base/global_variable.h"
 #include "../source_basis/module_ao/ORB_nonlocal.h"
 #include "../source_basis/module_ao/ORB_read.h"
 class InfoNonlocal
diff --git a/source/source_cell/test/read_atoms_helper_test.cpp b/source/source_cell/test/read_atoms_helper_test.cpp
index 1cd80847840..39336cd4a0c 100644
--- a/source/source_cell/test/read_atoms_helper_test.cpp
+++ b/source/source_cell/test/read_atoms_helper_test.cpp
@@ -3,6 +3,7 @@
 #include "../read_atoms_helper.h"
 #include "source_base/vector3.h"
 #include "source_base/matrix3.h"
+#include "source_io/module_output/output.h"
 #include <sstream>
 #include <fstream>
 
diff --git a/source/source_cell/test/unitcell_test_readpp.cpp b/source/source_cell/test/unitcell_test_readpp.cpp
index f0cf7c35390..77ab7a21a8b 100644
--- a/source/source_cell/test/unitcell_test_readpp.cpp
+++ b/source/source_cell/test/unitcell_test_readpp.cpp
@@ -8,6 +8,7 @@
 #include "source_base/mathzone.h"
 #include "source_cell/check_atomic_stru.h"
 #include "source_cell/unitcell.h"
+#include "source_estate/cal_nelec_nband.h"
 #include "source_estate/read_pseudo.h"
 #include <valarray>
 #include <vector>
diff --git a/source/source_cell/unitcell.cpp b/source/source_cell/unitcell.cpp
index a4966530074..f2c15102748 100644
--- a/source/source_cell/unitcell.cpp
+++ b/source/source_cell/unitcell.cpp
@@ -7,6 +7,7 @@
 #include "unitcell.h"
 #include "bcast_cell.h"
 #include "source_base/tool_quit.h"
+#include "source_io/module_output/output.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_cell/read_stru.h"
 #include "source_base/atom_in.h"
diff --git a/source/source_cell/unitcell.h b/source/source_cell/unitcell.h
index 3292a40a065..e2256b78363 100644
--- a/source/source_cell/unitcell.h
+++ b/source/source_cell/unitcell.h
@@ -2,14 +2,11 @@
 #define UNITCELL_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_cell/sep_cell.h"
 #include "source_estate/magnetism.h"
-#include "source_io/module_output/output.h"
 #include "module_symmetry/symmetry.h"
 
 #ifdef __LCAO
-#include "source_basis/module_ao/ORB_read.h"
 #include "setup_nonlocal.h"
 #endif
 
diff --git a/source/source_cell/update_cell.cpp b/source/source_cell/update_cell.cpp
index 8e2efaa04e2..4da4013d6af 100644
--- a/source/source_cell/update_cell.cpp
+++ b/source/source_cell/update_cell.cpp
@@ -1,6 +1,7 @@
 #include "update_cell.h"
 #include "bcast_cell.h"
 #include "source_base/global_function.h"
+#include "source_io/module_output/output.h"
 
 namespace unitcell
 {
diff --git a/source/source_esolver/esolver.cpp b/source/source_esolver/esolver.cpp
index 4809c6df776..e22b2f911e3 100644
--- a/source/source_esolver/esolver.cpp
+++ b/source/source_esolver/esolver.cpp
@@ -12,10 +12,7 @@
 #include "esolver_ks_lcao_tddft.h"
 #include "esolver_ks_lcaopw.h"
 #include "source_lcao/module_lr/esolver_lrtd_lcao.h"
-extern "C"
-{
 #include "source_base/module_external/blacs_connector.h"
-}
 #endif
 #include "esolver_dp.h"
 #include "esolver_nep.h"
diff --git a/source/source_esolver/esolver.h b/source/source_esolver/esolver.h
index dd621cfe155..d1f2b1ae782 100644
--- a/source/source_esolver/esolver.h
+++ b/source/source_esolver/esolver.h
@@ -3,7 +3,8 @@
 
 #include "source_base/matrix.h"
 #include "source_cell/unitcell.h"
-#include "source_io/module_parameter/parameter.h"
+
+struct Input_para;
 
 namespace ModuleESolver
 {
diff --git a/source/source_esolver/esolver_double_xc.cpp b/source/source_esolver/esolver_double_xc.cpp
index d1acaf83f03..14a86779edc 100644
--- a/source/source_esolver/esolver_double_xc.cpp
+++ b/source/source_esolver/esolver_double_xc.cpp
@@ -5,6 +5,7 @@
 #ifdef __MLALGO
 #include "source_lcao/module_deepks/LCAO_deepks.h"
 #include "source_lcao/module_deepks/LCAO_deepks_interface.h"
+#include "source_lcao/module_deepks/LCAO_deepks_io.h"
 #endif
 #include "source_lcao/FORCE_STRESS.h"
 
diff --git a/source/source_esolver/esolver_dp.cpp b/source/source_esolver/esolver_dp.cpp
index b59769f3ef5..879193e668b 100644
--- a/source/source_esolver/esolver_dp.cpp
+++ b/source/source_esolver/esolver_dp.cpp
@@ -18,6 +18,7 @@
  * @date 2023-05-15
  */
 #include "esolver_dp.h"
+#include "source_io/module_parameter/parameter.h"
 
 #include "source_base/parallel_common.h"
 #include "source_base/timer.h"
diff --git a/source/source_esolver/esolver_fp.h b/source/source_esolver/esolver_fp.h
index 59fd79a9943..501bef9b681 100644
--- a/source/source_esolver/esolver_fp.h
+++ b/source/source_esolver/esolver_fp.h
@@ -6,7 +6,6 @@
 #include "source_base/timer_wrapper.h"
 
 #include "source_basis/module_pw/pw_basis.h" // plane wave basis
-#include "source_cell/module_symmetry/symmetry.h" // symmetry analysis
 #include "source_estate/elecstate.h" // electronic states
 #include "source_estate/module_charge/charge_extra.h" // charge extrapolation
 #include "source_hamilt/module_surchem/surchem.h" // solvation model
diff --git a/source/source_esolver/esolver_ks.h b/source/source_esolver/esolver_ks.h
index b6affc7b0c7..c480d238ad1 100644
--- a/source/source_esolver/esolver_ks.h
+++ b/source/source_esolver/esolver_ks.h
@@ -8,6 +8,7 @@
 #include "source_hamilt/hamilt.h" // use Hamiltonian
 #include "source_hamilt/hamilt_base.h" // use Hamiltonian base class
 #include "source_lcao/module_dftu/dftu.h" // mohan add 20251107
+#include "source_pw/module_pwdft/vnl_pw.h"
 
 namespace ModuleESolver
 {
diff --git a/source/source_esolver/esolver_ks_lcao.cpp b/source/source_esolver/esolver_ks_lcao.cpp
index dd6201bd0b7..9d3906d6ebf 100644
--- a/source/source_esolver/esolver_ks_lcao.cpp
+++ b/source/source_esolver/esolver_ks_lcao.cpp
@@ -1,4 +1,6 @@
 #include "esolver_ks_lcao.h"
+#include "source_base/module_external/blacs_connector.h"
+#include "source_cell/module_neighbor/sltk_atom_arrange.h"
 #include "source_estate/elecstate_tools.h"
 #include "source_lcao/module_deltaspin/spin_constrain.h"
 #include "source_lcao/module_deltaspin/deltaspin_lcao.h"
diff --git a/source/source_esolver/esolver_ks_lcao_tddft.cpp b/source/source_esolver/esolver_ks_lcao_tddft.cpp
index 130fc94139f..61e43797e13 100644
--- a/source/source_esolver/esolver_ks_lcao_tddft.cpp
+++ b/source/source_esolver/esolver_ks_lcao_tddft.cpp
@@ -1,4 +1,5 @@
 #include "esolver_ks_lcao_tddft.h"
+#include "source_lcao/module_rt/boundary_fix.h"
 
 //----------------IO-----------------
 #include "source_io/module_ctrl/ctrl_output_td.h"
diff --git a/source/source_esolver/esolver_ks_lcao_tddft.h b/source/source_esolver/esolver_ks_lcao_tddft.h
index b4227a9ab7d..07b049b9fbb 100644
--- a/source/source_esolver/esolver_ks_lcao_tddft.h
+++ b/source/source_esolver/esolver_ks_lcao_tddft.h
@@ -3,8 +3,6 @@
 #include "esolver_ks.h"
 #include "esolver_ks_lcao.h"
 #include "source_base/module_container/ATen/core/tensor.h" // ct::Tensor
-#include "source_lcao/module_rt/boundary_fix.h"
-#include "source_lcao/module_rt/gather_mat.h" // MPI gathering and distributing functions
 #include "source_lcao/module_rt/kernels/cublasmp_context.h"
 #include "source_lcao/module_rt/td_info.h"
 #include "source_lcao/module_rt/td_moving_gauge.h"
diff --git a/source/source_esolver/esolver_ks_pw.h b/source/source_esolver/esolver_ks_pw.h
index 227aaeea254..9fd2600ce37 100644
--- a/source/source_esolver/esolver_ks_pw.h
+++ b/source/source_esolver/esolver_ks_pw.h
@@ -4,7 +4,6 @@
 #include "source_psi/setup_psi_pw.h" // mohan add 20251012
 #include "source_pw/module_pwdft/vsep_pw.h"
 #include "source_pw/module_pwdft/exx_helper_base.h"
-#include "source_pw/module_pwdft/op_pw_vel.h"
 
 #include <memory>
 #include <source_base/macros.h>
diff --git a/source/source_esolver/esolver_nep.cpp b/source/source_esolver/esolver_nep.cpp
index 1f9605b6207..8944776aaa6 100644
--- a/source/source_esolver/esolver_nep.cpp
+++ b/source/source_esolver/esolver_nep.cpp
@@ -16,6 +16,7 @@
  * @date 2025-10-10
  */
 #include "esolver_nep.h"
+#include "source_io/module_parameter/parameter.h"
 
 #include "source_base/parallel_common.h"
 #include "source_base/timer.h"
diff --git a/source/source_esolver/test/esolver_dp_test.cpp b/source/source_esolver/test/esolver_dp_test.cpp
index 5010c9ccf42..f25b89ab755 100644
--- a/source/source_esolver/test/esolver_dp_test.cpp
+++ b/source/source_esolver/test/esolver_dp_test.cpp
@@ -5,6 +5,7 @@
 #define private public
 #define protected public
 #include "../esolver_dp.h"
+#include "source_io/module_parameter/input_parameter.h"
 #undef private
 /************************************************
  *  unit tests of class ESolver_DP
diff --git a/source/source_estate/cal_wfc.cpp b/source/source_estate/cal_wfc.cpp
index ff069397a03..846ac965bb0 100644
--- a/source/source_estate/cal_wfc.cpp
+++ b/source/source_estate/cal_wfc.cpp
@@ -1,5 +1,7 @@
 #include "read_pseudo.h"
 
+#include "source_io/module_parameter/parameter.h"
+
 namespace elecstate
 {
     void cal_nwfc(std::ofstream& log,UnitCell& ucell,Atom* atoms) 
diff --git a/source/source_estate/elecstate_energy.cpp b/source/source_estate/elecstate_energy.cpp
index a0bc403cd5a..3c58360b902 100644
--- a/source/source_estate/elecstate_energy.cpp
+++ b/source/source_estate/elecstate_energy.cpp
@@ -1,5 +1,6 @@
 #include "elecstate.h"
 #include "source_base/global_variable.h"
+#include "source_base/parallel_comm.h"
 #include "source_base/parallel_reduce.h"
 #include "source_hamilt/module_xc/xc_functional.h"
 #include "source_io/module_parameter/parameter.h"
diff --git a/source/source_estate/elecstate_energy_terms.cpp b/source/source_estate/elecstate_energy_terms.cpp
index c7bb4b55a51..ebe0068c27b 100644
--- a/source/source_estate/elecstate_energy_terms.cpp
+++ b/source/source_estate/elecstate_energy_terms.cpp
@@ -1,4 +1,5 @@
 #include "elecstate.h"
+#include "source_base/parallel_reduce.h"
 #include "source_estate/module_pot/H_Hartree_pw.h"
 #include "source_estate/module_pot/efield.h"
 #include "source_estate/module_pot/gatefield.h"
diff --git a/source/source_estate/elecstate_pw.cpp b/source/source_estate/elecstate_pw.cpp
index 19047491194..de05d441b58 100644
--- a/source/source_estate/elecstate_pw.cpp
+++ b/source/source_estate/elecstate_pw.cpp
@@ -8,6 +8,7 @@
 #include "source_base/timer.h"
 #include "source_hamilt/module_xc/xc_functional.h"
 #include "source_io/module_parameter/parameter.h"
+#include "source_pw/module_pwdft/vnl_pw.h"
 
 namespace elecstate {
 
diff --git a/source/source_estate/elecstate_pw.h b/source/source_estate/elecstate_pw.h
index f674beed892..e8e4b95af36 100644
--- a/source/source_estate/elecstate_pw.h
+++ b/source/source_estate/elecstate_pw.h
@@ -9,6 +9,8 @@
 #include "source_pw/module_pwdft/kernels/meta_op.h"
 #include "source_base/kernels/math_kernel_op.h"
 
+class pseudopot_cell_vnl;
+
 namespace elecstate
 {
 
diff --git a/source/source_estate/elecstate_tools.cpp b/source/source_estate/elecstate_tools.cpp
index 4a4c24e3cfc..3076c6b437e 100644
--- a/source/source_estate/elecstate_tools.cpp
+++ b/source/source_estate/elecstate_tools.cpp
@@ -1,5 +1,6 @@
 #include "elecstate_tools.h"
 #include "occupy.h"
+#include "source_base/parallel_reduce.h"
 namespace elecstate
 {
     void calEBand(const ModuleBase::matrix& ekb,const ModuleBase::matrix& wg,fenergy& f_en)
diff --git a/source/source_estate/kernels/elecstate_op.h b/source/source_estate/kernels/elecstate_op.h
index 70cfcbb2ed2..f7b8d48c2ee 100644
--- a/source/source_estate/kernels/elecstate_op.h
+++ b/source/source_estate/kernels/elecstate_op.h
@@ -1,6 +1,5 @@
 // TODO: This is a temperary location for these functions.
 // And will be moved to a global module(module base) later.
-#include "source_io/module_parameter/parameter.h"
 #ifndef source_estate_ELECSTATE_MULTI_DEVICE_H
 #define source_estate_ELECSTATE_MULTI_DEVICE_H
 #include <complex>
diff --git a/source/source_estate/magnetism.h b/source/source_estate/magnetism.h
index 061ec415e79..b2cee2d6a95 100644
--- a/source/source_estate/magnetism.h
+++ b/source/source_estate/magnetism.h
@@ -2,7 +2,6 @@
 #define MAGNETISM_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/vector3.h"
 
 class Magnetism
diff --git a/source/source_estate/module_charge/charge.h b/source/source_estate/module_charge/charge.h
index 79a5f5ca9e5..e50f5eed535 100644
--- a/source/source_estate/module_charge/charge.h
+++ b/source/source_estate/module_charge/charge.h
@@ -4,7 +4,6 @@
 #include "source_base/complexmatrix.h"
 #include "source_base/global_function.h"
 #include "source_base/global_variable.h"
-#include "source_base/parallel_global.h"
 #include "source_basis/module_pw/pw_basis.h"
 #include "source_cell/module_symmetry/symmetry.h"
 // #include "source_estate/fp_energy.h"
diff --git a/source/source_estate/module_charge/charge_mpi.cpp b/source/source_estate/module_charge/charge_mpi.cpp
index e9c229897b8..02271f54d6c 100644
--- a/source/source_estate/module_charge/charge_mpi.cpp
+++ b/source/source_estate/module_charge/charge_mpi.cpp
@@ -1,6 +1,7 @@
 #include "charge.h"
 #include "source_base/global_function.h"
 #include "source_base/global_variable.h"
+#include "source_base/parallel_comm.h"
 #include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_hamilt/module_xc/xc_functional.h"
diff --git a/source/source_estate/module_dm/cal_dm_psi.h b/source/source_estate/module_dm/cal_dm_psi.h
index da78fc179d7..09ab3d3974a 100644
--- a/source/source_estate/module_dm/cal_dm_psi.h
+++ b/source/source_estate/module_dm/cal_dm_psi.h
@@ -2,6 +2,7 @@
 #define CAL_DM_PSI_H
 
 #include "source_base/matrix.h"
+#include "source_psi/psi.h"
 #include "density_matrix.h"
 
 namespace elecstate
diff --git a/source/source_estate/module_pot/H_Hartree_pw.h b/source/source_estate/module_pot/H_Hartree_pw.h
index 7973966033b..c5ca6bdd0b5 100644
--- a/source/source_estate/module_pot/H_Hartree_pw.h
+++ b/source/source_estate/module_pot/H_Hartree_pw.h
@@ -2,7 +2,6 @@
 #define HHARTREEPW_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_cell/unitcell.h"
 #include "source_basis/module_pw/pw_basis.h"
diff --git a/source/source_estate/module_pot/H_TDDFT_pw.h b/source/source_estate/module_pot/H_TDDFT_pw.h
index fc25f510bd5..4565cd000ff 100644
--- a/source/source_estate/module_pot/H_TDDFT_pw.h
+++ b/source/source_estate/module_pot/H_TDDFT_pw.h
@@ -2,8 +2,7 @@
 #define H_TDDFT_PW_H
 
 #include "pot_base.h"
-#include "source_io/module_parameter/input_conv.h"
-#include "source_io/module_parameter/parameter.h" // PARAM.globalv.global_readin_dir, PARAM.inp.mdp.md_restart
+#include "source_io/module_parameter/parameter.h"
 
 namespace elecstate
 {
diff --git a/source/source_estate/module_pot/pot_ml_exx.h b/source/source_estate/module_pot/pot_ml_exx.h
index fa95bb90d07..5936add9050 100644
--- a/source/source_estate/module_pot/pot_ml_exx.h
+++ b/source/source_estate/module_pot/pot_ml_exx.h
@@ -1,11 +1,9 @@
 #ifndef POT_ML_EXX_H
 #define POT_ML_EXX_H
-#include "source_io/module_parameter/parameter.h"
 
 #ifdef __MLALGO
 
 #include "pot_base.h"
-#include "source_pw/module_ofdft/nn_of.h"
 #include "source_io/module_ml/cal_mlkedf_descriptors.h"
 #include "source_pw/module_ofdft/ml_base.h"
 
diff --git a/source/source_estate/module_pot/pot_xc.h b/source/source_estate/module_pot/pot_xc.h
index bf1cf837d85..47243c633d7 100644
--- a/source/source_estate/module_pot/pot_xc.h
+++ b/source/source_estate/module_pot/pot_xc.h
@@ -1,7 +1,6 @@
 #ifndef POTXC_H
 #define POTXC_H
 
-#include "source_hamilt/module_xc/xc_functional.h"
 #include "pot_base.h"
 
 namespace elecstate
diff --git a/source/source_estate/module_pot/potential_new.h b/source/source_estate/module_pot/potential_new.h
index 5b888e7d8ba..ca79ca02f63 100644
--- a/source/source_estate/module_pot/potential_new.h
+++ b/source/source_estate/module_pot/potential_new.h
@@ -3,7 +3,6 @@
 
 #include "source_base/complexmatrix.h"
 #include "source_hamilt/module_surchem/surchem.h"
-#include "source_pw/module_pwdft/vnl_pw.h"
 #include "source_pw/module_pwdft/vsep_pw.h"
 #include "source_pw/module_pwdft/structure_factor.h"
 #include "pot_base.h"
diff --git a/source/source_estate/occupy.h b/source/source_estate/occupy.h
index 627103fcab6..24626e0d161 100644
--- a/source/source_estate/occupy.h
+++ b/source/source_estate/occupy.h
@@ -2,7 +2,6 @@
 #define OCCUPY_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/vector3.h"
 
diff --git a/source/source_estate/read_pseudo.cpp b/source/source_estate/read_pseudo.cpp
index 05c4c0f649c..c348635dde9 100644
--- a/source/source_estate/read_pseudo.cpp
+++ b/source/source_estate/read_pseudo.cpp
@@ -1,6 +1,7 @@
 #include "read_pseudo.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/global_file.h"
+#include "source_cell/cal_atoms_info.h"
 #include "source_cell/read_pp.h"
 #include "source_cell/bcast_cell.h"
 #include "source_base/element_elec_config.h"
diff --git a/source/source_estate/read_pseudo.h b/source/source_estate/read_pseudo.h
index e244697eb32..b42d81d439b 100644
--- a/source/source_estate/read_pseudo.h
+++ b/source/source_estate/read_pseudo.h
@@ -2,7 +2,6 @@
 #define READ_PSEUDO_H
 
 #include "source_cell/unitcell.h"
-#include "source_cell/cal_atoms_info.h"
 
 namespace elecstate {
 
diff --git a/source/source_estate/setup_estate_pw.cpp b/source/source_estate/setup_estate_pw.cpp
index 3ca02d79e67..654969faa9f 100644
--- a/source/source_estate/setup_estate_pw.cpp
+++ b/source/source_estate/setup_estate_pw.cpp
@@ -2,6 +2,7 @@
 #include "source_estate/elecstate_pw.h"
 #include "source_estate/elecstate_pw_sdft.h"
 #include "source_estate/elecstate_tools.h"
+#include "source_pw/module_pwdft/vnl_pw.h"
 
 namespace elecstate
 {
diff --git a/source/source_estate/setup_estate_pw.h b/source/source_estate/setup_estate_pw.h
index cd1a388a743..03e994369ae 100644
--- a/source/source_estate/setup_estate_pw.h
+++ b/source/source_estate/setup_estate_pw.h
@@ -1,7 +1,6 @@
 #ifndef SETUP_ESTATE_PW_H
 #define SETUP_ESTATE_PW_H
 
-#include "source_base/module_device/device.h"
 #include "source_cell/unitcell.h"
 #include "source_cell/klist.h"
 #include "source_pw/module_pwdft/structure_factor.h"
@@ -9,6 +8,8 @@
 #include "source_pw/module_pwdft/vl_pw.h"
 #include "source_pw/module_pwdft/vsep_pw.h"
 
+class pseudopot_cell_vnl;
+
 namespace elecstate
 {
 
diff --git a/source/source_estate/test/elecstate_pw_test.cpp b/source/source_estate/test/elecstate_pw_test.cpp
index c71a38002e1..c4e57298409 100644
--- a/source/source_estate/test/elecstate_pw_test.cpp
+++ b/source/source_estate/test/elecstate_pw_test.cpp
@@ -5,8 +5,13 @@
 #define private public
 #define protected public
 #include "source_estate/elecstate_pw.h"
+#ifdef __LCAO
+#include "source_basis/module_ao/ORB_gaunt_table.h"
+#endif
 #include "source_hamilt/module_xc/xc_functional.h"
 #include "source_pw/module_pwdft/vl_pw.h"
+#include "source_pw/module_pwdft/vnl_pw.h"
+#include "source_pw/module_pwdft/soc.h"
 #include "source_io/module_parameter/parameter.h"
 // mock functions for testing
 int XC_Functional::func_type = 1;
diff --git a/source/source_hamilt/module_ewald/H_Ewald_pw.cpp b/source/source_hamilt/module_ewald/H_Ewald_pw.cpp
index 488a74ef0be..0f4c7776d70 100644
--- a/source/source_hamilt/module_ewald/H_Ewald_pw.cpp
+++ b/source/source_hamilt/module_ewald/H_Ewald_pw.cpp
@@ -1,4 +1,5 @@
 #include "H_Ewald_pw.h"
+#include "source_base/parallel_comm.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/mymath.h" // use heapsort
 #include "source_io/module_parameter/parameter.h"
diff --git a/source/source_hamilt/module_ewald/H_Ewald_pw.h b/source/source_hamilt/module_ewald/H_Ewald_pw.h
index 42a931e10aa..64143c8aa83 100644
--- a/source/source_hamilt/module_ewald/H_Ewald_pw.h
+++ b/source/source_hamilt/module_ewald/H_Ewald_pw.h
@@ -2,11 +2,8 @@
 #define H_EWALD_PW_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_cell/unitcell.h"
 #include "source_basis/module_pw/pw_basis.h"
-#include "source_pw/module_pwdft/forces.h"
-#include "source_pw/module_pwdft/stress_func.h"
 
 class H_Ewald_pw 
 {
diff --git a/source/source_hamilt/module_surchem/cal_vcav.cpp b/source/source_hamilt/module_surchem/cal_vcav.cpp
index 46bea1d8b45..9a56953b6a3 100644
--- a/source/source_hamilt/module_surchem/cal_vcav.cpp
+++ b/source/source_hamilt/module_surchem/cal_vcav.cpp
@@ -1,4 +1,5 @@
 #include "source_base/timer.h"
+#include "source_base/parallel_reduce.h"
 #include "source_hamilt/module_xc/xc_functional.h"
 #include "source_io/module_parameter/parameter.h"
 #include "surchem.h"
diff --git a/source/source_hamilt/module_surchem/cal_vel.cpp b/source/source_hamilt/module_surchem/cal_vel.cpp
index d7281172d46..14b148a0f0d 100644
--- a/source/source_hamilt/module_surchem/cal_vel.cpp
+++ b/source/source_hamilt/module_surchem/cal_vel.cpp
@@ -1,4 +1,5 @@
 #include "source_base/timer.h"
+#include "source_base/parallel_reduce.h"
 #include "source_hamilt/module_xc/xc_functional.h"
 #include "source_io/module_parameter/parameter.h"
 #include "surchem.h"
diff --git a/source/source_hamilt/module_surchem/sol_force.cpp b/source/source_hamilt/module_surchem/sol_force.cpp
index 4c032328048..8c5e6b6096b 100644
--- a/source/source_hamilt/module_surchem/sol_force.cpp
+++ b/source/source_hamilt/module_surchem/sol_force.cpp
@@ -1,4 +1,5 @@
 #include "surchem.h"
+#include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_io/module_parameter/parameter.h"
 
diff --git a/source/source_hamilt/module_surchem/surchem.h b/source/source_hamilt/module_surchem/surchem.h
index b272d0f70e5..c792414ca61 100644
--- a/source/source_hamilt/module_surchem/surchem.h
+++ b/source/source_hamilt/module_surchem/surchem.h
@@ -3,9 +3,7 @@
 
 #include "source_base/atom_in.h"
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
-#include "source_base/parallel_reduce.h"
 #include "source_basis/module_pw/pw_basis.h"
 #include "source_cell/unitcell.h"
 #include "source_pw/module_pwdft/parallel_grid.h"
diff --git a/source/source_hamilt/module_xc/exx_info.h b/source/source_hamilt/module_xc/exx_info.h
index 1d5c5ede4e8..66e4a9d4f67 100644
--- a/source/source_hamilt/module_xc/exx_info.h
+++ b/source/source_hamilt/module_xc/exx_info.h
@@ -2,7 +2,6 @@
 #define EXX_INFO_H
 
 #include "source_lcao/module_ri/conv_coulomb_pot_k.h"
-#include "xc_functional.h"
 
 #include <vector>
 #include <map>
diff --git a/source/source_hamilt/module_xc/xc_functional.h b/source/source_hamilt/module_xc/xc_functional.h
index 86dcb4049d7..a311d28d8a0 100644
--- a/source/source_hamilt/module_xc/xc_functional.h
+++ b/source/source_hamilt/module_xc/xc_functional.h
@@ -12,7 +12,6 @@
 #endif	// ifdef USE_LIBXC
 #include "source_base/macros.h"
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/vector3.h"
 #include "source_base/matrix.h"
 #include "source_basis/module_pw/pw_basis_k.h"
diff --git a/source/source_hamilt/operator.cpp b/source/source_hamilt/operator.cpp
index 86f83827644..dba9367f055 100644
--- a/source/source_hamilt/operator.cpp
+++ b/source/source_hamilt/operator.cpp
@@ -1,6 +1,7 @@
 #include "operator.h"
 
 #include "source_base/timer.h"
+#include "source_base/tool_quit.h"
 
 using namespace hamilt;
 
diff --git a/source/source_hamilt/operator.h b/source/source_hamilt/operator.h
index 4198220a020..5264b47ba19 100644
--- a/source/source_hamilt/operator.h
+++ b/source/source_hamilt/operator.h
@@ -1,8 +1,6 @@
 #ifndef OPERATOR_H
 #define OPERATOR_H
 
-#include "source_base/global_function.h"
-#include "source_base/tool_quit.h"
 #include "source_psi/psi.h"
 
 #include <complex>
diff --git a/source/source_hsolver/diag_hs_para.cpp b/source/source_hsolver/diag_hs_para.cpp
index 8feac1a39a0..74dc8da33d6 100644
--- a/source/source_hsolver/diag_hs_para.cpp
+++ b/source/source_hsolver/diag_hs_para.cpp
@@ -1,5 +1,6 @@
 #include "source_hsolver/diag_hs_para.h"
 
+#include "source_base/module_external/blacs_connector.h"
 #include "source_base/module_external/scalapack_connector.h"
 #include "source_base/parallel_2d.h"
 #include "source_hsolver/diago_pxxxgvx.h"
diff --git a/source/source_hsolver/diago_bpcg.h b/source/source_hsolver/diago_bpcg.h
index 796ae77666b..27f528024ba 100644
--- a/source/source_hsolver/diago_bpcg.h
+++ b/source/source_hsolver/diago_bpcg.h
@@ -6,7 +6,6 @@
 #include "source_base/module_device/types.h"
 #include "source_base/para_gemm.h"
 #include "source_hamilt/hamilt.h"
-#include "source_pw/module_pwdft/structure_factor.h"
 #include "source_hsolver/kernels/hegvd_op.h"
 #include "source_hsolver/para_linear_transform.h"
 
diff --git a/source/source_hsolver/diago_cusolver.cpp b/source/source_hsolver/diago_cusolver.cpp
index a819eca7000..b02c4132574 100644
--- a/source/source_hsolver/diago_cusolver.cpp
+++ b/source/source_hsolver/diago_cusolver.cpp
@@ -1,8 +1,10 @@
 #include "diago_cusolver.h"
 
+#include "source_base/module_external/blas_connector.h"
 #include "source_base/module_external/blacs_connector.h"
 #include "source_base/global_variable.h"
 #include "source_base/module_external/scalapack_connector.h"
+#include "source_base/tool_title.h"
 #include "source_base/timer.h"
 #include "source_io/module_parameter/parameter.h"
 
diff --git a/source/source_hsolver/diago_dav_subspace.h b/source/source_hsolver/diago_dav_subspace.h
index 6ad3300b182..43e0304729c 100644
--- a/source/source_hsolver/diago_dav_subspace.h
+++ b/source/source_hsolver/diago_dav_subspace.h
@@ -8,7 +8,6 @@
 #include "source_base/module_container/ATen/kernels/lapack.h"
 
 #include "source_hsolver/diag_comm_info.h"
-#include "source_hsolver/diag_const_nums.h"
 
 #include <vector>
 #include <functional>
diff --git a/source/source_hsolver/diago_elpa.cpp b/source/source_hsolver/diago_elpa.cpp
index 23d19c5aed1..a264a41b9c3 100644
--- a/source/source_hsolver/diago_elpa.cpp
+++ b/source/source_hsolver/diago_elpa.cpp
@@ -1,4 +1,6 @@
 #include "diago_elpa.h"
+#include "source_base/global_function.h"
+#include "source_base/module_external/blas_connector.h"
 
 #include "source_io/module_parameter/parameter.h"
 #include "module_genelpa/elpa_solver.h"
diff --git a/source/source_hsolver/diago_elpa_native.cpp b/source/source_hsolver/diago_elpa_native.cpp
index 0ab09f09632..ee003a08e01 100644
--- a/source/source_hsolver/diago_elpa_native.cpp
+++ b/source/source_hsolver/diago_elpa_native.cpp
@@ -1,5 +1,7 @@
 #include "diago_elpa_native.h"
 
+#include "source_base/global_function.h"
+#include "source_base/module_external/blas_connector.h"
 #include "source_base/module_external/blacs_connector.h"
 #include "source_base/global_variable.h"
 #include "source_io/module_parameter/parameter.h"
diff --git a/source/source_hsolver/diago_iter_assist.cpp b/source/source_hsolver/diago_iter_assist.cpp
index a522f580c6f..c68dd4e5afe 100644
--- a/source/source_hsolver/diago_iter_assist.cpp
+++ b/source/source_hsolver/diago_iter_assist.cpp
@@ -2,6 +2,7 @@
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/complexmatrix.h"
 #include "source_base/constants.h"
+#include "source_base/global_function.h"
 #include "source_base/global_variable.h"
 #include "source_base/module_device/device.h"
 #include "source_base/parallel_reduce.h"
diff --git a/source/source_hsolver/diago_iter_assist.h b/source/source_hsolver/diago_iter_assist.h
index 2867b50b5c3..e9c4c005201 100644
--- a/source/source_hsolver/diago_iter_assist.h
+++ b/source/source_hsolver/diago_iter_assist.h
@@ -6,6 +6,8 @@
 #include "source_hamilt/hamilt.h"
 #include "source_psi/psi.h"
 
+#include <functional>
+
 namespace hsolver
 {
 
diff --git a/source/source_hsolver/diago_pexsi.cpp b/source/source_hsolver/diago_pexsi.cpp
index 78a32ba9403..e85f78b12b9 100644
--- a/source/source_hsolver/diago_pexsi.cpp
+++ b/source/source_hsolver/diago_pexsi.cpp
@@ -4,6 +4,7 @@
 #include <memory>
 #ifdef __PEXSI
 #include "diago_pexsi.h"
+#include "source_base/tool_title.h"
 #include "source_base/global_variable.h"
 #include "source_base/tool_quit.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
diff --git a/source/source_hsolver/diago_pexsi.h b/source/source_hsolver/diago_pexsi.h
index 9871935f0f0..9f0e0d1317b 100644
--- a/source/source_hsolver/diago_pexsi.h
+++ b/source/source_hsolver/diago_pexsi.h
@@ -5,7 +5,6 @@
 #include <memory>
 #include "source_base/macros.h"   // GetRealType
 #include "source_hamilt/hamilt.h"
-#include "source_base/global_variable.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
 #include "module_pexsi/pexsi_solver.h"
 
diff --git a/source/source_hsolver/hsolver.cpp b/source/source_hsolver/hsolver.cpp
index 1e8645cd37b..a6d955541ae 100644
--- a/source/source_hsolver/hsolver.cpp
+++ b/source/source_hsolver/hsolver.cpp
@@ -1,5 +1,6 @@
 #include "hsolver.h"
 
+#include "source_base/global_function.h"
 #include "source_io/module_parameter/parameter.h"
 
 namespace hsolver
diff --git a/source/source_hsolver/hsolver.h b/source/source_hsolver/hsolver.h
index f8eb5992da5..93806e64115 100644
--- a/source/source_hsolver/hsolver.h
+++ b/source/source_hsolver/hsolver.h
@@ -1,9 +1,8 @@
 #ifndef HSOLVER_H
 #define HSOLVER_H
 
-#include "source_estate/elecstate.h"
-#include "source_hamilt/hamilt.h"
-
+#include <fstream>
+#include <string>
 
 namespace hsolver
 {
diff --git a/source/source_hsolver/hsolver_lcaopw.h b/source/source_hsolver/hsolver_lcaopw.h
index 13c359b2e91..b13669ca754 100644
--- a/source/source_hsolver/hsolver_lcaopw.h
+++ b/source/source_hsolver/hsolver_lcaopw.h
@@ -4,7 +4,6 @@
 #include "source_estate/elecstate.h"
 #include "source_hamilt/hamilt.h"
 #include "source_base/macros.h"
-#include "source_base/module_device/types.h"
 namespace hsolver
 {
 
diff --git a/source/source_hsolver/hsolver_pw.cpp b/source/source_hsolver/hsolver_pw.cpp
index 780dac1eaf9..b88bc3b90dd 100644
--- a/source/source_hsolver/hsolver_pw.cpp
+++ b/source/source_hsolver/hsolver_pw.cpp
@@ -1,5 +1,6 @@
 #include "hsolver_pw.h"
 
+#include "source_base/parallel_comm.h"
 #include "source_base/global_variable.h"
 #include "source_base/timer.h"
 #include "source_base/tool_quit.h"
diff --git a/source/source_hsolver/kernels/hegvd_op.h b/source/source_hsolver/kernels/hegvd_op.h
index dfe1aaf287b..c88e51bc639 100644
--- a/source/source_hsolver/kernels/hegvd_op.h
+++ b/source/source_hsolver/kernels/hegvd_op.h
@@ -7,6 +7,11 @@
 #ifndef MODULE_HSOLVER_HEGVD_H
 #define MODULE_HSOLVER_HEGVD_H
 
+#include "source_base/parallel_reduce.h"
+#include "source_base/module_device/types.h"
+
+#include <cassert>
+
 // Note:
 // names follow the same style as standard LAPACK APIs:
 // -----------------------------------
@@ -26,8 +31,6 @@
 // And will be moved to a global module(module base) later.
 
 #include "source_base/macros.h"
-#include "source_base/parallel_reduce.h"
-#include "source_base/module_device/types.h"
 
 namespace hsolver
 {
diff --git a/source/source_hsolver/module_genelpa/elpa_new.h b/source/source_hsolver/module_genelpa/elpa_new.h
index ff1648ed858..cfa724bfc2a 100644
--- a/source/source_hsolver/module_genelpa/elpa_new.h
+++ b/source/source_hsolver/module_genelpa/elpa_new.h
@@ -37,6 +37,6 @@ extern "C"
 #endif
 }
 
-
 #include "elpa_generic.hpp" // This is a wrapper for `elpa/elpa_generic.h`.
+
 #endif
diff --git a/source/source_hsolver/para_linear_transform.cpp b/source/source_hsolver/para_linear_transform.cpp
index 4581f0f5b79..1ddcdb78591 100644
--- a/source/source_hsolver/para_linear_transform.cpp
+++ b/source/source_hsolver/para_linear_transform.cpp
@@ -1,5 +1,8 @@
 #include "para_linear_transform.h"
 
+#include "source_base/kernels/math_kernel_op.h"
+#include "source_base/parallel_common.h"
+#include "source_base/parallel_device.h"
 #include "source_base/timer.h"
 
 #include <algorithm>
diff --git a/source/source_hsolver/para_linear_transform.h b/source/source_hsolver/para_linear_transform.h
index 5651695e0b3..20d584b30d2 100644
--- a/source/source_hsolver/para_linear_transform.h
+++ b/source/source_hsolver/para_linear_transform.h
@@ -1,9 +1,7 @@
 #ifndef __PARA_LINEAR_TRANSFORM_H__
 #define __PARA_LINEAR_TRANSFORM_H__
-#include "source_base/kernels/math_kernel_op.h"
 #include "source_base/module_device/device.h"
 #include "source_base/module_device/memory_op.h"
-#include "source_base/parallel_device.h"
 
 #include <vector>
 #ifdef __MPI
diff --git a/source/source_hsolver/test/test_hsolver.cpp b/source/source_hsolver/test/test_hsolver.cpp
index 6e9ab260097..02b838aa3d0 100644
--- a/source/source_hsolver/test/test_hsolver.cpp
+++ b/source/source_hsolver/test/test_hsolver.cpp
@@ -4,6 +4,7 @@
 #define protected public
 
 #include "hsolver_supplementary_mock.h"
+#include "source_hamilt/hamilt.h"
 #include "source_hsolver/hsolver.h"
 
 #include <source_base/macros.h>
diff --git a/source/source_hsolver/test/test_para_linear_trans.cpp b/source/source_hsolver/test/test_para_linear_trans.cpp
index 7d275e97dd4..e7732990e17 100644
--- a/source/source_hsolver/test/test_para_linear_trans.cpp
+++ b/source/source_hsolver/test/test_para_linear_trans.cpp
@@ -1,5 +1,7 @@
 #include "../para_linear_transform.h"
 
+#include "source_base/kernels/math_kernel_op.h"
+
 #include <gtest/gtest.h>
 #ifdef __MPI
 #include <mpi.h>
diff --git a/source/source_io/module_bessel/bessel_basis.h b/source/source_io/module_bessel/bessel_basis.h
index e8307e76256..d46d7390fbd 100644
--- a/source/source_io/module_bessel/bessel_basis.h
+++ b/source/source_io/module_bessel/bessel_basis.h
@@ -6,7 +6,6 @@
 #ifndef BESSEL_BASIS_H
 #define BESSEL_BASIS_H
 #include "../../source_base/global_function.h"
-#include "../../source_base/global_variable.h"
 #include "../../source_base/realarray.h"
 
 #include "../../source_cell/unitcell.h"
diff --git a/source/source_io/module_bessel/numerical_basis.h b/source/source_io/module_bessel/numerical_basis.h
index d7ffc62ee18..04dacdc9e45 100644
--- a/source/source_io/module_bessel/numerical_basis.h
+++ b/source/source_io/module_bessel/numerical_basis.h
@@ -11,7 +11,6 @@
 #include "../../source_base/complexarray.h"
 #include "../../source_base/complexmatrix.h"
 #include "../../source_base/global_function.h"
-#include "../../source_base/global_variable.h"
 #include "../../source_base/intarray.h"
 #include "../../source_base/matrix.h"
 #include "../../source_base/vector3.h"
diff --git a/source/source_io/module_bessel/numerical_descriptor.h b/source/source_io/module_bessel/numerical_descriptor.h
index 8558779cfd9..6cd76f1d1cc 100644
--- a/source/source_io/module_bessel/numerical_descriptor.h
+++ b/source/source_io/module_bessel/numerical_descriptor.h
@@ -5,7 +5,6 @@
 #ifndef NUMERICAL_DESCRIPTOR_H
 #define NUMERICAL_DESCRIPTOR_H
 #include "../../source_base/global_function.h"
-#include "../../source_base/global_variable.h"
 #include "../../source_base/intarray.h"
 #include "../../source_base/complexmatrix.h"
 #include "bessel_basis.h"
diff --git a/source/source_io/module_chgpot/get_pchg_lcao.h b/source/source_io/module_chgpot/get_pchg_lcao.h
index 4b4de152f81..acf9cbbf62e 100644
--- a/source/source_io/module_chgpot/get_pchg_lcao.h
+++ b/source/source_io/module_chgpot/get_pchg_lcao.h
@@ -3,6 +3,9 @@
 
 #include "source_cell/klist.h"
 #include "source_estate/module_dm/density_matrix.h"
+#include "source_pw/module_pwdft/parallel_grid.h"
+#include "source_basis/module_pw/pw_basis.h"
+#include "source_psi/psi.h"
 
 /**
  * @brief Manages the computation of the charge densities for different bands (band-decomposed charge densities).
diff --git a/source/source_io/module_chgpot/write_init.h b/source/source_io/module_chgpot/write_init.h
index 08184931e97..323cbe7af8f 100644
--- a/source/source_io/module_chgpot/write_init.h
+++ b/source/source_io/module_chgpot/write_init.h
@@ -2,7 +2,6 @@
 #define WRITE_INIT_H
 
 #include "source_io/module_parameter/input_parameter.h" // use inp
-#include "source_cell/parallel_kpoints.h" // use para_grid
 #include "source_estate/module_charge/charge.h" // use chg
 #include "source_estate/fp_energy.h" // use efermi
 #include "source_estate/elecstate.h" // use pelec
diff --git a/source/source_io/module_chgpot/write_libxc_r.cpp b/source/source_io/module_chgpot/write_libxc_r.cpp
index 32500335acd..e8b20cc13e3 100644
--- a/source/source_io/module_chgpot/write_libxc_r.cpp
+++ b/source/source_io/module_chgpot/write_libxc_r.cpp
@@ -6,6 +6,7 @@
 #ifdef USE_LIBXC
 
 #include "write_libxc_r.h"
+#include "source_base/parallel_comm.h"
 #include "source_hamilt/module_xc/xc_functional.h"
 #include "source_hamilt/module_xc/xc_functional_libxc.h"
 #include "source_estate/module_charge/charge.h"
diff --git a/source/source_io/module_ctrl/ctrl_iter_lcao.cpp b/source/source_io/module_ctrl/ctrl_iter_lcao.cpp
index c42616dccae..4701aba2eeb 100644
--- a/source/source_io/module_ctrl/ctrl_iter_lcao.cpp
+++ b/source/source_io/module_ctrl/ctrl_iter_lcao.cpp
@@ -4,6 +4,7 @@
 #include "source_lcao/module_deepks/LCAO_deepks.h"
 #include "source_lcao/module_deepks/LCAO_deepks_interface.h"
 #endif
+#include "source_io/module_restart/restart.h"
 
 namespace ModuleIO
 {
diff --git a/source/source_io/module_ctrl/ctrl_iter_lcao.h b/source/source_io/module_ctrl/ctrl_iter_lcao.h
index 64cc0123d21..6297d4f1d03 100644
--- a/source/source_io/module_ctrl/ctrl_iter_lcao.h
+++ b/source/source_io/module_ctrl/ctrl_iter_lcao.h
@@ -10,7 +10,6 @@
 #include "source_lcao/hamilt_lcao.h" // use hamilt::HamiltLCAO<TK, TR>
 #include "source_lcao/setup_exx.h" // mohan add 20251008
 #include "source_lcao/setup_deepks.h" // mohan add 20251010
-#include "source_io/module_restart/restart.h"
 
 namespace ModuleIO
 {
diff --git a/source/source_io/module_ctrl/ctrl_output_td.h b/source/source_io/module_ctrl/ctrl_output_td.h
index 1b57944d87e..8de3ae325bd 100644
--- a/source/source_io/module_ctrl/ctrl_output_td.h
+++ b/source/source_io/module_ctrl/ctrl_output_td.h
@@ -3,7 +3,6 @@
 
 #include "source_basis/module_ao/ORB_read.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
-#include "source_basis/module_nao/two_center_bundle.h"
 #include "source_cell/unitcell.h"
 #include "source_estate/elecstate_lcao.h"
 #include "source_estate/module_pot/H_TDDFT_pw.h"
diff --git a/source/source_io/module_ctrl/ctrl_scf_lcao.cpp b/source/source_io/module_ctrl/ctrl_scf_lcao.cpp
index 0271c3daf46..7318a3f2b7b 100644
--- a/source/source_io/module_ctrl/ctrl_scf_lcao.cpp
+++ b/source/source_io/module_ctrl/ctrl_scf_lcao.cpp
@@ -1,5 +1,6 @@
 #include "ctrl_scf_lcao.h" // use ctrl_scf_lcao()
 
+#include "source_base/formatter.h"
 #include "source_estate/elecstate_lcao.h" // use elecstate::ElecState
 #include "source_hamilt/hamilt.h"         // use Hamilt<T>
 #include "source_lcao/hamilt_lcao.h"      // use hamilt::HamiltLCAO<TK, TR>
diff --git a/source/source_io/module_current/td_current_io.h b/source/source_io/module_current/td_current_io.h
index 9ed7b6a1115..2a64362b032 100644
--- a/source/source_io/module_current/td_current_io.h
+++ b/source/source_io/module_current/td_current_io.h
@@ -1,7 +1,6 @@
 #ifndef TD_CURRENT_IO_H
 #define TD_CURRENT_IO_H
 
-#include "source_basis/module_nao/two_center_bundle.h"
 #include "source_estate/elecstate_lcao.h"
 #include "source_estate/module_dm/density_matrix.h"
 #include "source_psi/psi.h"
diff --git a/source/source_io/module_energy/nscf_fermi_surf.h b/source/source_io/module_energy/nscf_fermi_surf.h
index 66cfd44b81d..f2c04e7509e 100644
--- a/source/source_io/module_energy/nscf_fermi_surf.h
+++ b/source/source_io/module_energy/nscf_fermi_surf.h
@@ -4,7 +4,6 @@
 #include "source_base/matrix.h"
 #include "source_cell/klist.h"
 #include "source_cell/unitcell.h"
-#include "source_cell/parallel_kpoints.h"
 
 namespace ModuleIO
 {
diff --git a/source/source_io/module_energy/write_bands.h b/source/source_io/module_energy/write_bands.h
index bc1c6942b96..c87e050653f 100644
--- a/source/source_io/module_energy/write_bands.h
+++ b/source/source_io/module_energy/write_bands.h
@@ -4,7 +4,6 @@
 #include "source_io/module_parameter/input_parameter.h"
 #include "source_base/matrix.h"
 #include "source_cell/klist.h"
-#include "source_cell/parallel_kpoints.h"
 
 namespace ModuleIO
 {
diff --git a/source/source_io/module_energy/write_eig_occ.h b/source/source_io/module_energy/write_eig_occ.h
index 26b7be7394b..58c9831e5bd 100644
--- a/source/source_io/module_energy/write_eig_occ.h
+++ b/source/source_io/module_energy/write_eig_occ.h
@@ -2,7 +2,6 @@
 #define WRITE_EIG_OCC_H
 #include "source_base/matrix.h"
 #include "source_cell/klist.h"
-#include "source_cell/parallel_kpoints.h"
 
 namespace ModuleIO
 {
diff --git a/source/source_io/module_energy/write_proj_band_lcao.h b/source/source_io/module_energy/write_proj_band_lcao.h
index 480d184d5bc..af005ae5712 100644
--- a/source/source_io/module_energy/write_proj_band_lcao.h
+++ b/source/source_io/module_energy/write_proj_band_lcao.h
@@ -1,8 +1,6 @@
 #ifndef WRITE_PROJ_BAND_LCAO_H
 #define WRITE_PROJ_BAND_LCAO_H
-#include "source_basis/module_ao/ORB_read.h"
 #include "source_cell/klist.h"
-#include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_cell/unitcell.h"
 #include "source_estate/elecstate.h"
 #include "source_psi/psi.h"
diff --git a/source/source_io/module_hs/cal_r_overlap_R.cpp b/source/source_io/module_hs/cal_r_overlap_R.cpp
index 2765fd18ef5..f75570a4116 100644
--- a/source/source_io/module_hs/cal_r_overlap_R.cpp
+++ b/source/source_io/module_hs/cal_r_overlap_R.cpp
@@ -1,5 +1,6 @@
 #include "cal_r_overlap_R.h"
 
+#include "single_R_io.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
diff --git a/source/source_io/module_hs/cal_r_overlap_R.h b/source/source_io/module_hs/cal_r_overlap_R.h
index 9ae15c92768..2329cd4ea85 100644
--- a/source/source_io/module_hs/cal_r_overlap_R.h
+++ b/source/source_io/module_hs/cal_r_overlap_R.h
@@ -14,7 +14,6 @@
 #include "source_lcao/center2_orb-orb11.h"
 #include "source_lcao/center2_orb-orb21.h"
 #include "source_lcao/center2_orb.h"
-#include "single_R_io.h"
 
 #include <map>
 #include <set>
diff --git a/source/source_io/module_hs/write_HS_R.h b/source/source_io/module_hs/write_HS_R.h
index c6489a85b1a..27c059f5875 100644
--- a/source/source_io/module_hs/write_HS_R.h
+++ b/source/source_io/module_hs/write_HS_R.h
@@ -9,7 +9,6 @@
 #include "source_lcao/module_dftu/dftu.h" // mohan add 20251107
 
 #ifdef __EXX
-#include "source_hamilt/module_xc/exx_info.h" // use GlobalC::exx_info
 #include "RI/global/Tensor.h" // for RI::Tensor
 #endif
 
diff --git a/source/source_io/module_hs/write_HS_sparse.h b/source/source_io/module_hs/write_HS_sparse.h
index f2e4560369c..8791a6bdafd 100644
--- a/source/source_io/module_hs/write_HS_sparse.h
+++ b/source/source_io/module_hs/write_HS_sparse.h
@@ -1,8 +1,6 @@
 #ifndef WRITE_HS_SPARSE_H
 #define WRITE_HS_SPARSE_H
 
-#include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
 #include "source_lcao/LCAO_HS_arrays.hpp"
 
diff --git a/source/source_io/module_json/output_info.h b/source/source_io/module_json/output_info.h
index 8ab42f73b48..f61c60c0b99 100644
--- a/source/source_io/module_json/output_info.h
+++ b/source/source_io/module_json/output_info.h
@@ -1,8 +1,6 @@
 #ifndef OUTPUT_INFO_H
 #define OUTPUT_INFO_H
 
-#include "source_cell/module_symmetry/symmetry.h"
-#include "source_cell/atom_spec.h"
 #include "source_cell/unitcell.h"
 #include "source_base/matrix.h"
 
diff --git a/source/source_io/module_json/readin_info.h b/source/source_io/module_json/readin_info.h
index 35a7205487e..c4a598c999d 100644
--- a/source/source_io/module_json/readin_info.h
+++ b/source/source_io/module_json/readin_info.h
@@ -1,8 +1,5 @@
 #ifndef READIN_INFO_H
 #define READIN_INFO_H
-#include "source_cell/module_symmetry/symmetry.h"
-#include "source_cell/atom_spec.h"
-#include "source_cell/unitcell.h"
 
 
 
diff --git a/source/source_io/module_ml/cal_mlkedf_descriptors.h b/source/source_io/module_ml/cal_mlkedf_descriptors.h
index 9c28763da5a..2569d091c8a 100644
--- a/source/source_io/module_ml/cal_mlkedf_descriptors.h
+++ b/source/source_io/module_ml/cal_mlkedf_descriptors.h
@@ -2,7 +2,6 @@
 #define CAL_MLKEDF_DESCRIPTORS_H
 
 #include <vector>
-#include "source_base/global_function.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_basis/module_pw/pw_basis.h"
 #include "source_cell/unitcell.h"
diff --git a/source/source_io/module_mulliken/output_mulliken.h b/source/source_io/module_mulliken/output_mulliken.h
index 4b58a7a9b8f..2fd1bebd98b 100644
--- a/source/source_io/module_mulliken/output_mulliken.h
+++ b/source/source_io/module_mulliken/output_mulliken.h
@@ -7,7 +7,6 @@
 #include "source_estate/elecstate_lcao.h"
 #include "source_io/module_mulliken/output_dmk.h"
 #include "source_io/module_mulliken/output_sk.h"
-#include "source_base/formatter.h"
 #include "source_lcao/module_operator_lcao/dspin_lcao.h"
 #include "source_estate/module_dm/density_matrix.h" // mohan add 2025-11-04
 
diff --git a/source/source_io/module_output/print_info.h b/source/source_io/module_output/print_info.h
index fcdb90704d8..f7917da9fb9 100644
--- a/source/source_io/module_output/print_info.h
+++ b/source/source_io/module_output/print_info.h
@@ -1,7 +1,6 @@
 #ifndef PRINT_INFO_H
 #define PRINT_INFO_H
 
-#include "source_base/timer.h"
 #include "source_basis/module_pw/pw_basis_k.h"
 #include "source_cell/klist.h"
 #include "source_cell/unitcell.h"
diff --git a/source/source_io/module_parameter/input_conv.cpp b/source/source_io/module_parameter/input_conv.cpp
index 41514706138..9d88945d88e 100644
--- a/source/source_io/module_parameter/input_conv.cpp
+++ b/source/source_io/module_parameter/input_conv.cpp
@@ -7,6 +7,7 @@
 #include "source_estate/occupy.h"
 #include "source_hamilt/module_surchem/surchem.h"
 #include "source_hamilt/module_xc/exx_info.h"
+#include "source_hamilt/module_xc/xc_functional.h"
 #include "../module_unk/berryphase.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_io/module_restart/restart.h"
diff --git a/source/source_io/module_restart/restart.h b/source/source_io/module_restart/restart.h
index 06dd5431726..4fe2787ea6c 100644
--- a/source/source_io/module_restart/restart.h
+++ b/source/source_io/module_restart/restart.h
@@ -3,7 +3,6 @@
 
 #include <string>
 #include "source_base/global_function.h"
-#include "source_lcao/module_ri/abfs-vector3_order.h"
 #ifdef __EXX
 #include <RI/global/Tensor.h>
 #endif
diff --git a/source/source_io/module_restart/restart_exx_csr.h b/source/source_io/module_restart/restart_exx_csr.h
index 2a40192e142..77d804d7f1c 100644
--- a/source/source_io/module_restart/restart_exx_csr.h
+++ b/source/source_io/module_restart/restart_exx_csr.h
@@ -1,7 +1,6 @@
 #pragma once
 #include "source_lcao/module_ri/abfs-vector3_order.h"
 #include "source_cell/unitcell.h"
-#include "source_lcao/module_ri/serialization_cereal.h"
 #include <RI/global/Tensor.h>
 #include <map>
 
diff --git a/source/source_io/module_unk/unk_overlap_lcao.h b/source/source_io/module_unk/unk_overlap_lcao.h
index 7abc37d3376..6c591f1c672 100644
--- a/source/source_io/module_unk/unk_overlap_lcao.h
+++ b/source/source_io/module_unk/unk_overlap_lcao.h
@@ -10,6 +10,7 @@
 #include "source_basis/module_ao/parallel_orbitals.h"
 #include "source_cell/klist.h"
 #include "source_lcao/center2_orb-orb11.h"
+#include "source_psi/psi.h"
 #include "source_lcao/center2_orb-orb21.h"
 #include "source_lcao/center2_orb.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
diff --git a/source/source_io/module_unk/unk_overlap_pw.h b/source/source_io/module_unk/unk_overlap_pw.h
index fc6ebd9f5e0..37f48be7457 100644
--- a/source/source_io/module_unk/unk_overlap_pw.h
+++ b/source/source_io/module_unk/unk_overlap_pw.h
@@ -7,8 +7,6 @@
 #include <string>
 
 #include "source_base/complexmatrix.h"
-#include "source_base/global_variable.h"
-#include "source_base/parallel_reduce.h"
 #include "source_base/vector3.h"
 #include "source_basis/module_pw/pw_basis.h"
 #include "source_basis/module_pw/pw_basis_k.h"
diff --git a/source/source_io/module_wannier/to_wannier90.cpp b/source/source_io/module_wannier/to_wannier90.cpp
index e7a291dcfcf..7476710812a 100644
--- a/source/source_io/module_wannier/to_wannier90.cpp
+++ b/source/source_io/module_wannier/to_wannier90.cpp
@@ -1,5 +1,6 @@
 #include "to_wannier90.h"
 
+#include "source_base/parallel_common.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/math_integral.h"
 #include "source_base/math_polyint.h"
diff --git a/source/source_io/module_wannier/to_wannier90.h b/source/source_io/module_wannier/to_wannier90.h
index e303b88b586..058d3cef4de 100644
--- a/source/source_io/module_wannier/to_wannier90.h
+++ b/source/source_io/module_wannier/to_wannier90.h
@@ -10,14 +10,9 @@
 
 #include "source_base/complexmatrix.h"
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/matrix3.h"
 #include "source_cell/klist.h"
-#include "source_lcao/wavefunc_in_pw.h"
-#include "source_psi/psi.h"
-#include "source_base/parallel_common.h"
-#include "source_base/parallel_reduce.h"
 
 class toWannier90
 {
diff --git a/source/source_io/module_wannier/to_wannier90_lcao.cpp b/source/source_io/module_wannier/to_wannier90_lcao.cpp
index 8c1b8288d94..a26a8ce9033 100644
--- a/source/source_io/module_wannier/to_wannier90_lcao.cpp
+++ b/source/source_io/module_wannier/to_wannier90_lcao.cpp
@@ -1,5 +1,6 @@
 #include "to_wannier90_lcao.h"
 
+#include "source_lcao/module_ri/abfs-vector3_order.h"
 #include "source_io/module_parameter/parameter.h"
 #include "fR_overlap.h"
 #include "source_base/math_integral.h"
diff --git a/source/source_io/module_wannier/to_wannier90_lcao.h b/source/source_io/module_wannier/to_wannier90_lcao.h
index 38bdcea4ca5..9561fb4d457 100644
--- a/source/source_io/module_wannier/to_wannier90_lcao.h
+++ b/source/source_io/module_wannier/to_wannier90_lcao.h
@@ -1,13 +1,10 @@
 #ifndef TOWannier90_LCAO_H
 #define TOWannier90_LCAO_H
 
-#include "source_lcao/module_ri/abfs-vector3_order.h"
 #include "source_base/complexmatrix.h"
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/matrix3.h"
-#include "source_base/parallel_reduce.h"
 #include "source_base/sph_bessel_recursive.h"
 #include "source_base/timer.h"
 #include "source_base/tool_quit.h"
@@ -22,9 +19,7 @@
 #include "source_lcao/center2_orb-orb11.h"
 #include "source_lcao/center2_orb-orb21.h"
 #include "source_lcao/center2_orb.h"
-#include "source_lcao/wavefunc_in_pw.h"
 #include "source_psi/psi.h"
-#include "../module_hs/single_R_io.h"
 #include "to_wannier90.h"
 
 #include <algorithm>
@@ -37,9 +32,7 @@
 
 #ifdef __LCAO
 #include "fR_overlap.h"
-#include "source_lcao/module_ri/abfs-vector3_order.h"
 #include "source_base/math_lebedev_laikov.h"
-#include "source_lcao/module_hcontainer/hcontainer.h"
 
 class Coordinate_3D
 {
diff --git a/source/source_io/module_wannier/to_wannier90_lcao_in_pw.h b/source/source_io/module_wannier/to_wannier90_lcao_in_pw.h
index fbbdcc80758..a6f204858f1 100644
--- a/source/source_io/module_wannier/to_wannier90_lcao_in_pw.h
+++ b/source/source_io/module_wannier/to_wannier90_lcao_in_pw.h
@@ -1,23 +1,15 @@
 #ifndef TO_WANNIER90_LCAO_IN_PW_H
 #define TO_WANNIER90_LCAO_IN_PW_H
 
-#include "source_lcao/module_ri/abfs-vector3_order.h"
 #include "source_base/complexmatrix.h"
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/matrix3.h"
-#include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_base/vector3.h"
 #include "source_base/ylm.h"
-#include "source_basis/module_ao/ORB_atomic_lm.h"
-#include "source_basis/module_ao/ORB_gaunt_table.h"
-#include "source_basis/module_ao/ORB_read.h"
 #include "source_cell/klist.h"
-#include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_psi/psi.h"
-#include "../module_hs/single_R_io.h"
 #include "to_wannier90.h"
 #include "to_wannier90_pw.h"
 
diff --git a/source/source_io/module_wannier/to_wannier90_pw.h b/source/source_io/module_wannier/to_wannier90_pw.h
index 757948b2073..f2f0c09bda5 100644
--- a/source/source_io/module_wannier/to_wannier90_pw.h
+++ b/source/source_io/module_wannier/to_wannier90_pw.h
@@ -11,7 +11,6 @@
 
 #include "source_base/complexmatrix.h"
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/matrix3.h"
 #include "source_cell/klist.h"
diff --git a/source/source_io/module_wf/get_wf_lcao.cpp b/source/source_io/module_wf/get_wf_lcao.cpp
index 139b0364f62..d23dc085950 100644
--- a/source/source_io/module_wf/get_wf_lcao.cpp
+++ b/source/source_io/module_wf/get_wf_lcao.cpp
@@ -1,5 +1,6 @@
 #include "get_wf_lcao.h"
 
+#include "source_base/module_external/blacs_connector.h"
 #include "source_io/module_output/cube_io.h"
 #include "source_io/module_wf/write_wfc_pw.h"
 #include "source_base/memory.h"
diff --git a/source/source_io/module_wf/read_wfc_pw.h b/source/source_io/module_wf/read_wfc_pw.h
index 7e70b28eae0..fcd3023301d 100644
--- a/source/source_io/module_wf/read_wfc_pw.h
+++ b/source/source_io/module_wf/read_wfc_pw.h
@@ -1,8 +1,8 @@
 #ifndef READ_WFC_PW_H
 #define READ_WFC_PW_H
 
+#include "source_base/complexmatrix.h"
 #include "source_basis/module_pw/pw_basis_k.h"
-#include "source_estate/module_charge/charge.h"
 
 #include <string>
 
diff --git a/source/source_io/test/cal_pLpR_test.cpp b/source/source_io/test/cal_pLpR_test.cpp
index 99b394568e9..f9a6a2640a3 100644
--- a/source/source_io/test/cal_pLpR_test.cpp
+++ b/source/source_io/test/cal_pLpR_test.cpp
@@ -21,6 +21,9 @@
 #include <memory>
 #include <vector>
 #include <cmath>
+#ifdef __MPI
+#include <mpi.h>
+#endif
 
 #include "source_io/module_hs/cal_pLpR.h"
 #include "source_basis/module_nao/two_center_integrator.h"
diff --git a/source/source_io/test/to_qo_test.cpp b/source/source_io/test/to_qo_test.cpp
index 90a2bec960c..fcb9bb9b249 100644
--- a/source/source_io/test/to_qo_test.cpp
+++ b/source/source_io/test/to_qo_test.cpp
@@ -1,5 +1,6 @@
 #include <gtest/gtest.h>
 #include "source_io/module_qo/to_qo.h"
+#include "source_io/module_output/output.h"
 #define private public
 #include "source_io/module_parameter/parameter.h"
 #undef private
diff --git a/source/source_lcao/FORCE.h b/source/source_lcao/FORCE.h
index 553cdfad769..e6f5f3735ce 100644
--- a/source/source_lcao/FORCE.h
+++ b/source/source_lcao/FORCE.h
@@ -2,14 +2,12 @@
 #define LCAO_FORCE_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_basis/module_nao/two_center_bundle.h"
 #include "source_estate/elecstate.h"
 #include "source_estate/module_dm/density_matrix.h"
 #include "source_estate/module_pot/potential_new.h"
 #include "source_lcao/force_stress_arrays.h"
-#include "source_lcao/module_deepks/LCAO_deepks.h"
 #include "source_psi/psi.h"
 #include "source_lcao/setup_deepks.h"
 
diff --git a/source/source_lcao/FORCE_STRESS.cpp b/source/source_lcao/FORCE_STRESS.cpp
index a15def000c2..f9f493eaf1d 100644
--- a/source/source_lcao/FORCE_STRESS.cpp
+++ b/source/source_lcao/FORCE_STRESS.cpp
@@ -1,5 +1,6 @@
 #include "FORCE_STRESS.h"
 
+#include "source_base/parallel_reduce.h"
 #include "source_lcao/module_dftu/dftu.h" //Quxin add for DFT+U on 20201029
 #include "source_io/module_output/output_log.h"
 #include "source_io/module_parameter/parameter.h"
@@ -16,6 +17,7 @@
 #ifdef __MLALGO
 #include "source_lcao/module_deepks/LCAO_deepks.h"    //caoyu add for deepks 2021-06-03
 #include "source_lcao/module_deepks/LCAO_deepks_io.h" // mohan add 2024-07-22
+#include "source_lcao/module_deepks/deepks_force.h"
 #endif
 #include "source_lcao/module_operator_lcao/dftu_lcao.h"
 #include "source_lcao/module_operator_lcao/dspin_lcao.h"
diff --git a/source/source_lcao/FORCE_STRESS.h b/source/source_lcao/FORCE_STRESS.h
index 1265664996e..f23a03f786a 100644
--- a/source/source_lcao/FORCE_STRESS.h
+++ b/source/source_lcao/FORCE_STRESS.h
@@ -3,7 +3,6 @@
 
 #include "FORCE.h"
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_pw/module_pwdft/forces.h"
 #include "source_pw/module_pwdft/stress_func.h"
diff --git a/source/source_lcao/FORCE_gamma.cpp b/source/source_lcao/FORCE_gamma.cpp
index dc8180a818c..56489287baf 100644
--- a/source/source_lcao/FORCE_gamma.cpp
+++ b/source/source_lcao/FORCE_gamma.cpp
@@ -7,6 +7,7 @@
 #ifdef __MLALGO
 #include "source_lcao/module_deepks/LCAO_deepks.h" //caoyu add for deepks on 20210813
 #include "source_lcao/module_deepks/LCAO_deepks_io.h"
+#include "source_lcao/module_deepks/deepks_force.h"
 #endif
 #include "source_cell/module_neighbor/sltk_grid_driver.h" //GridD
 #include "source_estate/elecstate_lcao.h"
diff --git a/source/source_lcao/FORCE_k.cpp b/source/source_lcao/FORCE_k.cpp
index 7269a685582..ed07782da3c 100644
--- a/source/source_lcao/FORCE_k.cpp
+++ b/source/source_lcao/FORCE_k.cpp
@@ -18,6 +18,7 @@
 
 #ifdef __MLALGO
 #include "source_lcao/module_deepks/LCAO_deepks.h"
+#include "source_lcao/module_deepks/deepks_force.h"
 #endif
 
 #ifdef _OPENMP
diff --git a/source/source_lcao/LCAO_domain.h b/source/source_lcao/LCAO_domain.h
index cf4af3ace97..870ea4a4a19 100644
--- a/source/source_lcao/LCAO_domain.h
+++ b/source/source_lcao/LCAO_domain.h
@@ -2,7 +2,6 @@
 #define LCAO_DOMAIN_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/vector3.h"
 #include "source_basis/module_nao/two_center_bundle.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
diff --git a/source/source_lcao/LCAO_set.h b/source/source_lcao/LCAO_set.h
index f086bc50272..7ca4550a9ce 100644
--- a/source/source_lcao/LCAO_set.h
+++ b/source/source_lcao/LCAO_set.h
@@ -12,7 +12,6 @@
 #include "source_basis/module_pw/pw_basis.h"
 #include "source_hamilt/module_surchem/surchem.h"
 #include "source_pw/module_pwdft/vl_pw.h"
-#include "source_lcao/module_deepks/LCAO_deepks.h"
 #include "source_lcao/module_dftu/dftu.h"
 #include "source_lcao/setup_exx.h"
 #include "source_lcao/setup_deepks.h"
diff --git a/source/source_lcao/hamilt_lcao.h b/source/source_lcao/hamilt_lcao.h
index c57c284bc81..70f73dfaad6 100644
--- a/source/source_lcao/hamilt_lcao.h
+++ b/source/source_lcao/hamilt_lcao.h
@@ -3,7 +3,6 @@
 
 #include "source_basis/module_nao/two_center_bundle.h"
 #include "source_cell/klist.h"
-#include "source_cell/module_neighbor/sltk_atom_arrange.h"
 #include "source_estate/module_dm/density_matrix.h"
 #include "source_estate/module_pot/potential_new.h"
 #include "source_hamilt/hamilt.h"
diff --git a/source/source_lcao/module_deepks/LCAO_deepks.h b/source/source_lcao/module_deepks/LCAO_deepks.h
index a9c022d153d..75daa9ffad1 100644
--- a/source/source_lcao/module_deepks/LCAO_deepks.h
+++ b/source/source_lcao/module_deepks/LCAO_deepks.h
@@ -4,23 +4,10 @@
 #ifdef __MLALGO
 
 #include "deepks_basic.h"
-#include "deepks_check.h"
-#include "deepks_descriptor.h"
-#include "deepks_force.h"
-#include "deepks_fpre.h"
-#include "deepks_orbital.h"
-#include "deepks_orbpre.h"
 #include "deepks_param.h"
-#include "deepks_pdm.h"
-#include "deepks_phialpha.h"
-#include "deepks_spre.h"
 #include "deepks_vdelta.h"
-#include "deepks_vdpre.h"
-#include "deepks_vdrpre.h"
 #include "source_base/complexmatrix.h"
-#include "source_base/intarray.h"
 #include "source_base/matrix.h"
-#include "source_base/timer.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
 #include "source_basis/module_nao/two_center_integrator.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
diff --git a/source/source_lcao/module_deepks/LCAO_deepks_interface.cpp b/source/source_lcao/module_deepks/LCAO_deepks_interface.cpp
index 10480253e67..928617f4cdb 100644
--- a/source/source_lcao/module_deepks/LCAO_deepks_interface.cpp
+++ b/source/source_lcao/module_deepks/LCAO_deepks_interface.cpp
@@ -6,6 +6,15 @@
 #include "source_base/tool_title.h"
 #include "source_estate/cal_dm.h"
 #include "source_io/module_parameter/parameter.h"
+#include "source_lcao/module_deepks/deepks_check.h"
+#include "source_lcao/module_deepks/deepks_descriptor.h"
+#include "source_lcao/module_deepks/deepks_fpre.h"
+#include "source_lcao/module_deepks/deepks_orbital.h"
+#include "source_lcao/module_deepks/deepks_orbpre.h"
+#include "source_lcao/module_deepks/deepks_pdm.h"
+#include "source_lcao/module_deepks/deepks_spre.h"
+#include "source_lcao/module_deepks/deepks_vdpre.h"
+#include "source_lcao/module_deepks/deepks_vdrpre.h"
 #include "source_lcao/module_hcontainer/hcontainer.h"
 #include "source_lcao/module_hcontainer/hcontainer_funcs.h"
 #include "source_lcao/module_hcontainer/output_hcontainer.h"
diff --git a/source/source_lcao/module_deepks/deepks_basic.h b/source/source_lcao/module_deepks/deepks_basic.h
index a98db86a4a4..2a1d3180591 100644
--- a/source/source_lcao/module_deepks/deepks_basic.h
+++ b/source/source_lcao/module_deepks/deepks_basic.h
@@ -2,10 +2,7 @@
 #define DEEPKS_BASIC_H
 
 #ifdef __MLALGO
-#include "LCAO_deepks_io.h"
 #include "deepks_param.h"
-#include "source_base/parallel_reduce.h"
-#include "source_base/tool_title.h"
 #include "source_cell/unitcell.h"
 
 #include <torch/script.h>
diff --git a/source/source_lcao/module_deepks/deepks_descriptor.h b/source/source_lcao/module_deepks/deepks_descriptor.h
index 93e1e95559d..b6238df3f4c 100644
--- a/source/source_lcao/module_deepks/deepks_descriptor.h
+++ b/source/source_lcao/module_deepks/deepks_descriptor.h
@@ -4,8 +4,6 @@
 #ifdef __MLALGO
 
 #include "deepks_param.h"
-#include "source_base/intarray.h"
-#include "source_base/timer.h"
 #include "source_cell/unitcell.h"
 
 #include <torch/script.h>
diff --git a/source/source_lcao/module_deepks/deepks_force.h b/source/source_lcao/module_deepks/deepks_force.h
index 3837d3a6d6d..ef5c0d8a949 100644
--- a/source/source_lcao/module_deepks/deepks_force.h
+++ b/source/source_lcao/module_deepks/deepks_force.h
@@ -9,9 +9,8 @@
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
-#include "source_basis/module_nao/two_center_integrator.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
-#include "source_estate/module_dm/density_matrix.h"
+#include "source_lcao/module_hcontainer/hcontainer.h"
 
 namespace DeePKS_domain
 {
diff --git a/source/source_lcao/module_deepks/deepks_iterate.cpp b/source/source_lcao/module_deepks/deepks_iterate.cpp
index 6aee04a6359..f5f9b399e51 100644
--- a/source/source_lcao/module_deepks/deepks_iterate.cpp
+++ b/source/source_lcao/module_deepks/deepks_iterate.cpp
@@ -2,6 +2,7 @@
 
 #ifdef __MLALGO
 #include "deepks_iterate.h"
+#include "source_io/module_parameter/parameter.h"
 
 void DeePKS_domain::iterate_ad1(const UnitCell& ucell,
                                 const Grid_Driver& GridD,
diff --git a/source/source_lcao/module_deepks/deepks_iterate.h b/source/source_lcao/module_deepks/deepks_iterate.h
index 69123f65220..887970935a6 100644
--- a/source/source_lcao/module_deepks/deepks_iterate.h
+++ b/source/source_lcao/module_deepks/deepks_iterate.h
@@ -1,7 +1,6 @@
 #ifndef DEEPKS_ITER_H
 #define DEEPKS_ITER_H
 
-#include "source_io/module_parameter/parameter.h"
 
 #ifdef __MLALGO
 
diff --git a/source/source_lcao/module_deepks/deepks_orbital.cpp b/source/source_lcao/module_deepks/deepks_orbital.cpp
index 90cfc15cc1c..77759858460 100644
--- a/source/source_lcao/module_deepks/deepks_orbital.cpp
+++ b/source/source_lcao/module_deepks/deepks_orbital.cpp
@@ -4,6 +4,7 @@
 
 #include "deepks_orbital.h"
 #include "source_base/parallel_reduce.h"
+#include "source_base/tool_title.h"
 #include "source_base/timer.h"
 
 template <typename TK, typename TH>
diff --git a/source/source_lcao/module_deepks/deepks_orbital.h b/source/source_lcao/module_deepks/deepks_orbital.h
index 8f77e58fb16..3681838e18b 100644
--- a/source/source_lcao/module_deepks/deepks_orbital.h
+++ b/source/source_lcao/module_deepks/deepks_orbital.h
@@ -8,7 +8,6 @@
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
-#include "source_estate/module_dm/density_matrix.h"
 
 namespace DeePKS_domain
 {
diff --git a/source/source_lcao/module_deepks/deepks_orbpre.h b/source/source_lcao/module_deepks/deepks_orbpre.h
index ec9dc1a1237..e1eb988f494 100644
--- a/source/source_lcao/module_deepks/deepks_orbpre.h
+++ b/source/source_lcao/module_deepks/deepks_orbpre.h
@@ -9,9 +9,7 @@
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
-#include "source_basis/module_nao/two_center_integrator.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
-#include "source_estate/module_dm/density_matrix.h"
 #include "source_lcao/module_hcontainer/hcontainer.h"
 
 #include <torch/script.h>
diff --git a/source/source_lcao/module_deepks/deepks_pdm.h b/source/source_lcao/module_deepks/deepks_pdm.h
index 4b395475767..3339dc75e90 100644
--- a/source/source_lcao/module_deepks/deepks_pdm.h
+++ b/source/source_lcao/module_deepks/deepks_pdm.h
@@ -8,7 +8,6 @@
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
-#include "source_estate/module_dm/density_matrix.h"
 #include "source_lcao/module_hcontainer/hcontainer.h"
 
 #include <torch/script.h>
diff --git a/source/source_lcao/module_deepks/deepks_phialpha.h b/source/source_lcao/module_deepks/deepks_phialpha.h
index 457c5f6e406..bd2298e31de 100644
--- a/source/source_lcao/module_deepks/deepks_phialpha.h
+++ b/source/source_lcao/module_deepks/deepks_phialpha.h
@@ -3,9 +3,6 @@
 
 #ifdef __MLALGO
 
-#include "source_base/complexmatrix.h"
-#include "source_base/matrix.h"
-#include "source_base/timer.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
 #include "source_basis/module_nao/two_center_integrator.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
diff --git a/source/source_lcao/module_deepks/deepks_vdelta.h b/source/source_lcao/module_deepks/deepks_vdelta.h
index 9c7649a6338..6df6f9b7832 100644
--- a/source/source_lcao/module_deepks/deepks_vdelta.h
+++ b/source/source_lcao/module_deepks/deepks_vdelta.h
@@ -2,7 +2,6 @@
 #define DEEPKS_VDELTA_H
 
 #ifdef __MLALGO
-#include "source_base/complexmatrix.h"
 #include "source_base/matrix.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
 
diff --git a/source/source_lcao/module_deepks/deepks_vdpre.h b/source/source_lcao/module_deepks/deepks_vdpre.h
index bf096a4267d..2b57dc8b3c8 100644
--- a/source/source_lcao/module_deepks/deepks_vdpre.h
+++ b/source/source_lcao/module_deepks/deepks_vdpre.h
@@ -9,7 +9,6 @@
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
-#include "source_basis/module_nao/two_center_integrator.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_lcao/module_hcontainer/hcontainer.h"
 
diff --git a/source/source_lcao/module_deepks/deepks_vdrpre.h b/source/source_lcao/module_deepks/deepks_vdrpre.h
index fc7975ce498..c22eb408fa7 100644
--- a/source/source_lcao/module_deepks/deepks_vdrpre.h
+++ b/source/source_lcao/module_deepks/deepks_vdrpre.h
@@ -9,7 +9,6 @@
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
-#include "source_basis/module_nao/two_center_integrator.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_lcao/module_hcontainer/hcontainer.h"
 
diff --git a/source/source_lcao/module_deepks/test/LCAO_deepks_test.cpp b/source/source_lcao/module_deepks/test/LCAO_deepks_test.cpp
index 517b9f99402..071605bf0a3 100644
--- a/source/source_lcao/module_deepks/test/LCAO_deepks_test.cpp
+++ b/source/source_lcao/module_deepks/test/LCAO_deepks_test.cpp
@@ -1,4 +1,15 @@
 #include "LCAO_deepks_test.h"
+#include "source_lcao/module_deepks/deepks_check.h"
+#include "source_lcao/module_deepks/deepks_descriptor.h"
+#include "source_lcao/module_deepks/deepks_force.h"
+#include "source_lcao/module_deepks/deepks_fpre.h"
+#include "source_lcao/module_deepks/deepks_orbpre.h"
+#include "source_lcao/module_deepks/deepks_orbital.h"
+#include "source_lcao/module_deepks/deepks_pdm.h"
+#include "source_lcao/module_deepks/deepks_phialpha.h"
+#include "source_lcao/module_deepks/deepks_spre.h"
+#include "source_lcao/module_deepks/deepks_vdpre.h"
+#include "source_lcao/module_deepks/deepks_vdrpre.h"
 #define private public
 #include "source_io/module_parameter/parameter.h"
 
diff --git a/source/source_lcao/module_deepks/test/LCAO_deepks_test.h b/source/source_lcao/module_deepks/test/LCAO_deepks_test.h
index 6d819898f83..d90d881eff9 100644
--- a/source/source_lcao/module_deepks/test/LCAO_deepks_test.h
+++ b/source/source_lcao/module_deepks/test/LCAO_deepks_test.h
@@ -5,6 +5,7 @@
 #include "source_cell/module_neighbor/sltk_atom_arrange.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_cell/unitcell.h"
+#include "source_estate/module_dm/density_matrix.h"
 //#include "parallel_orbitals.h"
 
 #include "../LCAO_deepks.h"
diff --git a/source/source_lcao/module_deltaspin/cal_mw.cpp b/source/source_lcao/module_deltaspin/cal_mw.cpp
index 0482f8f0709..563f506f3b8 100644
--- a/source/source_lcao/module_deltaspin/cal_mw.cpp
+++ b/source/source_lcao/module_deltaspin/cal_mw.cpp
@@ -2,6 +2,7 @@
 
 #include "source_base/matrix.h"
 #include "source_base/name_angular.h"
+#include "source_base/parallel_reduce.h"
 #include "source_base/tool_title.h"
 #include "source_base/timer.h"
 #include "source_pw/module_pwdft/onsite_proj.h"
diff --git a/source/source_lcao/module_dftu/dftu.h b/source/source_lcao/module_dftu/dftu.h
index 56d213386d7..9fa468aca5c 100644
--- a/source/source_lcao/module_dftu/dftu.h
+++ b/source/source_lcao/module_dftu/dftu.h
@@ -5,7 +5,6 @@
 #include "source_cell/unitcell.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
 #ifdef __LCAO
-#include "source_estate/module_charge/charge_mixing.h"
 #include "source_hamilt/hamilt.h"
 #include "source_lcao/module_hcontainer/hcontainer.h"
 #include "source_estate/module_dm/density_matrix.h"
diff --git a/source/source_lcao/module_gint/gint_env_gamma.h b/source/source_lcao/module_gint/gint_env_gamma.h
index f0c54d8bb4c..58fc093bb7e 100644
--- a/source/source_lcao/module_gint/gint_env_gamma.h
+++ b/source/source_lcao/module_gint/gint_env_gamma.h
@@ -2,7 +2,6 @@
 
 #include <memory>
 #include <vector>
-#include "source_lcao/module_hcontainer/hcontainer.h"
 #include "gint.h"
 #include "gint_info.h"
 
diff --git a/source/source_lcao/module_gint/gint_env_k.h b/source/source_lcao/module_gint/gint_env_k.h
index afa9b8f8ee0..3627e443d61 100644
--- a/source/source_lcao/module_gint/gint_env_k.h
+++ b/source/source_lcao/module_gint/gint_env_k.h
@@ -2,7 +2,6 @@
 
 #include <memory>
 #include <vector>
-#include "source_lcao/module_hcontainer/hcontainer.h"
 #include "gint.h"
 #include "gint_info.h"
 
diff --git a/source/source_lcao/module_gint/gint_helper.h b/source/source_lcao/module_gint/gint_helper.h
index abbc7c3a27b..e1efce01f11 100644
--- a/source/source_lcao/module_gint/gint_helper.h
+++ b/source/source_lcao/module_gint/gint_helper.h
@@ -3,7 +3,6 @@
 #include <memory>
 #include <cmath>
 #include "gint_type.h"
-#include "source_base/timer.h"
 
 namespace ModuleGint
 {
diff --git a/source/source_lcao/module_gint/gint_info.h b/source/source_lcao/module_gint/gint_info.h
index e772c2d797f..fc8b23c59e5 100644
--- a/source/source_lcao/module_gint/gint_info.h
+++ b/source/source_lcao/module_gint/gint_info.h
@@ -5,8 +5,8 @@
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_cell/unitcell.h"
 #include "source_cell/atom_spec.h"
-#include "source_io/module_parameter/parameter.h"
 #include "source_lcao/module_hcontainer/hcontainer.h"
+#include "source_io/module_parameter/parameter.h"
 #include "gint_helper.h"
 #include "big_grid.h"
 #include "gint_atom.h"
diff --git a/source/source_lcao/module_gint/gint_rho_gpu.h b/source/source_lcao/module_gint/gint_rho_gpu.h
index 5e6df025a4c..10e6e9b9dad 100644
--- a/source/source_lcao/module_gint/gint_rho_gpu.h
+++ b/source/source_lcao/module_gint/gint_rho_gpu.h
@@ -5,7 +5,6 @@
 #include "source_lcao/module_hcontainer/hcontainer.h"
 #include "gint.h"
 #include "gint_info.h"
-#include "source_lcao/module_gint/kernel/cuda_mem_wrapper.h"
 
 namespace ModuleGint
 {
diff --git a/source/source_lcao/module_gint/gint_vl_gpu.h b/source/source_lcao/module_gint/gint_vl_gpu.h
index 776ef963445..6e90805fe91 100644
--- a/source/source_lcao/module_gint/gint_vl_gpu.h
+++ b/source/source_lcao/module_gint/gint_vl_gpu.h
@@ -5,7 +5,6 @@
 #include "source_lcao/module_hcontainer/hcontainer.h"
 #include "gint.h"
 #include "gint_info.h"
-#include "source_lcao/module_gint/kernel/cuda_mem_wrapper.h"
 
 namespace ModuleGint
 {
diff --git a/source/source_lcao/module_gint/kernel/gint_gpu_vars.h b/source/source_lcao/module_gint/kernel/gint_gpu_vars.h
index e37b63ffdbd..c9fb7e3f14c 100644
--- a/source/source_lcao/module_gint/kernel/gint_gpu_vars.h
+++ b/source/source_lcao/module_gint/kernel/gint_gpu_vars.h
@@ -2,11 +2,8 @@
 
 #include <cuda_runtime.h>
 #include "set_const_mem.cuh"
-#include "source_base/ylm.h"
 #include "source_cell/unitcell.h"
-#include "source_cell/atom_spec.h"
 #include "source_lcao/module_gint/biggrid_info.h"
-#include "gint_helper.cuh"
 
 namespace ModuleGint
 {
diff --git a/source/source_lcao/module_gint/kernel/phi_operator_gpu.h b/source/source_lcao/module_gint/kernel/phi_operator_gpu.h
index b24f26527ea..188129db679 100644
--- a/source/source_lcao/module_gint/kernel/phi_operator_gpu.h
+++ b/source/source_lcao/module_gint/kernel/phi_operator_gpu.h
@@ -3,7 +3,6 @@
 #include <cuda_runtime.h>
 
 #include "source_lcao/module_gint/batch_biggrid.h"
-#include "gint_helper.cuh"
 #include "gint_gpu_vars.h"
 #include "cuda_mem_wrapper.h"
 
diff --git a/source/source_lcao/module_gint/meshgrid_info.h b/source/source_lcao/module_gint/meshgrid_info.h
index a8307b10483..6f91278756b 100644
--- a/source/source_lcao/module_gint/meshgrid_info.h
+++ b/source/source_lcao/module_gint/meshgrid_info.h
@@ -1,7 +1,6 @@
 #pragma once
 
 #include "gint_type.h"
-#include "source_cell/unitcell.h"
 
 namespace ModuleGint
 {
diff --git a/source/source_lcao/module_hcontainer/transfer.h b/source/source_lcao/module_hcontainer/transfer.h
index 5b274cbad3f..deea0f5d7ce 100644
--- a/source/source_lcao/module_hcontainer/transfer.h
+++ b/source/source_lcao/module_hcontainer/transfer.h
@@ -4,7 +4,6 @@
 #include <unordered_map>
 #include <vector>
 
-#include "source_base/vector3.h"
 #include "./hcontainer.h"
 
 #ifdef __MPI
diff --git a/source/source_lcao/module_lr/operator_casida/operator_lr_diag.h b/source/source_lcao/module_lr/operator_casida/operator_lr_diag.h
index 7f0f656df77..e29ca438b8b 100644
--- a/source/source_lcao/module_lr/operator_casida/operator_lr_diag.h
+++ b/source/source_lcao/module_lr/operator_casida/operator_lr_diag.h
@@ -1,9 +1,7 @@
 #pragma once
-#include "source_lcao/module_lr/utils/lr_util.h"
 #include "source_base/kernels/math_kernel_op.h"
 #include "source_hamilt/operator.h"
 #ifdef __MPI
-#include "source_base/parallel_common.h"
 #endif
 namespace LR
 {
diff --git a/source/source_lcao/module_lr/utils/lr_util.h b/source/source_lcao/module_lr/utils/lr_util.h
index fa7dce0b9bf..f2764fe179c 100644
--- a/source/source_lcao/module_lr/utils/lr_util.h
+++ b/source/source_lcao/module_lr/utils/lr_util.h
@@ -7,7 +7,6 @@
 #include "source_base/parallel_2d.h"
 #include "source_psi/psi.h"
 #include <ATen/core/tensor.h>
-#include "source_basis/module_pw/pw_basis.h"
 
 using DAT = container::DataType;
 using DEV = container::DeviceType;
diff --git a/source/source_lcao/module_operator_lcao/deepks_lcao.cpp b/source/source_lcao/module_operator_lcao/deepks_lcao.cpp
index 040de01e0bd..8c93965cdb0 100644
--- a/source/source_lcao/module_operator_lcao/deepks_lcao.cpp
+++ b/source/source_lcao/module_operator_lcao/deepks_lcao.cpp
@@ -4,6 +4,8 @@
 #include "source_base/tool_title.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_lcao/module_deepks/LCAO_deepks.h"
+#include "source_lcao/module_deepks/deepks_descriptor.h"
+#include "source_lcao/module_deepks/deepks_pdm.h"
 #include "source_lcao/module_hcontainer/hcontainer_funcs.h"
 #include "source_io/module_parameter/parameter.h"
 #ifdef _OPENMP
diff --git a/source/source_lcao/module_operator_lcao/op_exx_lcao.h b/source/source_lcao/module_operator_lcao/op_exx_lcao.h
index 628cfb4a1a0..fdbc3743431 100644
--- a/source/source_lcao/module_operator_lcao/op_exx_lcao.h
+++ b/source/source_lcao/module_operator_lcao/op_exx_lcao.h
@@ -7,6 +7,7 @@
 #include <RI/ri/Cell_Nearest.h>
 #include "operator_lcao.h"
 #include "source_cell/klist.h"
+#include "source_hamilt/module_xc/exx_info.h"
 
 namespace hamilt
 {
diff --git a/source/source_lcao/module_operator_lcao/td_ekinetic_lcao.cpp b/source/source_lcao/module_operator_lcao/td_ekinetic_lcao.cpp
index 3836811b6cd..ed841346a37 100644
--- a/source/source_lcao/module_operator_lcao/td_ekinetic_lcao.cpp
+++ b/source/source_lcao/module_operator_lcao/td_ekinetic_lcao.cpp
@@ -8,6 +8,7 @@
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_estate/module_pot/H_TDDFT_pw.h"
 #include "source_lcao/center2_orb-orb11.h"
+#include "source_lcao/module_rt/td_info.h"
 #include "source_lcao/spar_hsr.h"
 #include "source_lcao/module_hcontainer/hcontainer_funcs.h"
 
diff --git a/source/source_lcao/module_operator_lcao/td_ekinetic_lcao.h b/source/source_lcao/module_operator_lcao/td_ekinetic_lcao.h
index 25f3c65c351..f0eba68036a 100644
--- a/source/source_lcao/module_operator_lcao/td_ekinetic_lcao.h
+++ b/source/source_lcao/module_operator_lcao/td_ekinetic_lcao.h
@@ -5,7 +5,6 @@
 #include "source_cell/klist.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_lcao/module_hcontainer/hcontainer.h"
-#include "source_lcao/module_rt/td_info.h"
 #include "operator_lcao.h"
 #include <vector>
 
diff --git a/source/source_lcao/module_operator_lcao/td_nonlocal_lcao.cpp b/source/source_lcao/module_operator_lcao/td_nonlocal_lcao.cpp
index 41d72bdf670..a4be96b0b3e 100644
--- a/source/source_lcao/module_operator_lcao/td_nonlocal_lcao.cpp
+++ b/source/source_lcao/module_operator_lcao/td_nonlocal_lcao.cpp
@@ -3,9 +3,11 @@
 #include "source_base/timer.h"
 #include "source_base/tool_title.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
+#include "source_estate/module_pot/H_TDDFT_pw.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_lcao/module_hcontainer/hcontainer_funcs.h"
 #include "source_lcao/module_operator_lcao/operator_lcao.h"
+#include "source_lcao/module_rt/td_info.h"
 #include "source_lcao/module_rt/snap_psibeta_half_tddft.h"
 #ifdef __CUDA
 #include "source_base/module_device/device.h"
diff --git a/source/source_lcao/module_operator_lcao/td_nonlocal_lcao.h b/source/source_lcao/module_operator_lcao/td_nonlocal_lcao.h
index 18228b1040e..67a1c11f28d 100644
--- a/source/source_lcao/module_operator_lcao/td_nonlocal_lcao.h
+++ b/source/source_lcao/module_operator_lcao/td_nonlocal_lcao.h
@@ -3,10 +3,8 @@
 #include "source_basis/module_ao/parallel_orbitals.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_cell/unitcell.h"
-#include "source_estate/module_pot/H_TDDFT_pw.h"
 #include "source_lcao/module_operator_lcao/operator_lcao.h"
 #include "source_lcao/module_hcontainer/hcontainer.h"
-#include "source_lcao/module_rt/td_info.h"
 
 #include <unordered_map>
 
diff --git a/source/source_lcao/module_operator_lcao/td_pot_hybrid.cpp b/source/source_lcao/module_operator_lcao/td_pot_hybrid.cpp
index 634ac464cf7..ba16cfa0325 100644
--- a/source/source_lcao/module_operator_lcao/td_pot_hybrid.cpp
+++ b/source/source_lcao/module_operator_lcao/td_pot_hybrid.cpp
@@ -3,7 +3,9 @@
 #include "source_base/timer.h"
 #include "source_base/tool_title.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
+#include "source_estate/module_pot/H_TDDFT_pw.h"
 #include "source_lcao/module_operator_lcao/operator_lcao.h"
+#include "source_lcao/module_rt/td_info.h"
 #include "source_lcao/module_hcontainer/hcontainer_funcs.h"
 
 template <typename TK, typename TR>
diff --git a/source/source_lcao/module_operator_lcao/td_pot_hybrid.h b/source/source_lcao/module_operator_lcao/td_pot_hybrid.h
index bdb53f3480b..751e94f3fe0 100644
--- a/source/source_lcao/module_operator_lcao/td_pot_hybrid.h
+++ b/source/source_lcao/module_operator_lcao/td_pot_hybrid.h
@@ -9,8 +9,6 @@
 #include "source_lcao/module_hcontainer/hcontainer.h"
 #include <vector>
 #include "source_io/module_hs/cal_r_overlap_R.h"
-#include "source_lcao/module_rt/td_info.h"
-#include "source_estate/module_pot/H_TDDFT_pw.h"
 
 namespace hamilt
 {
diff --git a/source/source_lcao/module_rdmft/rdmft.h b/source/source_lcao/module_rdmft/rdmft.h
index 8e9fb71ced9..c11b504ebd6 100644
--- a/source/source_lcao/module_rdmft/rdmft.h
+++ b/source/source_lcao/module_rdmft/rdmft.h
@@ -5,7 +5,6 @@
 #ifndef RDMFT_H
 #define RDMFT_H
 
-#include "source_io/module_parameter/parameter.h"
 #include "source_psi/psi.h"
 #include "source_base/matrix.h"
 
diff --git a/source/source_lcao/module_rdmft/rdmft_tools.h b/source/source_lcao/module_rdmft/rdmft_tools.h
index 01b433f5959..56517ff4dad 100644
--- a/source/source_lcao/module_rdmft/rdmft_tools.h
+++ b/source/source_lcao/module_rdmft/rdmft_tools.h
@@ -6,7 +6,6 @@
 #define RDMFT_TOOLS_H
 
 #include "source_cell/klist.h"
-#include "source_io/module_parameter/parameter.h" // use PARAM
 #include "source_psi/psi.h"
 #include "source_base/matrix.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
@@ -16,7 +15,6 @@
 #include "source_base/module_external/scalapack_connector.h"
 #include "source_base/parallel_2d.h"
 #include "source_basis/module_ao/parallel_orbitals.h"
-#include "source_base/parallel_reduce.h"
 #include "source_estate/module_dm/cal_dm_psi.h"
 #include "source_estate/module_dm/density_matrix.h"
 
@@ -26,7 +24,6 @@
 
 
 #ifdef __EXX
-#include "source_lcao/module_ri/RI_2D_Comm.h"
 #include "source_lcao/module_ri/Exx_LRI.h"
 // there are some operator reload to print data in different formats
 #endif
diff --git a/source/source_lcao/module_ri/Exx_LRI_interface.h b/source/source_lcao/module_ri/Exx_LRI_interface.h
index 7a0cab7a58f..6f6f9569803 100644
--- a/source/source_lcao/module_ri/Exx_LRI_interface.h
+++ b/source/source_lcao/module_ri/Exx_LRI_interface.h
@@ -2,6 +2,7 @@
 #define EXX_LRI_INTERFACE_H
 
 #include "Exx_LRI.h"
+#include "source_estate/module_charge/charge_mixing.h"
 #include "source_lcao/module_ri/Mix_DMk_2D.h"
 #include "source_lcao/module_ri/module_exx_symmetry/symmetry_rotation.h"
 #include "source_estate/module_dm/density_matrix.h" // mohan add 2025-11-04
diff --git a/source/source_lcao/module_ri/Mix_DMk_2D.h b/source/source_lcao/module_ri/Mix_DMk_2D.h
index 2f24471d91c..aefe1b297bd 100644
--- a/source/source_lcao/module_ri/Mix_DMk_2D.h
+++ b/source/source_lcao/module_ri/Mix_DMk_2D.h
@@ -9,7 +9,6 @@
 #include "Mix_Matrix.h"
 #include "source_base/module_mixing/mixing.h"
 #include "source_base/matrix.h"
-#include "source_base/complexmatrix.h"
 
 #include <vector>
 
diff --git a/source/source_lcao/module_ri/RI_Util.h b/source/source_lcao/module_ri/RI_Util.h
index f683a4f416b..48a6fe196c5 100644
--- a/source/source_lcao/module_ri/RI_Util.h
+++ b/source/source_lcao/module_ri/RI_Util.h
@@ -6,8 +6,8 @@
 #ifndef RI_UTIL_H
 #define RI_UTIL_H
 
-#include "source_hamilt/module_xc/exx_info.h"
 #include "source_cell/klist.h"
+#include "source_lcao/module_ri/conv_coulomb_pot_k.h"
 
 #include <RI/global/Array_Operator.h>
 #include <RI/global/Global_Func-2.h>
diff --git a/source/source_lcao/module_ri/RPA_LRI.h b/source/source_lcao/module_ri/RPA_LRI.h
index 00792a13e11..7dfbdfdf731 100644
--- a/source/source_lcao/module_ri/RPA_LRI.h
+++ b/source/source_lcao/module_ri/RPA_LRI.h
@@ -6,7 +6,6 @@
 #ifndef RPA_LRI_H
 #define RPA_LRI_H
 
-#include "source_esolver/esolver_ks_lcao.h"
 #include "LRI_CV.h"
 // #include "module_xc/exx_info.h"
 // #include "source_basis/module_ao/ORB_atomic_lm.h"
diff --git a/source/source_lcao/module_ri/abfs.h b/source/source_lcao/module_ri/abfs.h
index ecf8977be95..1d80ca0a69c 100644
--- a/source/source_lcao/module_ri/abfs.h
+++ b/source/source_lcao/module_ri/abfs.h
@@ -2,8 +2,6 @@
 #define ABFS_H	
 
 #include "../../source_base/vector3.h"
-#include "../../source_base/matrix.h"
-#include "exx_abfs.h"
 
 #include <set>
 #include <vector>
diff --git a/source/source_lcao/module_ri/ewald_Vq.h b/source/source_lcao/module_ri/ewald_Vq.h
index 4f53a80a704..7a125b4bcc3 100644
--- a/source/source_lcao/module_ri/ewald_Vq.h
+++ b/source/source_lcao/module_ri/ewald_Vq.h
@@ -11,7 +11,7 @@
 #include "source_base/element_basis_index.h"
 #include "source_cell/klist.h"
 #include "source_hamilt/module_xc/exx_info.h"
-#include "source_io/module_parameter/parameter.h"
+#include "source_lcao/module_ri/conv_coulomb_pot_k.h"
 
 #include <RI/global/Tensor.h>
 #include <array>
diff --git a/source/source_lcao/module_ri/exx_abfs-io.h b/source/source_lcao/module_ri/exx_abfs-io.h
index 354eb78b183..665d975d61d 100644
--- a/source/source_lcao/module_ri/exx_abfs-io.h
+++ b/source/source_lcao/module_ri/exx_abfs-io.h
@@ -6,8 +6,6 @@
 #include <map>
 #include <vector>
 #include "../../source_basis/module_ao/ORB_atomic_lm.h"
-#include "../../source_base/matrix.h"
-#include "../../source_base/element_basis_index.h"
 #include "source_cell/klist.h"
 #ifdef __MPI
 #include "mpi.h"
diff --git a/source/source_lcao/module_ri/exx_abfs.h b/source/source_lcao/module_ri/exx_abfs.h
index 8a78307b368..0c5c84f1628 100644
--- a/source/source_lcao/module_ri/exx_abfs.h
+++ b/source/source_lcao/module_ri/exx_abfs.h
@@ -7,10 +7,6 @@ using std::vector;
 using std::map;
 #include <string>
 
-#include "../../source_basis/module_ao/ORB_atomic_lm.h"
-#include "../../source_base/element_basis_index.h"
-#include "../../source_base/matrix.h"
-#include "../../source_base/vector3.h"
 
 class Exx_Abfs
 {
diff --git a/source/source_lcao/module_ri/exx_rotate_abfs.h b/source/source_lcao/module_ri/exx_rotate_abfs.h
index 7f546f4183f..cd53ef7bf68 100644
--- a/source/source_lcao/module_ri/exx_rotate_abfs.h
+++ b/source/source_lcao/module_ri/exx_rotate_abfs.h
@@ -5,7 +5,6 @@
 #include "LRI_CV.h"
 // #include "module_xc/exx_info.h"
 // #include "module_basis/module_ao/ORB_atomic_lm.h"
-#include "source_base/matrix.h"
 #include "Exx_LRI.h"
 // #include "module_ri/Exx_LRI.h"
 // #include <RI/physics/Exx.h>
diff --git a/source/source_lcao/module_ri/gaussian_abfs.h b/source/source_lcao/module_ri/gaussian_abfs.h
index c6d032e98d5..312598cabf8 100644
--- a/source/source_lcao/module_ri/gaussian_abfs.h
+++ b/source/source_lcao/module_ri/gaussian_abfs.h
@@ -6,9 +6,7 @@
 #ifndef GAUSSIAN_ABFS_H
 #define GAUSSIAN_ABFS_H
 
-#include "conv_coulomb_pot_k.h"
 #include "source_basis/module_ao/ORB_atomic_lm.h"
-#include "source_basis/module_ao/ORB_gaunt_table.h"
 //#include "source_basis/module_pw/pw_basis_k.h"
 #include "source_cell/klist.h"
 
diff --git a/source/source_lcao/module_ri/module_exx_symmetry/irreducible_sector.h b/source/source_lcao/module_ri/module_exx_symmetry/irreducible_sector.h
index e2ff540d734..4563307c3e7 100644
--- a/source/source_lcao/module_ri/module_exx_symmetry/irreducible_sector.h
+++ b/source/source_lcao/module_ri/module_exx_symmetry/irreducible_sector.h
@@ -4,7 +4,6 @@
 #include <set>
 #include "source_lcao/module_ri/abfs-vector3_order.h"
 #include "source_base/matrix3.h"
-#include "source_cell/unitcell.h" 
 #include "source_cell/module_symmetry/symmetry.h"
 #include "source_cell/klist.h"
 
diff --git a/source/source_lcao/module_ri/test/dm_mixing_test.cpp b/source/source_lcao/module_ri/test/dm_mixing_test.cpp
index cf0250a0251..3d8f3308a37 100644
--- a/source/source_lcao/module_ri/test/dm_mixing_test.cpp
+++ b/source/source_lcao/module_ri/test/dm_mixing_test.cpp
@@ -1,5 +1,6 @@
 #include "gmock/gmock.h"
 #include "gtest/gtest.h"
+#include "source_base/complexmatrix.h"
 #include "source_base/module_mixing/broyden_mixing.h"
 #include "source_lcao/module_ri/Mix_DMk_2D.h"
 #include "source_lcao/module_ri/Mix_Matrix.h"
diff --git a/source/source_lcao/module_rt/evolve_elec.cpp b/source/source_lcao/module_rt/evolve_elec.cpp
index ede4365258e..491f5c63e0f 100644
--- a/source/source_lcao/module_rt/evolve_elec.cpp
+++ b/source/source_lcao/module_rt/evolve_elec.cpp
@@ -10,9 +10,9 @@
 namespace module_rt
 {
 template <typename Device>
-Evolve_elec<Device>::Evolve_elec() {};
+Evolve_elec<Device>::Evolve_elec(){};
 template <typename Device>
-Evolve_elec<Device>::~Evolve_elec() {};
+Evolve_elec<Device>::~Evolve_elec(){};
 
 template <typename Device>
 ct::DeviceType Evolve_elec<Device>::ct_device_type = ct::DeviceTypeToEnum<Device>::value;
diff --git a/source/source_lcao/module_rt/evolve_elec.h b/source/source_lcao/module_rt/evolve_elec.h
index cabd57e947d..bd6420f5ca2 100644
--- a/source/source_lcao/module_rt/evolve_elec.h
+++ b/source/source_lcao/module_rt/evolve_elec.h
@@ -4,10 +4,8 @@
 #include "source_base/global_function.h"
 #include "source_base/global_variable.h"
 #include "source_base/module_container/ATen/core/tensor.h"     // ct::Tensor
-#include "source_base/module_container/ATen/core/tensor_map.h" // TensorMap
 #include "source_base/module_device/device.h"                  // base_device
 #include "source_base/module_device/memory_op.h"               // memory operations
-#include "source_base/module_external/scalapack_connector.h"   // Cpxgemr2d
 #include "source_esolver/esolver_ks_lcao.h"
 #include "source_esolver/esolver_ks_lcao_tddft.h"
 #include "source_lcao/hamilt_lcao.h"
diff --git a/source/source_lcao/module_rt/evolve_psi.cpp b/source/source_lcao/module_rt/evolve_psi.cpp
index 5f3b1556057..162f64e4574 100644
--- a/source/source_lcao/module_rt/evolve_psi.cpp
+++ b/source/source_lcao/module_rt/evolve_psi.cpp
@@ -87,14 +87,14 @@ void evolve_psi(const int nband,
     {
         /// @brief solve the propagation equation
         /// @input Stmp, Htmp, psi_k_laststep
-        /// @output psi_k        
+        /// @output psi_k
         if (use_td_moving_gauge)
         {
             solve_propagation(pv, nband, nlocal, PARAM.inp.td_dt, Stmp, Htmp, P_k, psi_k_laststep, psi_k);
         }
         else
         {
-            solve_propagation(pv, nband, nlocal, PARAM.inp.td_dt, Stmp, Htmp, psi_k_laststep, psi_k);
+        solve_propagation(pv, nband, nlocal, PARAM.inp.td_dt, Stmp, Htmp, psi_k_laststep, psi_k);
         }
     }
 
diff --git a/source/source_lcao/module_rt/evolve_psi.h b/source/source_lcao/module_rt/evolve_psi.h
index 287b47e10c0..c723b6fba75 100644
--- a/source/source_lcao/module_rt/evolve_psi.h
+++ b/source/source_lcao/module_rt/evolve_psi.h
@@ -7,7 +7,6 @@
 #define ELEC_PSI_H
 
 #include "source_base/module_container/ATen/core/tensor.h"     // ct::Tensor
-#include "source_base/module_container/ATen/core/tensor_map.h" // TensorMap
 #include "source_basis/module_ao/parallel_orbitals.h"
 #include "source_lcao/hamilt_lcao.h"
 #include "source_lcao/module_rt/evolve_elec.h"
diff --git a/source/source_lcao/module_rt/solve_propagation.cpp b/source/source_lcao/module_rt/solve_propagation.cpp
index f17837bf9a7..aa0a9f38371 100644
--- a/source/source_lcao/module_rt/solve_propagation.cpp
+++ b/source/source_lcao/module_rt/solve_propagation.cpp
@@ -11,13 +11,13 @@ namespace module_rt
 {
 #ifdef __MPI
 void solve_propagation(const Parallel_Orbitals* pv,
-                       const int nband,
-                       const int nlocal,
-                       const double dt,
-                       const std::complex<double>* Stmp,
-                       const std::complex<double>* Htmp,
-                       const std::complex<double>* psi_k_laststep,
-                       std::complex<double>* psi_k)
+                        const int nband,
+                        const int nlocal,
+                        const double dt,
+                        const std::complex<double>* Stmp,
+                        const std::complex<double>* Htmp,
+                        const std::complex<double>* psi_k_laststep,
+                        std::complex<double>* psi_k)
 {
     // (1) init A,B and copy Htmp to A & B
     std::complex<double>* operator_A = new std::complex<double>[pv->nloc];
@@ -29,7 +29,7 @@ void solve_propagation(const Parallel_Orbitals* pv,
     BlasConnector::copy(pv->nloc, Htmp, 1, operator_B, 1);
 
     const double dt_au = dt / ModuleBase::AU_to_FS;
-
+    
     // ->>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
     // (2) compute operator_A & operator_B by GEADD
     // operator_A = Stmp + i*para * Htmp;   beta2 = para = 0.25 * dt
@@ -44,25 +44,25 @@ void solve_propagation(const Parallel_Orbitals* pv,
     // (3) b = operator_B @ psi_k_laststep
     std::complex<double>* tmp_b = new std::complex<double>[pv->nloc_wfc];
     ScalapackConnector::gemm('N',
-                             'N',
-                             nlocal,
-                             nband,
-                             nlocal,
-                             1.0,
-                             operator_B,
-                             1,
-                             1,
-                             pv->desc,
-                             psi_k_laststep,
-                             1,
-                             1,
-                             pv->desc_wfc,
-                             0.0,
-                             tmp_b,
-                             1,
-                             1,
-                             pv->desc_wfc);
-    // get ipiv
+                        'N',
+                        nlocal,
+                        nband,
+                        nlocal,
+                        1.0,
+                        operator_B,
+                        1,
+                        1,
+                        pv->desc,
+                        psi_k_laststep,
+                        1,
+                        1,
+                        pv->desc_wfc,
+                        0.0,
+                        tmp_b,
+                        1,
+                        1,
+                        pv->desc_wfc);
+    //get ipiv
     int* ipiv = new int[pv->nloc];
     int info = 0;
     // (4) solve Ac=b
@@ -119,21 +119,21 @@ void solve_propagation(const Parallel_Orbitals* pv,
     ScalapackConnector::gemm('N',
                              'N',
                              nlocal,
-                             nband,
+                            nband,
                              nlocal,
                              1.0,
                              operator_B,
-                             1,
-                             1,
-                             pv->desc,
+                            1,
+                            1,
+                            pv->desc,
                              psi_k_laststep,
                              1,
                              1,
                              pv->desc_wfc,
                              0.0,
-                             tmp_b,
-                             1,
-                             1,
+                            tmp_b,
+                            1,
+                            1,
                              pv->desc_wfc);
 
     // get ipiv
@@ -143,13 +143,13 @@ void solve_propagation(const Parallel_Orbitals* pv,
     // (4) solve Ac=b
     ScalapackConnector::gesv(nlocal, nband, operator_A, 1, 1, pv->desc, ipiv, tmp_b, 1, 1, pv->desc_wfc, &info);
 
-    // copy solution to psi_k
+    //copy solution to psi_k
     BlasConnector::copy(pv->nloc_wfc, tmp_b, 1, psi_k, 1);
 
-    delete[] tmp_b;
-    delete[] ipiv;
-    delete[] operator_A;
-    delete[] operator_B;
+    delete []tmp_b;
+    delete []ipiv;
+    delete []operator_A;
+    delete []operator_B;
 }
 #endif // __MPI
 } // namespace module_rt
diff --git a/source/source_lcao/module_rt/solve_propagation.h b/source/source_lcao/module_rt/solve_propagation.h
index 23a38ac25c0..d39c8e1210d 100644
--- a/source/source_lcao/module_rt/solve_propagation.h
+++ b/source/source_lcao/module_rt/solve_propagation.h
@@ -2,32 +2,31 @@
 #define TD_SOLVE_PROPAGATION_H
 
 #include "source_basis/module_ao/parallel_orbitals.h"
-
 #include <complex>
 
 namespace module_rt
 {
 #ifdef __MPI
 /**
- *  @brief solve propagation equation A@c(t+dt) = B@c(t)
- *
- * @param[in] pv information of parallel
- * @param[in] nband number of bands
- * @param[in] nlocal number of orbitals
- * @param[in] dt time interval
- * @param[in] Stmp overlap matrix S(t+dt/2)
- * @param[in] Htmp H(t+dt/2)
- * @param[in] psi_k_laststep psi of last step
- * @param[out] psi_k psi of this step
- */
+*  @brief solve propagation equation A@c(t+dt) = B@c(t)
+*
+* @param[in] pv information of parallel
+* @param[in] nband number of bands
+* @param[in] nlocal number of orbitals
+* @param[in] dt time interval
+* @param[in] Stmp overlap matrix S(t+dt/2)
+* @param[in] Htmp H(t+dt/2)
+* @param[in] psi_k_laststep psi of last step
+* @param[out] psi_k psi of this step
+*/
 void solve_propagation(const Parallel_Orbitals* pv,
-                       const int nband,
-                       const int nlocal,
-                       const double dt,
-                       const std::complex<double>* Stmp,
-                       const std::complex<double>* Htmp,
-                       const std::complex<double>* psi_k_laststep,
-                       std::complex<double>* psi_k);
+                        const int nband,
+                        const int nlocal,
+                        const double dt,
+                        const std::complex<double>* Stmp,
+                        const std::complex<double>* Htmp,
+                        const std::complex<double>* psi_k_laststep,
+                        std::complex<double>* psi_k);
 
 /**
  * @brief solve propagation equation A@c(t+dt) = B@c(t) with moving spatial gauge P_k
diff --git a/source/source_lcao/module_rt/td_folding.h b/source/source_lcao/module_rt/td_folding.h
index a086c56f9a8..486b65af5c8 100644
--- a/source/source_lcao/module_rt/td_folding.h
+++ b/source/source_lcao/module_rt/td_folding.h
@@ -1,7 +1,6 @@
 #ifndef TD_FOLDING_H
 #define TD_FOLDING_H
 #include "source_lcao/module_hcontainer/hcontainer.h"
-#include "source_lcao/module_ri/abfs-vector3_order.h"
 
 namespace module_rt{
 // folding HR to hk, for hybrid gauge
diff --git a/source/source_lcao/pulay_fs.h b/source/source_lcao/pulay_fs.h
index ea25e9186a2..a2f1d1ee1a0 100644
--- a/source/source_lcao/pulay_fs.h
+++ b/source/source_lcao/pulay_fs.h
@@ -1,5 +1,4 @@
 #pragma once
-#include "source_basis/module_nao/two_center_bundle.h"
 #include "source_estate/module_dm/density_matrix.h"
 #include "source_estate/module_pot/potential_new.h"
 #include "source_cell/unitcell.h"
diff --git a/source/source_lcao/setup_deepks.cpp b/source/source_lcao/setup_deepks.cpp
index 190571661cf..88f84bbc8ad 100644
--- a/source/source_lcao/setup_deepks.cpp
+++ b/source/source_lcao/setup_deepks.cpp
@@ -2,6 +2,12 @@
 
 #include "source_io/module_parameter/parameter.h" // use parameter
 #include "source_lcao/LCAO_domain.h"
+#ifdef __MLALGO
+#include "source_lcao/module_deepks/LCAO_deepks_io.h"
+#include "source_lcao/module_deepks/deepks_basic.h"
+#include "source_lcao/module_deepks/deepks_pdm.h"
+#include "source_lcao/module_deepks/deepks_phialpha.h"
+#endif
 
 template <typename TK>
 Setup_DeePKS<TK>::Setup_DeePKS()
diff --git a/source/source_lcao/setup_exx.h b/source/source_lcao/setup_exx.h
index 9805ff8c91a..badf9d14c7c 100644
--- a/source/source_lcao/setup_exx.h
+++ b/source/source_lcao/setup_exx.h
@@ -11,7 +11,6 @@
 // for EXX
 #ifdef __EXX
 #include "source_lcao/module_ri/Exx_LRI_interface.h"
-#include "source_lcao/module_ri/Mix_DMk_2D.h"
 #endif
 
 template <typename TK>
diff --git a/source/source_lcao/spar_dh.h b/source/source_lcao/spar_dh.h
index 3df85fefc99..4ed94e52c5d 100644
--- a/source/source_lcao/spar_dh.h
+++ b/source/source_lcao/spar_dh.h
@@ -5,7 +5,6 @@
 #include "source_basis/module_ao/parallel_orbitals.h"
 #include "source_basis/module_nao/two_center_bundle.h"
 #include "source_basis/module_ao/ORB_read.h"
-#include "source_cell/module_neighbor/sltk_atom_arrange.h"
 #include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_lcao/LCAO_HS_arrays.hpp"
 #include "source_lcao/force_stress_arrays.h"
diff --git a/source/source_lcao/spar_hsr.h b/source/source_lcao/spar_hsr.h
index 09e41a614af..5a1f1f743d3 100644
--- a/source/source_lcao/spar_hsr.h
+++ b/source/source_lcao/spar_hsr.h
@@ -4,7 +4,6 @@
 #include "source_lcao/LCAO_HS_arrays.hpp"
 #include "source_lcao/module_hcontainer/hcontainer.h"
 #include "source_hamilt/hamilt.h"
-#include "source_lcao/module_dftu/dftu.h" // mohan add 20251107
 
 #ifdef __EXX
 #include <RI/global/Tensor.h>
diff --git a/source/source_lcao/spar_u.h b/source/source_lcao/spar_u.h
index 8e070334961..4ecfa25c012 100644
--- a/source/source_lcao/spar_u.h
+++ b/source/source_lcao/spar_u.h
@@ -2,8 +2,6 @@
 #define SPARSE_FORMAT_U_H
 
 #include "source_lcao/module_ri/abfs-vector3_order.h"
-#include "source_cell/module_neighbor/sltk_atom_arrange.h"
-#include "source_cell/module_neighbor/sltk_grid_driver.h"
 #include "source_lcao/module_dftu/dftu.h" // mohan add 20251107
 
 namespace sparse_format
diff --git a/source/source_lcao/wavefunc_in_pw.h b/source/source_lcao/wavefunc_in_pw.h
index e46f4151ae3..eb72962fced 100644
--- a/source/source_lcao/wavefunc_in_pw.h
+++ b/source/source_lcao/wavefunc_in_pw.h
@@ -3,7 +3,6 @@
 
 #include "source_base/complexmatrix.h"
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/realarray.h"
 #include "source_base/vector3.h"
 #include "source_basis/module_pw/pw_basis_k.h"
diff --git a/source/source_main/driver.h b/source/source_main/driver.h
index 9bdcf1d2851..e0204d079ca 100644
--- a/source/source_main/driver.h
+++ b/source/source_main/driver.h
@@ -1,7 +1,6 @@
 #ifndef DRIVER_H
 #define DRIVER_H
 
-#include "source_cell/unitcell.h"
 
 class Driver
 {
diff --git a/source/source_md/md_func.cpp b/source/source_md/md_func.cpp
index 933b3c3f4c2..6bd1b60dd59 100644
--- a/source/source_md/md_func.cpp
+++ b/source/source_md/md_func.cpp
@@ -2,6 +2,7 @@
 
 #include "source_base/global_variable.h"
 #include "source_base/timer.h"
+#include "source_io/module_parameter/parameter.h"
 
 
 namespace MD_func
diff --git a/source/source_md/md_func.h b/source/source_md/md_func.h
index 28ae5101b97..be433ffe4ac 100644
--- a/source/source_md/md_func.h
+++ b/source/source_md/md_func.h
@@ -3,6 +3,8 @@
 
 #include "source_esolver/esolver.h"
 
+class Parameter;
+
 #ifdef __MPI
 #include <mpi.h> // MPI functions
 #endif
diff --git a/source/source_psi/psi_init_atomic_random.h b/source/source_psi/psi_init_atomic_random.h
index 46a79ff0e62..2c8e49fc8d6 100644
--- a/source/source_psi/psi_init_atomic_random.h
+++ b/source/source_psi/psi_init_atomic_random.h
@@ -1,6 +1,5 @@
 #ifndef PSI_INIT_ATOMIC_RANDOM_H
 #define PSI_INIT_ATOMIC_RANDOM_H
-#include "source_cell/parallel_kpoints.h"
 #include "source_pw/module_pwdft/vnl_pw.h"
 #include "psi_init_atomic.h"
 
diff --git a/source/source_psi/psi_init_nao.h b/source/source_psi/psi_init_nao.h
index b965c72e3ef..bb05962ec07 100644
--- a/source/source_psi/psi_init_nao.h
+++ b/source/source_psi/psi_init_nao.h
@@ -2,6 +2,7 @@
 #define PSI_INIT_NAO_H
 #include "source_base/cubic_spline.h"
 #include "source_base/realarray.h"
+#include "source_base/spherical_bessel_transformer.h"
 #include "psi_initializer.h"
 
 #include <memory>
diff --git a/source/source_psi/psi_init_nao_random.h b/source/source_psi/psi_init_nao_random.h
index dbe07d8c771..d6b38bb5568 100644
--- a/source/source_psi/psi_init_nao_random.h
+++ b/source/source_psi/psi_init_nao_random.h
@@ -1,6 +1,5 @@
 #ifndef PSI_INIT_NAO_RANDOM_H
 #define PSI_INIT_NAO_RANDOM_H
-#include "source_cell/parallel_kpoints.h"
 #include "source_pw/module_pwdft/vnl_pw.h"
 #include "psi_init_nao.h"
 
diff --git a/source/source_psi/psi_initializer.cpp b/source/source_psi/psi_initializer.cpp
index 59b52e29b53..e5dda9af381 100644
--- a/source/source_psi/psi_initializer.cpp
+++ b/source/source_psi/psi_initializer.cpp
@@ -1,6 +1,7 @@
 #include "psi_initializer.h"
 
 #include "source_base/memory.h"
+#include "source_base/parallel_global.h"
 // basic functions support
 #include "source_base/timer.h"
 #include "source_base/tool_quit.h"
diff --git a/source/source_psi/psi_initializer.h b/source/source_psi/psi_initializer.h
index a8126562097..589355d2710 100644
--- a/source/source_psi/psi_initializer.h
+++ b/source/source_psi/psi_initializer.h
@@ -8,12 +8,10 @@
 // smart pointer for auto-memory management
 #include <memory>
 // numerical algorithm support
-#include "source_base/spherical_bessel_transformer.h" // for spherical bessel transform
 #ifdef __MPI
 #include <mpi.h>
 #endif
 #include "source_base/macros.h"
-#include "source_base/parallel_global.h"
 #include "source_cell/klist.h"
 
 #include <type_traits>
diff --git a/source/source_psi/psi_prepare.cpp b/source/source_psi/psi_prepare.cpp
index a20d5f2f222..2f0530d8b96 100644
--- a/source/source_psi/psi_prepare.cpp
+++ b/source/source_psi/psi_prepare.cpp
@@ -3,6 +3,7 @@
 #include "source_base/macros.h"
 #include "source_base/memory.h"
 #include "source_base/parallel_device.h"
+#include "source_base/parallel_global.h"
 #include "source_base/timer.h"
 #include "source_base/tool_quit.h"
 #include "source_hsolver/diago_iter_assist.h"
diff --git a/source/source_psi/test/psi_initializer_unit_test.cpp b/source/source_psi/test/psi_initializer_unit_test.cpp
index 3ae38cbc218..6ede4ce8928 100644
--- a/source/source_psi/test/psi_initializer_unit_test.cpp
+++ b/source/source_psi/test/psi_initializer_unit_test.cpp
@@ -10,6 +10,7 @@
 #include "../psi_init_random.h"
 #include "source_pw/module_pwdft/vl_pw.h"
 #include "source_cell/klist.h"
+#include "source_io/module_output/output.h"
 
 /*
 =========================
diff --git a/source/source_pw/module_ofdft/evolve_ofdft.h b/source/source_pw/module_ofdft/evolve_ofdft.h
index 8d592a56a42..63b6b4f86f7 100644
--- a/source/source_pw/module_ofdft/evolve_ofdft.h
+++ b/source/source_pw/module_ofdft/evolve_ofdft.h
@@ -4,7 +4,6 @@
 #include <stdio.h>
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_pw/pw_basis.h"
diff --git a/source/source_pw/module_ofdft/kedf_extwt.h b/source/source_pw/module_ofdft/kedf_extwt.h
index e968fc51868..f084e5731a4 100644
--- a/source/source_pw/module_ofdft/kedf_extwt.h
+++ b/source/source_pw/module_ofdft/kedf_extwt.h
@@ -4,7 +4,6 @@
 #include <cstdio>
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_pw/pw_basis.h"
diff --git a/source/source_pw/module_ofdft/kedf_lkt.h b/source/source_pw/module_ofdft/kedf_lkt.h
index 963bb6c3405..730ceb54dd3 100644
--- a/source/source_pw/module_ofdft/kedf_lkt.h
+++ b/source/source_pw/module_ofdft/kedf_lkt.h
@@ -4,7 +4,6 @@
 #include <cstdio>
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_pw/pw_basis.h"
diff --git a/source/source_pw/module_ofdft/kedf_manager.cpp b/source/source_pw/module_ofdft/kedf_manager.cpp
index 9c589fa9a95..8aaec2a8a4f 100644
--- a/source/source_pw/module_ofdft/kedf_manager.cpp
+++ b/source/source_pw/module_ofdft/kedf_manager.cpp
@@ -1,5 +1,7 @@
 #include "kedf_manager.h"
 
+#include "source_io/module_parameter/parameter.h"
+
 /**
  * @brief [Interface to kedf]
  * Initialize the KEDFs.
diff --git a/source/source_pw/module_ofdft/kedf_manager.h b/source/source_pw/module_ofdft/kedf_manager.h
index 8cd556d7868..cbebe2ccbb4 100644
--- a/source/source_pw/module_ofdft/kedf_manager.h
+++ b/source/source_pw/module_ofdft/kedf_manager.h
@@ -1,9 +1,7 @@
 #ifndef KEDF_MANAGER_H
 #define KEDF_MANAGER_H
 
-#include "source_io/module_parameter/parameter.h"
 #include "source_basis/module_pw/pw_basis.h"
-#include "source_estate/elecstate.h"
 #include "kedf_lkt.h"
 #include "kedf_tf.h"
 #include "kedf_vw.h"
@@ -12,6 +10,8 @@
 #include "kedf_xwm.h"
 #include "kedf_ml.h"
 
+struct Input_para;
+
 class KEDF_Manager
 {
   public:
diff --git a/source/source_pw/module_ofdft/kedf_tf.h b/source/source_pw/module_ofdft/kedf_tf.h
index e3a0f58a5f9..a5c2f300639 100644
--- a/source/source_pw/module_ofdft/kedf_tf.h
+++ b/source/source_pw/module_ofdft/kedf_tf.h
@@ -4,7 +4,6 @@
 #include <stdio.h>
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 
diff --git a/source/source_pw/module_ofdft/kedf_vw.h b/source/source_pw/module_ofdft/kedf_vw.h
index d394ed7d796..b370aa5018f 100644
--- a/source/source_pw/module_ofdft/kedf_vw.h
+++ b/source/source_pw/module_ofdft/kedf_vw.h
@@ -4,7 +4,6 @@
 #include <cstdio>
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_pw/pw_basis.h"
diff --git a/source/source_pw/module_ofdft/kedf_wt.h b/source/source_pw/module_ofdft/kedf_wt.h
index 52f998d9462..e41f3836f56 100644
--- a/source/source_pw/module_ofdft/kedf_wt.h
+++ b/source/source_pw/module_ofdft/kedf_wt.h
@@ -4,7 +4,6 @@
 #include <cstdio>
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/timer.h"
 #include "source_basis/module_pw/pw_basis.h"
diff --git a/source/source_pw/module_pwdft/deltaspin_pw.cpp b/source/source_pw/module_pwdft/deltaspin_pw.cpp
index caf8ea7852f..680ec26afc2 100644
--- a/source/source_pw/module_pwdft/deltaspin_pw.cpp
+++ b/source/source_pw/module_pwdft/deltaspin_pw.cpp
@@ -1,6 +1,7 @@
 #include "source_pw/module_pwdft/deltaspin_pw.h"
 #include "source_lcao/module_deltaspin/spin_constrain.h"
 #include "source_estate/module_charge/charge_mixing.h"
+#include "source_io/module_parameter/parameter.h"
 
 namespace pw
 {
diff --git a/source/source_pw/module_pwdft/deltaspin_pw.h b/source/source_pw/module_pwdft/deltaspin_pw.h
index 0509b61bb89..b965dda53e4 100644
--- a/source/source_pw/module_pwdft/deltaspin_pw.h
+++ b/source/source_pw/module_pwdft/deltaspin_pw.h
@@ -1,9 +1,9 @@
 #ifndef DELTASPIN_PW_H
 #define DELTASPIN_PW_H
 
-#include "source_io/module_parameter/parameter.h"
 
 class Charge_Mixing;
+struct Input_para;
 
 namespace pw
 {
diff --git a/source/source_pw/module_pwdft/dftu_pw.cpp b/source/source_pw/module_pwdft/dftu_pw.cpp
index 475a34620a8..7d74449bfb3 100644
--- a/source/source_pw/module_pwdft/dftu_pw.cpp
+++ b/source/source_pw/module_pwdft/dftu_pw.cpp
@@ -1,5 +1,6 @@
 #include "source_pw/module_pwdft/dftu_pw.h"
 #include "source_lcao/module_dftu/dftu.h"
+#include "source_io/module_parameter/parameter.h"
 
 namespace pw
 {
diff --git a/source/source_pw/module_pwdft/dftu_pw.h b/source/source_pw/module_pwdft/dftu_pw.h
index 8a30b04e766..db67834a188 100644
--- a/source/source_pw/module_pwdft/dftu_pw.h
+++ b/source/source_pw/module_pwdft/dftu_pw.h
@@ -1,10 +1,10 @@
 #ifndef DFTU_PW_H
 #define DFTU_PW_H
 
-#include "source_io/module_parameter/parameter.h"
 #include "source_cell/unitcell.h"
 #include "source_base/matrix.h"
 
+struct Input_para;
 class Plus_U;
 
 namespace pw
diff --git a/source/source_pw/module_pwdft/elecond.cpp b/source/source_pw/module_pwdft/elecond.cpp
index e7862538abe..a362a3088a9 100644
--- a/source/source_pw/module_pwdft/elecond.cpp
+++ b/source/source_pw/module_pwdft/elecond.cpp
@@ -3,7 +3,9 @@
 #include "source_base/global_function.h"
 #include "source_base/global_variable.h"
 #include "source_base/kernels/math_kernel_op.h"
+#include "source_base/parallel_comm.h"
 #include "source_base/parallel_device.h"
+#include "source_base/parallel_reduce.h"
 #include "source_estate/occupy.h"
 #include "source_io/module_output/binstream.h"
 #include "source_io/module_parameter/parameter.h"
diff --git a/source/source_pw/module_pwdft/forces.cpp b/source/source_pw/module_pwdft/forces.cpp
index 6888d89dacc..2f2e1ea3a86 100644
--- a/source/source_pw/module_pwdft/forces.cpp
+++ b/source/source_pw/module_pwdft/forces.cpp
@@ -1,5 +1,8 @@
 #include "forces.h"
 
+#include "source_base/global_variable.h"
+#include "source_base/parallel_reduce.h"
+#include "source_pw/module_pwdft/kernels/force_op.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_io/module_output/output_log.h"
 // new
diff --git a/source/source_pw/module_pwdft/forces.h b/source/source_pw/module_pwdft/forces.h
index 97301090712..b71e9c6a385 100644
--- a/source/source_pw/module_pwdft/forces.h
+++ b/source/source_pw/module_pwdft/forces.h
@@ -2,7 +2,6 @@
 #define FORCES_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_base/module_device/memory_op.h"
 #include "source_basis/module_pw/pw_basis_k.h"
@@ -10,12 +9,13 @@
 #include "source_cell/module_symmetry/symmetry.h"
 #include "source_estate/elecstate.h"
 #include "source_pw/module_pwdft/vl_pw.h"
-#include "source_pw/module_pwdft/kernels/force_op.h"
 #include "source_base/kernels/math_kernel_op.h"
 #include "source_psi/psi.h"
 #include "structure_factor.h"
 #include "source_lcao/module_dftu/dftu.h" // mohan add 2025-11-06
 
+class pseudopot_cell_vnl;
+
 template <typename FPTYPE, typename Device = base_device::DEVICE_CPU>
 class Forces
 {
diff --git a/source/source_pw/module_pwdft/forces_cc.cpp b/source/source_pw/module_pwdft/forces_cc.cpp
index 3a2cc737744..51cc2c04c6c 100644
--- a/source/source_pw/module_pwdft/forces_cc.cpp
+++ b/source/source_pw/module_pwdft/forces_cc.cpp
@@ -1,5 +1,6 @@
 #include "forces.h"
 #include "stress_func.h"
+#include "source_base/parallel_reduce.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_io/module_output/output_log.h"
 // new
diff --git a/source/source_pw/module_pwdft/forces_nl.cpp b/source/source_pw/module_pwdft/forces_nl.cpp
index 930a1ce21ff..599121591c8 100644
--- a/source/source_pw/module_pwdft/forces_nl.cpp
+++ b/source/source_pw/module_pwdft/forces_nl.cpp
@@ -1,4 +1,5 @@
 #include "forces.h"
+#include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_base/tool_title.h"
 #include "source_pw/module_pwdft/fs_nonlocal_tools.h"
diff --git a/source/source_pw/module_pwdft/forces_onsite.cpp b/source/source_pw/module_pwdft/forces_onsite.cpp
index afa5cfcfe94..2429a015515 100644
--- a/source/source_pw/module_pwdft/forces_onsite.cpp
+++ b/source/source_pw/module_pwdft/forces_onsite.cpp
@@ -1,4 +1,5 @@
 #include "forces.h"
+#include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_base/tool_title.h"
 #include "source_pw/module_pwdft/onsite_proj.h"
diff --git a/source/source_pw/module_pwdft/forces_scc.cpp b/source/source_pw/module_pwdft/forces_scc.cpp
index cd1215cd1b0..3d454cf9a09 100644
--- a/source/source_pw/module_pwdft/forces_scc.cpp
+++ b/source/source_pw/module_pwdft/forces_scc.cpp
@@ -1,4 +1,5 @@
 #include "forces.h"
+#include "source_base/parallel_reduce.h"
 #include "source_io/module_output/output_log.h"
 #include "stress_func.h"
 // new
diff --git a/source/source_pw/module_pwdft/forces_us.cpp b/source/source_pw/module_pwdft/forces_us.cpp
index 8fbc110c458..ea2efeb50a2 100644
--- a/source/source_pw/module_pwdft/forces_us.cpp
+++ b/source/source_pw/module_pwdft/forces_us.cpp
@@ -1,4 +1,6 @@
 #include "forces.h"
+#include "source_base/parallel_reduce.h"
+#include "source_pw/module_pwdft/vnl_pw.h"
 #include "source_base/libm/libm.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/math_ylmreal.h"
diff --git a/source/source_pw/module_pwdft/hamilt_pw.cpp b/source/source_pw/module_pwdft/hamilt_pw.cpp
index 152e3451428..3b0f2b8ca7b 100644
--- a/source/source_pw/module_pwdft/hamilt_pw.cpp
+++ b/source/source_pw/module_pwdft/hamilt_pw.cpp
@@ -3,6 +3,7 @@
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/global_function.h"
 #include "source_base/global_variable.h"
+#include "source_base/parallel_reduce.h"
 
 #include "op_pw_veff.h"
 #include "op_pw_ekin.h"
diff --git a/source/source_pw/module_pwdft/kernels/ekinetic_op.h b/source/source_pw/module_pwdft/kernels/ekinetic_op.h
index 5da3e340186..e4d2eaca126 100644
--- a/source/source_pw/module_pwdft/kernels/ekinetic_op.h
+++ b/source/source_pw/module_pwdft/kernels/ekinetic_op.h
@@ -1,7 +1,7 @@
 #ifndef MODULE_HAMILT_EKINETIC_H
 #define MODULE_HAMILT_EKINETIC_H
 
-#include "source_psi/psi.h"
+#include "source_base/module_device/types.h"
 #include <complex>
 
 namespace hamilt {
diff --git a/source/source_pw/module_pwdft/kernels/force_op.h b/source/source_pw/module_pwdft/kernels/force_op.h
index e31721913c7..0e1d51666bf 100644
--- a/source/source_pw/module_pwdft/kernels/force_op.h
+++ b/source/source_pw/module_pwdft/kernels/force_op.h
@@ -1,8 +1,7 @@
 #ifndef W_ABACUS_DEVELOP_ABACUS_DEVELOP_SOURCE_source_pw_HAMILT_PWDFT_KERNELS_FORCE_OP_H
 #define W_ABACUS_DEVELOP_ABACUS_DEVELOP_SOURCE_source_pw_HAMILT_PWDFT_KERNELS_FORCE_OP_H
-#include "source_io/module_parameter/parameter.h"
 
-#include "source_psi/psi.h"
+#include "source_base/module_device/types.h"
 
 #include <complex>
 
diff --git a/source/source_pw/module_pwdft/kernels/meta_op.h b/source/source_pw/module_pwdft/kernels/meta_op.h
index 745abd625db..408f1dfb123 100644
--- a/source/source_pw/module_pwdft/kernels/meta_op.h
+++ b/source/source_pw/module_pwdft/kernels/meta_op.h
@@ -1,6 +1,7 @@
 #ifndef MODULE_HAMILT_META_H
 #define MODULE_HAMILT_META_H
 
+#include "source_base/module_device/types.h"
 #include "source_psi/psi.h"
 #include <complex>
 
diff --git a/source/source_pw/module_pwdft/kernels/mul_potential_op.h b/source/source_pw/module_pwdft/kernels/mul_potential_op.h
index b1cd647b196..2f34d9bdf61 100644
--- a/source/source_pw/module_pwdft/kernels/mul_potential_op.h
+++ b/source/source_pw/module_pwdft/kernels/mul_potential_op.h
@@ -1,6 +1,5 @@
 #ifndef MUL_POTENTIAL_OP_H
 #define MUL_POTENTIAL_OP_H
-#include "source_psi/psi.h"
 #include "source_base/macros.h"
 
 namespace hamilt {
diff --git a/source/source_pw/module_pwdft/kernels/nonlocal_op.h b/source/source_pw/module_pwdft/kernels/nonlocal_op.h
index 6e60957a006..340b0f0c9b7 100644
--- a/source/source_pw/module_pwdft/kernels/nonlocal_op.h
+++ b/source/source_pw/module_pwdft/kernels/nonlocal_op.h
@@ -1,7 +1,7 @@
 #ifndef MODULE_HAMILT_NONLOCAL_H
 #define MODULE_HAMILT_NONLOCAL_H
 
-#include "source_psi/psi.h"
+#include "source_base/module_device/types.h"
 #include <complex>
 
 namespace hamilt {
diff --git a/source/source_pw/module_pwdft/kernels/onsite_op.h b/source/source_pw/module_pwdft/kernels/onsite_op.h
index cc7e8d9cc25..83f3790d6bd 100644
--- a/source/source_pw/module_pwdft/kernels/onsite_op.h
+++ b/source/source_pw/module_pwdft/kernels/onsite_op.h
@@ -1,7 +1,7 @@
 #ifndef MODULE_HAMILT_OPERATOR_KERNELS_ONSITE_H
 #define MODULE_HAMILT_OPERATOR_KERNELS_ONSITE_H
 
-#include "source_psi/psi.h"
+#include "source_base/module_device/types.h"
 #include <complex>
 
 namespace hamilt {
diff --git a/source/source_pw/module_pwdft/kernels/stress_op.h b/source/source_pw/module_pwdft/kernels/stress_op.h
index fc81f355e41..995557ffa05 100644
--- a/source/source_pw/module_pwdft/kernels/stress_op.h
+++ b/source/source_pw/module_pwdft/kernels/stress_op.h
@@ -1,7 +1,7 @@
 #ifndef SRC_PW_STRESS_MULTI_DEVICE_H
 #define SRC_PW_STRESS_MULTI_DEVICE_H
-#include "source_io/module_parameter/parameter.h"
 
+#include "source_base/module_device/types.h"
 #include "source_psi/psi.h"
 
 #include <complex>
diff --git a/source/source_pw/module_pwdft/kernels/veff_op.h b/source/source_pw/module_pwdft/kernels/veff_op.h
index cda82d9a9a4..9611c84303c 100644
--- a/source/source_pw/module_pwdft/kernels/veff_op.h
+++ b/source/source_pw/module_pwdft/kernels/veff_op.h
@@ -1,6 +1,7 @@
 #ifndef MODULE_HAMILT_VEFF_H
 #define MODULE_HAMILT_VEFF_H
 
+#include "source_base/module_device/types.h"
 #include "source_psi/psi.h"
 #include <complex>
 
diff --git a/source/source_pw/module_pwdft/kernels/vnl_op.h b/source/source_pw/module_pwdft/kernels/vnl_op.h
index 16b01b2e491..13f9c12da18 100644
--- a/source/source_pw/module_pwdft/kernels/vnl_op.h
+++ b/source/source_pw/module_pwdft/kernels/vnl_op.h
@@ -1,6 +1,7 @@
 #ifndef W_ABACUS_DEVELOP_ABACUS_DEVELOP_SOURCE_source_pw_HAMILT_PWDFT_KERNELS_VNL_OP_H
 #define W_ABACUS_DEVELOP_ABACUS_DEVELOP_SOURCE_source_pw_HAMILT_PWDFT_KERNELS_VNL_OP_H
 
+#include "source_base/module_device/types.h"
 #include "source_psi/psi.h"
 
 #include <complex>
diff --git a/source/source_pw/module_pwdft/kernels/wf_op.h b/source/source_pw/module_pwdft/kernels/wf_op.h
index 6fab25bcc60..98c9249cfb0 100644
--- a/source/source_pw/module_pwdft/kernels/wf_op.h
+++ b/source/source_pw/module_pwdft/kernels/wf_op.h
@@ -1,6 +1,7 @@
 #ifndef SRC_PW_WF_MULTI_DEVICE_H
 #define SRC_PW_WF_MULTI_DEVICE_H
 
+#include "source_base/module_device/types.h"
 #include "source_psi/psi.h"
 #include <complex>
 
diff --git a/source/source_pw/module_pwdft/onsite_proj.cpp b/source/source_pw/module_pwdft/onsite_proj.cpp
index 82bd3516fd4..f9bd19dee03 100644
--- a/source/source_pw/module_pwdft/onsite_proj.cpp
+++ b/source/source_pw/module_pwdft/onsite_proj.cpp
@@ -9,8 +9,8 @@
 
 #include "source_base/projgen.h"
 #include "source_base/kernels/math_kernel_op.h"
-#ifdef __MPI
 #include "source_base/parallel_reduce.h"
+#ifdef __MPI
 #include "source_base/parallel_common.h"
 #endif
 #include "source_io/module_parameter/parameter.h"
diff --git a/source/source_pw/module_pwdft/onsite_proj_print.h b/source/source_pw/module_pwdft/onsite_proj_print.h
index 12e5a977432..5ff40bdbda7 100644
--- a/source/source_pw/module_pwdft/onsite_proj_print.h
+++ b/source/source_pw/module_pwdft/onsite_proj_print.h
@@ -2,7 +2,6 @@
 #define MODULEHAMILTPW_ONSITE_PROJ_PRINT_H
 
 #include "source_cell/unitcell.h"
-#include "source_base/global_variable.h"
 #include <vector>
 #include <string>
 #include <complex>
diff --git a/source/source_pw/module_pwdft/onsite_proj_tools.cpp b/source/source_pw/module_pwdft/onsite_proj_tools.cpp
index fec5f0a9fb2..488b6e76177 100644
--- a/source/source_pw/module_pwdft/onsite_proj_tools.cpp
+++ b/source/source_pw/module_pwdft/onsite_proj_tools.cpp
@@ -3,9 +3,11 @@
 #include "source_base/math_polyint.h"
 #include "source_base/math_ylmreal.h"
 #include "source_base/memory.h"
+#include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_base/tool_title.h"
 #include "source_pw/module_pwdft/kernels/force_op.h"
+#include "source_io/module_parameter/parameter.h"
 #include "nonlocal_maths.hpp"
 
 #include <numeric>
diff --git a/source/source_pw/module_pwdft/op_pw_exx_ace.cpp b/source/source_pw/module_pwdft/op_pw_exx_ace.cpp
index ef19285a361..4a47b2ac030 100644
--- a/source/source_pw/module_pwdft/op_pw_exx_ace.cpp
+++ b/source/source_pw/module_pwdft/op_pw_exx_ace.cpp
@@ -1,5 +1,6 @@
 #include "op_pw_exx.h"
 #include "source_base/parallel_comm.h"
+#include "source_base/parallel_reduce.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_hamilt/module_xc/exx_info.h"
 
diff --git a/source/source_pw/module_pwdft/op_pw_exx_pot.cpp b/source/source_pw/module_pwdft/op_pw_exx_pot.cpp
index 0116cfe7c3b..9f31bf642e4 100644
--- a/source/source_pw/module_pwdft/op_pw_exx_pot.cpp
+++ b/source/source_pw/module_pwdft/op_pw_exx_pot.cpp
@@ -1,4 +1,5 @@
 #include "op_pw_exx.h"
+#include "source_base/parallel_reduce.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_hamilt/module_xc/exx_info.h" // use GlobalC::exx_info
 
diff --git a/source/source_pw/module_pwdft/parallel_grid.cpp b/source/source_pw/module_pwdft/parallel_grid.cpp
index ff20f40d73d..dc59f2528d9 100644
--- a/source/source_pw/module_pwdft/parallel_grid.cpp
+++ b/source/source_pw/module_pwdft/parallel_grid.cpp
@@ -1,4 +1,6 @@
 #include "parallel_grid.h"
+#include "source_base/global_function.h"
+#include "source_base/global_variable.h"
 #include "source_io/module_parameter/parameter.h"
 
 #ifdef __MPI
diff --git a/source/source_pw/module_pwdft/parallel_grid.h b/source/source_pw/module_pwdft/parallel_grid.h
index 6cee615a347..ffa81d83f50 100644
--- a/source/source_pw/module_pwdft/parallel_grid.h
+++ b/source/source_pw/module_pwdft/parallel_grid.h
@@ -1,8 +1,7 @@
 #ifndef PARALLEL_GRID_H
 #define PARALLEL_GRID_H
 
-#include "source_base/global_function.h"
-#include "source_base/global_variable.h"
+#include <cassert>
 
 class Parallel_Grid
 {
diff --git a/source/source_pw/module_pwdft/radial_proj.h b/source/source_pw/module_pwdft/radial_proj.h
index e1af25cc3df..b19590be8e4 100644
--- a/source/source_pw/module_pwdft/radial_proj.h
+++ b/source/source_pw/module_pwdft/radial_proj.h
@@ -22,7 +22,6 @@
 #include <algorithm>
 
 #include "source_cell/unitcell.h"
-#include "source_psi/psi.h"
 #include "source_basis/module_pw/pw_basis_k.h"
 
 namespace RadialProjection
diff --git a/source/source_pw/module_pwdft/setup_pot.cpp b/source/source_pw/module_pwdft/setup_pot.cpp
index 4a194bc0483..1073774b38c 100644
--- a/source/source_pw/module_pwdft/setup_pot.cpp
+++ b/source/source_pw/module_pwdft/setup_pot.cpp
@@ -3,6 +3,7 @@
 #include "source_estate/module_charge/symmetry_rho.h"
 #include "source_lcao/module_deltaspin/spin_constrain.h"
 #include "source_pw/module_pwdft/onsite_proj.h"
+#include "source_pw/module_pwdft/vnl_pw.h"
 #include "source_lcao/module_dftu/dftu.h"
 #include "source_pw/module_pwdft/vsep_pw.h"
 
diff --git a/source/source_pw/module_pwdft/setup_pot.h b/source/source_pw/module_pwdft/setup_pot.h
index de0b4e8f4c8..a292579a6c2 100644
--- a/source/source_pw/module_pwdft/setup_pot.h
+++ b/source/source_pw/module_pwdft/setup_pot.h
@@ -1,7 +1,6 @@
 #ifndef SETUP_POT_H
 #define SETUP_POT_H
 
-#include "source_base/module_device/device.h" // use Device
 #include "source_cell/unitcell.h"
 #include "source_cell/klist.h"
 #include "source_pw/module_pwdft/structure_factor.h"
@@ -10,6 +9,8 @@
 #include "source_hamilt/hamilt.h"
 #include "source_lcao/module_dftu/dftu.h" // mohan add 2025-11-06
 
+class pseudopot_cell_vnl;
+
 namespace pw
 {
 
diff --git a/source/source_pw/module_pwdft/setup_pwrho.h b/source/source_pw/module_pwdft/setup_pwrho.h
index 4e11848d627..7a6ad1bfd33 100644
--- a/source/source_pw/module_pwdft/setup_pwrho.h
+++ b/source/source_pw/module_pwdft/setup_pwrho.h
@@ -2,7 +2,6 @@
 #define SETUP_PWRHO_H
 
 #include "source_cell/unitcell.h" // use UnitCell
-#include "source_pw/module_pwdft/structure_factor.h" // use Structure_Factor
 #include "source_basis/module_pw/pw_basis.h" // use PW_Basis
 #include "source_io/module_parameter/input_parameter.h" // use Input_para
 
diff --git a/source/source_pw/module_pwdft/setup_pwwfc.cpp b/source/source_pw/module_pwdft/setup_pwwfc.cpp
index 995e7b7f42a..5ed26ba397f 100644
--- a/source/source_pw/module_pwdft/setup_pwwfc.cpp
+++ b/source/source_pw/module_pwdft/setup_pwwfc.cpp
@@ -2,6 +2,7 @@
 #include "source_base/parallel_comm.h" // POOL_WORLD
 #include "source_base/parallel_reduce.h" // Parallel_Reduce
 #include "source_io/module_output/print_info.h" // print information
+#include "source_io/module_parameter/parameter.h"
 
 void pw::teardown_pwwfc(ModulePW::PW_Basis_K* &pw_wfc)
 {
diff --git a/source/source_pw/module_pwdft/setup_pwwfc.h b/source/source_pw/module_pwdft/setup_pwwfc.h
index db39e289412..d52c0426e0d 100644
--- a/source/source_pw/module_pwdft/setup_pwwfc.h
+++ b/source/source_pw/module_pwdft/setup_pwwfc.h
@@ -1,12 +1,13 @@
 #ifndef SETUP_PWWFC_H
 #define SETUP_PWWFC_H
 
-#include "source_io/module_parameter/parameter.h" // input parameters
 #include "source_cell/unitcell.h" // cell information
 #include "source_cell/klist.h" // k-points
 #include "source_basis/module_pw/pw_basis.h" // pw_rho
 #include "source_basis/module_pw/pw_basis_k.h" // pw_wfc 
 
+struct Input_para;
+
 namespace pw
 {
 
diff --git a/source/source_pw/module_pwdft/soc.h b/source/source_pw/module_pwdft/soc.h
index 25a56a6429d..40a3b2e41ac 100644
--- a/source/source_pw/module_pwdft/soc.h
+++ b/source/source_pw/module_pwdft/soc.h
@@ -2,7 +2,9 @@
 #define SOC_H
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
+
+#include <complex>
+#include <iostream>
 
 class Fcoef
 {
diff --git a/source/source_pw/module_pwdft/stress_cc.cpp b/source/source_pw/module_pwdft/stress_cc.cpp
index 8b38d34c5f1..2ee46650b00 100644
--- a/source/source_pw/module_pwdft/stress_cc.cpp
+++ b/source/source_pw/module_pwdft/stress_cc.cpp
@@ -1,4 +1,5 @@
 #include "stress_func.h"
+#include "source_base/parallel_reduce.h"
 #include "source_hamilt/module_xc/xc_functional.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/math_integral.h"
diff --git a/source/source_pw/module_pwdft/stress_ewa.cpp b/source/source_pw/module_pwdft/stress_ewa.cpp
index 594bd05d3b8..69c64075f8d 100644
--- a/source/source_pw/module_pwdft/stress_ewa.cpp
+++ b/source/source_pw/module_pwdft/stress_ewa.cpp
@@ -1,8 +1,10 @@
 #include "stress_func.h"
+#include "source_base/parallel_reduce.h"
 #include "source_hamilt/module_ewald/H_Ewald_pw.h"
 #include "source_base/timer.h"
 #include "source_base/tool_threading.h"
 #include "source_base/libm/libm.h"
+#include "source_io/module_parameter/parameter.h"
 
 #ifdef _OPENMP
 #include <omp.h>
diff --git a/source/source_pw/module_pwdft/stress_exx.cpp b/source/source_pw/module_pwdft/stress_exx.cpp
index 73e7f7e2143..29900f92f67 100644
--- a/source/source_pw/module_pwdft/stress_exx.cpp
+++ b/source/source_pw/module_pwdft/stress_exx.cpp
@@ -1,6 +1,7 @@
 #include "source_hamilt/module_xc/exx_info.h"
 #include "op_pw_exx.h"
 #include "source_base/parallel_common.h"
+#include "source_base/parallel_reduce.h"
 #include "stress_pw.h"
 
 template <typename FPTYPE, typename Device>
diff --git a/source/source_pw/module_pwdft/stress_func.h b/source/source_pw/module_pwdft/stress_func.h
index 0a144e3c81d..383329e8ae2 100644
--- a/source/source_pw/module_pwdft/stress_func.h
+++ b/source/source_pw/module_pwdft/stress_func.h
@@ -3,9 +3,7 @@
 
 #include "source_base/complexmatrix.h"
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
-#include "source_base/parallel_reduce.h"
 #include "source_base/realarray.h"
 #include "source_base/vector3.h"
 #include "source_basis/module_pw/pw_basis_k.h"
diff --git a/source/source_pw/module_pwdft/stress_gga.cpp b/source/source_pw/module_pwdft/stress_gga.cpp
index d4b218d584d..0c23f58ef05 100644
--- a/source/source_pw/module_pwdft/stress_gga.cpp
+++ b/source/source_pw/module_pwdft/stress_gga.cpp
@@ -1,4 +1,5 @@
 #include "stress_func.h"
+#include "source_base/parallel_reduce.h"
 #include "source_hamilt/module_xc/xc_functional.h"
 #include "source_base/timer.h"
 
diff --git a/source/source_pw/module_pwdft/stress_har.cpp b/source/source_pw/module_pwdft/stress_har.cpp
index 7729e0202b7..cc22a31d9b0 100644
--- a/source/source_pw/module_pwdft/stress_har.cpp
+++ b/source/source_pw/module_pwdft/stress_har.cpp
@@ -1,4 +1,5 @@
 #include "stress_func.h"
+#include "source_base/parallel_reduce.h"
 #include "source_estate/module_pot/H_Hartree_pw.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/timer.h"
diff --git a/source/source_pw/module_pwdft/stress_loc.cpp b/source/source_pw/module_pwdft/stress_loc.cpp
index 820cce38b0d..29fa1ee0900 100644
--- a/source/source_pw/module_pwdft/stress_loc.cpp
+++ b/source/source_pw/module_pwdft/stress_loc.cpp
@@ -1,4 +1,5 @@
 #include "stress_func.h"
+#include "source_base/parallel_reduce.h"
 #include "source_base/math_integral.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/tool_threading.h"
diff --git a/source/source_pw/module_pwdft/stress_mgga.cpp b/source/source_pw/module_pwdft/stress_mgga.cpp
index cfdcd12099a..1ee187a4e41 100644
--- a/source/source_pw/module_pwdft/stress_mgga.cpp
+++ b/source/source_pw/module_pwdft/stress_mgga.cpp
@@ -2,6 +2,7 @@
 #include "source_hamilt/module_xc/xc_functional.h"
 #include "source_io/module_parameter/parameter.h"
 #include "stress_func.h"
+#include "source_base/parallel_reduce.h"
 
 #include <ATen/core/tensor.h>
 #include <ATen/core/tensor_types.h>
diff --git a/source/source_pw/module_pwdft/stress_nl.cpp b/source/source_pw/module_pwdft/stress_nl.cpp
index 10a225ef17d..ae421d7b16c 100644
--- a/source/source_pw/module_pwdft/stress_nl.cpp
+++ b/source/source_pw/module_pwdft/stress_nl.cpp
@@ -1,4 +1,5 @@
 #include "source_base/math_polyint.h"
+#include "source_base/parallel_reduce.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/math_ylmreal.h"
 #include "source_base/memory.h"
diff --git a/source/source_pw/module_pwdft/stress_onsite.cpp b/source/source_pw/module_pwdft/stress_onsite.cpp
index 1b9a08bb882..3e8fac403fa 100644
--- a/source/source_pw/module_pwdft/stress_onsite.cpp
+++ b/source/source_pw/module_pwdft/stress_onsite.cpp
@@ -1,4 +1,5 @@
 #include "source_base/module_device/device.h"
+#include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_pw/module_pwdft/onsite_proj.h"
 #include "source_io/module_parameter/parameter.h"
diff --git a/source/source_pw/module_pwdft/stress_us.cpp b/source/source_pw/module_pwdft/stress_us.cpp
index bf7c9f1ad7a..82a0f16eb73 100644
--- a/source/source_pw/module_pwdft/stress_us.cpp
+++ b/source/source_pw/module_pwdft/stress_us.cpp
@@ -1,4 +1,5 @@
 #include "source_base/libm/libm.h"
+#include "source_base/parallel_reduce.h"
 #include "source_io/module_parameter/parameter.h"
 #include "source_base/math_polyint.h"
 #include "source_base/math_ylmreal.h"
diff --git a/source/source_pw/module_pwdft/structure_factor.h b/source/source_pw/module_pwdft/structure_factor.h
index ae10a8d8a9b..8aadb3511fc 100644
--- a/source/source_pw/module_pwdft/structure_factor.h
+++ b/source/source_pw/module_pwdft/structure_factor.h
@@ -5,7 +5,6 @@
 #include "source_basis/module_pw/pw_basis_k.h"
 #include "source_cell/unitcell.h"
 #include "source_pw/module_pwdft/parallel_grid.h"
-#include "source_psi/psi.h"
 
 class Structure_Factor
 {
diff --git a/source/source_pw/module_pwdft/update_cell_pw.cpp b/source/source_pw/module_pwdft/update_cell_pw.cpp
index a027884cc2f..172d7cb61a2 100644
--- a/source/source_pw/module_pwdft/update_cell_pw.cpp
+++ b/source/source_pw/module_pwdft/update_cell_pw.cpp
@@ -1,6 +1,7 @@
 #include "source_pw/module_pwdft/update_cell_pw.h"
 #include "source_base/global_variable.h"
 #include "source_base/global_function.h"
+#include "source_io/module_parameter/parameter.h"
 
 namespace pw
 {
diff --git a/source/source_pw/module_pwdft/update_cell_pw.h b/source/source_pw/module_pwdft/update_cell_pw.h
index 704d5b6f804..77320e52702 100644
--- a/source/source_pw/module_pwdft/update_cell_pw.h
+++ b/source/source_pw/module_pwdft/update_cell_pw.h
@@ -1,12 +1,13 @@
 #ifndef UPDATE_CELL_PW_H
 #define UPDATE_CELL_PW_H
 
-#include "source_io/module_parameter/parameter.h"
 #include "source_cell/unitcell.h"
 #include "source_cell/klist.h"
 #include "source_basis/module_pw/pw_basis_k.h"
 #include "source_pw/module_pwdft/vnl_pw.h"
 
+struct Input_para;
+
 namespace pw
 {
 
diff --git a/source/source_pw/module_pwdft/vl_pw.h b/source/source_pw/module_pwdft/vl_pw.h
index 0a0f0789dba..1a85c4e077a 100644
--- a/source/source_pw/module_pwdft/vl_pw.h
+++ b/source/source_pw/module_pwdft/vl_pw.h
@@ -2,7 +2,6 @@
 #define VL_IN_PW_H 
 
 #include "source_base/global_function.h"
-#include "source_base/global_variable.h"
 #include "source_base/matrix.h"
 #include "source_basis/module_pw/pw_basis.h"
 #include "source_cell/unitcell.h"
diff --git a/source/source_pw/module_pwdft/vnl_pw.cpp b/source/source_pw/module_pwdft/vnl_pw.cpp
index 83c42adac89..ac149130a9d 100644
--- a/source/source_pw/module_pwdft/vnl_pw.cpp
+++ b/source/source_pw/module_pwdft/vnl_pw.cpp
@@ -6,6 +6,7 @@
 #include "source_base/global_variable.h"
 #include "source_base/math_integral.h"
 #include "source_base/math_polyint.h"
+#include "source_io/module_output/output.h"
 #include "source_base/math_sphbes.h"
 #include "source_base/math_ylmreal.h"
 #include "source_base/memory.h"
@@ -218,9 +219,9 @@ void pseudopot_cell_vnl::init(const UnitCell& ucell,
     if (nkb > 0 && allocate_vkb)
     {
         if (!this->use_gpu_)
-        {
-            vkb.create(nkb, npwx);
-            ModuleBase::Memory::record("VNL::vkb", nkb * npwx * sizeof(std::complex<double>));
+    {
+        vkb.create(nkb, npwx);
+        ModuleBase::Memory::record("VNL::vkb", nkb * npwx * sizeof(std::complex<double>));
         }
         // GPU path: vkb ComplexMatrix is not allocated.
         // Column dimension is stored in vkbnc for gemm/gemv leading dimension.
diff --git a/source/source_pw/module_pwdft/vsep_pw.h b/source/source_pw/module_pwdft/vsep_pw.h
index 2c05b26491a..49d24e019f1 100644
--- a/source/source_pw/module_pwdft/vsep_pw.h
+++ b/source/source_pw/module_pwdft/vsep_pw.h
@@ -1,6 +1,7 @@
 #ifndef VSEP_IN_PW
 #define VSEP_IN_PW
 
+#include "source_base/complexmatrix.h"
 #include "source_base/matrix.h"
 #include "source_basis/module_pw/pw_basis.h"
 #include "source_cell/sep_cell.h"
diff --git a/source/source_pw/module_stodft/kernels/hpsi_norm_op.h b/source/source_pw/module_stodft/kernels/hpsi_norm_op.h
index 1d6bff3eb66..c707c3f3e5b 100644
--- a/source/source_pw/module_stodft/kernels/hpsi_norm_op.h
+++ b/source/source_pw/module_stodft/kernels/hpsi_norm_op.h
@@ -1,5 +1,6 @@
 #ifndef HPSI_NORM_OP_H
 #define HPSI_NORM_OP_H
+#include "source_base/module_device/types.h"
 #include <complex>
 #include "source_base/module_device/device.h"
 namespace hamilt
diff --git a/source/source_pw/module_stodft/sto_dos.cpp b/source/source_pw/module_stodft/sto_dos.cpp
index fccf4f2ba12..245a23f8fd4 100644
--- a/source/source_pw/module_stodft/sto_dos.cpp
+++ b/source/source_pw/module_stodft/sto_dos.cpp
@@ -1,5 +1,6 @@
 #include "sto_dos.h"
 
+#include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_base/tool_title.h"
 #include "source_io/module_parameter/parameter.h"
diff --git a/source/source_pw/module_stodft/sto_elecond.cpp b/source/source_pw/module_stodft/sto_elecond.cpp
index be3ae0c4404..59117dcbaec 100644
--- a/source/source_pw/module_stodft/sto_elecond.cpp
+++ b/source/source_pw/module_stodft/sto_elecond.cpp
@@ -5,6 +5,7 @@
 #include "source_base/memory.h"
 #include "source_base/module_container/ATen/tensor.h"
 #include "source_base/parallel_device.h"
+#include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_base/vector3.h"
 #include "source_io/module_parameter/parameter.h"
diff --git a/source/source_pw/module_stodft/sto_elecond.h b/source/source_pw/module_stodft/sto_elecond.h
index 78cb5fcfb6f..540e9880c4c 100644
--- a/source/source_pw/module_stodft/sto_elecond.h
+++ b/source/source_pw/module_stodft/sto_elecond.h
@@ -2,9 +2,9 @@
 #define STOELECOND_H
 
 #include "source_hamilt/hamilt.h"
+#include "source_hsolver/hsolver_pw_sdft.h"
 #include "source_pw/module_pwdft/elecond.h"
 #include "source_pw/module_stodft/sto_wf.h"
-#include "source_hsolver/hsolver_pw_sdft.h"
 
 template <typename FPTYPE, typename Device>
 class Sto_EleCond : protected EleCond<FPTYPE, Device>
diff --git a/source/source_pw/module_stodft/sto_stress_pw.cpp b/source/source_pw/module_stodft/sto_stress_pw.cpp
index ace6162357d..de0dd9279de 100644
--- a/source/source_pw/module_stodft/sto_stress_pw.cpp
+++ b/source/source_pw/module_stodft/sto_stress_pw.cpp
@@ -1,5 +1,6 @@
 #include "sto_stress_pw.h"
 
+#include "source_base/parallel_reduce.h"
 #include "source_base/timer.h"
 #include "source_pw/module_pwdft/fs_kin_tools.h"
 #include "source_pw/module_pwdft/fs_nonlocal_tools.h"
diff --git a/source/source_relax/bfgs.cpp b/source/source_relax/bfgs.cpp
index f535f4a5377..13b87f55097 100644
--- a/source/source_relax/bfgs.cpp
+++ b/source/source_relax/bfgs.cpp
@@ -2,6 +2,7 @@
 #include "source_base/module_external/lapack_connector.h"
 #include "source_io/module_parameter/parameter.h"
 #include "ions_move_basic.h"
+#include "matrix_methods.h"
 #include "source_cell/update_cell.h"
 #include "source_cell/print_cell.h" // lanshuyue add 2025-06-19  
 
diff --git a/source/source_relax/bfgs.h b/source/source_relax/bfgs.h
index a483551a517..8484fa5a782 100644
--- a/source/source_relax/bfgs.h
+++ b/source/source_relax/bfgs.h
@@ -9,7 +9,6 @@
 #include "source_base/matrix3.h"
 #include "source_cell/unitcell.h"
 
-#include "matrix_methods.h"
 
 class BFGS
 {
diff --git a/source/source_relax/ions_move_methods.h b/source/source_relax/ions_move_methods.h
index 746b5ed0005..cdddc4fdd61 100644
--- a/source/source_relax/ions_move_methods.h
+++ b/source/source_relax/ions_move_methods.h
@@ -7,8 +7,6 @@
 #include "ions_move_sd.h"
 #include "bfgs.h"
 #include "lbfgs.h"
-#include "source_esolver/esolver.h"
-#include "source_esolver/esolver_ks.h"
 
 class Ions_Move_Methods
 {
diff --git a/source/source_relax/lbfgs.cpp b/source/source_relax/lbfgs.cpp
index b347fe86fb8..9eb2c7ccda0 100644
--- a/source/source_relax/lbfgs.cpp
+++ b/source/source_relax/lbfgs.cpp
@@ -1,4 +1,5 @@
 #include "lbfgs.h"
+#include "matrix_methods.h"
 #include "source_io/module_parameter/parameter.h"
 #include "ions_move_basic.h"
 #include "source_cell/update_cell.h"
diff --git a/source/source_relax/lbfgs.h b/source/source_relax/lbfgs.h
index 94e33fec704..b931b528415 100644
--- a/source/source_relax/lbfgs.h
+++ b/source/source_relax/lbfgs.h
@@ -5,7 +5,6 @@
 #include <tuple> 
 #include <algorithm>
 #include <cmath>
-#include "matrix_methods.h"
 //#include "line_search.h"
 #include "source_base/matrix.h"
 #include "source_base/matrix3.h"
diff --git a/source/source_relax/relax_nsync.h b/source/source_relax/relax_nsync.h
index 7c424753835..33eca958020 100644
--- a/source/source_relax/relax_nsync.h
+++ b/source/source_relax/relax_nsync.h
@@ -4,8 +4,6 @@
 #include "ions_move_methods.h"
 #include "lattice_change_methods.h"
 #include "source_cell/unitcell.h"
-#include "source_esolver/esolver.h"
-#include "source_esolver/esolver_ks.h"
 
 class Relax_old
 {
diff --git a/toolchain/scripts/lib/config_manager.sh b/toolchain/scripts/lib/config_manager.sh
index 71ec05780ad..7e1afcef6e5 100644
--- a/toolchain/scripts/lib/config_manager.sh
+++ b/toolchain/scripts/lib/config_manager.sh
@@ -1242,4 +1242,4 @@ config_apply_modes() {
                 ;;
         esac
     fi
-}
+}
\ No newline at end of file