diff --git a/align.c b/align.c
index 3ba104a..48b4478 100644
--- a/align.c
+++ b/align.c
@@ -330,7 +330,7 @@ static void mm_align_pair(void *km, const mm_mapopt_t *opt, int qlen, const uint
 {
 	if (mm_dbg_flag & MM_DBG_PRINT_ALN_SEQ) {
 		int i;
-		fprintf(stderr, "===> q=(%d,%d), e=(%d,%d), bw=%d, ksw_flag=%d, zdrop=%d <===\n", opt->q, opt->q2, opt->e, opt->e2, w, ksw_flag, opt->zdrop);
+		fprintf(stderr, "===> q=(%d,%d), e=(%d,%d), bw=%d, ksw_flag=%d, zdrop=%d, end_bonus=%d <===\n", opt->q, opt->q2, opt->e, opt->e2, w, ksw_flag, opt->zdrop, end_bonus);
 		for (i = 0; i < tlen; ++i) fputc("ACGTN"[tseq[i]], stderr);
 		fputc('\n', stderr);
 		for (i = 0; i < qlen; ++i) fputc("ACGTN"[qseq[i]], stderr);
@@ -344,7 +344,7 @@ static void mm_align_pair(void *km, const mm_mapopt_t *opt, int qlen, const uint
 	} else if (opt->flag & MM_F_SPLICE) { // spliced alignment
 		assert((ksw_flag & KSW_EZ_SPLICE_FOR) == 0 || (ksw_flag & KSW_EZ_SPLICE_REV) == 0);
 		if (!(opt->flag & MM_F_SPLICE_OLD)) ksw_flag |= KSW_EZ_SPLICE_CMPLX;
-		ksw_exts2_sse(km, qlen, qseq, tlen, tseq, 5, mat, opt->q, opt->e, opt->q2, opt->noncan, zdrop, opt->junc_bonus, opt->junc_pen, ksw_flag, junc, ez);
+		ksw_exts2_sse(km, qlen, qseq, tlen, tseq, 5, mat, opt->q, opt->e, opt->q2, opt->noncan, zdrop, end_bonus, opt->junc_bonus, opt->junc_pen, ksw_flag, junc, ez);
 	} else if (opt->q == opt->q2 && opt->e == opt->e2) { // affine gap
 		ksw_extz2_sse(km, qlen, qseq, tlen, tseq, 5, mat, opt->q, opt->e, w, zdrop, end_bonus, ksw_flag, ez);
 	} else { // dual affine gap
diff --git a/ksw2.h b/ksw2.h
index b66e2f5..4c70fcf 100644
--- a/ksw2.h
+++ b/ksw2.h
@@ -72,7 +72,7 @@ void ksw_extd2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
 				   int8_t gapo, int8_t gape, int8_t gapo2, int8_t gape2, int w, int zdrop, int end_bonus, int flag, ksw_extz_t *ez);
 
 void ksw_exts2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t m, const int8_t *mat,
-				   int8_t gapo, int8_t gape, int8_t gapo2, int8_t noncan, int zdrop, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez);
+				   int8_t gapo, int8_t gape, int8_t gapo2, int8_t noncan, int zdrop, int end_bonus, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez);
 
 void ksw_extf2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t mch, int8_t mis, int8_t e, int w, int xdrop, ksw_extz_t *ez);
 
diff --git a/ksw2_dispatch.c b/ksw2_dispatch.c
index 6083214..5f5c905 100644
--- a/ksw2_dispatch.c
+++ b/ksw2_dispatch.c
@@ -80,17 +80,17 @@ void ksw_extd2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
 }
 
 void ksw_exts2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t m, const int8_t *mat,
-				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez)
+				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int end_bonus, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez)
 {
 	extern void ksw_exts2_sse2(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t m, const int8_t *mat,
-				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez);
+				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int end_bonus, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez);
 	extern void ksw_exts2_sse41(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t m, const int8_t *mat,
-				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez);
+				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int end_bonus, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez);
 	if (ksw_simd < 0) ksw_simd = x86_simd();
 	if (ksw_simd & SIMD_SSE4_1)
-		ksw_exts2_sse41(km, qlen, query, tlen, target, m, mat, q, e, q2, noncan, zdrop, junc_bonus, junc_pen, flag, junc, ez);
+		ksw_exts2_sse41(km, qlen, query, tlen, target, m, mat, q, e, q2, noncan, zdrop, end_bonus, junc_bonus, junc_pen, flag, junc, ez);
 	else if (ksw_simd & SIMD_SSE2)
-		ksw_exts2_sse2(km, qlen, query, tlen, target, m, mat, q, e, q2, noncan, zdrop, junc_bonus, junc_pen, flag, junc, ez);
+		ksw_exts2_sse2(km, qlen, query, tlen, target, m, mat, q, e, q2, noncan, zdrop, end_bonus, junc_bonus, junc_pen, flag, junc, ez);
 	else abort();
 }
 #endif
diff --git a/ksw2_exts2_sse.c b/ksw2_exts2_sse.c
index 7892317..c738257 100644
--- a/ksw2_exts2_sse.c
+++ b/ksw2_exts2_sse.c
@@ -24,14 +24,14 @@
 #ifdef KSW_CPU_DISPATCH
 #ifdef __SSE4_1__
 void ksw_exts2_sse41(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t m, const int8_t *mat,
-				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez)
+				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int end_bonus, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez)
 #else
 void ksw_exts2_sse2(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t m, const int8_t *mat,
-				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez)
+				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int end_bonus, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez)
 #endif
 #else
 void ksw_exts2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t m, const int8_t *mat,
-				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez)
+				   int8_t q, int8_t e, int8_t q2, int8_t noncan, int zdrop, int end_bonus, int8_t junc_bonus, int8_t junc_pen, int flag, const uint8_t *junc, ksw_extz_t *ez)
 #endif // ~KSW_CPU_DISPATCH
 {
 #define __dp_code_block1 \
@@ -452,10 +452,14 @@ void ksw_exts2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
 	if (!approx_max) kfree(km, H);
 	if (with_cigar) { // backtrack
 		int rev_cigar = !!(flag & KSW_EZ_REV_CIGAR);
-		if (!ez->zdropped && !(flag&KSW_EZ_EXTZ_ONLY))
+		if (!ez->zdropped && !(flag&KSW_EZ_EXTZ_ONLY)) {
 			ksw_backtrack(km, 1, rev_cigar, long_thres, (uint8_t*)p, off, off_end, n_col_*16, tlen-1, qlen-1, &ez->m_cigar, &ez->n_cigar, &ez->cigar);
-		else if (ez->max_t >= 0 && ez->max_q >= 0)
+		} else if (!ez->zdropped && (flag&KSW_EZ_EXTZ_ONLY) && ez->mqe + end_bonus > (int)ez->max) {
+			ez->reach_end = 1;
+			ksw_backtrack(km, 1, rev_cigar, long_thres, (uint8_t*)p, off, off_end, n_col_*16, ez->mqe_t, qlen-1, &ez->m_cigar, &ez->n_cigar, &ez->cigar);
+		} else if (ez->max_t >= 0 && ez->max_q >= 0) {
 			ksw_backtrack(km, 1, rev_cigar, long_thres, (uint8_t*)p, off, off_end, n_col_*16, ez->max_t, ez->max_q, &ez->m_cigar, &ez->n_cigar, &ez->cigar);
+		}
 		kfree(km, mem2); kfree(km, off);
 	}
 }
diff --git a/minimap.h b/minimap.h
index e6ae9ce..00a844c 100644
--- a/minimap.h
+++ b/minimap.h
@@ -5,7 +5,7 @@
 #include <stdio.h>
 #include <sys/types.h>
 
-#define MM_VERSION "2.28-r1245-dirty"
+#define MM_VERSION "2.28-r1248-dirty"
 
 #define MM_F_NO_DIAG       (0x001LL) // no exact diagonal hit
 #define MM_F_NO_DUAL       (0x002LL) // skip pairs where query name is lexicographically larger than target name
diff --git a/minimap2.1 b/minimap2.1
index 59bff44..a0f8ab9 100644
--- a/minimap2.1
+++ b/minimap2.1
@@ -1,4 +1,4 @@
-.TH minimap2 1 "30 March 2025" "minimap2-2.28-dirty (r1237)" "Bioinformatics tools"
+.TH minimap2 1 "2 April 2025" "minimap2-2.28-dirty (r1248)" "Bioinformatics tools"
 .SH NAME
 .PP
 minimap2 - mapping and alignment between collections of DNA sequences
@@ -689,7 +689,7 @@ Spliced alignment for accurate long RNA-seq reads such as PacBio iso-seq
 .B splice:sr
 Spliced alignment for short RNA-seq reads
 .RB ( -xsplice:hq
-.B --frag=yes --end-bonus=10 -2K50m --heap-sort=yes --pe-ind-chain
+.B --frag=yes -m25 -s40 -2K50m --heap-sort=yes --pe-ind-chain
 .BR --secondary=no ).
 .TP
 .B sr